diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 73f46ec04..4999154e6 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.05.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [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 2020.01.24 + [debug] youtube-dl version 2020.05.08 [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/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 7e3c9f669..be994f368 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.05.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index b9bb3bd11..f05326c8c 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.05.08** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 265ea80c1..0dbb867cd 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.05.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [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 2020.01.24 + [debug] youtube-dl version 2020.05.08 [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/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index e71778a3d..4b31c88ed 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.05.08** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 94aa9f327..7805c62b6 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,161 @@ +version 2020.05.08 + +Core +* [downloader/http] Request last data block of exact remaining size +* [downloader/http] Finish downloading once received data length matches + expected +* [extractor/common] Use compat_cookiejar_Cookie for _set_cookie to always + ensure cookie name and value are bytestrings on python 2 (#23256, #24776) ++ [compat] Introduce compat_cookiejar_Cookie +* [utils] Improve cookie files support + + Add support for UTF-8 in cookie files + * Skip malformed cookie file entries instead of crashing (invalid entry + length, invalid expires at) + +Extractors +* [youtube] Improve signature cipher extraction (#25187, #25188) +* [iprima] Improve extraction (#25138) +* [uol] Fix extraction (#22007) ++ [orf] Add support for more radio stations (#24938, #24968) +* [dailymotion] Fix typo +- [puhutv] Remove no longer available HTTP formats (#25124) + + +version 2020.05.03 + +Core ++ [extractor/common] Extract multiple JSON-LD entries +* [options] Clarify doc on --exec command (#19087, #24883) +* [extractor/common] Skip malformed ISM manifest XMLs while extracting + ISM formats (#24667) + +Extractors +* [crunchyroll] Fix and improve extraction (#25096, #25060) +* [youtube] Improve player id extraction +* [youtube] Use redirected video id if any (#25063) +* [yahoo] Fix GYAO Player extraction and relax URL regular expression + (#24178, #24778) +* [tvplay] Fix Viafree extraction (#15189, #24473, #24789) +* [tenplay] Relax URL regular expression (#25001) ++ [prosiebensat1] Extract series metadata +* [prosiebensat1] Improve extraction and remove 7tv.de support (#24948) +- [prosiebensat1] Remove 7tv.de support (#24948) +* [youtube] Fix DRM videos detection (#24736) +* [thisoldhouse] Fix video id extraction (#24548, #24549) ++ [soundcloud] Extract AAC format (#19173, #24708) +* [youtube] Skip broken multifeed videos (#24711) +* [nova:embed] Fix extraction (#24700) +* [motherless] Fix extraction (#24699) +* [twitch:clips] Extend URL regular expression (#24290, #24642) +* [tv4] Fix ISM formats extraction (#24667) +* [tele5] Fix extraction (#24553) ++ [mofosex] Add support for generic embeds (#24633) ++ [youporn] Add support for generic embeds ++ [spankwire] Add support for generic embeds (#24633) +* [spankwire] Fix extraction (#18924, #20648) + + +version 2020.03.24 + +Core +- [utils] Revert support for cookie files with spaces used instead of tabs + +Extractors +* [teachable] Update upskillcourses and gns3 domains +* [generic] Look for teachable embeds before wistia ++ [teachable] Extract chapter metadata (#24421) ++ [bilibili] Add support for player.bilibili.com (#24402) ++ [bilibili] Add support for new URL schema with BV ids (#24439, #24442) +* [limelight] Remove disabled API requests (#24255) +* [soundcloud] Fix download URL extraction (#24394) ++ [cbc:watch] Add support for authentication (#19160) +* [hellporno] Fix extraction (#24399) +* [xtube] Fix formats extraction (#24348) +* [ndr] Fix extraction (#24326) +* [nhk] Update m3u8 URL and use native HLS downloader (#24329) +- [nhk] Remove obsolete rtmp formats (#24329) +* [nhk] Relax URL regular expression (#24329) +- [vimeo] Revert fix showcase password protected video extraction (#24224) + + +version 2020.03.08 + +Core ++ [utils] Add support for cookie files with spaces used instead of tabs + +Extractors ++ [pornhub] Add support for pornhubpremium.com (#24288) +- [youtube] Remove outdated code and unnecessary requests +* [youtube] Improve extraction in 429 HTTP error conditions (#24283) +* [nhk] Update API version (#24270) + + +version 2020.03.06 + +Extractors +* [youtube] Fix age-gated videos support without login (#24248) +* [vimeo] Fix showcase password protected video extraction (#24224) +* [pornhub] Improve title extraction (#24184) +* [peertube] Improve extraction (#23657) ++ [servus] Add support for new URL schema (#23475, #23583, #24142) +* [vimeo] Fix subtitles URLs (#24209) + + +version 2020.03.01 + +Core +* [YoutubeDL] Force redirect URL to unicode on python 2 +- [options] Remove duplicate short option -v for --version (#24162) + +Extractors +* [xhamster] Fix extraction (#24205) +* [franceculture] Fix extraction (#24204) ++ [telecinco] Add support for article opening videos +* [telecinco] Fix extraction (#24195) +* [xtube] Fix metadata extraction (#21073, #22455) +* [youjizz] Fix extraction (#24181) +- Remove no longer needed compat_str around geturl +* [pornhd] Fix extraction (#24128) ++ [teachable] Add support for multiple videos per lecture (#24101) ++ [wistia] Add support for multiple generic embeds (#8347, 11385) +* [imdb] Fix extraction (#23443) +* [tv2dk:bornholm:play] Fix extraction (#24076) + + +version 2020.02.16 + +Core +* [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591, + #10622) +* [update] Fix updating via symlinks (#23991) ++ [compat] Introduce compat_realpath (#23991) + +Extractors ++ [npr] Add support for streams (#24042) ++ [24video] Add support for porn.24video.net (#23779, #23784) +- [jpopsuki] Remove extractor (#23858) +* [nova] Improve extraction (#23690) +* [nova:embed] Improve (#23690) +* [nova:embed] Fix extraction (#23672) ++ [abc:iview] Add support for 720p (#22907, #22921) +* [nytimes] Improve format sorting (#24010) ++ [toggle] Add support for mewatch.sg (#23895, #23930) +* [thisoldhouse] Fix extraction (#23951) ++ [popcorntimes] Add support for popcorntimes.tv (#23949) +* [sportdeutschland] Update to new API +* [twitch:stream] Lowercase channel id for stream request (#23917) +* [tv5mondeplus] Fix extraction (#23907, #23911) +* [tva] Relax URL regular expression (#23903) +* [vimeo] Fix album extraction (#23864) +* [viewlift] Improve extraction + * Fix extraction (#23851) + + Add support for authentication + + Add support for more domains +* [svt] Fix series extraction (#22297) +* [svt] Fix article extraction (#22897, #22919) +* [soundcloud] Imporve private playlist/set tracks extraction (#3707) + + version 2020.01.24 Extractors diff --git a/README.md b/README.md index 01f975958..45326c69e 100644 --- a/README.md +++ b/README.md @@ -434,9 +434,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo either the path to the binary or its containing directory. --exec CMD Execute a command on the file after - downloading, similar to find's -exec - syntax. Example: --exec 'adb push {} - /sdcard/Music/ && rm {}' + downloading and post-processing, similar to + find's -exec syntax. Example: --exec 'adb + push {} /sdcard/Music/ && rm {}' --convert-subs FORMAT Convert the subtitles to other format (currently supported: srt|ass|vtt|lrc) @@ -835,7 +835,9 @@ In February 2015, the new YouTube player contained a character sequence in a str ### HTTP Error 429: Too Many Requests or 402: Payment Required -These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address. +These two error codes indicate that the service is blocking your IP address because of overuse. Usually this is a soft block meaning that you can gain access again after solving CAPTCHA. Just open a browser and solve a CAPTCHA the service suggests you and after that [pass cookies](#how-do-i-pass-cookies-to-youtube-dl) to youtube-dl. Note that if your machine has multiple external IPs then you should also pass exactly the same IP you've used for solving CAPTCHA with [`--source-address`](#network-options). Also you may need to pass a `User-Agent` HTTP header of your browser with [`--user-agent`](#workarounds). + +If this is not the case (no CAPTCHA suggested to solve by the service) then you can contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address. ### SyntaxError: Non-ASCII character @@ -1030,7 +1032,7 @@ 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/ytdl-org/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/ytdl-org/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/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want. -8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart): +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart): $ flake8 youtube_dl/extractor/yourextractor.py diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e9a8cc27a..35c1050e5 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -98,6 +98,7 @@ - **BiliBili** - **BilibiliAudio** - **BilibiliAudioAlbum** + - **BiliBiliPlayer** - **BioBioChileTV** - **BIQLE** - **BitChute** @@ -389,7 +390,6 @@ - **JeuxVideo** - **Joj** - **Jove** - - **jpopsuki.tv** - **JWPlatform** - **Kakao** - **Kaltura** @@ -497,6 +497,7 @@ - **MNetTV** - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net - **Mofosex** + - **MofosexEmbed** - **Mojvideo** - **Morningstar**: morningstar.com - **Motherless** @@ -619,11 +620,21 @@ - **Ooyala** - **OoyalaExternal** - **OraTV** + - **orf:burgenland**: Radio Burgenland - **orf:fm4**: radio FM4 - **orf:fm4:story**: fm4.orf.at stories - **orf:iptv**: iptv.ORF.at + - **orf:kaernten**: Radio Kärnten + - **orf:noe**: Radio Niederösterreich + - **orf:oberoesterreich**: Radio Oberösterreich - **orf:oe1**: Radio Österreich 1 + - **orf:oe3**: Radio Österreich 3 + - **orf:salzburg**: Radio Salzburg + - **orf:steiermark**: Radio Steiermark + - **orf:tirol**: Radio Tirol - **orf:tvthek**: ORF TVthek + - **orf:vorarlberg**: Radio Vorarlberg + - **orf:wien**: Radio Wien - **OsnatelTV** - **OutsideTV** - **PacktPub** @@ -663,6 +674,7 @@ - **Pokemon** - **PolskieRadio** - **PolskieRadioCategory** + - **Popcorntimes** - **PopcornTV** - **PornCom** - **PornerBros** @@ -1004,8 +1016,8 @@ - **Vidzi** - **vier**: vier.be and vijf.be - **vier:videos** - - **ViewLift** - - **ViewLiftEmbed** + - **viewlift** + - **viewlift:embed** - **Viidea** - **viki** - **viki:channel** diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index ce9666171..1e204e551 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -816,11 +816,15 @@ class TestYoutubeDL(unittest.TestCase): 'webpage_url': 'http://example.com', } - def get_ids(params): + def get_downloaded_info_dicts(params): ydl = YDL(params) - # make a copy because the dictionary can be modified - ydl.process_ie_result(playlist.copy()) - return [int(v['id']) for v in ydl.downloaded_info_dicts] + # make a deep copy because the dictionary and nested entries + # can be modified + ydl.process_ie_result(copy.deepcopy(playlist)) + return ydl.downloaded_info_dicts + + def get_ids(params): + return [int(v['id']) for v in get_downloaded_info_dicts(params)] result = get_ids({}) self.assertEqual(result, [1, 2, 3, 4]) @@ -852,6 +856,22 @@ class TestYoutubeDL(unittest.TestCase): result = get_ids({'playlist_items': '2-4,3-4,3'}) self.assertEqual(result, [2, 3, 4]) + # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591 + # @{ + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + self.assertEqual(result[2]['playlist_index'], 4) + + result = get_downloaded_info_dicts({'playlist_items': '4,2'}) + self.assertEqual(result[0]['playlist_index'], 4) + self.assertEqual(result[1]['playlist_index'], 2) + # @} + def test_urlopen_no_file_protocol(self): # see https://github.com/ytdl-org/youtube-dl/issues/8227 ydl = YDL() diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py index f959798de..05f48bd74 100644 --- a/test/test_YoutubeDLCookieJar.py +++ b/test/test_YoutubeDLCookieJar.py @@ -39,6 +39,13 @@ class TestYoutubeDLCookieJar(unittest.TestCase): assert_cookie_has_value('HTTPONLY_COOKIE') assert_cookie_has_value('JS_ACCESSIBLE_COOKIE') + def test_malformed_cookies(self): + cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/malformed_cookies.txt') + cookiejar.load(ignore_discard=True, ignore_expires=True) + # Cookies should be empty since all malformed cookie file entries + # will be ignored + self.assertFalse(cookiejar._cookies) + if __name__ == '__main__': unittest.main() diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index f0c370eee..69df30eda 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -74,6 +74,28 @@ _TESTS = [ ] +class TestPlayerInfo(unittest.TestCase): + def test_youtube_extract_player_info(self): + PLAYER_URLS = ( + ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/en_US/base.js', '64dddad9'), + # obsolete + ('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'), + ('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'), + ('https://www.youtube.com/yts/jsbin/player_ias-vflCPQUIL/en_US/base.js', 'vflCPQUIL'), + ('https://www.youtube.com/yts/jsbin/player-vflzQZbt7/en_US/base.js', 'vflzQZbt7'), + ('https://www.youtube.com/yts/jsbin/player-en_US-vflaxXRn1/base.js', 'vflaxXRn1'), + ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'), + ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'), + ('http://s.ytimg.com/yt/swfbin/watch_as3-vflrEm9Nq.swf', 'vflrEm9Nq'), + ('https://s.ytimg.com/yts/swfbin/player-vflenCdZL/watch_as3.swf', 'vflenCdZL'), + ) + for player_url, expected_player_id in PLAYER_URLS: + expected_player_type = player_url.split('.')[-1] + player_type, player_id = YoutubeIE._extract_player_info(player_url) + self.assertEqual(player_type, expected_player_type) + self.assertEqual(player_id, expected_player_id) + + class TestSignature(unittest.TestCase): def setUp(self): TEST_DIR = os.path.dirname(os.path.abspath(__file__)) diff --git a/test/testdata/cookies/malformed_cookies.txt b/test/testdata/cookies/malformed_cookies.txt new file mode 100644 index 000000000..17bc40354 --- /dev/null +++ b/test/testdata/cookies/malformed_cookies.txt @@ -0,0 +1,9 @@ +# Netscape HTTP Cookie File +# http://curl.haxx.se/rfc/cookie_spec.html +# This is a generated file! Do not edit. + +# Cookie file entry with invalid number of fields - 6 instead of 7 +www.foobar.foobar FALSE / FALSE 0 COOKIE + +# Cookie file entry with invalid expires at +www.foobar.foobar FALSE / FALSE 1.7976931348623157e+308 COOKIE VALUE diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index f5cb46308..19370f62b 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -92,6 +92,7 @@ from .utils import ( YoutubeDLCookieJar, YoutubeDLCookieProcessor, YoutubeDLHandler, + YoutubeDLRedirectHandler, ) from .cache import Cache from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER @@ -990,7 +991,7 @@ class YoutubeDL(object): 'playlist_title': ie_result.get('title'), 'playlist_uploader': ie_result.get('uploader'), 'playlist_uploader_id': ie_result.get('uploader_id'), - 'playlist_index': i + playliststart, + 'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart, 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], 'webpage_url_basename': url_basename(ie_result['webpage_url']), @@ -2343,6 +2344,7 @@ class YoutubeDL(object): debuglevel = 1 if self.params.get('debug_printtraffic') else 0 https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) + redirect_handler = YoutubeDLRedirectHandler() data_handler = compat_urllib_request_DataHandler() # When passing our own FileHandler instance, build_opener won't add the @@ -2356,7 +2358,7 @@ class YoutubeDL(object): file_handler.file_open = file_open opener = compat_urllib_request.build_opener( - proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler) + proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler) # Delete the default user-agent header, which would otherwise apply in # cases where our custom HTTP handler doesn't come into play diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index c75ab131b..0ee9bc760 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -57,6 +57,17 @@ try: except ImportError: # Python 2 import cookielib as compat_cookiejar +if sys.version_info[0] == 2: + class compat_cookiejar_Cookie(compat_cookiejar.Cookie): + def __init__(self, version, name, value, *args, **kwargs): + if isinstance(name, compat_str): + name = name.encode() + if isinstance(value, compat_str): + value = value.encode() + compat_cookiejar.Cookie.