diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index a4602287a..63aefe013 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.18*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.18** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.24*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.01.24** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.09.18 +[debug] youtube-dl version 2019.01.24 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.travis.yml b/.travis.yml index 92f326860..79287ccf6 100644 --- a/.travis.yml +++ b/.travis.yml @@ -15,6 +15,18 @@ env: - YTDL_TEST_SET=download matrix: include: + - python: 3.7 + dist: xenial + env: YTDL_TEST_SET=core + - python: 3.7 + dist: xenial + env: YTDL_TEST_SET=download + - python: 3.8-dev + dist: xenial + env: YTDL_TEST_SET=core + - python: 3.8-dev + dist: xenial + env: YTDL_TEST_SET=download - env: JYTHON=true; YTDL_TEST_SET=core - env: JYTHON=true; YTDL_TEST_SET=download fast_finish: true diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 333acee80..a71b045d0 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -152,16 +152,20 @@ After you have ensured this site is distributing its content legally, you can fo ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. -8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. -9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart): + + $ flake8 youtube_dl/extractor/yourextractor.py + +9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! @@ -173,7 +177,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou ### Mandatory and optional metafields -For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: - `id` (media identifier) - `title` (media title) @@ -181,7 +185,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken. -[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. +[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. #### Example @@ -257,11 +261,33 @@ title = meta.get('title') or self._og_search_title(webpage) This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. -### Make regular expressions flexible +### Regular expressions -When using regular expressions try to write them fuzzy and flexible. +#### Don't capture groups you don't use + +Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing. + +##### Example + +Don't capture id attribute name here since you can't use it for anything anyway. + +Correct: + +```python +r'(?:id|ID)=(?P\d+)' +``` + +Incorrect: +```python +r'(id|ID)=(?P\d+)' +``` + + +#### Make regular expressions relaxed and flexible + +When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on. -#### Example +##### Example Say you need to extract `title` from the following HTML code: @@ -294,7 +320,47 @@ title = self._search_regex( webpage, 'title', group='title') ``` +### Long lines policy + +There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse. + +For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit: + +Correct: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + +Incorrect: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=' +'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + ### Use safe conversion functions -Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. +Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + +Use `url_or_none` for safe URL processing. + +Use `try_get` for safe metadata extraction from parsed JSON. + +Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. + +#### More examples + +##### Safely extract optional description from parsed JSON +```python +description = try_get(response, lambda x: x['result']['video'][0]['summary'], compat_str) +``` + +##### Safely extract more optional metadata +```python +video = try_get(response, lambda x: x['result']['video'][0], dict) or {} +description = video.get('summary') +duration = float_or_none(video.get('durationMs'), scale=1000) +view_count = int_or_none(video.get('views')) +``` diff --git a/ChangeLog b/ChangeLog index 800ece790..1fda747bb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,304 @@ +version 2019.01.24 + +Core +* [YoutubeDL] Fix negation for string operators in format selection (#18961) + + +version 2019.01.23 + +Core +* [utils] Fix urljoin for paths with non-http(s) schemes +* [extractor/common] Improve jwplayer relative URL handling (#18892) ++ [YoutubeDL] Add negation support for string comparisons in format selection + expressions (#18600, #18805) +* [extractor/common] Improve HLS video-only format detection (#18923) + +Extractors +* [crunchyroll] Extend URL regular expression (#18955) +* [pornhub] Bypass scrape detection (#4822, #5930, #7074, #10175, #12722, + #17197, #18338 #18842, #18899) ++ [vrv] Add support for authentication (#14307) +* [videomore:season] Fix extraction +* [videomore] Improve extraction (#18908) ++ [tnaflix] Pass Referer in metadata request (#18925) +* [radiocanada] Relax DRM check (#18608, #18609) +* [vimeo] Fix video password verification for videos protected by + Referer HTTP header ++ [hketv] Add support for hkedcity.net (#18696) ++ [streamango] Add support for fruithosts.net (#18710) ++ [instagram] Add support for tags (#18757) ++ [odnoklassniki] Detect paid videos (#18876) +* [ted] Correct acodec for HTTP formats (#18923) +* [cartoonnetwork] Fix extraction (#15664, #17224) +* [vimeo] Fix extraction for password protected player URLs (#18889) + + +version 2019.01.17 + +Extractors +* [youtube] Extend JS player signature function name regular expressions + (#18890, #18891, #18893) + + +version 2019.01.16 + +Core ++ [test/helper] Add support for maxcount and count collection len checkers +* [downloader/hls] Fix uplynk ad skipping (#18824) +* [postprocessor/ffmpeg] Improve ffmpeg version parsing (#18813) + +Extractors +* [youtube] Skip unsupported adaptive stream type (#18804) ++ [youtube] Extract DASH formats from player response (#18804) +* [funimation] Fix extraction (#14089) +* [skylinewebcams] Fix extraction (#18853) ++ [curiositystream] Add support for non app URLs ++ [bitchute] Check formats (#18833) +* [wistia] Extend URL regular expression (#18823) ++ [playplustv] Add support for playplus.com (#18789) + + +version 2019.01.10 + +Core +* [extractor/common] Use episode name as title in _json_ld ++ [extractor/common] Add support for movies in _json_ld +* [postprocessor/ffmpeg] Embed subtitles with non-standard language codes + (#18765) ++ [utils] Add language codes replaced in 1989 revision of ISO 639 + to ISO639Utils (#18765) + +Extractors +* [youtube] Extract live HLS URL from player response (#18799) ++ [outsidetv] Add support for outsidetv.com (#18774) +* [jwplatform] Use JW Platform Delivery API V2 and add support for more URLs ++ [fox] Add support National Geographic (#17985, #15333, #14698) ++ [playplustv] Add support for playplus.tv (#18789) +* [globo] Set GLBID cookie manually (#17346) ++ [gaia] Add support for gaia.com (#14605) +* [youporn] Fix title and description extraction (#18748) ++ [hungama] Add support for hungama.com (#17402, #18771) +* [dtube] Fix extraction (#18741) +* [tvnow] Fix and rework extractors and prepare for a switch to the new API + (#17245, #18499) +* [carambatv:page] Fix extraction (#18739) + + +version 2019.01.02 + +Extractors +* [discovery] Use geo verification headers (#17838) ++ [packtpub] Add support for subscription.packtpub.com (#18718) +* [yourporn] Fix extraction (#18583) ++ [acast:channel] Add support for play.acast.com (#18587) ++ [extractors] Add missing age limits (#18621) ++ [rmcdecouverte] Add support for live stream +* [rmcdecouverte] Bypass geo restriction +* [rmcdecouverte] Update URL regular expression (#18595, 18697) +* [manyvids] Fix extraction (#18604, #18614) +* [bitchute] Fix extraction (#18567) + + +version 2018.12.31 + +Extractors ++ [bbc] Add support for another embed pattern (#18643) ++ [npo:live] Add support for npostart.nl (#18644) +* [beeg] Fix extraction (#18610, #18626) +* [youtube] Unescape HTML for series (#18641) ++ [youtube] Extract more format metadata +* [youtube] Detect DRM protected videos (#1774) +* [youtube] Relax HTML5 player regular expressions (#18465, #18466) +* [youtube] Extend HTML5 player regular expression (#17516) ++ [liveleak] Add support for another embed type and restore original + format extraction ++ [crackle] Extract ISM and HTTP formats ++ [twitter] Pass Referer with card request (#18579) +* [mediasite] Extend URL regular expression (#18558) ++ [lecturio] Add support for lecturio.de (#18562) ++ [discovery] Add support for Scripps Networks watch domains (#17947) + + +version 2018.12.17 + +Extractors +* [ard:beta] Improve geo restricted videos extraction +* [ard:beta] Fix subtitles extraction +* [ard:beta] Improve extraction robustness +* [ard:beta] Relax URL regular expression (#18441) +* [acast] Add support for embed.acast.com and play.acast.com (#18483) +* [iprima] Relax URL regular expression (#18515, #18540) +* [vrv] Fix initial state extraction (#18553) +* [youtube] Fix mark watched (#18546) ++ [safari] Add support for learning.oreilly.com (#18510) +* [youtube] Fix multifeed extraction (#18531) +* [lecturio] Improve subtitles extraction (#18488) +* [uol] Fix format URL extraction (#18480) ++ [ard:mediathek] Add support for classic.ardmediathek.de (#18473) + + +version 2018.12.09 + +Core +* [YoutubeDL] Keep session cookies in cookie file between runs +* [YoutubeDL] Recognize session cookies with expired set to 0 (#12929) + +Extractors ++ [teachable] Add support for teachable platform sites (#5451, #18150, #18272) ++ [aenetworks] Add support for historyvault.com (#18460) +* [imgur] Improve gallery and album detection and extraction (#9133, #16577, + #17223, #18404) +* [iprima] Relax URL regular expression (#18453) +* [hotstar] Fix video data extraction (#18386) +* [ard:mediathek] Fix title and description extraction (#18349, #18371) +* [xvideos] Switch to HTTPS (#18422, #18427) ++ [lecturio] Add support for lecturio.com (#18405) ++ [nrktv:series] Add support for extra materials +* [nrktv:season,series] Fix extraction (#17159, #17258) +* [nrktv] Relax URL regular expression (#18304, #18387) +* [yourporn] Fix extraction (#18424, #18425) +* [tbs] Fix info extraction (#18403) ++ [gamespot] Add support for review URLs + + +version 2018.12.03 + +Core +* [utils] Fix random_birthday to generate existing dates only (#18284) + +Extractors ++ [tiktok] Add support for tiktok.com (#18108, #18135) +* [pornhub] Use actual URL host for requests (#18359) +* [lynda] Fix authentication (#18158, #18217) +* [gfycat] Update API endpoint (#18333, #18343) ++ [hotstar] Add support for alternative app state layout (#18320) +* [azmedien] Fix extraction (#18334, #18336) ++ [vimeo] Add support for VHX (Vimeo OTT) (#14835) +* [joj] Fix extraction (#18280, #18281) ++ [wistia] Add support for fast.wistia.com (#18287) + + +version 2018.11.23 + +Core ++ [setup.py] Add more relevant classifiers + +Extractors +* [mixcloud] Fallback to hardcoded decryption key (#18016) +* [nbc:news] Fix article extraction (#16194) +* [foxsports] Fix extraction (#17543) +* [loc] Relax regular expression and improve formats extraction ++ [ciscolive] Add support for ciscolive.cisco.com (#17984) +* [nzz] Relax kaltura regex (#18228) +* [sixplay] Fix formats extraction +* [bitchute] Improve title extraction +* [kaltura] Limit requested MediaEntry fields ++ [americastestkitchen] Add support for zype embeds (#18225) ++ [pornhub] Add pornhub.net alias +* [nova:embed] Fix extraction (#18222) + + +version 2018.11.18 + +Extractors ++ [wwe] Extract subtitles ++ [wwe] Add support for playlistst (#14781) ++ [wwe] Add support for wwe.com (#14781, #17450) +* [vk] Detect geo restriction (#17767) +* [openload] Use original host during extraction (#18211) +* [atvat] Fix extraction (#18041) ++ [rte] Add support for new API endpoint (#18206) +* [tnaflixnetwork:embed] Fix extraction (#18205) +* [picarto] Use API and add token support (#16518) ++ [zype] Add support for player.zype.com (#18143) +* [vivo] Fix extraction (#18139) +* [ruutu] Update API endpoint (#18138) + + +version 2018.11.07 + +Extractors ++ [youtube] Add another JS signature function name regex (#18091, #18093, + #18094) +* [facebook] Fix tahoe request (#17171) +* [cliphunter] Fix extraction (#18083) ++ [youtube:playlist] Add support for invidio.us (#18077) +* [zattoo] Arrange API hosts for derived extractors (#18035) ++ [youtube] Add fallback metadata extraction from videoDetails (#18052) + + +version 2018.11.03 + +Core +* [extractor/common] Ensure response handle is not prematurely closed before + it can be read if it matches expected_status (#17195, #17846, #17447) + +Extractors +* [laola1tv:embed] Set correct stream access URL scheme (#16341) ++ [ehftv] Add support for ehftv.com (#15408) +* [azmedien] Adopt to major site redesign (#17745, #17746) ++ [twitcasting] Add support for twitcasting.tv (#17981) +* [orf:tvthek] Fix extraction (#17737, #17956, #18024) ++ [openload] Add support for oload.fun (#18045) +* [njpwworld] Fix authentication (#17427) ++ [linkedin:learning] Add support for linkedin.com/learning (#13545) +* [theplatform] Improve error detection (#13222) +* [cnbc] Simplify extraction (#14280, #17110) ++ [cbnc] Add support for new URL schema (#14193) +* [aparat] Improve extraction and extract more metadata (#17445, #18008) +* [aparat] Fix extraction + + +version 2018.10.29 + +Core ++ [extractor/common] Add validation for JSON-LD URLs + +Extractors ++ [sportbox] Add support for matchtv.ru +* [sportbox] Fix extraction (#17978) +* [screencast] Fix extraction (#14590, #14617, #17990) ++ [openload] Add support for oload.icu ++ [ivi] Add support for ivi.tv +* [crunchyroll] Improve extraction failsafeness (#17991) +* [dailymail] Fix formats extraction (#17976) +* [viewster] Reduce format requests +* [cwtv] Handle API errors (#17905) ++ [rutube] Use geo verification headers (#17897) ++ [brightcove:legacy] Add fallbacks to brightcove:new (#13912) +- [tv3] Remove extractor (#10461, #15339) +* [ted] Fix extraction for HTTP and RTMP formats (#5941, #17572, #17894) ++ [openload] Add support for oload.cc (#17823) ++ [patreon] Extract post_file URL (#17792) +* [patreon] Fix extraction (#14502, #10471) + + +version 2018.10.05 + +Extractors +* [pluralsight] Improve authentication (#17762) +* [dailymotion] Fix extraction (#17699) +* [crunchyroll] Switch to HTTPS for RpcApi (#17749) ++ [philharmoniedeparis] Add support for pad.philharmoniedeparis.fr (#17705) +* [philharmoniedeparis] Fix extraction (#17705) ++ [jamendo] Add support for licensing.jamendo.com (#17724) ++ [openload] Add support for oload.cloud (#17710) +* [pluralsight] Fix subtitles extraction (#17726, #17728) ++ [vimeo] Add another config regular expression (#17690) +* [spike] Fix Paramount Network extraction (#17677) +* [hotstar] Fix extraction (#14694, #14931, #17637) + + +version 2018.09.26 + +Extractors +* [pluralsight] Fix subtitles extraction (#17671) +* [mediaset] Improve embed support (#17668) ++ [youtube] Add support for invidio.us (#17613) ++ [zattoo] Add support for more zattoo platform sites +* [zattoo] Fix extraction (#17175, #17542) + + version 2018.09.18 Core diff --git a/README.md b/README.md index dd068a462..4ba982907 100644 --- a/README.md +++ b/README.md @@ -496,7 +496,7 @@ The `-o` option allows users to indicate a template for the output file names. **tl;dr:** [navigate me to examples](#output-template-examples). -The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a formatting operations. Allowed names along with sequence type are: +The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Allowed names along with sequence type are: - `id` (string): Video identifier - `title` (string): Video title @@ -511,6 +511,8 @@ The basic usage is not to set any template arguments when downloading a single f - `timestamp` (numeric): UNIX timestamp of the moment the video became available - `upload_date` (string): Video upload date (YYYYMMDD) - `uploader_id` (string): Nickname or id of the video uploader + - `channel` (string): Full name of the channel the video is uploaded on + - `channel_id` (string): Id of the channel - `location` (string): Physical location where the video was filmed - `duration` (numeric): Length of the video in seconds - `view_count` (numeric): How many users have watched the video on the platform @@ -665,7 +667,7 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, ` - `asr`: Audio sampling rate in Hertz - `fps`: Frame rate -Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begins with), `$=` (ends with), `*=` (contains) and following string meta fields: +Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields: - `ext`: File extension - `acodec`: Name of the audio codec in use - `vcodec`: Name of the video codec in use @@ -673,6 +675,8 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`) - `format_id`: A short description of the format +Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). + Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster. Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. @@ -1022,16 +1026,20 @@ After you have ensured this site is distributing its content legally, you can fo ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. -8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. -9. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart): + + $ flake8 youtube_dl/extractor/yourextractor.py + +9. Make sure your code works under all [Python](https://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +10. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files and [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! @@ -1043,7 +1051,7 @@ Extractors are very fragile by nature since they depend on the layout of the sou ### Mandatory and optional metafields -For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by an [information dictionary](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303) or simply *info dict*. Only the following meta fields in the *info dict* are considered mandatory for a successful extraction process by youtube-dl: - `id` (media identifier) - `title` (media title) @@ -1051,7 +1059,7 @@ For extraction to work youtube-dl relies on metadata your extractor extracts and In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` as mandatory. Thus the aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken. -[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. +[Any field](https://github.com/rg3/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L188-L303) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. #### Example @@ -1127,11 +1135,33 @@ title = meta.get('title') or self._og_search_title(webpage) This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. -### Make regular expressions flexible +### Regular expressions -When using regular expressions try to write them fuzzy and flexible. +#### Don't capture groups you don't use + +Capturing group must be an indication that it's used somewhere in the code. Any group that is not used must be non capturing. + +##### Example + +Don't capture id attribute name here since you can't use it for anything anyway. + +Correct: + +```python +r'(?:id|ID)=(?P\d+)' +``` + +Incorrect: +```python +r'(id|ID)=(?P\d+)' +``` + + +#### Make regular expressions relaxed and flexible + +When using regular expressions try to write them fuzzy, relaxed and flexible, skipping insignificant parts that are more likely to change, allowing both single and double quotes for quoted values and so on. -#### Example +##### Example Say you need to extract `title` from the following HTML code: @@ -1164,9 +1194,49 @@ title = self._search_regex( webpage, 'title', group='title') ``` +### Long lines policy + +There is a soft limit to keep lines of code under 80 characters long. This means it should be respected if possible and if it does not make readability and code maintenance worse. + +For example, you should **never** split long string literals like URLs or some other often copied entities over multiple lines to fit this limit: + +Correct: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + +Incorrect: + +```python +'https://www.youtube.com/watch?v=FqZTN594JQw&list=' +'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' +``` + ### Use safe conversion functions -Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. +Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + +Use `url_or_none` for safe URL processing. + +Use `try_get` for safe metadata extraction from parsed JSON. + +Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. + +#### More examples + +##### Safely extract optional description from parsed JSON +```python +description = try_get(response, lambda x: x['result']['video'][0]['summary'], compat_str) +``` + +##### Safely extract more optional metadata +```python +video = try_get(response, lambda x: x['result']['video'][0], dict) or {} +description = video.get('summary') +duration = float_or_none(video.get('durationMs'), scale=1000) +view_count = int_or_none(video.get('views')) +``` # EMBEDDING YOUTUBE-DL diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 9b8601751..d759d0273 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -33,7 +33,7 @@ - **AdobeTVShow** - **AdobeTVVideo** - **AdultSwim** - - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network + - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault - **afreecatv**: afreecatv.com - **AirMozilla** - **AliExpressLive** @@ -84,8 +84,6 @@ - **awaan:season** - **awaan:video** - **AZMedien**: AZ Medien videos - - **AZMedienPlaylist**: AZ Medien playlists - - **AZMedienShowPlaylist**: AZ Medien show playlists - **BaiduVideo**: 百度视频 - **bambuser** - **bambuser:channel** @@ -98,6 +96,7 @@ - **bbc.co.uk:article**: BBC articles - **bbc.co.uk:iplayer:playlist** - **bbc.co.uk:playlist** + - **BBVTV** - **Beatport** - **Beeg** - **BehindKink** @@ -164,6 +163,8 @@ - **chirbit** - **chirbit:profile** - **Cinchcast** + - **CiscoLiveSearch** + - **CiscoLiveSession** - **CJSW** - **cliphunter** - **Clippit** @@ -177,6 +178,7 @@ - **Clyp** - **cmt.com** - **CNBC** + - **CNBCVideo** - **CNN** - **CNNArticle** - **CNNBlogs** @@ -250,7 +252,9 @@ - **EchoMsk** - **egghead:course**: egghead.io course - **egghead:lesson**: egghead.io lesson + - **ehftv** - **eHow** + - **EinsUndEinsTV** - **Einthusan** - **eitb.tv** - **EllenTube** @@ -268,6 +272,7 @@ - **EsriVideo** - **Europa** - **EveryonesMixtape** + - **EWETV** - **ExpoTV** - **Expressen** - **ExtremeTube** @@ -315,6 +320,7 @@ - **Fusion** - **Fux** - **FXNetworks** + - **Gaia** - **GameInformer** - **GameOne** - **gameone:playlist** @@ -327,6 +333,7 @@ - **Gfycat** - **GiantBomb** - **Giga** + - **GlattvisionTV** - **Glide**: Glide mobile video messages (glide.me) - **Globo** - **GloboArticle** @@ -354,9 +361,10 @@ - **hitbox** - **hitbox:live** - **HitRecord** + - **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau - **HornBunny** - **HotNewHipHop** - - **HotStar** + - **hotstar** - **hotstar:playlist** - **Howcast** - **HowStuffWorks** @@ -364,18 +372,22 @@ - **HRTiPlaylist** - **Huajiao**: 花椒直播 - **HuffPost**: Huffington Post + - **Hungama** + - **HungamaSong** - **Hypem** - **Iconosquare** - **ign.com** - **imdb**: Internet Movie Database trailers - **imdb:list**: Internet Movie Database lists - **Imgur** - - **ImgurAlbum** + - **imgur:album** + - **imgur:gallery** - **Ina** - **Inc** - **IndavideoEmbed** - **InfoQ** - **Instagram** + - **instagram:tag**: Instagram hashtag search - **instagram:user**: Instagram user profile - **Internazionale** - **InternetVideoArchive** @@ -429,6 +441,9 @@ - **Le**: 乐视网 - **Learnr** - **Lecture2Go** + - **Lecturio** + - **LecturioCourse** + - **LecturioDeCourse** - **LEGO** - **Lemonde** - **Lenta** @@ -441,6 +456,8 @@ - **limelight:channel** - **limelight:channel_list** - **LineTV** + - **linkedin:learning** + - **linkedin:learning:course** - **LiTV** - **LiveLeak** - **LiveLeakEmbed** @@ -494,6 +511,7 @@ - **Mixer:vod** - **MLB** - **Mnet** + - **MNetTV** - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net - **Mofosex** - **Mojvideo** @@ -525,9 +543,8 @@ - **Myvi** - **MyVidster** - **MyviEmbed** + - **MyVisionTV** - **n-tv.de** - - **natgeo** - - **natgeo:episodeguide** - **natgeo:video** - **Naver** - **NBA** @@ -550,6 +567,7 @@ - **netease:program**: 网易云音乐 - 电台节目 - **netease:singer**: 网易云音乐 - 歌手 - **netease:song**: 网易云音乐 + - **NetPlus** - **Netzkino** - **Newgrounds** - **NewgroundsPlaylist** @@ -626,6 +644,8 @@ - **orf:iptv**: iptv.ORF.at - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek + - **OsnatelTV** + - **OutsideTV** - **PacktPub** - **PacktPubCourse** - **PandaTV**: 熊猫TV @@ -650,6 +670,7 @@ - **Pinkbike** - **Pladform** - **play.fm** + - **PlayPlusTV** - **PlaysTV** - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz - **Playvid** @@ -686,6 +707,7 @@ - **qqmusic:playlist**: QQ音乐 - 歌单 - **qqmusic:singer**: QQ音乐 - 歌手 - **qqmusic:toplist**: QQ音乐 - 排行榜 + - **QuantumTV** - **Quickline** - **QuicklineLive** - **R7** @@ -753,6 +775,7 @@ - **safari**: safaribooksonline.com online video - **safari:api** - **safari:course**: safaribooksonline.com online courses + - **SAKTV** - **Sapo**: SAPO Vídeos - **savefrom.net** - **SBS**: sbs.com.au @@ -808,7 +831,7 @@ - **Spiegeltv** - **sport.francetvinfo.fr** - **Sport5** - - **SportBoxEmbed** + - **SportBox** - **SportDeutschland** - **SpringboardPlatform** - **Sprout** @@ -839,6 +862,8 @@ - **TastyTrade** - **TBS** - **TDSLifeway** + - **Teachable** + - **TeachableCourse** - **teachertube**: teachertube.com videos - **teachertube:user:collection**: teachertube.com user and collection videos - **TeachingChannel** @@ -871,6 +896,8 @@ - **ThisAmericanLife** - **ThisAV** - **ThisOldHouse** + - **TikTok** + - **TikTokUser** - **tinypic**: tinypic.com videos - **TMZ** - **TMZArticle** @@ -899,7 +926,6 @@ - **TV2** - **tv2.hu** - **TV2Article** - - **TV3** - **TV4**: tv4.se and tv4play.se - **TV5MondePlus**: TV5MONDE+ - **TVA** @@ -913,7 +939,9 @@ - **TVNet** - **TVNoe** - **TVNow** - - **TVNowList** + - **TVNowAnnual** + - **TVNowNew** + - **TVNowSeason** - **TVNowShow** - **tvp**: Telewizja Polska - **tvp:embed**: Telewizja Polska @@ -921,6 +949,7 @@ - **TVPlayer** - **TVPlayHome** - **Tweakers** + - **TwitCasting** - **twitch:chapter** - **twitch:clips** - **twitch:profile** @@ -945,8 +974,6 @@ - **uol.com.br** - **uplynk** - **uplynk:preplay** - - **Upskill** - - **UpskillCourse** - **Urort**: NRK P3 Urørt - **URPlay** - **USANetwork** @@ -965,6 +992,7 @@ - **VevoPlaylist** - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet - **vh1.com** + - **vhx:embed** - **Viafree** - **vice** - **vice:article** @@ -1035,12 +1063,14 @@ - **vrv** - **vrv:series** - **VShare** + - **VTXTV** - **vube**: Vube.com - **VuClip** - **VVVVID** - **VyboryMos** - **Vzaar** - **Walla** + - **WalyTV** - **washingtonpost** - **washingtonpost:article** - **wat.tv** @@ -1066,6 +1096,7 @@ - **wrzuta.pl:playlist** - **WSJ**: Wall Street Journal - **WSJArticle** + - **WWE** - **XBef** - **XboxClips** - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me @@ -1125,3 +1156,4 @@ - **ZDF** - **ZDFChannel** - **zingmp3**: mp3.zing.vn + - **Zype** diff --git a/setup.py b/setup.py index 7dbb5805f..dfb669ad2 100644 --- a/setup.py +++ b/setup.py @@ -124,6 +124,8 @@ setup( 'Development Status :: 5 - Production/Stable', 'Environment :: Console', 'License :: Public Domain', + 'Programming Language :: Python', + 'Programming Language :: Python :: 2', 'Programming Language :: Python :: 2.6', 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3', @@ -132,6 +134,13 @@ setup( 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', + 'Programming Language :: Python :: 3.7', + 'Programming Language :: Python :: 3.8', + 'Programming Language :: Python :: Implementation', + 'Programming Language :: Python :: Implementation :: CPython', + 'Programming Language :: Python :: Implementation :: IronPython', + 'Programming Language :: Python :: Implementation :: Jython', + 'Programming Language :: Python :: Implementation :: PyPy', ], cmdclass={'build_lazy_extractors': build_lazy_extractors}, diff --git a/test/helper.py b/test/helper.py index dfee217a9..e62aab11e 100644 --- a/test/helper.py +++ b/test/helper.py @@ -7,6 +7,7 @@ import json import os.path import re import types +import ssl import sys import youtube_dl.extractor @@ -152,15 +153,27 @@ def expect_value(self, got, expected, field): isinstance(got, compat_str), 'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got))) got = 'md5:' + md5(got) - elif isinstance(expected, compat_str) and expected.startswith('mincount:'): + elif isinstance(expected, compat_str) and re.match(r'^(?:min|max)?count:\d+', expected): self.assertTrue( isinstance(got, (list, dict)), 'Expected field %s to be a list or a dict, but it is of type %s' % ( field, type(got).__name__)) - expected_num = int(expected.partition(':')[2]) - assertGreaterEqual( + op, _, expected_num = expected.partition(':') + expected_num = int(expected_num) + if op == 'mincount': + assert_func = assertGreaterEqual + msg_tmpl = 'Expected %d items in field %s, but only got %d' + elif op == 'maxcount': + assert_func = assertLessEqual + msg_tmpl = 'Expected maximum %d items in field %s, but got %d' + elif op == 'count': + assert_func = assertEqual + msg_tmpl = 'Expected exactly %d items in field %s, but got %d' + else: + assert False + assert_func( self, len(got), expected_num, - 'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got))) + msg_tmpl % (expected_num, field, len(got))) return self.assertEqual( expected, got, @@ -236,6 +249,20 @@ def assertGreaterEqual(self, got, expected, msg=None): self.assertTrue(got >= expected, msg) +def assertLessEqual(self, got, expected, msg=None): + if not (got <= expected): + if msg is None: + msg = '%r not less than or equal to %r' % (got, expected) + self.assertTrue(got <= expected, msg) + + +def assertEqual(self, got, expected, msg=None): + if not (got == expected): + if msg is None: + msg = '%r not equal to %r' % (got, expected) + self.assertTrue(got == expected, msg) + + def expect_warnings(ydl, warnings_re): real_warning = ydl.report_warning @@ -244,3 +271,12 @@ def expect_warnings(ydl, warnings_re): real_warning(w) ydl.report_warning = _report_warning + + +def http_server_port(httpd): + if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): + # In Jython SSLSocket is not a subclass of socket.socket + sock = httpd.socket.sock + else: + sock = httpd.socket + return sock.getsockname()[1] diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 4833396a5..75fa0bbb7 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -9,11 +9,30 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import FakeYDL, expect_dict, expect_value -from youtube_dl.compat import compat_etree_fromstring +from test.helper import FakeYDL, expect_dict, expect_value, http_server_port +from youtube_dl.compat import compat_etree_fromstring, compat_http_server from youtube_dl.extractor.common import InfoExtractor from youtube_dl.extractor import YoutubeIE, get_info_extractor from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError +import threading + + +TEAPOT_RESPONSE_STATUS = 418 +TEAPOT_RESPONSE_BODY = "

418 I'm a teapot

" + + +class InfoExtractorTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): + def log_message(self, format, *args): + pass + + def do_GET(self): + if self.path == '/teapot': + self.send_response(TEAPOT_RESPONSE_STATUS) + self.send_header('Content-Type', 'text/html; charset=utf-8') + self.end_headers() + self.wfile.write(TEAPOT_RESPONSE_BODY.encode()) + else: + assert False class TestIE(InfoExtractor): @@ -478,7 +497,64 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ 'width': 1280, 'height': 720, }] - ) + ), + ( + # https://github.com/rg3/youtube-dl/issues/18923 + # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa + 'ted_18923', + 'http://hls.ted.com/talks/31241.m3u8', + [{ + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '600k-Audio', + 'vcodec': 'none', + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '68', + 'vcodec': 'none', + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '163', + 'acodec': 'none', + 'width': 320, + 'height': 180, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '481', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '769', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '984', + 'acodec': 'none', + 'width': 512, + 'height': 288, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '1255', + 'acodec': 'none', + 'width': 640, + 'height': 360, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '1693', + 'acodec': 'none', + 'width': 853, + 'height': 480, + }, { + 'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b', + 'format_id': '2462', + 'acodec': 'none', + 'width': 1280, + 'height': 720, + }] + ), ] for m3u8_file, m3u8_url, expected_formats in _TEST_CASES: @@ -743,6 +819,25 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ for i in range(len(entries)): expect_dict(self, entries[i], expected_entries[i]) + def test_response_with_expected_status_returns_content(self): + # Checks for mitigations against the effects of + # that affect Python 3.4.1+, which + # manifest as `_download_webpage`, `_download_xml`, `_download_json`, + # or the underlying `_download_webpage_handle` returning no content + # when a response matches `expected_status`. + + httpd = compat_http_server.HTTPServer( + ('127.0.0.1', 0), InfoExtractorTestRequestHandler) + port = http_server_port(httpd) + server_thread = threading.Thread(target=httpd.serve_forever) + server_thread.daemon = True + server_thread.start() + + (content, urlh) = self.ie._download_webpage_handle( + 'http://127.0.0.1:%d/teapot' % port, None, + expected_status=TEAPOT_RESPONSE_STATUS) + self.assertEqual(content, TEAPOT_RESPONSE_BODY) + if __name__ == '__main__': unittest.main() diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index f0f5a8470..1d7452744 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -239,6 +239,76 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot') + def test_format_selection_string_ops(self): + formats = [ + {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL}, + {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL}, + ] + info_dict = _make_result(formats) + + # equals (=) + ydl = YDL({'format': '[format_id=abc-cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not equal (!=) + ydl = YDL({'format': '[format_id!=abc-cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # starts with (^=) + ydl = YDL({'format': '[format_id^=abc]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not start with (!^=) + ydl = YDL({'format': '[format_id!^=abc]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # ends with ($=) + ydl = YDL({'format': '[format_id$=cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not end with (!$=) + ydl = YDL({'format': '[format_id!$=cba]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + # contains (*=) + ydl = YDL({'format': '[format_id*=bc-cb]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'abc-cba') + + # does not contain (!*=) + ydl = YDL({'format': '[format_id!*=bc-cb]'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'zxc-cxz') + + ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + + ydl = YDL({'format': '[format_id!*=-]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + def test_youtube_format_selection(self): order = [ '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13', diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py new file mode 100644 index 000000000..6a8243590 --- /dev/null +++ b/test/test_YoutubeDLCookieJar.py @@ -0,0 +1,34 @@ +#!/usr/bin/env python +# coding: utf-8 + +from __future__ import unicode_literals + +import os +import re +import sys +import tempfile +import unittest +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.utils import YoutubeDLCookieJar + + +class TestYoutubeDLCookieJar(unittest.TestCase): + def test_keep_session_cookies(self): + cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt') + cookiejar.load(ignore_discard=True, ignore_expires=True) + tf = tempfile.NamedTemporaryFile(delete=False) + try: + cookiejar.save(filename=tf.name, ignore_discard=True, ignore_expires=True) + temp = tf.read().decode('utf-8') + self.assertTrue(re.search( + r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpiresEmpty\s+YoutubeDLExpiresEmptyValue', temp)) + self.assertTrue(re.search( + r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpires0\s+YoutubeDLExpires0Value', temp)) + finally: + tf.close() + os.remove(tf.name) + + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_compat.py b/test/test_compat.py index d6c54e135..51fe6aa0b 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -39,7 +39,7 @@ class TestCompat(unittest.TestCase): def test_compat_expanduser(self): old_home = os.environ.get('HOME') - test_str = 'C:\Documents and Settings\тест\Application Data' + test_str = r'C:\Documents and Settings\тест\Application Data' compat_setenv('HOME', test_str) self.assertEqual(compat_expanduser('~'), test_str) compat_setenv('HOME', old_home or '') diff --git a/test/test_downloader_http.py b/test/test_downloader_http.py index 5cf2bf1a5..750472281 100644 --- a/test/test_downloader_http.py +++ b/test/test_downloader_http.py @@ -9,26 +9,16 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from test.helper import try_rm +from test.helper import http_server_port, try_rm from youtube_dl import YoutubeDL from youtube_dl.compat import compat_http_server from youtube_dl.downloader.http import HttpFD from youtube_dl.utils import encodeFilename -import ssl import threading TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -def http_server_port(httpd): - if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): - # In Jython SSLSocket is not a subclass of socket.socket - sock = httpd.socket.sock - else: - sock = httpd.socket - return sock.getsockname()[1] - - TEST_SIZE = 10 * 1024 diff --git a/test/test_http.py b/test/test_http.py index 409fec9c8..3ee0a5dda 100644 --- a/test/test_http.py +++ b/test/test_http.py @@ -8,6 +8,7 @@ import sys import unittest sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) +from test.helper import http_server_port from youtube_dl import YoutubeDL from youtube_dl.compat import compat_http_server, compat_urllib_request import ssl @@ -16,15 +17,6 @@ import threading TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -def http_server_port(httpd): - if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): - # In Jython SSLSocket is not a subclass of socket.socket - sock = httpd.socket.sock - else: - sock = httpd.socket - return sock.getsockname()[1] - - class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): def log_message(self, format, *args): pass diff --git a/test/test_postprocessors.py b/test/test_postprocessors.py index addb69d6f..4209d1d9a 100644 --- a/test/test_postprocessors.py +++ b/test/test_postprocessors.py @@ -14,4 +14,4 @@ from youtube_dl.postprocessor import MetadataFromTitlePP class TestMetadataFromTitle(unittest.TestCase): def test_format_to_regex(self): pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s') - self.assertEqual(pp._titleregex, '(?P.+)\ \-\ (?P<artist>.+)') + self.assertEqual(pp._titleregex, r'(?P<title>.+)\ \-\ (?P<artist>.+)') diff --git a/test/test_utils.py b/test/test_utils.py index 9e28e008f..409482c3b 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -507,6 +507,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(urljoin('http://foo.de/', ''), None) self.assertEqual(urljoin('http://foo.de/', ['foobar']), None) self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt') + self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de') + self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de') def test_url_or_none(self): self.assertEqual(url_or_none(None), None) diff --git a/test/testdata/cookies/session_cookies.txt b/test/testdata/cookies/session_cookies.txt new file mode 100644 index 000000000..f6996f031 --- /dev/null +++ b/test/testdata/cookies/session_cookies.txt @@ -0,0 +1,6 @@ +# Netscape HTTP Cookie File +# http://curl.haxx.se/rfc/cookie_spec.html +# This is a generated file! Do not edit. + +www.foobar.foobar FALSE / TRUE YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue +www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpires0 YoutubeDLExpires0Value diff --git a/test/testdata/m3u8/ted_18923.m3u8 b/test/testdata/m3u8/ted_18923.m3u8 new file mode 100644 index 000000000..52a27118b --- /dev/null +++ b/test/testdata/m3u8/ted_18923.m3u8 @@ -0,0 +1,28 @@ +#EXTM3U +#EXT-X-VERSION:4 +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1255659,PROGRAM-ID=1,CODECS="avc1.42c01e,mp4a.40.2",RESOLUTION=640x360 +/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=163154,PROGRAM-ID=1,CODECS="avc1.42c00c,mp4a.40.2",RESOLUTION=320x180 +/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=481701,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=769968,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=984037,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288 +/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1693925,PROGRAM-ID=1,CODECS="avc1.4d401f,mp4a.40.2",RESOLUTION=853x480 +/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=2462469,PROGRAM-ID=1,CODECS="avc1.640028,mp4a.40.2",RESOLUTION=1280x720 +/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b +#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=68101,PROGRAM-ID=1,CODECS="mp4a.40.2",DEFAULT=YES +/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b + +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=74298,PROGRAM-ID=1,CODECS="avc1.42c00c",RESOLUTION=320x180,URI="/videos/BorisHesser_2018S/video/64k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=216200,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/180k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=304717,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/320k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=350933,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/450k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=495850,PROGRAM-ID=1,CODECS="avc1.42c01e",RESOLUTION=640x360,URI="/videos/BorisHesser_2018S/video/600k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=810750,PROGRAM-ID=1,CODECS="avc1.4d401f",RESOLUTION=853x480,URI="/videos/BorisHesser_2018S/video/950k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" +#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=1273700,PROGRAM-ID=1,CODECS="avc1.640028",RESOLUTION=1280x720,URI="/videos/BorisHesser_2018S/video/1500k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b" + +#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="600k",LANGUAGE="en",NAME="Audio",AUTOSELECT=YES,DEFAULT=YES,URI="/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b",BANDWIDTH=614400 diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 38ba43a97..80ed8d7e5 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -88,6 +88,7 @@ from .utils import ( version_tuple, write_json_file, write_string, + YoutubeDLCookieJar, YoutubeDLCookieProcessor, YoutubeDLHandler, ) @@ -558,7 +559,7 @@ class YoutubeDL(object): self.restore_console_title() if self.params.get('cookiefile') is not None: - self.cookiejar.save() + self.cookiejar.save(ignore_discard=True, ignore_expires=True) def trouble(self, message=None, tb=None): """Determine action to take when a download problem appears. @@ -1062,21 +1063,24 @@ class YoutubeDL(object): if not m: STR_OPERATORS = { '=': operator.eq, - '!=': operator.ne, '^=': lambda attr, value: attr.startswith(value), '$=': lambda attr, value: attr.endswith(value), '*=': lambda attr, value: value in attr, } str_operator_rex = re.compile(r'''(?x) \s*(?P<key>ext|acodec|vcodec|container|protocol|format_id) - \s*(?P<op>%s)(?P<none_inclusive>\s*\?)