diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index b84559932..f529e3f4b 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 *2018.12.17*. 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 Issues with outdated version will be rejected.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 **2018.12.17** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.01.27*. 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 Issues with outdated version will be rejected.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 **2019.01.27** ### 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 2018.12.17 +[debug] youtube-dl version 2019.01.27 [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/CONTRIBUTING.md b/CONTRIBUTING.md index cba87190d..6c1739860 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -153,15 +153,19 @@ 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/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](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: +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! @@ -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 +320,26 @@ title = self._search_regex( webpage, 'title', group='title') ``` -### Use safe conversion functions +### 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 convenience conversion and parsing functions 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. @@ -302,6 +347,8 @@ Use `url_or_none` for safe URL processing. Use `try_get` for safe metadata extraction from parsed JSON. +Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. + Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. #### More examples diff --git a/ChangeLog b/ChangeLog index 510013e89..d94fe36ec 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,143 @@ +version 2019.01.27 + +Core ++ [extractor/common] Extract season in _json_ld +* [postprocessor/ffmpeg] Fallback to ffmpeg/avconv for audio codec detection + (#681) + +Extractors +* [vice] Fix extraction for locked videos (#16248) ++ [wakanim] Detect DRM protected videos ++ [wakanim] Add support for wakanim.tv (#14374) +* [usatoday] Fix extraction for videos with custom brightcove partner id + (#18990) +* [drtv] Fix extraction (#18989) +* [nhk] Extend URL regular expression (#18968) +* [go] Fix Adobe Pass requests for Disney Now (#18901) ++ [openload] Add support for oload.club (#18969) + + +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 diff --git a/README.md b/README.md index a1d2904c0..c1572f771 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 @@ -667,7 +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 @@ -675,6 +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. @@ -1025,15 +1027,19 @@ 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/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](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: +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! @@ -1129,11 +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: @@ -1166,7 +1194,26 @@ title = self._search_regex( webpage, 'title', group='title') ``` -### Use safe conversion functions +### 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 convenience conversion and parsing functions 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. @@ -1174,6 +1221,8 @@ Use `url_or_none` for safe URL processing. Use `try_get` for safe metadata extraction from parsed JSON. +Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. + Explore [`youtube_dl/utils.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/utils.py) for more useful convenience functions. #### More examples diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 31d20f255..6377bf815 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -320,6 +320,7 @@ - **Fusion** - **Fux** - **FXNetworks** + - **Gaia** - **GameInformer** - **GameOne** - **gameone:playlist** @@ -360,6 +361,7 @@ - **hitbox** - **hitbox:live** - **HitRecord** + - **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau - **HornBunny** - **HotNewHipHop** - **hotstar** @@ -370,6 +372,8 @@ - **HRTiPlaylist** - **Huajiao**: 花椒直播 - **HuffPost**: Huffington Post + - **Hungama** + - **HungamaSong** - **Hypem** - **Iconosquare** - **ign.com** @@ -383,6 +387,7 @@ - **IndavideoEmbed** - **InfoQ** - **Instagram** + - **instagram:tag**: Instagram hashtag search - **instagram:user**: Instagram user profile - **Internazionale** - **InternetVideoArchive** @@ -438,6 +443,7 @@ - **Lecture2Go** - **Lecturio** - **LecturioCourse** + - **LecturioDeCourse** - **LEGO** - **Lemonde** - **Lenta** @@ -539,8 +545,6 @@ - **MyviEmbed** - **MyVisionTV** - **n-tv.de** - - **natgeo** - - **natgeo:episodeguide** - **natgeo:video** - **Naver** - **NBA** @@ -641,6 +645,7 @@ - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek - **OsnatelTV** + - **OutsideTV** - **PacktPub** - **PacktPubCourse** - **PandaTV**: 熊猫TV @@ -665,6 +670,7 @@ - **Pinkbike** - **Pladform** - **play.fm** + - **PlayPlusTV** - **PlaysTV** - **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz - **Playvid** @@ -933,7 +939,9 @@ - **TVNet** - **TVNoe** - **TVNow** - - **TVNowList** + - **TVNowAnnual** + - **TVNowNew** + - **TVNowSeason** - **TVNowShow** - **tvp**: Telewizja Polska - **tvp:embed**: Telewizja Polska @@ -1061,6 +1069,7 @@ - **VVVVID** - **VyboryMos** - **Vzaar** + - **Wakanim** - **Walla** - **WalyTV** - **washingtonpost** diff --git a/test/helper.py b/test/helper.py index aa9a1c9b2..e62aab11e 100644 --- a/test/helper.py +++ b/test/helper.py @@ -153,15 +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, @@ -237,6 +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 diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 06be72616..75fa0bbb7 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -497,7 +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: 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_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/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 4493fd0e1..80ed8d7e5 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1063,21 +1063,24 @@ class YoutubeDL(object): if not m: STR_OPERATORS = { '=': operator.eq, - '!