__init__(self, version, name, value, *args, **kwargs) +else: + compat_cookiejar_Cookie = compat_cookiejar.Cookie + try: import http.cookies as compat_cookies except ImportError: # Python 2 @@ -2754,6 +2765,17 @@ else: compat_expanduser = os.path.expanduser +if compat_os_name == 'nt' and sys.version_info < (3, 8): + # os.path.realpath on Windows does not follow symbolic links + # prior to Python 3.8 (see https://bugs.python.org/issue9949) + def compat_realpath(path): + while os.path.islink(path): + path = os.path.abspath(os.readlink(path)) + return path +else: + compat_realpath = os.path.realpath + + if sys.version_info < (3, 0): def compat_print(s): from .utils import preferredencoding @@ -2976,6 +2998,7 @@ __all__ = [ 'compat_basestring', 'compat_chr', 'compat_cookiejar', + 'compat_cookiejar_Cookie', 'compat_cookies', 'compat_ctypes_WINFUNCTYPE', 'compat_etree_Element', @@ -2998,6 +3021,7 @@ __all__ = [ 'compat_os_name', 'compat_parse_qs', 'compat_print', + 'compat_realpath', 'compat_setenv', 'compat_shlex_quote', 'compat_shlex_split', diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 3c72ea18b..5046878df 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -227,7 +227,7 @@ class HttpFD(FileDownloader): while True: try: # Download and write - data_block = ctx.data.read(block_size if not is_test else min(block_size, data_len - byte_counter)) + data_block = ctx.data.read(block_size if data_len is None else min(block_size, data_len - byte_counter)) # socket.timeout is a subclass of socket.error but may not have # errno set except socket.timeout as e: @@ -299,7 +299,7 @@ class HttpFD(FileDownloader): 'elapsed': now - ctx.start_time, }) - if is_test and byte_counter == data_len: + if data_len is not None and byte_counter == data_len: break if not is_test and ctx.chunk_size and ctx.data_len is not None and byte_counter < ctx.data_len: diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 4ac323bf6..6637f4f35 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -110,17 +110,17 @@ class ABCIViewIE(InfoExtractor): # ABC iview programs are normally available for 14 days only. _TESTS = [{ - 'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00', - 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', + 'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00', + 'md5': '67715ce3c78426b11ba167d875ac6abf', 'info_dict': { - 'id': 'ZX9371A050S00', + 'id': 'LE1927H001S00', 'ext': 'mp4', - 'title': "Gaston's Birthday", - 'series': "Ben And Holly's Little Kingdom", - 'description': 'md5:f9de914d02f226968f598ac76f105bcf', - 'upload_date': '20180604', - 'uploader_id': 'abc4kids', - 'timestamp': 1528140219, + 'title': "Series 11 Ep 1", + 'series': "Gruen", + 'description': 'md5:52cc744ad35045baf6aded2ce7287f67', + 'upload_date': '20190925', + 'uploader_id': 'abc1', + 'timestamp': 1569445289, }, 'params': { 'skip_download': True, @@ -148,7 +148,7 @@ class ABCIViewIE(InfoExtractor): 'hdnea': token, }) - for sd in ('sd', 'sd-low'): + for sd in ('720', 'sd', 'sd-low'): sd_url = try_get( stream, lambda x: x['streams']['hls'][sd], compat_str) if not sd_url: diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 901c5a54f..002c39c39 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -528,7 +528,7 @@ class BBCCoUkIE(InfoExtractor): def get_programme_id(item): def get_from_attributes(item): - for p in('identifier', 'group'): + for p in ('identifier', 'group'): value = item.get(p) if value and re.match(r'^[pb][\da-z]{7}$', value): return value diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 80bd696e2..4dc597e16 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -24,7 +24,18 @@ from ..utils import ( class BiliBiliIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/(?P\d+)/play#)(?P\d+)' + _VALID_URL = r'''(?x) + https?:// + (?:(?:www|bangumi)\.)? + bilibili\.(?:tv|com)/ + (?: + (?: + video/[aA][vV]| + anime/(?P\d+)/play\# + )(?P\d+)| + video/[bB][vV](?P[^/?#&]+) + ) + ''' _TESTS = [{ 'url': 'http://www.bilibili.tv/video/av1074402/', @@ -92,6 +103,10 @@ class BiliBiliIE(InfoExtractor): 'skip_download': True, # Test metadata only }, }] + }, { + # new BV video id format + 'url': 'https://www.bilibili.com/video/BV1JE411F741', + 'only_matching': True, }] _APP_KEY = 'iVGUTjsxvpLeuDCf' @@ -109,7 +124,7 @@ class BiliBiliIE(InfoExtractor): url, smuggled_data = unsmuggle_url(url, {}) mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = mobj.group('id') or mobj.group('id_bv') anime_id = mobj.group('anime_id') webpage = self._download_webpage(url, video_id) @@ -419,3 +434,17 @@ class BilibiliAudioAlbumIE(BilibiliAudioBaseIE): entries, am_id, album_title, album_data.get('intro')) return self.playlist_result(entries, am_id) + + +class BiliBiliPlayerIE(InfoExtractor): + _VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P\d+)' + _TEST = { + 'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1', + 'only_matching': True, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'http://www.bilibili.tv/video/av%s/' % video_id, + ie=BiliBiliIE.ie_key(), video_id=video_id) diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index 751a3a8f2..fd5ec6033 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -1,8 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals +import hashlib import json import re +from xml.sax.saxutils import escape from .common import InfoExtractor from ..compat import ( @@ -216,6 +218,29 @@ class CBCWatchBaseIE(InfoExtractor): 'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/', } _GEO_COUNTRIES = ['CA'] + _LOGIN_URL = 'https://api.loginradius.com/identity/v2/auth/login' + _TOKEN_URL = 'https://cloud-api.loginradius.com/sso/jwt/api/token' + _API_KEY = '3f4beddd-2061-49b0-ae80-6f1f2ed65b37' + _NETRC_MACHINE = 'cbcwatch' + + def _signature(self, email, password): + data = json.dumps({ + 'email': email, + 'password': password, + }).encode() + headers = {'content-type': 'application/json'} + query = {'apikey': self._API_KEY} + resp = self._download_json(self._LOGIN_URL, None, data=data, headers=headers, query=query) + access_token = resp['access_token'] + + # token + query = { + 'access_token': access_token, + 'apikey': self._API_KEY, + 'jwtapp': 'jwt', + } + resp = self._download_json(self._TOKEN_URL, None, headers=headers, query=query) + return resp['signature'] def _call_api(self, path, video_id): url = path if path.startswith('http') else self._API_BASE_URL + path @@ -239,7 +264,8 @@ class CBCWatchBaseIE(InfoExtractor): def _real_initialize(self): if self._valid_device_token(): return - device = self._downloader.cache.load('cbcwatch', 'device') or {} + device = self._downloader.cache.load( + 'cbcwatch', self._cache_device_key()) or {} self._device_id, self._device_token = device.get('id'), device.get('token') if self._valid_device_token(): return @@ -248,16 +274,30 @@ class CBCWatchBaseIE(InfoExtractor): def _valid_device_token(self): return self._device_id and self._device_token + def _cache_device_key(self): + email, _ = self._get_login_info() + return '%s_device' % hashlib.sha256(email.encode()).hexdigest() if email else 'device' + def _register_device(self): - self._device_id = self._device_token = None result = self._download_xml( self._API_BASE_URL + 'device/register', None, 'Acquiring device token', data=b'web') self._device_id = xpath_text(result, 'deviceId', fatal=True) - self._device_token = xpath_text(result, 'deviceToken', fatal=True) + email, password = self._get_login_info() + if email and password: + signature = self._signature(email, password) + data = '{0}{1}web'.format( + escape(signature), escape(self._device_id)).encode() + url = self._API_BASE_URL + 'device/login' + result = self._download_xml( + url, None, data=data, + headers={'content-type': 'application/xml'}) + self._device_token = xpath_text(result, 'token', fatal=True) + else: + self._device_token = xpath_text(result, 'deviceToken', fatal=True) self._downloader.cache.store( - 'cbcwatch', 'device', { + 'cbcwatch', self._cache_device_key(), { 'id': self._device_id, 'token': self._device_token, }) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index eaae5e484..a61753b17 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -15,7 +15,7 @@ import time import math from ..compat import ( - compat_cookiejar, + compat_cookiejar_Cookie, compat_cookies, compat_etree_Element, compat_etree_fromstring, @@ -1182,16 +1182,33 @@ class InfoExtractor(object): 'twitter card player') def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): - json_ld = self._search_regex( - JSON_LD_RE, html, 'JSON-LD', group='json_ld', **kwargs) + json_ld_list = list(re.finditer(JSON_LD_RE, html)) default = kwargs.get('default', NO_DEFAULT) - if not json_ld: - return default if default is not NO_DEFAULT else {} # JSON-LD may be malformed and thus `fatal` should be respected. # At the same time `default` may be passed that assumes `fatal=False` # for _search_regex. Let's simulate the same behavior here as well. fatal = kwargs.get('fatal', True) if default == NO_DEFAULT else False - return self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type) + json_ld = [] + for mobj in json_ld_list: + json_ld_item = self._parse_json( + mobj.group('json_ld'), video_id, fatal=fatal) + if not json_ld_item: + continue + if isinstance(json_ld_item, dict): + json_ld.append(json_ld_item) + elif isinstance(json_ld_item, (list, tuple)): + json_ld.extend(json_ld_item) + if json_ld: + json_ld = self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type) + if json_ld: + return json_ld + if default is not NO_DEFAULT: + return default + elif fatal: + raise RegexNotFoundError('Unable to extract JSON-LD') + else: + self._downloader.report_warning('unable to extract JSON-LD %s' % bug_reports_message()) + return {} def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None): if isinstance(json_ld, compat_str): @@ -1256,10 +1273,10 @@ class InfoExtractor(object): extract_interaction_statistic(e) for e in json_ld: - if isinstance(e.get('@context'), compat_str) and re.match(r'^https?://schema.org/?$', e.get('@context')): + if '@context' in e: item_type = e.get('@type') if expected_type is not None and expected_type != item_type: - return info + continue if item_type in ('TVEpisode', 'Episode'): episode_name = unescapeHTML(e.get('name')) info.update({ @@ -1293,11 +1310,17 @@ class InfoExtractor(object): }) elif item_type == 'VideoObject': extract_video_object(e) - continue + if expected_type is None: + continue + else: + break video = e.get('video') if isinstance(video, dict) and video.get('@type') == 'VideoObject': extract_video_object(video) - break + if expected_type is None: + continue + else: + break return dict((k, v) for k, v in info.items() if v is not None) @staticmethod @@ -2340,6 +2363,8 @@ class InfoExtractor(object): if res is False: return [] ism_doc, urlh = res + if ism_doc is None: + return [] return self._parse_ism_formats(ism_doc, urlh.geturl(), ism_id) @@ -2818,7 +2843,7 @@ class InfoExtractor(object): def _set_cookie(self, domain, name, value, expire_time=None, port=None, path='/', secure=False, discard=False, rest={}, **kwargs): - cookie = compat_cookiejar.Cookie( + cookie = compat_cookiejar_Cookie( 0, name, value, port, port is not None, domain, True, domain.startswith('.'), path, True, secure, expire_time, discard, None, None, rest) diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 85a9a577f..bc2d1fa8b 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -13,6 +13,7 @@ from ..compat import ( compat_b64decode, compat_etree_Element, compat_etree_fromstring, + compat_str, compat_urllib_parse_urlencode, compat_urllib_request, compat_urlparse, @@ -25,9 +26,9 @@ from ..utils import ( intlist_to_bytes, int_or_none, lowercase_escape, + merge_dicts, remove_end, sanitized_Request, - unified_strdate, urlencode_postdata, xpath_text, ) @@ -136,6 +137,7 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): # rtmp 'skip_download': True, }, + 'skip': 'Video gone', }, { 'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1', 'info_dict': { @@ -157,11 +159,12 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): 'info_dict': { 'id': '702409', 'ext': 'mp4', - 'title': 'Re:ZERO -Starting Life in Another World- Episode 5 – The Morning of Our Promise Is Still Distant', - 'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9', + 'title': compat_str, + 'description': compat_str, 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'TV TOKYO', - 'upload_date': '20160508', + 'uploader': 'Re:Zero Partners', + 'timestamp': 1462098900, + 'upload_date': '20160501', }, 'params': { # m3u8 download @@ -172,12 +175,13 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): 'info_dict': { 'id': '727589', 'ext': 'mp4', - 'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance From This Judicial Injustice!", - 'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d', + 'title': compat_str, + 'description': compat_str, 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Kadokawa Pictures Inc.', - 'upload_date': '20170118', - 'series': "KONOSUBA -God's blessing on this wonderful world!", + 'timestamp': 1484130900, + 'upload_date': '20170111', + 'series': compat_str, 'season': "KONOSUBA -God's blessing on this wonderful world! 2", 'season_number': 2, 'episode': 'Give Me Deliverance From This Judicial Injustice!', @@ -200,10 +204,11 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): 'info_dict': { 'id': '535080', 'ext': 'mp4', - 'title': '11eyes Episode 1 – Red Night ~ Piros éjszaka', - 'description': 'Kakeru and Yuka are thrown into an alternate nightmarish world they call "Red Night".', + 'title': compat_str, + 'description': compat_str, 'uploader': 'Marvelous AQL Inc.', - 'upload_date': '20091021', + 'timestamp': 1255512600, + 'upload_date': '20091014', }, 'params': { # Just test metadata extraction @@ -224,15 +229,17 @@ class CrunchyrollIE(CrunchyrollBaseIE, VRVIE): # just test metadata extraction 'skip_download': True, }, + 'skip': 'Video gone', }, { # A video with a vastly different season name compared to the series name 'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532', 'info_dict': { 'id': '590532', 'ext': 'mp4', - 'title': 'Haiyoru! Nyaruani (ONA) Episode 1 – Test', - 'description': 'Mahiro and Nyaruko talk about official certification.', + 'title': compat_str, + 'description': compat_str, 'uploader': 'TV TOKYO', + 'timestamp': 1330956000, 'upload_date': '20120305', 'series': 'Nyarko-san: Another Crawling Chaos', 'season': 'Haiyoru! Nyaruani (ONA)', @@ -442,23 +449,21 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text webpage, 'language', default=None, group='lang') video_title = self._html_search_regex( - r'(?s)]*>((?:(?!]+itemprop=["\']title["\'][^>]*>(?:(?!', - webpage, 'video_title') + (r'(?s)]*>((?:(?!]+itemprop=["\']title["\']|meta[^>]+itemprop=["\']position["\'])[^>]*>(?:(?!', + r'(.+?),\s+-\s+.+? Crunchyroll'), + webpage, 'video_title', default=None) + if not video_title: + video_title = re.sub(r'^Watch\s+', '', self._og_search_description(webpage)) video_title = re.sub(r' {2,}', ' ', video_title) video_description = (self._parse_json(self._html_search_regex( r'<script[^>]*>\s*.+?\[media_id=%s\].+?({.+?"description"\s*:.+?