? + \s*(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)? \s*(?P<value>[a-zA-Z0-9._-]+) \s*$ ''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) m = str_operator_rex.search(filter_spec) if m: comparison_value = m.group('value') - op = STR_OPERATORS[m.group('op')] + str_op = STR_OPERATORS[m.group('op')] + if m.group('negation'): + op = lambda attr, value: not str_op(attr, value) + else: + op = str_op if not m: raise ValueError('Invalid filter specification %r' % filter_spec) @@ -2297,10 +2301,9 @@ class YoutubeDL(object): self.cookiejar = compat_cookiejar.CookieJar() else: opts_cookiefile = expand_path(opts_cookiefile) - self.cookiejar = compat_cookiejar.MozillaCookieJar( - opts_cookiefile) + self.cookiejar = YoutubeDLCookieJar(opts_cookiefile) if os.access(opts_cookiefile, os.R_OK): - self.cookiejar.load() + self.cookiejar.load(ignore_discard=True, ignore_expires=True) cookie_processor = YoutubeDLCookieProcessor(self.cookiejar) if opts_proxy is not None: diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index fd304527e..4def8e2d5 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -75,10 +75,14 @@ class HlsFD(FragmentFD): fd.add_progress_hook(ph) return fd.real_download(filename, info_dict) - def is_ad_fragment(s): + def is_ad_fragment_start(s): return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad')) + def is_ad_fragment_end(s): + return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or + s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment')) + media_frags = 0 ad_frags = 0 ad_frag_next = False @@ -87,12 +91,13 @@ class HlsFD(FragmentFD): if not line: continue if line.startswith('#'): - if is_ad_fragment(line): - ad_frags += 1 + if is_ad_fragment_start(line): ad_frag_next = True + elif is_ad_fragment_end(line): + ad_frag_next = False continue if ad_frag_next: - ad_frag_next = False + ad_frags += 1 continue media_frags += 1 @@ -123,7 +128,6 @@ class HlsFD(FragmentFD): if line: if not line.startswith('#'): if ad_frag_next: - ad_frag_next = False continue frag_index += 1 if frag_index <= ctx['fragment_index']: @@ -196,8 +200,10 @@ class HlsFD(FragmentFD): 'start': sub_range_start, 'end': sub_range_start + int(splitted_byte_range[0]), } - elif is_ad_fragment(line): + elif is_ad_fragment_start(line): ad_frag_next = True + elif is_ad_fragment_end(line): + ad_frag_next = False self._finish_frag_download(ctx) diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index 6d846ea7a..c4362be88 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -17,25 +17,15 @@ from ..utils import ( class ACastIE(InfoExtractor): IE_NAME = 'acast' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?:embed|www)\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P<channel>[^/]+)/(?P<id>[^/#?]+) + ''' _TESTS = [{ - # test with one bling - 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan', - 'md5': 'ada3de5a1e3a2a381327d749854788bb', - 'info_dict': { - 'id': '57de3baa-4bb0-487e-9418-2692c1277a34', - 'ext': 'mp3', - 'title': '"Where Are You?": Taipei 101, Taiwan', - 'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e', - 'timestamp': 1196172000, - 'upload_date': '20071127', - 'duration': 211, - 'creator': 'Concierge', - 'series': 'Condé Nast Traveler Podcast', - 'episode': '"Where Are You?": Taipei 101, Taiwan', - } - }, { - # test with multiple blings 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', 'md5': 'a02393c74f3bdb1801c3ec2695577ce0', 'info_dict': { @@ -50,6 +40,12 @@ class ACastIE(InfoExtractor): 'series': 'Spår', 'episode': '2. Raggarmordet - Röster ur det förflutna', } + }, { + 'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015', + 'only_matching': True, + }, { + 'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22', + 'only_matching': True, }] def _real_extract(self, url): @@ -83,17 +79,27 @@ class ACastIE(InfoExtractor): class ACastChannelIE(InfoExtractor): IE_NAME = 'acast:channel' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)' - _TEST = { - 'url': 'https://www.acast.com/condenasttraveler', + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P<id>[^/#?]+) + ''' + _TESTS = [{ + 'url': 'https://www.acast.com/todayinfocus', 'info_dict': { - 'id': '50544219-29bb-499e-a083-6087f4cb7797', - 'title': 'Condé Nast Traveler Podcast', - 'description': 'md5:98646dee22a5b386626ae31866638fbd', + 'id': '4efc5294-5385-4847-98bd-519799ce5786', + 'title': 'Today in Focus', + 'description': 'md5:9ba5564de5ce897faeb12963f4537a64', }, - 'playlist_mincount': 20, - } - _API_BASE_URL = 'https://www.acast.com/api/' + 'playlist_mincount': 35, + }, { + 'url': 'http://play.acast.com/s/ft-banking-weekly', + 'only_matching': True, + }] + _API_BASE_URL = 'https://play.acast.com/api/' _PAGE_SIZE = 10 @classmethod @@ -106,7 +112,7 @@ class ACastChannelIE(InfoExtractor): channel_slug, note='Download page %d of channel data' % page) for cast in casts: yield self.url_result( - 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']), + 'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']), 'ACast', cast['id']) def _real_extract(self, url): diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 398e56ea3..85ec6392d 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -22,18 +22,19 @@ class AENetworksBaseIE(ThePlatformIE): class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' - IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' + IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault' _VALID_URL = r'''(?x) https?:// (?:www\.)? (?P<domain> - (?:history|aetv|mylifetime|lifetimemovieclub)\.com| + (?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com| fyi\.tv )/ (?: shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})| movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?| - specials/(?P<special_display_id>[^/]+)/full-special + specials/(?P<special_display_id>[^/]+)/full-special| + collections/[^/]+/(?P<collection_display_id>[^/]+) ) ''' _TESTS = [{ @@ -80,6 +81,9 @@ class AENetworksIE(AENetworksBaseIE): }, { 'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special', 'only_matching': True + }, { + 'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward', + 'only_matching': True }] _DOMAIN_TO_REQUESTOR_ID = { 'history.com': 'HISTORY', @@ -90,9 +94,9 @@ class AENetworksIE(AENetworksBaseIE): } def _real_extract(self, url): - domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups() - display_id = show_path or movie_display_id or special_display_id - webpage = self._download_webpage(url, display_id) + domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups() + display_id = show_path or movie_display_id or special_display_id or collection_display_id + webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers()) if show_path: url_parts = show_path.split('/') url_parts_len = len(url_parts) diff --git a/youtube_dl/extractor/americastestkitchen.py b/youtube_dl/extractor/americastestkitchen.py index 01736872d..8b32aa886 100644 --- a/youtube_dl/extractor/americastestkitchen.py +++ b/youtube_dl/extractor/americastestkitchen.py @@ -43,10 +43,6 @@ class AmericasTestKitchenIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - partner_id = self._search_regex( - r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', - webpage, 'kaltura partner id') - video_data = self._parse_json( self._search_regex( r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>', @@ -58,7 +54,18 @@ class AmericasTestKitchenIE(InfoExtractor): (lambda x: x['episodeDetail']['content']['data'], lambda x: x['videoDetail']['content']['data']), dict) ep_meta = ep_data.get('full_video', {}) - external_id = ep_data.get('external_id') or ep_meta['external_id'] + + zype_id = ep_meta.get('zype_id') + if zype_id: + embed_url = 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id + ie_key = 'Zype' + else: + partner_id = self._search_regex( + r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', + webpage, 'kaltura partner id') + external_id = ep_data.get('external_id') or ep_meta['external_id'] + embed_url = 'kaltura:%s:%s' % (partner_id, external_id) + ie_key = 'Kaltura' title = ep_data.get('title') or ep_meta.get('title') description = clean_html(ep_meta.get('episode_description') or ep_data.get( @@ -72,8 +79,8 @@ class AmericasTestKitchenIE(InfoExtractor): return { '_type': 'url_transparent', - 'url': 'kaltura:%s:%s' % (partner_id, external_id), - 'ie_key': 'Kaltura', + 'url': embed_url, + 'ie_key': ie_key, 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 6eb8bbb6e..883dcee7a 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( int_or_none, + merge_dicts, mimetype2ext, url_or_none, ) @@ -12,59 +13,83 @@ from ..utils import ( class AparatIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.aparat.com/v/wP8On', 'md5': '131aca2e14fe7c4dcb3c4877ba300c89', 'info_dict': { 'id': 'wP8On', 'ext': 'mp4', 'title': 'تیم گلکسی 11 - زومیت', - 'age_limit': 0, + 'description': 'md5:096bdabcdcc4569f2b8a5e903a3b3028', + 'duration': 231, + 'timestamp': 1387394859, + 'upload_date': '20131218', + 'view_count': int, }, - # 'skip': 'Extremely unreliable', - } + }, { + # multiple formats + 'url': 'https://www.aparat.com/v/8dflw/', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - # Note: There is an easier-to-parse configuration at - # http://www.aparat.com/video/video/config/videohash/%video_id - # but the URL in there does not work - webpage = self._download_webpage( - 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id, - video_id) + # Provides more metadata + webpage = self._download_webpage(url, video_id, fatal=False) - title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title') + if not webpage: + # Note: There is an easier-to-parse configuration at + # http://www.aparat.com/video/video/config/videohash/%video_id + # but the URL in there does not work + webpage = self._download_webpage( + 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id, + video_id) - file_list = self._parse_json( + options = self._parse_json( self._search_regex( - r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, - 'file list'), + r'options\s*=\s*JSON\.parse\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1\s*\)', + webpage, 'options', group='value'), video_id) + player = options['plugins']['sabaPlayerPlugin'] + formats = [] - for item in file_list[0]: - file_url = url_or_none(item.get('file')) - if not file_url: - continue - ext = mimetype2ext(item.get('type')) - label = item.get('label') - formats.append({ - 'url': file_url, - 'ext': ext, - 'format_id': label or ext, - 'height': int_or_none(self._search_regex( - r'(\d+)[pP]', label or '', 'height', default=None)), - }) - self._sort_formats(formats) + for sources in player['multiSRC']: + for item in sources: + if not isinstance(item, dict): + continue + file_url = url_or_none(item.get('src')) + if not file_url: + continue + item_type = item.get('type') + if item_type == 'application/vnd.apple.mpegurl': + formats.extend(self._extract_m3u8_formats( + file_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + else: + ext = mimetype2ext(item.get('type')) + label = item.get('label') + formats.append({ + 'url': file_url, + 'ext': ext, + 'format_id': 'http-%s' % (label or ext), + 'height': int_or_none(self._search_regex( + r'(\d+)[pP]', label or '', 'height', + default=None)), + }) + self._sort_formats( + formats, field_preference=('height', 'width', 'tbr', 'format_id')) - thumbnail = self._search_regex( - r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) + info = self._search_json_ld(webpage, video_id, default={}) - return { + if not info.get('title'): + info['title'] = player['title'] + + return merge_dicts(info, { 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'age_limit': self._family_friendly_search(webpage), + 'thumbnail': url_or_none(options.get('poster')), + 'duration': int_or_none(player.get('duration')), 'formats': formats, - } + }) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 6bf8f61eb..8adae4644 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -8,20 +8,23 @@ from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, - qualities, int_or_none, parse_duration, + qualities, + str_or_none, + try_get, unified_strdate, - xpath_text, + unified_timestamp, update_url_query, url_or_none, + xpath_text, ) from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): IE_NAME = 'ARD:mediathek' - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' + _VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ # available till 26.07.2022 @@ -51,8 +54,15 @@ class ARDMediathekIE(InfoExtractor): # audio 'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158', 'only_matching': True, + }, { + 'url': 'https://classic.ardmediathek.de/tv/Panda-Gorilla-Co/Panda-Gorilla-Co-Folge-274/Das-Erste/Video?bcastId=16355486&documentId=58234698', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url) + def _extract_media_info(self, media_info_url, webpage, video_id): media_info = self._download_json( media_info_url, video_id, 'Downloading media JSON') @@ -173,13 +183,18 @@ class ARDMediathekIE(InfoExtractor): title = self._html_search_regex( [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', r'<meta name="dcterms\.title" content="(.*?)"/>', - r'<h4 class="headline">(.*?)</h4>'], + r'<h4 class="headline">(.*?)</h4>', + r'<title[^>]*>(.*?)'], webpage, 'title') description = self._html_search_meta( 'dcterms.abstract', webpage, 'description', default=None) if description is None: description = self._html_search_meta( - 'description', webpage, 'meta description') + 'description', webpage, 'meta description', default=None) + if description is None: + description = self._html_search_regex( + r'(.+?)

', + webpage, 'teaser text', default=None) # Thumbnail is sometimes not present. # It is in the mobile version, but that seems to use a different URL @@ -288,7 +303,7 @@ class ARDIE(InfoExtractor): class ARDBetaMediathekIE(InfoExtractor): - _VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P[a-zA-Z0-9]+)/(?P[^/?#]+)' + _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P[a-zA-Z0-9]+)(?:/(?P[^/?#]+))?' _TESTS = [{ 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', 'md5': '2d02d996156ea3c397cfc5036b5d7f8f', @@ -302,12 +317,18 @@ class ARDBetaMediathekIE(InfoExtractor): 'upload_date': '20180826', 'ext': 'mp4', }, + }, { + 'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/', + 'only_matching': True, + }, { + 'url': 'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') or video_id webpage = self._download_webpage(url, display_id) data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json') @@ -318,43 +339,62 @@ class ARDBetaMediathekIE(InfoExtractor): 'display_id': display_id, } formats = [] + subtitles = {} + geoblocked = False for widget in data.values(): - if widget.get('_geoblocked'): - raise ExtractorError('This video is not available due to geoblocking', expected=True) - + if widget.get('_geoblocked') is True: + geoblocked = True if '_duration' in widget: - res['duration'] = widget['_duration'] + res['duration'] = int_or_none(widget['_duration']) if 'clipTitle' in widget: res['title'] = widget['clipTitle'] if '_previewImage' in widget: res['thumbnail'] = widget['_previewImage'] if 'broadcastedOn' in widget: - res['upload_date'] = unified_strdate(widget['broadcastedOn']) + res['timestamp'] = unified_timestamp(widget['broadcastedOn']) if 'synopsis' in widget: res['description'] = widget['synopsis'] - if '_subtitleUrl' in widget: - res['subtitles'] = {'de': [{ + subtitle_url = url_or_none(widget.get('_subtitleUrl')) + if subtitle_url: + subtitles.setdefault('de', []).append({ 'ext': 'ttml', - 'url': widget['_subtitleUrl'], - }]} + 'url': subtitle_url, + }) if '_quality' in widget: - format_url = widget['_stream']['json'][0] - - if format_url.endswith('.f4m'): + format_url = url_or_none(try_get( + widget, lambda x: x['_stream']['json'][0])) + if not format_url: + continue + ext = determine_ext(format_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( format_url + '?hdcore=3.11.0', video_id, f4m_id='hds', fatal=False)) - elif format_url.endswith('m3u8'): + elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + format_url, video_id, 'mp4', m3u8_id='hls', + fatal=False)) else: + # HTTP formats are not available when geoblocked is True, + # other formats are fine though + if geoblocked: + continue + quality = str_or_none(widget.get('_quality')) formats.append({ - 'format_id': 'http-' + widget['_quality'], + 'format_id': ('http-' + quality) if quality else 'http', 'url': format_url, 'preference': 10, # Plain HTTP, that's nice }) + if not formats and geoblocked: + self.raise_geo_restricted( + msg='This video is not available due to geoblocking', + countries=['DE']) + self._sort_formats(formats) - res['formats'] = formats + res.update({ + 'subtitles': subtitles, + 'formats': formats, + }) return res diff --git a/youtube_dl/extractor/atvat.py b/youtube_dl/extractor/atvat.py index 1584d53fc..95e572d70 100644 --- a/youtube_dl/extractor/atvat.py +++ b/youtube_dl/extractor/atvat.py @@ -28,8 +28,10 @@ class ATVAtIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_data = self._parse_json(unescapeHTML(self._search_regex( - r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="([^"]+)"', - webpage, 'player data')), display_id)['config']['initial_video'] + [r'flashPlayerOptions\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="(?P[^"]+)"'], + webpage, 'player data', group='json')), + display_id)['config']['initial_video'] video_id = video_data['id'] video_title = video_data['title'] diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index 62049b921..cc7771354 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -62,7 +62,7 @@ class AudiomackIE(InfoExtractor): # Audiomack wraps a lot of soundcloud tracks in their branded wrapper # if so, pass the work off to the soundcloud extractor if SoundcloudIE.suitable(api_response['url']): - return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'} + return self.url_result(api_response['url'], SoundcloudIE.ie_key()) return { 'id': compat_str(api_response.get('id', album_url_tag)), diff --git a/youtube_dl/extractor/azmedien.py b/youtube_dl/extractor/azmedien.py index 68f26e2ca..fcbdc71b9 100644 --- a/youtube_dl/extractor/azmedien.py +++ b/youtube_dl/extractor/azmedien.py @@ -1,213 +1,86 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor from .kaltura import KalturaIE -from ..utils import ( - get_element_by_class, - get_element_by_id, - strip_or_none, - urljoin, -) -class AZMedienBaseIE(InfoExtractor): - def _kaltura_video(self, partner_id, entry_id): - return self.url_result( - 'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(), - video_id=entry_id) - - -class AZMedienIE(AZMedienBaseIE): +class AZMedienIE(InfoExtractor): IE_DESC = 'AZ Medien videos' _VALID_URL = r'''(?x) https?:// (?:www\.)? - (?: + (?P telezueri\.ch| telebaern\.tv| telem1\.ch )/ - [0-9]+-show-[^/\#]+ - (?: - /[0-9]+-episode-[^/\#]+ - (?: - /[0-9]+-segment-(?:[^/\#]+\#)?| - \# - )| - \# + [^/]+/ + (?P + [^/]+-(?P\d+) ) - (?P[^\#]+) + (?: + \#video= + (?P + [_0-9a-z]+ + ) + )? ''' _TESTS = [{ - # URL with 'segment' - 'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom', + 'url': 'https://www.telezueri.ch/sonntalk/bundesrats-vakanzen-eu-rahmenabkommen-133214569', 'info_dict': { - 'id': '1_2444peh4', + 'id': '1_anruz3wy', 'ext': 'mp4', - 'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom', - 'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8', - 'uploader_id': 'TeleZ?ri', - 'upload_date': '20161218', - 'timestamp': 1482084490, + 'title': 'Bundesrats-Vakanzen / EU-Rahmenabkommen', + 'uploader_id': 'TVOnline', + 'upload_date': '20180930', + 'timestamp': 1538328802, }, 'params': { 'skip_download': True, }, }, { - # URL with 'segment' and fragment: - 'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger', - 'only_matching': True - }, { - # URL with 'episode' and fragment: - 'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz', - 'only_matching': True - }, { - # URL with 'show' and fragment: - 'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch', + 'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1', 'only_matching': True }] - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - partner_id = self._search_regex( - r']+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)', - webpage, 'kaltura partner id') - entry_id = self._html_search_regex( - r']+data-id=(["\'])(?P(?:(?!\1).)+)\1[^>]+data-slug=["\']%s' - % re.escape(video_id), webpage, 'kaltura entry id', group='id') - - return self._kaltura_video(partner_id, entry_id) - - -class AZMedienPlaylistIE(AZMedienBaseIE): - IE_DESC = 'AZ Medien playlists' - _VALID_URL = r'''(?x) - https?:// - (?:www\.)? - (?: - telezueri\.ch| - telebaern\.tv| - telem1\.ch - )/ - (?P[0-9]+- - (?: - show| - topic| - themen - )-[^/\#]+ - (?: - /[0-9]+-episode-[^/\#]+ - )? - )$ - ''' - - _TESTS = [{ - # URL with 'episode' - 'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016', - 'info_dict': { - 'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016', - 'title': 'News - Donnerstag, 15. Dezember 2016', - }, - 'playlist_count': 9, - }, { - # URL with 'themen' - 'url': 'http://www.telem1.ch/258-themen-tele-m1-classics', - 'info_dict': { - 'id': '258-themen-tele-m1-classics', - 'title': 'Tele M1 Classics', - }, - 'playlist_mincount': 15, - }, { - # URL with 'topic', contains nested playlists - 'url': 'http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen', - 'only_matching': True, - }, { - # URL with 'show' only - 'url': 'http://www.telezueri.ch/86-show-talktaeglich', - 'only_matching': True - }] + _PARTNER_ID = '1719221' def _real_extract(self, url): - show_id = self._match_id(url) - webpage = self._download_webpage(url, show_id) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + video_id = mobj.group('id') + entry_id = mobj.group('kaltura_id') - entries = [] + if not entry_id: + api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0]) + payload = { + 'query': '''query VideoContext($articleId: ID!) { + article: node(id: $articleId) { + ... on Article { + mainAssetRelation { + asset { + ... on VideoAsset { + kalturaId + } + } + } + } + } + }''', + 'variables': {'articleId': 'Article:%s' % mobj.group('article_id')}, + } + json_data = self._download_json( + api_url, video_id, headers={ + 'Content-Type': 'application/json', + }, + data=json.dumps(payload).encode()) + entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId'] - partner_id = self._search_regex( - r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)', - webpage, 'kaltura partner id', default=None) - - if partner_id: - entries = [ - self._kaltura_video(partner_id, m.group('id')) - for m in re.finditer( - r'data-id=(["\'])(?P(?:(?!\1).)+)\1', webpage)] - - if not entries: - entries = [ - self.url_result(m.group('url'), ie=AZMedienIE.ie_key()) - for m in re.finditer( - r']+data-real=(["\'])(?Phttp.+?)\1', webpage)] - - if not entries: - entries = [ - # May contain nested playlists (e.g. [1]) thus no explicit - # ie_key - # 1. http://www.telezueri.ch/219-topic-aera-trump-hat-offiziell-begonnen) - self.url_result(urljoin(url, m.group('url'))) - for m in re.finditer( - r']+name=[^>]+href=(["\'])(?P/.+?)\1', webpage)] - - title = self._search_regex( - r'episodeShareTitle\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', - webpage, 'title', - default=strip_or_none(get_element_by_id( - 'video-title', webpage)), group='title') - - return self.playlist_result(entries, show_id, title) - - -class AZMedienShowPlaylistIE(AZMedienBaseIE): - IE_DESC = 'AZ Medien show playlists' - _VALID_URL = r'''(?x) - https?:// - (?:www\.)? - (?: - telezueri\.ch| - telebaern\.tv| - telem1\.ch - )/ - (?: - all-episodes| - alle-episoden - )/ - (?P<id>[^/?#&]+) - ''' - - _TEST = { - 'url': 'http://www.telezueri.ch/all-episodes/astrotalk', - 'info_dict': { - 'id': 'astrotalk', - 'title': 'TeleZüri: AstroTalk - alle episoden', - 'description': 'md5:4c0f7e7d741d906004266e295ceb4a26', - }, - 'playlist_mincount': 13, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - episodes = get_element_by_class('search-mobile-box', webpage) - entries = [self.url_result( - urljoin(url, m.group('url'))) for m in re.finditer( - r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', episodes)] - title = self._og_search_title(webpage, fatal=False) - description = self._og_search_description(webpage) - return self.playlist_result(entries, playlist_id, title, description) + return self.url_result( + 'kaltura:%s:%s' % (self._PARTNER_ID, entry_id), + ie=KalturaIE.ie_key(), video_id=entry_id) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index abcfa301d..eac9a5a46 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -795,6 +795,15 @@ class BBCIE(BBCCoUkIE): 'uploader': 'Radio 3', 'uploader_id': 'bbc_radio_three', }, + }, { + 'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227', + 'info_dict': { + 'id': 'p06w9tws', + 'ext': 'mp4', + 'title': 'md5:2fabf12a726603193a2879a055f72514', + 'description': 'Learn English words and phrases from this story', + }, + 'add_ie': [BBCCoUkIE.ie_key()], }] @classmethod @@ -945,6 +954,15 @@ class BBCIE(BBCCoUkIE): if entries: return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) + # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227 + group_id = self._search_regex( + r'<div[^>]+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX, + webpage, 'group id', default=None) + if playlist_id: + return self.url_result( + 'https://www.bbc.co.uk/programmes/%s' % group_id, + ie=BBCCoUkIE.ie_key()) + # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) programme_id = self._search_regex( [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX, diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index bf22a41b7..1086d7632 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -1,15 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_chr, - compat_ord, - compat_urllib_parse_unquote, -) +from ..compat import compat_str from ..utils import ( int_or_none, - parse_iso8601, - urljoin, + unified_timestamp, ) @@ -36,29 +31,9 @@ class BeegIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - cpl_url = self._search_regex( - r'<script[^>]+src=(["\'])(?P<url>(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1', - webpage, 'cpl', default=None, group='url') - - cpl_url = urljoin(url, cpl_url) - - beeg_version, beeg_salt = [None] * 2 - - if cpl_url: - cpl = self._download_webpage( - self._proto_relative_url(cpl_url), video_id, - 'Downloading cpl JS', fatal=False) - if cpl: - beeg_version = int_or_none(self._search_regex( - r'beeg_version\s*=\s*([^\b]+)', cpl, - 'beeg version', default=None)) or self._search_regex( - r'/(\d+)\.js', cpl_url, 'beeg version', default=None) - beeg_salt = self._search_regex( - r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt', - default=None, group='beeg_salt') - - beeg_version = beeg_version or '2185' - beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H' + beeg_version = self._search_regex( + r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', + default='1546225636701') for api_path in ('', 'api.'): video = self._download_json( @@ -68,37 +43,6 @@ class BeegIE(InfoExtractor): if video: break - def split(o, e): - def cut(s, x): - n.append(s[:x]) - return s[x:] - n = [] - r = len(o) % e - if r > 0: - o = cut(o, r) - while len(o) > e: - o = cut(o, e) - n.append(o) - return n - - def decrypt_key(key): - # Reverse engineered from http://static.beeg.com/cpl/1738.js - a = beeg_salt - e = compat_urllib_parse_unquote(key) - o = ''.join([ - compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21) - for n in range(len(e))]) - return ''.join(split(o, 3)[::-1]) - - def decrypt_url(encrypted_url): - encrypted_url = self._proto_relative_url( - encrypted_url.replace('{DATA_MARKERS}', ''), 'https:') - key = self._search_regex( - r'/key=(.*?)%2Cend=', encrypted_url, 'key', default=None) - if not key: - return encrypted_url - return encrypted_url.replace(key, decrypt_key(key)) - formats = [] for format_id, video_url in video.items(): if not video_url: @@ -108,18 +52,20 @@ class BeegIE(InfoExtractor): if not height: continue formats.append({ - 'url': decrypt_url(video_url), + 'url': self._proto_relative_url( + video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'), 'format_id': format_id, 'height': int(height), }) self._sort_formats(formats) title = video['title'] - video_id = video.get('id') or video_id + video_id = compat_str(video.get('id') or video_id) display_id = video.get('code') description = video.get('desc') + series = video.get('ps_name') - timestamp = parse_iso8601(video.get('date'), ' ') + timestamp = unified_timestamp(video.get('date')) duration = int_or_none(video.get('duration')) tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None @@ -129,6 +75,7 @@ class BeegIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'series': series, 'timestamp': timestamp, 'duration': duration, 'tags': tags, diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 446a1ab19..4f39424f5 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -5,7 +5,10 @@ import itertools import re from .common import InfoExtractor -from ..utils import urlencode_postdata +from ..utils import ( + orderedSet, + urlencode_postdata, +) class BitChuteIE(InfoExtractor): @@ -37,16 +40,22 @@ class BitChuteIE(InfoExtractor): 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36', }) - title = self._search_regex( + title = self._html_search_regex( (r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'), webpage, 'title', default=None) or self._html_search_meta( 'description', webpage, 'title', default=None) or self._og_search_description(webpage) + format_urls = [] + for mobj in re.finditer( + r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage): + format_urls.append(mobj.group('url')) + format_urls.extend(re.findall(r'as=(https?://[^&"\']+)', webpage)) + formats = [ - {'url': mobj.group('url')} - for mobj in re.finditer( - r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)] + {'url': format_url} + for format_url in orderedSet(format_urls)] + self._check_formats(formats, video_id) self._sort_formats(formats) description = self._html_search_regex( diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 14f9a14ed..465ae396e 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -1,8 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import base64 import json +import re +import struct from .common import InfoExtractor from .adobepass import AdobePassIE @@ -310,6 +312,10 @@ class BrightcoveLegacyIE(InfoExtractor): 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?', expected=True) + def _brightcove_new_url_result(self, publisher_id, video_id): + brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id) + return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id) + def _get_video_info(self, video_id, query, referer=None): headers = {} linkBase = query.get('linkBaseURL') @@ -323,6 +329,28 @@ class BrightcoveLegacyIE(InfoExtractor): r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage, 'error message', default=None) if error_msg is not None: + publisher_id = query.get('publisherId') + if publisher_id and publisher_id[0].isdigit(): + publisher_id = publisher_id[0] + if not publisher_id: + player_key = query.get('playerKey') + if player_key and ',' in player_key[0]: + player_key = player_key[0] + else: + player_id = query.get('playerID') + if player_id and player_id[0].isdigit(): + player_page = self._download_webpage( + 'http://link.brightcove.com/services/player/bcpid' + player_id[0], + video_id, headers=headers, fatal=False) + if player_page: + player_key = self._search_regex( + r'<param\s+name="playerKey"\s+value="([\w~,-]+)"', + player_page, 'player key', fatal=False) + if player_key: + enc_pub_id = player_key.split(',')[1].replace('~', '=') + publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0] + if publisher_id: + return self._brightcove_new_url_result(publisher_id, video_id) raise ExtractorError( 'brightcove said: %s' % error_msg, expected=True) @@ -444,8 +472,12 @@ class BrightcoveLegacyIE(InfoExtractor): else: return ad_info - if 'url' not in info and not info.get('formats'): - raise ExtractorError('Unable to extract video url for %s' % video_id) + if not info.get('url') and not info.get('formats'): + uploader_id = info.get('uploader_id') + if uploader_id: + info.update(self._brightcove_new_url_result(uploader_id, video_id)) + else: + raise ExtractorError('Unable to extract video url for %s' % video_id) return info diff --git a/youtube_dl/extractor/cammodels.py b/youtube_dl/extractor/cammodels.py index 79350817f..1eb81b75e 100644 --- a/youtube_dl/extractor/cammodels.py +++ b/youtube_dl/extractor/cammodels.py @@ -14,6 +14,7 @@ class CamModelsIE(InfoExtractor): _TESTS = [{ 'url': 'https://www.cammodels.com/cam/AutumnKnight/', 'only_matching': True, + 'age_limit': 18 }] def _real_extract(self, url): @@ -93,4 +94,5 @@ class CamModelsIE(InfoExtractor): 'title': self._live_title(user_id), 'is_live': True, 'formats': formats, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/camtube.py b/youtube_dl/extractor/camtube.py index c7d40f849..b3be3bdcf 100644 --- a/youtube_dl/extractor/camtube.py +++ b/youtube_dl/extractor/camtube.py @@ -20,6 +20,7 @@ class CamTubeIE(InfoExtractor): 'duration': 1274, 'timestamp': 1528018608, 'upload_date': '20180603', + 'age_limit': 18 }, 'params': { 'skip_download': True, @@ -66,4 +67,5 @@ class CamTubeIE(InfoExtractor): 'like_count': like_count, 'creator': creator, 'formats': formats, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/camwithher.py b/youtube_dl/extractor/camwithher.py index afbc5ea26..bbc5205fd 100644 --- a/youtube_dl/extractor/camwithher.py +++ b/youtube_dl/extractor/camwithher.py @@ -25,6 +25,7 @@ class CamWithHerIE(InfoExtractor): 'comment_count': int, 'uploader': 'MileenaK', 'upload_date': '20160322', + 'age_limit': 18, }, 'params': { 'skip_download': True, @@ -84,4 +85,5 @@ class CamWithHerIE(InfoExtractor): 'comment_count': comment_count, 'uploader': uploader, 'upload_date': upload_date, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/carambatv.py b/youtube_dl/extractor/carambatv.py index 9ba909a91..b57b86af7 100644 --- a/youtube_dl/extractor/carambatv.py +++ b/youtube_dl/extractor/carambatv.py @@ -82,6 +82,12 @@ class CarambaTVPageIE(InfoExtractor): webpage = self._download_webpage(url, video_id) videomore_url = VideomoreIE._extract_url(webpage) + if not videomore_url: + videomore_id = self._search_regex( + r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id', + default=None) + if videomore_id: + videomore_url = 'videomore:%s' % videomore_id if videomore_url: title = self._og_search_title(webpage) return { diff --git a/youtube_dl/extractor/cartoonnetwork.py b/youtube_dl/extractor/cartoonnetwork.py index 6aeebd7b3..48b33617f 100644 --- a/youtube_dl/extractor/cartoonnetwork.py +++ b/youtube_dl/extractor/cartoonnetwork.py @@ -1,20 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .turner import TurnerBaseIE +from ..utils import int_or_none class CartoonNetworkIE(TurnerBaseIE): _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html' _TEST = { - 'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html', + 'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html', 'info_dict': { - 'id': '8a250ab04ed07e6c014ef3f1e2f9016c', + 'id': '6e3375097f63874ebccec7ef677c1c3845fa850e', 'ext': 'mp4', - 'title': 'Starfire the Cat Lady', - 'description': 'Robin decides to become a cat so that Starfire will finally love him.', + 'title': 'How to Draw Upgrade', + 'description': 'md5:2061d83776db7e8be4879684eefe8c0f', }, 'params': { # m3u8 download @@ -25,18 +24,39 @@ class CartoonNetworkIE(TurnerBaseIE): def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups() - query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id - return self._extract_cvp_info( - 'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, { - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big', - 'tokenizer_src': 'https://token.vgtf.net/token/token_mobile', - }, - }, { + + def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False): + metadata_re = '' + if content_re: + metadata_re = r'|video_metadata\.content_' + content_re + return self._search_regex( + r'(?:_cnglobal\.currentVideo\.%s%s)\s*=\s*"(%s)";' % (global_re, metadata_re, value_re), + webpage, name, fatal=fatal) + + media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True) + title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True) + + info = self._extract_ngtv_info( + media_id, {'networkId': 'cartoonnetwork'}, { 'url': url, 'site_name': 'CartoonNetwork', - 'auth_required': self._search_regex( - r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);', - webpage, 'auth required', default='false') == 'true', + 'auth_required': find_field('authType', 'auth type') != 'unauth', }) + + series = find_field( + 'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage) + info.update({ + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'description': self._html_search_meta('description', webpage), + 'series': series, + 'episode': title, + }) + + for field in ('season', 'episode'): + field_name = field + 'Number' + info[field + '_number'] = int_or_none(find_field( + field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage)) + + return info diff --git a/youtube_dl/extractor/ciscolive.py b/youtube_dl/extractor/ciscolive.py new file mode 100644 index 000000000..c99b6ee58 --- /dev/null +++ b/youtube_dl/extractor/ciscolive.py @@ -0,0 +1,142 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import itertools + +from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) +from ..utils import ( + clean_html, + float_or_none, + int_or_none, + try_get, + urlencode_postdata, +) + + +class CiscoLiveBaseIE(InfoExtractor): + # These appear to be constant across all Cisco Live presentations + # and are not tied to any user session or event + RAINFOCUS_API_URL = 'https://events.rainfocus.com/api/%s' + RAINFOCUS_API_PROFILE_ID = 'Na3vqYdAlJFSxhYTYQGuMbpafMqftalz' + RAINFOCUS_WIDGET_ID = 'n6l4Lo05R8fiy3RpUBm447dZN8uNWoye' + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5647924234001/SyK2FdqjM_default/index.html?videoId=%s' + + HEADERS = { + 'Origin': 'https://ciscolive.cisco.com', + 'rfApiProfileId': RAINFOCUS_API_PROFILE_ID, + 'rfWidgetId': RAINFOCUS_WIDGET_ID, + } + + def _call_api(self, ep, rf_id, query, referrer, note=None): + headers = self.HEADERS.copy() + headers['Referer'] = referrer + return self._download_json( + self.RAINFOCUS_API_URL % ep, rf_id, note=note, + data=urlencode_postdata(query), headers=headers) + + def _parse_rf_item(self, rf_item): + event_name = rf_item.get('eventName') + title = rf_item['title'] + description = clean_html(rf_item.get('abstract')) + presenter_name = try_get(rf_item, lambda x: x['participants'][0]['fullName']) + bc_id = rf_item['videos'][0]['url'] + bc_url = self.BRIGHTCOVE_URL_TEMPLATE % bc_id + duration = float_or_none(try_get(rf_item, lambda x: x['times'][0]['length'])) + location = try_get(rf_item, lambda x: x['times'][0]['room']) + + if duration: + duration = duration * 60 + + return { + '_type': 'url_transparent', + 'url': bc_url, + 'ie_key': 'BrightcoveNew', + 'title': title, + 'description': description, + 'duration': duration, + 'creator': presenter_name, + 'location': location, + 'series': event_name, + } + + +class CiscoLiveSessionIE(CiscoLiveBaseIE): + _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/\??[^#]*#/session/(?P<id>[^/?&]+)' + _TEST = { + 'url': 'https://ciscolive.cisco.com/on-demand-library/?#/session/1423353499155001FoSs', + 'md5': 'c98acf395ed9c9f766941c70f5352e22', + 'info_dict': { + 'id': '5803694304001', + 'ext': 'mp4', + 'title': '13 Smart Automations to Monitor Your Cisco IOS Network', + 'description': 'md5:ec4a436019e09a918dec17714803f7cc', + 'timestamp': 1530305395, + 'upload_date': '20180629', + 'uploader_id': '5647924234001', + 'location': '16B Mezz.', + }, + } + + def _real_extract(self, url): + rf_id = self._match_id(url) + rf_result = self._call_api('session', rf_id, {'id': rf_id}, url) + return self._parse_rf_item(rf_result['items'][0]) + + +class CiscoLiveSearchIE(CiscoLiveBaseIE): + _VALID_URL = r'https?://ciscolive\.cisco\.com/on-demand-library/' + _TESTS = [{ + 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.event=ciscoliveus2018&search.technicallevel=scpsSkillLevel_aintroductory&search.focus=scpsSessionFocus_designAndDeployment#/', + 'info_dict': { + 'title': 'Search query', + }, + 'playlist_count': 5, + }, { + 'url': 'https://ciscolive.cisco.com/on-demand-library/?search.technology=scpsTechnology_applicationDevelopment&search.technology=scpsTechnology_ipv6&search.focus=scpsSessionFocus_troubleshootingTroubleshooting#/', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if CiscoLiveSessionIE.suitable(url) else super(CiscoLiveSearchIE, cls).suitable(url) + + @staticmethod + def _check_bc_id_exists(rf_item): + return int_or_none(try_get(rf_item, lambda x: x['videos'][0]['url'])) is not None + + def _entries(self, query, url): + query['size'] = 50 + query['from'] = 0 + for page_num in itertools.count(1): + results = self._call_api( + 'search', None, query, url, + 'Downloading search JSON page %d' % page_num) + sl = try_get(results, lambda x: x['sectionList'][0], dict) + if sl: + results = sl + items = results.get('items') + if not items or not isinstance(items, list): + break + for item in items: + if not isinstance(item, dict): + continue + if not self._check_bc_id_exists(item): + continue + yield self._parse_rf_item(item) + size = int_or_none(results.get('size')) + if size is not None: + query['size'] = size + total = int_or_none(results.get('total')) + if total is not None and query['from'] + query['size'] > total: + break + query['from'] += query['size'] + + def _real_extract(self, url): + query = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + query['type'] = 'session' + return self.playlist_result( + self._entries(query, url), playlist_title='Search query') diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index ab651d1c8..f2ca7a337 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,19 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none - - -_translation_table = { - 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n', - 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r', - 'y': 'l', 'z': 'i', - '$': ':', '&': '.', '(': '=', '^': '&', '=': '/', -} - - -def _decode(s): - return ''.join(_translation_table.get(c, c) for c in s) +from ..utils import ( + int_or_none, + url_or_none, +) class CliphunterIE(InfoExtractor): @@ -60,14 +51,14 @@ class CliphunterIE(InfoExtractor): formats = [] for format_id, f in gexo_files.items(): - video_url = f.get('url') + video_url = url_or_none(f.get('url')) if not video_url: continue fmt = f.get('fmt') height = f.get('h') format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id formats.append({ - 'url': _decode(video_url), + 'url': video_url, 'format_id': format_id, 'width': int_or_none(f.get('w')), 'height': int_or_none(height), diff --git a/youtube_dl/extractor/cnbc.py b/youtube_dl/extractor/cnbc.py index d354d9f95..6889b0f40 100644 --- a/youtube_dl/extractor/cnbc.py +++ b/youtube_dl/extractor/cnbc.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals + from .common import InfoExtractor from ..utils import smuggle_url @@ -34,3 +35,32 @@ class CNBCIE(InfoExtractor): {'force_smil_url': True}), 'id': video_id, } + + +class CNBCVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cnbc\.com/video/(?:[^/]+/)+(?P<id>[^./?