=': operator.ne, '^=': lambda attr, value: attr.startswith(value), '$=': lambda attr, value: attr.endswith(value), '*=': lambda attr, value: value in attr, } str_operator_rex = re.compile(r'''(?x) \s*(?Pext|acodec|vcodec|container|protocol|format_id) - \s*(?P%s)(?P\s*\?)? + \s*(?P!\s*)?(?P%s)(?P\s*\?)? \s*(?P[a-zA-Z0-9._-]+) \s*$ ''' % '|'.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) 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 b32f74a37..c4362be88 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -79,17 +79,27 @@ class ACastIE(InfoExtractor): class ACastChannelIE(InfoExtractor): IE_NAME = 'acast:channel' - _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/#?]+)' - _TEST = { - 'url': 'https://www.acast.com/condenasttraveler', + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?acast\.com/| + play\.acast\.com/s/ + ) + (?P[^/#?]+) + ''' + _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 @@ -102,7 +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/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/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']+\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']+src=(["\'])(?P(?:/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.+?)\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 43b4732aa..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): @@ -43,10 +46,16 @@ class BitChuteIE(InfoExtractor): 'description', webpage, 'title', default=None) or self._og_search_description(webpage) + format_urls = [] + for mobj in re.finditer( + r'addWebSeed\s*\(\s*(["\'])(?P(?:(?!\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(?:(?!\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/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[^/?#]+)-(?: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/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 e5f8136fc..c4ea2882f 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1239,17 +1239,30 @@ 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')) + info.update({ + 'season': unescapeHTML(part_of_season.get('name')), + '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')), @@ -1586,6 +1599,7 @@ 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 @@ -1657,11 +1671,16 @@ 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: @@ -2614,7 +2633,7 @@ 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, @@ -2641,12 +2660,9 @@ 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 4a68d092b..5e2cbe41d 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -144,7 +144,7 @@ class CrunchyrollBaseIE(InfoExtractor): class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): IE_NAME = 'crunchyroll' - _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|(?:[^/]*/){1,2}[^/?&]*?)(?P[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', 'info_dict': { @@ -269,6 +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 = { 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\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\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\d+)' - _TEST = { + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P\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/discovery.py b/youtube_dl/extractor/discovery.py index 44fbc41bb..b70c307a7 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -94,11 +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[0-9a-z.-]+)/(?P[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 d72f52e36..b40be42e6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -411,6 +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, @@ -451,6 +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 @@ -469,6 +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 ( @@ -489,7 +495,11 @@ 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, + InstagramUserIE, + InstagramTagIE, +) from .internazionale import InternazionaleIE from .internetvideoarchive import InternetVideoArchiveIE from .iprima import IPrimaIE @@ -684,8 +694,7 @@ from .myvi import ( from .myvidster import MyVidsterIE from .nationalgeographic import ( NationalGeographicVideoIE, - NationalGeographicIE, - NationalGeographicEpisodeGuideIE, + NationalGeographicTVIE, ) from .naver import NaverIE from .nba import NBAIE @@ -828,6 +837,7 @@ from .orf import ( ORFOE1IE, ORFIPTVIE, ) +from .outsidetv import OutsideTVIE from .packtpub import ( PacktPubIE, PacktPubCourseIE, @@ -856,6 +866,7 @@ 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 @@ -1193,7 +1204,9 @@ from .tvnet import TVNetIE from .tvnoe import TVNoeIE from .tvnow import ( TVNowIE, - TVNowListIE, + TVNowNewIE, + TVNowSeasonIE, + TVNowAnnualIE, TVNowShowIE, ) from .tvp import ( @@ -1363,6 +1376,7 @@ from .vuclip import VuClipIE from .vvvvid import VVVVIDIE from .vyborymos