})\);' % video_id, webpage, 'description', default='{}'), video_id) or media_metadata).get('description') if video_description: video_description = lowercase_escape(video_description.replace(r'\r\n', '\n')) - video_upload_date = self._html_search_regex( - [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'], - webpage, 'video_upload_date', fatal=False, flags=re.DOTALL) - if video_upload_date: - video_upload_date = unified_strdate(video_upload_date) video_uploader = self._html_search_regex( # try looking for both an uploader that's a link and one that's not [r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'], - webpage, 'video_uploader', fatal=False) + webpage, 'video_uploader', default=False) formats = [] for stream in media.get('streams', []): @@ -611,14 +616,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)', webpage, 'season number', default=None)) - return { + info = self._search_json_ld(webpage, video_id, default={}) + + return merge_dicts({ 'id': video_id, 'title': video_title, 'description': video_description, 'duration': duration, 'thumbnail': thumbnail, 'uploader': video_uploader, - 'upload_date': video_upload_date, 'series': series, 'season': season, 'season_number': season_number, @@ -626,7 +632,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'episode_number': episode_number, 'subtitles': subtitles, 'formats': formats, - } + }, info) class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE): diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 327fdb04a..b8529050c 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -32,7 +32,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor): @staticmethod def _get_cookie_value(cookies, name): - cookie = cookies.get('name') + cookie = cookies.get(name) if cookie: return cookie.value diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index c050bf9df..fe42821c7 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( encode_base_n, ExtractorError, @@ -55,7 +54,7 @@ class EpornerIE(InfoExtractor): webpage, urlh = self._download_webpage_handle(url, display_id) - video_id = self._match_id(compat_str(urlh.geturl())) + video_id = self._match_id(urlh.geturl()) hash = self._search_regex( r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 1cab440f4..4b3092028 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -105,6 +105,7 @@ from .bilibili import ( BiliBiliBangumiIE, BilibiliAudioIE, BilibiliAudioAlbumIE, + BiliBiliPlayerIE, ) from .biobiochiletv import BioBioChileTVIE from .bitchute import ( @@ -497,7 +498,6 @@ from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .joj import JojIE from .jwplatform import JWPlatformIE -from .jpopsukitv import JpopsukiIE from .kakao import KakaoIE from .kaltura import KalturaIE from .kanalplay import KanalPlayIE @@ -636,7 +636,10 @@ from .mixcloud import ( from .mlb import MLBIE from .mnet import MnetIE from .moevideo import MoeVideoIE -from .mofosex import MofosexIE +from .mofosex import ( + MofosexIE, + MofosexEmbedIE, +) from .mojvideo import MojvideoIE from .morningstar import MorningstarIE from .motherless import ( @@ -801,6 +804,16 @@ from .orf import ( ORFFM4IE, ORFFM4StoryIE, ORFOE1IE, + ORFOE3IE, + ORFNOEIE, + ORFWIEIE, + ORFBGLIE, + ORFOOEIE, + ORFSTMIE, + ORFKTNIE, + ORFSBGIE, + ORFTIRIE, + ORFVBGIE, ORFIPTVIE, ) from .outsidetv import OutsideTVIE @@ -850,6 +863,7 @@ from .polskieradio import ( PolskieRadioIE, PolskieRadioCategoryIE, ) +from .popcorntimes import PopcorntimesIE from .popcorntv import PopcornTVIE from .porn91 import Porn91IE from .porncom import PornComIE diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index b8fa17588..306b45fc9 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -31,7 +31,13 @@ class FranceCultureIE(InfoExtractor): webpage = self._download_webpage(url, display_id) video_data = extract_attributes(self._search_regex( - r'(?s)<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(<button[^>]+data-asset-source="[^"]+"[^>]+>)', + r'''(?sx) + (?: + </h1>| + <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*> + ).*? + (<button[^>]+data-asset-source="[^"]+"[^>]+>) + ''', webpage, 'video data')) video_url = video_data['data-asset-source'] diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 3c002472f..ce8252f6a 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -60,6 +60,9 @@ from .tnaflix import TNAFlixNetworkEmbedIE from .drtuber import DrTuberIE from .redtube import RedTubeIE from .tube8 import Tube8IE +from .mofosex import MofosexEmbedIE +from .spankwire import SpankwireIE +from .youporn import YouPornIE from .vimeo import VimeoIE from .dailymotion import DailymotionIE from .dailymail import DailyMailIE @@ -2287,7 +2290,7 @@ class GenericIE(InfoExtractor): if head_response is not False: # Check for redirect - new_url = compat_str(head_response.geturl()) + new_url = head_response.geturl() if url != new_url: self.report_following_redirect(new_url) if force_videoid: @@ -2387,12 +2390,12 @@ class GenericIE(InfoExtractor): return self.playlist_result( self._parse_xspf( doc, video_id, xspf_url=url, - xspf_base_url=compat_str(full_response.geturl())), + xspf_base_url=full_response.geturl()), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'] = self._parse_mpd_formats( doc, - mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0], + mpd_base_url=full_response.geturl().rpartition('/')[0], mpd_url=url) self._sort_formats(info_dict['formats']) return info_dict @@ -2536,15 +2539,21 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) + # Look for Teachable embeds, must be before Wistia + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + # Look for embedded Wistia player - wistia_url = WistiaIE._extract_url(webpage) - if wistia_url: - return { - '_type': 'url_transparent', - 'url': self._proto_relative_url(wistia_url), - 'ie_key': WistiaIE.ie_key(), - 'uploader': video_uploader, - } + wistia_urls = WistiaIE._extract_urls(webpage) + if wistia_urls: + playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key()) + for entry in playlist['entries']: + entry.update({ + '_type': 'url_transparent', + 'uploader': video_uploader, + }) + return playlist # Look for SVT player svt_url = SVTIE._extract_url(webpage) @@ -2709,6 +2718,21 @@ class GenericIE(InfoExtractor): if tube8_urls: return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key()) + # Look for embedded Mofosex player + mofosex_urls = MofosexEmbedIE._extract_urls(webpage) + if mofosex_urls: + return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key()) + + # Look for embedded Spankwire player + spankwire_urls = SpankwireIE._extract_urls(webpage) + if spankwire_urls: + return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key()) + + # Look for embedded YouPorn player + youporn_urls = YouPornIE._extract_urls(webpage) + if youporn_urls: + return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key()) + # Look for embedded Tvigle player mobj = re.search( r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) @@ -3140,10 +3164,6 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) - teachable_url = TeachableIE._extract_url(webpage, url) - if teachable_url: - return self.url_result(teachable_url) - indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) if indavideo_urls: return self.playlist_from_matches( diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 0ee8ea712..fae425103 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -1,12 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - js_to_json, + int_or_none, + merge_dicts, remove_end, - determine_ext, + unified_timestamp, ) @@ -14,15 +13,21 @@ class HellPornoIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', - 'md5': '1fee339c610d2049699ef2aa699439f1', + 'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3', 'info_dict': { 'id': '149116', 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic', 'ext': 'mp4', 'title': 'Dixie is posing with naked ass very erotic', + 'description': 'md5:9a72922749354edb1c4b6e540ad3d215', + 'categories': list, 'thumbnail': r're:https?://.*\.jpg$', + 'duration': 240, + 'timestamp': 1398762720, + 'upload_date': '20140429', + 'view_count': int, 'age_limit': 18, - } + }, }, { 'url': 'http://hellporno.net/v/186271/', 'only_matching': True, @@ -36,40 +41,36 @@ class HellPornoIE(InfoExtractor): title = remove_end(self._html_search_regex( r'<title>([^<]+)', webpage, 'title'), ' - Hell Porno') - flashvars = self._parse_json(self._search_regex( - r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), - display_id, transform_source=js_to_json) + info = self._parse_html5_media_entries(url, webpage, display_id)[0] + self._sort_formats(info['formats']) - video_id = flashvars.get('video_id') - thumbnail = flashvars.get('preview_url') - ext = determine_ext(flashvars.get('postfix'), 'mp4') + video_id = self._search_regex( + (r'chs_object\s*=\s*["\'](\d+)', + r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id', + default=display_id) + description = self._search_regex( + r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage, + 'description', fatal=False) + categories = [ + c.strip() + for c in self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + if c.strip()] + duration = int_or_none(self._og_search_property( + 'video:duration', webpage, fatal=False)) + timestamp = unified_timestamp(self._og_search_property( + 'video:release_date', webpage, fatal=False)) + view_count = int_or_none(self._search_regex( + r'>Views\s+(\d+)', webpage, 'view count', fatal=False)) - formats = [] - for video_url_key in ['video_url', 'video_alt_url']: - video_url = flashvars.get(video_url_key) - if not video_url: - continue - video_text = flashvars.get('%s_text' % video_url_key) - fmt = { - 'url': video_url, - 'ext': ext, - 'format_id': video_text, - } - m = re.search(r'^(?P\d+)[pP]', video_text) - if m: - fmt['height'] = int(m.group('height')) - formats.append(fmt) - self._sort_formats(formats) - - categories = self._html_search_meta( - 'keywords', webpage, 'categories', default='').split(',') - - return { + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, 'title': title, - 'thumbnail': thumbnail, + 'description': description, 'categories': categories, + 'duration': duration, + 'timestamp': timestamp, + 'view_count': view_count, 'age_limit': 18, - 'formats': formats, - } + }) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 436759da5..a31301985 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import base64 +import json import re from .common import InfoExtractor @@ -8,6 +10,7 @@ from ..utils import ( mimetype2ext, parse_duration, qualities, + try_get, url_or_none, ) @@ -15,15 +18,16 @@ from ..utils import ( class ImdbIE(InfoExtractor): IE_NAME = 'imdb' IE_DESC = 'Internet Movie Database trailers' - _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P\d+)' + _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P\d+)' _TESTS = [{ 'url': 'http://www.imdb.com/video/imdb/vi2524815897', 'info_dict': { 'id': '2524815897', 'ext': 'mp4', - 'title': 'No. 2 from Ice Age: Continental Drift (2012)', + 'title': 'No. 2', 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7', + 'duration': 152, } }, { 'url': 'http://www.imdb.com/video/_/vi2524815897', @@ -47,21 +51,23 @@ class ImdbIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'https://www.imdb.com/videoplayer/vi' + video_id, video_id) - video_metadata = self._parse_json(self._search_regex( - r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage, - 'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id] - title = self._html_search_meta( - ['og:title', 'twitter:title'], webpage) or self._html_search_regex( - r'(.+?)', webpage, 'title', fatal=False) or video_metadata['title'] + + data = self._download_json( + 'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id, + query={ + 'key': base64.b64encode(json.dumps({ + 'type': 'VIDEO_PLAYER', + 'subType': 'FORCE_LEGACY', + 'id': 'vi%s' % video_id, + }).encode()).decode(), + })[0] quality = qualities(('SD', '480p', '720p', '1080p')) formats = [] - for encoding in video_metadata.get('encodings', []): + for encoding in data['videoLegacyEncodings']: if not encoding or not isinstance(encoding, dict): continue - video_url = url_or_none(encoding.get('videoUrl')) + video_url = url_or_none(encoding.get('url')) if not video_url: continue ext = mimetype2ext(encoding.get( @@ -69,7 +75,7 @@ class ImdbIE(InfoExtractor): if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( video_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + preference=1, m3u8_id='hls', fatal=False)) continue format_id = encoding.get('definition') formats.append({ @@ -80,13 +86,33 @@ class ImdbIE(InfoExtractor): }) self._sort_formats(formats) + webpage = self._download_webpage( + 'https://www.imdb.com/video/vi' + video_id, video_id) + video_metadata = self._parse_json(self._search_regex( + r'args\.push\(\s*({.+?})\s*\)\s*;', webpage, + 'video metadata'), video_id) + + video_info = video_metadata.get('VIDEO_INFO') + if video_info and isinstance(video_info, dict): + info = try_get( + video_info, lambda x: x[list(video_info.keys())[0]][0], dict) + else: + info = {} + + title = self._html_search_meta( + ['og:title', 'twitter:title'], webpage) or self._html_search_regex( + r'(.+?)', webpage, 'title', + default=None) or info['videoTitle'] + return { 'id': video_id, 'title': title, + 'alt_title': info.get('videoSubTitle'), 'formats': formats, - 'description': video_metadata.get('description'), - 'thumbnail': video_metadata.get('slate', {}).get('url'), - 'duration': parse_duration(video_metadata.get('duration')), + 'description': info.get('videoDescription'), + 'thumbnail': url_or_none(try_get( + video_metadata, lambda x: x['videoSlate']['source'])), + 'duration': parse_duration(info.get('videoRuntime')), } diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 11bbeb592..53a550c11 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -16,12 +16,22 @@ class IPrimaIE(InfoExtractor): _GEO_BYPASS = False _TESTS = [{ - 'url': 'http://play.iprima.cz/gondici-s-r-o-33', + 'url': 'https://prima.iprima.cz/particka/92-epizoda', 'info_dict': { - 'id': 'p136534', + 'id': 'p51388', 'ext': 'mp4', - 'title': 'Gondíci s. r. o. (34)', - 'description': 'md5:16577c629d006aa91f59ca8d8e7f99bd', + 'title': 'Partička (92)', + 'description': 'md5:859d53beae4609e6dd7796413f1b6cac', + }, + 'params': { + 'skip_download': True, # m3u8 download + }, + }, { + 'url': 'https://cnn.iprima.cz/videa/70-epizoda', + 'info_dict': { + 'id': 'p681554', + 'ext': 'mp4', + 'title': 'HLAVNÍ ZPRÁVY 3.5.2020', }, 'params': { 'skip_download': True, # m3u8 download @@ -68,9 +78,15 @@ class IPrimaIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + title = self._og_search_title( + webpage, default=None) or self._search_regex( + r'

([^<]+)', webpage, 'title') + video_id = self._search_regex( (r']+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)', - r'data-product="([^"]+)">'), + r'data-product="([^"]+)">', + r'id=["\']player-(p\d+)"', + r'playerId\s*:\s*["\']player-(p\d+)'), webpage, 'real id') playerpage = self._download_webpage( @@ -125,8 +141,8 @@ class IPrimaIE(InfoExtractor): return { 'id': video_id, - 'title': self._og_search_title(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage, default=None), 'formats': formats, - 'description': self._og_search_description(webpage), + 'description': self._og_search_description(webpage, default=None), } diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py deleted file mode 100644 index 4b5f346d1..000000000 --- a/youtube_dl/extractor/jpopsukitv.py +++ /dev/null @@ -1,68 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - unified_strdate, -) - - -class JpopsukiIE(InfoExtractor): - IE_NAME = 'jpopsuki.tv' - _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P\S+)' - - _TEST = { - 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', - 'md5': '88018c0c1a9b1387940e90ec9e7e198e', - 'info_dict': { - 'id': '00be659d23b0b40508169cdee4545771', - 'ext': 'mp4', - 'title': 'ayumi hamasaki - evolution', - 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution', - 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', - 'uploader': 'plama_chan', - 'uploader_id': '404', - 'upload_date': '20121101' - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_url = 'http://www.jpopsuki.tv' + self._html_search_regex( - r'from: uploaded: (.*?)', webpage, 'video upload_date', - fatal=False)) - view_count_str = self._html_search_regex( - r'
  • Hits: ([0-9]+?)