#&]+)' + _TEST = { + 'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html', + 'info_dict': { + 'id': '7000031301', + 'ext': 'mp4', + 'title': "Trump: I don't necessarily agree with raising rates", + 'description': 'md5:878d8f0b4ebb5bb1dda3514b91b49de3', + 'timestamp': 1531958400, + 'upload_date': '20180719', + 'uploader': 'NBCU-CNBC', + }, + 'params': { + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r'content_id["\']\s*:\s*["\'](\d+)', webpage, display_id, + 'video id') + return self.url_result( + 'http://video.cnbc.com/gallery/?video=%s' % video_id, + CNBCIE.ie_key()) diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 5fc311f53..774b71055 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -119,11 +119,7 @@ class CNNBlogsIE(InfoExtractor): def _real_extract(self, url): webpage = self._download_webpage(url, url_basename(url)) cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url') - return { - '_type': 'url', - 'url': cnn_url, - 'ie_key': CNNIE.ie_key(), - } + return self.url_result(cnn_url, CNNIE.ie_key()) class CNNArticleIE(InfoExtractor): @@ -145,8 +141,4 @@ class CNNArticleIE(InfoExtractor): def _real_extract(self, url): webpage = self._download_webpage(url, url_basename(url)) cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url') - return { - '_type': 'url', - 'url': 'http://cnn.com/video/?/video/' + cnn_url, - 'ie_key': CNNIE.ie_key(), - } + return self.url_result('http://cnn.com/video/?/video/' + cnn_url, CNNIE.ie_key()) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 2dbf81e6e..95456b291 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -69,6 +69,7 @@ from ..utils import ( update_url_query, urljoin, url_basename, + url_or_none, xpath_element, xpath_text, xpath_with_ns, @@ -605,6 +606,11 @@ class InfoExtractor(object): except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: if isinstance(err, compat_urllib_error.HTTPError): if self.__can_accept_status_code(err, expected_status): + # Retain reference to error to prevent file object from + # being closed before it can be read. Works around the + # effects of <https://bugs.python.org/issue15002> + # introduced in Python 3.4.1. + err.fp._error = err return err.fp if errnote is False: @@ -1213,10 +1219,10 @@ class InfoExtractor(object): def extract_video_object(e): assert e['@type'] == 'VideoObject' info.update({ - 'url': e.get('contentUrl'), + 'url': url_or_none(e.get('contentUrl')), 'title': unescapeHTML(e.get('name')), 'description': unescapeHTML(e.get('description')), - 'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'), + 'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')), 'duration': parse_duration(e.get('duration')), 'timestamp': unified_timestamp(e.get('uploadDate')), 'filesize': float_or_none(e.get('contentSize')), @@ -1233,17 +1239,27 @@ class InfoExtractor(object): if expected_type is not None and expected_type != item_type: return info if item_type in ('TVEpisode', 'Episode'): + episode_name = unescapeHTML(e.get('name')) info.update({ - 'episode': unescapeHTML(e.get('name')), + 'episode': episode_name, 'episode_number': int_or_none(e.get('episodeNumber')), 'description': unescapeHTML(e.get('description')), }) + if not info.get('title') and episode_name: + info['title'] = episode_name part_of_season = e.get('partOfSeason') if isinstance(part_of_season, dict) and part_of_season.get('@type') in ('TVSeason', 'Season', 'CreativeWorkSeason'): info['season_number'] = int_or_none(part_of_season.get('seasonNumber')) part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries') if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'): info['series'] = unescapeHTML(part_of_series.get('name')) + elif item_type == 'Movie': + info.update({ + 'title': unescapeHTML(e.get('name')), + 'description': unescapeHTML(e.get('description')), + 'duration': parse_duration(e.get('duration')), + 'timestamp': unified_timestamp(e.get('dateCreated')), + }) elif item_type in ('Article', 'NewsArticle'): info.update({ 'timestamp': parse_iso8601(e.get('datePublished')), @@ -1580,6 +1596,7 @@ class InfoExtractor(object): # References: # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21 # 2. https://github.com/rg3/youtube-dl/issues/12211 + # 3. https://github.com/rg3/youtube-dl/issues/18923 # We should try extracting formats only from master playlists [1, 4.3.4], # i.e. playlists that describe available qualities. On the other hand @@ -1651,11 +1668,16 @@ class InfoExtractor(object): rendition = stream_group[0] return rendition.get('NAME') or stream_group_id + # parse EXT-X-MEDIA tags before EXT-X-STREAM-INF in order to have the + # chance to detect video only formats when EXT-X-STREAM-INF tags + # precede EXT-X-MEDIA tags in HLS manifest such as [3]. + for line in m3u8_doc.splitlines(): + if line.startswith('#EXT-X-MEDIA:'): + extract_media(line) + for line in m3u8_doc.splitlines(): if line.startswith('#EXT-X-STREAM-INF:'): last_stream_inf = parse_m3u8_attributes(line) - elif line.startswith('#EXT-X-MEDIA:'): - extract_media(line) elif line.startswith('#') or not line.strip(): continue else: @@ -2608,7 +2630,7 @@ class InfoExtractor(object): 'id': this_video_id, 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')), 'description': video_data.get('description'), - 'thumbnail': self._proto_relative_url(video_data.get('image')), + 'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))), 'timestamp': int_or_none(video_data.get('pubdate')), 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), 'subtitles': subtitles, @@ -2635,12 +2657,9 @@ class InfoExtractor(object): for source in jwplayer_sources_data: if not isinstance(source, dict): continue - source_url = self._proto_relative_url(source.get('file')) - if not source_url: - continue - if base_url: - source_url = compat_urlparse.urljoin(base_url, source_url) - if source_url in urls: + source_url = urljoin( + base_url, self._proto_relative_url(source.get('file'))) + if not source_url or source_url in urls: continue urls.append(source_url) source_type = source.get('type') or '' diff --git a/youtube_dl/extractor/crackle.py b/youtube_dl/extractor/crackle.py index 8dd9d6687..f73ef6b63 100644 --- a/youtube_dl/extractor/crackle.py +++ b/youtube_dl/extractor/crackle.py @@ -48,6 +48,21 @@ class CrackleIE(InfoExtractor): 'only_matching': True, }] + _MEDIA_FILE_SLOTS = { + '360p.mp4': { + 'width': 640, + 'height': 360, + }, + '480p.mp4': { + 'width': 768, + 'height': 432, + }, + '480p_1mbps.mp4': { + 'width': 852, + 'height': 480, + }, + } + def _real_extract(self, url): video_id = self._match_id(url) @@ -95,6 +110,20 @@ class CrackleIE(InfoExtractor): elif ext == 'mpd': formats.extend(self._extract_mpd_formats( format_url, video_id, mpd_id='dash', fatal=False)) + elif format_url.endswith('.ism/Manifest'): + formats.extend(self._extract_ism_formats( + format_url, video_id, ism_id='mss', fatal=False)) + else: + mfs_path = e.get('Type') + mfs_info = self._MEDIA_FILE_SLOTS.get(mfs_path) + if not mfs_info: + continue + formats.append({ + 'url': format_url, + 'format_id': 'http-' + mfs_path.split('.')[0], + 'width': mfs_info['width'], + 'height': mfs_info['height'], + }) self._sort_formats(formats) description = media.get('Description') diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index af786d096..5e2cbe41d 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re import json +import xml.etree.ElementTree as etree import zlib from hashlib import sha1 @@ -45,7 +46,7 @@ class CrunchyrollBaseIE(InfoExtractor): data['req'] = 'RpcApi' + method data = compat_urllib_parse_urlencode(data).encode('utf-8') return self._download_xml( - 'http://www.crunchyroll.com/xml/', + 'https://www.crunchyroll.com/xml/', video_id, note, fatal=False, data=data, headers={ 'Content-Type': 'application/x-www-form-urlencoded', }) @@ -143,7 +144,7 @@ class CrunchyrollBaseIE(InfoExtractor): class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): IE_NAME = 'crunchyroll' - _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'info_dict': { @@ -268,6 +269,9 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): }, { 'url': 'http://www.crunchyroll.com/media-723735', 'only_matching': True, + }, { + 'url': 'https://www.crunchyroll.com/en-gb/mob-psycho-100/episode-2-urban-legends-encountering-rumors-780921', + 'only_matching': True, }] _FORMAT_IDS = { @@ -398,7 +402,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'Downloading subtitles for ' + sub_name, data={ 'subtitle_script_id': sub_id, }) - if sub_doc is None: + if not isinstance(sub_doc, etree.Element): continue sid = sub_doc.get('id') iv = xpath_text(sub_doc, 'iv', 'subtitle iv') @@ -515,7 +519,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_quality': stream_quality, 'current_page': url, }) - if streamdata is not None: + if isinstance(streamdata, etree.Element): stream_info = streamdata.find('./{default}preload/stream_info') if stream_info is not None: stream_infos.append(stream_info) @@ -526,7 +530,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_format': stream_format, 'video_encode_quality': stream_quality, }) - if stream_info is not None: + if isinstance(stream_info, etree.Element): stream_infos.append(stream_info) for stream_info in stream_infos: video_encode_id = xpath_text(stream_info, './video_encode_id') @@ -598,10 +602,22 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text series = self._html_search_regex( r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d', webpage, 'series', fatal=False) - season = xpath_text(metadata, 'series_title') - episode = xpath_text(metadata, 'episode_title') or media_metadata.get('title') - episode_number = int_or_none(xpath_text(metadata, 'episode_number') or media_metadata.get('episode_number')) + season = episode = episode_number = duration = thumbnail = None + + if isinstance(metadata, etree.Element): + season = xpath_text(metadata, 'series_title') + episode = xpath_text(metadata, 'episode_title') + episode_number = int_or_none(xpath_text(metadata, 'episode_number')) + duration = float_or_none(media_metadata.get('duration'), 1000) + thumbnail = xpath_text(metadata, 'episode_image_url') + + if not episode: + episode = media_metadata.get('title') + if not episode_number: + episode_number = int_or_none(media_metadata.get('episode_number')) + if not thumbnail: + thumbnail = media_metadata.get('thumbnail', {}).get('url') season_number = int_or_none(self._search_regex( r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)', @@ -611,8 +627,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'id': video_id, 'title': video_title, 'description': video_description, - 'duration': float_or_none(media_metadata.get('duration'), 1000), - 'thumbnail': xpath_text(metadata, 'episode_image_url') or media_metadata.get('thumbnail', {}).get('url'), + 'duration': duration, + 'thumbnail': thumbnail, 'uploader': video_uploader, 'upload_date': video_upload_date, 'series': series, diff --git a/youtube_dl/extractor/curiositystream.py b/youtube_dl/extractor/curiositystream.py index 35b1e7a34..e4a7fca6c 100644 --- a/youtube_dl/extractor/curiositystream.py +++ b/youtube_dl/extractor/curiositystream.py @@ -46,8 +46,24 @@ class CuriosityStreamBaseIE(InfoExtractor): self._handle_errors(result) self._auth_token = result['message']['auth_token'] - def _extract_media_info(self, media): - video_id = compat_str(media['id']) + +class CuriosityStreamIE(CuriosityStreamBaseIE): + IE_NAME = 'curiositystream' + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)' + _TEST = { + 'url': 'https://app.curiositystream.com/video/2', + 'md5': '262bb2f257ff301115f1973540de8983', + 'info_dict': { + 'id': '2', + 'ext': 'mp4', + 'title': 'How Did You Develop The Internet?', + 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + media = self._call_api('media/' + video_id, video_id) title = media['title'] formats = [] @@ -114,38 +130,21 @@ class CuriosityStreamBaseIE(InfoExtractor): } -class CuriosityStreamIE(CuriosityStreamBaseIE): - IE_NAME = 'curiositystream' - _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)' - _TEST = { - 'url': 'https://app.curiositystream.com/video/2', - 'md5': '262bb2f257ff301115f1973540de8983', - 'info_dict': { - 'id': '2', - 'ext': 'mp4', - 'title': 'How Did You Develop The Internet?', - 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - media = self._call_api('media/' + video_id, video_id) - return self._extract_media_info(media) - - class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): IE_NAME = 'curiositystream:collection' - _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P<id>\d+)' + _TESTS = [{ 'url': 'https://app.curiositystream.com/collection/2', 'info_dict': { 'id': '2', 'title': 'Curious Minds: The Internet', 'description': 'How is the internet shaping our lives in the 21st Century?', }, - 'playlist_mincount': 12, - } + 'playlist_mincount': 17, + }, { + 'url': 'https://curiositystream.com/series/2', + 'only_matching': True, + }] def _real_extract(self, url): collection_id = self._match_id(url) @@ -153,7 +152,10 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): 'collections/' + collection_id, collection_id) entries = [] for media in collection.get('media', []): - entries.append(self._extract_media_info(media)) + media_id = compat_str(media.get('id')) + entries.append(self.url_result( + 'https://curiositystream.com/video/' + media_id, + CuriosityStreamIE.ie_key(), media_id)) return self.playlist_result( entries, collection_id, collection.get('title'), collection.get('description')) diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py index 224a1fb5d..f9bd535f6 100644 --- a/youtube_dl/extractor/cwtv.py +++ b/youtube_dl/extractor/cwtv.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + ExtractorError, int_or_none, parse_age_limit, parse_iso8601, @@ -66,9 +67,12 @@ class CWTVIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_json( + data = self._download_json( 'http://images.cwtv.com/feed/mobileapp/video-meta/apiversion_8/guid_' + video_id, - video_id)['video'] + video_id) + if data.get('result') != 'ok': + raise ExtractorError(data['msg'], expected=True) + video_data = data['video'] title = video_data['title'] mpx_url = video_data.get('mpx_url') or 'http://link.theplatform.com/s/cwtv/media/guid/2703454149/%s?formats=M3U' % video_id diff --git a/youtube_dl/extractor/dailymail.py b/youtube_dl/extractor/dailymail.py index af3978035..4f75a2a30 100644 --- a/youtube_dl/extractor/dailymail.py +++ b/youtube_dl/extractor/dailymail.py @@ -49,6 +49,9 @@ class DailyMailIE(InfoExtractor): 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id) video_sources = self._download_json(sources_url, video_id) + body = video_sources.get('body') + if body: + video_sources = body formats = [] for rendition in video_sources['renditions']: diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 040f0bd02..1816c559e 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -22,7 +22,10 @@ from ..utils import ( parse_iso8601, sanitized_Request, str_to_int, + try_get, unescapeHTML, + update_url_query, + url_or_none, urlencode_postdata, ) @@ -171,10 +174,25 @@ class DailymotionIE(DailymotionBaseInfoExtractor): r'__PLAYER_CONFIG__\s*=\s*({.+?});'], webpage, 'player v5', default=None) if player_v5: - player = self._parse_json(player_v5, video_id) - metadata = player['metadata'] + player = self._parse_json(player_v5, video_id, fatal=False) or {} + metadata = try_get(player, lambda x: x['metadata'], dict) + if not metadata: + metadata_url = url_or_none(try_get( + player, lambda x: x['context']['metadata_template_url1'])) + if metadata_url: + metadata_url = metadata_url.replace(':videoId', video_id) + else: + metadata_url = update_url_query( + 'https://www.dailymotion.com/player/metadata/video/%s' + % video_id, { + 'embedder': url, + 'integration': 'inline', + 'GK_PV5_NEON': '1', + }) + metadata = self._download_json( + metadata_url, video_id, 'Downloading metadata JSON') - if metadata.get('error', {}).get('type') == 'password_protected': + if try_get(metadata, lambda x: x['error']['type']) == 'password_protected': password = self._downloader.params.get('videopassword') if password: r = int(metadata['id'][1:], 36) diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 3589bd428..b70c307a7 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -17,16 +17,29 @@ from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site> - discovery| - investigationdiscovery| - discoverylife| - animalplanet| - ahctv| - destinationamerica| - sciencechannel| - tlc| - velocity + _VALID_URL = r'''(?x)https?:// + (?P<site> + (?:www\.)? + (?: + discovery| + investigationdiscovery| + discoverylife| + animalplanet| + ahctv| + destinationamerica| + sciencechannel| + tlc| + velocity + )| + watch\. + (?: + hgtv| + foodnetwork| + travelchannel| + diynetwork| + cookingchanneltv| + motortrend + ) )\.com(?P<path>/tv-shows/[^/]+/(?:video|full-episode)s/(?P<id>[^./?#]+))''' _TESTS = [{ 'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley', @@ -71,7 +84,7 @@ class DiscoveryIE(DiscoveryGoBaseIE): if not access_token: access_token = self._download_json( - 'https://www.%s.com/anonymous' % site, display_id, query={ + 'https://%s.com/anonymous' % site, display_id, query={ 'authRel': 'authorization', 'client_id': try_get( react_data, lambda x: x['application']['apiClientId'], @@ -81,11 +94,12 @@ class DiscoveryIE(DiscoveryGoBaseIE): })['access_token'] try: + headers = self.geo_verification_headers() + headers['Authorization'] = 'Bearer ' + access_token + stream = self._download_json( 'https://api.discovery.com/v1/streaming/video/' + video_id, - display_id, headers={ - 'Authorization': 'Bearer ' + access_token, - }) + display_id, headers=headers) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403): e_description = self._parse_json( diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index f757745ba..8d63ca433 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -77,10 +77,9 @@ class DRTVIE(InfoExtractor): r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'), webpage, 'video id') - programcard = self._download_json( - 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, - video_id, 'Downloading video JSON') - data = programcard['Data'][0] + data = self._download_json( + 'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id, + video_id, 'Downloading video JSON', query={'expanded': 'true'}) title = remove_end(self._og_search_title( webpage, default=None), ' | TV | DR') or data['Title'] @@ -97,7 +96,7 @@ class DRTVIE(InfoExtractor): formats = [] subtitles = {} - for asset in data['Assets']: + for asset in [data['PrimaryAsset']]: kind = asset.get('Kind') if kind == 'Image': thumbnail = asset.get('Uri') diff --git a/youtube_dl/extractor/dtube.py b/youtube_dl/extractor/dtube.py index 5887887e1..114d2dbe3 100644 --- a/youtube_dl/extractor/dtube.py +++ b/youtube_dl/extractor/dtube.py @@ -15,16 +15,16 @@ from ..utils import ( class DTubeIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?d\.tube/(?:#!/)?v/(?P<uploader_id>[0-9a-z.-]+)/(?P<id>[0-9a-z]{8})' _TEST = { - 'url': 'https://d.tube/#!/v/benswann/zqd630em', - 'md5': 'a03eaa186618ffa7a3145945543a251e', + 'url': 'https://d.tube/#!/v/broncnutz/x380jtr1', + 'md5': '9f29088fa08d699a7565ee983f56a06e', 'info_dict': { - 'id': 'zqd630em', + 'id': 'x380jtr1', 'ext': 'mp4', - 'title': 'Reality Check: FDA\'s Disinformation Campaign on Kratom', - 'description': 'md5:700d164e066b87f9eac057949e4227c2', - 'uploader_id': 'benswann', - 'upload_date': '20180222', - 'timestamp': 1519328958, + 'title': 'Lefty 3-Rings is Back Baby!! NCAA Picks', + 'description': 'md5:60be222088183be3a42f196f34235776', + 'uploader_id': 'broncnutz', + 'upload_date': '20190107', + 'timestamp': 1546854054, }, 'params': { 'format': '480p', @@ -48,7 +48,7 @@ class DTubeIE(InfoExtractor): def canonical_url(h): if not h: return None - return 'https://ipfs.io/ipfs/' + h + return 'https://video.dtube.top/ipfs/' + h formats = [] for q in ('240', '480', '720', '1080', ''): diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 464c8d690..322205b62 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -88,11 +88,7 @@ from .awaan import ( AWAANLiveIE, AWAANSeasonIE, ) -from .azmedien import ( - AZMedienIE, - AZMedienPlaylistIE, - AZMedienShowPlaylistIE, -) +from .azmedien import AZMedienIE from .baidu import BaiduVideoIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE @@ -198,6 +194,10 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE +from .ciscolive import ( + CiscoLiveSessionIE, + CiscoLiveSearchIE, +) from .cjsw import CJSWIE from .cliphunter import CliphunterIE from .clippit import ClippitIE @@ -209,7 +209,10 @@ from .cloudy import CloudyIE from .clubic import ClubicIE from .clyp import ClypIE from .cmt import CMTIE -from .cnbc import CNBCIE +from .cnbc import ( + CNBCIE, + CNBCVideoIE, +) from .cnn import ( CNNIE, CNNBlogsIE, @@ -408,6 +411,7 @@ from .funk import ( from .funnyordie import FunnyOrDieIE from .fusion import FusionIE from .fxnetworks import FXNetworksIE +from .gaia import GaiaIE from .gameinformer import GameInformerIE from .gameone import ( GameOneIE, @@ -448,6 +452,7 @@ from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE from .hgtv import HGTVComShowIE +from .hketv import HKETVIE from .hidive import HiDiveIE from .historicfilms import HistoricFilmsIE from .hitbox import HitboxIE, HitboxLiveIE @@ -466,6 +471,10 @@ from .hrti import ( ) from .huajiao import HuajiaoIE from .huffpost import HuffPostIE +from .hungama import ( + HungamaIE, + HungamaSongIE, +) from .hypem import HypemIE from .iconosquare import IconosquareIE from .ign import ( @@ -480,12 +489,18 @@ from .imdb import ( from .imgur import ( ImgurIE, ImgurAlbumIE, + ImgurGalleryIE, ) from .ina import InaIE from .inc import IncIE from .indavideo import IndavideoEmbedIE from .infoq import InfoQIE -from .instagram import InstagramIE, InstagramUserIE +from .instagram import ( + InstagramIE, + InstagramSavedIE, + InstagramUserIE, + InstagramTagIE, +) from .internazionale import InternazionaleIE from .internetvideoarchive import InternetVideoArchiveIE from .iprima import IPrimaIE @@ -540,6 +555,7 @@ from .la7 import LA7IE from .laola1tv import ( Laola1TvEmbedIE, Laola1TvIE, + EHFTVIE, ITTFIE, ) from .lci import LCIIE @@ -549,6 +565,11 @@ from .lcp import ( ) from .learnr import LearnrIE from .lecture2go import Lecture2GoIE +from .lecturio import ( + LecturioIE, + LecturioCourseIE, + LecturioDeCourseIE, +) from .leeco import ( LeIE, LePlaylistIE, @@ -569,6 +590,10 @@ from .limelight import ( LimelightChannelListIE, ) from .line import LineTVIE +from .linkedin import ( + LinkedInLearningIE, + LinkedInLearningCourseIE, +) from .litv import LiTVIE from .liveleak import ( LiveLeakIE, @@ -668,11 +693,7 @@ from .myvi import ( MyviEmbedIE, ) from .myvidster import MyVidsterIE -from .nationalgeographic import ( - NationalGeographicVideoIE, - NationalGeographicIE, - NationalGeographicEpisodeGuideIE, -) +from .nationalgeographic import NationalGeographicVideoIE from .naver import NaverIE from .nba import NBAIE from .nbc import ( @@ -814,6 +835,7 @@ from .orf import ( ORFOE1IE, ORFIPTVIE, ) +from .outsidetv import OutsideTVIE from .packtpub import ( PacktPubIE, PacktPubCourseIE, @@ -842,6 +864,7 @@ from .piksel import PikselIE from .pinkbike import PinkbikeIE from .pladform import PladformIE from .playfm import PlayFMIE +from .playplustv import PlayPlusTVIE from .plays import PlaysTVIE from .playtvak import PlaytvakIE from .playvid import PlayvidIE @@ -1043,7 +1066,7 @@ from .spike import ( ) from .stitcher import StitcherIE from .sport5 import Sport5IE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .sportdeutschland import SportDeutschlandIE from .springboardplatform import SpringboardPlatformIE from .sprout import SproutIE @@ -1078,6 +1101,10 @@ from .tass import TassIE from .tastytrade import TastyTradeIE from .tbs import TBSIE from .tdslifeway import TDSLifewayIE +from .teachable import ( + TeachableIE, + TeachableCourseIE, +) from .teachertube import ( TeacherTubeIE, TeacherTubeUserIE, @@ -1116,6 +1143,10 @@ from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE from .threeqsdn import ThreeQSDNIE +from .tiktok import ( + TikTokIE, + TikTokUserIE, +) from .tinypic import TinyPicIE from .tmz import ( TMZIE, @@ -1153,7 +1184,6 @@ from .tv2 import ( TV2ArticleIE, ) from .tv2hu import TV2HuIE -from .tv3 import TV3IE from .tv4 import TV4IE from .tv5mondeplus import TV5MondePlusIE from .tva import TVAIE @@ -1172,7 +1202,9 @@ from .tvnet import TVNetIE from .tvnoe import TVNoeIE from .tvnow import ( TVNowIE, - TVNowListIE, + TVNowNewIE, + TVNowSeasonIE, + TVNowAnnualIE, TVNowShowIE, ) from .tvp import ( @@ -1190,6 +1222,7 @@ from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE from .twentymin import TwentyMinutenIE from .twentythreevideo import TwentyThreeVideoIE +from .twitcasting import TwitCastingIE from .twitch import ( TwitchVideoIE, TwitchChapterIE, @@ -1223,10 +1256,6 @@ from .uplynk import ( UplynkIE, UplynkPreplayIE, ) -from .upskill import ( - UpskillIE, - UpskillCourseIE, -) from .urort import UrortIE from .urplay import URPlayIE from .usanetwork import USANetworkIE @@ -1295,6 +1324,7 @@ from .vimeo import ( VimeoReviewIE, VimeoUserIE, VimeoWatchLaterIE, + VHXEmbedIE, ) from .vimple import VimpleIE from .vine import ( @@ -1367,7 +1397,7 @@ from .webofstories import ( WebOfStoriesPlaylistIE, ) from .weibo import ( - WeiboIE, + WeiboIE, WeiboMobileIE ) from .weiqitv import WeiqiTVIE @@ -1382,6 +1412,7 @@ from .wsj import ( WSJIE, WSJArticleIE, ) +from .wwe import WWEIE from .xbef import XBefIE from .xboxclips import XboxClipsIE from .xfileshare import XFileShareIE @@ -1474,3 +1505,4 @@ from .zattoo import ( ) from .zdf import ZDFIE, ZDFChannelIE from .zingmp3 import ZingMp3IE +from .zype import ZypeIE diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 97cfe0fc3..74954049d 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -57,7 +57,7 @@ class FacebookIE(InfoExtractor): _CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36' _VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s' - _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true' + _VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true&payloadtype=primary' _TESTS = [{ 'url': 'https://www.facebook.com/video.php?v=637842556329505&fref=nf', diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 11d6c9c32..b1c91f095 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -1,11 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals +# import json +# import uuid + from .adobepass import AdobePassIE -from .uplynk import UplynkPreplayIE -from ..compat import compat_str from ..utils import ( - HEADRequest, int_or_none, parse_age_limit, parse_duration, @@ -16,7 +16,7 @@ from ..utils import ( class FOXIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)' + _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)' _TESTS = [{ # clip 'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/', @@ -43,41 +43,47 @@ class FOXIE(AdobePassIE): # episode, geo-restricted, tv provided required 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', 'only_matching': True, + }, { + 'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/', + 'only_matching': True, }] + # _access_token = None + + # def _call_api(self, path, video_id, data=None): + # headers = { + # 'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd', + # } + # if self._access_token: + # headers['Authorization'] = 'Bearer ' + self._access_token + # return self._download_json( + # 'https://api2.fox.com/v2.0/' + path, video_id, data=data, headers=headers) + + # def _real_initialize(self): + # self._access_token = self._call_api( + # 'login', None, json.dumps({ + # 'deviceId': compat_str(uuid.uuid4()), + # }).encode())['accessToken'] def _real_extract(self, url): video_id = self._match_id(url) video = self._download_json( - 'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id, + 'https://api.fox.com/fbc-content/v1_5/video/%s' % video_id, video_id, headers={ 'apikey': 'abdcbed02c124d393b39e818a4312055', 'Content-Type': 'application/json', 'Referer': url, }) + # video = self._call_api('vodplayer/' + video_id, video_id) title = video['name'] release_url = video['videoRelease']['url'] - - description = video.get('description') - duration = int_or_none(video.get('durationInSeconds')) or int_or_none( - video.get('duration')) or parse_duration(video.get('duration')) - timestamp = unified_timestamp(video.get('datePublished')) - rating = video.get('contentRating') - age_limit = parse_age_limit(rating) + # release_url = video['url'] data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} - creator = data.get('brand') or data.get('network') or video.get('network') - - series = video.get('seriesName') or data.get( - 'seriesName') or data.get('show') - season_number = int_or_none(video.get('seasonNumber')) - episode = video.get('name') - episode_number = int_or_none(video.get('episodeNumber')) - release_year = int_or_none(video.get('releaseYear')) - + rating = video.get('contentRating') if data.get('authRequired'): resource = self._get_mvpd_resource( 'fbc-fox', title, video.get('guid'), rating) @@ -86,6 +92,18 @@ class FOXIE(AdobePassIE): 'auth': self._extract_mvpd_auth( url, video_id, 'fbc-fox', resource) }) + m3u8_url = self._download_json(release_url, video_id)['playURL'] + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + self._sort_formats(formats) + + duration = int_or_none(video.get('durationInSeconds')) or int_or_none( + video.get('duration')) or parse_duration(video.get('duration')) + timestamp = unified_timestamp(video.get('datePublished')) + creator = data.get('brand') or data.get('network') or video.get('network') + series = video.get('seriesName') or data.get( + 'seriesName') or data.get('show') subtitles = {} for doc_rel in video.get('documentReleases', []): @@ -98,36 +116,19 @@ class FOXIE(AdobePassIE): }] break - info = { + return { 'id': video_id, 'title': title, - 'description': description, + 'formats': formats, + 'description': video.get('description'), 'duration': duration, 'timestamp': timestamp, - 'age_limit': age_limit, + 'age_limit': parse_age_limit(rating), 'creator': creator, 'series': series, - 'season_number': season_number, - 'episode': episode, - 'episode_number': episode_number, - 'release_year': release_year, + 'season_number': int_or_none(video.get('seasonNumber')), + 'episode': video.get('name'), + 'episode_number': int_or_none(video.get('episodeNumber')), + 'release_year': int_or_none(video.get('releaseYear')), 'subtitles': subtitles, } - - urlh = self._request_webpage(HEADRequest(release_url), video_id) - video_url = compat_str(urlh.geturl()) - - if UplynkPreplayIE.suitable(video_url): - info.update({ - '_type': 'url_transparent', - 'url': video_url, - 'ie_key': UplynkPreplayIE.ie_key(), - }) - else: - m3u8_url = self._download_json(release_url, video_id)['playURL'] - formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls') - self._sort_formats(formats) - info['formats'] = formats - return info diff --git a/youtube_dl/extractor/foxsports.py b/youtube_dl/extractor/foxsports.py index 985542727..2b2cb6c6f 100644 --- a/youtube_dl/extractor/foxsports.py +++ b/youtube_dl/extractor/foxsports.py @@ -1,43 +1,33 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - smuggle_url, - update_url_query, -) class FoxSportsIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*video/(?P<id>\d+)' _TEST = { 'url': 'http://www.foxsports.com/tennessee/video/432609859715', 'md5': 'b49050e955bebe32c301972e4012ac17', 'info_dict': { - 'id': 'bwduI3X_TgUB', + 'id': '432609859715', 'ext': 'mp4', 'title': 'Courtney Lee on going up 2-0 in series vs. Blazers', 'description': 'Courtney Lee talks about Memphis being focused.', - 'upload_date': '20150423', - 'timestamp': 1429761109, + # TODO: fix timestamp + 'upload_date': '19700101', # '20150423', + # 'timestamp': 1429761109, 'uploader': 'NEWA-FNG-FOXSPORTS', }, + 'params': { + # m3u8 download + 'skip_download': True, + }, 'add_ie': ['ThePlatform'], } def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - config = self._parse_json( - self._html_search_regex( - r"""class="[^"]*(?:fs-player|platformPlayer-wrapper)[^"]*".+?data-player-config='([^']+)'""", - webpage, 'data player config'), - video_id) - - return self.url_result(smuggle_url(update_url_query( - config['releaseURL'], { - 'mbr': 'true', - 'switch': 'http', - }), {'force_smil_url': True})) + return self.url_result( + 'https://feed.theplatform.com/f/BKQ29B/foxsports-all?byId=' + video_id, 'ThePlatformFeed') diff --git a/youtube_dl/extractor/freespeech.py b/youtube_dl/extractor/freespeech.py index 486a49c05..ea9c3e317 100644 --- a/youtube_dl/extractor/freespeech.py +++ b/youtube_dl/extractor/freespeech.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from .youtube import YoutubeIE class FreespeechIE(InfoExtractor): @@ -27,8 +28,4 @@ class FreespeechIE(InfoExtractor): r'data-video-url="([^"]+)"', webpage, 'youtube url') - return { - '_type': 'url', - 'url': youtube_url, - 'ie_key': 'Youtube', - } + return self.url_result(youtube_url, YoutubeIE.ie_key()) diff --git a/youtube_dl/extractor/funimation.py b/youtube_dl/extractor/funimation.py index 07d01caec..8bbedca26 100644 --- a/youtube_dl/extractor/funimation.py +++ b/youtube_dl/extractor/funimation.py @@ -1,6 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals +import random +import string + from .common import InfoExtractor from ..compat import compat_HTTPError from ..utils import ( @@ -87,7 +90,7 @@ class FunimationIE(InfoExtractor): video_id = title_data.get('id') or self._search_regex([ r"KANE_customdimensions.videoID\s*=\s*'(\d+)';", - r'<iframe[^>]+src="/player/(\d+)"', + r'<iframe[^>]+src="/player/(\d+)', ], webpage, 'video_id', default=None) if not video_id: player_url = self._html_search_meta([ @@ -108,8 +111,10 @@ class FunimationIE(InfoExtractor): if self._TOKEN: headers['Authorization'] = 'Token %s' % self._TOKEN sources = self._download_json( - 'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id, - video_id, headers=headers)['items'] + 'https://www.funimation.com/api/showexperience/%s/' % video_id, + video_id, headers=headers, query={ + 'pinst_id': ''.join([random.choice(string.digits + string.ascii_letters) for _ in range(8)]), + })['items'] except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: error = self._parse_json(e.cause.read(), video_id)['errors'][0] diff --git a/youtube_dl/extractor/gaia.py b/youtube_dl/extractor/gaia.py new file mode 100644 index 000000000..f2eef3f4c --- /dev/null +++ b/youtube_dl/extractor/gaia.py @@ -0,0 +1,98 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + str_or_none, + strip_or_none, + try_get, +) + + +class GaiaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gaia\.com/video/(?P<id>[^/?]+).*?\bfullplayer=(?P<type>feature|preview)' + _TESTS = [{ + 'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=feature', + 'info_dict': { + 'id': '89356', + 'ext': 'mp4', + 'title': 'Connecting with Universal Consciousness', + 'description': 'md5:844e209ad31b7d31345f5ed689e3df6f', + 'upload_date': '20151116', + 'timestamp': 1447707266, + 'duration': 936, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://www.gaia.com/video/connecting-universal-consciousness?fullplayer=preview', + 'info_dict': { + 'id': '89351', + 'ext': 'mp4', + 'title': 'Connecting with Universal Consciousness', + 'description': 'md5:844e209ad31b7d31345f5ed689e3df6f', + 'upload_date': '20151116', + 'timestamp': 1447707266, + 'duration': 53, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + display_id, vtype = re.search(self._VALID_URL, url).groups() + node_id = self._download_json( + 'https://brooklyn.gaia.com/pathinfo', display_id, query={ + 'path': 'video/' + display_id, + })['id'] + node = self._download_json( + 'https://brooklyn.gaia.com/node/%d' % node_id, node_id) + vdata = node[vtype] + media_id = compat_str(vdata['nid']) + title = node['title'] + + media = self._download_json( + 'https://brooklyn.gaia.com/media/' + media_id, media_id) + formats = self._extract_m3u8_formats( + media['mediaUrls']['bcHLS'], media_id, 'mp4') + self._sort_formats(formats) + + subtitles = {} + text_tracks = media.get('textTracks', {}) + for key in ('captions', 'subtitles'): + for lang, sub_url in text_tracks.get(key, {}).items(): + subtitles.setdefault(lang, []).append({ + 'url': sub_url, + }) + + fivestar = node.get('fivestar', {}) + fields = node.get('fields', {}) + + def get_field_value(key, value_key='value'): + return try_get(fields, lambda x: x[key][0][value_key]) + + return { + 'id': media_id, + 'display_id': display_id, + 'title': title, + 'formats': formats, + 'description': strip_or_none(get_field_value('body') or get_field_value('teaser')), + 'timestamp': int_or_none(node.get('created')), + 'subtitles': subtitles, + 'duration': int_or_none(vdata.get('duration')), + 'like_count': int_or_none(try_get(fivestar, lambda x: x['up_count']['value'])), + 'dislike_count': int_or_none(try_get(fivestar, lambda x: x['down_count']['value'])), + 'comment_count': int_or_none(node.get('comment_count')), + 'series': try_get(node, lambda x: x['series']['title'], compat_str), + 'season_number': int_or_none(get_field_value('season')), + 'season_id': str_or_none(get_field_value('series_nid', 'nid')), + 'episode_number': int_or_none(get_field_value('episode')), + } diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index ab647dd41..4236a5ed8 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -14,7 +14,7 @@ from ..utils import ( class GameSpotIE(OnceIE): - _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -41,6 +41,9 @@ class GameSpotIE(OnceIE): }, { 'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/', 'only_matching': True, + }, { + 'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 76ef01332..067de28cd 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -47,7 +47,7 @@ from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .tvc import TVCIE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .smotri import SmotriIE from .myvi import MyviIE from .condenast import CondeNastIE @@ -109,11 +109,13 @@ from .vice import ViceIE from .xfileshare import XFileShareIE from .cloudflarestream import CloudflareStreamIE from .peertube import PeerTubeIE +from .teachable import TeachableIE from .indavideo import IndavideoEmbedIE from .apa import APAIE from .foxnews import FoxNewsIE from .viqeo import ViqeoIE from .expressen import ExpressenIE +from .zype import ZypeIE class GenericIE(InfoExtractor): @@ -2070,6 +2072,20 @@ class GenericIE(InfoExtractor): }, 'playlist_count': 6, }, + { + # Zype embed + 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + 'ext': 'mp4', + 'title': 'Smoky Barbecue Favorites', + 'thumbnail': r're:^https?://.*\.jpe?g', + }, + 'add_ie': [ZypeIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, { # videojs embed 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', @@ -2181,10 +2197,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): if url.startswith('//'): - return { - '_type': 'url', - 'url': self.http_scheme() + url, - } + return self.url_result(self.http_scheme() + url) parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: @@ -2636,9 +2649,9 @@ class GenericIE(InfoExtractor): return self.url_result(tvc_url, 'TVC') # Look for embedded SportBox player - sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) + sportbox_urls = SportBoxIE._extract_urls(webpage) if sportbox_urls: - return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed') + return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key()) # Look for embedded XHamster player xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) @@ -3023,7 +3036,7 @@ class GenericIE(InfoExtractor): wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key()) # Look for Mediaset embeds - mediaset_urls = MediasetIE._extract_urls(webpage) + mediaset_urls = MediasetIE._extract_urls(self, webpage) if mediaset_urls: return self.playlist_from_matches( mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key()) @@ -3097,6 +3110,10 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) if indavideo_urls: return self.playlist_from_matches( @@ -3129,6 +3146,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + zype_urls = ZypeIE._extract_urls(webpage) + if zype_urls: + return self.playlist_from_matches( + zype_urls, video_id, video_title, ie=ZypeIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: diff --git a/youtube_dl/extractor/gfycat.py b/youtube_dl/extractor/gfycat.py index a0670b645..c1b36a59b 100644 --- a/youtube_dl/extractor/gfycat.py +++ b/youtube_dl/extractor/gfycat.py @@ -53,7 +53,7 @@ class GfycatIE(InfoExtractor): video_id = self._match_id(url) gfy = self._download_json( - 'http://gfycat.com/cajax/get/%s' % video_id, + 'https://api.gfycat.com/v1/gfycats/%s' % video_id, video_id, 'Downloading video info') if 'error' in gfy: raise ExtractorError('Gfycat said: ' + gfy['error'], expected=True) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index c2140c362..fb8f7679b 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -72,7 +72,7 @@ class GloboIE(InfoExtractor): return try: - self._download_json( + glb_id = (self._download_json( 'https://login.globo.com/api/authentication', None, data=json.dumps({ 'payload': { 'email': email, @@ -81,7 +81,9 @@ class GloboIE(InfoExtractor): }, }).encode(), headers={ 'Content-Type': 'application/json; charset=utf-8', - }) + }) or {}).get('glbId') + if glb_id: + self._set_cookie('.globo.com', 'GLBID', glb_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: resp = self._parse_json(e.cause.read(), None) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index ec9dd6e3a..206d89e82 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -25,15 +25,15 @@ class GoIE(AdobePassIE): }, 'watchdisneychannel': { 'brand': '004', - 'requestor_id': 'Disney', + 'resource_id': 'Disney', }, 'watchdisneyjunior': { 'brand': '008', - 'requestor_id': 'DisneyJunior', + 'resource_id': 'DisneyJunior', }, 'watchdisneyxd': { 'brand': '009', - 'requestor_id': 'DisneyXD', + 'resource_id': 'DisneyXD', } } _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\ @@ -130,8 +130,8 @@ class GoIE(AdobePassIE): 'device': '001', } if video_data.get('accesslevel') == '1': - requestor_id = site_info['requestor_id'] - resource = self._get_mvpd_resource( + requestor_id = site_info.get('requestor_id', 'DisneyChannels') + resource = site_info.get('resource_id') or self._get_mvpd_resource( requestor_id, title, video_id, None) auth = self._extract_mvpd_auth( url, video_id, requestor_id, resource) diff --git a/youtube_dl/extractor/hketv.py b/youtube_dl/extractor/hketv.py new file mode 100644 index 000000000..b57927fc1 --- /dev/null +++ b/youtube_dl/extractor/hketv.py @@ -0,0 +1,191 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + merge_dicts, + parse_count, + str_or_none, + try_get, + unified_strdate, + urlencode_postdata, + urljoin, +) + + +class HKETVIE(InfoExtractor): + IE_NAME = 'hketv' + IE_DESC = '香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau' + _GEO_BYPASS = False + _GEO_COUNTRIES = ['HK'] + _VALID_URL = r'https?://(?:www\.)