import VyboryMosIE from .vzaar import VzaarIE +from .wakanim import WakanimIE from .walla import WallaIE from .washingtonpost import ( WashingtonPostIE, @@ -1486,6 +1500,7 @@ from .zattoo import ( QuantumTVIE, QuicklineIE, QuicklineLiveIE, + SaltTVIE, SAKTVIE, VTXTVIE, WalyTVIE, diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 11d6c9c32..568656542 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -1,17 +1,22 @@ # 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 ..compat import ( + compat_HTTPError, + compat_str, + compat_urllib_parse_unquote, +) from ..utils import ( - HEADRequest, + ExtractorError, int_or_none, parse_age_limit, parse_duration, try_get, unified_timestamp, - update_url_query, ) @@ -31,6 +36,7 @@ class FOXIE(AdobePassIE): 'upload_date': '20170901', 'creator': 'FOX', 'series': 'Gotham', + 'age_limit': 14, }, 'params': { 'skip_download': True, @@ -44,48 +50,54 @@ class FOXIE(AdobePassIE): 'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/', 'only_matching': True, }] + _HOME_PAGE_URL = 'https://www.fox.com/' + _API_KEY = 'abdcbed02c124d393b39e818a4312055' + _access_token = None + + def _call_api(self, path, video_id, data=None): + headers = { + 'X-Api-Key': self._API_KEY, + } + 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): + if not self._access_token: + mvpd_auth = self._get_cookies(self._HOME_PAGE_URL).get('mvpd-auth') + if mvpd_auth: + self._access_token = (self._parse_json(compat_urllib_parse_unquote( + mvpd_auth.value), None, fatal=False) or {}).get('accessToken') + if not self._access_token: + 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, - 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'] + 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) data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} + 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') - 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')) - - if data.get('authRequired'): - resource = self._get_mvpd_resource( - 'fbc-fox', title, video.get('guid'), rating) - release_url = update_url_query( - release_url, { - 'auth': self._extract_mvpd_auth( - url, video_id, 'fbc-fox', resource) - }) subtitles = {} for doc_rel in video.get('documentReleases', []): @@ -98,36 +110,19 @@ 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(video.get('contentRating')), '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/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']+src="/player/(\d+)"', + r']+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[^/?]+).*?\bfullplayer=(?Pfeature|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/generic.py b/youtube_dl/extractor/generic.py index 65b482333..067de28cd 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2197,10 +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: 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%s)\.)?go\.com/(?:(?:[^/]+/)*(?Pvdka\w+)|(?:[^/]+/)*(?P[^/?#]+))'\ @@ -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[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': '', + }, + '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(?:(?!\1).)+)\1', + webpage, 'title', default=None, group='url') or + self._html_search_regex( + r'

([^<]+)

', 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/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\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\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/instagram.py b/youtube_dl/extractor/instagram.py index 7e0e838f0..ffd87b55f 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -227,44 +227,37 @@ class InstagramIE(InfoExtractor): } -class InstagramUserIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P[^/]{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, - } - } +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] @@ -276,21 +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 @@ -348,14 +346,80 @@ class InstagramUserIE(InfoExtractor): 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) - - 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 InstagramUserIE(InstagramPlaylistIE): + _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P[^/]{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[^/]+)' + 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/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[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[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/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']+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"', + r']+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[if])=(?P[\w_]+)' + _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P[ift])=(?P[\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[\'"])(?P%s)(?P=q1)' % LiveLeakIE._VALID_URL, + r'(?:logourl\s*:\s*|window\.open\()(?P[\'"])(?P%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/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\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(?:(?!\1).)+)\1', webpage, 'video URL', group='url') - title = '%s (Preview)' % self._html_search_regex( - r']+class="m-a-0"[^>]*>([^<]+)', webpage, 'title') + title = self._html_search_regex( + (r']+class=["\']item-title[^>]+>([^<]+)', + r']+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(?:(?!\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)]+class="views-wrapper"[^>]*>(.+?)[^/?]