    • ', webpage, 'video view_count', - fatal=False) - comment_count_str = self._html_search_regex( - r'

    ([0-9]+?) comments

    ', webpage, 'video comment_count', - fatal=False) - - return { - 'id': video_id, - 'url': video_url, - 'title': video_title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, - 'view_count': int_or_none(view_count_str), - 'comment_count': int_or_none(comment_count_str), - } diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 6ed7da4ab..1b2dcef46 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( clean_html, determine_ext, @@ -36,7 +35,7 @@ class LecturioBaseIE(InfoExtractor): self._LOGIN_URL, None, 'Downloading login popup') def is_logged(url_handle): - return self._LOGIN_URL not in compat_str(url_handle.geturl()) + return self._LOGIN_URL not in url_handle.geturl() # Already logged in if is_logged(urlh): diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 729d8de50..39f74d282 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -18,7 +18,6 @@ from ..utils import ( class LimelightBaseIE(InfoExtractor): _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' - _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json' @classmethod def _extract_urls(cls, webpage, source_url): @@ -70,7 +69,8 @@ class LimelightBaseIE(InfoExtractor): try: return self._download_json( self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), - item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) + item_id, 'Downloading PlaylistService %s JSON' % method, + fatal=fatal, headers=headers) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] @@ -79,22 +79,22 @@ class LimelightBaseIE(InfoExtractor): raise ExtractorError(error, expected=True) raise - def _call_api(self, organization_id, item_id, method): - return self._download_json( - self._API_URL % (organization_id, self._API_PATH, item_id, method), - item_id, 'Downloading API %s JSON' % method) - - def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None): + def _extract(self, item_id, pc_method, mobile_method, referer=None): pc = self._call_playlist_service(item_id, pc_method, referer=referer) - metadata = self._call_api(pc['orgId'], item_id, meta_method) - mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer) - return pc, mobile, metadata + mobile = self._call_playlist_service( + item_id, mobile_method, fatal=False, referer=referer) + return pc, mobile + + def _extract_info(self, pc, mobile, i, referer): + get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {} + pc_item = get_item(pc, 'playlistItems') + mobile_item = get_item(mobile, 'mediaList') + video_id = pc_item.get('mediaId') or mobile_item['mediaId'] + title = pc_item.get('title') or mobile_item['title'] - def _extract_info(self, streams, mobile_urls, properties): - video_id = properties['media_id'] formats = [] urls = [] - for stream in streams: + for stream in pc_item.get('streams', []): stream_url = stream.get('url') if not stream_url or stream.get('drmProtected') or stream_url in urls: continue @@ -155,7 +155,7 @@ class LimelightBaseIE(InfoExtractor): }) formats.append(fmt) - for mobile_url in mobile_urls: + for mobile_url in mobile_item.get('mobileUrls', []): media_url = mobile_url.get('mobileUrl') format_id = mobile_url.get('targetMediaPlatform') if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls: @@ -179,54 +179,34 @@ class LimelightBaseIE(InfoExtractor): self._sort_formats(formats) - title = properties['title'] - description = properties.get('description') - timestamp = int_or_none(properties.get('publish_date') or properties.get('create_date')) - duration = float_or_none(properties.get('duration_in_milliseconds'), 1000) - filesize = int_or_none(properties.get('total_storage_in_bytes')) - categories = [properties.get('category')] - tags = properties.get('tags', []) - thumbnails = [{ - 'url': thumbnail['url'], - 'width': int_or_none(thumbnail.get('width')), - 'height': int_or_none(thumbnail.get('height')), - } for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')] - subtitles = {} - for caption in properties.get('captions', []): - lang = caption.get('language_code') - subtitles_url = caption.get('url') - if lang and subtitles_url: - subtitles.setdefault(lang, []).append({ - 'url': subtitles_url, - }) - closed_captions_url = properties.get('closed_captions_url') - if closed_captions_url: - subtitles.setdefault('en', []).append({ - 'url': closed_captions_url, - 'ext': 'ttml', - }) + for flag in mobile_item.get('flags'): + if flag == 'ClosedCaptions': + closed_captions = self._call_playlist_service( + video_id, 'getClosedCaptionsDetailsByMediaId', + False, referer) or [] + for cc in closed_captions: + cc_url = cc.get('webvttFileUrl') + if not cc_url: + continue + lang = cc.get('languageCode') or self._search_regex(r'/[a-z]{2}\.vtt', cc_url, 'lang', default='en') + subtitles.setdefault(lang, []).append({ + 'url': cc_url, + }) + break + + get_meta = lambda x: pc_item.get(x) or mobile_item.get(x) return { 'id': video_id, 'title': title, - 'description': description, + 'description': get_meta('description'), 'formats': formats, - 'timestamp': timestamp, - 'duration': duration, - 'filesize': filesize, - 'categories': categories, - 'tags': tags, - 'thumbnails': thumbnails, + 'duration': float_or_none(get_meta('durationInMilliseconds'), 1000), + 'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'), 'subtitles': subtitles, } - def _extract_info_helper(self, pc, mobile, i, metadata): - return self._extract_info( - try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [], - try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [], - metadata) - class LimelightMediaIE(LimelightBaseIE): IE_NAME = 'limelight' @@ -251,8 +231,6 @@ class LimelightMediaIE(LimelightBaseIE): 'description': 'md5:8005b944181778e313d95c1237ddb640', 'thumbnail': r're:^https?://.*\.jpeg$', 'duration': 144.23, - 'timestamp': 1244136834, - 'upload_date': '20090604', }, 'params': { # m3u8 download @@ -268,30 +246,29 @@ class LimelightMediaIE(LimelightBaseIE): 'title': '3Play Media Overview Video', 'thumbnail': r're:^https?://.*\.jpeg$', 'duration': 78.101, - 'timestamp': 1338929955, - 'upload_date': '20120605', - 'subtitles': 'mincount:9', + # TODO: extract all languages that were accessible via API + # 'subtitles': 'mincount:9', + 'subtitles': 'mincount:1', }, }, { 'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452', 'only_matching': True, }] _PLAYLIST_SERVICE_PATH = 'media' - _API_PATH = 'media' def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) video_id = self._match_id(url) + source_url = smuggled_data.get('source_url') self._initialize_geo_bypass({ 'countries': smuggled_data.get('geo_countries'), }) - pc, mobile, metadata = self._extract( + pc, mobile = self._extract( video_id, 'getPlaylistByMediaId', - 'getMobilePlaylistByMediaId', 'properties', - smuggled_data.get('source_url')) + 'getMobilePlaylistByMediaId', source_url) - return self._extract_info_helper(pc, mobile, 0, metadata) + return self._extract_info(pc, mobile, 0, source_url) class LimelightChannelIE(LimelightBaseIE): @@ -313,6 +290,7 @@ class LimelightChannelIE(LimelightBaseIE): 'info_dict': { 'id': 'ab6a524c379342f9b23642917020c082', 'title': 'Javascript Sample Code', + 'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html', }, 'playlist_mincount': 3, }, { @@ -320,22 +298,23 @@ class LimelightChannelIE(LimelightBaseIE): 'only_matching': True, }] _PLAYLIST_SERVICE_PATH = 'channel' - _API_PATH = 'channels' def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) channel_id = self._match_id(url) + source_url = smuggled_data.get('source_url') - pc, mobile, medias = self._extract( + pc, mobile = self._extract( channel_id, 'getPlaylistByChannelId', 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', - 'media', smuggled_data.get('source_url')) + source_url) entries = [ - self._extract_info_helper(pc, mobile, i, medias['media_list'][i]) - for i in range(len(medias['media_list']))] + self._extract_info(pc, mobile, i, source_url) + for i in range(len(pc['playlistItems']))] - return self.playlist_result(entries, channel_id, pc['title']) + return self.playlist_result( + entries, channel_id, pc.get('title'), mobile.get('description')) class LimelightChannelListIE(LimelightBaseIE): @@ -368,10 +347,12 @@ class LimelightChannelListIE(LimelightBaseIE): def _real_extract(self, url): channel_list_id = self._match_id(url) - channel_list = self._call_playlist_service(channel_list_id, 'getMobileChannelListById') + channel_list = self._call_playlist_service( + channel_list_id, 'getMobileChannelListById') entries = [ self.url_result('limelight:channel:%s' % channel['id'], 'LimelightChannel') for channel in channel_list['channelList']] - return self.playlist_result(entries, channel_list_id, channel_list['title']) + return self.playlist_result( + entries, channel_list_id, channel_list['title']) diff --git a/youtube_dl/extractor/linuxacademy.py b/youtube_dl/extractor/linuxacademy.py index a78c6556e..23ca965d9 100644 --- a/youtube_dl/extractor/linuxacademy.py +++ b/youtube_dl/extractor/linuxacademy.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_b64decode, compat_HTTPError, - compat_str, ) from ..utils import ( ExtractorError, @@ -99,7 +98,7 @@ class LinuxAcademyIE(InfoExtractor): 'sso': 'true', }) - login_state_url = compat_str(urlh.geturl()) + login_state_url = urlh.geturl() try: login_page = self._download_webpage( @@ -129,7 +128,7 @@ class LinuxAcademyIE(InfoExtractor): }) access_token = self._search_regex( - r'access_token=([^=&]+)', compat_str(urlh.geturl()), + r'access_token=([^=&]+)', urlh.geturl(), 'access token') self._download_webpage( diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index 50234798b..65cc474db 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -128,6 +128,12 @@ class MailRuIE(InfoExtractor): 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON') + headers = {} + + video_key = self._get_cookies('https://my.mail.ru').get('video_key') + if video_key: + headers['Cookie'] = 'video_key=%s' % video_key.value + formats = [] for f in video_data['videos']: video_url = f.get('url') @@ -140,6 +146,7 @@ class MailRuIE(InfoExtractor): 'url': video_url, 'format_id': format_id, 'height': height, + 'http_headers': headers, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 027a790b8..933df1495 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -6,7 +6,6 @@ import re from .theplatform import ThePlatformBaseIE from ..compat import ( compat_parse_qs, - compat_str, compat_urllib_parse_urlparse, ) from ..utils import ( @@ -114,7 +113,7 @@ class MediasetIE(ThePlatformBaseIE): continue urlh = ie._request_webpage( embed_url, video_id, note='Following embed URL redirect') - embed_url = compat_str(urlh.geturl()) + embed_url = urlh.geturl() program_guid = _program_guid(_qs(embed_url)) if program_guid: entries.append(embed_url) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 694a264d6..d6eb15740 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -129,7 +129,7 @@ class MediasiteIE(InfoExtractor): query = mobj.group('query') webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer? - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() # XXX: might have also extracted UrlReferrer and QueryString from the html service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex( diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index 1c652813a..5234cac02 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -1,5 +1,8 @@ from __future__ import unicode_literals +import re + +from .common import InfoExtractor from ..utils import ( int_or_none, str_to_int, @@ -54,3 +57,23 @@ class MofosexIE(KeezMoviesIE): }) return info + + +class MofosexEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P\d+)' + _TESTS = [{ + 'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+\bsrc=["\']((?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)', + webpage) + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'http://www.mofosex.com/videos/{0}/{0}.html'.format(video_id), + ie=MofosexIE.ie_key(), video_id=video_id) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 43fd70f11..b1615b4d8 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -26,7 +26,7 @@ class MotherlessIE(InfoExtractor): 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], 'upload_date': '20100913', 'uploader_id': 'famouslyfuckedup', - 'thumbnail': r're:http://.*\.jpg', + 'thumbnail': r're:https?://.*\.jpg', 'age_limit': 18, } }, { @@ -40,7 +40,7 @@ class MotherlessIE(InfoExtractor): 'game', 'hairy'], 'upload_date': '20140622', 'uploader_id': 'Sulivana7x', - 'thumbnail': r're:http://.*\.jpg', + 'thumbnail': r're:https?://.*\.jpg', 'age_limit': 18, }, 'skip': '404', @@ -54,7 +54,7 @@ class MotherlessIE(InfoExtractor): 'categories': ['superheroine heroine superher'], 'upload_date': '20140827', 'uploader_id': 'shade0230', - 'thumbnail': r're:http://.*\.jpg', + 'thumbnail': r're:https?://.*\.jpg', 'age_limit': 18, } }, { @@ -76,7 +76,8 @@ class MotherlessIE(InfoExtractor): raise ExtractorError('Video %s is for friends only' % video_id, expected=True) title = self._html_search_regex( - r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') + (r'(?s)]+\bclass=["\']media-meta-title[^>]+>(.+?)', + r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title') video_url = (self._html_search_regex( (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', r'fileurl\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'), @@ -84,14 +85,15 @@ class MotherlessIE(InfoExtractor): or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id) age_limit = self._rta_search(webpage) view_count = str_to_int(self._html_search_regex( - r'Views\s+([^<]+)<', + (r'>(\d+)\s+Views<', r'Views\s+([^<]+)<'), webpage, 'view count', fatal=False)) like_count = str_to_int(self._html_search_regex( - r'Favorited\s+([^<]+)<', + (r'>(\d+)\s+Favorites<', r'Favorited\s+([^<]+)<'), webpage, 'like count', fatal=False)) upload_date = self._html_search_regex( - r'Uploaded\s+([^<]+)<', webpage, 'upload date') + (r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<', + r'Uploaded\s+([^<]+)<'), webpage, 'upload date') if 'Ago' in upload_date: days = int(re.search(r'([0-9]+)', upload_date).group(1)) upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 9c8bf05af..2447c812e 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( determine_ext, int_or_none, + merge_dicts, parse_iso8601, qualities, try_get, @@ -87,21 +88,25 @@ class NDRIE(NDRBaseIE): def _extract_embed(self, webpage, display_id): embed_url = self._html_search_meta( - 'embedURL', webpage, 'embed URL', fatal=True) + 'embedURL', webpage, 'embed URL', + default=None) or self._search_regex( + r'\bembedUrl["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'embed URL', group='url') description = self._search_regex( r']+itemprop="description">([^<]+)

    ', webpage, 'description', default=None) or self._og_search_description(webpage) timestamp = parse_iso8601( self._search_regex( r']+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"', - webpage, 'upload date', fatal=False)) - return { + webpage, 'upload date', default=None)) + info = self._search_json_ld(webpage, display_id, default={}) + return merge_dicts({ '_type': 'url_transparent', 'url': embed_url, 'display_id': display_id, 'description': description, 'timestamp': timestamp, - } + }, info) class NJoyIE(NDRBaseIE): diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 6a2c6cb7b..de6a707c4 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class NhkVodIE(InfoExtractor): - _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P[a-z]{2})/ondemand/(?Pvideo|audio)/(?P\d{7}|[a-z]+-\d{8}-\d+)' + _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P[a-z]{2})/ondemand/(?Pvideo|audio)/(?P\d{7}|[^/]+?-\d{8}-\d+)' # Content available only for a limited period of time. Visit # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples. _TESTS = [{ @@ -30,8 +30,11 @@ class NhkVodIE(InfoExtractor): }, { 'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/', 'only_matching': True, + }, { + 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/', + 'only_matching': True, }] - _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json' + _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json' def _real_extract(self, url): lang, m_type, episode_id = re.match(self._VALID_URL, url).groups() @@ -82,15 +85,9 @@ class NhkVodIE(InfoExtractor): audio = episode['audio'] audio_path = audio['audio'] info['formats'] = self._extract_m3u8_formats( - 'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path, - episode_id, 'm4a', m3u8_id='hls', fatal=False) - for proto in ('rtmpt', 'rtmp'): - info['formats'].append({ - 'ext': 'flv', - 'format_id': proto, - 'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path), - 'vcodec': 'none', - }) + 'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path, + episode_id, 'm4a', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False) for f in info['formats']: f['language'] = lang return info diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 901f44b54..47b9748f0 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import ( clean_html, + determine_ext, int_or_none, js_to_json, qualities, @@ -18,7 +19,7 @@ class NovaEmbedIE(InfoExtractor): _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P[^/?#&]+)' _TEST = { 'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1', - 'md5': 'b3834f6de5401baabf31ed57456463f7', + 'md5': 'ee009bafcc794541570edd44b71cbea3', 'info_dict': { 'id': '8o0n0r', 'ext': 'mp4', @@ -33,36 +34,76 @@ class NovaEmbedIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - bitrates = self._parse_json( - self._search_regex( - r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'), - video_id, transform_source=js_to_json) - - QUALITIES = ('lq', 'mq', 'hq', 'hd') - quality_key = qualities(QUALITIES) - + duration = None formats = [] - for format_id, format_list in bitrates.items(): - if not isinstance(format_list, list): - continue - for format_url in format_list: - format_url = url_or_none(format_url) - if not format_url: - continue - f = { - 'url': format_url, - } - f_id = format_id - for quality in QUALITIES: - if '%s.mp4' % quality in format_url: - f_id += '-%s' % quality - f.update({ - 'quality': quality_key(quality), - 'format_note': quality.upper(), + + player = self._parse_json( + self._search_regex( + r'Player\.init\s*\([^,]+,\s*({.+?})\s*,\s*{.+?