?hkedcity\.net/etv/resource/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'https://www.hkedcity.net/etv/resource/2932360618', + 'md5': 'f193712f5f7abb208ddef3c5ea6ed0b7', + 'info_dict': { + 'id': '2932360618', + 'ext': 'mp4', + 'title': '喜閱一生(共享閱讀樂) (中、英文字幕可供選擇)', + 'description': 'md5:d5286d05219ef50e0613311cbe96e560', + 'upload_date': '20181024', + 'duration': 900, + 'subtitles': 'count:2', + }, + 'skip': 'Geo restricted to HK', + }, { + 'url': 'https://www.hkedcity.net/etv/resource/972641418', + 'md5': '1ed494c1c6cf7866a8290edad9b07dc9', + 'info_dict': { + 'id': '972641418', + 'ext': 'mp4', + 'title': '衣冠楚楚 (天使系列之一)', + 'description': 'md5:10bb3d659421e74f58e5db5691627b0f', + 'upload_date': '20070109', + 'duration': 907, + 'subtitles': {}, + }, + 'params': { + 'geo_verification_proxy': '<HK proxy here>', + }, + 'skip': 'Geo restricted to HK', + }] + + _CC_LANGS = { + '中文（繁體中文）': 'zh-Hant', + '中文（简体中文）': 'zh-Hans', + 'English': 'en', + 'Bahasa Indonesia': 'id', + '\u0939\u093f\u0928\u094d\u0926\u0940': 'hi', + '\u0928\u0947\u092a\u093e\u0932\u0940': 'ne', + 'Tagalog': 'tl', + '\u0e44\u0e17\u0e22': 'th', + '\u0627\u0631\u062f\u0648': 'ur', + } + _FORMAT_HEIGHTS = { + 'SD': 360, + 'HD': 720, + } + _APPS_BASE_URL = 'https://apps.hkedcity.net' + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = ( + self._html_search_meta( + ('ed_title', 'search.ed_title'), webpage, default=None) or + self._search_regex( + r'data-favorite_title_(?:eng|chi)=(["\'])(?P<id>(?:(?!\1).)+)\1', + webpage, 'title', default=None, group='url') or + self._html_search_regex( + r'<h1>([^<]+)</h1>', webpage, 'title', default=None) or + self._og_search_title(webpage) + ) + + file_id = self._search_regex( + r'post_var\[["\']file_id["\']\s*\]\s*=\s*(.+?);', + webpage, 'file ID') + curr_url = self._search_regex( + r'post_var\[["\']curr_url["\']\s*\]\s*=\s*"(.+?)";', + webpage, 'curr URL') + data = { + 'action': 'get_info', + 'curr_url': curr_url, + 'file_id': file_id, + 'video_url': file_id, + } + + response = self._download_json( + self._APPS_BASE_URL + '/media/play/handler.php', video_id, + data=urlencode_postdata(data), + headers=merge_dicts({ + 'Content-Type': 'application/x-www-form-urlencoded'}, + self.geo_verification_headers())) + + result = response['result'] + + if not response.get('success') or not response.get('access'): + error = clean_html(response.get('access_err_msg')) + if 'Video streaming is not available in your country' in error: + self.raise_geo_restricted( + msg=error, countries=self._GEO_COUNTRIES) + else: + raise ExtractorError(error, expected=True) + + formats = [] + + width = int_or_none(result.get('width')) + height = int_or_none(result.get('height')) + + playlist0 = result['playlist'][0] + for fmt in playlist0['sources']: + file_url = urljoin(self._APPS_BASE_URL, fmt.get('file')) + if not file_url: + continue + # If we ever wanted to provide the final resolved URL that + # does not require cookies, albeit with a shorter lifespan: + # urlh = self._downloader.urlopen(file_url) + # resolved_url = urlh.geturl() + label = fmt.get('label') + h = self._FORMAT_HEIGHTS.get(label) + w = h * width // height if h and width and height else None + formats.append({ + 'format_id': label, + 'ext': fmt.get('type'), + 'url': file_url, + 'width': w, + 'height': h, + }) + self._sort_formats(formats) + + subtitles = {} + tracks = try_get(playlist0, lambda x: x['tracks'], list) or [] + for track in tracks: + if not isinstance(track, dict): + continue + track_kind = str_or_none(track.get('kind')) + if not track_kind or not isinstance(track_kind, compat_str): + continue + if track_kind.lower() not in ('captions', 'subtitles'): + continue + track_url = urljoin(self._APPS_BASE_URL, track.get('file')) + if not track_url: + continue + track_label = track.get('label') + subtitles.setdefault(self._CC_LANGS.get( + track_label, track_label), []).append({ + 'url': self._proto_relative_url(track_url), + 'ext': 'srt', + }) + + # Likes + emotion = self._download_json( + 'https://emocounter.hkedcity.net/handler.php', video_id, + data=urlencode_postdata({ + 'action': 'get_emotion', + 'data[bucket_id]': 'etv', + 'data[identifier]': video_id, + }), + headers={'Content-Type': 'application/x-www-form-urlencoded'}, + fatal=False) or {} + like_count = int_or_none(try_get( + emotion, lambda x: x['data']['emotion_data'][0]['count'])) + + return { + 'id': video_id, + 'title': title, + 'description': self._html_search_meta( + 'description', webpage, fatal=False), + 'upload_date': unified_strdate(self._html_search_meta( + 'ed_date', webpage, fatal=False), day_first=False), + 'duration': int_or_none(result.get('length')), + 'formats': formats, + 'subtitles': subtitles, + 'thumbnail': urljoin(self._APPS_BASE_URL, result.get('image')), + 'view_count': parse_count(result.get('view_count')), + 'like_count': like_count, + } diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index d28af36ec..8de9c4faf 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -1,49 +1,56 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import hashlib +import hmac +import time from .common import InfoExtractor -from ..compat import compat_str +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, int_or_none, + try_get, ) class HotStarBaseIE(InfoExtractor): - _GEO_COUNTRIES = ['IN'] + _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee' - def _download_json(self, *args, **kwargs): - response = super(HotStarBaseIE, self)._download_json(*args, **kwargs) - if response['resultCode'] != 'OK': - if kwargs.get('fatal'): - raise ExtractorError( - response['errorDescription'], expected=True) - return None - return response['resultObj'] - - def _download_content_info(self, content_id): - return self._download_json( - 'https://account.hotstar.com/AVS/besc', content_id, query={ - 'action': 'GetAggregatedContentDetails', - 'appVersion': '5.0.40', - 'channel': 'PCTV', - 'contentId': content_id, - })['contentInfo'][0] + def _call_api(self, path, video_id, query_name='contentId'): + st = int(time.time()) + exp = st + 6000 + auth = 'st=%d~exp=%d~acl=/*' % (st, exp) + auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest() + response = self._download_json( + 'https://api.hotstar.com/' + path, + video_id, headers={ + 'hotstarauth': auth, + 'x-country-code': 'IN', + 'x-platform-code': 'JIO', + }, query={ + query_name: video_id, + 'tas': 10000, + }) + if response['statusCode'] != 'OK': + raise ExtractorError( + response['body']['message'], expected=True) + return response['body']['results'] class HotStarIE(HotStarBaseIE): + IE_NAME = 'hotstar' _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})' _TESTS = [{ - 'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273', + # contentData + 'url': 'https://www.hotstar.com/can-you-not-spread-rumours/1000076273', 'info_dict': { 'id': '1000076273', 'ext': 'mp4', - 'title': 'On Air With AIB', + 'title': 'Can You Not Spread Rumours?', 'description': 'md5:c957d8868e9bc793ccb813691cc4c434', - 'timestamp': 1447227000, + 'timestamp': 1447248600, 'upload_date': '20151111', 'duration': 381, }, @@ -51,6 +58,10 @@ class HotStarIE(HotStarBaseIE): # m3u8 download 'skip_download': True, } + }, { + # contentDetail + 'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157', + 'only_matching': True, }, { 'url': 'http://www.hotstar.com/sports/cricket/rajitha-sizzles-on-debut-with-329/2001477583', 'only_matching': True, @@ -58,47 +69,52 @@ class HotStarIE(HotStarBaseIE): 'url': 'http://www.hotstar.com/1000000515', 'only_matching': True, }] + _GEO_BYPASS = False def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_content_info(video_id) + webpage = self._download_webpage(url, video_id) + app_state = self._parse_json(self._search_regex( + r'<script>window\.APP_STATE\s*=\s*({.+?})</script>', + webpage, 'app state'), video_id) + video_data = {} + getters = list( + lambda x, k=k: x['initialState']['content%s' % k]['content'] + for k in ('Data', 'Detail') + ) + for v in app_state.values(): + content = try_get(v, getters, dict) + if content and content.get('contentId') == video_id: + video_data = content + break - title = video_data['episodeTitle'] + title = video_data['title'] - if video_data.get('encrypted') == 'Y': + if video_data.get('drmProtected'): raise ExtractorError('This video is DRM protected.', expected=True) formats = [] - for f in ('JIO',): - format_data = self._download_json( - 'http://getcdn.hotstar.com/AVS/besc', - video_id, 'Downloading %s JSON metadata' % f, - fatal=False, query={ - 'action': 'GetCDN', - 'asJson': 'Y', - 'channel': f, - 'id': video_id, - 'type': 'VOD', - }) - if format_data: - format_url = format_data.get('src') - if not format_url: - continue - ext = determine_ext(format_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', - m3u8_id='hls', fatal=False)) - elif ext == 'f4m': - # produce broken files - continue - else: - formats.append({ - 'url': format_url, - 'width': int_or_none(format_data.get('width')), - 'height': int_or_none(format_data.get('height')), - }) + format_data = self._call_api('h/v1/play', video_id)['item'] + format_url = format_data['playbackUrl'] + ext = determine_ext(format_url) + if ext == 'm3u8': + try: + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id='hls')) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + self.raise_geo_restricted(countries=['IN']) + raise + elif ext == 'f4m': + # produce broken files + pass + else: + formats.append({ + 'url': format_url, + 'width': int_or_none(format_data.get('width')), + 'height': int_or_none(format_data.get('height')), + }) self._sort_formats(formats) return { @@ -106,57 +122,43 @@ class HotStarIE(HotStarBaseIE): 'title': title, 'description': video_data.get('description'), 'duration': int_or_none(video_data.get('duration')), - 'timestamp': int_or_none(video_data.get('broadcastDate')), + 'timestamp': int_or_none(video_data.get('broadcastDate') or video_data.get('startDate')), 'formats': formats, + 'channel': video_data.get('channelName'), + 'channel_id': video_data.get('channelId'), + 'series': video_data.get('showName'), + 'season': video_data.get('seasonName'), + 'season_number': int_or_none(video_data.get('seasonNo')), + 'season_id': video_data.get('seasonId'), 'episode': title, - 'episode_number': int_or_none(video_data.get('episodeNumber')), - 'series': video_data.get('contentTitle'), + 'episode_number': int_or_none(video_data.get('episodeNo')), } class HotStarPlaylistIE(HotStarBaseIE): IE_NAME = 'hotstar:playlist' - _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)' _TESTS = [{ - 'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993', + 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26', 'info_dict': { - 'id': '14812', + 'id': '3_2_26', }, - 'playlist_mincount': 75, + 'playlist_mincount': 20, }, { - 'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998', + 'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480', 'only_matching': True, }] - _ITEM_TYPES = { - 'episodes': 'EPISODE', - 'popular-clips': 'CLIPS', - } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - base_url = mobj.group('url') - content_id = mobj.group('content_id') - playlist_type = mobj.group('type') + playlist_id = self._match_id(url) - content_info = self._download_content_info(content_id) - playlist_id = compat_str(content_info['categoryId']) - - collection = self._download_json( - 'https://search.hotstar.com/AVS/besc', playlist_id, query={ - 'action': 'SearchContents', - 'appVersion': '5.0.40', - 'channel': 'PCTV', - 'moreFilters': 'series:%s;' % playlist_id, - 'query': '*', - 'searchOrder': 'last_broadcast_date desc,year desc,title asc', - 'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'), - }) + collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId') entries = [ self.url_result( - '%s/_/%s' % (base_url, video['contentId']), + 'https://www.hotstar.com/%s' % video['contentId'], ie=HotStarIE.ie_key(), video_id=video['contentId']) - for video in collection['response']['docs'] + for video in collection['assets']['items'] if video.get('contentId')] return self.playlist_result(entries, playlist_id) diff --git a/youtube_dl/extractor/hungama.py b/youtube_dl/extractor/hungama.py new file mode 100644 index 000000000..3fdaac5b6 --- /dev/null +++ b/youtube_dl/extractor/hungama.py @@ -0,0 +1,117 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + urlencode_postdata, +) + + +class HungamaIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?hungama\.com/ + (?: + (?:video|movie)/[^/]+/| + tv-show/(?:[^/]+/){2}\d+/episode/[^/]+/ + ) + (?P<id>\d+) + ''' + _TESTS = [{ + 'url': 'http://www.hungama.com/video/krishna-chants/39349649/', + 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', + 'info_dict': { + 'id': '2931166', + 'ext': 'mp4', + 'title': 'Lucky Ali - Kitni Haseen Zindagi', + 'track': 'Kitni Haseen Zindagi', + 'artist': 'Lucky Ali', + 'album': 'Aks', + 'release_year': 2000, + } + }, { + 'url': 'https://www.hungama.com/movie/kahaani-2/44129919/', + 'only_matching': True, + }, { + 'url': 'https://www.hungama.com/tv-show/padded-ki-pushup/season-1/44139461/episode/ep-02-training-sasu-pathlaag-karing/44139503/', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + info = self._search_json_ld(webpage, video_id) + + m3u8_url = self._download_json( + 'https://www.hungama.com/index.php', video_id, + data=urlencode_postdata({'content_id': video_id}), headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + 'X-Requested-With': 'XMLHttpRequest', + }, query={ + 'c': 'common', + 'm': 'get_video_mdn_url', + })['stream_url'] + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + info.update({ + 'id': video_id, + 'formats': formats, + }) + return info + + +class HungamaSongIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?hungama\.com/song/[^/]+/(?P<id>\d+)' + _TEST = { + 'url': 'https://www.hungama.com/song/kitni-haseen-zindagi/2931166/', + 'md5': 'a845a6d1ebd08d80c1035126d49bd6a0', + 'info_dict': { + 'id': '2931166', + 'ext': 'mp4', + 'title': 'Lucky Ali - Kitni Haseen Zindagi', + 'track': 'Kitni Haseen Zindagi', + 'artist': 'Lucky Ali', + 'album': 'Aks', + 'release_year': 2000, + } + } + + def _real_extract(self, url): + audio_id = self._match_id(url) + + data = self._download_json( + 'https://www.hungama.com/audio-player-data/track/%s' % audio_id, + audio_id, query={'_country': 'IN'})[0] + + track = data['song_name'] + artist = data.get('singer_name') + + m3u8_url = self._download_json( + data.get('file') or data['preview_link'], + audio_id)['response']['media_url'] + + formats = self._extract_m3u8_formats( + m3u8_url, audio_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + title = '%s - %s' % (artist, track) if artist else track + thumbnail = data.get('img_src') or data.get('album_image') + + return { + 'id': audio_id, + 'title': title, + 'thumbnail': thumbnail, + 'track': track, + 'artist': artist, + 'album': data.get('album_name'), + 'release_year': int_or_none(data.get('date')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index ecc958a17..0eb54db3f 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -12,7 +12,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P<id>[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -20,28 +20,9 @@ class ImgurIE(InfoExtractor): 'id': 'A61SaA1', 'ext': 'mp4', 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 'Imgur: The magic of the Internet', }, }, { 'url': 'https://imgur.com/A61SaA1', - 'info_dict': { - 'id': 'A61SaA1', - 'ext': 'mp4', - 'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$', - 'description': 'Imgur: The magic of the Internet', - }, - }, { - 'url': 'https://imgur.com/gallery/YcAQlkx', - 'info_dict': { - 'id': 'YcAQlkx', - 'ext': 'mp4', - 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', - } - }, { - 'url': 'http://imgur.com/topic/Funny/N8rOudd', - 'only_matching': True, - }, { - 'url': 'http://imgur.com/r/aww/VQcQPhM', 'only_matching': True, }, { 'url': 'https://i.imgur.com/crGpqCV.mp4', @@ -50,8 +31,8 @@ class ImgurIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - gifv_url = 'https://i.imgur.com/{id}.gifv'.format(id=video_id) - webpage = self._download_webpage(gifv_url, video_id) + webpage = self._download_webpage( + 'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id) width = int_or_none(self._og_search_property( 'video:width', webpage, default=None)) @@ -72,7 +53,6 @@ class ImgurIE(InfoExtractor): 'format_id': m.group('type').partition('/')[2], 'url': self._proto_relative_url(m.group('src')), 'ext': mimetype2ext(m.group('type')), - 'acodec': 'none', 'width': width, 'height': height, 'http_headers': { @@ -107,44 +87,64 @@ class ImgurIE(InfoExtractor): return { 'id': video_id, 'formats': formats, - 'description': self._og_search_description(webpage, default=None), 'title': self._og_search_title(webpage), } -class ImgurAlbumIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:a|gallery|topic/[^/]+)/)?(?P<id>[a-zA-Z0-9]{5})(?:[/?#&]+)?$' +class ImgurGalleryIE(InfoExtractor): + IE_NAME = 'imgur:gallery' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P<id>[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'http://imgur.com/gallery/Q95ko', 'info_dict': { 'id': 'Q95ko', + 'title': 'Adding faces make every GIF better', }, 'playlist_count': 25, }, { - 'url': 'http://imgur.com/a/j6Orj', + 'url': 'http://imgur.com/topic/Aww/ll5Vk', 'only_matching': True, }, { - 'url': 'http://imgur.com/topic/Aww/ll5Vk', + 'url': 'https://imgur.com/gallery/YcAQlkx', + 'info_dict': { + 'id': 'YcAQlkx', + 'ext': 'mp4', + 'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....', + } + }, { + 'url': 'http://imgur.com/topic/Funny/N8rOudd', + 'only_matching': True, + }, { + 'url': 'http://imgur.com/r/aww/VQcQPhM', 'only_matching': True, }] def _real_extract(self, url): - album_id = self._match_id(url) + gallery_id = self._match_id(url) - album_images = self._download_json( - 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, - album_id, fatal=False) + data = self._download_json( + 'https://imgur.com/gallery/%s.json' % gallery_id, + gallery_id)['data']['image'] - if album_images: - data = album_images.get('data') - if data and isinstance(data, dict): - images = data.get('images') - if images and isinstance(images, list): - entries = [ - self.url_result('http://imgur.com/%s' % image['hash']) - for image in images if image.get('hash')] - return self.playlist_result(entries, album_id) + if data.get('is_album'): + entries = [ + self.url_result('http://imgur.com/%s' % image['hash'], ImgurIE.ie_key(), image['hash']) + for image in data['album_images']['images'] if image.get('hash')] + return self.playlist_result(entries, gallery_id, data.get('title'), data.get('description')) - # Fallback to single video - return self.url_result('http://imgur.com/%s' % album_id, ImgurIE.ie_key()) + return self.url_result('http://imgur.com/%s' % gallery_id, ImgurIE.ie_key(), gallery_id) + + +class ImgurAlbumIE(ImgurGalleryIE): + IE_NAME = 'imgur:album' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P<id>[a-zA-Z0-9]+)' + + _TESTS = [{ + 'url': 'http://imgur.com/a/j6Orj', + 'info_dict': { + 'id': 'j6Orj', + 'title': 'A Literary Analysis of "Star Wars: The Force Awakens"', + }, + 'playlist_count': 12, + }] diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index d11fdfc96..25900e692 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -8,7 +8,6 @@ import re from .common import InfoExtractor from ..compat import ( compat_str, - compat_urllib_parse_urlparse, compat_HTTPError, ) from ..utils import ( @@ -228,44 +227,37 @@ class InstagramIE(InfoExtractor): } -class InstagramUserIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:saved/?)(?:$|[?#])' - IE_DESC = 'Instagram user profile' - IE_NAME = 'instagram:user' - _TEST = { - 'url': 'https://instagram.com/porsche', - 'info_dict': { - 'id': 'porsche', - 'title': 'porsche', - }, - 'playlist_count': 5, - 'params': { - 'extract_flat': True, - 'skip_download': True, - 'playlistend': 5, - } - } +class InstagramPlaylistIE(InfoExtractor): + # A superclass for handling any kind of query based on GraphQL which + # results in a playlist. - _gis_tmpl = None + _gis_tmpl = None # used to cache GIS request type - def _entries(self, data): + def _parse_graphql(self, webpage, item_id): + # Reads a webpage and returns its GraphQL data. + return self._parse_json( + self._search_regex( + r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'), + item_id) + + def _extract_graphql(self, data, url): + # Parses GraphQL queries containing videos and generates a playlist. def get_count(suffix): return int_or_none(try_get( node, lambda x: x['edge_media_' + suffix]['count'])) - uploader_id = data['entry_data']['ProfilePage'][0]['graphql']['user']['id'] + uploader_id = self._match_id(url) csrf_token = data['config']['csrf_token'] rhx_gis = data.get('rhx_gis') or '3c7ca9dcefcf966d11dacf1f151335e8' - self._set_cookie('instagram.com', 'ig_pr', '1') - cursor = '' for page_num in itertools.count(1): - variables = json.dumps({ - 'id': uploader_id, + variables = { 'first': 12, 'after': cursor, - }) + } + variables.update(self._query_vars_for(data)) + variables = json.dumps(variables) if self._gis_tmpl: gis_tmpls = [self._gis_tmpl] @@ -277,21 +269,26 @@ class InstagramUserIE(InfoExtractor): '%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']), ] + # try all of the ways to generate a GIS query, and not only use the + # first one that works, but cache it for future requests for gis_tmpl in gis_tmpls: try: - media = self._download_json( + json_data = self._download_json( 'https://www.instagram.com/graphql/query/', uploader_id, 'Downloading JSON page %d' % page_num, headers={ 'X-Requested-With': 'XMLHttpRequest', 'X-Instagram-GIS': hashlib.md5( ('%s:%s' % (gis_tmpl, variables)).encode('utf-8')).hexdigest(), }, query={ - 'query_hash': '42323d64886122307be10013ad2dcc44', + 'query_hash': self._QUERY_HASH, 'variables': variables, - })['data']['user']['edge_owner_to_timeline_media'] + }) + media = self._parse_timeline_from(json_data) self._gis_tmpl = gis_tmpl break except ExtractorError as e: + # if it's an error caused by a bad query, and there are + # more GIS templates to try, ignore it and keep trying if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if gis_tmpl != gis_tmpls[-1]: continue @@ -348,68 +345,99 @@ class InstagramUserIE(InfoExtractor): if not cursor or not isinstance(cursor, compat_str): break - def _saved_entries(self, username): - cookies = self._get_cookies('https://www.instagram.com/%s/saved/' % username) - cursor = '' - has_next_page = True - - while has_next_page: - query = { - 'query_hash': '8c86fed24fa03a8a2eea2a70a80c7b6b', - 'variables': json.dumps({ - 'id': cookies.get('ds_user_id').value, - 'first': 12, - 'after': cursor, - }) - } - resp = self._download_json('https://www.instagram.com/graphql/query/', - username, - query=query) - media = try_get(resp, - lambda x: x['data']['user']['edge_saved_media']) - - for edge in media.get('edges', []): - node = try_get(edge, lambda x: x['node'], dict) - if not node: - continue - if node.get('__typename') != 'GraphVideo' and node.get('is_video') is not True: - continue - video_id = node.get('shortcode') - if not video_id: - continue - info = self.url_result( - 'https://instagram.com/p/%s/' % video_id, - ie=InstagramIE.ie_key(), video_id=video_id) - - yield info - - page_info = try_get(media, lambda x: x['page_info'], dict) - if not page_info: - break - - has_next_page = page_info.get('has_next_page') - if not has_next_page: - break - - cursor = try_get(page_info, lambda x: x['end_cursor'], compat_str) - if not cursor: - break - def _real_extract(self, url): - username = self._match_id(url) + user_or_tag = self._match_id(url) + webpage = self._download_webpage(url, user_or_tag) + data = self._parse_graphql(webpage, user_or_tag) - webpage = self._download_webpage(url, username) - last = filter(lambda x: len(x) > 0, - compat_urllib_parse_urlparse(url).path.split('/'))[-1] - if last == 'saved': - return self.playlist_result( - self._saved_entries(username), - username, '%s - Saved media' % username) - - data = self._parse_json( - self._search_regex( - r'sharedData\s*=\s*({.+?})\s*;\s*[<\n]', webpage, 'data'), - username) + self._set_cookie('instagram.com', 'ig_pr', '1') return self.playlist_result( - self._entries(data), username, username) + self._extract_graphql(data, url), user_or_tag, user_or_tag) + + +class InstagramSavedIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/saved/?(?:$|[?#])' + IE_DESC = 'Instagram saved media' + IE_NAME = 'instagram:saved' + + _QUERY_HASH = '8c86fed24fa03a8a2eea2a70a80c7b6b' + + @staticmethod + def _parse_timeline_from(data): + return data['data']['user']['edge_saved_media'] + + @staticmethod + def _query_vars_for(data): + return { + 'id': data['entry_data']['ProfilePage'][0]['graphql']['user']['id'] + } + + +class InstagramUserIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])' + IE_DESC = 'Instagram user profile' + IE_NAME = 'instagram:user' + _TEST = { + 'url': 'https://instagram.com/porsche', + 'info_dict': { + 'id': 'porsche', + 'title': 'porsche', + }, + 'playlist_count': 5, + 'params': { + 'extract_flat': True, + 'skip_download': True, + 'playlistend': 5, + } + } + + _QUERY_HASH = '42323d64886122307be10013ad2dcc44', + + @staticmethod + def _parse_timeline_from(data): + # extracts the media timeline data from a GraphQL result + return data['data']['user']['edge_owner_to_timeline_media'] + + @staticmethod + def _query_vars_for(data): + # returns a dictionary of variables to add to the timeline query based + # on the GraphQL of the original page + return { + 'id': data['entry_data']['ProfilePage'][0]['graphql']['user']['id'] + } + + +class InstagramTagIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/explore/tags/(?P<id>[^/]+)' + IE_DESC = 'Instagram hashtag search' + IE_NAME = 'instagram:tag' + _TEST = { + 'url': 'https://instagram.com/explore/tags/lolcats', + 'info_dict': { + 'id': 'lolcats', + 'title': 'lolcats', + }, + 'playlist_count': 50, + 'params': { + 'extract_flat': True, + 'skip_download': True, + 'playlistend': 50, + } + } + + _QUERY_HASH = 'f92f56d47dc7a55b606908374b43a314', + + @staticmethod + def _parse_timeline_from(data): + # extracts the media timeline data from a GraphQL result + return data['data']['hashtag']['edge_hashtag_to_media'] + + @staticmethod + def _query_vars_for(data): + # returns a dictionary of variables to add to the timeline query based + # on the GraphQL of the original page + return { + 'tag_name': + data['entry_data']['TagPage'][0]['graphql']['hashtag']['name'] + } diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 1d58d6e85..11bbeb592 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -12,7 +12,7 @@ from ..utils import ( class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)' + _VALID_URL = r'https?://(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)' _GEO_BYPASS = False _TESTS = [{ @@ -41,6 +41,24 @@ class IPrimaIE(InfoExtractor): # iframe prima.iprima.cz 'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha', 'only_matching': True, + }, { + 'url': 'http://www.iprima.cz/filmy/desne-rande', + 'only_matching': True, + }, { + 'url': 'https://zoom.iprima.cz/10-nejvetsich-tajemstvi-zahad/posvatna-mista-a-stavby', + 'only_matching': True, + }, { + 'url': 'https://krimi.iprima.cz/mraz-0/sebevrazdy', + 'only_matching': True, + }, { + 'url': 'https://cool.iprima.cz/derava-silnice-nevadi', + 'only_matching': True, + }, { + 'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi', + 'only_matching': True, + }, { + 'url': 'https://autosalon.iprima.cz/motorsport/7-epizoda-1', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index cb51cef2d..86c014b07 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -15,7 +15,7 @@ from ..utils import ( class IviIE(InfoExtractor): IE_DESC = 'ivi.ru' IE_NAME = 'ivi' - _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)' _GEO_BYPASS = False _GEO_COUNTRIES = ['RU'] @@ -65,7 +65,11 @@ class IviIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', }, 'skip': 'Only works from Russia', - } + }, + { + 'url': 'https://www.ivi.tv/watch/33560/', + 'only_matching': True, + }, ] # Sorted by quality diff --git a/youtube_dl/extractor/jamendo.py b/youtube_dl/extractor/jamendo.py index 595d7a5b7..c21827618 100644 --- a/youtube_dl/extractor/jamendo.py +++ b/youtube_dl/extractor/jamendo.py @@ -26,8 +26,15 @@ class JamendoBaseIE(InfoExtractor): class JamendoIE(JamendoBaseIE): - _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)' - _TEST = { + _VALID_URL = r'''(?x) + https?:// + (?: + licensing\.jamendo\.com/[^/]+| + (?:www\.)?jamendo\.com + ) + /track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+) + ''' + _TESTS = [{ 'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i', 'md5': '6e9e82ed6db98678f171c25a8ed09ffd', 'info_dict': { @@ -40,14 +47,19 @@ class JamendoIE(JamendoBaseIE): 'duration': 210, 'thumbnail': r're:^https?://.*\.jpg' } - } + }, { + 'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock', + 'only_matching': True, + }] def _real_extract(self, url): mobj = self._VALID_URL_RE.match(url) track_id = mobj.group('id') display_id = mobj.group('display_id') - webpage = self._download_webpage(url, display_id) + webpage = self._download_webpage( + 'https://www.jamendo.com/track/%s/%s' % (track_id, display_id), + display_id) title, artist, track = self._extract_meta(webpage) diff --git a/youtube_dl/extractor/joj.py b/youtube_dl/extractor/joj.py index d9f8dbfd2..62b28e980 100644 --- a/youtube_dl/extractor/joj.py +++ b/youtube_dl/extractor/joj.py @@ -61,7 +61,7 @@ class JojIE(InfoExtractor): bitrates = self._parse_json( self._search_regex( - r'(?s)bitrates\s*=\s*({.+?});', webpage, 'bitrates', + r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates', default='{}'), video_id, transform_source=js_to_json, fatal=False) diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 63d0dc998..d19a6a774 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -7,8 +7,8 @@ from .common import InfoExtractor class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' - _TEST = { + _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video|manifest)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})' + _TESTS = [{ 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', 'info_dict': { @@ -19,7 +19,10 @@ class JWPlatformIE(InfoExtractor): 'upload_date': '20081127', 'timestamp': 1227796140, } - } + }, { + 'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js', + 'only_matching': True, + }] @staticmethod def _extract_url(webpage): @@ -34,5 +37,5 @@ class JWPlatformIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id) + json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id) return self._parse_jwplayer_data(json_data, video_id) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 04f68fce4..fdf7f5bbc 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -192,6 +192,8 @@ class KalturaIE(InfoExtractor): 'entryId': video_id, 'service': 'baseentry', 'ks': '{1:result:ks}', + 'responseProfile:fields': 'createdAt,dataUrl,duration,name,plays,thumbnailUrl,userId', + 'responseProfile:type': 1, }, { 'action': 'getbyentryid', diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py index c7f813370..fa217365a 100644 --- a/youtube_dl/extractor/laola1tv.py +++ b/youtube_dl/extractor/laola1tv.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import json +import re from .common import InfoExtractor from ..utils import ( @@ -32,7 +33,8 @@ class Laola1TvEmbedIE(InfoExtractor): def _extract_token_url(self, stream_access_url, video_id, data): return self._download_json( - stream_access_url, video_id, headers={ + self._proto_relative_url(stream_access_url, 'https:'), video_id, + headers={ 'Content-Type': 'application/json', }, data=json.dumps(data).encode())['data']['stream-access'][0] @@ -119,9 +121,59 @@ class Laola1TvEmbedIE(InfoExtractor): } -class Laola1TvIE(Laola1TvEmbedIE): +class Laola1TvBaseIE(Laola1TvEmbedIE): + def _extract_video(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + if 'Dieser Livestream ist bereits beendet.' in webpage: + raise ExtractorError('This live stream has already finished.', expected=True) + + conf = self._parse_json(self._search_regex( + r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'), + display_id, + transform_source=lambda s: js_to_json(re.sub(r'shareurl:.+,', '', s))) + video_id = conf['videoid'] + + config = self._download_json(conf['configUrl'], video_id, query={ + 'videoid': video_id, + 'partnerid': conf['partnerid'], + 'language': conf.get('language', ''), + 'portal': conf.get('portalid', ''), + }) + error = config.get('error') + if error: + raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) + + video_data = config['video'] + title = video_data['title'] + is_live = video_data.get('isLivestream') and video_data.get('isLive') + meta = video_data.get('metaInformation') + sports = meta.get('sports') + categories = sports.split(',') if sports else [] + + token_url = self._extract_token_url( + video_data['streamAccess'], video_id, + video_data['abo']['required']) + + formats = self._extract_formats(token_url, video_id) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': self._live_title(title) if is_live else title, + 'description': video_data.get('description'), + 'thumbnail': video_data.get('image'), + 'categories': categories, + 'formats': formats, + 'is_live': is_live, + } + + +class Laola1TvIE(Laola1TvBaseIE): IE_NAME = 'laola1tv' _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)' + _TESTS = [{ 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html', 'info_dict': { @@ -169,52 +221,30 @@ class Laola1TvIE(Laola1TvEmbedIE): }] def _real_extract(self, url): - display_id = self._match_id(url) + return self._extract_video(url) - webpage = self._download_webpage(url, display_id) - if 'Dieser Livestream ist bereits beendet.' in webpage: - raise ExtractorError('This live stream has already finished.', expected=True) +class EHFTVIE(Laola1TvBaseIE): + IE_NAME = 'ehftv' + _VALID_URL = r'https?://(?:www\.)?ehftv\.com/[a-z]+(?:-[a-z]+)?/[^/]+/(?P<id>[^/?#&]+)' - conf = self._parse_json(self._search_regex( - r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'), - display_id, js_to_json) + _TESTS = [{ + 'url': 'https://www.ehftv.com/int/video/paris-saint-germain-handball-pge-vive-kielce/1166761', + 'info_dict': { + 'id': '1166761', + 'display_id': 'paris-saint-germain-handball-pge-vive-kielce', + 'ext': 'mp4', + 'title': 'Paris Saint-Germain Handball - PGE Vive Kielce', + 'is_live': False, + 'categories': ['Handball'], + }, + 'params': { + 'skip_download': True, + }, + }] - video_id = conf['videoid'] - - config = self._download_json(conf['configUrl'], video_id, query={ - 'videoid': video_id, - 'partnerid': conf['partnerid'], - 'language': conf.get('language', ''), - 'portal': conf.get('portalid', ''), - }) - error = config.get('error') - if error: - raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) - - video_data = config['video'] - title = video_data['title'] - is_live = video_data.get('isLivestream') and video_data.get('isLive') - meta = video_data.get('metaInformation') - sports = meta.get('sports') - categories = sports.split(',') if sports else [] - - token_url = self._extract_token_url( - video_data['streamAccess'], video_id, - video_data['abo']['required']) - - formats = self._extract_formats(token_url, video_id) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': self._live_title(title) if is_live else title, - 'description': video_data.get('description'), - 'thumbnail': video_data.get('image'), - 'categories': categories, - 'formats': formats, - 'is_live': is_live, - } + def _real_extract(self, url): + return self._extract_video(url) class ITTFIE(InfoExtractor): diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py new file mode 100644 index 000000000..24f78d928 --- /dev/null +++ b/youtube_dl/extractor/lecturio.py @@ -0,0 +1,229 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + determine_ext, + extract_attributes, + ExtractorError, + float_or_none, + int_or_none, + str_or_none, + url_or_none, + urlencode_postdata, + urljoin, +) + + +class LecturioBaseIE(InfoExtractor): + _LOGIN_URL = 'https://app.lecturio.com/en/login' + _NETRC_MACHINE = 'lecturio' + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + # Sets some cookies + _, urlh = self._download_webpage_handle( + self._LOGIN_URL, None, 'Downloading login popup') + + def is_logged(url_handle): + return self._LOGIN_URL not in compat_str(url_handle.geturl()) + + # Already logged in + if is_logged(urlh): + return + + login_form = { + 'signin[email]': username, + 'signin[password]': password, + 'signin[remember]': 'on', + } + + response, urlh = self._download_webpage_handle( + self._LOGIN_URL, None, 'Logging in', + data=urlencode_postdata(login_form)) + + # Logged in successfully + if is_logged(urlh): + return + + errors = self._html_search_regex( + r'(?s)<ul[^>]+class=["\']error_list[^>]+>(.+?)</ul>', response, + 'errors', default=None) + if errors: + raise ExtractorError('Unable to login: %s' % errors, expected=True) + raise ExtractorError('Unable to log in') + + +class LecturioIE(LecturioBaseIE): + _VALID_URL = r'''(?x) + https:// + (?: + app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture| + (?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag + ) + ''' + _TESTS = [{ + 'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos', + 'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870', + 'info_dict': { + 'id': '39634', + 'ext': 'mp4', + 'title': 'Important Concepts and Terms – Introduction to Microbiology', + }, + 'skip': 'Requires lecturio account credentials', + }, { + 'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag', + 'only_matching': True, + }] + + _CC_LANGS = { + 'German': 'de', + 'English': 'en', + 'Spanish': 'es', + 'French': 'fr', + 'Polish': 'pl', + 'Russian': 'ru', + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') or mobj.group('id_de') + + webpage = self._download_webpage( + 'https://app.lecturio.com/en/lecture/%s/player.html' % display_id, + display_id) + + lecture_id = self._search_regex( + r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id') + + api_url = self._search_regex( + r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'api url', group='url') + + video = self._download_json(api_url, display_id) + + title = video['title'].strip() + + formats = [] + for format_ in video['content']['media']: + if not isinstance(format_, dict): + continue + file_ = format_.get('file') + if not file_: + continue + ext = determine_ext(file_) + if ext == 'smil': + # smil contains only broken RTMP formats anyway + continue + file_url = url_or_none(file_) + if not file_url: + continue + label = str_or_none(format_.get('label')) + filesize = int_or_none(format_.get('fileSize')) + formats.append({ + 'url': file_url, + 'format_id': label, + 'filesize': float_or_none(filesize, invscale=1000) + }) + self._sort_formats(formats) + + subtitles = {} + automatic_captions = {} + cc = self._parse_json( + self._search_regex( + r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles', + default='{}'), display_id, fatal=False) + for cc_label, cc_url in cc.items(): + cc_url = url_or_none(cc_url) + if not cc_url: + continue + lang = self._search_regex( + r'/([a-z]{2})_', cc_url, 'lang', + default=cc_label.split()[0] if cc_label else 'en') + original_lang = self._search_regex( + r'/[a-z]{2}_([a-z]{2})_', cc_url, 'original lang', + default=None) + sub_dict = (automatic_captions + if 'auto-translated' in cc_label or original_lang + else subtitles) + sub_dict.setdefault(self._CC_LANGS.get(lang, lang), []).append({ + 'url': cc_url, + }) + + return { + 'id': lecture_id, + 'title': title, + 'formats': formats, + 'subtitles': subtitles, + 'automatic_captions': automatic_captions, + } + + +class LecturioCourseIE(LecturioBaseIE): + _VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course' + _TEST = { + 'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/', + 'info_dict': { + 'id': 'microbiology-introduction', + 'title': 'Microbiology: Introduction', + }, + 'playlist_count': 45, + 'skip': 'Requires lecturio account credentials', + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>', + webpage): + params = extract_attributes(mobj.group(0)) + lecture_url = urljoin(url, params.get('data-url')) + lecture_id = params.get('data-id') + entries.append(self.url_result( + lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id)) + + title = self._search_regex( + r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage, + 'title', default=None) + + return self.playlist_result(entries, display_id, title) + + +class LecturioDeCourseIE(LecturioBaseIE): + _VALID_URL = r'https://(?:www\.)?lecturio\.de/[^/]+/(?P<id>[^/?#&]+)\.kurs' + _TEST = { + 'url': 'https://www.lecturio.de/jura/grundrechte.kurs', + 'only_matching': True, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'(?s)<td[^>]+\bdata-lecture-id=["\'](?P<id>\d+).+?\bhref=(["\'])(?P<url>(?:(?!\2).)+\.vortrag)\b[^>]+>', + webpage): + lecture_url = urljoin(url, mobj.group('url')) + lecture_id = mobj.group('id') + entries.append(self.url_result( + lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id)) + + title = self._search_regex( + r'<h1[^>]*>([^<]+)', webpage, 'title', default=None) + + return self.playlist_result(entries, display_id, title) diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py index 40295a30b..03f205144 100644 --- a/youtube_dl/extractor/libraryofcongress.py +++ b/youtube_dl/extractor/libraryofcongress.py @@ -16,16 +16,15 @@ from ..utils import ( class LibraryOfCongressIE(InfoExtractor): IE_NAME = 'loc' IE_DESC = 'Library of Congress' - _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9a-z_.]+)' _TESTS = [{ # embedded via <div class="media-player" 'url': 'http://loc.gov/item/90716351/', - 'md5': '353917ff7f0255aa6d4b80a034833de8', + 'md5': '6ec0ae8f07f86731b1b2ff70f046210a', 'info_dict': { 'id': '90716351', 'ext': 'mp4', 'title': "Pa's trip to Mars", - 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 0, 'view_count': int, }, @@ -57,6 +56,12 @@ class LibraryOfCongressIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.loc.gov/item/ihas.200197114/', + 'only_matching': True, + }, { + 'url': 'https://www.loc.gov/item/afc1981005_afs20503/', + 'only_matching': True, }] def _real_extract(self, url): @@ -67,12 +72,13 @@ class LibraryOfCongressIE(InfoExtractor): (r'id=(["\'])media-player-(?P<id>.+?)\1', r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1', r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1', - r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1'), + r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1', + r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'), webpage, 'media id', group='id') data = self._download_json( 'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id, - video_id)['mediaObject'] + media_id)['mediaObject'] derivative = data['derivatives'][0] media_url = derivative['derivativeUrl'] @@ -89,25 +95,29 @@ class LibraryOfCongressIE(InfoExtractor): if ext not in ('mp4', 'mp3'): media_url += '.mp4' if is_video else '.mp3' - if 'vod/mp4:' in media_url: - formats = [{ - 'url': media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8', + formats = [] + if '/vod/mp4:' in media_url: + formats.append({ + 'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8', 'format_id': 'hls', 'ext': 'mp4', 'protocol': 'm3u8_native', 'quality': 1, - }] - elif 'vod/mp3:' in media_url: - formats = [{ - 'url': media_url.replace('vod/mp3:', ''), - 'vcodec': 'none', - }] + }) + http_format = { + 'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url), + 'format_id': 'http', + 'quality': 1, + } + if not is_video: + http_format['vcodec'] = 'none' + formats.append(http_format) download_urls = set() for m in re.finditer( r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?: |\s+)\((?P<size>.+?)\))?