+)' - - _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'], +class NationalGeographicTVIE(FOXIE): + _VALID_URL = r'https?://(?:www\.)?nationalgeographic\.com/tv/watch/(?P[\da-fA-F]+)' + _TESTS = [{ + 'url': 'https://www.nationalgeographic.com/tv/watch/6a875e6e734b479beda26438c9f21138/', + 'info_dict': { + 'id': '6a875e6e734b479beda26438c9f21138', + 'ext': 'mp4', + 'title': 'Why Nat Geo? Valley of the Boom', + 'description': 'The lives of prominent figures in the tech world, including their friendships, rivalries, victories and failures.', + 'timestamp': 1542662458, + 'upload_date': '20181119', + 'age_limit': 14, }, - { - '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'], + 'params': { + 'skip_download': True, }, - { - '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[^/]+)/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']+class="select-seasons[^"]*".*?]*>(.*?)', - webpage, 'selected season') - entries = [ - self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic') - for entry_url in re.findall('(?s)]+class="col-inner"[^>]*?>.*?]+href="([^"]+)"', webpage)] - return self.playlist_result( - entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')), - '%s - %s' % (show, selected_season)) + }] + _HOME_PAGE_URL = 'https://www.nationalgeographic.com/tv/' + _API_KEY = '238bb0a0c2aba67922c48709ce0c06fd' 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[^/]+/[^/?#&]+)' - _TEST = { + _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/(?:vod|ondemand)/(?P[^/]+/[^/?#&]+)' + _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/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[^/?#&]+))?' + _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P[^/?#&]+))?' _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/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 cf51e4770..b713e78b8 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor): (?:www\.)? (?: openload\.(?:co|io|link)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun) + oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club) ) )/ (?:f|embed)/ @@ -334,6 +334,9 @@ class OpenloadIE(InfoExtractor): }, { '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' 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[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\d+)/(?P\d+)/(?P\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+)/(?P\d+)/(?P\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'(?Phttps?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P\d+))' - _TEST = { + _VALID_URL = r'(?Phttps?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\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/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[0-9]+)/(?P[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/pornhub.py b/youtube_dl/extractor/pornhub.py index e377de196..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, @@ -22,7 +24,29 @@ 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']+\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?:// @@ -307,7 +331,7 @@ class PornHubIE(InfoExtractor): } -class PornHubPlaylistBaseIE(InfoExtractor): +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 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\d+)' + _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/(?:(?:[^/]+/)*program_(?P\d+)|(?Pmediaplayer-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/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/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(?:https?:)?//.+?\.m3u8.*?)\1', webpage, + r'(?:url|source)\s*:\s*(["\'])(?P(?:https?:)?//.+?\.m3u8.*?)\1', webpage, 'stream url', group='url') title = self._og_search_title(webpage) 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[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net)/(?:f|embed)/(?P[^/?#&]+)' _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/ted.py b/youtube_dl/extractor/ted.py index f9b6aa48f..645942dfd 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -203,10 +203,8 @@ 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') @@ -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/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 6798ef4c3..b3573c6e0 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -96,7 +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/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)(?:/|$))(?P[^/?\#&]+) ''' + @classmethod + def suitable(cls, url): + return (False if TVNowNewIE.suitable(url) or TVNowSeasonIE.suitable(url) or TVNowAnnualIE.suitable(url) or TVNowShowIE.suitable(url) + else super(TVNowIE, cls).suitable(url)) + _TESTS = [{ 'url': 'https://www.tvnow.de/rtl2/grip-das-motormagazin/der-neue-porsche-911-gt-3/player', 'info_dict': { @@ -116,7 +121,6 @@ class TVNowIE(TVNowBaseIE): 'ext': 'mp4', 'title': 'Der neue Porsche 911 GT 3', 'description': 'md5:6143220c661f9b0aae73b245e5d898bb', - 'thumbnail': r're:^https?://.*\.jpg$', '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 - https?:// - (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/ - (?P[^/]+) - ) +class TVNowNewIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?Phttps?:// + (?:www\.)?tvnow\.(?:de|at|ch)/ + (?:shows|serien))/ + (?P[^/]+)-\d+/ + [^/]+/ + episode-\d+-(?P[^/?$&]+)-(?P\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[^?\#&]+)' % 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[^/?$&]+)-(?P\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 + https?:// + (?:www\.)?tvnow\.(?:de|at|ch)/(?:shows|serien)/ + [^/?