}\s*\)\s*;', + webpage, 'player', default='{}'), video_id, fatal=False) + if player: + for format_id, format_list in player['tracks'].items(): + if not isinstance(format_list, list): + format_list = [format_list] + for format_dict in format_list: + if not isinstance(format_dict, dict): + continue + format_url = url_or_none(format_dict.get('src')) + format_type = format_dict.get('type') + ext = determine_ext(format_url) + if (format_type == 'application/x-mpegURL' + or format_id == 'HLS' or ext == 'm3u8'): + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + elif (format_type == 'application/dash+xml' + or format_id == 'DASH' or ext == 'mpd'): + formats.extend(self._extract_mpd_formats( + format_url, video_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'url': format_url, }) - break - f['format_id'] = f_id - formats.append(f) + duration = int_or_none(player.get('duration')) + else: + # Old path, not actual as of 08.04.2020 + bitrates = self._parse_json( + self._search_regex( + r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'), + video_id, transform_source=js_to_json) + + QUALITIES = ('lq', 'mq', 'hq', 'hd') + quality_key = qualities(QUALITIES) + + for format_id, format_list in bitrates.items(): + if not isinstance(format_list, list): + format_list = [format_list] + for format_url in format_list: + format_url = url_or_none(format_url) + if not format_url: + continue + if format_id == 'hls': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + continue + f = { + 'url': format_url, + } + f_id = format_id + for quality in QUALITIES: + if '%s.mp4' % quality in format_url: + f_id += '-%s' % quality + f.update({ + 'quality': quality_key(quality), + 'format_note': quality.upper(), + }) + break + f['format_id'] = f_id + formats.append(f) + self._sort_formats(formats) title = self._og_search_title( @@ -75,7 +116,8 @@ class NovaEmbedIE(InfoExtractor): r'poster\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'thumbnail', fatal=False, group='value') duration = int_or_none(self._search_regex( - r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False)) + r'videoDuration\s*:\s*(\d+)', webpage, 'duration', + default=duration)) return { 'id': video_id, @@ -91,7 +133,7 @@ class NovaIE(InfoExtractor): _VALID_URL = r'https?://(?:[^.]+\.)?(?Ptv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P[^/]+?)(?:\.html|/|$)' _TESTS = [{ 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', - 'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', + 'md5': '249baab7d0104e186e78b0899c7d5f28', 'info_dict': { 'id': '1757139', 'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci', @@ -113,7 +155,8 @@ class NovaIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'gone', }, { # media.cms.nova.cz embed 'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil', @@ -128,6 +171,7 @@ class NovaIE(InfoExtractor): 'skip_download': True, }, 'add_ie': [NovaEmbedIE.ie_key()], + 'skip': 'CHYBA 404: STRÁNKA NENALEZENA', }, { 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', 'only_matching': True, @@ -152,14 +196,29 @@ class NovaIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + description = clean_html(self._og_search_description(webpage, default=None)) + if site == 'novaplus': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) + elif site == 'fanda': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) + else: + upload_date = None + # novaplus embed_id = self._search_regex( r']+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)', webpage, 'embed url', default=None) if embed_id: - return self.url_result( - 'https://media.cms.nova.cz/embed/%s' % embed_id, - ie=NovaEmbedIE.ie_key(), video_id=embed_id) + return { + '_type': 'url_transparent', + 'url': 'https://media.cms.nova.cz/embed/%s' % embed_id, + 'ie_key': NovaEmbedIE.ie_key(), + 'id': embed_id, + 'description': description, + 'upload_date': upload_date + } video_id = self._search_regex( [r"(?:media|video_id)\s*:\s*'(\d+)'", @@ -233,18 +292,8 @@ class NovaIE(InfoExtractor): self._sort_formats(formats) title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage) - description = clean_html(self._og_search_description(webpage, default=None)) thumbnail = config.get('poster') - if site == 'novaplus': - upload_date = unified_strdate(self._search_regex( - r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) - elif site == 'fanda': - upload_date = unified_strdate(self._search_regex( - r'(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) - else: - upload_date = None - return { 'id': video_id, 'display_id': display_id, diff --git a/youtube_dl/extractor/npr.py b/youtube_dl/extractor/npr.py index a5e8baa7e..53acc6e57 100644 --- a/youtube_dl/extractor/npr.py +++ b/youtube_dl/extractor/npr.py @@ -4,6 +4,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, qualities, + url_or_none, ) @@ -48,6 +49,10 @@ class NprIE(InfoExtractor): }, }], 'expected_warnings': ['Failed to download m3u8 information'], + }, { + # multimedia, no formats, stream + 'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert', + 'only_matching': True, }] def _real_extract(self, url): @@ -95,6 +100,17 @@ class NprIE(InfoExtractor): 'format_id': format_id, 'quality': quality(format_id), }) + for stream_id, stream_entry in media.get('stream', {}).items(): + if not isinstance(stream_entry, dict): + continue + if stream_id != 'hlsUrl': + continue + stream_url = url_or_none(stream_entry.get('$text')) + if not stream_url: + continue + formats.extend(self._extract_m3u8_formats( + stream_url, stream_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) self._sort_formats(formats) entries.append({ diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index 2bb77ab24..fc78ca56c 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -69,10 +69,10 @@ class NYTimesBaseIE(InfoExtractor): 'width': int_or_none(video.get('width')), 'height': int_or_none(video.get('height')), 'filesize': get_file_size(video.get('file_size') or video.get('fileSize')), - 'tbr': int_or_none(video.get('bitrate'), 1000), + 'tbr': int_or_none(video.get('bitrate'), 1000) or None, 'ext': ext, }) - self._sort_formats(formats) + self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id')) thumbnails = [] for image in video_data.get('images', []): diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index d54b8ace6..700ce448c 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -162,13 +162,12 @@ class ORFTVthekIE(InfoExtractor): class ORFRadioIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - station = mobj.group('station') show_date = mobj.group('date') show_id = mobj.group('show') data = self._download_json( 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' - % (station, show_id, show_date), show_id) + % (self._API_STATION, show_id, show_date), show_id) entries = [] for info in data['streams']: @@ -183,7 +182,7 @@ class ORFRadioIE(InfoExtractor): duration = end - start if end and start else None entries.append({ 'id': loop_stream_id.replace('.mp3', ''), - 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, loop_stream_id), + 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id), 'title': title, 'description': clean_html(data.get('subtitle')), 'duration': duration, @@ -205,6 +204,8 @@ class ORFFM4IE(ORFRadioIE): IE_NAME = 'orf:fm4' IE_DESC = 'radio FM4' _VALID_URL = r'https?://(?Pfm4)\.orf\.at/player/(?P[0-9]+)/(?P4\w+)' + _API_STATION = 'fm4' + _LOOP_STATION = 'fm4' _TEST = { 'url': 'http://fm4.orf.at/player/20170107/4CC', @@ -223,10 +224,142 @@ class ORFFM4IE(ORFRadioIE): } +class ORFNOEIE(ORFRadioIE): + IE_NAME = 'orf:noe' + IE_DESC = 'Radio Niederösterreich' + _VALID_URL = r'https?://(?Pnoe)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'noe' + _LOOP_STATION = 'oe2n' + + _TEST = { + 'url': 'https://noe.orf.at/player/20200423/NGM', + 'only_matching': True, + } + + +class ORFWIEIE(ORFRadioIE): + IE_NAME = 'orf:wien' + IE_DESC = 'Radio Wien' + _VALID_URL = r'https?://(?Pwien)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'wie' + _LOOP_STATION = 'oe2w' + + _TEST = { + 'url': 'https://wien.orf.at/player/20200423/WGUM', + 'only_matching': True, + } + + +class ORFBGLIE(ORFRadioIE): + IE_NAME = 'orf:burgenland' + IE_DESC = 'Radio Burgenland' + _VALID_URL = r'https?://(?Pburgenland)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'bgl' + _LOOP_STATION = 'oe2b' + + _TEST = { + 'url': 'https://burgenland.orf.at/player/20200423/BGM', + 'only_matching': True, + } + + +class ORFOOEIE(ORFRadioIE): + IE_NAME = 'orf:oberoesterreich' + IE_DESC = 'Radio Oberösterreich' + _VALID_URL = r'https?://(?Pooe)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'ooe' + _LOOP_STATION = 'oe2o' + + _TEST = { + 'url': 'https://ooe.orf.at/player/20200423/OGMO', + 'only_matching': True, + } + + +class ORFSTMIE(ORFRadioIE): + IE_NAME = 'orf:steiermark' + IE_DESC = 'Radio Steiermark' + _VALID_URL = r'https?://(?Psteiermark)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'stm' + _LOOP_STATION = 'oe2st' + + _TEST = { + 'url': 'https://steiermark.orf.at/player/20200423/STGMS', + 'only_matching': True, + } + + +class ORFKTNIE(ORFRadioIE): + IE_NAME = 'orf:kaernten' + IE_DESC = 'Radio Kärnten' + _VALID_URL = r'https?://(?Pkaernten)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'ktn' + _LOOP_STATION = 'oe2k' + + _TEST = { + 'url': 'https://kaernten.orf.at/player/20200423/KGUMO', + 'only_matching': True, + } + + +class ORFSBGIE(ORFRadioIE): + IE_NAME = 'orf:salzburg' + IE_DESC = 'Radio Salzburg' + _VALID_URL = r'https?://(?Psalzburg)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'sbg' + _LOOP_STATION = 'oe2s' + + _TEST = { + 'url': 'https://salzburg.orf.at/player/20200423/SGUM', + 'only_matching': True, + } + + +class ORFTIRIE(ORFRadioIE): + IE_NAME = 'orf:tirol' + IE_DESC = 'Radio Tirol' + _VALID_URL = r'https?://(?Ptirol)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'tir' + _LOOP_STATION = 'oe2t' + + _TEST = { + 'url': 'https://tirol.orf.at/player/20200423/TGUMO', + 'only_matching': True, + } + + +class ORFVBGIE(ORFRadioIE): + IE_NAME = 'orf:vorarlberg' + IE_DESC = 'Radio Vorarlberg' + _VALID_URL = r'https?://(?Pvorarlberg)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'vbg' + _LOOP_STATION = 'oe2v' + + _TEST = { + 'url': 'https://vorarlberg.orf.at/player/20200423/VGUM', + 'only_matching': True, + } + + +class ORFOE3IE(ORFRadioIE): + IE_NAME = 'orf:oe3' + IE_DESC = 'Radio Österreich 3' + _VALID_URL = r'https?://(?Poe3)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'oe3' + _LOOP_STATION = 'oe3' + + _TEST = { + 'url': 'https://oe3.orf.at/player/20200424/3WEK', + 'only_matching': True, + } + + class ORFOE1IE(ORFRadioIE): IE_NAME = 'orf:oe1' IE_DESC = 'Radio Österreich 1' _VALID_URL = r'https?://(?Poe1)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' + _API_STATION = 'oe1' + _LOOP_STATION = 'oe1' _TEST = { 'url': 'http://oe1.orf.at/player/20170108/456544', diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index d3a83ea2b..48fb95416 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -8,6 +8,7 @@ from ..compat import compat_str from ..utils import ( int_or_none, parse_resolution, + str_or_none, try_get, unified_timestamp, url_or_none, @@ -415,6 +416,7 @@ class PeerTubeIE(InfoExtractor): peertube\.cpy\.re )''' _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}' + _API_BASE = 'https://%s/api/v1/videos/%s/%s' _VALID_URL = r'''(?x) (?: peertube:(?P[^:]+):| @@ -423,26 +425,30 @@ class PeerTubeIE(InfoExtractor): (?P%s) ''' % (_INSTANCES_RE, _UUID_RE) _TESTS = [{ - 'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c', - 'md5': '80f24ff364cc9d333529506a263e7feb', + 'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d', + 'md5': '9bed8c0137913e17b86334e5885aacff', 'info_dict': { - 'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c', + 'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d', 'ext': 'mp4', - 'title': 'wow', - 'description': 'wow such video, so gif', + 'title': 'What is PeerTube?', + 'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10', 'thumbnail': r're:https?://.*\.(?:jpg|png)', - 'timestamp': 1519297480, - 'upload_date': '20180222', - 'uploader': 'Luclu7', - 'uploader_id': '7fc42640-efdb-4505-a45d-a15b1a5496f1', - 'uploder_url': 'https://peertube.nsa.ovh/accounts/luclu7', - 'license': 'Unknown', - 'duration': 3, + 'timestamp': 1538391166, + 'upload_date': '20181001', + 'uploader': 'Framasoft', + 'uploader_id': '3', + 'uploader_url': 'https://framatube.org/accounts/framasoft', + 'channel': 'Les vidéos de Framasoft', + 'channel_id': '2', + 'channel_url': 'https://framatube.org/video-channels/bf54d359-cfad-4935-9d45-9d6be93f63e8', + 'language': 'en', + 'license': 'Attribution - Share Alike', + 'duration': 113, 'view_count': int, 'like_count': int, 'dislike_count': int, - 'tags': list, - 'categories': list, + 'tags': ['framasoft', 'peertube'], + 'categories': ['Science & Technology'], } }, { 'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44', @@ -484,13 +490,38 @@ class PeerTubeIE(InfoExtractor): entries = [peertube_url] return entries + def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True): + return self._download_json( + self._API_BASE % (host, video_id, path), video_id, + note=note, errnote=errnote, fatal=fatal) + + def _get_subtitles(self, host, video_id): + captions = self._call_api( + host, video_id, 'captions', note='Downloading captions JSON', + fatal=False) + if not isinstance(captions, dict): + return + data = captions.get('data') + if not isinstance(data, list): + return + subtitles = {} + for e in data: + language_id = try_get(e, lambda x: x['language']['id'], compat_str) + caption_url = urljoin('https://%s' % host, e.get('captionPath')) + if not caption_url: + continue + subtitles.setdefault(language_id or 'en', []).append({ + 'url': caption_url, + }) + return subtitles + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) host = mobj.group('host') or mobj.group('host_2') video_id = mobj.group('id') - video = self._download_json( - 'https://%s/api/v1/videos/%s' % (host, video_id), video_id) + video = self._call_api( + host, video_id, '', note='Downloading video JSON') title = video['name'] @@ -513,10 +544,28 @@ class PeerTubeIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - def account_data(field): - return try_get(video, lambda x: x['account'][field], compat_str) + full_description = self._call_api( + host, video_id, 'description', note='Downloading description JSON', + fatal=False) - category = try_get(video, lambda x: x['category']['label'], compat_str) + description = None + if isinstance(full_description, dict): + description = str_or_none(full_description.get('description')) + if not description: + description = video.get('description') + + subtitles = self.extract_subtitles(host, video_id) + + def data(section, field, type_): + return try_get(video, lambda x: x[section][field], type_) + + def account_data(field, type_): + return data('account', field, type_) + + def channel_data(field, type_): + return data('channel', field, type_) + + category = data('category', 'label', compat_str) categories = [category] if category else None nsfw = video.get('nsfw') @@ -528,14 +577,17 @@ class PeerTubeIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'description': video.get('description'), + 'description': description, 'thumbnail': urljoin(url, video.get('thumbnailPath')), 'timestamp': unified_timestamp(video.get('publishedAt')), - 'uploader': account_data('displayName'), - 'uploader_id': account_data('uuid'), - 'uploder_url': account_data('url'), - 'license': try_get( - video, lambda x: x['licence']['label'], compat_str), + 'uploader': account_data('displayName', compat_str), + 'uploader_id': str_or_none(account_data('id', int)), + 'uploader_url': url_or_none(account_data('url', compat_str)), + 'channel': channel_data('displayName', compat_str), + 'channel_id': str_or_none(channel_data('id', int)), + 'channel_url': url_or_none(channel_data('url', compat_str)), + 'language': data('language', 'id', compat_str), + 'license': data('licence', 'label', compat_str), 'duration': int_or_none(video.get('duration')), 'view_count': int_or_none(video.get('views')), 'like_count': int_or_none(video.get('likes')), @@ -544,4 +596,5 @@ class PeerTubeIE(InfoExtractor): 'tags': try_get(video, lambda x: x['tags'], list), 'categories': categories, 'formats': formats, + 'subtitles': subtitles } diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py index 602207beb..23c8256b5 100644 --- a/youtube_dl/extractor/platzi.py +++ b/youtube_dl/extractor/platzi.py @@ -46,7 +46,7 @@ class PlatziBaseIE(InfoExtractor): headers={'Referer': self._LOGIN_URL}) # login succeeded - if 'platzi.com/login' not in compat_str(urlh.geturl()): + if 'platzi.com/login' not in urlh.geturl(): return login_error = self._webpage_read_content( diff --git a/youtube_dl/extractor/pokemon.py b/youtube_dl/extractor/pokemon.py index dd5f17f11..80222d428 100644 --- a/youtube_dl/extractor/pokemon.py +++ b/youtube_dl/extractor/pokemon.py @@ -20,20 +20,16 @@ class PokemonIE(InfoExtractor): 'ext': 'mp4', 'title': 'The Ol’ Raise and Switch!', 'description': 'md5:7db77f7107f98ba88401d3adc80ff7af', - 'timestamp': 1511824728, - 'upload_date': '20171127', }, 'add_id': ['LimelightMedia'], }, { # no data-video-title - 'url': 'https://www.pokemon.com/us/pokemon-episodes/pokemon-movies/pokemon-the-rise-of-darkrai-2008', + 'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008', 'info_dict': { - 'id': '99f3bae270bf4e5097274817239ce9c8', + 'id': 'dfbaf830d7e54e179837c50c0c6cc0e1', 'ext': 'mp4', - 'title': 'Pokémon: The Rise of Darkrai', - 'description': 'md5:ea8fbbf942e1e497d54b19025dd57d9d', - 'timestamp': 1417778347, - 'upload_date': '20141205', + 'title': "Pokémon : L'ascension de Darkrai", + 'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5', }, 'add_id': ['LimelightMedia'], 'params': { diff --git a/youtube_dl/extractor/popcorntimes.py b/youtube_dl/extractor/popcorntimes.py new file mode 100644 index 000000000..7bf7f9858 --- /dev/null +++ b/youtube_dl/extractor/popcorntimes.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_chr, +) +from ..utils import int_or_none + + +class PopcorntimesIE(InfoExtractor): + _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P[^/]+)/(?P[^/?#&]+)' + _TEST = { + 'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy', + 'md5': '93f210991ad94ba8c3485950a2453257', + 'info_dict': { + 'id': 'A1XCFvz', + 'display_id': 'haensel-und-gretel-opera-fantasy', + 'ext': 'mp4', + 'title': 'Hänsel und Gretel', + 'description': 'md5:1b8146791726342e7b22ce8125cf6945', + 'thumbnail': r're:^https?://.*\.jpg$', + 'creator': 'John Paul', + 'release_date': '19541009', + 'duration': 4260, + 'tbr': 5380, + 'width': 720, + 'height': 540, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id, display_id = mobj.group('id', 'display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._search_regex( + r'