\s*<', webpage): format_id = m.group('id').lower() - if format_id == 'gif': + if format_id in ('gif', 'jpeg'): continue download_url = m.group('url') if download_url in download_urls: diff --git a/youtube_dl/extractor/linkedin.py b/youtube_dl/extractor/linkedin.py new file mode 100644 index 000000000..259fc4c5e --- /dev/null +++ b/youtube_dl/extractor/linkedin.py @@ -0,0 +1,175 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + float_or_none, + int_or_none, + urlencode_postdata, +) + + +class LinkedInLearningBaseIE(InfoExtractor): + _NETRC_MACHINE = 'linkedin' + + def _call_api(self, course_slug, fields, video_slug=None, resolution=None): + query = { + 'courseSlug': course_slug, + 'fields': fields, + 'q': 'slugs', + } + sub = '' + if video_slug: + query.update({ + 'videoSlug': video_slug, + 'resolution': '_%s' % resolution, + }) + sub = ' %dp' % resolution + api_url = 'https://www.linkedin.com/learning-api/detailedCourses' + return self._download_json( + api_url, video_slug, 'Downloading%s JSON metadata' % sub, headers={ + 'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value, + }, query=query)['elements'][0] + + def _get_video_id(self, urn, course_slug, video_slug): + if urn: + mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn) + if mobj: + return mobj.group(1) + return '%s/%s' % (course_slug, video_slug) + + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: + return + + login_page = self._download_webpage( + 'https://www.linkedin.com/uas/login?trk=learning', + None, 'Downloading login page') + action_url = self._search_regex( + r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, 'post url', + default='https://www.linkedin.com/uas/login-submit', group='url') + data = self._hidden_inputs(login_page) + data.update({ + 'session_key': email, + 'session_password': password, + }) + login_submit_page = self._download_webpage( + action_url, None, 'Logging in', + data=urlencode_postdata(data)) + error = self._search_regex( + r'<span[^>]+class="error"[^>]*>\s*(.+?)\s*</span>', + login_submit_page, 'error', default=None) + if error: + raise ExtractorError(error, expected=True) + + +class LinkedInLearningIE(LinkedInLearningBaseIE): + IE_NAME = 'linkedin:learning' + _VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P<course_slug>[^/]+)/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals/welcome?autoplay=true', + 'md5': 'a1d74422ff0d5e66a792deb996693167', + 'info_dict': { + 'id': '90426', + 'ext': 'mp4', + 'title': 'Welcome', + 'timestamp': 1430396150.82, + 'upload_date': '20150430', + }, + } + + def _real_extract(self, url): + course_slug, video_slug = re.match(self._VALID_URL, url).groups() + + video_data = None + formats = [] + for width, height in ((640, 360), (960, 540), (1280, 720)): + video_data = self._call_api( + course_slug, 'selectedVideo', video_slug, height)['selectedVideo'] + + video_url_data = video_data.get('url') or {} + progressive_url = video_url_data.get('progressiveUrl') + if progressive_url: + formats.append({ + 'format_id': 'progressive-%dp' % height, + 'url': progressive_url, + 'height': height, + 'width': width, + 'source_preference': 1, + }) + + title = video_data['title'] + + audio_url = video_data.get('audio', {}).get('progressiveUrl') + if audio_url: + formats.append({ + 'abr': 64, + 'ext': 'm4a', + 'format_id': 'audio', + 'url': audio_url, + 'vcodec': 'none', + }) + + streaming_url = video_url_data.get('streamingUrl') + if streaming_url: + formats.extend(self._extract_m3u8_formats( + streaming_url, video_slug, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + + self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr')) + + return { + 'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug), + 'title': title, + 'formats': formats, + 'thumbnail': video_data.get('defaultThumbnail'), + 'timestamp': float_or_none(video_data.get('publishedOn'), 1000), + 'duration': int_or_none(video_data.get('durationInSeconds')), + } + + +class LinkedInLearningCourseIE(LinkedInLearningBaseIE): + IE_NAME = 'linkedin:learning:course' + _VALID_URL = r'https?://(?:www\.)?linkedin\.com/learning/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'https://www.linkedin.com/learning/programming-foundations-fundamentals', + 'info_dict': { + 'id': 'programming-foundations-fundamentals', + 'title': 'Programming Foundations: Fundamentals', + 'description': 'md5:76e580b017694eb89dc8e8923fff5c86', + }, + 'playlist_mincount': 61, + } + + @classmethod + def suitable(cls, url): + return False if LinkedInLearningIE.suitable(url) else super(LinkedInLearningCourseIE, cls).suitable(url) + + def _real_extract(self, url): + course_slug = self._match_id(url) + course_data = self._call_api(course_slug, 'chapters,description,title') + + entries = [] + for chapter in course_data.get('chapters', []): + chapter_title = chapter.get('title') + for video in chapter.get('videos', []): + video_slug = video.get('slug') + if not video_slug: + continue + entries.append({ + '_type': 'url_transparent', + 'id': self._get_video_id(video.get('urn'), course_slug, video_slug), + 'title': video.get('title'), + 'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug), + 'chapter': chapter_title, + 'ie_key': LinkedInLearningIE.ie_key(), + }) + + return self.playlist_result( + entries, course_slug, + course_data.get('title'), + course_data.get('description')) diff --git a/youtube_dl/extractor/liveleak.py b/youtube_dl/extractor/liveleak.py index 26671753c..22a067e40 100644 --- a/youtube_dl/extractor/liveleak.py +++ b/youtube_dl/extractor/liveleak.py @@ -87,7 +87,7 @@ class LiveLeakIE(InfoExtractor): @staticmethod def _extract_urls(webpage): return re.findall( - r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"', + r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[ift]=[\w_]+[^"]+)"', webpage) def _real_extract(self, url): @@ -120,13 +120,27 @@ class LiveLeakIE(InfoExtractor): } for idx, info_dict in enumerate(entries): + formats = [] for a_format in info_dict['formats']: if not a_format.get('height'): a_format['height'] = int_or_none(self._search_regex( r'([0-9]+)p\.mp4', a_format['url'], 'height label', default=None)) + formats.append(a_format) - self._sort_formats(info_dict['formats']) + # Removing '.*.mp4' gives the raw video, which is essentially + # the same video without the LiveLeak logo at the top (see + # https://github.com/rg3/youtube-dl/pull/4768) + orig_url = re.sub(r'\.mp4\.[^.]+', '', a_format['url']) + if a_format['url'] != orig_url: + format_id = a_format.get('format_id') + formats.append({ + 'format_id': 'original' + ('-' + format_id if format_id else ''), + 'url': orig_url, + 'preference': 1, + }) + self._sort_formats(formats) + info_dict['formats'] = formats # Don't append entry ID for one-video pages to keep backward compatibility if len(entries) > 1: @@ -146,7 +160,7 @@ class LiveLeakIE(InfoExtractor): class LiveLeakEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[if])=(?P<id>[\w_]+)' + _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[ift])=(?P<id>[\w_]+)' # See generic.py for actual test cases _TESTS = [{ @@ -158,15 +172,14 @@ class LiveLeakEmbedIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - kind, video_id = mobj.group('kind', 'id') + kind, video_id = re.match(self._VALID_URL, url).groups() if kind == 'f': webpage = self._download_webpage(url, video_id) liveleak_url = self._search_regex( - r'logourl\s*:\s*(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL, + r'(?:logourl\s*:\s*|window\.open\()(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL, webpage, 'LiveLeak URL', group='url') - elif kind == 'i': - liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id + else: + liveleak_url = 'http://www.liveleak.com/view?%s=%s' % (kind, video_id) return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key()) diff --git a/youtube_dl/extractor/livestream.py b/youtube_dl/extractor/livestream.py index c4776bbf3..e55b1a202 100644 --- a/youtube_dl/extractor/livestream.py +++ b/youtube_dl/extractor/livestream.py @@ -363,7 +363,4 @@ class LivestreamShortenerIE(InfoExtractor): id = mobj.group('id') webpage = self._download_webpage(url, id) - return { - '_type': 'url', - 'url': self._og_search_url(webpage), - } + return self.url_result(self._og_search_url(webpage)) diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 4ba61cd8a..3084c6dff 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -15,7 +15,7 @@ from ..utils import ( class LyndaBaseIE(InfoExtractor): - _SIGNIN_URL = 'https://www.lynda.com/signin' + _SIGNIN_URL = 'https://www.lynda.com/signin/lynda' _PASSWORD_URL = 'https://www.lynda.com/signin/password' _USER_URL = 'https://www.lynda.com/signin/user' _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.' diff --git a/youtube_dl/extractor/manyvids.py b/youtube_dl/extractor/manyvids.py index b94b3c2ab..e8d7163e4 100644 --- a/youtube_dl/extractor/manyvids.py +++ b/youtube_dl/extractor/manyvids.py @@ -2,12 +2,18 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + determine_ext, + int_or_none, + str_to_int, + urlencode_postdata, +) class ManyVidsIE(InfoExtractor): _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)' - _TEST = { + _TESTS = [{ + # preview video 'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/', 'md5': '03f11bb21c52dd12a05be21a5c7dcc97', 'info_dict': { @@ -17,7 +23,18 @@ class ManyVidsIE(InfoExtractor): 'view_count': int, 'like_count': int, }, - } + }, { + # full video + 'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/', + 'md5': 'f3e8f7086409e9b470e2643edb96bdcc', + 'info_dict': { + 'id': '935718', + 'ext': 'mp4', + 'title': 'MY FACE REVEAL', + 'view_count': int, + 'like_count': int, + }, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -28,12 +45,41 @@ class ManyVidsIE(InfoExtractor): r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'video URL', group='url') - title = '%s (Preview)' % self._html_search_regex( - r'<h2[^>]+class="m-a-0"[^>]*>([^<]+)', webpage, 'title') + title = self._html_search_regex( + (r'<span[^>]+class=["\']item-title[^>]+>([^<]+)', + r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'), + webpage, 'title', default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', fatal=True) + + if any(p in webpage for p in ('preview_videos', '_preview.mp4')): + title += ' (Preview)' + + mv_token = self._search_regex( + r'data-mvtoken=(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, + 'mv token', default=None, group='value') + + if mv_token: + # Sets some cookies + self._download_webpage( + 'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php', + video_id, fatal=False, data=urlencode_postdata({ + 'mvtoken': mv_token, + 'vid': video_id, + }), headers={ + 'Referer': url, + 'X-Requested-With': 'XMLHttpRequest' + }) + + if determine_ext(video_url) == 'm3u8': + formats = self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + else: + formats = [{'url': video_url}] like_count = int_or_none(self._search_regex( r'data-likes=["\'](\d+)', webpage, 'like count', default=None)) - view_count = int_or_none(self._html_search_regex( + view_count = str_to_int(self._html_search_regex( r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage, 'view count', default=None)) @@ -42,7 +88,5 @@ class ManyVidsIE(InfoExtractor): 'title': title, 'view_count': view_count, 'like_count': like_count, - 'formats': [{ - 'url': video_url, - }], + 'formats': formats, } diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 57f97409d..df3748798 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -4,6 +4,11 @@ from __future__ import unicode_literals import re from .theplatform import ThePlatformBaseIE +from ..compat import ( + compat_parse_qs, + compat_str, + compat_urllib_parse_urlparse, +) from ..utils import ( ExtractorError, int_or_none, @@ -76,12 +81,33 @@ class MediasetIE(ThePlatformBaseIE): }] @staticmethod - def _extract_urls(webpage): - return [ - mobj.group('url') - for mobj in re.finditer( - r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1', - webpage)] + def _extract_urls(ie, webpage): + def _qs(url): + return compat_parse_qs(compat_urllib_parse_urlparse(url).query) + + def _program_guid(qs): + return qs.get('programGuid', [None])[0] + + entries = [] + for mobj in re.finditer( + r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1', + webpage): + embed_url = mobj.group('url') + embed_qs = _qs(embed_url) + program_guid = _program_guid(embed_qs) + if program_guid: + entries.append(embed_url) + continue + video_id = embed_qs.get('id', [None])[0] + if not video_id: + continue + urlh = ie._request_webpage( + embed_url, video_id, note='Following embed URL redirect') + embed_url = compat_str(urlh.geturl()) + program_guid = _program_guid(_qs(embed_url)) + if program_guid: + entries.append(embed_url) + return entries def _real_extract(self, url): guid = self._match_id(url) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 84876b883..ef9628e65 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -21,7 +21,7 @@ from ..utils import ( class MediasiteIE(InfoExtractor): - _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)' + _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/(?:default|livebroadcast)/Presentation)/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)' _TESTS = [ { 'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d', @@ -84,7 +84,15 @@ class MediasiteIE(InfoExtractor): 'timestamp': 1333983600, 'duration': 7794, } - } + }, + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Showcase/livebroadcast/Presentation/ada7020854f743c49fbb45c9ec7dbb351d', + 'only_matching': True, + }, + { + 'url': 'https://mediasite.ntnu.no/Mediasite/Showcase/default/Presentation/7d8b913259334b688986e970fae6fcb31d', + 'only_matching': True, + }, ] # look in Mediasite.Core.js (Mediasite.ContentStreamType[*]) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index b7bccb504..bcac13ec5 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -161,11 +161,17 @@ class MixcloudIE(InfoExtractor): stream_info = info_json['streamInfo'] formats = [] + def decrypt_url(f_url): + for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'): + decrypted_url = self._decrypt_xor_cipher(k, f_url) + if re.search(r'^https?://[0-9a-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url): + return decrypted_url + for url_key in ('url', 'hlsUrl', 'dashUrl'): format_url = stream_info.get(url_key) if not format_url: continue - decrypted = self._decrypt_xor_cipher(key, compat_b64decode(format_url)) + decrypted = decrypt_url(compat_b64decode(format_url)) if not decrypted: continue if url_key == 'hlsUrl': diff --git a/youtube_dl/extractor/nationalgeographic.py b/youtube_dl/extractor/nationalgeographic.py index 4d2ee6408..165964ca0 100644 --- a/youtube_dl/extractor/nationalgeographic.py +++ b/youtube_dl/extractor/nationalgeographic.py @@ -1,15 +1,9 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from .adobepass import AdobePassIE -from .theplatform import ThePlatformIE from ..utils import ( smuggle_url, url_basename, - update_url_query, - get_element_by_class, ) @@ -64,132 +58,3 @@ class NationalGeographicVideoIE(InfoExtractor): {'force_smil_url': True}), 'id': guid, } - - -class NationalGeographicIE(ThePlatformIE, AdobePassIE): - IE_NAME = 'natgeo' - _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:(?:(?:wild/)?[^/]+/)?(?:videos|episodes)|u)/(?P<id>[^/?]+)' - - _TESTS = [ - { - 'url': 'http://channel.nationalgeographic.com/u/kdi9Ld0PN2molUUIMSBGxoeDhD729KRjQcnxtetilWPMevo8ZwUBIDuPR0Q3D2LVaTsk0MPRkRWDB8ZhqWVeyoxfsZZm36yRp1j-zPfsHEyI_EgAeFY/', - 'md5': '518c9aa655686cf81493af5cc21e2a04', - 'info_dict': { - 'id': 'vKInpacll2pC', - 'ext': 'mp4', - 'title': 'Uncovering a Universal Knowledge', - 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a', - 'timestamp': 1458680907, - 'upload_date': '20160322', - 'uploader': 'NEWA-FNG-NGTV', - }, - 'add_ie': ['ThePlatform'], - }, - { - 'url': 'http://channel.nationalgeographic.com/u/kdvOstqYaBY-vSBPyYgAZRUL4sWUJ5XUUPEhc7ISyBHqoIO4_dzfY3K6EjHIC0hmFXoQ7Cpzm6RkET7S3oMlm6CFnrQwSUwo/', - 'md5': 'c4912f656b4cbe58f3e000c489360989', - 'info_dict': { - 'id': 'Pok5lWCkiEFA', - 'ext': 'mp4', - 'title': 'The Stunning Red Bird of Paradise', - 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c', - 'timestamp': 1459362152, - 'upload_date': '20160330', - 'uploader': 'NEWA-FNG-NGTV', - }, - 'add_ie': ['ThePlatform'], - }, - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/videos/treasures-rediscovered/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/', - 'only_matching': True, - }, - { - 'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/', - 'only_matching': True, - } - ] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - release_url = self._search_regex( - r'video_auth_playlist_url\s*=\s*"([^"]+)"', - webpage, 'release url') - theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path') - video_id = theplatform_path.split('/')[-1] - query = { - 'mbr': 'true', - } - is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False) - if is_auth == 'auth': - auth_resource_id = self._search_regex( - r"video_auth_resourceId\s*=\s*'([^']+)'", - webpage, 'auth resource id') - query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id) - - formats = [] - subtitles = {} - for key, value in (('switch', 'http'), ('manifest', 'm3u')): - tp_query = query.copy() - tp_query.update({ - key: value, - }) - tp_formats, tp_subtitles = self._extract_theplatform_smil( - update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - info = self._extract_theplatform_metadata(theplatform_path, display_id) - info.update({ - 'id': video_id, - 'formats': formats, - 'subtitles': subtitles, - 'display_id': display_id, - }) - return info - - -class NationalGeographicEpisodeGuideIE(InfoExtractor): - IE_NAME = 'natgeo:episodeguide' - _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide' - _TESTS = [ - { - 'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/', - 'info_dict': { - 'id': 'the-story-of-god-with-morgan-freeman-season-1', - 'title': 'The Story of God with Morgan Freeman - Season 1', - }, - 'playlist_mincount': 6, - }, - { - 'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2', - 'info_dict': { - 'id': 'underworld-inc-season-2', - 'title': 'Underworld, Inc. - Season 2', - }, - 'playlist_mincount': 7, - }, - ] - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - show = get_element_by_class('show', webpage) - selected_season = self._search_regex( - r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>', - webpage, 'selected season') - entries = [ - self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic') - for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)] - return self.playlist_result( - entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')), - '%s - %s' % (show, selected_season)) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 765c46fd2..3282f84ee 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -9,10 +9,8 @@ from .theplatform import ThePlatformIE from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( - find_xpath_attr, smuggle_url, try_get, - unescapeHTML, update_url_query, int_or_none, ) @@ -269,27 +267,14 @@ class CSNNEIE(InfoExtractor): class NBCNewsIE(ThePlatformIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/ - (?:video/.+?/(?P<id>\d+)| - ([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+)) - ''' + _VALID_URL = r'(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/([^/]+/)*(?:.*-)?(?P<id>[^/?]+)' _TESTS = [ - { - 'url': 'http://www.nbcnews.com/video/nbc-news/52753292', - 'md5': '47abaac93c6eaf9ad37ee6c4463a5179', - 'info_dict': { - 'id': '52753292', - 'ext': 'flv', - 'title': 'Crew emerges after four-month Mars food study', - 'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1', - }, - }, { 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880', 'md5': 'af1adfa51312291a017720403826bb64', 'info_dict': { - 'id': 'p_tweet_snow_140529', + 'id': '269389891880', 'ext': 'mp4', 'title': 'How Twitter Reacted To The Snowden Interview', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', @@ -313,7 +298,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844', 'md5': '73135a2e0ef819107bbb55a5a9b2a802', 'info_dict': { - 'id': 'nn_netcast_150204', + 'id': '394064451844', 'ext': 'mp4', 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)', 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5', @@ -326,7 +311,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456', 'md5': 'a49e173825e5fcd15c13fc297fced39d', 'info_dict': { - 'id': 'x_lon_vwhorn_150922', + 'id': '529953347624', 'ext': 'mp4', 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up', 'description': 'md5:c8be487b2d80ff0594c005add88d8351', @@ -339,7 +324,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788', 'md5': '118d7ca3f0bea6534f119c68ef539f71', 'info_dict': { - 'id': 'tdy_al_space_160420', + 'id': '669831235788', 'ext': 'mp4', 'title': 'See the aurora borealis from space in stunning new NASA video', 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1', @@ -352,7 +337,7 @@ class NBCNewsIE(ThePlatformIE): 'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924', 'md5': '6d236bf4f3dddc226633ce6e2c3f814d', 'info_dict': { - 'id': 'n_hayes_Aimm_140801_272214', + 'id': '314487875924', 'ext': 'mp4', 'title': 'The chaotic GOP immigration vote', 'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.', @@ -374,60 +359,22 @@ class NBCNewsIE(ThePlatformIE): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - if video_id is not None: - all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id) - info = all_info.find('video') - - return { - 'id': video_id, - 'title': info.find('headline').text, - 'ext': 'flv', - 'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text, - 'description': info.find('caption').text, - 'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text, - } - else: - # "feature" and "nightly-news" pages use theplatform.com - video_id = mobj.group('mpx_id') + video_id = self._match_id(url) + if not video_id.isdigit(): webpage = self._download_webpage(url, video_id) - filter_param = 'byId' - bootstrap_json = self._search_regex( - [r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$', - r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"', - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'], - webpage, 'bootstrap json', default=None) - if bootstrap_json: - bootstrap = self._parse_json( - bootstrap_json, video_id, transform_source=unescapeHTML) + data = self._parse_json(self._search_regex( + r'window\.__data\s*=\s*({.+});', webpage, + 'bootstrap json'), video_id) + video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id'] - info = None - if 'results' in bootstrap: - info = bootstrap['results'][0]['video'] - elif 'video' in bootstrap: - info = bootstrap['video'] - elif 'msnbcVideoInfo' in bootstrap: - info = bootstrap['msnbcVideoInfo']['meta'] - elif 'msnbcThePlatform' in bootstrap: - info = bootstrap['msnbcThePlatform']['videoPlayer']['video'] - else: - info = bootstrap - - if 'guid' in info: - video_id = info['guid'] - filter_param = 'byGuid' - elif 'mpxId' in info: - video_id = info['mpxId'] - - return { - '_type': 'url_transparent', - 'id': video_id, - # http://feed.theplatform.com/f/2E2eJC/nbcnews also works - 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}), - 'ie_key': 'ThePlatformFeed', - } + return { + '_type': 'url_transparent', + 'id': video_id, + # http://feed.theplatform.com/f/2E2eJC/nbcnews also works + 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}), + 'ie_key': 'ThePlatformFeed', + } class NBCOlympicsIE(InfoExtractor): diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 5c8cd76dc..d4acbcc3e 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -5,8 +5,8 @@ from ..utils import ExtractorError class NhkVodIE(InfoExtractor): - _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)' - _TEST = { + _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P<id>[^/]+/[^/?#&]+)' + _TESTS = [{ # Videos available only for a limited period of time. Visit # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples. 'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815', @@ -19,7 +19,10 @@ class NhkVodIE(InfoExtractor): 'episode': 'The Kimono as Global Fashion', }, 'skip': 'Videos available only for a limited period of time', - } + }, { + 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/', + 'only_matching': True, + }] _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k' def _real_extract(self, url): diff --git a/youtube_dl/extractor/njpwworld.py b/youtube_dl/extractor/njpwworld.py index febef097a..025c5d249 100644 --- a/youtube_dl/extractor/njpwworld.py +++ b/youtube_dl/extractor/njpwworld.py @@ -31,6 +31,8 @@ class NJPWWorldIE(InfoExtractor): 'skip': 'Requires login', } + _LOGIN_URL = 'https://front.njpwworld.com/auth/login' + def _real_initialize(self): self._login() @@ -40,13 +42,17 @@ class NJPWWorldIE(InfoExtractor): if not username: return True + # Setup session (will set necessary cookies) + self._request_webpage( + 'https://njpwworld.com/', None, note='Setting up session') + webpage, urlh = self._download_webpage_handle( - 'https://njpwworld.com/auth/login', None, + self._LOGIN_URL, None, note='Logging in', errnote='Unable to login', data=urlencode_postdata({'login_id': username, 'pw': password}), - headers={'Referer': 'https://njpwworld.com/auth'}) + headers={'Referer': 'https://front.njpwworld.com/auth'}) # /auth/login will return 302 for successful logins - if urlh.geturl() == 'https://njpwworld.com/auth/login': + if urlh.geturl() == self._LOGIN_URL: self.report_warning('unable to login') return False diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 80186ec50..901f44b54 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -35,7 +35,7 @@ class NovaEmbedIE(InfoExtractor): bitrates = self._parse_json( self._search_regex( - r'(?s)bitrates\s*=\s*({.+?})\s*;', webpage, 'formats'), + r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'), video_id, transform_source=js_to_json) QUALITIES = ('lq', 'mq', 'hq', 'hd') diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index c2cb85a73..5a427c396 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -363,7 +363,7 @@ class NPOIE(NPOBaseIE): class NPOLiveIE(NPOBaseIE): IE_NAME = 'npo.nl:live' - _VALID_URL = r'https?://(?:www\.)?npo\.nl/live(?:/(?P<id>[^/?#&]+))?' + _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?' _TESTS = [{ 'url': 'http://www.npo.nl/live/npo-1', @@ -380,6 +380,9 @@ class NPOLiveIE(NPOBaseIE): }, { 'url': 'http://www.npo.nl/live', 'only_matching': True, + }, { + 'url': 'https://www.npostart.nl/live/npo-1', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index a231735fb..072f920a9 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -211,13 +211,13 @@ class NRKIE(NRKBaseIE): _TESTS = [{ # video 'url': 'http://www.nrk.no/video/PS*150533', - 'md5': '2f7f6eeb2aacdd99885f355428715cfa', + 'md5': '706f34cdf1322577589e369e522b50ef', 'info_dict': { 'id': '150533', 'ext': 'mp4', 'title': 'Dompap og andre fugler i Piip-Show', 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', - 'duration': 263, + 'duration': 262, } }, { # audio @@ -248,7 +248,7 @@ class NRKTVIE(NRKBaseIE): _VALID_URL = r'''(?x) https?:// (?:tv|radio)\.nrk(?:super)?\.no/ - (?:serie/[^/]+|program)/ + (?:serie(?:/[^/]+){1,2}|program)/ (?![Ee]pisodes)%s (?:/\d{2}-\d{2}-\d{4})? (?:\#del=(?P<part_id>\d+))? @@ -256,14 +256,14 @@ class NRKTVIE(NRKBaseIE): _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no') _TESTS = [{ 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', - 'md5': '4e9ca6629f09e588ed240fb11619922a', + 'md5': '9a167e54d04671eb6317a37b7bc8a280', 'info_dict': { 'id': 'MUHH48000314AA', 'ext': 'mp4', 'title': '20 spørsmål 23.05.2014', 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 'duration': 1741, - 'series': '20 spørsmål - TV', + 'series': '20 spørsmål', 'episode': '23.05.2014', }, }, { @@ -301,7 +301,7 @@ class NRKTVIE(NRKBaseIE): 'id': 'MSPO40010515AH', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', 'duration': 772, 'series': 'Tour de Ski', 'episode': '06.01.2015', @@ -314,7 +314,7 @@ class NRKTVIE(NRKBaseIE): 'id': 'MSPO40010515BH', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', 'duration': 6175, 'series': 'Tour de Ski', 'episode': '06.01.2015', @@ -326,7 +326,7 @@ class NRKTVIE(NRKBaseIE): 'info_dict': { 'id': 'MSPO40010515', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', - 'description': 'md5:c03aba1e917561eface5214020551b7a', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', }, 'expected_warnings': ['Video is geo restricted'], }, { @@ -362,6 +362,9 @@ class NRKTVIE(NRKBaseIE): }, { 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', 'only_matching': True, + }, { + 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller', + 'only_matching': True, }] @@ -403,21 +406,35 @@ class NRKTVSerieBaseIE(InfoExtractor): def _extract_series(self, webpage, display_id, fatal=True): config = self._parse_json( self._search_regex( - r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>', webpage, 'config', - default='{}' if not fatal else NO_DEFAULT), + (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;', + r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'), + webpage, 'config', default='{}' if not fatal else NO_DEFAULT), display_id, fatal=False) if not config: return - return try_get(config, lambda x: x['series'], dict) + return try_get( + config, + (lambda x: x['initialState']['series'], lambda x: x['series']), + dict) + + def _extract_seasons(self, seasons): + if not isinstance(seasons, list): + return [] + entries = [] + for season in seasons: + entries.extend(self._extract_episodes(season)) + return entries def _extract_episodes(self, season): - entries = [] if not isinstance(season, dict): - return entries - episodes = season.get('episodes') - if not isinstance(episodes, list): - return entries - for episode in episodes: + return [] + return self._extract_entries(season.get('episodes')) + + def _extract_entries(self, entry_list): + if not isinstance(entry_list, list): + return [] + entries = [] + for episode in entry_list: nrk_id = episode.get('prfId') if not nrk_id or not isinstance(nrk_id, compat_str): continue @@ -462,7 +479,7 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)' _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)' _TESTS = [{ - # new layout + # new layout, seasons 'url': 'https://tv.nrk.no/serie/backstage', 'info_dict': { 'id': 'backstage', @@ -471,20 +488,21 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): }, 'playlist_mincount': 60, }, { - # old layout + # new layout, instalments 'url': 'https://tv.nrk.no/serie/groenn-glede', 'info_dict': { 'id': 'groenn-glede', 'title': 'Grønn glede', 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', }, - 'playlist_mincount': 9, + 'playlist_mincount': 10, }, { - 'url': 'http://tv.nrksuper.no/serie/labyrint', + # old layout + 'url': 'https://tv.nrksuper.no/serie/labyrint', 'info_dict': { 'id': 'labyrint', 'title': 'Labyrint', - 'description': 'md5:58afd450974c89e27d5a19212eee7115', + 'description': 'md5:318b597330fdac5959247c9b69fdb1ec', }, 'playlist_mincount': 3, }, { @@ -517,11 +535,12 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): description = try_get( series, lambda x: x['titles']['subtitle'], compat_str) entries = [] - for season in series['seasons']: - entries.extend(self._extract_episodes(season)) + entries.extend(self._extract_seasons(series.get('seasons'))) + entries.extend(self._extract_entries(series.get('instalments'))) + entries.extend(self._extract_episodes(series.get('extraMaterial'))) return self.playlist_result(entries, series_id, title, description) - # Old layout (e.g. https://tv.nrk.no/serie/groenn-glede) + # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint) entries = [ self.url_result( 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format( @@ -533,6 +552,9 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE): 'seriestitle', webpage, 'title', default=None) or self._og_search_title( webpage, fatal=False) + if title: + title = self._search_regex( + r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title) description = self._html_search_meta( 'series_description', webpage, @@ -593,7 +615,7 @@ class NRKPlaylistIE(NRKPlaylistBaseIE): 'title': 'Rivertonprisen til Karin Fossum', 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', }, - 'playlist_count': 5, + 'playlist_count': 2, }] def _extract_title(self, webpage): diff --git a/youtube_dl/extractor/nzz.py b/youtube_dl/extractor/nzz.py index 2d352f53f..61ee77adb 100644 --- a/youtube_dl/extractor/nzz.py +++ b/youtube_dl/extractor/nzz.py @@ -11,20 +11,27 @@ from ..utils import ( class NZZIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153', 'info_dict': { 'id': '9153', }, 'playlist_mincount': 6, - } + }, { + 'url': 'https://www.nzz.ch/video/nzz-standpunkte/cvp-auf-der-suche-nach-dem-mass-der-mitte-ld.1368112', + 'info_dict': { + 'id': '1368112', + }, + 'playlist_count': 1, + }] def _real_extract(self, url): page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) entries = [] - for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage): + for player_element in re.findall( + r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage): player_params = extract_attributes(player_element) if player_params.get('data-type') not in ('kaltura_singleArticle',): self.report_warning('Unsupported player type') diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 190d8af4d..114b93c07 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -115,6 +115,10 @@ class OdnoklassnikiIE(InfoExtractor): }, { 'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#', 'only_matching': True, + }, { + # Paid video + 'url': 'https://ok.ru/video/954886983203', + 'only_matching': True, }] def _real_extract(self, url): @@ -244,6 +248,11 @@ class OdnoklassnikiIE(InfoExtractor): 'ext': 'flv', }) + if not formats: + payment_info = metadata.get('paymentInfo') + if payment_info: + raise ExtractorError('This video is paid, subscribe to download it', expected=True) + self._sort_formats(formats) info['formats'] = formats diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index d264fe206..b713e78b8 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,7 +243,18 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream|site|xyz|win|download))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' + _VALID_URL = r'''(?x) + https?:// + (?P<host> + (?:www\.)? + (?: + openload\.(?:co|io|link)| + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club) + ) + )/ + (?:f|embed)/ + (?P<id>[a-zA-Z0-9-_]+) + ''' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -307,10 +318,25 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.download/f/kUEfGclsU9o', 'only_matching': True, + }, { + 'url': 'https://oload.cloud/f/4ZDnBXRWiB8', + 'only_matching': True, }, { # Its title has not got its extension but url has it 'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4', 'only_matching': True, + }, { + 'url': 'https://oload.cc/embed/5NEAbI2BDSk', + 'only_matching': True, + }, { + 'url': 'https://oload.icu/f/-_i4y_F_Hs8', + 'only_matching': True, + }, { + 'url': 'https://oload.fun/f/gb6G1H4sHXY', + 'only_matching': True, + }, { + 'url': 'https://oload.club/f/Nr1L-aZ2dbQ', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' @@ -322,8 +348,11 @@ class OpenloadIE(InfoExtractor): webpage) def _real_extract(self, url): - video_id = self._match_id(url) - url_pattern = 'https://openload.co/%%s/%s/' % video_id + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + video_id = mobj.group('id') + + url_pattern = 'https://%s/%%s/%s/' % (host, video_id) headers = { 'User-Agent': self._USER_AGENT, } @@ -356,7 +385,7 @@ class OpenloadIE(InfoExtractor): r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage, 'stream URL')) - video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id + video_url = 'https://%s/stream/%s?mime=true' % (host, decoded_id) title = self._og_search_title(webpage, default=None) or self._search_regex( r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage, @@ -367,7 +396,7 @@ class OpenloadIE(InfoExtractor): entry = entries[0] if entries else {} subtitles = entry.get('subtitles') - info_dict = { + return { 'id': video_id, 'title': title, 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None), @@ -376,4 +405,3 @@ class OpenloadIE(InfoExtractor): 'subtitles': subtitles, 'http_headers': headers, } - return info_dict diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index c1fb580ca..d432e3449 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -15,6 +15,7 @@ from ..utils import ( strip_jsonp, unescapeHTML, unified_strdate, + url_or_none, ) @@ -68,26 +69,35 @@ class ORFTVthekIE(InfoExtractor): webpage, 'playlist', group='json'), playlist_id, transform_source=unescapeHTML)['playlist']['videos'] - def quality_to_int(s): - m = re.search('([0-9]+)', s) - if m is None: - return -1 - return int(m.group(1)) - entries = [] for sd in data_jsb: video_id, title = sd.get('id'), sd.get('title') if not video_id or not title: continue video_id = compat_str(video_id) - formats = [{ - 'preference': -10 if fd['delivery'] == 'hls' else None, - 'format_id': '%s-%s-%s' % ( - fd['delivery'], fd['quality'], fd['quality_string']), - 'url': fd['src'], - 'protocol': fd['protocol'], - 'quality': quality_to_int(fd['quality']), - } for fd in sd['sources']] + formats = [] + for fd in sd['sources']: + src = url_or_none(fd.get('src')) + if not src: + continue + format_id_list = [] + for key in ('delivery', 'quality', 'quality_string'): + value = fd.get(key) + if value: + format_id_list.append(value) + format_id = '-'.join(format_id_list) + if determine_ext(fd['src']) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + fd['src'], video_id, 'mp4', m3u8_id=format_id)) + elif determine_ext(fd['src']) == 'f4m': + formats.extend(self._extract_f4m_formats( + fd['src'], video_id, f4m_id=format_id)) + else: + formats.append({ + 'format_id': format_id, + 'url': src, + 'protocol': fd.get('protocol'), + }) # Check for geoblocking. # There is a property is_geoprotection, but that's always false diff --git a/youtube_dl/extractor/outsidetv.py b/youtube_dl/extractor/outsidetv.py new file mode 100644 index 000000000..c5333b08c --- /dev/null +++ b/youtube_dl/extractor/outsidetv.py @@ -0,0 +1,28 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class OutsideTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?outsidetv\.com/(?:[^/]+/)*?play/[a-zA-Z0-9]{8}/\d+/\d+/(?P<id>[a-zA-Z0-9]{8})' + _TESTS = [{ + 'url': 'http://www.outsidetv.com/category/snow/play/ZjQYboH6/1/10/Hdg0jukV/4', + 'md5': '192d968fedc10b2f70ec31865ffba0da', + 'info_dict': { + 'id': 'Hdg0jukV', + 'ext': 'mp4', + 'title': 'Home - Jackson Ep 1 | Arbor Snowboards', + 'description': 'md5:41a12e94f3db3ca253b04bb1e8d8f4cd', + 'upload_date': '20181225', + 'timestamp': 1545742800, + } + }, { + 'url': 'http://www.outsidetv.com/home/play/ZjQYboH6/1/10/Hdg0jukV/4', + 'only_matching': True, + }] + + def _real_extract(self, url): + jw_media_id = self._match_id(url) + return self.url_result( + 'jwplatform:' + jw_media_id, 'JWPlatform', jw_media_id) diff --git a/youtube_dl/extractor/packtpub.py b/youtube_dl/extractor/packtpub.py index 56a2a1083..1324137df 100644 --- a/youtube_dl/extractor/packtpub.py +++ b/youtube_dl/extractor/packtpub.py @@ -24,9 +24,9 @@ class PacktPubBaseIE(InfoExtractor): class PacktPubIE(PacktPubBaseIE): - _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro', 'md5': '1e74bd6cfd45d7d07666f4684ef58f70', 'info_dict': { @@ -37,7 +37,10 @@ class PacktPubIE(PacktPubBaseIE): 'timestamp': 1490918400, 'upload_date': '20170331', }, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro', + 'only_matching': True, + }] _NETRC_MACHINE = 'packtpub' _TOKEN = None @@ -110,15 +113,18 @@ class PacktPubIE(PacktPubBaseIE): class PacktPubCourseIE(PacktPubBaseIE): - _VALID_URL = r'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))' - _TEST = { + _VALID_URL = r'(?P<url>https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<id>\d+))' + _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215', 'info_dict': { 'id': '9781787122215', 'title': 'Learn Nodejs by building 12 projects [Video]', }, 'playlist_count': 90, - } + }, { + 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215', + 'only_matching': True, + }] @classmethod def suitable(cls, url): diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index 9eb027679..426dd8121 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -2,52 +2,63 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import js_to_json +from ..utils import ( + clean_html, + determine_ext, + int_or_none, + parse_iso8601, +) class PatreonIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?patreon\.com/creation\?hid=(?P<id>[^&#]+)' - _TESTS = [ - { - 'url': 'http://www.patreon.com/creation?hid=743933', - 'md5': 'e25505eec1053a6e6813b8ed369875cc', - 'info_dict': { - 'id': '743933', - 'ext': 'mp3', - 'title': 'Episode 166: David Smalley of Dogma Debate', - 'uploader': 'Cognitive Dissonance Podcast', - 'thumbnail': 're:^https?://.*$', - }, + _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.patreon.com/creation?hid=743933', + 'md5': 'e25505eec1053a6e6813b8ed369875cc', + 'info_dict': { + 'id': '743933', + 'ext': 'mp3', + 'title': 'Episode 166: David Smalley of Dogma Debate', + 'description': 'md5:713b08b772cd6271b9f3906683cfacdf', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', + 'timestamp': 1406473987, + 'upload_date': '20140727', }, - { - 'url': 'http://www.patreon.com/creation?hid=754133', - 'md5': '3eb09345bf44bf60451b8b0b81759d0a', - 'info_dict': { - 'id': '754133', - 'ext': 'mp3', - 'title': 'CD 167 Extra', - 'uploader': 'Cognitive Dissonance Podcast', - 'thumbnail': 're:^https?://.*$', - }, + }, { + 'url': 'http://www.patreon.com/creation?hid=754133', + 'md5': '3eb09345bf44bf60451b8b0b81759d0a', + 'info_dict': { + 'id': '754133', + 'ext': 'mp3', + 'title': 'CD 167 Extra', + 'uploader': 'Cognitive Dissonance Podcast', + 'thumbnail': 're:^https?://.*$', }, - { - 'url': 'https://www.patreon.com/creation?hid=1682498', - 'info_dict': { - 'id': 'SU4fj_aEMVw', - 'ext': 'mp4', - 'title': 'I\'m on Patreon!', - 'uploader': 'TraciJHines', - 'thumbnail': 're:^https?://.*$', - 'upload_date': '20150211', - 'description': 'md5:c5a706b1f687817a3de09db1eb93acd4', - 'uploader_id': 'TraciJHines', - }, - 'params': { - 'noplaylist': True, - 'skip_download': True, - } + 'skip': 'Patron-only content', + }, { + 'url': 'https://www.patreon.com/creation?hid=1682498', + 'info_dict': { + 'id': 'SU4fj_aEMVw', + 'ext': 'mp4', + 'title': 'I\'m on Patreon!', + 'uploader': 'TraciJHines', + 'thumbnail': 're:^https?://.*$', + 'upload_date': '20150211', + 'description': 'md5:c5a706b1f687817a3de09db1eb93acd4', + 'uploader_id': 'TraciJHines', + }, + 'params': { + 'noplaylist': True, + 'skip_download': True, } - ] + }, { + 'url': 'https://www.patreon.com/posts/episode-166-of-743933', + 'only_matching': True, + }, { + 'url': 'https://www.patreon.com/posts/743933', + 'only_matching': True, + }] # Currently Patreon exposes download URL via hidden CSS, so login is not # needed. Keeping this commented for when this inevitably changes. @@ -78,38 +89,48 @@ class PatreonIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage).strip() - - attach_fn = self._html_search_regex( - r'<div class="attach"><a target="_blank" href="([^"]+)">', - webpage, 'attachment URL', default=None) - embed = self._html_search_regex( - r'<div[^>]+id="watchCreation"[^>]*>\s*<iframe[^>]+src="([^"]+)"', - webpage, 'embedded URL', default=None) - - if attach_fn is not None: - video_url = 'http://www.patreon.com' + attach_fn - thumbnail = self._og_search_thumbnail(webpage) - uploader = self._html_search_regex( - r'<strong>(.*?)</strong> is creating', webpage, 'uploader') - elif embed is not None: - return self.url_result(embed) - else: - playlist = self._parse_json(self._search_regex( - r'(?s)new\s+jPlayerPlaylist\(\s*\{\s*[^}]*},\s*(\[.*?,?