#&]+-(?P\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\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\d{4})-(?P\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/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[^?/#]+)' - _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/vice.py b/youtube_dl/extractor/vice.py index 538258617..8fdfd743d 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -94,7 +94,6 @@ class ViceIE(AdobePassIE): 'url': 'https://www.viceland.com/en_us/video/thursday-march-1-2018/5a8f2d7ff1cdb332dd446ec1', 'only_matching': True, }] - _PREPLAY_HOST = 'vms.vice' @staticmethod def _extract_urls(webpage): @@ -158,9 +157,8 @@ class ViceIE(AdobePassIE): }) try: - host = 'www.viceland' if is_locked else self._PREPLAY_HOST preplay = self._download_json( - 'https://%s.com/%s/video/preplay/%s' % (host, locale, video_id), + 'https://vms.vice.com/%s/video/preplay/%s' % (locale, video_id), video_id, query=query) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401): 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\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P\d+)(?:[/?#&]|\.(?:xml|json)|$)' + _VALID_URL = r'''(?x) + videomore:(?P\d+)$| + https?://(?:player\.)?videomore\.ru/ + (?: + (?: + embed| + [^/]+/[^/]+ + )/| + [^/]*\?.*?\btrack_id= + ) + (?P\d+) + (?:[/?#&]|\.(?:xml|json)|$) + ''' _TESTS = [{ 'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617', 'md5': '44455a346edc0d509ac5b5a5b531dc35', @@ -79,6 +97,9 @@ class VideomoreIE(InfoExtractor): }, { 'url': 'videomore:367617', 'only_matching': True, + }, { + 'url': 'https://player.videomore.ru/?partner_id=97&track_id=736234&autoplay=0&userToken=', + 'only_matching': True, }] @staticmethod @@ -136,7 +157,7 @@ class VideomoreIE(InfoExtractor): class VideomoreVideoIE(InfoExtractor): IE_NAME = 'videomore:video' - _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?:(?:[^/]+/){2})?(?P[^/?#&]+)(?:/*|[?#&].*?)$' _TESTS = [{ # single video with og:video:iframe 'url': 'http://videomore.ru/elki_3', @@ -176,6 +197,9 @@ class VideomoreVideoIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://videomore.ru/molodezhka/6_sezon/29_seriya?utm_so', + 'only_matching': True, }] @classmethod @@ -196,13 +220,16 @@ class VideomoreVideoIE(InfoExtractor): r'track-id=["\'](\d+)', r'xcnt_product_id\s*=\s*(\d+)'), webpage, 'video id') video_url = 'videomore:%s' % video_id + else: + video_id = None - return self.url_result(video_url, VideomoreIE.ie_key()) + return self.url_result( + video_url, ie=VideomoreIE.ie_key(), video_id=video_id) class VideomoreSeasonIE(InfoExtractor): IE_NAME = 'videomore:season' - _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P[^/]+/[^/?#&]+)[/?#&]*$' + _VALID_URL = r'https?://videomore\.ru/(?!embed)(?P[^/]+/[^/?#&]+)(?:/*|[?#&].*?)$' _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']+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{.+?})\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']+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/vimeo.py b/youtube_dl/extractor/vimeo.py index 5e15f060b..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 @@ -392,6 +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, @@ -418,6 +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 @@ -448,18 +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() @@ -572,7 +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', {}) diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index 483a3be3a..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*({.+?})', - 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*({.+?})(?:|;)', + 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'): @@ -116,28 +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*({.+?})(?:|;)', - r'window\.__INITIAL_STATE__\s*=\s*({.+})' - ], 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 = [] @@ -202,11 +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/wakanim.py b/youtube_dl/extractor/wakanim.py new file mode 100644 index 000000000..f9a2395d9 --- /dev/null +++ b/youtube_dl/extractor/wakanim.py @@ -0,0 +1,66 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + merge_dicts, + urljoin, +) + + +class WakanimIE(InfoExtractor): + _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P\d+)' + _TESTS = [{ + 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu', + 'info_dict': { + 'id': '2997', + 'ext': 'mp4', + 'title': 'Episode 02', + 'description': 'md5:2927701ea2f7e901de8bfa8d39b2852d', + 'series': 'The Asterisk War (OmU.)', + 'season_number': 1, + 'episode': 'Episode 02', + 'episode_number': 2, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + }, + }, { + # DRM Protected + 'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/7843/sword-art-online-alicization-omu-arc-2-folge-15-omu', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + m3u8_url = urljoin(url, self._search_regex( + r'file\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'm3u8 url', + group='url')) + # https://docs.microsoft.com/en-us/azure/media-services/previous/media-services-content-protection-overview#streaming-urls + encryption = self._search_regex( + r'encryption%3D(c(?:enc|bc(?:s-aapl)?))', + m3u8_url, 'encryption', default=None) + if encryption and encryption in ('cenc', 'cbcs-aapl'): + raise ExtractorError('This video is DRM protected.', expected=True) + + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + info = self._search_json_ld(webpage, video_id, default={}) + + title = self._search_regex( + (r']+\bclass=["\']episode_h1[^>]+\btitle=(["\'])(?P(?:(?!