    ([^<]+)', webpage, 'title', + default=None) or self._html_search_meta( + 'ya:ovs:original_name', webpage, 'title', fatal=True) + + loc = self._search_regex( + r'PCTMLOC\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'loc', + group='value') + + loc_b64 = '' + for c in loc: + c_ord = ord(c) + if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'): + upper = ord('Z') if c_ord <= ord('Z') else ord('z') + c_ord += 13 + if upper < c_ord: + c_ord -= 26 + loc_b64 += compat_chr(c_ord) + + video_url = compat_b64decode(loc_b64).decode('utf-8') + + description = self._html_search_regex( + r'(?s)]+class=["\']pt-movie-desc[^>]+>(.+?)', webpage, + 'description', fatal=False) + + thumbnail = self._search_regex( + r']+class=["\']video-preview[^>]+\bsrc=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'thumbnail', default=None, + group='value') or self._og_search_thumbnail(webpage) + + creator = self._html_search_meta( + 'video:director', webpage, 'creator', default=None) + + release_date = self._html_search_meta( + 'video:release_date', webpage, default=None) + if release_date: + release_date = release_date.replace('-', '') + + def int_meta(name): + return int_or_none(self._html_search_meta( + name, webpage, default=None)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'creator': creator, + 'release_date': release_date, + 'duration': int_meta('video:duration'), + 'tbr': int_meta('ya:ovs:bitrate'), + 'width': int_meta('og:video:width'), + 'height': int_meta('og:video:height'), + 'http_headers': { + 'Referer': url, + }, + } diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 27d65d4b9..c6052ac9f 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -8,6 +8,7 @@ from ..utils import ( ExtractorError, int_or_none, js_to_json, + merge_dicts, urljoin, ) @@ -27,23 +28,22 @@ class PornHdIE(InfoExtractor): 'view_count': int, 'like_count': int, 'age_limit': 18, - } + }, + 'skip': 'HTTP Error 404: Not Found', }, { - # removed video 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - 'md5': '956b8ca569f7f4d8ec563e2c41598441', + 'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de', 'info_dict': { 'id': '1962', 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', - 'title': 'Sierra loves doing laundry', + 'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, 'like_count': int, 'age_limit': 18, }, - 'skip': 'Not available anymore', }] def _real_extract(self, url): @@ -61,7 +61,13 @@ class PornHdIE(InfoExtractor): r"(?s)sources'?\s*[:=]\s*(\{.+?\})", webpage, 'sources', default='{}')), video_id) + info = {} if not sources: + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info = entries[0] + + if not sources and not info: message = self._html_search_regex( r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P.+?)]+class="description"[^>]*>(?P[^<]+)]+class=["\']video-description[^>]+>(?P.+?)', + r'<(div|p)[^>]+class="description"[^>]*>(?P[^<]+)(?:(?!\1).)+)\1", webpage, - 'thumbnail', fatal=False, group='url') + 'thumbnail', default=None, group='url') like_count = int_or_none(self._search_regex( - (r'(\d+)\s*]+>(?: |\s)*\blikes', + (r'(\d+)\s*likes', + r'(\d+)\s*]+>(?: |\s)*\blikes', r'class=["\']save-count["\'][^>]*>\s*(\d+)'), webpage, 'like count', fatal=False)) - return { + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -106,4 +118,4 @@ class PornHdIE(InfoExtractor): 'like_count': like_count, 'formats': formats, 'age_limit': 18, - } + }) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index b3251ccd9..3567a3283 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -52,7 +52,7 @@ class PornHubIE(PornHubBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?(?Ppornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?(?Ppornhub(?:premium)?\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P[\da-z]+) @@ -149,6 +149,9 @@ class PornHubIE(PornHubBaseIE): }, { 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', 'only_matching': True, + }, { + 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82', + 'only_matching': True, }] @staticmethod @@ -166,6 +169,13 @@ class PornHubIE(PornHubBaseIE): host = mobj.group('host') or 'pornhub.com' video_id = mobj.group('id') + if 'premium' in host: + if not self._downloader.params.get('cookiefile'): + raise ExtractorError( + 'PornHub Premium requires authentication.' + ' You may want to use --cookies.', + expected=True) + self._set_cookie(host, 'age_verified', '1') def dl_webpage(platform): @@ -189,10 +199,10 @@ class PornHubIE(PornHubBaseIE): # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. title = self._html_search_meta( - 'twitter:title', webpage, default=None) or self._search_regex( - (r']+class=["\']title["\'][^>]*>(?P[^<]+)', - r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', - r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), + 'twitter:title', webpage, default=None) or self._html_search_regex( + (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>', + r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1', + r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'), webpage, 'title', group='title') video_urls = [] @@ -405,7 +415,7 @@ class PornHubPlaylistBaseIE(PornHubBaseIE): class PornHubUserIE(PornHubPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph', 'playlist_mincount': 118, @@ -473,7 +483,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph/videos', 'only_matching': True, @@ -588,7 +598,7 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' _TESTS = [{ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', 'info_dict': { diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 1bc4f9b6b..e47088292 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -11,6 +11,7 @@ from ..utils import ( determine_ext, float_or_none, int_or_none, + merge_dicts, unified_strdate, ) @@ -175,7 +176,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): (?: (?:beta\.)? (?: - prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|7tv|advopedia + prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|advopedia )\.(?:de|at|ch)| ran\.de|fem\.com|advopedia\.de|galileo\.tv/video ) @@ -193,10 +194,14 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): 'info_dict': { 'id': '2104602', 'ext': 'mp4', - 'title': 'Episode 18 - Staffel 2', + 'title': 'CIRCUS HALLIGALLI - Episode 18 - Staffel 2', 'description': 'md5:8733c81b702ea472e069bc48bb658fc1', 'upload_date': '20131231', 'duration': 5845.04, + 'series': 'CIRCUS HALLIGALLI', + 'season_number': 2, + 'episode': 'Episode 18 - Staffel 2', + 'episode_number': 18, }, }, { @@ -300,8 +305,9 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): 'info_dict': { 'id': '2572814', 'ext': 'mp4', - 'title': 'Andreas Kümmert: Rocket Man', + 'title': 'The Voice of Germany - Andreas Kümmert: Rocket Man', 'description': 'md5:6ddb02b0781c6adf778afea606652e38', + 'timestamp': 1382041620, 'upload_date': '20131017', 'duration': 469.88, }, @@ -310,7 +316,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): }, }, { - 'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html', + 'url': 'http://www.fem.com/videos/beauty-lifestyle/kurztrips-zum-valentinstag', 'info_dict': { 'id': '2156342', 'ext': 'mp4', @@ -332,19 +338,6 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): 'playlist_count': 2, 'skip': 'This video is unavailable', }, - { - 'url': 'http://www.7tv.de/circus-halligalli/615-best-of-circus-halligalli-ganze-folge', - 'info_dict': { - 'id': '4187506', - 'ext': 'mp4', - 'title': 'Best of Circus HalliGalli', - 'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9', - 'upload_date': '20151229', - }, - 'params': { - 'skip_download': True, - }, - }, { # title in <h2 class="subtitle"> 'url': 'http://www.prosieben.de/stars/oscar-award/videos/jetzt-erst-enthuellt-das-geheimnis-von-emma-stones-oscar-robe-clip', @@ -421,7 +414,6 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): r'<div[^>]+id="veeseoDescription"[^>]*>(.+?)</div>', ] _UPLOAD_DATE_REGEXES = [ - r'<meta property="og:published_time" content="(.+?)">', r'<span>\s*(\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}) \|\s*<span itemprop="duration"', r'<footer>\s*(\d{2}\.\d{2}\.\d{4}) \d{2}:\d{2} Uhr', r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>', @@ -451,17 +443,21 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): if description is None: description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage) - upload_date = unified_strdate(self._html_search_regex( - self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None)) + upload_date = unified_strdate( + self._html_search_meta('og:published_time', webpage, + 'upload date', default=None) + or self._html_search_regex(self._UPLOAD_DATE_REGEXES, + webpage, 'upload date', default=None)) - info.update({ + json_ld = self._search_json_ld(webpage, clip_id, default={}) + + return merge_dicts(info, { 'id': clip_id, 'title': title, 'description': description, 'thumbnail': thumbnail, 'upload_date': upload_date, - }) - return info + }, json_ld) def _extract_playlist(self, url, webpage): playlist_id = self._html_search_regex( diff --git a/youtube_dl/extractor/puhutv.py b/youtube_dl/extractor/puhutv.py index fb704a3c4..ca71665e0 100644 --- a/youtube_dl/extractor/puhutv.py +++ b/youtube_dl/extractor/puhutv.py @@ -82,17 +82,6 @@ class PuhuTVIE(InfoExtractor): urls = [] formats = [] - def add_http_from_hls(m3u8_f): - http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4') - if http_url != m3u8_f['url']: - f = m3u8_f.copy() - f.update({ - 'format_id': f['format_id'].replace('hls', 'http'), - 'protocol': 'http', - 'url': http_url, - }) - formats.append(f) - for video in videos['data']['videos']: media_url = url_or_none(video.get('url')) if not media_url or media_url in urls: @@ -101,12 +90,9 @@ class PuhuTVIE(InfoExtractor): playlist = video.get('is_playlist') if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url: - m3u8_formats = self._extract_m3u8_formats( + formats.extend(self._extract_m3u8_formats( media_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False) - for m3u8_f in m3u8_formats: - formats.append(m3u8_f) - add_http_from_hls(m3u8_f) + m3u8_id='hls', fatal=False)) continue quality = int_or_none(video.get('quality')) @@ -128,8 +114,6 @@ class PuhuTVIE(InfoExtractor): format_id += '-%sp' % quality f['format_id'] = format_id formats.append(f) - if is_hls: - add_http_from_hls(f) self._sort_formats(formats) creator = try_get( diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 4942437c7..2cc665122 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_parse_qs, - compat_str, compat_urlparse, ) from ..utils import ( @@ -39,13 +38,13 @@ class SafariBaseIE(InfoExtractor): 'Downloading login page') def is_logged(urlh): - return 'learning.oreilly.com/home/' in compat_str(urlh.geturl()) + return 'learning.oreilly.com/home/' in urlh.geturl() if is_logged(urlh): self.LOGGED_IN = True return - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() parsed_url = compat_urlparse.urlparse(redirect_url) qs = compat_parse_qs(parsed_url.query) next_uri = compat_urlparse.urljoin( diff --git a/youtube_dl/extractor/servus.py b/youtube_dl/extractor/servus.py index e579d42cf..9401bf2cf 100644 --- a/youtube_dl/extractor/servus.py +++ b/youtube_dl/extractor/servus.py @@ -7,9 +7,18 @@ from .common import InfoExtractor class ServusIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?: + servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)| + servustv\.com/videos + ) + /(?P<id>[aA]{2}-\w+|\d+-\d+) + ''' _TESTS = [{ - 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', + # new URL schema + 'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/', 'md5': '3e1dd16775aa8d5cbef23628cfffc1f4', 'info_dict': { 'id': 'AA-1T6VBU5PW1W12', @@ -18,6 +27,10 @@ class ServusIE(InfoExtractor): 'description': 'md5:1247204d85783afe3682644398ff2ec4', 'thumbnail': r're:^https?://.*\.jpg', } + }, { + # old URL schema + 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', + 'only_matching': True, }, { 'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/', 'only_matching': True, diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index a1372d389..422ce1626 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -27,6 +27,7 @@ from ..utils import ( unified_timestamp, update_url_query, url_or_none, + urlhandle_detect_ext, ) @@ -96,7 +97,7 @@ class SoundcloudIE(InfoExtractor): 'repost_count': int, } }, - # not streamable song, preview + # geo-restricted { 'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep', 'info_dict': { @@ -108,17 +109,13 @@ class SoundcloudIE(InfoExtractor): 'uploader_id': '9615865', 'timestamp': 1337635207, 'upload_date': '20120521', - 'duration': 30, + 'duration': 227.155, 'license': 'all-rights-reserved', 'view_count': int, 'like_count': int, 'comment_count': int, 'repost_count': int, }, - 'params': { - # rtmp - 'skip_download': True, - }, }, # private link { @@ -229,7 +226,6 @@ class SoundcloudIE(InfoExtractor): 'skip_download': True, }, }, - # not available via api.soundcloud.com/i1/tracks/id/streams { 'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer', 'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7', @@ -250,11 +246,14 @@ class SoundcloudIE(InfoExtractor): 'comment_count': int, 'repost_count': int, }, - 'expected_warnings': ['Unable to download JSON metadata'], - } + }, + { + # with AAC HQ format available via OAuth token + 'url': 'https://soundcloud.com/wandw/the-chainsmokers-ft-daya-dont-let-me-down-ww-remix-1', + 'only_matching': True, + }, ] - _API_BASE = 'https://api.soundcloud.com/' _API_V2_BASE = 'https://api-v2.soundcloud.com/' _BASE_URL = 'https://soundcloud.com/' _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg' @@ -316,10 +315,9 @@ class SoundcloudIE(InfoExtractor): def _resolv_url(cls, url): return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url - def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2): + def _extract_info_dict(self, info, full_title=None, secret_token=None): track_id = compat_str(info['id']) title = info['title'] - track_base_url = self._API_BASE + 'tracks/%s' % track_id format_urls = set() formats = [] @@ -328,21 +326,22 @@ class SoundcloudIE(InfoExtractor): query['secret_token'] = secret_token if info.get('downloadable') and info.get('has_downloads_left'): - format_url = update_url_query( - info.get('download_url') or track_base_url + '/download', query) - format_urls.add(format_url) - if version == 2: - v1_info = self._download_json( - track_base_url, track_id, query=query, fatal=False) or {} - else: - v1_info = info - formats.append({ - 'format_id': 'download', - 'ext': v1_info.get('original_format') or 'mp3', - 'filesize': int_or_none(v1_info.get('original_content_size')), - 'url': format_url, - 'preference': 10, - }) + download_url = update_url_query( + self._API_V2_BASE + 'tracks/' + track_id + '/download', query) + redirect_url = (self._download_json(download_url, track_id, fatal=False) or {}).get('redirectUri') + if redirect_url: + urlh = self._request_webpage( + HEADRequest(redirect_url), track_id, fatal=False) + if urlh: + format_url = urlh.geturl() + format_urls.add(format_url) + formats.append({ + 'format_id': 'download', + 'ext': urlhandle_detect_ext(urlh) or 'mp3', + 'filesize': int_or_none(urlh.headers.get('Content-Length')), + 'url': format_url, + 'preference': 10, + }) def invalid_url(url): return not url or url in format_urls @@ -356,6 +355,9 @@ class SoundcloudIE(InfoExtractor): format_id_list = [] if protocol: format_id_list.append(protocol) + ext = f.get('ext') + if ext == 'aac': + f['abr'] = '256' for k in ('ext', 'abr'): v = f.get(k) if v: @@ -366,9 +368,13 @@ class SoundcloudIE(InfoExtractor): abr = f.get('abr') if abr: f['abr'] = int(abr) + if protocol == 'hls': + protocol = 'm3u8' if ext == 'aac' else 'm3u8_native' + else: + protocol = 'http' f.update({ 'format_id': '_'.join(format_id_list), - 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', + 'protocol': protocol, 'preference': -10 if preview else None, }) formats.append(f) @@ -406,42 +412,11 @@ class SoundcloudIE(InfoExtractor): }, 'http' if protocol == 'progressive' else protocol, t.get('snipped') or '/preview/' in format_url) - if not formats: - # Old API, does not work for some tracks (e.g. - # https://soundcloud.com/giovannisarani/mezzo-valzer) - # and might serve preview URLs (e.g. - # http://www.soundcloud.com/snbrn/ele) - format_dict = self._download_json( - track_base_url + '/streams', track_id, - 'Downloading track url', query=query, fatal=False) or {} - - for key, stream_url in format_dict.items(): - if invalid_url(stream_url): - continue - format_urls.add(stream_url) - mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key) - if mobj: - protocol, ext, abr = mobj.groups() - add_format({ - 'abr': abr, - 'ext': ext, - 'url': stream_url, - }, protocol) - - if not formats: - # We fallback to the stream_url in the original info, this - # cannot be always used, sometimes it can give an HTTP 404 error - urlh = self._request_webpage( - HEADRequest(info.get('stream_url') or track_base_url + '/stream'), - track_id, query=query, fatal=False) - if urlh: - stream_url = urlh.geturl() - if not invalid_url(stream_url): - add_format({'url': stream_url}, 'http') - for f in formats: f['vcodec'] = 'none' + if not formats and info.get('policy') == 'BLOCK': + self.raise_geo_restricted() self._sort_formats(formats) user = info.get('user') or {} @@ -511,16 +486,10 @@ class SoundcloudIE(InfoExtractor): resolve_title += '/%s' % token info_json_url = self._resolv_url(self._BASE_URL + resolve_title) - version = 2 info = self._download_json( - info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False) - if not info: - info = self._download_json( - info_json_url.replace(self._API_V2_BASE, self._API_BASE), - full_title, 'Downloading info JSON', query=query) - version = 1 + info_json_url, full_title, 'Downloading info JSON', query=query) - return self._extract_info_dict(info, full_title, token, version) + return self._extract_info_dict(info, full_title, token) class SoundcloudPlaylistBaseIE(SoundcloudIE): diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 44d8fa52f..35ab9ec37 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -3,34 +3,47 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_unquote, - compat_urllib_parse_urlparse, -) from ..utils import ( - sanitized_Request, + float_or_none, + int_or_none, + merge_dicts, + str_or_none, str_to_int, - unified_strdate, + url_or_none, ) -from ..aes import aes_decrypt_text class SpankwireIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<id>[0-9]+)/?)