\s*\])', - webpage, 'playlist JSON'), - video_id, transform_source=js_to_json) - data = playlist[0] - video_url = self._proto_relative_url(data['mp3']) - thumbnail = self._proto_relative_url(data.get('cover')) - uploader = data.get('artist') - - return { + post = self._download_json( + 'https://www.patreon.com/api/posts/' + video_id, video_id) + attributes = post['data']['attributes'] + title = attributes['title'].strip() + image = attributes.get('image') or {} + info = { 'id': video_id, - 'url': video_url, - 'ext': 'mp3', 'title': title, - 'uploader': uploader, - 'thumbnail': thumbnail, + 'description': clean_html(attributes.get('content')), + 'thumbnail': image.get('large_url') or image.get('url'), + 'timestamp': parse_iso8601(attributes.get('published_at')), + 'like_count': int_or_none(attributes.get('like_count')), + 'comment_count': int_or_none(attributes.get('comment_count')), } + + def add_file(file_data): + file_url = file_data.get('url') + if file_url: + info.update({ + 'url': file_url, + 'ext': determine_ext(file_data.get('name'), 'mp3'), + }) + + for i in post.get('included', []): + i_type = i.get('type') + if i_type == 'attachment': + add_file(i.get('attributes') or {}) + elif i_type == 'user': + user_attributes = i.get('attributes') + if user_attributes: + info.update({ + 'uploader': user_attributes.get('full_name'), + 'uploader_url': user_attributes.get('url'), + }) + + if not info.get('url'): + add_file(attributes.get('post_file') or {}) + + if not info.get('url'): + info.update({ + '_type': 'url', + 'url': attributes['embed']['url'], + }) + + return info diff --git a/youtube_dl/extractor/philharmoniedeparis.py b/youtube_dl/extractor/philharmoniedeparis.py index f1008ae51..f723a2b3b 100644 --- a/youtube_dl/extractor/philharmoniedeparis.py +++ b/youtube_dl/extractor/philharmoniedeparis.py @@ -2,31 +2,38 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - float_or_none, - int_or_none, - parse_iso8601, - xpath_text, + try_get, + urljoin, ) class PhilharmonieDeParisIE(InfoExtractor): IE_DESC = 'Philharmonie de Paris' - _VALID_URL = r'https?://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)' + _VALID_URL = r'''(?x) + https?:// + (?: + live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)| + pad\.philharmoniedeparis\.fr/doc/CIMU/ + ) + (?P<id>\d+) + ''' _TESTS = [{ + 'url': 'http://pad.philharmoniedeparis.fr/doc/CIMU/1086697/jazz-a-la-villette-knower', + 'md5': 'a0a4b195f544645073631cbec166a2c2', + 'info_dict': { + 'id': '1086697', + 'ext': 'mp4', + 'title': 'Jazz à la Villette : Knower', + }, + }, { 'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html', 'info_dict': { 'id': '1032066', - 'ext': 'flv', - 'title': 'md5:d1f5585d87d041d07ce9434804bc8425', - 'timestamp': 1428179400, - 'upload_date': '20150404', - 'duration': 6592.278, + 'title': 'md5:0a031b81807b3593cffa3c9a87a167a0', }, - 'params': { - # rtmp download - 'skip_download': True, - } + 'playlist_mincount': 2, }, { 'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html', 'only_matching': True, @@ -34,45 +41,60 @@ class PhilharmonieDeParisIE(InfoExtractor): 'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr', 'only_matching': True, }] + _LIVE_URL = 'https://live.philharmoniedeparis.fr' def _real_extract(self, url): video_id = self._match_id(url) - concert = self._download_xml( - 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id, - video_id).find('./concert') + config = self._download_json( + '%s/otoPlayer/config.ashx' % self._LIVE_URL, video_id, query={ + 'id': video_id, + 'lang': 'fr-FR', + }) - formats = [] - info_dict = { - 'id': video_id, - 'title': xpath_text(concert, './titre', 'title', fatal=True), - 'formats': formats, - } - - fichiers = concert.find('./fichiers') - stream = fichiers.attrib['serveurstream'] - for fichier in fichiers.findall('./fichier'): - info_dict['duration'] = float_or_none(fichier.get('timecodefin')) - for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]): - format_url = fichier.get('url%s' % suffix) - if not format_url: + def extract_entry(source): + if not isinstance(source, dict): + return + title = source.get('title') + if not title: + return + files = source.get('files') + if not isinstance(files, dict): + return + format_urls = set() + formats = [] + for format_id in ('mobile', 'desktop'): + format_url = try_get( + files, lambda x: x[format_id]['file'], compat_str) + if not format_url or format_url in format_urls: continue - formats.append({ - 'url': stream, - 'play_path': format_url, - 'ext': 'flv', - 'format_id': format_id, - 'width': int_or_none(concert.get('largeur%s' % suffix)), - 'height': int_or_none(concert.get('hauteur%s' % suffix)), - 'quality': quality, - }) - self._sort_formats(formats) + format_urls.add(format_url) + m3u8_url = urljoin(self._LIVE_URL, format_url) + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + if not formats: + return + self._sort_formats(formats) + return { + 'title': title, + 'formats': formats, + } - date, hour = concert.get('date'), concert.get('heure') - if date and hour: - info_dict['timestamp'] = parse_iso8601( - '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour)) - elif date: - info_dict['upload_date'] = date + thumbnail = urljoin(self._LIVE_URL, config.get('image')) - return info_dict + info = extract_entry(config) + if info: + info.update({ + 'id': video_id, + 'thumbnail': thumbnail, + }) + return info + + entries = [] + for num, chapter in enumerate(config['chapters'], start=1): + entry = extract_entry(chapter) + entry['id'] = '%s-%d' % (video_id, num) + entries.append(entry) + + return self.playlist_result(entries, video_id, config.get('title')) diff --git a/youtube_dl/extractor/picarto.py b/youtube_dl/extractor/picarto.py index 2366dfb34..8099ef1d6 100644 --- a/youtube_dl/extractor/picarto.py +++ b/youtube_dl/extractor/picarto.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import re import time from .common import InfoExtractor @@ -15,7 +16,7 @@ from ..utils import ( class PicartoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)(?:/(?P<token>[a-zA-Z0-9]+))?' _TEST = { 'url': 'https://picarto.tv/Setz', 'info_dict': { @@ -33,20 +34,14 @@ class PicartoIE(InfoExtractor): return False if PicartoVodIE.suitable(url) else super(PicartoIE, cls).suitable(url) def _real_extract(self, url): - channel_id = self._match_id(url) - stream_page = self._download_webpage(url, channel_id) + mobj = re.match(self._VALID_URL, url) + channel_id = mobj.group('id') - if '>This channel does not exist' in stream_page: - raise ExtractorError( - 'Channel %s does not exist' % channel_id, expected=True) + metadata = self._download_json( + 'https://api.picarto.tv/v1/channel/name/' + channel_id, + channel_id) - player = self._parse_json( - self._search_regex( - r'(?s)playerSettings\[\d+\]\s*=\s*(\{.+?\}\s*\n)', stream_page, - 'player settings'), - channel_id, transform_source=js_to_json) - - if player.get('online') is False: + if metadata.get('online') is False: raise ExtractorError('Stream is offline', expected=True) cdn_data = self._download_json( @@ -54,20 +49,13 @@ class PicartoIE(InfoExtractor): data=urlencode_postdata({'loadbalancinginfo': channel_id}), note='Downloading load balancing info') - def get_event(key): - return try_get(player, lambda x: x['event'][key], compat_str) or '' - + token = mobj.group('token') or 'public' params = { - 'token': player.get('token') or '', - 'ticket': get_event('ticket'), 'con': int(time.time() * 1000), - 'type': get_event('ticket'), - 'scope': get_event('scope'), + 'token': token, } prefered_edge = cdn_data.get('preferedEdge') - default_tech = player.get('defaultTech') - formats = [] for edge in cdn_data['edges']: @@ -81,8 +69,6 @@ class PicartoIE(InfoExtractor): preference = 0 if edge_id == prefered_edge: preference += 1 - if tech_type == default_tech: - preference += 1 format_id = [] if edge_id: format_id.append(edge_id) @@ -109,7 +95,7 @@ class PicartoIE(InfoExtractor): continue self._sort_formats(formats) - mature = player.get('mature') + mature = metadata.get('adult') if mature is None: age_limit = None else: @@ -117,9 +103,11 @@ class PicartoIE(InfoExtractor): return { 'id': channel_id, - 'title': self._live_title(channel_id), + 'title': self._live_title(metadata.get('title') or channel_id), 'is_live': True, - 'thumbnail': player.get('vodThumb'), + 'thumbnail': try_get(metadata, lambda x: x['thumbnails']['web']), + 'channel': channel_id, + 'channel_url': 'https://picarto.tv/%s' % channel_id, 'age_limit': age_limit, 'formats': formats, } diff --git a/youtube_dl/extractor/playplustv.py b/youtube_dl/extractor/playplustv.py new file mode 100644 index 000000000..1e30ab23a --- /dev/null +++ b/youtube_dl/extractor/playplustv.py @@ -0,0 +1,109 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + clean_html, + ExtractorError, + int_or_none, + PUTRequest, +) + + +class PlayPlusTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?playplus\.(?:com|tv)/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})' + _TEST = { + 'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e', + 'md5': 'd078cb89d7ab6b9df37ce23c647aef72', + 'info_dict': { + 'id': 'db8d274a5163424e967f35a30ddafb8e', + 'ext': 'mp4', + 'title': 'Capítulo 179 - Final', + 'description': 'md5:01085d62d8033a1e34121d3c3cabc838', + 'timestamp': 1529992740, + 'upload_date': '20180626', + }, + 'skip': 'Requires account credential', + } + _NETRC_MACHINE = 'playplustv' + _GEO_COUNTRIES = ['BR'] + _token = None + _profile_id = None + + def _call_api(self, resource, video_id=None, query=None): + return self._download_json('https://api.playplus.tv/api/media/v2/get' + resource, video_id, headers={ + 'Authorization': 'Bearer ' + self._token, + }, query=query) + + def _real_initialize(self): + email, password = self._get_login_info() + if email is None: + self.raise_login_required() + + req = PUTRequest( + 'https://api.playplus.tv/api/web/login', json.dumps({ + 'email': email, + 'password': password, + }).encode(), { + 'Content-Type': 'application/json; charset=utf-8', + }) + + try: + self._token = self._download_json(req, None)['token'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError(self._parse_json( + e.cause.read(), None)['errorMessage'], expected=True) + raise + + self._profile = self._call_api('Profiles')['list'][0]['_id'] + + def _real_extract(self, url): + project_id, media_id = re.match(self._VALID_URL, url).groups() + media = self._call_api( + 'Media', media_id, { + 'profileId': self._profile, + 'projectId': project_id, + 'mediaId': media_id, + })['obj'] + title = media['title'] + + formats = [] + for f in media.get('files', []): + f_url = f.get('url') + if not f_url: + continue + file_info = f.get('fileInfo') or {} + formats.append({ + 'url': f_url, + 'width': int_or_none(file_info.get('width')), + 'height': int_or_none(file_info.get('height')), + }) + self._sort_formats(formats) + + thumbnails = [] + for thumb in media.get('thumbs', []): + thumb_url = thumb.get('url') + if not thumb_url: + continue + thumbnails.append({ + 'url': thumb_url, + 'width': int_or_none(thumb.get('width')), + 'height': int_or_none(thumb.get('height')), + }) + + return { + 'id': media_id, + 'title': title, + 'formats': formats, + 'thumbnails': thumbnails, + 'description': clean_html(media.get('description')) or media.get('shortDescription'), + 'timestamp': int_or_none(media.get('publishDate'), 1000), + 'view_count': int_or_none(media.get('numberOfViews')), + 'comment_count': int_or_none(media.get('numberOfComments')), + 'tags': media.get('tags'), + } diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 1257841e4..eafe56897 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -4,6 +4,7 @@ import collections import json import os import random +import re from .common import InfoExtractor from ..compat import ( @@ -196,7 +197,10 @@ query viewClip { if error: raise ExtractorError('Unable to login: %s' % error, expected=True) - if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')): + if all(not re.search(p, response) for p in ( + r'__INITIAL_STATE__', r'["\']currentUser["\']', + # new layout? + r'>\s*Sign out\s*<')): BLOCKED = 'Your account has been blocked due to suspicious activity' if BLOCKED in response: raise ExtractorError( @@ -210,18 +214,26 @@ query viewClip { raise ExtractorError('Unable to log in') - def _get_subtitles(self, author, clip_idx, lang, name, duration, video_id): - captions_post = { - 'a': author, - 'cn': clip_idx, - 'lc': lang, - 'm': name, - } - captions = self._download_json( - '%s/player/retrieve-captions' % self._API_BASE, video_id, - 'Downloading captions JSON', 'Unable to download captions JSON', - fatal=False, data=json.dumps(captions_post).encode('utf-8'), - headers={'Content-Type': 'application/json;charset=utf-8'}) + def _get_subtitles(self, author, clip_idx, clip_id, lang, name, duration, video_id): + captions = None + if clip_id: + captions = self._download_json( + '%s/transcript/api/v1/caption/json/%s/%s' + % (self._API_BASE, clip_id, lang), video_id, + 'Downloading captions JSON', 'Unable to download captions JSON', + fatal=False) + if not captions: + captions_post = { + 'a': author, + 'cn': int(clip_idx), + 'lc': lang, + 'm': name, + } + captions = self._download_json( + '%s/player/retrieve-captions' % self._API_BASE, video_id, + 'Downloading captions JSON', 'Unable to download captions JSON', + fatal=False, data=json.dumps(captions_post).encode('utf-8'), + headers={'Content-Type': 'application/json;charset=utf-8'}) if captions: return { lang: [{ @@ -413,7 +425,7 @@ query viewClip { # TODO: other languages? subtitles = self.extract_subtitles( - author, clip_idx, 'en', name, duration, display_id) + author, clip_idx, clip.get('clipId'), 'en', name, duration, display_id) return { 'id': clip_id, diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 19eaf389f..be93d5d48 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -10,7 +10,9 @@ from .common import InfoExtractor from ..compat import ( compat_HTTPError, compat_str, + compat_urllib_request, ) +from .openload import PhantomJSwrapper from ..utils import ( ExtractorError, int_or_none, @@ -22,12 +24,34 @@ from ..utils import ( ) -class PornHubIE(InfoExtractor): +class PornHubBaseIE(InfoExtractor): + def _download_webpage_handle(self, *args, **kwargs): + def dl(*args, **kwargs): + return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs) + + webpage, urlh = dl(*args, **kwargs) + + if any(re.search(p, webpage) for p in ( + r'<body\b[^>]+\bonload=["\']go\(\)', + r'document\.cookie\s*=\s*["\']RNKEY=', + r'document\.location\.reload\(true\)')): + url_or_request = args[0] + url = (url_or_request.get_full_url() + if isinstance(url_or_request, compat_urllib_request.Request) + else url_or_request) + phantom = PhantomJSwrapper(self, required_version='2.0') + phantom.get(url, html=webpage) + webpage, urlh = dl(*args, **kwargs) + + return webpage, urlh + + +class PornHubIE(PornHubBaseIE): IE_DESC = 'PornHub and Thumbzilla' _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P<id>[\da-z]+) @@ -121,12 +145,15 @@ class PornHubIE(InfoExtractor): }, { 'url': 'http://www.pornhub.com/video/show?viewkey=648719015', 'only_matching': True, + }, { + 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', + 'only_matching': True, }] @staticmethod def _extract_urls(webpage): return re.findall( - r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)', + r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)', webpage) def _extract_count(self, pattern, webpage, name): @@ -134,14 +161,16 @@ class PornHubIE(InfoExtractor): pattern, webpage, '%s count' % name, fatal=False)) def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') or 'pornhub.com' + video_id = mobj.group('id') - self._set_cookie('pornhub.com', 'age_verified', '1') + self._set_cookie(host, 'age_verified', '1') def dl_webpage(platform): - self._set_cookie('pornhub.com', 'platform', platform) + self._set_cookie(host, 'platform', platform) return self._download_webpage( - 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, + 'http://www.%s/view_video.php?viewkey=%s' % (host, video_id), video_id, 'Downloading %s webpage' % platform) webpage = dl_webpage('pc') @@ -302,8 +331,8 @@ class PornHubIE(InfoExtractor): } -class PornHubPlaylistBaseIE(InfoExtractor): - def _extract_entries(self, webpage): +class PornHubPlaylistBaseIE(PornHubBaseIE): + def _extract_entries(self, webpage, host): # Only process container div with main playlist content skipping # drop-down menu that uses similar pattern for videos (see # https://github.com/rg3/youtube-dl/issues/11594). @@ -313,7 +342,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): return [ self.url_result( - 'http://www.pornhub.com/%s' % video_url, + 'http://www.%s/%s' % (host, video_url), PornHubIE.ie_key(), video_title=title) for video_url, title in orderedSet(re.findall( r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', @@ -321,11 +350,13 @@ class PornHubPlaylistBaseIE(InfoExtractor): ] def _real_extract(self, url): - playlist_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + playlist_id = mobj.group('id') webpage = self._download_webpage(url, playlist_id) - entries = self._extract_entries(webpage) + entries = self._extract_entries(webpage, host) playlist = self._parse_json( self._search_regex( @@ -340,7 +371,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): class PornHubPlaylistIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)' + _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/playlist/(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.pornhub.com/playlist/4667351', 'info_dict': { @@ -355,7 +386,7 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE): class PornHubUserVideosIE(PornHubPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' + _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos' _TESTS = [{ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public', 'info_dict': { @@ -396,7 +427,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): }] def _real_extract(self, url): - user_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + user_id = mobj.group('id') entries = [] for page_num in itertools.count(1): @@ -408,7 +441,7 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE): if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: break raise - page_entries = self._extract_entries(webpage) + page_entries = self._extract_entries(webpage, host) if not page_entries: break entries.extend(page_entries) diff --git a/youtube_dl/extractor/radiocanada.py b/youtube_dl/extractor/radiocanada.py index b952e59b4..302f67d96 100644 --- a/youtube_dl/extractor/radiocanada.py +++ b/youtube_dl/extractor/radiocanada.py @@ -49,6 +49,16 @@ class RadioCanadaIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + }, + { + # with protectionType but not actually DRM protected + 'url': 'radiocanada:toutv:140872', + 'info_dict': { + 'id': '140872', + 'title': 'Épisode 1', + 'series': 'District 31', + }, + 'only_matching': True, } ] @@ -67,8 +77,10 @@ class RadioCanadaIE(InfoExtractor): el = find_xpath_attr(metadata, './/Meta', 'name', name) return el.text if el is not None else None + # protectionType does not necessarily mean the video is DRM protected (see + # https://github.com/rg3/youtube-dl/pull/18609). if get_meta('protectionType'): - raise ExtractorError('This video is DRM protected.', expected=True) + self.report_warning('This video is probably DRM protected.') device_types = ['ipad'] if not smuggled_data: diff --git a/youtube_dl/extractor/rmcdecouverte.py b/youtube_dl/extractor/rmcdecouverte.py index e921ca3e6..c3623edcc 100644 --- a/youtube_dl/extractor/rmcdecouverte.py +++ b/youtube_dl/extractor/rmcdecouverte.py @@ -1,38 +1,46 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from .brightcove import BrightcoveLegacyIE from ..compat import ( compat_parse_qs, compat_urlparse, ) +from ..utils import smuggle_url class RMCDecouverteIE(InfoExtractor): - _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P<id>\d+)' + _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/(?:(?:[^/]+/)*program_(?P<id>\d+)|(?P<live_id>mediaplayer-direct))' - _TEST = { - 'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=13502&title=AQUAMEN:LES%20ROIS%20DES%20AQUARIUMS%20:UN%20DELICIEUX%20PROJET', + _TESTS = [{ + 'url': 'https://rmcdecouverte.bfmtv.com/wheeler-dealers-occasions-a-saisir/program_2566/', 'info_dict': { - 'id': '5419055995001', + 'id': '5983675500001', 'ext': 'mp4', - 'title': 'UN DELICIEUX PROJET', - 'description': 'md5:63610df7c8b1fc1698acd4d0d90ba8b5', + 'title': 'CORVETTE', + 'description': 'md5:c1e8295521e45ffebf635d6a7658f506', 'uploader_id': '1969646226001', - 'upload_date': '20170502', - 'timestamp': 1493745308, + 'upload_date': '20181226', + 'timestamp': 1545861635, }, 'params': { 'skip_download': True, }, 'skip': 'only available for a week', - } + }, { + # live, geo restricted, bypassable + 'url': 'https://rmcdecouverte.bfmtv.com/mediaplayer-direct/', + 'only_matching': True, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s' def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') or mobj.group('live_id') + webpage = self._download_webpage(url, display_id) brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) if brightcove_legacy_url: brightcove_id = compat_parse_qs(compat_urlparse.urlparse( @@ -41,5 +49,7 @@ class RMCDecouverteIE(InfoExtractor): brightcove_id = self._search_regex( r'data-video-id=["\'](\d+)', webpage, 'brightcove id') return self.url_result( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', - brightcove_id) + smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['FR']}), + 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/rte.py b/youtube_dl/extractor/rte.py index a6fac6c35..1fbc72915 100644 --- a/youtube_dl/extractor/rte.py +++ b/youtube_dl/extractor/rte.py @@ -8,7 +8,10 @@ from ..compat import compat_HTTPError from ..utils import ( float_or_none, parse_iso8601, + str_or_none, + try_get, unescapeHTML, + url_or_none, ExtractorError, ) @@ -17,65 +20,87 @@ class RteBaseIE(InfoExtractor): def _real_extract(self, url): item_id = self._match_id(url) - try: - json_string = self._download_json( - 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=' + item_id, - item_id) - except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: - error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False) - if error_info: - raise ExtractorError( - '%s said: %s' % (self.IE_NAME, error_info['message']), - expected=True) - raise - - # NB the string values in the JSON are stored using XML escaping(!) - show = json_string['shows'][0] - title = unescapeHTML(show['title']) - description = unescapeHTML(show.get('description')) - thumbnail = show.get('thumbnail') - duration = float_or_none(show.get('duration'), 1000) - timestamp = parse_iso8601(show.get('published')) - - mg = show['media:group'][0] - + info_dict = {} formats = [] - if mg.get('url'): - m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url']) - if m: - m = m.groupdict() - formats.append({ - 'url': m['url'] + '/' + m['app'], - 'app': m['app'], - 'play_path': m['playpath'], - 'player_url': url, - 'ext': 'flv', - 'format_id': 'rtmp', - }) + ENDPOINTS = ( + 'https://feeds.rasset.ie/rteavgen/player/playlist?type=iptv&format=json&showId=', + 'http://www.rte.ie/rteavgen/getplaylist/?type=web&format=json&id=', + ) - if mg.get('hls_server') and mg.get('hls_url'): - formats.extend(self._extract_m3u8_formats( - mg['hls_server'] + mg['hls_url'], item_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + for num, ep_url in enumerate(ENDPOINTS, start=1): + try: + data = self._download_json(ep_url + item_id, item_id) + except ExtractorError as ee: + if num < len(ENDPOINTS) or formats: + continue + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404: + error_info = self._parse_json(ee.cause.read().decode(), item_id, fatal=False) + if error_info: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error_info['message']), + expected=True) + raise - if mg.get('hds_server') and mg.get('hds_url'): - formats.extend(self._extract_f4m_formats( - mg['hds_server'] + mg['hds_url'], item_id, - f4m_id='hds', fatal=False)) + # NB the string values in the JSON are stored using XML escaping(!) + show = try_get(data, lambda x: x['shows'][0], dict) + if not show: + continue + + if not info_dict: + title = unescapeHTML(show['title']) + description = unescapeHTML(show.get('description')) + thumbnail = show.get('thumbnail') + duration = float_or_none(show.get('duration'), 1000) + timestamp = parse_iso8601(show.get('published')) + info_dict = { + 'id': item_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + } + + mg = try_get(show, lambda x: x['media:group'][0], dict) + if not mg: + continue + + if mg.get('url'): + m = re.match(r'(?P<url>rtmpe?://[^/]+)/(?P<app>.+)/(?P<playpath>mp4:.*)', mg['url']) + if m: + m = m.groupdict() + formats.append({ + 'url': m['url'] + '/' + m['app'], + 'app': m['app'], + 'play_path': m['playpath'], + 'player_url': url, + 'ext': 'flv', + 'format_id': 'rtmp', + }) + + if mg.get('hls_server') and mg.get('hls_url'): + formats.extend(self._extract_m3u8_formats( + mg['hls_server'] + mg['hls_url'], item_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)) + + if mg.get('hds_server') and mg.get('hds_url'): + formats.extend(self._extract_f4m_formats( + mg['hds_server'] + mg['hds_url'], item_id, + f4m_id='hds', fatal=False)) + + mg_rte_server = str_or_none(mg.get('rte:server')) + mg_url = str_or_none(mg.get('url')) + if mg_rte_server and mg_url: + hds_url = url_or_none(mg_rte_server + mg_url) + if hds_url: + formats.extend(self._extract_f4m_formats( + hds_url, item_id, f4m_id='hds', fatal=False)) self._sort_formats(formats) - return { - 'id': item_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } + info_dict['formats'] = formats + return info_dict class RteIE(RteBaseIE): diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index 261bcbb83..10ac8ed1f 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -103,7 +103,8 @@ class RutubeIE(RutubeBaseIE): options = self._download_json( 'http://rutube.ru/api/play/options/%s/?format=json' % video_id, - video_id, 'Downloading options JSON') + video_id, 'Downloading options JSON', + headers=self.geo_verification_headers()) formats = [] for format_id, format_url in options['video_balancer'].items(): diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index 9fa8688f8..f530f0083 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -65,7 +65,8 @@ class RuutuIE(InfoExtractor): video_id = self._match_id(url) video_xml = self._download_xml( - 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id) + 'https://gatling.nelonenmedia.fi/media-xml-cache', video_id, + query={'id': video_id}) formats = [] processed_urls = [] diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 30e2a38b4..c0d32a1b9 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -15,10 +15,10 @@ from ..utils import ( class SafariBaseIE(InfoExtractor): - _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' + _LOGIN_URL = 'https://learning.oreilly.com/accounts/login/' _NETRC_MACHINE = 'safari' - _API_BASE = 'https://www.safaribooksonline.com/api/v1' + _API_BASE = 'https://learning.oreilly.com/api/v1' _API_FORMAT = 'json' LOGGED_IN = False @@ -76,7 +76,7 @@ class SafariIE(SafariBaseIE): IE_DESC = 'safaribooksonline.com online video' _VALID_URL = r'''(?x) https?:// - (?:www\.)?safaribooksonline\.com/ + (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ (?: library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html| videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+) @@ -104,6 +104,9 @@ class SafariIE(SafariBaseIE): }, { 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00', 'only_matching': True, + }, { + 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro', + 'only_matching': True, }] _PARTNER_ID = '1926081' @@ -160,7 +163,7 @@ class SafariIE(SafariBaseIE): class SafariApiIE(SafariBaseIE): IE_NAME = 'safari:api' - _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html' + _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html' _TESTS = [{ 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', @@ -185,7 +188,7 @@ class SafariCourseIE(SafariBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:www\.)?safaribooksonline\.com/ + (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ (?: library/view/[^/]+| api/v1/book| @@ -213,6 +216,9 @@ class SafariCourseIE(SafariBaseIE): }, { 'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314', 'only_matching': True, + }, { + 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838', + 'only_matching': True, }] @classmethod diff --git a/youtube_dl/extractor/savefrom.py b/youtube_dl/extractor/savefrom.py index 30f9cf824..21e44b69a 100644 --- a/youtube_dl/extractor/savefrom.py +++ b/youtube_dl/extractor/savefrom.py @@ -30,8 +30,5 @@ class SaveFromIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = os.path.splitext(url.split('/')[-1])[0] - return { - '_type': 'url', - 'id': video_id, - 'url': mobj.group('url'), - } + + return self.url_result(mobj.group('url'), video_id=video_id) diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index 62a6a8337..69a0d01f3 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -90,6 +90,15 @@ class ScreencastIE(InfoExtractor): r'src=(.*?)(?:$|&)', video_meta, 'meta tag video URL', default=None) + if video_url is None: + video_url = self._html_search_regex( + r'MediaContentUrl["\']\s*:(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage, 'video url', default=None, group='url') + + if video_url is None: + video_url = self._html_search_meta( + 'og:video', webpage, default=None) + if video_url is None: raise ExtractorError('Cannot find video') diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py index 4023aeef8..8b3275735 100644 --- a/youtube_dl/extractor/scrippsnetworks.py +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -19,7 +19,7 @@ class ScrippsNetworksWatchIE(AWSIE): _VALID_URL = r'''(?x) https?:// watch\. - (?P<site>hgtv|foodnetwork|travelchannel|diynetwork|cookingchanneltv|geniuskitchen)\.com/ + (?P<site>geniuskitchen)\.com/ (?: player\.[A-Z0-9]+\.html\#| show/(?:[^/]+/){2}| @@ -28,38 +28,23 @@ class ScrippsNetworksWatchIE(AWSIE): (?P<id>\d+) ''' _TESTS = [{ - 'url': 'http://watch.hgtv.com/show/HGTVE/Best-Ever-Treehouses/2241515/Best-Ever-Treehouses/', - 'md5': '26545fd676d939954c6808274bdb905a', + 'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/', 'info_dict': { - 'id': '4173834', + 'id': '4194875', 'ext': 'mp4', - 'title': 'Best Ever Treehouses', - 'description': "We're searching for the most over the top treehouses.", + 'title': 'Ample Hills Ice Cream Bike', + 'description': 'Courtney Rada churns up a signature GK Now ice cream with The Scoopmaster.', 'uploader': 'ANV', - 'upload_date': '20170922', - 'timestamp': 1506056400, + 'upload_date': '20171011', + 'timestamp': 1507698000, }, 'params': { 'skip_download': True, }, 'add_ie': [AnvatoIE.ie_key()], - }, { - 'url': 'http://watch.diynetwork.com/show/DSAL/Salvage-Dawgs/2656646/Covington-Church/', - 'only_matching': True, - }, { - 'url': 'http://watch.diynetwork.com/player.HNT.html#2656646', - 'only_matching': True, - }, { - 'url': 'http://watch.geniuskitchen.com/player/3787617/Ample-Hills-Ice-Cream-Bike/', - 'only_matching': True, }] _SNI_TABLE = { - 'hgtv': 'hgtv', - 'diynetwork': 'diy', - 'foodnetwork': 'food', - 'cookingchanneltv': 'cook', - 'travelchannel': 'trav', 'geniuskitchen': 'genius', } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index b2250afdd..931a0f70e 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -5,6 +5,7 @@ from ..compat import compat_b64decode from ..utils import ( ExtractorError, int_or_none, + url_or_none, urlencode_postdata, ) @@ -86,9 +87,16 @@ class VivoIE(SharedBaseIE): } def _extract_video_url(self, webpage, video_id, *args): + def decode_url(encoded_url): + return compat_b64decode(encoded_url).decode('utf-8') + + stream_url = url_or_none(decode_url(self._search_regex( + r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'stream url', default=None, group='url'))) + if stream_url: + return stream_url return self._parse_json( self._search_regex( r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'stream', group='url'), - video_id, - transform_source=lambda x: compat_b64decode(x).decode('utf-8'))[0] + video_id, transform_source=decode_url)[0] diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py index 207ab4477..0c4f865ef 100644 --- a/youtube_dl/extractor/sixplay.py +++ b/youtube_dl/extractor/sixplay.py @@ -64,7 +64,7 @@ class SixPlayIE(InfoExtractor): for asset in clip_data['assets']: asset_url = asset.get('full_physical_path') protocol = asset.get('protocol') - if not asset_url or protocol == 'primetime' or asset_url in urls: + if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls: continue urls.append(asset_url) container = asset.get('video_container') @@ -81,19 +81,17 @@ class SixPlayIE(InfoExtractor): if not urlh: continue asset_url = urlh.geturl() - asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url) - formats.extend(self._extract_m3u8_formats( - asset_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - asset_url.replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - formats.extend(self._extract_mpd_formats( - asset_url.replace('.m3u8', '.mpd'), - video_id, mpd_id='dash', fatal=False)) - formats.extend(self._extract_ism_formats( - re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url), - video_id, ism_id='mss', fatal=False)) + for i in range(3, 0, -1): + asset_url = asset_url = asset_url.replace('_sd1/', '_sd%d/' % i) + m3u8_formats = self._extract_m3u8_formats( + asset_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + formats.extend(m3u8_formats) + formats.extend(self._extract_mpd_formats( + asset_url.replace('.m3u8', '.mpd'), + video_id, mpd_id='dash', fatal=False)) + if m3u8_formats: + break else: formats.extend(self._extract_m3u8_formats( asset_url, video_id, 'mp4', 'm3u8_native', diff --git a/youtube_dl/extractor/skylinewebcams.py b/youtube_dl/extractor/skylinewebcams.py index 5b4aaac6f..b7f8ac736 100644 --- a/youtube_dl/extractor/skylinewebcams.py +++ b/youtube_dl/extractor/skylinewebcams.py @@ -26,7 +26,7 @@ class SkylineWebcamsIE(InfoExtractor): webpage = self._download_webpage(url, video_id) stream_url = self._search_regex( - r'url\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage, + r'(?:url|source)\s*:\s*(["\'])(?P<url>(?:https?:)?//.+?\.m3u8.*?)\1', webpage, 'stream url', group='url') title = self._og_search_title(webpage) diff --git a/youtube_dl/extractor/spike.py b/youtube_dl/extractor/spike.py index e76522b45..6090e0066 100644 --- a/youtube_dl/extractor/spike.py +++ b/youtube_dl/extractor/spike.py @@ -44,3 +44,10 @@ class ParamountNetworkIE(MTVServicesInfoExtractor): _FEED_URL = 'http://www.paramountnetwork.com/feeds/mrss/' _GEO_COUNTRIES = ['US'] + + def _extract_mgid(self, webpage): + cs = self._parse_json(self._search_regex( + r'window\.__DATA__\s*=\s*({.+})', + webpage, 'data'), None)['children'] + c = next(c for c in cs if c.get('type') == 'VideoPlayer') + return c['props']['media']['video']['config']['uri'] diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py index 54497c880..b9017fd2a 100644 --- a/youtube_dl/extractor/sportbox.py +++ b/youtube_dl/extractor/sportbox.py @@ -8,20 +8,24 @@ from ..utils import ( determine_ext, int_or_none, js_to_json, + merge_dicts, ) -class SportBoxEmbedIE(InfoExtractor): - _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)' +class SportBoxIE(InfoExtractor): + _VALID_URL = r'https?://(?:news\.sportbox|matchtv)\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)' _TESTS = [{ 'url': 'http://news.sportbox.ru/vdl/player/ci/211355', 'info_dict': { - 'id': '211355', + 'id': '109158', 'ext': 'mp4', - 'title': '211355', + 'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»', + 'description': 'В Новороссийске прошел детский турнир «Поле славы боевой»', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 292, 'view_count': int, + 'timestamp': 1426237001, + 'upload_date': '20150313', }, 'params': { # m3u8 download @@ -33,12 +37,18 @@ class SportBoxEmbedIE(InfoExtractor): }, { 'url': 'https://news.sportbox.ru/vdl/player/media/193095', 'only_matching': True, + }, { + 'url': 'https://news.sportbox.ru/vdl/player/media/109158', + 'only_matching': True, + }, { + 'url': 'https://matchtv.ru/vdl/player/media/109158', + 'only_matching': True, }] @staticmethod def _extract_urls(webpage): return re.findall( - r'<iframe[^>]+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"', + r'<iframe[^>]+src="(https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"', webpage) def _real_extract(self, url): @@ -46,13 +56,14 @@ class SportBoxEmbedIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - wjplayer_data = self._parse_json( + sources = self._parse_json( self._search_regex( - r'(?s)wjplayer\(({.+?})\);', webpage, 'wjplayer settings'), + r'(?s)playerOptions\.sources(?:WithRes)?\s*=\s*(\[.+?\])\s*;\s*\n', + webpage, 'sources'), video_id, transform_source=js_to_json) formats = [] - for source in wjplayer_data['sources']: + for source in sources: src = source.get('src') if not src: continue @@ -66,14 +77,23 @@ class SportBoxEmbedIE(InfoExtractor): }) self._sort_formats(formats) + player = self._parse_json( + self._search_regex( + r'(?s)playerOptions\s*=\s*({.+?})\s*;\s*\n', webpage, + 'player options', default='{}'), + video_id, transform_source=js_to_json) + media_id = player['mediaId'] + + info = self._search_json_ld(webpage, media_id, default={}) + view_count = int_or_none(self._search_regex( r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None)) - return { - 'id': video_id, - 'title': video_id, - 'thumbnail': wjplayer_data.get('poster'), - 'duration': int_or_none(wjplayer_data.get('duration')), + return merge_dicts(info, { + 'id': media_id, + 'title': self._og_search_title(webpage, default=None) or media_id, + 'thumbnail': player.get('poster'), + 'duration': int_or_none(player.get('duration')), 'view_count': view_count, 'formats': formats, - } + }) diff --git a/youtube_dl/extractor/streamango.py b/youtube_dl/extractor/streamango.py index fcaa5ac0b..efb259f96 100644 --- a/youtube_dl/extractor/streamango.py +++ b/youtube_dl/extractor/streamango.py @@ -14,7 +14,7 @@ from ..utils import ( class StreamangoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?streamango\.com/(?:f|embed)/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4', 'md5': 'e992787515a182f55e38fc97588d802a', @@ -38,6 +38,9 @@ class StreamangoIE(InfoExtractor): }, { 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4', 'only_matching': True, + }, { + 'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/tbs.py b/youtube_dl/extractor/tbs.py index 784f8ed66..e8a7c65e0 100644 --- a/youtube_dl/extractor/tbs.py +++ b/youtube_dl/extractor/tbs.py @@ -16,7 +16,7 @@ from ..utils import ( class TBSIE(TurnerBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com(?P<path>/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+))' _TESTS = [{ 'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster', 'info_dict': { @@ -40,12 +40,12 @@ class TBSIE(TurnerBaseIE): }] def _real_extract(self, url): - site, display_id = re.match(self._VALID_URL, url).groups() + site, path, display_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) drupal_settings = self._parse_json(self._search_regex( r'<script[^>]+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})</script>', webpage, 'drupal setting'), display_id) - video_data = drupal_settings['turner_playlist'][0] + video_data = next(v for v in drupal_settings['turner_playlist'] if v.get('url') == path) media_id = video_data['mediaID'] title = video_data['title'] diff --git a/youtube_dl/extractor/upskill.py b/youtube_dl/extractor/teachable.py similarity index 53% rename from youtube_dl/extractor/upskill.py rename to youtube_dl/extractor/teachable.py index 30297b4dd..47ac95ee8 100644 --- a/youtube_dl/extractor/upskill.py +++ b/youtube_dl/extractor/teachable.py @@ -14,20 +14,38 @@ from ..utils import ( ) -class UpskillBaseIE(InfoExtractor): - _LOGIN_URL = 'http://upskillcourses.com/sign_in' - _NETRC_MACHINE = 'upskill' +class TeachableBaseIE(InfoExtractor): + _NETRC_MACHINE = 'teachable' + _URL_PREFIX = 'teachable:' + + _SITES = { + # Only notable ones here + 'upskillcourses.com': 'upskill', + 'academy.gns3.com': 'gns3', + 'academyhacker.com': 'academyhacker', + 'stackskills.com': 'stackskills', + 'market.saleshacker.com': 'saleshacker', + 'learnability.org': 'learnability', + 'edurila.com': 'edurila', + } + + _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys())) def _real_initialize(self): - self._login() + self._logged_in = False - def _login(self): - username, password = self._get_login_info() + def _login(self, site): + if self._logged_in: + return + + username, password = self._get_login_info( + netrc_machine=self._SITES.get(site, site)) if username is None: return login_page, urlh = self._download_webpage_handle( - self._LOGIN_URL, None, 'Downloading login page') + 'https://%s/sign_in' % site, None, + 'Downloading %s login page' % site) login_url = compat_str(urlh.geturl()) @@ -46,18 +64,24 @@ class UpskillBaseIE(InfoExtractor): post_url = urljoin(login_url, post_url) response = self._download_webpage( - post_url, None, 'Logging in', + post_url, None, 'Logging in to %s' % site, data=urlencode_postdata(login_form), headers={ 'Content-Type': 'application/x-www-form-urlencoded', 'Referer': login_url, }) + if '>I accept the new Privacy Policy<' in response: + raise ExtractorError( + 'Unable to login: %s asks you to accept new Privacy Policy. ' + 'Go to https://%s/ and accept.' % (site, site), expected=True) + # Successful login if any(re.search(p, response) for p in ( r'class=["\']user-signout', r'<a[^>]+\bhref=["\']/sign_out', r'>\s*Log out\s*<')): + self._logged_in = True return message = get_element_by_class('alert', response) @@ -68,8 +92,14 @@ class UpskillBaseIE(InfoExtractor): raise ExtractorError('Unable to log in') -class UpskillIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/[^/]+/lectures/(?P<id>\d+)' +class TeachableIE(TeachableBaseIE): + _VALID_URL = r'''(?x) + (?: + %shttps?://(?P<site_t>[^/]+)| + https?://(?:www\.)?(?P<site>%s) + ) + /courses/[^/]+/lectures/(?P<id>\d+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', @@ -77,7 +107,7 @@ class UpskillIE(UpskillBaseIE): 'id': 'uzw6zw58or', 'ext': 'mp4', 'title': 'Welcome to the Course!', - 'description': 'md5:8d66c13403783370af62ca97a7357bdd', + 'description': 'md5:65edb0affa582974de4625b9cdea1107', 'duration': 138.763, 'timestamp': 1479846621, 'upload_date': '20161122', @@ -88,10 +118,37 @@ class UpskillIE(UpskillBaseIE): }, { 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100', 'only_matching': True, + }, { + 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939', + 'only_matching': True, + }, { + 'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'only_matching': True, }] + @staticmethod + def _is_teachable(webpage): + return 'teachableTracker.linker:autoLink' in webpage and re.search( + r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com', + webpage) + + @staticmethod + def _extract_url(webpage, source_url): + if not TeachableIE._is_teachable(webpage): + return + if re.match(r'https?://[^/]+/(?:courses|p)', source_url): + return '%s%s' % (TeachableBaseIE._URL_PREFIX, source_url) + def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') or mobj.group('site_t') + video_id = mobj.group('id') + + self._login(site) + + prefixed = url.startswith(self._URL_PREFIX) + if prefixed: + url = url[len(self._URL_PREFIX):] webpage = self._download_webpage(url, video_id) @@ -113,12 +170,18 @@ class UpskillIE(UpskillBaseIE): } -class UpskillCourseIE(UpskillBaseIE): - _VALID_URL = r'https?://(?:www\.)?upskillcourses\.com/courses/(?:enrolled/)?(?P<id>[^/?#&]+)' +class TeachableCourseIE(TeachableBaseIE): + _VALID_URL = r'''(?x) + (?: + %shttps?://(?P<site_t>[^/]+)| + https?://(?:www\.)?