\1).)+)\1', + r'<span[^>]+\bclass=["\']episode_title["\'][^>]*>(?P<title>[^<]+)'), + webpage, 'title', default=None, group='title') + + return merge_dicts(info, { + 'id': video_id, + 'title': title, + 'formats': formats, + }) 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 01a51275e..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|com)/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' @@ -38,6 +38,9 @@ class WistiaIE(InfoExtractor): }, { 'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt', 'only_matching': True, + }, { + 'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json', + 'only_matching': True, }] @staticmethod 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 a9951f3b8..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]).replace('/cdn/', '/cdn2/') + 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 44c25c11c..c8bf98b58 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -498,7 +498,6 @@ 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'], @@ -527,7 +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', @@ -540,14 +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', @@ -566,7 +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, } }, @@ -581,7 +577,6 @@ 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'], @@ -605,7 +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': { @@ -620,13 +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, @@ -640,13 +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': { @@ -662,10 +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', } @@ -683,7 +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, }, }, @@ -692,7 +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, @@ -700,7 +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, }, }, @@ -718,7 +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', }, @@ -736,7 +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', @@ -758,7 +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', }, }, @@ -792,7 +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', @@ -808,7 +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': { @@ -881,6 +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) @@ -917,7 +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', @@ -1021,13 +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, @@ -1053,7 +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, @@ -1077,6 +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): @@ -1105,7 +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) @@ -1192,8 +1198,8 @@ 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') @@ -1540,6 +1546,13 @@ 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 @@ -1597,6 +1610,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 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 @@ -1628,6 +1642,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 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) @@ -1673,6 +1688,9 @@ 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 {} @@ -1786,11 +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] @@ -1834,7 +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 @@ -1868,7 +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, @@ -1876,7 +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(): @@ -1904,31 +1945,38 @@ 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( @@ -2016,7 +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: diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py index 896276301..ee514666b 100644 --- a/youtube_dl/extractor/zattoo.py +++ b/youtube_dl/extractor/zattoo.py @@ -420,3 +420,14 @@ class EinsUndEinsTVIE(ZattooIE): 'url': 'https://www.1und1.tv/watch/abc/123-abc', 'only_matching': True, }] + + +class SaltTVIE(ZattooIE): + _NETRC_MACHINE = 'salttv' + _HOST = 'tv.salt.ch' + _VALID_URL = _make_valid_url(ZattooIE._VALID_URL_TEMPLATE, _HOST) + + _TESTS = [{ + 'url': 'https://tv.salt.ch/watch/abc/123-abc', + 'only_matching': True, + }] diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 757b496a1..88b9ae9be 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): @@ -190,6 +218,7 @@ class FFmpegPostProcessor(PostProcessor): encodeFilename(self._ffmpeg_filename_argument(path), True) ]) cmd = ([encodeFilename(self.executable, True), encodeArgument('-y')] + + [encodeArgument('-loglevel'), encodeArgument('repeat+info')] + files_cmd + [encodeArgument(o) for o in opts] + [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) @@ -379,14 +408,16 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): # Don't copy the existing subtitles, we may be running the # postprocessor a second time '-map', '-0:s', + # Don't copy Apple TV chapters track, bin_data (see #19042, #19024, + # https://trac.ffmpeg.org/ticket/6016) + '-map', '-0:d', ] if information['ext'] == 'mp4': 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 62e769fd5..d0cb65814 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1868,7 +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') @@ -2968,6 +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', @@ -2977,6 +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', @@ -3091,6 +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', diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0461aac0c..ec89cfc64 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.12.17' +__version__ = '2019.01.27'