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?spankwire\.com/ + (?: + [^/]+/video| + EmbedPlayer\.aspx/?\?.*?\bArticleId= + ) + (?P<id>\d+) + ''' _TESTS = [{ # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/', - 'md5': '8bbfde12b101204b39e4b9fe7eb67095', + 'md5': '5aa0e4feef20aad82cbcae3aed7ab7cd', 'info_dict': { 'id': '103545', 'ext': 'mp4', 'title': 'Buckcherry`s X Rated Music Video Crazy Bitch', 'description': 'Crazy Bitch X rated music video.', + 'duration': 222, 'uploader': 'oreusz', 'uploader_id': '124697', - 'upload_date': '20070507', + 'timestamp': 1178587885, + 'upload_date': '20070508', + 'average_rating': float, + 'view_count': int, + 'comment_count': int, 'age_limit': 18, - } + 'categories': list, + 'tags': list, + }, }, { # download URL pattern: */mp4_<format_id>_<video_id>.mp4 'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/', @@ -45,83 +58,125 @@ class SpankwireIE(InfoExtractor): 'upload_date': '20150822', 'age_limit': 18, }, + 'params': { + 'proxy': '127.0.0.1:8118' + }, + 'skip': 'removed', + }, { + 'url': 'https://www.spankwire.com/EmbedPlayer.aspx/?ArticleId=156156&autostart=true', + 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?spankwire\.com/EmbedPlayer\.aspx/?\?.*?\bArticleId=\d+)', + webpage) + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - req = sanitized_Request('http://www.' + mobj.group('url')) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + video = self._download_json( + 'https://www.spankwire.com/api/video/%s.json' % video_id, video_id) - title = self._html_search_regex( - r'<h1>([^<]+)', webpage, 'title') - description = self._html_search_regex( - r'(?s)<div\s+id="descriptionContent">(.+?)</div>', - webpage, 'description', fatal=False) - thumbnail = self._html_search_regex( - r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']', - webpage, 'thumbnail', fatal=False) - - uploader = self._html_search_regex( - r'by:\s*<a [^>]*>(.+?)</a>', - webpage, 'uploader', fatal=False) - uploader_id = self._html_search_regex( - r'by:\s*<a href="/(?:user/viewProfile|Profile\.aspx)\?.*?UserId=(\d+).*?"', - webpage, 'uploader id', fatal=False) - upload_date = unified_strdate(self._html_search_regex( - r'</a> on (.+?) at \d+:\d+', - webpage, 'upload date', fatal=False)) - - view_count = str_to_int(self._html_search_regex( - r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>', - webpage, 'view count', fatal=False)) - comment_count = str_to_int(self._html_search_regex( - r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>', - webpage, 'comment count', fatal=False)) - - videos = re.findall( - r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage) - heights = [int(video[0]) for video in videos] - video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos])) - if webpage.find(r'flashvars\.encrypted = "true"') != -1: - password = self._search_regex( - r'flashvars\.video_title = "([^"]+)', - webpage, 'password').replace('+', ' ') - video_urls = list(map( - lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), - video_urls)) + title = video['title'] formats = [] - for height, video_url in zip(heights, video_urls): - path = compat_urllib_parse_urlparse(video_url).path - m = re.search(r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', path) - if m: - tbr = int(m.group('tbr')) - height = int(m.group('height')) - else: - tbr = None - formats.append({ - 'url': video_url, - 'format_id': '%dp' % height, - 'height': height, - 'tbr': tbr, + videos = video.get('videos') + if isinstance(videos, dict): + for format_id, format_url in videos.items(): + video_url = url_or_none(format_url) + if not format_url: + continue + height = int_or_none(self._search_regex( + r'(\d+)[pP]', format_id, 'height', default=None)) + m = re.search( + r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', video_url) + if m: + tbr = int(m.group('tbr')) + height = height or int(m.group('height')) + else: + tbr = None + formats.append({ + 'url': video_url, + 'format_id': '%dp' % height if height else format_id, + 'height': height, + 'tbr': tbr, + }) + m3u8_url = url_or_none(video.get('HLS')) + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + self._sort_formats(formats, ('height', 'tbr', 'width', 'format_id')) + + view_count = str_to_int(video.get('viewed')) + + thumbnails = [] + for preference, t in enumerate(('', '2x'), start=0): + thumbnail_url = url_or_none(video.get('poster%s' % t)) + if not thumbnail_url: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'preference': preference, }) - self._sort_formats(formats) - age_limit = self._rta_search(webpage) + def extract_names(key): + entries_list = video.get(key) + if not isinstance(entries_list, list): + return + entries = [] + for entry in entries_list: + name = str_or_none(entry.get('name')) + if name: + entries.append(name) + return entries - return { + categories = extract_names('categories') + tags = extract_names('tags') + + uploader = None + info = {} + + webpage = self._download_webpage( + 'https://www.spankwire.com/_/video%s/' % video_id, video_id, + fatal=False) + if webpage: + info = self._search_json_ld(webpage, video_id, default={}) + thumbnail_url = None + if 'thumbnail' in info: + thumbnail_url = url_or_none(info['thumbnail']) + del info['thumbnail'] + if not thumbnail_url: + thumbnail_url = self._og_search_thumbnail(webpage) + if thumbnail_url: + thumbnails.append({ + 'url': thumbnail_url, + 'preference': 10, + }) + uploader = self._html_search_regex( + r'(?s)by\s*<a[^>]+\bclass=["\']uploaded__by[^>]*>(.+?)</a>', + webpage, 'uploader', fatal=False) + if not view_count: + view_count = str_to_int(self._search_regex( + r'data-views=["\']([\d,.]+)', webpage, 'view count', + fatal=False)) + + return merge_dicts({ 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, + 'description': video.get('description'), + 'duration': int_or_none(video.get('duration')), + 'thumbnails': thumbnails, 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, + 'uploader_id': str_or_none(video.get('userId')), + 'timestamp': int_or_none(video.get('time_approved_on')), + 'average_rating': float_or_none(video.get('rating')), 'view_count': view_count, - 'comment_count': comment_count, + 'comment_count': int_or_none(video.get('comments')), + 'age_limit': 18, + 'categories': categories, + 'tags': tags, 'formats': formats, - 'age_limit': age_limit, - } + }, info) diff --git a/youtube_dl/extractor/spike.py b/youtube_dl/extractor/spike.py index 7c11ea7aa..aabff7a3c 100644 --- a/youtube_dl/extractor/spike.py +++ b/youtube_dl/extractor/spike.py @@ -8,15 +8,10 @@ class BellatorIE(MTVServicesInfoExtractor): _TESTS = [{ 'url': 'http://www.bellator.com/fight/atwr7k/bellator-158-michael-page-vs-evangelista-cyborg', 'info_dict': { - 'id': 'b55e434e-fde1-4a98-b7cc-92003a034de4', - 'ext': 'mp4', - 'title': 'Douglas Lima vs. Paul Daley - Round 1', - 'description': 'md5:805a8dd29310fd611d32baba2f767885', - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'title': 'Michael Page vs. Evangelista Cyborg', + 'description': 'md5:0d917fc00ffd72dd92814963fc6cbb05', }, + 'playlist_count': 3, }, { 'url': 'http://www.bellator.com/video-clips/bw6k7n/bellator-158-foundations-michael-venom-page', 'only_matching': True, @@ -25,6 +20,9 @@ class BellatorIE(MTVServicesInfoExtractor): _FEED_URL = 'http://www.bellator.com/feeds/mrss/' _GEO_COUNTRIES = ['US'] + def _extract_mgid(self, webpage): + return self._extract_triforce_mgid(webpage) + class ParamountNetworkIE(MTVServicesInfoExtractor): _VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)' diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 6b7f13b43..a75369dbe 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -4,11 +4,12 @@ import re from .common import InfoExtractor from .wistia import WistiaIE -from ..compat import compat_str from ..utils import ( clean_html, ExtractorError, + int_or_none, get_element_by_class, + strip_or_none, urlencode_postdata, urljoin, ) @@ -20,8 +21,8 @@ class TeachableBaseIE(InfoExtractor): _SITES = { # Only notable ones here - 'upskillcourses.com': 'upskill', - 'academy.gns3.com': 'gns3', + 'v1.upskillcourses.com': 'upskill', + 'gns3.teachable.com': 'gns3', 'academyhacker.com': 'academyhacker', 'stackskills.com': 'stackskills', 'market.saleshacker.com': 'saleshacker', @@ -58,7 +59,7 @@ class TeachableBaseIE(InfoExtractor): self._logged_in = True return - login_url = compat_str(urlh.geturl()) + login_url = urlh.geturl() login_form = self._hidden_inputs(login_page) @@ -110,27 +111,29 @@ class TeachableIE(TeachableBaseIE): ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ - 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364', 'info_dict': { - 'id': 'uzw6zw58or', - 'ext': 'mp4', - 'title': 'Welcome to the Course!', - 'description': 'md5:65edb0affa582974de4625b9cdea1107', - 'duration': 138.763, - 'timestamp': 1479846621, - 'upload_date': '20161122', + 'id': 'untlgzk1v7', + 'ext': 'bin', + 'title': 'Overview', + 'description': 'md5:071463ff08b86c208811130ea1c2464c', + 'duration': 736.4, + 'timestamp': 1542315762, + 'upload_date': '20181115', + 'chapter': 'Welcome', + 'chapter_number': 1, }, 'params': { 'skip_download': True, }, }, { - 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100', + 'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100', 'only_matching': True, }, { - 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939', + 'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939', 'only_matching': True, }, { - 'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', 'only_matching': True, }] @@ -160,8 +163,8 @@ class TeachableIE(TeachableBaseIE): webpage = self._download_webpage(url, video_id) - wistia_url = WistiaIE._extract_url(webpage) - if not wistia_url: + wistia_urls = WistiaIE._extract_urls(webpage) + if not wistia_urls: if any(re.search(p, webpage) for p in ( r'class=["\']lecture-contents-locked', r'>\s*Lecture contents locked', @@ -174,12 +177,37 @@ class TeachableIE(TeachableBaseIE): title = self._og_search_title(webpage, default=None) - return { + chapter = None + chapter_number = None + section_item = self._search_regex( + r'(?s)(?P<li><li[^>]+\bdata-lecture-id=["\']%s[^>]+>.+?</li>)' % video_id, + webpage, 'section item', default=None, group='li') + if section_item: + chapter_number = int_or_none(self._search_regex( + r'data-ss-position=["\'](\d+)', section_item, 'section id', + default=None)) + if chapter_number is not None: + sections = [] + for s in re.findall( + r'(?s)<div[^>]+\bclass=["\']section-title[^>]+>(.+?)</div>', webpage): + section = strip_or_none(clean_html(s)) + if not section: + sections = [] + break + sections.append(section) + if chapter_number <= len(sections): + chapter = sections[chapter_number - 1] + + entries = [{ '_type': 'url_transparent', 'url': wistia_url, 'ie_key': WistiaIE.ie_key(), 'title': title, - } + 'chapter': chapter, + 'chapter_number': chapter_number, + } for wistia_url in wistia_urls] + + return self.playlist_result(entries, video_id, title) class TeachableCourseIE(TeachableBaseIE): @@ -191,20 +219,20 @@ class TeachableCourseIE(TeachableBaseIE): /(?:courses|p)/(?:enrolled/)?(?P<id>[^/?#&]+) ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ - 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/', + 'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/', 'info_dict': { 'id': 'essential-web-developer-course', 'title': 'The Essential Web Developer Course (Free)', }, 'playlist_count': 192, }, { - 'url': 'http://upskillcourses.com/courses/119763/', + 'url': 'http://v1.upskillcourses.com/courses/119763/', 'only_matching': True, }, { - 'url': 'http://upskillcourses.com/courses/enrolled/119763', + 'url': 'http://v1.upskillcourses.com/courses/enrolled/119763', 'only_matching': True, }, { - 'url': 'https://academy.gns3.com/courses/enrolled/423415', + 'url': 'https://gns3.teachable.com/courses/enrolled/423415', 'only_matching': True, }, { 'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini', diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py index 33a72083b..364556a1f 100644 --- a/youtube_dl/extractor/tele5.py +++ b/youtube_dl/extractor/tele5.py @@ -1,9 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor +from .jwplatform import JWPlatformIE from .nexx import NexxIE -from ..compat import compat_urlparse +from ..compat import ( + compat_str, + compat_urlparse, +) +from ..utils import ( + NO_DEFAULT, + try_get, +) class Tele5IE(InfoExtractor): @@ -44,14 +54,49 @@ class Tele5IE(InfoExtractor): qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0] - if not video_id: + NEXX_ID_RE = r'\d{6,}' + JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}' + + def nexx_result(nexx_id): + return self.url_result( + 'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id, + ie=NexxIE.ie_key(), video_id=nexx_id) + + nexx_id = jwplatform_id = None + + if video_id: + if re.match(NEXX_ID_RE, video_id): + return nexx_result(video_id) + elif re.match(JWPLATFORM_ID_RE, video_id): + jwplatform_id = video_id + + if not nexx_id: display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - video_id = self._html_search_regex( - (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)', - r'\s+id\s*=\s*["\']player_(\d{6,})', - r'\bdata-id\s*=\s*["\'](\d{6,})'), webpage, 'video id') + + def extract_id(pattern, name, default=NO_DEFAULT): + return self._html_search_regex( + (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern, + r'\s+id\s*=\s*["\']player_(%s)' % pattern, + r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name, + default=default) + + nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None) + if nexx_id: + return nexx_result(nexx_id) + + if not jwplatform_id: + jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id') + + media = self._download_json( + 'https://cdn.jwplayer.com/v2/media/' + jwplatform_id, + display_id) + nexx_id = try_get( + media, lambda x: x['playlist'][0]['nexx_id'], compat_str) + + if nexx_id: + return nexx_result(nexx_id) return self.url_result( - 'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id, - ie=NexxIE.ie_key(), video_id=video_id) + 'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(), + video_id=jwplatform_id) diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index d37e1b055..9ba3da341 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -11,6 +11,7 @@ from ..utils import ( determine_ext, int_or_none, str_or_none, + try_get, urljoin, ) @@ -24,7 +25,7 @@ class TelecincoIE(InfoExtractor): 'info_dict': { 'id': '1876350223', 'title': 'Bacalao con kokotxas al pil-pil', - 'description': 'md5:1382dacd32dd4592d478cbdca458e5bb', + 'description': 'md5:716caf5601e25c3c5ab6605b1ae71529', }, 'playlist': [{ 'md5': 'adb28c37238b675dad0f042292f209a7', @@ -55,6 +56,26 @@ class TelecincoIE(InfoExtractor): 'description': 'md5:2771356ff7bfad9179c5f5cd954f1477', 'duration': 50, }, + }, { + # video in opening's content + 'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html', + 'info_dict': { + 'id': '2907195140', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'description': 'md5:73f340a7320143d37ab895375b2bf13a', + }, + 'playlist': [{ + 'md5': 'adb28c37238b675dad0f042292f209a7', + 'info_dict': { + 'id': 'TpI2EttSDAReWpJ1o0NVh2', + 'ext': 'mp4', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'duration': 1015, + }, + }], + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', 'only_matching': True, @@ -135,17 +156,28 @@ class TelecincoIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) article = self._parse_json(self._search_regex( - r'window\.\$REACTBASE_STATE\.article\s*=\s*({.+})', + r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})', webpage, 'article'), display_id)['article'] title = article.get('title') - description = clean_html(article.get('leadParagraph')) + description = clean_html(article.get('leadParagraph')) or '' if article.get('editorialType') != 'VID': entries = [] - for p in article.get('body', []): - content = p.get('content') - if p.get('type') != 'video' or not content: + body = [article.get('opening')] + body.extend(try_get(article, lambda x: x['body'], list) or []) + for p in body: + if not isinstance(p, dict): continue - entries.append(self._parse_content(content, url)) + content = p.get('content') + if not content: + continue + type_ = p.get('type') + if type_ == 'paragraph': + content_str = str_or_none(content) + if content_str: + description += content_str + continue + if type_ == 'video' and isinstance(content, dict): + entries.append(self._parse_content(content, url)) return self.playlist_result( entries, str_or_none(article.get('id')), title, description) content = article['opening']['content'] diff --git a/youtube_dl/extractor/telequebec.py b/youtube_dl/extractor/telequebec.py index ae9f66787..c82c94b3a 100644 --- a/youtube_dl/extractor/telequebec.py +++ b/youtube_dl/extractor/telequebec.py @@ -38,8 +38,6 @@ class TeleQuebecIE(TeleQuebecBaseIE): 'ext': 'mp4', 'title': 'Un petit choc et puis repart!', 'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374', - 'upload_date': '20180222', - 'timestamp': 1519326631, }, 'params': { 'skip_download': True, diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py index dff44a4e2..af325fea8 100644 --- a/youtube_dl/extractor/tenplay.py +++ b/youtube_dl/extractor/tenplay.py @@ -10,8 +10,8 @@ from ..utils import ( class TenPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/[^/]+/episodes/[^/]+/[^/]+/(?P<id>tpv\d{6}[a-z]{5})' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/]+/)+(?P<id>tpv\d{6}[a-z]{5})' + _TESTS = [{ 'url': 'https://10play.com.au/masterchef/episodes/season-1/masterchef-s1-ep-1/tpv190718kwzga', 'info_dict': { 'id': '6060533435001', @@ -27,7 +27,10 @@ class TenPlayIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, } - } + }, { + 'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc', + 'only_matching': True, + }] BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s' def _real_extract(self, url): diff --git a/youtube_dl/extractor/tfo.py b/youtube_dl/extractor/tfo.py index 0e2370cd8..0631cb7ab 100644 --- a/youtube_dl/extractor/tfo.py +++ b/youtube_dl/extractor/tfo.py @@ -17,14 +17,12 @@ class TFOIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)' _TEST = { 'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon', - 'md5': '47c987d0515561114cf03d1226a9d4c7', + 'md5': 'cafbe4f47a8dae0ca0159937878100d6', 'info_dict': { - 'id': '100463871', + 'id': '7da3d50e495c406b8fc0b997659cc075', 'ext': 'mp4', 'title': 'Video Game Hackathon', 'description': 'md5:558afeba217c6c8d96c60e5421795c07', - 'upload_date': '20160212', - 'timestamp': 1455310233, } } diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py index 6ab147ad7..a3d9b4017 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -2,43 +2,46 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str -from ..utils import try_get class ThisOldHouseIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P<id>[^/?