(?P<site>%s) + ) + /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+) + ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/', 'info_dict': { - 'id': '119763', + 'id': 'essential-web-developer-course', 'title': 'The Essential Web Developer Course (Free)', }, 'playlist_count': 192, @@ -128,21 +191,37 @@ class UpskillCourseIE(UpskillBaseIE): }, { 'url': 'http://upskillcourses.com/courses/enrolled/119763', 'only_matching': True, + }, { + 'url': 'https://academy.gns3.com/courses/enrolled/423415', + 'only_matching': True, + }, { + 'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini', + 'only_matching': True, + }, { + 'url': 'teachable:https://filmsimplified.com/p/davinci-resolve-15-crash-course', + 'only_matching': True, }] @classmethod def suitable(cls, url): - return False if UpskillIE.suitable(url) else super( - UpskillCourseIE, cls).suitable(url) + return False if TeachableIE.suitable(url) else super( + TeachableCourseIE, cls).suitable(url) def _real_extract(self, url): - course_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') or mobj.group('site_t') + course_id = mobj.group('id') + + self._login(site) + + prefixed = url.startswith(self._URL_PREFIX) + if prefixed: + prefix = self._URL_PREFIX + url = url[len(prefix):] webpage = self._download_webpage(url, course_id) - course_id = self._search_regex( - r'data-course-id=["\'](\d+)', webpage, 'course id', - default=course_id) + url_base = 'https://%s/' % site entries = [] @@ -162,10 +241,13 @@ class UpskillCourseIE(UpskillBaseIE): title = self._html_search_regex( r'<span[^>]+class=["\']lecture-name[^>]+>([^<]+)', li, 'title', default=None) + entry_url = urljoin(url_base, lecture_url) + if prefixed: + entry_url = self._URL_PREFIX + entry_url entries.append( self.url_result( - urljoin('http://upskillcourses.com/', lecture_url), - ie=UpskillIE.ie_key(), video_id=lecture_id, + entry_url, + ie=TeachableIE.ie_key(), video_id=lecture_id, video_title=clean_html(title))) course_title = self._html_search_regex( diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 212ac80ab..645942dfd 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -203,17 +203,13 @@ class TEDIE(InfoExtractor): ext_url = None if service.lower() == 'youtube': ext_url = external.get('code') - return { - '_type': 'url', - 'url': ext_url or external['uri'], - } + + return self.url_result(ext_url or external['uri']) resources_ = player_talk.get('resources') or talk_info.get('resources') http_url = None for format_id, resources in resources_.items(): - if not isinstance(resources, dict): - continue if format_id == 'h264': for resource in resources: h264_url = resource.get('file') @@ -242,6 +238,8 @@ class TEDIE(InfoExtractor): 'tbr': int_or_none(resource.get('bitrate')), }) elif format_id == 'hls': + if not isinstance(resources, dict): + continue stream_url = url_or_none(resources.get('stream')) if not stream_url: continue @@ -267,6 +265,8 @@ class TEDIE(InfoExtractor): 'format_id': m3u8_format['format_id'].replace('hls', 'http'), 'protocol': 'http', }) + if f.get('acodec') == 'none': + del f['acodec'] formats.append(f) audio_download = talk_info.get('audioDownload') diff --git a/youtube_dl/extractor/testurl.py b/youtube_dl/extractor/testurl.py index 46918adb0..84a14a0bd 100644 --- a/youtube_dl/extractor/testurl.py +++ b/youtube_dl/extractor/testurl.py @@ -61,8 +61,4 @@ class TestURLIE(InfoExtractor): self.to_screen('Test URL: %s' % tc['url']) - return { - '_type': 'url', - 'url': tc['url'], - 'id': video_id, - } + return self.url_result(tc['url'], video_id=video_id) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index ffef5bf06..90b351cbb 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -39,9 +39,17 @@ class ThePlatformBaseIE(OnceIE): smil_url, video_id, note=note, query={'format': 'SMIL'}, headers=self.geo_verification_headers()) error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src') - if error_element is not None and error_element.attrib['src'].startswith( - 'http://link.theplatform.%s/s/errorFiles/Unavailable.' % self._TP_TLD): - raise ExtractorError(error_element.attrib['abstract'], expected=True) + if error_element is not None: + exception = find_xpath_attr( + error_element, _x('.//smil:param'), 'name', 'exception') + if exception is not None: + if exception.get('value') == 'GeoLocationBlocked': + self.raise_geo_restricted(error_element.attrib['abstract']) + elif error_element.attrib['src'].startswith( + 'http://link.theplatform.%s/s/errorFiles/Unavailable.' + % self._TP_TLD): + raise ExtractorError( + error_element.attrib['abstract'], expected=True) smil_formats = self._parse_smil_formats( meta, smil_url, video_id, namespace=default_ns, @@ -335,7 +343,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None): real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query) entry = self._download_json(real_url, video_id)['entries'][0] - main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None + main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else entry.get('plmedia$publicUrl') formats = [] subtitles = {} @@ -348,7 +356,8 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if first_video_id is None: first_video_id = cur_video_id duration = float_or_none(item.get('plfile$duration')) - for asset_type in item['plfile$assetTypes']: + file_asset_types = item.get('plfile$assetTypes') or compat_parse_qs(compat_urllib_parse_urlparse(smil_url).query)['assetTypes'] + for asset_type in file_asset_types: if asset_type in asset_types: continue asset_types.append(asset_type) diff --git a/youtube_dl/extractor/tiktok.py b/youtube_dl/extractor/tiktok.py new file mode 100644 index 000000000..083e9f36d --- /dev/null +++ b/youtube_dl/extractor/tiktok.py @@ -0,0 +1,117 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + compat_str, + ExtractorError, + int_or_none, + str_or_none, + try_get, + url_or_none, +) + + +class TikTokBaseIE(InfoExtractor): + def _extract_aweme(self, data): + video = data['video'] + description = str_or_none(try_get(data, lambda x: x['desc'])) + width = int_or_none(try_get(data, lambda x: video['width'])) + height = int_or_none(try_get(data, lambda x: video['height'])) + + format_urls = set() + formats = [] + for format_id in ( + 'play_addr_lowbr', 'play_addr', 'play_addr_h264', + 'download_addr'): + for format in try_get( + video, lambda x: x[format_id]['url_list'], list) or []: + format_url = url_or_none(format) + if not format_url: + continue + if format_url in format_urls: + continue + format_urls.add(format_url) + formats.append({ + 'url': format_url, + 'ext': 'mp4', + 'height': height, + 'width': width, + }) + self._sort_formats(formats) + + thumbnail = url_or_none(try_get( + video, lambda x: x['cover']['url_list'][0], compat_str)) + uploader = try_get(data, lambda x: x['author']['nickname'], compat_str) + timestamp = int_or_none(data.get('create_time')) + comment_count = int_or_none(data.get('comment_count')) or int_or_none( + try_get(data, lambda x: x['statistics']['comment_count'])) + repost_count = int_or_none(try_get( + data, lambda x: x['statistics']['share_count'])) + + aweme_id = data['aweme_id'] + + return { + 'id': aweme_id, + 'title': uploader or aweme_id, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'timestamp': timestamp, + 'comment_count': comment_count, + 'repost_count': repost_count, + 'formats': formats, + } + + +class TikTokIE(TikTokBaseIE): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>\d+)' + _TEST = { + 'url': 'https://m.tiktok.com/v/6606727368545406213.html', + 'md5': 'd584b572e92fcd48888051f238022420', + 'info_dict': { + 'id': '6606727368545406213', + 'ext': 'mp4', + 'title': 'Zureeal', + 'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay', + 'thumbnail': r're:^https?://.*~noop.image', + 'uploader': 'Zureeal', + 'timestamp': 1538248586, + 'upload_date': '20180929', + 'comment_count': int, + 'repost_count': int, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + data = self._parse_json(self._search_regex( + r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id) + return self._extract_aweme(data) + + +class TikTokUserIE(TikTokBaseIE): + _VALID_URL = r'https?://(?:m\.)?tiktok\.com/h5/share/usr/(?P<id>\d+)' + _TEST = { + 'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html', + 'info_dict': { + 'id': '188294915489964032', + }, + 'playlist_mincount': 24, + } + + def _real_extract(self, url): + user_id = self._match_id(url) + data = self._download_json( + 'https://m.tiktok.com/h5/share/usr/list/%s/' % user_id, user_id, + query={'_signature': '_'}) + entries = [] + for aweme in data['aweme_list']: + try: + entry = self._extract_aweme(aweme) + except ExtractorError: + continue + entry['extractor_key'] = TikTokIE.ie_key() + entries.append(entry) + return self.playlist_result(entries, user_id) diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 0c2f8f119..b3573c6e0 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -18,8 +18,9 @@ from ..utils import ( class TNAFlixNetworkBaseIE(InfoExtractor): # May be overridden in descendants if necessary _CONFIG_REGEX = [ - r'flashvars\.config\s*=\s*escape\("([^"]+)"', - r'<input[^>]+name="config\d?" value="([^"]+)"', + r'flashvars\.config\s*=\s*escape\("(?P<url>[^"]+)"', + r'<input[^>]+name="config\d?" value="(?P<url>[^"]+)"', + r'config\s*=\s*(["\'])(?P<url>(?:https?:)?//(?:(?!\1).)+)\1', ] _HOST = 'tna' _VKEY_SUFFIX = '' @@ -85,7 +86,8 @@ class TNAFlixNetworkBaseIE(InfoExtractor): webpage = self._download_webpage(url, display_id) cfg_url = self._proto_relative_url(self._html_search_regex( - self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:') + self._CONFIG_REGEX, webpage, 'flashvars.config', default=None, + group='url'), 'http:') if not cfg_url: inputs = self._hidden_inputs(webpage) @@ -94,7 +96,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor): cfg_xml = self._download_xml( cfg_url, display_id, 'Downloading metadata', - transform_source=fix_xml_ampersands) + transform_source=fix_xml_ampersands, headers={'Referer': url}) formats = [] diff --git a/youtube_dl/extractor/tv3.py b/youtube_dl/extractor/tv3.py deleted file mode 100644 index 3867ec90d..000000000 --- a/youtube_dl/extractor/tv3.py +++ /dev/null @@ -1,34 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class TV3IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tv3\.co\.nz/(?P<id>[^/]+)/tabid/\d+/articleID/\d+/MCat/\d+/Default\.aspx' - _TEST = { - 'url': 'http://www.tv3.co.nz/MOTORSPORT-SRS-SsangYong-Hampton-Downs-Round-3/tabid/3692/articleID/121615/MCat/2915/Default.aspx', - 'info_dict': { - 'id': '4659127992001', - 'ext': 'mp4', - 'title': 'CRC Motorsport: SRS SsangYong Hampton Downs Round 3 - S2015 Ep3', - 'description': 'SsangYong Racing Series returns for Round 3 with drivers from New Zealand and Australia taking to the grid at Hampton Downs raceway.', - 'uploader_id': '3812193411001', - 'upload_date': '20151213', - 'timestamp': 1449975272, - }, - 'expected_warnings': [ - 'Failed to download MPD manifest' - ], - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/3812193411001/default_default/index.html?videoId=%s' - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - brightcove_id = self._search_regex(r'<param\s*name="@videoPlayer"\s*value="(\d+)"', webpage, 'brightcove id') - return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/tvnow.py b/youtube_dl/extractor/tvnow.py index 60937616f..3c6a60c39 100644 --- a/youtube_dl/extractor/tvnow.py +++ b/youtube_dl/extractor/tvnow.py @@ -10,8 +10,9 @@ from ..utils import ( int_or_none, parse_iso8601, parse_duration, - try_get, + str_or_none, update_url_query, + urljoin, ) @@ -24,8 +25,7 @@ class TVNowBaseIE(InfoExtractor): def _call_api(self, path, video_id, query): return self._download_json( - 'https://api.tvnow.de/v3/' + path, - video_id, query=query) + 'https://api.tvnow.de/v3/' + path, video_id, query=query) def _extract_video(self, info, display_id): video_id = compat_str(info['id']) @@ -108,6 +108,11 @@ class TVNowIE(TVNowBaseIE): (?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+) ''' + @classmethod + def suitable(cls, url): + return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) or TVNowShowIE.suitable(url) + else super(TVNowIE, cls).suitable(url)) + _TESTS = [{ 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player', 'info_dict': { @@ -116,7 +121,6 @@ class TVNowIE(TVNowBaseIE): 'ext': 'mp4', 'title': 'Der neue Porsche 911 GT 3', 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', - 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1495994400, 'upload_date': '20170528', 'duration': 5283, @@ -161,136 +165,314 @@ class TVNowIE(TVNowBaseIE): info = self._call_api( 'movies/' + display_id, display_id, query={ 'fields': ','.join(self._VIDEO_FIELDS), - 'station': mobj.group(1), }) return self._extract_video(info, display_id) -class TVNowListBaseIE(TVNowBaseIE): - _SHOW_VALID_URL = r'''(?x) - (?P<base_url> - https?:// - (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/ - (?P<show_id>[^/]+) - ) +class TVNowNewIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?P<base_url>https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/ + (?:shows|serien))/ + (?P<show>[^/]+)-\d+/ + [^/]+/ + episode-\d+-(?P<episode>[^/?$&]+)-(?P<id>\d+) ''' - def _extract_list_info(self, display_id, show_id): - fields = list(self._SHOW_FIELDS) - fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) - fields.extend( - 'formatTabs.formatTabPages.container.movies.%s' % field - for field in self._VIDEO_FIELDS) - return self._call_api( - 'formats/seo', display_id, query={ - 'fields': ','.join(fields), - 'name': show_id + '.php' - }) - - -class TVNowListIE(TVNowListBaseIE): - _VALID_URL = r'%s/(?:list|jahr)/(?P<id>[^?\#&]+)' % TVNowListBaseIE._SHOW_VALID_URL - - _SHOW_FIELDS = ('title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', ) - _TESTS = [{ - 'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell', - 'info_dict': { - 'id': '28296', - 'title': '30 Minuten Deutschland - Aktuell', - }, - 'playlist_mincount': 1, - }, { - 'url': 'https://www.tvnow.de/vox/ab-ins-beet/list/staffel-14', - 'only_matching': True, - }, { - 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/2018/3', + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', 'only_matching': True, }] - @classmethod - def suitable(cls, url): - return (False if TVNowIE.suitable(url) - else super(TVNowListIE, cls).suitable(url)) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + base_url = re.sub(r'(?:shows|serien)', '_', mobj.group('base_url')) + show, episode = mobj.group('show', 'episode') + return self.url_result( + # Rewrite new URLs to the old format and use extraction via old API + # at api.tvnow.de as a loophole for bypassing premium content checks + '%s/%s/%s' % (base_url, show, episode), + ie=TVNowIE.ie_key(), video_id=mobj.group('id')) + + +class TVNowNewBaseIE(InfoExtractor): + def _call_api(self, path, video_id, query={}): + result = self._download_json( + 'https://apigw.tvnow.de/module/' + path, video_id, query=query) + error = result.get('error') + if error: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error), expected=True) + return result + + +""" +TODO: new apigw.tvnow.de based version of TVNowIE. Replace old TVNowIE with it +when api.tvnow.de is shut down. This version can't bypass premium checks though. +class TVNowIE(TVNowNewBaseIE): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/ + (?:shows|serien)/[^/]+/ + (?:[^/]+/)+ + (?P<display_id>[^/?$&]+)-(?P<id>\d+) + ''' + + _TESTS = [{ + # episode with annual navigation + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', + 'info_dict': { + 'id': '331082', + 'display_id': 'grip-das-motormagazin/der-neue-porsche-911-gt-3', + 'ext': 'mp4', + 'title': 'Der neue Porsche 911 GT 3', + 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1495994400, + 'upload_date': '20170528', + 'duration': 5283, + 'series': 'GRIP - Das Motormagazin', + 'season_number': 14, + 'episode_number': 405, + 'episode': 'Der neue Porsche 911 GT 3', + }, + }, { + # rtl2, episode with season navigation + 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471/staffel-3/episode-14-bernd-steht-seit-der-trennung-von-seiner-frau-allein-da-526124', + 'only_matching': True, + }, { + # rtlnitro + 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13/episode-5-auf-eigene-faust-pilot-366822', + 'only_matching': True, + }, { + # superrtl + 'url': 'https://www.tvnow.de/shows/die-lustigsten-schlamassel-der-welt-1221/staffel-2/episode-14-u-a-ketchup-effekt-364120', + 'only_matching': True, + }, { + # ntv + 'url': 'https://www.tvnow.de/shows/startup-news-10674/staffel-2/episode-39-goetter-in-weiss-387630', + 'only_matching': True, + }, { + # vox + 'url': 'https://www.tvnow.de/shows/auto-mobil-174/2017-11/episode-46-neues-vom-automobilmarkt-2017-11-19-17-00-00-380072', + 'only_matching': True, + }, { + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05/episode-405-der-neue-porsche-911-gt-3-331082', + 'only_matching': True, + }] + + def _extract_video(self, info, url, display_id): + config = info['config'] + source = config['source'] + + video_id = compat_str(info.get('id') or source['videoId']) + title = source['title'].strip() + + paths = [] + for manifest_url in (info.get('manifest') or {}).values(): + if not manifest_url: + continue + manifest_url = update_url_query(manifest_url, {'filter': ''}) + path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path') + if path in paths: + continue + paths.append(path) + + def url_repl(proto, suffix): + return re.sub( + r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub( + r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)', + '.ism/' + suffix, manifest_url)) + + formats = self._extract_mpd_formats( + url_repl('dash', '.mpd'), video_id, + mpd_id='dash', fatal=False) + formats.extend(self._extract_ism_formats( + url_repl('hss', 'Manifest'), + video_id, ism_id='mss', fatal=False)) + formats.extend(self._extract_m3u8_formats( + url_repl('hls', '.m3u8'), video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + if formats: + break + else: + if try_get(info, lambda x: x['rights']['isDrm']): + raise ExtractorError( + 'Video %s is DRM protected' % video_id, expected=True) + if try_get(config, lambda x: x['boards']['geoBlocking']['block']): + raise self.raise_geo_restricted() + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + self._sort_formats(formats) + + description = source.get('description') + thumbnail = url_or_none(source.get('poster')) + timestamp = unified_timestamp(source.get('previewStart')) + duration = parse_duration(source.get('length')) + + series = source.get('format') + season_number = int_or_none(self._search_regex( + r'staffel-(\d+)', url, 'season number', default=None)) + episode_number = int_or_none(self._search_regex( + r'episode-(\d+)', url, 'episode number', default=None)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'series': series, + 'season_number': season_number, + 'episode_number': episode_number, + 'episode': title, + 'formats': formats, + } def _real_extract(self, url): - base_url, show_id, season_id = re.match(self._VALID_URL, url).groups() + display_id, video_id = re.match(self._VALID_URL, url).groups() + info = self._call_api('player/' + video_id, video_id) + return self._extract_video(info, video_id, display_id) +""" - list_info = self._extract_list_info(season_id, show_id) - season = next( - season for season in list_info['formatTabs']['items'] - if season.get('seoheadline') == season_id) +class TVNowListBaseIE(TVNowNewBaseIE): + _SHOW_VALID_URL = r'''(?x) + (?P<base_url> + https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/(?:shows|serien)/ + [^/?#&]+-(?P<show_id>\d+) + ) + ''' - title = list_info.get('title') - headline = season.get('headline') - if title and headline: - title = '%s - %s' % (title, headline) - else: - title = headline or title + @classmethod + def suitable(cls, url): + return (False if TVNowNewIE.suitable(url) + else super(TVNowListBaseIE, cls).suitable(url)) + + def _extract_items(self, url, show_id, list_id, query): + items = self._call_api( + 'teaserrow/format/episode/' + show_id, list_id, + query=query)['items'] entries = [] - for container in season['formatTabPages']['items']: - items = try_get( - container, lambda x: x['container']['movies']['items'], - list) or [] - for info in items: - seo_url = info.get('seoUrl') - if not seo_url: - continue - video_id = info.get('id') - entries.append(self.url_result( - '%s/%s/player' % (base_url, seo_url), TVNowIE.ie_key(), - compat_str(video_id) if video_id else None)) + for item in items: + if not isinstance(item, dict): + continue + item_url = urljoin(url, item.get('url')) + if not item_url: + continue + video_id = str_or_none(item.get('id') or item.get('videoId')) + item_title = item.get('subheadline') or item.get('text') + entries.append(self.url_result( + item_url, ie=TVNowNewIE.ie_key(), video_id=video_id, + video_title=item_title)) - return self.playlist_result( - entries, compat_str(season.get('id') or season_id), title) + return self.playlist_result(entries, '%s/%s' % (show_id, list_id)) + + +class TVNowSeasonIE(TVNowListBaseIE): + _VALID_URL = r'%s/staffel-(?P<id>\d+)' % TVNowListBaseIE._SHOW_VALID_URL + _TESTS = [{ + 'url': 'https://www.tvnow.de/serien/alarm-fuer-cobra-11-die-autobahnpolizei-1815/staffel-13', + 'info_dict': { + 'id': '1815/13', + }, + 'playlist_mincount': 22, + }] + + def _real_extract(self, url): + _, show_id, season_id = re.match(self._VALID_URL, url).groups() + return self._extract_items( + url, show_id, season_id, {'season': season_id}) + + +class TVNowAnnualIE(TVNowListBaseIE): + _VALID_URL = r'%s/(?P<year>\d{4})-(?P<month>\d{2})' % TVNowListBaseIE._SHOW_VALID_URL + _TESTS = [{ + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669/2017-05', + 'info_dict': { + 'id': '1669/2017-05', + }, + 'playlist_mincount': 2, + }] + + def _real_extract(self, url): + _, show_id, year, month = re.match(self._VALID_URL, url).groups() + return self._extract_items( + url, show_id, '%s-%s' % (year, month), { + 'year': int(year), + 'month': int(month), + }) class TVNowShowIE(TVNowListBaseIE): _VALID_URL = TVNowListBaseIE._SHOW_VALID_URL - - _SHOW_FIELDS = ('id', 'title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - _VIDEO_FIELDS = () - _TESTS = [{ - 'url': 'https://www.tvnow.at/vox/ab-ins-beet', + # annual navigationType + 'url': 'https://www.tvnow.de/shows/grip-das-motormagazin-1669', 'info_dict': { - 'id': 'ab-ins-beet', - 'title': 'Ab ins Beet!', + 'id': '1669', }, - 'playlist_mincount': 7, + 'playlist_mincount': 73, }, { - 'url': 'https://www.tvnow.at/vox/ab-ins-beet/list', - 'only_matching': True, - }, { - 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/jahr/', - 'only_matching': True, + # season navigationType + 'url': 'https://www.tvnow.de/shows/armes-deutschland-11471', + 'info_dict': { + 'id': '11471', + }, + 'playlist_mincount': 3, }] @classmethod def suitable(cls, url): - return (False if TVNowIE.suitable(url) or TVNowListIE.suitable(url) + return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) else super(TVNowShowIE, cls).suitable(url)) def _real_extract(self, url): base_url, show_id = re.match(self._VALID_URL, url).groups() - list_info = self._extract_list_info(show_id, show_id) + result = self._call_api( + 'teaserrow/format/navigation/' + show_id, show_id) + + items = result['items'] entries = [] - for season_info in list_info['formatTabs']['items']: - season_url = season_info.get('seoheadline') - if not season_url: - continue - season_id = season_info.get('id') - entries.append(self.url_result( - '%s/list/%s' % (base_url, season_url), TVNowListIE.ie_key(), - compat_str(season_id) if season_id else None, - season_info.get('headline'))) + navigation = result.get('navigationType') + if navigation == 'annual': + for item in items: + if not isinstance(item, dict): + continue + year = int_or_none(item.get('year')) + if year is None: + continue + months = item.get('months') + if not isinstance(months, list): + continue + for month_dict in months: + if not isinstance(month_dict, dict) or not month_dict: + continue + month_number = int_or_none(list(month_dict.keys())[0]) + if month_number is None: + continue + entries.append(self.url_result( + '%s/%04d-%02d' % (base_url, year, month_number), + ie=TVNowAnnualIE.ie_key())) + elif navigation == 'season': + for item in items: + if not isinstance(item, dict): + continue + season_number = int_or_none(item.get('season')) + if season_number is None: + continue + entries.append(self.url_result( + '%s/staffel-%d' % (base_url, season_number), + ie=TVNowSeasonIE.ie_key())) + else: + raise ExtractorError('Unknown navigationType') - return self.playlist_result(entries, show_id, list_info.get('title')) + return self.playlist_result(entries, show_id) diff --git a/youtube_dl/extractor/twitcasting.py b/youtube_dl/extractor/twitcasting.py new file mode 100644 index 000000000..05f8aa9ce --- /dev/null +++ b/youtube_dl/extractor/twitcasting.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +import re + + +class TwitCastingIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^/]+\.)?twitcasting\.tv/(?P<uploader_id>[^/]+)/movie/(?P<id>\d+)' + _TEST = { + 'url': 'https://twitcasting.tv/ivetesangalo/movie/2357609', + 'md5': '745243cad58c4681dc752490f7540d7f', + 'info_dict': { + 'id': '2357609', + 'ext': 'mp4', + 'title': 'Recorded Live #2357609', + 'uploader_id': 'ivetesangalo', + 'description': "Moi! I'm live on TwitCasting from my iPhone.", + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + uploader_id = mobj.group('uploader_id') + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'(?s)<[^>]+id=["\']movietitle[^>]+>(.+?)</', + webpage, 'title', default=None) or self._html_search_meta( + 'twitter:title', webpage, fatal=True) + + m3u8_url = self._search_regex( + (r'data-movie-url=(["\'])(?P<url>(?:(?!\1).)+)\1', + r'(["\'])(?P<url>http.+?\.m3u8.*?)\1'), + webpage, 'm3u8 url', group='url') + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader_id': uploader_id, + 'formats': formats, + } diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index de41065d6..41d0b6be8 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -171,7 +171,8 @@ class TwitterCardIE(TwitterBaseIE): urls.append('https://twitter.com/i/videos/' + video_id) for u in urls: - webpage = self._download_webpage(u, video_id) + webpage = self._download_webpage( + u, video_id, headers={'Referer': 'https://twitter.com/'}) iframe_url = self._html_search_regex( r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', diff --git a/youtube_dl/extractor/uol.py b/youtube_dl/extractor/uol.py index e67083004..08f0c072e 100644 --- a/youtube_dl/extractor/uol.py +++ b/youtube_dl/extractor/uol.py @@ -61,7 +61,7 @@ class UOLIE(InfoExtractor): 'height': 360, }, '5': { - 'width': 1080, + 'width': 1280, 'height': 720, }, '6': { @@ -80,6 +80,10 @@ class UOLIE(InfoExtractor): 'width': 568, 'height': 320, }, + '11': { + 'width': 640, + 'height': 360, + } } def _real_extract(self, url): @@ -111,19 +115,31 @@ class UOLIE(InfoExtractor): 'ver': video_data.get('numRevision', 2), 'r': 'http://mais.uol.com.br', } + for k in ('token', 'sign'): + v = video_data.get(k) + if v: + query[k] = v + formats = [] for f in video_data.get('formats', []): f_url = f.get('url') or f.get('secureUrl') if not f_url: continue + f_url = update_url_query(f_url, query) format_id = str_or_none(f.get('id')) + if format_id == '10': + formats.extend(self._extract_m3u8_formats( + f_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + continue fmt = { 'format_id': format_id, - 'url': update_url_query(f_url, query), + 'url': f_url, + 'source_preference': 1, } fmt.update(self._FORMATS.get(format_id, {})) formats.append(fmt) - self._sort_formats(formats) + self._sort_formats(formats, ('height', 'width', 'source_preference', 'tbr', 'ext')) tags = [] for tag in video_data.get('tags', []): diff --git a/youtube_dl/extractor/usatoday.py b/youtube_dl/extractor/usatoday.py index e5678dc78..b2103448d 100644 --- a/youtube_dl/extractor/usatoday.py +++ b/youtube_dl/extractor/usatoday.py @@ -3,21 +3,23 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + ExtractorError, get_element_by_attribute, parse_duration, + try_get, update_url_query, - ExtractorError, ) from ..compat import compat_str class USATodayIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?usatoday\.com/(?:[^/]+/)*(?P<id>[^?/#]+)' - _TEST = { + _TESTS = [{ + # Brightcove Partner ID = 29906170001 'url': 'http://www.usatoday.com/media/cinematic/video/81729424/us-france-warn-syrian-regime-ahead-of-new-peace-talks/', - 'md5': '4d40974481fa3475f8bccfd20c5361f8', + 'md5': '033587d2529dc3411a1ab3644c3b8827', 'info_dict': { - 'id': '81729424', + 'id': '4799374959001', 'ext': 'mp4', 'title': 'US, France warn Syrian regime ahead of new peace talks', 'timestamp': 1457891045, @@ -25,8 +27,20 @@ class USATodayIE(InfoExtractor): 'uploader_id': '29906170001', 'upload_date': '20160313', } - } - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/29906170001/38a9eecc-bdd8-42a3-ba14-95397e48b3f8_default/index.html?videoId=%s' + }, { + # ui-video-data[asset_metadata][items][brightcoveaccount] = 28911775001 + 'url': 'https://www.usatoday.com/story/tech/science/2018/08/21/yellowstone-supervolcano-eruption-stop-worrying-its-blow/973633002/', + 'info_dict': { + 'id': '5824495846001', + 'ext': 'mp4', + 'title': 'Yellowstone more likely to crack rather than explode', + 'timestamp': 1534790612, + 'description': 'md5:3715e7927639a4f16b474e9391687c62', + 'uploader_id': '28911775001', + 'upload_date': '20180820', + } + }] + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' def _real_extract(self, url): display_id = self._match_id(url) @@ -35,10 +49,11 @@ class USATodayIE(InfoExtractor): if not ui_video_data: raise ExtractorError('no video on the webpage', expected=True) video_data = self._parse_json(ui_video_data, display_id) + item = try_get(video_data, lambda x: x['asset_metadata']['items'], dict) or {} return { '_type': 'url_transparent', - 'url': self.BRIGHTCOVE_URL_TEMPLATE % video_data['brightcove_id'], + 'url': self.BRIGHTCOVE_URL_TEMPLATE % (item.get('brightcoveaccount', '29906170001'), item.get('brightcoveid') or video_data['brightcove_id']), 'id': compat_str(video_data['id']), 'title': video_data['title'], 'thumbnail': video_data.get('thumbnail'), diff --git a/youtube_dl/extractor/videomore.py b/youtube_dl/extractor/videomore.py index 9b56630de..e3eda3327 100644 --- a/youtube_dl/extractor/videomore.py +++ b/youtube_dl/extractor/videomore.py @@ -4,8 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( int_or_none, + orderedSet, + parse_duration, + str_or_none, + unified_strdate, + url_or_none, xpath_element, xpath_text, ) @@ -13,7 +19,19 @@ from ..utils import ( class VideomoreIE(InfoExtractor): IE_NAME = 'videomore' - _VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)' + _VALID_URL = r'''(?x) + videomore:(?P<sid>\d+)$| + https?://(?:player\.)?videomore\.ru/ + (?: + (?: + embed| + [^/]+/[^/]+ + )/| + [^/]*\?.*?\btrack_id= + ) + (?P<id>\d+) + (?:[/?#&]|\.(?:xml|json)|$) + ''' _TESTS = [{ 'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617', 'md5': '44455a346edc0d509ac5b5a5b531dc35', @@ -79,6 +97,9 @@ class VideomoreIE(InfoExtractor): }, { 'url': 'videomore:367617', 'only_matching': True, + }, { + 'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=', + 'only_matching': True, }] @staticmethod @@ -136,7 +157,7 @@ class VideomoreIE(InfoExtractor): class VideomoreVideoIE(InfoExtractor): IE_NAME = 'videomore:video' - _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P<id>[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ # single video with og:video:iframe 'url': 'http://videomore.ru/elki_3', @@ -176,6 +197,9 @@ class VideomoreVideoIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so', + 'only_matching': True, }] @classmethod @@ -196,13 +220,16 @@ class VideomoreVideoIE(InfoExtractor): r'track-id=["\'](\d+)', r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id') video_url = 'videomore:%s' % video_id + else: + video_id = None - return self.url_result(video_url, VideomoreIE.ie_key()) + return self.url_result( + video_url, ie=VideomoreIE.ie_key(), video_id=video_id) class VideomoreSeasonIE(InfoExtractor): IE_NAME = 'videomore:season' - _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P<id>[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ 'url': 'http://videomore.ru/molodezhka/sezon_promo', 'info_dict': { @@ -210,8 +237,16 @@ class VideomoreSeasonIE(InfoExtractor): 'title': 'Молодежка Промо', }, 'playlist_mincount': 12, + }, { + 'url': 'http://videomore.ru/molodezhka/sezon_promo?utm_so', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return (False if (VideomoreIE.suitable(url) or VideomoreVideoIE.suitable(url)) + else super(VideomoreSeasonIE, cls).suitable(url)) + def _real_extract(self, url): display_id = self._match_id(url) @@ -219,9 +254,54 @@ class VideomoreSeasonIE(InfoExtractor): title = self._og_search_title(webpage) - entries = [ - self.url_result(item) for item in re.findall( - r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' - % display_id, webpage)] + data = self._parse_json( + self._html_search_regex( + r'\bclass=["\']seasons-tracks["\'][^>]+\bdata-custom-data=(["\'])(?P<value>{.+?})\1', + webpage, 'data', default='{}', group='value'), + display_id, fatal=False) + + entries = [] + + if data: + episodes = data.get('episodes') + if isinstance(episodes, list): + for ep in episodes: + if not isinstance(ep, dict): + continue + ep_id = int_or_none(ep.get('id')) + ep_url = url_or_none(ep.get('url')) + if ep_id: + e = { + 'url': 'videomore:%s' % ep_id, + 'id': compat_str(ep_id), + } + elif ep_url: + e = {'url': ep_url} + else: + continue + e.update({ + '_type': 'url', + 'ie_key': VideomoreIE.ie_key(), + 'title': str_or_none(ep.get('title')), + 'thumbnail': url_or_none(ep.get('image')), + 'duration': parse_duration(ep.get('duration')), + 'episode_number': int_or_none(ep.get('number')), + 'upload_date': unified_strdate(ep.get('date')), + }) + entries.append(e) + + if not entries: + entries = [ + self.url_result( + 'videomore:%s' % video_id, ie=VideomoreIE.ie_key(), + video_id=video_id) + for video_id in orderedSet(re.findall( + r':(?:id|key)=["\'](\d+)["\']', webpage))] + + if not entries: + entries = [ + self.url_result(item) for item in re.findall( + r'<a[^>]+href="((?:https?:)?//videomore\.ru/%s/[^/]+)"[^>]+class="widget-item-desc"' + % display_id, webpage)] return self.playlist_result(entries, display_id, title) diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py index d5d5b4c69..6e318479c 100644 --- a/youtube_dl/extractor/viewster.py +++ b/youtube_dl/extractor/viewster.py @@ -130,16 +130,16 @@ class ViewsterIE(InfoExtractor): def concat(suffix, sep='-'): return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix - for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'): - media = self._download_json( - 'https://public-api.viewster.com/movies/%s/video' % entry_id, - video_id, 'Downloading %s JSON' % concat(media_type, ' '), fatal=False, query={ - 'mediaType': media_type, - 'language': audio, - 'subtitle': subtitle, - }) - if not media: - continue + medias = self._download_json( + 'https://public-api.viewster.com/movies/%s/videos' % entry_id, + video_id, fatal=False, query={ + 'mediaTypes': ['application/f4m+xml', 'application/x-mpegURL', 'video/mp4'], + 'language': audio, + 'subtitle': subtitle, + }) + if not medias: + continue + for media in medias: video_url = media.get('Uri') if not video_url: continue diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 0a9239b62..6215b3258 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import json import re import itertools @@ -14,10 +15,13 @@ from ..compat import ( from ..utils import ( determine_ext, ExtractorError, + js_to_json, InAdvancePagedList, int_or_none, merge_dicts, NO_DEFAULT, + parse_filesize, + qualities, RegexNotFoundError, sanitized_Request, smuggle_url, @@ -27,7 +31,6 @@ from ..utils import ( unsmuggle_url, urlencode_postdata, unescapeHTML, - parse_filesize, ) @@ -390,6 +393,22 @@ class VimeoIE(VimeoBaseInfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://player.vimeo.com/video/68375962', + 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', + 'info_dict': { + 'id': '68375962', + 'ext': 'mp4', + 'title': 'youtube-dl password protected test video', + 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', + 'uploader_id': 'user18948128', + 'uploader': 'Jaime Marquínez Ferrándiz', + 'duration': 10, + }, + 'params': { + 'videopassword': 'youtube-dl', + }, + }, { 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', 'only_matching': True, @@ -416,6 +435,8 @@ class VimeoIE(VimeoBaseInfoExtractor): 'url': 'https://vimeo.com/160743502/abd0e13fb4', 'only_matching': True, } + # https://gettingthingsdone.com/workflowmap/ + # vimeo embed with check-password page protected by Referer header ] @staticmethod @@ -446,18 +467,22 @@ class VimeoIE(VimeoBaseInfoExtractor): urls = VimeoIE._extract_urls(url, webpage) return urls[0] if urls else None - def _verify_player_video_password(self, url, video_id): + def _verify_player_video_password(self, url, video_id, headers): password = self._downloader.params.get('videopassword') if password is None: raise ExtractorError('This video is protected by a password, use the --video-password option') - data = urlencode_postdata({'password': password}) - pass_url = url + '/check-password' - password_request = sanitized_Request(pass_url, data) - password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') - password_request.add_header('Referer', url) - return self._download_json( - password_request, video_id, - 'Verifying the password', 'Wrong password') + data = urlencode_postdata({ + 'password': base64.b64encode(password.encode()), + }) + headers = merge_dicts(headers, { + 'Content-Type': 'application/x-www-form-urlencoded', + }) + checked = self._download_json( + url + '/check-password', video_id, + 'Verifying the password', data=data, headers=headers) + if checked is False: + raise ExtractorError('Wrong video password', expected=True) + return checked def _real_initialize(self): self._login() @@ -551,6 +576,7 @@ class VimeoIE(VimeoBaseInfoExtractor): else: config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;') + config_re.append(r'\bconfig\s*=\s*({.+?})\s*;') config = self._search_regex(config_re, webpage, 'info section', flags=re.DOTALL) config = json.loads(config) @@ -569,7 +595,7 @@ class VimeoIE(VimeoBaseInfoExtractor): cause=e) else: if config.get('view') == 4: - config = self._verify_player_video_password(redirect_url, video_id) + config = self._verify_player_video_password(redirect_url, video_id, headers) vod = config.get('video', {}).get('vod', {}) @@ -1062,3 +1088,96 @@ class VimeoLikesIE(InfoExtractor): 'description': description, 'entries': pl, } + + +class VHXEmbedIE(InfoExtractor): + IE_NAME = 'vhx:embed' + _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)' + + def _call_api(self, video_id, access_token, path='', query=None): + return self._download_json( + 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={ + 'Authorization': 'Bearer ' + access_token, + }, query=query) + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + credentials = self._parse_json(self._search_regex( + r'(?s)credentials\s*:\s*({.+?}),', webpage, + 'config'), video_id, js_to_json) + access_token = credentials['access_token'] + + query = {} + for k, v in credentials.items(): + if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined': + if k == 'authUserToken': + query['auth_user_token'] = v + else: + query[k] = v + files = self._call_api(video_id, access_token, '/files', query) + + formats = [] + for f in files: + href = try_get(f, lambda x: x['_links']['source']['href']) + if not href: + continue + method = f.get('method') + if method == 'hls': + formats.extend(self._extract_m3u8_formats( + href, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif method == 'dash': + formats.extend(self._extract_mpd_formats( + href, video_id, mpd_id='dash', fatal=False)) + else: + fmt = { + 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])), + 'format_id': 'http', + 'preference': 1, + 'url': href, + 'vcodec': f.get('codec'), + } + quality = f.get('quality') + if quality: + fmt.update({ + 'format_id': 'http-' + quality, + 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)), + }) + formats.append(fmt) + self._sort_formats(formats) + + video_data = self._call_api(video_id, access_token) + title = video_data.get('title') or video_data['name'] + + subtitles = {} + for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []: + lang = subtitle.get('srclang') or subtitle.get('label') + for _link in subtitle.get('_links', {}).values(): + href = _link.get('href') + if not href: + continue + subtitles.setdefault(lang, []).append({ + 'url': href, + }) + + q = qualities(['small', 'medium', 'large', 'source']) + thumbnails = [] + for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): + thumbnails.append({ + 'id': thumbnail_id, + 'url': thumbnail_url, + 'preference': q(thumbnail_id), + }) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), + 'formats': formats, + 'subtitles': subtitles, + 'thumbnails': thumbnails, + 'timestamp': unified_timestamp(video_data.get('created_at')), + 'view_count': int_or_none(video_data.get('plays_count')), + } diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index ef8b9bcb7..b52d15ac6 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -293,8 +293,12 @@ class VKIE(VKBaseIE): # This video is no longer available, because its author has been blocked. 'url': 'https://vk.com/video-10639516_456240611', 'only_matching': True, - } - ] + }, + { + # The video is not available in your region. + 'url': 'https://vk.com/video-51812607_171445436', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -354,6 +358,9 @@ class VKIE(VKBaseIE): r'<!>This video is no longer available, because it has been deleted.': 'Video %s is no longer available, because it has been deleted.', + + r'<!>The video .+? is not available in your region.': + 'Video %s is not available in your region.', } for error_re, error_msg in ERRORS.items(): diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index ac0819c7c..6c060ae76 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -11,10 +11,12 @@ import time from .common import InfoExtractor from ..compat import ( + compat_HTTPError, compat_urllib_parse_urlencode, compat_urllib_parse, ) from ..utils import ( + ExtractorError, float_or_none, int_or_none, ) @@ -24,29 +26,41 @@ class VRVBaseIE(InfoExtractor): _API_DOMAIN = None _API_PARAMS = {} _CMS_SIGNING = {} + _TOKEN = None + _TOKEN_SECRET = '' def _call_api(self, path, video_id, note, data=None): + # https://tools.ietf.org/html/rfc5849#section-3 base_url = self._API_DOMAIN + '/core/' + path - encoded_query = compat_urllib_parse_urlencode({ - 'oauth_consumer_key': self._API_PARAMS['oAuthKey'], - 'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]), - 'oauth_signature_method': 'HMAC-SHA1', - 'oauth_timestamp': int(time.time()), - 'oauth_version': '1.0', - }) + query = [ + ('oauth_consumer_key', self._API_PARAMS['oAuthKey']), + ('oauth_nonce', ''.join([random.choice(string.ascii_letters) for _ in range(32)])), + ('oauth_signature_method', 'HMAC-SHA1'), + ('oauth_timestamp', int(time.time())), + ] + if self._TOKEN: + query.append(('oauth_token', self._TOKEN)) + encoded_query = compat_urllib_parse_urlencode(query) headers = self.geo_verification_headers() if data: data = json.dumps(data).encode() headers['Content-Type'] = 'application/json' - method = 'POST' if data else 'GET' - base_string = '&'.join([method, compat_urllib_parse.quote(base_url, ''), compat_urllib_parse.quote(encoded_query, '')]) + base_string = '&'.join([ + 'POST' if data else 'GET', + compat_urllib_parse.quote(base_url, ''), + compat_urllib_parse.quote(encoded_query, '')]) oauth_signature = base64.b64encode(hmac.new( - (self._API_PARAMS['oAuthSecret'] + '&').encode('ascii'), + (self._API_PARAMS['oAuthSecret'] + '&' + self._TOKEN_SECRET).encode('ascii'), base_string.encode(), hashlib.sha1).digest()).decode() encoded_query += '&oauth_signature=' + compat_urllib_parse.quote(oauth_signature, '') - return self._download_json( - '?'.join([base_url, encoded_query]), video_id, - note='Downloading %s JSON metadata' % note, headers=headers, data=data) + try: + return self._download_json( + '?'.join([base_url, encoded_query]), video_id, + note='Downloading %s JSON metadata' % note, headers=headers, data=data) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError(json.loads(e.cause.read().decode())['message'], expected=True) + raise def _call_cms(self, path, video_id, note): if not self._CMS_SIGNING: @@ -55,19 +69,22 @@ class VRVBaseIE(InfoExtractor): self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING, note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers()) - def _set_api_params(self, webpage, video_id): - if not self._API_PARAMS: - self._API_PARAMS = self._parse_json(self._search_regex( - r'window\.__APP_CONFIG__\s*=\s*({.+?})</script>', - webpage, 'api config'), video_id)['cxApiParams'] - self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co') - def _get_cms_resource(self, resource_key, video_id): return self._call_api( 'cms_resource', video_id, 'resource path', data={ 'resource_key': resource_key, })['__links__']['cms_resource']['href'] + def _real_initialize(self): + webpage = self._download_webpage( + 'https://vrv.co/', None, headers=self.geo_verification_headers()) + self._API_PARAMS = self._parse_json(self._search_regex( + [ + r'window\.__APP_CONFIG__\s*=\s*({.+?})(?:</script>|;)', + r'window\.__APP_CONFIG__\s*=\s*({.+})' + ], webpage, 'app config'), None)['cxApiParams'] + self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co') + class VRVIE(VRVBaseIE): IE_NAME = 'vrv' @@ -86,6 +103,22 @@ class VRVIE(VRVBaseIE): 'skip_download': True, }, }] + _NETRC_MACHINE = 'vrv' + + def _real_initialize(self): + super(VRVIE, self)._real_initialize() + + email, password = self._get_login_info() + if email is None: + return + + token_credentials = self._call_api( + 'authenticate/by:credentials', None, 'Token Credentials', data={ + 'email': email, + 'password': password, + }) + self._TOKEN = token_credentials['oauth_token'] + self._TOKEN_SECRET = token_credentials['oauth_token_secret'] def _extract_vrv_formats(self, url, video_id, stream_format, audio_lang, hardsub_lang): if not url or stream_format not in ('hls', 'dash'): @@ -116,26 +149,16 @@ class VRVIE(VRVBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - url, video_id, - headers=self.geo_verification_headers()) - media_resource = self._parse_json(self._search_regex( - r'window\.__INITIAL_STATE__\s*=\s*({.+?})</script>', - webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {} - video_data = media_resource.get('json') - if not video_data: - self._set_api_params(webpage, video_id) - episode_path = self._get_cms_resource( - 'cms:/episodes/' + video_id, video_id) - video_data = self._call_cms(episode_path, video_id, 'video') + episode_path = self._get_cms_resource( + 'cms:/episodes/' + video_id, video_id) + video_data = self._call_cms(episode_path, video_id, 'video') title = video_data['title'] - streams_json = media_resource.get('streams', {}).get('json', {}) - if not streams_json: - self._set_api_params(webpage, video_id) - streams_path = video_data['__links__']['streams']['href'] - streams_json = self._call_cms(streams_path, video_id, 'streams') + streams_path = video_data['__links__'].get('streams', {}).get('href') + if not streams_path: + self.raise_login_required() + streams_json = self._call_cms(streams_path, video_id, 'streams') audio_locale = streams_json.get('audio_locale') formats = [] @@ -200,11 +223,7 @@ class VRVSeriesIE(VRVBaseIE): def _real_extract(self, url): series_id = self._match_id(url) - webpage = self._download_webpage( - url, series_id, - headers=self.geo_verification_headers()) - self._set_api_params(webpage, series_id) seasons_path = self._get_cms_resource( 'cms:/seasons?series_id=' + series_id, series_id) seasons_data = self._call_cms(seasons_path, series_id, 'seasons') diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index 3dab9145b..ea234e3c5 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -40,11 +40,7 @@ class WimpIE(InfoExtractor): r'data-id=["\']([0-9A-Za-z_-]{11})'), webpage, 'video URL', default=None) if youtube_id: - return { - '_type': 'url', - 'url': youtube_id, - 'ie_key': YoutubeIE.ie_key(), - } + return self.url_result(youtube_id, YoutubeIE.ie_key()) info_dict = self._extract_jwplayer_data( webpage, video_id, require_title=False) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 2182d6fd4..fa142b974 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -12,7 +12,7 @@ from ..utils import ( class WistiaIE(InfoExtractor): - _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.net/embed/iframe/)(?P<id>[a-z0-9]+)' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P<id>[a-z0-9]+)' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' @@ -35,12 +35,18 @@ class WistiaIE(InfoExtractor): # with hls video 'url': 'wistia:807fafadvk', 'only_matching': True, + }, { + 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt', + 'only_matching': True, + }, { + 'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json', + 'only_matching': True, }] @staticmethod def _extract_url(webpage): match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage) if match: return unescapeHTML(match.group('url')) diff --git a/youtube_dl/extractor/wwe.py b/youtube_dl/extractor/wwe.py new file mode 100644 index 000000000..bebc77bb5 --- /dev/null +++ b/youtube_dl/extractor/wwe.py @@ -0,0 +1,140 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + try_get, + unescapeHTML, + url_or_none, + urljoin, +) + + +class WWEBaseIE(InfoExtractor): + _SUBTITLE_LANGS = { + 'English': 'en', + 'Deutsch': 'de', + } + + def _extract_entry(self, data, url, video_id=None): + video_id = compat_str(video_id or data['nid']) + title = data['title'] + + formats = self._extract_m3u8_formats( + data['file'], video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + description = data.get('description') + thumbnail = urljoin(url, data.get('image')) + series = data.get('show_name') + episode = data.get('episode_name') + + subtitles = {} + tracks = data.get('tracks') + if isinstance(tracks, list): + for track in tracks: + if not isinstance(track, dict): + continue + if track.get('kind') != 'captions': + continue + track_file = url_or_none(track.get('file')) + if not track_file: + continue + label = track.get('label') + lang = self._SUBTITLE_LANGS.get(label, label) or 'en' + subtitles.setdefault(lang, []).append({ + 'url': track_file, + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'series': series, + 'episode': episode, + 'formats': formats, + 'subtitles': subtitles, + } + + +class WWEIE(WWEBaseIE): + _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*videos/(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.wwe.com/videos/daniel-bryan-vs-andrade-cien-almas-smackdown-live-sept-4-2018', + 'md5': '92811c6a14bfc206f7a6a9c5d9140184', + 'info_dict': { + 'id': '40048199', + 'ext': 'mp4', + 'title': 'Daniel Bryan vs. Andrade "Cien" Almas: SmackDown LIVE, Sept. 4, 2018', + 'description': 'md5:2d7424dbc6755c61a0e649d2a8677f67', + 'thumbnail': r're:^https?://.*\.jpg$', + } + }, { + 'url': 'https://de.wwe.com/videos/gran-metalik-vs-tony-nese-wwe-205-live-sept-4-2018', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + landing = self._parse_json( + self._html_search_regex( + r'(?s)Drupal\.settings\s*,\s*({.+?})\s*\)\s*;', + webpage, 'drupal settings'), + display_id)['WWEVideoLanding'] + + data = landing['initialVideo']['playlist'][0] + video_id = landing.get('initialVideoId') + + info = self._extract_entry(data, url, video_id) + info['display_id'] = display_id + return info + + +class WWEPlaylistIE(WWEBaseIE): + _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.wwe.com/shows/raw/2018-11-12', + 'info_dict': { + 'id': '2018-11-12', + }, + 'playlist_mincount': 11, + }, { + 'url': 'http://www.wwe.com/article/walk-the-prank-wwe-edition', + 'only_matching': True, + }, { + 'url': 'https://www.wwe.com/shows/wwenxt/article/matt-riddle-interview', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if WWEIE.suitable(url) else super(WWEPlaylistIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + entries = [] + for mobj in re.finditer( + r'data-video\s*=\s*(["\'])(?P<data>{.+?})\1', webpage): + video = self._parse_json( + mobj.group('data'), display_id, transform_source=unescapeHTML, + fatal=False) + if not video: + continue + data = try_get(video, lambda x: x['playlist'][0], dict) + if not data: + continue + try: + entry = self._extract_entry(data, url) + except Exception: + continue + entry['extractor_key'] = WWEIE.ie_key() + entries.append(entry) + + return self.playlist_result(entries, display_id) diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index efee95651..ec2d913fc 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -45,7 +45,7 @@ class XVideosIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - 'http://www.xvideos.com/video%s/' % video_id, video_id) + 'https://www.xvideos.com/video%s/' % video_id, video_id) mobj = re.search(r'<h1 class="inlineError">(.+?)</h1>', webpage) if mobj: diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index ea0bce784..d4eccb4b2 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -68,11 +68,9 @@ class YouPornIE(InfoExtractor): request.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(request, display_id) - title = self._search_regex( - [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1', - r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'], - webpage, 'title', group='title', - default=None) or self._og_search_title( + title = self._html_search_regex( + r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>', + webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or self._html_search_meta( 'title', webpage, fatal=True) @@ -134,7 +132,11 @@ class YouPornIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - description = self._og_search_description(webpage, default=None) + description = self._html_search_regex( + r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>', + webpage, 'description', + default=None) or self._og_search_description( + webpage, default=None) thumbnail = self._search_regex( r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1', webpage, 'thumbnail', fatal=False, group='thumbnail') diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py index 6602f7c03..c8dc29bd8 100644 --- a/youtube_dl/extractor/yourporn.py +++ b/youtube_dl/extractor/yourporn.py @@ -14,6 +14,7 @@ class YourPornIE(InfoExtractor): 'ext': 'mp4', 'title': 'md5:c9f43630bd968267672651ba905a7d35', 'thumbnail': r're:^https?://.*\.jpg$', + 'age_limit': 18 }, } @@ -26,7 +27,7 @@ class YourPornIE(InfoExtractor): self._search_regex( r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info', group='data'), - video_id)[video_id]) + video_id)[video_id]).replace('/cdn/', '/cdn3/') title = (self._search_regex( r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title', @@ -38,4 +39,5 @@ class YourPornIE(InfoExtractor): 'url': video_url, 'title': title, 'thumbnail': thumbnail, + 'age_limit': 18 } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 78203ef84..c8bf98b58 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -41,12 +41,14 @@ from ..utils import ( remove_quotes, remove_start, smuggle_url, + str_or_none, str_to_int, try_get, unescapeHTML, unified_strdate, unsmuggle_url, uppercase_escape, + url_or_none, urlencode_postdata, ) @@ -496,11 +498,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', 'upload_date': '20121002', - 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], 'duration': 10, + 'view_count': int, 'like_count': int, 'dislike_count': int, 'start_time': 1, @@ -524,7 +526,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Icona Pop', 'uploader_id': 'IconaPop', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', - 'license': 'Standard YouTube License', 'creator': 'Icona Pop', 'track': 'I Love It (feat. Charli XCX)', 'artist': 'Icona Pop', @@ -537,14 +538,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': '07FYdnEawAQ', 'ext': 'mp4', 'upload_date': '20130703', - 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', + 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)', 'alt_title': 'Tunnel Vision', - 'description': 'md5:64249768eec3bc4276236606ea996373', + 'description': 'md5:07dab3356cde4199048e4c7cd93471e1', 'duration': 419, 'uploader': 'justintimberlakeVEVO', 'uploader_id': 'justintimberlakeVEVO', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', - 'license': 'Standard YouTube License', 'creator': 'Justin Timberlake', 'track': 'Tunnel Vision', 'artist': 'Justin Timberlake', @@ -563,7 +563,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'SET India', 'uploader_id': 'setindia', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', - 'license': 'Standard YouTube License', 'age_limit': 18, } }, @@ -578,11 +577,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'phihag', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', 'upload_date': '20121002', - 'license': 'Standard YouTube License', 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', 'categories': ['Science & Technology'], 'tags': ['youtube-dl'], 'duration': 10, + 'view_count': int, 'like_count': int, 'dislike_count': int, }, @@ -601,7 +600,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', 'description': '', 'uploader': '8KVIDEO', - 'license': 'Standard YouTube License', 'title': 'UHDTV TEST 8K VIDEO.mp4' }, 'params': { @@ -616,13 +614,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'info_dict': { 'id': 'IB3lcPjvWLA', 'ext': 'm4a', - 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', - 'description': 'md5:1900ed86ee514927b9e00fbead6969a5', + 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', + 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', 'duration': 244, 'uploader': 'AfrojackVEVO', 'uploader_id': 'AfrojackVEVO', 'upload_date': '20131011', - 'license': 'Standard YouTube License', }, 'params': { 'youtube_include_dash_manifest': True, @@ -636,13 +633,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', - 'alt_title': 'Shake It Off', - 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', + 'description': 'md5:bec2185232c05479482cb5a9b82719bf', 'duration': 242, 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', - 'license': 'Standard YouTube License', 'creator': 'Taylor Swift', }, 'params': { @@ -658,10 +653,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'ext': 'mp4', 'duration': 219, 'upload_date': '20100909', - 'uploader': 'TJ Kirk', + 'uploader': 'Amazing Atheist', 'uploader_id': 'TheAmazingAtheist', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', - 'license': 'Standard YouTube License', 'title': 'Burning Everyone\'s Koran', 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', } @@ -679,7 +673,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'WitcherGame', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', 'upload_date': '20140605', - 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -688,7 +681,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', 'info_dict': { 'id': '6kLq3WMV1nU', - 'ext': 'webm', + 'ext': 'mp4', 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', 'duration': 246, @@ -696,7 +689,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'LloydVEVO', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', 'upload_date': '20110629', - 'license': 'Standard YouTube License', 'age_limit': 18, }, }, @@ -714,7 +706,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'creator': 'deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', - 'license': 'Standard YouTube License', 'title': 'Deadmau5 - Some Chords (HD)', 'alt_title': 'Some Chords', }, @@ -732,7 +723,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20150827', 'uploader_id': 'olympic', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', - 'license': 'Standard YouTube License', 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', 'uploader': 'Olympic', 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', @@ -754,7 +744,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', 'uploader': '孫ᄋᄅ', - 'license': 'Standard YouTube License', 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', }, }, @@ -788,7 +777,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'dorappi2000', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', 'uploader': 'dorappi2000', - 'license': 'Standard YouTube License', 'formats': 'mincount:31', }, 'skip': 'not actual anymore', @@ -804,7 +792,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'Airtek', 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', - 'license': 'Standard YouTube License', 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', }, 'params': { @@ -877,6 +864,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'This video is not available.', }, { # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536) @@ -913,7 +901,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader_id': 'IronSoulElf', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', 'uploader': 'IronSoulElf', - 'license': 'Standard YouTube License', 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', 'track': 'Dark Walk - Position Music', 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', @@ -1017,13 +1004,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'iqKdEhx-dD4', 'ext': 'mp4', 'title': 'Isolation - Mind Field (Ep 1)', - 'description': 'md5:25b78d2f64ae81719f5c96319889b736', + 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f', 'duration': 2085, 'upload_date': '20170118', 'uploader': 'Vsauce', 'uploader_id': 'Vsauce', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', - 'license': 'Standard YouTube License', 'series': 'Mind Field', 'season_number': 1, 'episode_number': 1, @@ -1049,7 +1035,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'uploader': 'New Century Foundation', 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', - 'license': 'Standard YouTube License', }, 'params': { 'skip_download': True, @@ -1073,6 +1058,31 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://invidio.us/watch?v=BaW_jenozKc', 'only_matching': True, }, + { + # DRM protected + 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', + 'only_matching': True, + }, + { + # Video with unsupported adaptive stream type formats + 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', + 'info_dict': { + 'id': 'Z4Vy8R84T1U', + 'ext': 'mp4', + 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 433, + 'upload_date': '20130923', + 'uploader': 'Amelia Putri Harwita', + 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', + 'formats': 'maxcount:10', + }, + 'params': { + 'skip_download': True, + 'youtube_include_dash_manifest': False, + }, + } ] def __init__(self, *args, **kwargs): @@ -1101,7 +1111,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', + r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -1188,8 +1198,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): funcname = self._search_regex( (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', - r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', - r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\('), + r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(', + r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', + r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), jscode, 'Initial JS player signature function name', group='sig') jsi = JSInterpreter(jscode) @@ -1382,8 +1393,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._downloader.report_warning(err_msg) return {} - def _mark_watched(self, video_id, video_info): - playback_url = video_info.get('videostats_playback_base_url', [None])[0] + def _mark_watched(self, video_id, video_info, player_response): + playback_url = url_or_none(try_get( + player_response, + lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get( + video_info, lambda x: x['videostats_playback_base_url'][0])) if not playback_url: return parsed_playback_url = compat_urlparse.urlparse(playback_url) @@ -1532,12 +1546,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if dash_mpd and dash_mpd[0] not in dash_mpds: dash_mpds.append(dash_mpd[0]) + def add_dash_mpd_pr(pl_response): + dash_mpd = url_or_none(try_get( + pl_response, lambda x: x['streamingData']['dashManifestUrl'], + compat_str)) + if dash_mpd and dash_mpd not in dash_mpds: + dash_mpds.append(dash_mpd) + is_live = None view_count = None def extract_view_count(v_info): return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) + player_response = {} + # Get video info embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: @@ -1580,7 +1603,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if args.get('livestream') == '1' or args.get('live_playback') == 1: is_live = True sts = ytplayer_config.get('sts') + if not player_response: + pl_response = str_or_none(args.get('player_response')) + if pl_response: + pl_response = self._parse_json(pl_response, video_id, fatal=False) + if isinstance(pl_response, dict): + player_response = pl_response if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): + add_dash_mpd_pr(player_response) # We also try looking in get_video_info since it may contain different dashmpd # URL that points to a DASH manifest with possibly different itag set (some itags # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH @@ -1608,6 +1638,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if not video_info_webpage: continue get_video_info = compat_parse_qs(video_info_webpage) + if not player_response: + pl_response = get_video_info.get('player_response', [None])[0] + if isinstance(pl_response, dict): + player_response = pl_response + add_dash_mpd_pr(player_response) add_dash_mpd(get_video_info) if view_count is None: view_count = extract_view_count(get_video_info) @@ -1653,9 +1688,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '"token" parameter not in video info for unknown reason', video_id=video_id) + if video_info.get('license_info'): + raise ExtractorError('This video is DRM protected.', expected=True) + + video_details = try_get( + player_response, lambda x: x['videoDetails'], dict) or {} + # title if 'title' in video_info: video_title = video_info['title'][0] + elif 'title' in player_response: + video_title = video_details['title'] else: self._downloader.report_warning('Unable to extract video title') video_title = '_' @@ -1691,33 +1734,41 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: video_description = '' - if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False): + if not smuggled_data.get('force_singlefeed', False): if not self._downloader.params.get('noplaylist'): - entries = [] - feed_ids = [] - multifeed_metadata_list = video_info['multifeed_metadata_list'][0] - for feed in multifeed_metadata_list.split(','): - # Unquote should take place before split on comma (,) since textual - # fields may contain comma as well (see - # https://github.com/rg3/youtube-dl/issues/8536) - feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) - entries.append({ - '_type': 'url_transparent', - 'ie_key': 'Youtube', - 'url': smuggle_url( - '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), - {'force_singlefeed': True}), - 'title': '%s (%s)' % (video_title, feed_data['title'][0]), - }) - feed_ids.append(feed_data['id'][0]) - self.to_screen( - 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' - % (', '.join(feed_ids), video_id)) - return self.playlist_result(entries, video_id, video_title, video_description) - self.to_screen('Downloading just video %s because of --no-playlist' % video_id) + multifeed_metadata_list = try_get( + player_response, + lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'], + compat_str) or try_get( + video_info, lambda x: x['multifeed_metadata_list'][0], compat_str) + if multifeed_metadata_list: + entries = [] + feed_ids = [] + for feed in multifeed_metadata_list.split(','): + # Unquote should take place before split on comma (,) since textual + # fields may contain comma as well (see + # https://github.com/rg3/youtube-dl/issues/8536) + feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) + entries.append({ + '_type': 'url_transparent', + 'ie_key': 'Youtube', + 'url': smuggle_url( + '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), + {'force_singlefeed': True}), + 'title': '%s (%s)' % (video_title, feed_data['title'][0]), + }) + feed_ids.append(feed_data['id'][0]) + self.to_screen( + 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' + % (', '.join(feed_ids), video_id)) + return self.playlist_result(entries, video_id, video_title, video_description) + else: + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) if view_count is None: view_count = extract_view_count(video_info) + if view_count is None and video_details: + view_count = int_or_none(video_details.get('viewCount')) # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: @@ -1753,11 +1804,34 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'height': int_or_none(width_height[1]), } q = qualities(['small', 'medium', 'hd720']) + streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) + if streaming_formats: + for fmt in streaming_formats: + itag = str_or_none(fmt.get('itag')) + if not itag: + continue + quality = fmt.get('quality') + quality_label = fmt.get('qualityLabel') or quality + formats_spec[itag] = { + 'asr': int_or_none(fmt.get('audioSampleRate')), + 'filesize': int_or_none(fmt.get('contentLength')), + 'format_note': quality_label, + 'fps': int_or_none(fmt.get('fps')), + 'height': int_or_none(fmt.get('height')), + 'quality': q(quality), + # bitrate for itag 43 is always 2147483647 + 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, + 'width': int_or_none(fmt.get('width')), + } formats = [] for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) if 'itag' not in url_data or 'url' not in url_data: continue + stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) + # Unsupported FORMAT_STREAM_TYPE_OTF + if stream_type == 3: + continue format_id = url_data['itag'][0] url = url_data['url'][0] @@ -1801,7 +1875,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: player_version = self._search_regex( [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], + r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version @@ -1835,7 +1909,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): filesize = int_or_none(url_data.get( 'clen', [None])[0]) or _extract_filesize(url) - quality = url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0] + quality = url_data.get('quality', [None])[0] more_fields = { 'filesize': filesize, @@ -1843,7 +1917,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'width': width, 'height': height, 'fps': int_or_none(url_data.get('fps', [None])[0]), - 'format_note': quality, + 'format_note': url_data.get('quality_label', [None])[0] or quality, 'quality': q(quality), } for key, value in more_fields.items(): @@ -1871,34 +1945,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'http_chunk_size': 10485760, } formats.append(dct) - elif video_info.get('hlsvp'): - manifest_url = video_info['hlsvp'][0] - formats = [] - m3u8_formats = self._extract_m3u8_formats( - manifest_url, video_id, 'mp4', fatal=False) - for a_format in m3u8_formats: - itag = self._search_regex( - r'/itag/(\d+)/', a_format['url'], 'itag', default=None) - if itag: - a_format['format_id'] = itag - if itag in self._formats: - dct = self._formats[itag].copy() - dct.update(a_format) - a_format = dct - a_format['player_url'] = player_url - # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming - a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' - formats.append(a_format) else: - error_message = clean_html(video_info.get('reason', [None])[0]) - if not error_message: - error_message = extract_unavailable_message() - if error_message: - raise ExtractorError(error_message, expected=True) - raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') + manifest_url = ( + url_or_none(try_get( + player_response, + lambda x: x['streamingData']['hlsManifestUrl'], + compat_str)) or + url_or_none(try_get( + video_info, lambda x: x['hlsvp'][0], compat_str))) + if manifest_url: + formats = [] + m3u8_formats = self._extract_m3u8_formats( + manifest_url, video_id, 'mp4', fatal=False) + for a_format in m3u8_formats: + itag = self._search_regex( + r'/itag/(\d+)/', a_format['url'], 'itag', default=None) + if itag: + a_format['format_id'] = itag + if itag in self._formats: + dct = self._formats[itag].copy() + dct.update(a_format) + a_format = dct + a_format['player_url'] = player_url + # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming + a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' + formats.append(a_format) + else: + error_message = clean_html(video_info.get('reason', [None])[0]) + if not error_message: + error_message = extract_unavailable_message() + if error_message: + raise ExtractorError(error_message, expected=True) + raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info') # uploader - video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str) + video_uploader = try_get( + video_info, lambda x: x['author'][0], + compat_str) or str_or_none(video_details.get('author')) if video_uploader: video_uploader = compat_urllib_parse_unquote_plus(video_uploader) else: @@ -1981,7 +2064,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>', video_webpage) if m_episode: - series = m_episode.group('series') + series = unescapeHTML(m_episode.group('series')) season_number = int(m_episode.group('season')) episode_number = int(m_episode.group('episode')) else: @@ -2011,12 +2094,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor): like_count = _extract_count('like') dislike_count = _extract_count('dislike') + if view_count is None: + view_count = str_to_int(self._search_regex( + r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage, + 'view count', default=None)) + # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) automatic_captions = self.extract_automatic_captions(video_id, video_webpage) video_duration = try_get( video_info, lambda x: int_or_none(x['length_seconds'][0])) + if not video_duration: + video_duration = int_or_none(video_details.get('lengthSeconds')) if not video_duration: video_duration = parse_duration(self._html_search_meta( 'duration', video_webpage, 'video duration')) @@ -2084,7 +2174,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self._sort_formats(formats) - self.mark_watched(video_id, video_info) + self.mark_watched(video_id, video_info, player_response) return { 'id': video_id, @@ -2131,7 +2221,11 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): (?:https?://)? (?:\w+\.)? (?: - youtube\.com/ + (?: + youtube\.com| + invidio\.us + ) + / (?: (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) \? (?:.*?[&;])*? (?:p|a|list)= @@ -2244,6 +2338,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', 'categories': ['People & Blogs'], 'tags': list, + 'view_count': int, 'like_count': int, 'dislike_count': int, }, @@ -2282,6 +2377,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): # music album playlist 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', 'only_matching': True, + }, { + 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', + 'only_matching': True, }] def _real_initialize(self): diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index bbe0aecb6..896276301 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -22,7 +22,7 @@ class ZattooPlatformBaseIE(InfoExtractor): _power_guide_hash = None def _host_url(self): - return 'https://%s' % self._HOST + return 'https://%s' % (self._API_HOST if hasattr(self, '_API_HOST') else self._HOST) def _login(self): username, password = self._get_login_info() @@ -286,6 +286,7 @@ class ZattooLiveIE(ZattooBaseIE): class NetPlusIE(ZattooIE): _NETRC_MACHINE = 'netplus' _HOST = 'netplus.tv' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -300,7 +301,7 @@ class MNetTVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.tvplus.m-net.de/watch/abc/123-abc', + 'url': 'https://tvplus.m-net.de/watch/abc/123-abc', 'only_matching': True, }] @@ -311,7 +312,7 @@ class WalyTVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.player.waly.tv/watch/abc/123-abc', + 'url': 'https://player.waly.tv/watch/abc/123-abc', 'only_matching': True, }] @@ -319,6 +320,7 @@ class WalyTVIE(ZattooIE): class BBVTVIE(ZattooIE): _NETRC_MACHINE = 'bbvtv' _HOST = 'bbv-tv.net' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -330,6 +332,7 @@ class BBVTVIE(ZattooIE): class VTXTVIE(ZattooIE): _NETRC_MACHINE = 'vtxtv' _HOST = 'vtxtv.ch' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -341,6 +344,7 @@ class VTXTVIE(ZattooIE): class MyVisionTVIE(ZattooIE): _NETRC_MACHINE = 'myvisiontv' _HOST = 'myvisiontv.ch' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -355,7 +359,7 @@ class GlattvisionTVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.iptv.glattvision.ch/watch/abc/123-abc', + 'url': 'https://iptv.glattvision.ch/watch/abc/123-abc', 'only_matching': True, }] @@ -363,6 +367,7 @@ class GlattvisionTVIE(ZattooIE): class SAKTVIE(ZattooIE): _NETRC_MACHINE = 'saktv' _HOST = 'saktv.ch' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -377,7 +382,7 @@ class EWETVIE(ZattooIE): _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.tvonline.ewe.de/watch/abc/123-abc', + 'url': 'https://tvonline.ewe.de/watch/abc/123-abc', 'only_matching': True, }] @@ -385,6 +390,7 @@ class EWETVIE(ZattooIE): class QuantumTVIE(ZattooIE): _NETRC_MACHINE = 'quantumtv' _HOST = 'quantum-tv.com' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ @@ -395,11 +401,11 @@ class QuantumTVIE(ZattooIE): class OsnatelTVIE(ZattooIE): _NETRC_MACHINE = 'osnateltv' - _HOST = 'onlinetv.osnatel.de' + _HOST = 'tvonline.osnatel.de' _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ - 'url': 'https://www.onlinetv.osnatel.de/watch/abc/123-abc', + 'url': 'https://tvonline.osnatel.de/watch/abc/123-abc', 'only_matching': True, }] @@ -407,6 +413,7 @@ class OsnatelTVIE(ZattooIE): class EinsUndEinsTVIE(ZattooIE): _NETRC_MACHINE = '1und1tv' _HOST = '1und1.tv' + _API_HOST = 'www.%s' % _HOST _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) _TESTS = [{ diff --git a/youtube_dl/extractor/zype.py b/youtube_dl/extractor/zype.py new file mode 100644 index 000000000..3b16e703b --- /dev/null +++ b/youtube_dl/extractor/zype.py @@ -0,0 +1,57 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class ZypeIE(InfoExtractor): + _VALID_URL = r'https?://player\.zype\.com/embed/(?P<id>[\da-fA-F]+)\.js\?.*?api_key=[^&]+' + _TEST = { + 'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false', + 'md5': 'eaee31d474c76a955bdaba02a505c595', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + 'ext': 'mp4', + 'title': 'Smoky Barbecue Favorites', + 'thumbnail': r're:^https?://.*\.jpe?g', + }, + } + + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//player\.zype\.com/embed/[\da-fA-F]+\.js\?.*?api_key=.+?)\1', + webpage)] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex( + r'video_title\s*[:=]\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, + 'title', group='value') + + m3u8_url = self._search_regex( + r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', webpage, + 'm3u8 url', group='url') + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) + + thumbnail = self._search_regex( + r'poster\s*[:=]\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'thumbnail', + default=False, group='url') + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 757b496a1..b952b0970 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -9,9 +9,6 @@ import re from .common import AudioConversionError, PostProcessor -from ..compat import ( - compat_subprocess_get_DEVNULL, -) from ..utils import ( encodeArgument, encodeFilename, @@ -79,6 +76,20 @@ class FFmpegPostProcessor(PostProcessor): programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] prefer_ffmpeg = True + def get_ffmpeg_version(path): + ver = get_exe_version(path, args=['-version']) + if ver: + regexs = [ + r'(?:\d+:)?([0-9.]+)-[0-9]+ubuntu[0-9.]+$', # Ubuntu, see [1] + r'n([0-9.]+)$', # Arch Linux + # 1. http://www.ducea.com/2006/06/17/ubuntu-package-version-naming-explanation/ + ] + for regex in regexs: + mobj = re.match(regex, ver) + if mobj: + ver = mobj.group(1) + return ver + self.basename = None self.probe_basename = None @@ -110,11 +121,10 @@ class FFmpegPostProcessor(PostProcessor): self._paths = dict( (p, os.path.join(location, p)) for p in programs) self._versions = dict( - (p, get_exe_version(self._paths[p], args=['-version'])) - for p in programs) + (p, get_ffmpeg_version(self._paths[p])) for p in programs) if self._versions is None: self._versions = dict( - (p, get_exe_version(p, args=['-version'])) for p in programs) + (p, get_ffmpeg_version(p)) for p in programs) self._paths = dict((p, p) for p in programs) if prefer_ffmpeg is False: @@ -152,27 +162,45 @@ class FFmpegPostProcessor(PostProcessor): return self._paths[self.probe_basename] def get_audio_codec(self, path): - if not self.probe_available: - raise PostProcessingError('ffprobe or avprobe not found. Please install one.') + if not self.probe_available and not self.available: + raise PostProcessingError('ffprobe/avprobe and ffmpeg/avconv not found. Please install one.') try: - cmd = [ - encodeFilename(self.probe_executable, True), - encodeArgument('-show_streams'), - encodeFilename(self._ffmpeg_filename_argument(path), True)] + if self.probe_available: + cmd = [ + encodeFilename(self.probe_executable, True), + encodeArgument('-show_streams')] + else: + cmd = [ + encodeFilename(self.executable, True), + encodeArgument('-i')] + cmd.append(encodeFilename(self._ffmpeg_filename_argument(path), True)) if self._downloader.params.get('verbose', False): - self._downloader.to_screen('[debug] %s command line: %s' % (self.basename, shell_quote(cmd))) - handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE, stdin=subprocess.PIPE) - output = handle.communicate()[0] - if handle.wait() != 0: + self._downloader.to_screen( + '[debug] %s command line: %s' % (self.basename, shell_quote(cmd))) + handle = subprocess.Popen( + cmd, stderr=subprocess.PIPE, + stdout=subprocess.PIPE, stdin=subprocess.PIPE) + stdout_data, stderr_data = handle.communicate() + expected_ret = 0 if self.probe_available else 1 + if handle.wait() != expected_ret: return None except (IOError, OSError): return None - audio_codec = None - for line in output.decode('ascii', 'ignore').split('\n'): - if line.startswith('codec_name='): - audio_codec = line.split('=')[1].strip() - elif line.strip() == 'codec_type=audio' and audio_codec is not None: - return audio_codec + output = (stdout_data if self.probe_available else stderr_data).decode('ascii', 'ignore') + if self.probe_available: + audio_codec = None + for line in output.split('\n'): + if line.startswith('codec_name='): + audio_codec = line.split('=')[1].strip() + elif line.strip() == 'codec_type=audio' and audio_codec is not None: + return audio_codec + else: + # Stream #FILE_INDEX:STREAM_INDEX[STREAM_ID](LANGUAGE): CODEC_TYPE: CODEC_NAME + mobj = re.search( + r'Stream\s*#\d+:\d+(?:\[0x[0-9a-f]+\])?(?:\([a-z]{3}\))?:\s*Audio:\s*([0-9a-z]+)', + output) + if mobj: + return mobj.group(1) return None def run_ffmpeg_multiple_files(self, input_paths, out_path, opts): @@ -384,9 +412,8 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): opts += ['-c:s', 'mov_text'] for (i, lang) in enumerate(sub_langs): opts.extend(['-map', '%d:0' % (i + 1)]) - lang_code = ISO639Utils.short2long(lang) - if lang_code is not None: - opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) + lang_code = ISO639Utils.short2long(lang) or lang + opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) temp_filename = prepend_extension(filename, 'temp') self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index e84d35d4d..d0cb65814 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -39,6 +39,7 @@ from .compat import ( compat_HTMLParser, compat_basestring, compat_chr, + compat_cookiejar, compat_ctypes_WINFUNCTYPE, compat_etree_fromstring, compat_expanduser, @@ -1139,6 +1140,33 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): req, **kwargs) +class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): + def save(self, filename=None, ignore_discard=False, ignore_expires=False): + # Store session cookies with `expires` set to 0 instead of an empty + # string + for cookie in self: + if cookie.expires is None: + cookie.expires = 0 + compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires) + + def load(self, filename=None, ignore_discard=False, ignore_expires=False): + compat_cookiejar.MozillaCookieJar.load(self, filename, ignore_discard, ignore_expires) + # Session cookies are denoted by either `expires` field set to + # an empty string or 0. MozillaCookieJar only recognizes the former + # (see [1]). So we need force the latter to be recognized as session + # cookies on our own. + # Session cookies may be important for cookies-based authentication, + # e.g. usually, when user does not check 'Remember me' check box while + # logging in on a site, some important cookies are stored as session + # cookies so that not recognizing them will result in failed login. + # 1. https://bugs.python.org/issue17164 + for cookie in self: + # Treat `expires=0` cookies as session cookies + if cookie.expires == 0: + cookie.expires = None + cookie.discard = True + + class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor): def __init__(self, cookiejar=None): compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar) @@ -1840,7 +1868,7 @@ def urljoin(base, path): path = path.decode('utf-8') if not isinstance(path, compat_str) or not path: return None - if re.match(r'^(?:https?:)?//', path): + if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path): return path if isinstance(base, bytes): base = base.decode('utf-8') @@ -2940,6 +2968,7 @@ class ISO639Utils(object): 'gv': 'glv', 'ha': 'hau', 'he': 'heb', + 'iw': 'heb', # Replaced by he in 1989 revision 'hi': 'hin', 'ho': 'hmo', 'hr': 'hrv', @@ -2949,6 +2978,7 @@ class ISO639Utils(object): 'hz': 'her', 'ia': 'ina', 'id': 'ind', + 'in': 'ind', # Replaced by id in 1989 revision 'ie': 'ile', 'ig': 'ibo', 'ii': 'iii', @@ -3063,6 +3093,7 @@ class ISO639Utils(object): 'wo': 'wol', 'xh': 'xho', 'yi': 'yid', + 'ji': 'yid', # Replaced by yi in 1989 revision 'yo': 'yor', 'za': 'zha', 'zh': 'zho', @@ -3948,8 +3979,12 @@ def write_xattr(path, key, value): def random_birthday(year_field, month_field, day_field): + start_date = datetime.date(1950, 1, 1) + end_date = datetime.date(1995, 12, 31) + offset = random.randint(0, (end_date - start_date).days) + random_date = start_date + datetime.timedelta(offset) return { - year_field: str(random.randint(1950, 1995)), - month_field: str(random.randint(1, 12)), - day_field: str(random.randint(1, 31)), + year_field: str(random_date.year), + month_field: str(random_date.month), + day_field: str(random_date.day), } diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 2b3b584a4..18c1f8d4c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.09.18' +__version__ = '2019.01.24'