#]+)' _TESTS = [{ 'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', - 'md5': '568acf9ca25a639f0c4ff905826b662f', 'info_dict': { - 'id': '2REGtUDQ', + 'id': '5dcdddf673c3f956ef5db202', 'ext': 'mp4', 'title': 'How to Build a Storage Bench', 'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.', 'timestamp': 1442548800, 'upload_date': '20150918', - } + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins', 'only_matching': True, }, { 'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric', 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench', + 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost', + 'only_matching': True, + }, { + # iframe www.thisoldhouse.com + 'url': 'https://www.thisoldhouse.com/21083431/seaside-transformation-the-westerly-project', + 'only_matching': True, }] + _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe' def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - (r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', - r'id=(["\'])inline-video-player-(?P<id>(?:(?!\1).)+)\1'), - webpage, 'video id', default=None, group='id') - if not video_id: - drupal_settings = self._parse_json(self._search_regex( - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', - webpage, 'drupal settings'), display_id) - video_id = try_get( - drupal_settings, lambda x: x['jwplatform']['video_id'], - compat_str) or list(drupal_settings['comScore'])[0] - return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id) + r'<iframe[^>]+src=[\'"](?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})', + webpage, 'video id') + return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id) diff --git a/youtube_dl/extractor/toggle.py b/youtube_dl/extractor/toggle.py index 5e5efda0f..ca2e36efe 100644 --- a/youtube_dl/extractor/toggle.py +++ b/youtube_dl/extractor/toggle.py @@ -17,9 +17,9 @@ from ..utils import ( class ToggleIE(InfoExtractor): IE_NAME = 'toggle' - _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)' + _VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)' _TESTS = [{ - 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', + 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', 'info_dict': { 'id': '343115', 'ext': 'mp4', @@ -33,7 +33,7 @@ class ToggleIE(InfoExtractor): } }, { 'note': 'DRM-protected video', - 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413', + 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413', 'info_dict': { 'id': '341413', 'ext': 'wvm', @@ -48,7 +48,7 @@ class ToggleIE(InfoExtractor): }, { # this also tests correct video id extraction 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay', - 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', + 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', 'info_dict': { 'id': '332861', 'ext': 'mp4', @@ -65,19 +65,22 @@ class ToggleIE(InfoExtractor): 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367', + 'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', + 'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/movies/seven-days/321936', + 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', 'only_matching': True, }, { - 'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'url': 'http://www.mewatch.sg/en/movies/seven-days/321936', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585', + 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'only_matching': True, + }, { + 'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585', 'only_matching': True, }] diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index edbb0aa69..ae584ad69 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, @@ -151,7 +150,7 @@ class TumblrIE(InfoExtractor): url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) webpage, urlh = self._download_webpage_handle(url, video_id) - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() if 'tumblr.com/safe-mode' in redirect_url or redirect_url.startswith('/safe-mode'): raise ExtractorError( 'This Tumblr may contain sensitive media. ' diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py index 611fdc0c6..8bda9348d 100644 --- a/youtube_dl/extractor/tv2dk.py +++ b/youtube_dl/extractor/tv2dk.py @@ -106,7 +106,7 @@ class TV2DKBornholmPlayIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id, + 'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id, data=json.dumps({ 'playlist_id': video_id, 'serienavn': '', diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py index a819d048c..c498b0191 100644 --- a/youtube_dl/extractor/tv4.py +++ b/youtube_dl/extractor/tv4.py @@ -99,7 +99,7 @@ class TV4IE(InfoExtractor): manifest_url.replace('.m3u8', '.f4m'), video_id, f4m_id='hds', fatal=False)) formats.extend(self._extract_ism_formats( - re.sub(r'\.ism/.+?\.m3u8', r'.ism/Manifest', manifest_url), + re.sub(r'\.ism/.*?\.m3u8', r'.ism/Manifest', manifest_url), video_id, ism_id='mss', fatal=False)) if not formats and info.get('is_geo_restricted'): diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index d82d48f94..3c2450dd0 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -6,7 +6,6 @@ import re from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_str, compat_urlparse, ) from ..utils import ( @@ -15,9 +14,7 @@ from ..utils import ( int_or_none, parse_iso8601, qualities, - smuggle_url, try_get, - unsmuggle_url, update_url_query, url_or_none, ) @@ -235,11 +232,6 @@ class TVPlayIE(InfoExtractor): ] def _real_extract(self, url): - url, smuggled_data = unsmuggle_url(url, {}) - self._initialize_geo_bypass({ - 'countries': smuggled_data.get('geo_countries'), - }) - video_id = self._match_id(url) geo_country = self._search_regex( r'https?://[^/]+\.([a-z]{2})', url, @@ -285,8 +277,6 @@ class TVPlayIE(InfoExtractor): 'ext': ext, } if video_url.startswith('rtmp'): - if smuggled_data.get('skip_rtmp'): - continue m = re.search( r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url) if not m: @@ -347,115 +337,80 @@ class ViafreeIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?:www\.)? - viafree\. - (?: - (?:dk|no)/programmer| - se/program - ) - /(?:[^/]+/)+(?P<id>[^/?#&]+) + viafree\.(?P<country>dk|no|se) + /(?P<id>program(?:mer)?/(?:[^/]+/)+[^/?#&]+) ''' _TESTS = [{ - 'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2', + 'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1', 'info_dict': { - 'id': '395375', + 'id': '757786', 'ext': 'mp4', - 'title': 'Husräddarna S02E02', - 'description': 'md5:4db5c933e37db629b5a2f75dfb34829e', - 'series': 'Husräddarna', - 'season': 'Säsong 2', + 'title': 'Det beste vorspielet - Sesong 2 - Episode 1', + 'description': 'md5:b632cb848331404ccacd8cd03e83b4c3', + 'series': 'Det beste vorspielet', 'season_number': 2, - 'duration': 2576, - 'timestamp': 1400596321, - 'upload_date': '20140520', + 'duration': 1116, + 'timestamp': 1471200600, + 'upload_date': '20160814', }, 'params': { 'skip_download': True, }, - 'add_ie': [TVPlayIE.ie_key()], }, { # with relatedClips 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1', - 'info_dict': { - 'id': '758770', - 'ext': 'mp4', - 'title': 'Sommaren med YouTube-stjärnorna S01E01', - 'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f', - 'series': 'Sommaren med YouTube-stjärnorna', - 'season': 'Säsong 1', - 'season_number': 1, - 'duration': 1326, - 'timestamp': 1470905572, - 'upload_date': '20160811', - }, - 'params': { - 'skip_download': True, - }, - 'add_ie': [TVPlayIE.ie_key()], + 'only_matching': True, }, { # Different og:image URL schema 'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-2', 'only_matching': True, }, { - 'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1', + 'url': 'http://www.viafree.se/program/livsstil/husraddarna/sasong-2/avsnitt-2', 'only_matching': True, }, { 'url': 'http://www.viafree.dk/programmer/reality/paradise-hotel/saeson-7/episode-5', 'only_matching': True, }] + _GEO_BYPASS = False @classmethod def suitable(cls, url): return False if TVPlayIE.suitable(url) else super(ViafreeIE, cls).suitable(url) def _real_extract(self, url): - video_id = self._match_id(url) + country, path = re.match(self._VALID_URL, url).groups() + content = self._download_json( + 'https://viafree-content.mtg-api.com/viafree-content/v1/%s/path/%s' % (country, path), path) + program = content['_embedded']['viafreeBlocks'][0]['_embedded']['program'] + guid = program['guid'] + meta = content['meta'] + title = meta['title'] - webpage = self._download_webpage(url, video_id) + try: + stream_href = self._download_json( + program['_links']['streamLink']['href'], guid, + headers=self.geo_verification_headers())['embedded']['prioritizedStreams'][0]['links']['stream']['href'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + self.raise_geo_restricted(countries=[country]) + raise - data = self._parse_json( - self._search_regex( - r'(?s)window\.App\s*=\s*({.+?})\s*;\s*</script', - webpage, 'data', default='{}'), - video_id, transform_source=lambda x: re.sub( - r'(?s)function\s+[a-zA-Z_][\da-zA-Z_]*\s*\([^)]*\)\s*{[^}]*}\s*', - 'null', x), fatal=False) + formats = self._extract_m3u8_formats(stream_href, guid, 'mp4') + self._sort_formats(formats) + episode = program.get('episode') or {} - video_id = None - - if data: - video_id = try_get( - data, lambda x: x['context']['dispatcher']['stores'][ - 'ContentPageProgramStore']['currentVideo']['id'], - compat_str) - - # Fallback #1 (extract from og:image URL schema) - if not video_id: - thumbnail = self._og_search_thumbnail(webpage, default=None) - if thumbnail: - video_id = self._search_regex( - # Patterns seen: - # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/inbox/765166/a2e95e5f1d735bab9f309fa345cc3f25.jpg - # http://cdn.playapi.mtgx.tv/imagecache/600x315/cloud/content-images/seasons/15204/758770/4a5ba509ca8bc043e1ebd1a76131cdf2.jpg - r'https?://[^/]+/imagecache/(?:[^/]+/)+(\d{6,})/', - thumbnail, 'video id', default=None) - - # Fallback #2. Extract from raw JSON string. - # May extract wrong video id if relatedClips is present. - if not video_id: - video_id = self._search_regex( - r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})', - webpage, 'video id') - - return self.url_result( - smuggle_url( - 'mtg:%s' % video_id, - { - 'geo_countries': [ - compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]], - # rtmp host mtgfs.fplive.net for viafree is unresolvable - 'skip_rtmp': True, - }), - ie=TVPlayIE.ie_key(), video_id=video_id) + return { + 'id': guid, + 'title': title, + 'thumbnail': meta.get('image'), + 'description': meta.get('description'), + 'series': episode.get('seriesTitle'), + 'episode_number': int_or_none(episode.get('episodeNumber')), + 'season_number': int_or_none(episode.get('seasonNumber')), + 'duration': int_or_none(try_get(program, lambda x: x['video']['duration']['milliseconds']), 1000), + 'timestamp': parse_iso8601(try_get(program, lambda x: x['availability']['start'])), + 'formats': formats, + } class TVPlayHomeIE(InfoExtractor): diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index 2830c212e..74d14049b 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -17,7 +17,7 @@ class TwentyFourVideoIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?P<host> - (?:(?:www|porno)\.)?24video\. + (?:(?:www|porno?)\.)?24video\. (?:net|me|xxx|sexy?|tube|adult|site|vip) )/ (?: @@ -62,6 +62,9 @@ class TwentyFourVideoIE(InfoExtractor): }, { 'url': 'https://www.24video.vip/video/view/1044982', 'only_matching': True, + }, { + 'url': 'https://porn.24video.net/video/2640421-vsya-takay', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 0db2dca41..78ee0115c 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -643,7 +643,14 @@ class TwitchStreamIE(TwitchBaseIE): class TwitchClipsIE(TwitchBaseIE): IE_NAME = 'twitch:clips' - _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:embed\?.*?\bclip=|(?:[^/]+/)*)|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)' + _VALID_URL = r'''(?x) + https?:// + (?: + clips\.twitch\.tv/(?:embed\?.*?\bclip=|(?:[^/]+/)*)| + (?:(?:www|go|m)\.)?twitch\.tv/[^/]+/clip/ + ) + (?P<id>[^/?#&]+) + ''' _TESTS = [{ 'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat', @@ -669,6 +676,12 @@ class TwitchClipsIE(TwitchBaseIE): }, { 'url': 'https://clips.twitch.tv/embed?clip=InquisitiveBreakableYogurtJebaited', 'only_matching': True, + }, { + 'url': 'https://m.twitch.tv/rossbroadcast/clip/ConfidentBraveHumanChefFrank', + 'only_matching': True, + }, { + 'url': 'https://go.twitch.tv/rossbroadcast/clip/ConfidentBraveHumanChefFrank', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/uol.py b/youtube_dl/extractor/uol.py index 08f0c072e..628adf219 100644 --- a/youtube_dl/extractor/uol.py +++ b/youtube_dl/extractor/uol.py @@ -2,12 +2,17 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse_urlencode, +) from ..utils import ( clean_html, int_or_none, parse_duration, + parse_iso8601, + qualities, update_url_query, - str_or_none, ) @@ -16,21 +21,25 @@ class UOLIE(InfoExtractor): _VALID_URL = r'https?://(?:.+?\.)?uol\.com\.br/.*?(?:(?:mediaId|v)=|view/(?:[a-z0-9]+/)?|video(?:=|/(?:\d{4}/\d{2}/\d{2}/)?))(?P<id>\d+|[\w-]+-[A-Z0-9]+)' _TESTS = [{ 'url': 'http://player.mais.uol.com.br/player_video_v3.swf?mediaId=15951931', - 'md5': '25291da27dc45e0afb5718a8603d3816', + 'md5': '4f1e26683979715ff64e4e29099cf020', 'info_dict': { 'id': '15951931', 'ext': 'mp4', 'title': 'Miss simpatia é encontrada morta', 'description': 'md5:3f8c11a0c0556d66daf7e5b45ef823b2', + 'timestamp': 1470421860, + 'upload_date': '20160805', } }, { 'url': 'http://tvuol.uol.com.br/video/incendio-destroi-uma-das-maiores-casas-noturnas-de-londres-04024E9A3268D4C95326', - 'md5': 'e41a2fb7b7398a3a46b6af37b15c00c9', + 'md5': '2850a0e8dfa0a7307e04a96c5bdc5bc2', 'info_dict': { 'id': '15954259', 'ext': 'mp4', 'title': 'Incêndio destrói uma das maiores casas noturnas de Londres', 'description': 'Em Londres, um incêndio destruiu uma das maiores boates da cidade. Não há informações sobre vítimas.', + 'timestamp': 1470674520, + 'upload_date': '20160808', } }, { 'url': 'http://mais.uol.com.br/static/uolplayer/index.html?mediaId=15951931', @@ -55,91 +64,55 @@ class UOLIE(InfoExtractor): 'only_matching': True, }] - _FORMATS = { - '2': { - 'width': 640, - 'height': 360, - }, - '5': { - 'width': 1280, - 'height': 720, - }, - '6': { - 'width': 426, - 'height': 240, - }, - '7': { - 'width': 1920, - 'height': 1080, - }, - '8': { - 'width': 192, - 'height': 144, - }, - '9': { - 'width': 568, - 'height': 320, - }, - '11': { - 'width': 640, - 'height': 360, - } - } - def _real_extract(self, url): video_id = self._match_id(url) - media_id = None - - if video_id.isdigit(): - media_id = video_id - - if not media_id: - embed_page = self._download_webpage( - 'https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id, - video_id, 'Downloading embed page', fatal=False) - if embed_page: - media_id = self._search_regex( - (r'uol\.com\.br/(\d+)', r'mediaId=(\d+)'), - embed_page, 'media id', default=None) - - if not media_id: - webpage = self._download_webpage(url, video_id) - media_id = self._search_regex(r'mediaId=(\d+)', webpage, 'media id') video_data = self._download_json( - 'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % media_id, - media_id)['item'] + # https://api.mais.uol.com.br/apiuol/v4/player/data/[MEDIA_ID] + 'https://api.mais.uol.com.br/apiuol/v3/media/detail/' + video_id, + video_id)['item'] + media_id = compat_str(video_data['mediaId']) title = video_data['title'] + ver = video_data.get('revision', 2) - query = { - 'ver': video_data.get('numRevision', 2), - 'r': 'http://mais.uol.com.br', - } - for k in ('token', 'sign'): - v = video_data.get(k) - if v: - query[k] = v - + uol_formats = self._download_json( + 'https://croupier.mais.uol.com.br/v3/formats/%s/jsonp' % media_id, + media_id) + quality = qualities(['mobile', 'WEBM', '360p', '720p', '1080p']) formats = [] - for f in video_data.get('formats', []): + for format_id, f in uol_formats.items(): + if not isinstance(f, dict): + continue f_url = f.get('url') or f.get('secureUrl') if not f_url: continue + query = { + 'ver': ver, + 'r': 'http://mais.uol.com.br', + } + for k in ('token', 'sign'): + v = f.get(k) + if v: + query[k] = v f_url = update_url_query(f_url, query) - format_id = str_or_none(f.get('id')) - if format_id == '10': - formats.extend(self._extract_m3u8_formats( - f_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) + format_id = format_id + if format_id == 'HLS': + m3u8_formats = self._extract_m3u8_formats( + f_url, media_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + encoded_query = compat_urllib_parse_urlencode(query) + for m3u8_f in m3u8_formats: + m3u8_f['extra_param_to_segment_url'] = encoded_query + m3u8_f['url'] = update_url_query(m3u8_f['url'], query) + formats.extend(m3u8_formats) continue - fmt = { + formats.append({ 'format_id': format_id, 'url': f_url, - 'source_preference': 1, - } - fmt.update(self._FORMATS.get(format_id, {})) - formats.append(fmt) - self._sort_formats(formats, ('height', 'width', 'source_preference', 'tbr', 'ext')) + 'quality': quality(format_id), + 'preference': -1, + }) + self._sort_formats(formats) tags = [] for tag in video_data.get('tags', []): @@ -148,12 +121,24 @@ class UOLIE(InfoExtractor): continue tags.append(tag_description) + thumbnails = [] + for q in ('Small', 'Medium', 'Wmedium', 'Large', 'Wlarge', 'Xlarge'): + q_url = video_data.get('thumb' + q) + if not q_url: + continue + thumbnails.append({ + 'id': q, + 'url': q_url, + }) + return { 'id': media_id, 'title': title, - 'description': clean_html(video_data.get('desMedia')), - 'thumbnail': video_data.get('thumbnail'), - 'duration': int_or_none(video_data.get('durationSeconds')) or parse_duration(video_data.get('duration')), + 'description': clean_html(video_data.get('description')), + 'thumbnails': thumbnails, + 'duration': parse_duration(video_data.get('duration')), 'tags': tags, 'formats': formats, + 'timestamp': parse_iso8601(video_data.get('publishDate'), ' '), + 'view_count': int_or_none(video_data.get('viewsQtty')), } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index f378aa283..8cd611e1e 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -33,6 +33,7 @@ from ..utils import ( unified_timestamp, unsmuggle_url, urlencode_postdata, + urljoin, unescapeHTML, ) @@ -191,7 +192,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): for tt in text_tracks: subtitles[tt['lang']] = [{ 'ext': 'vtt', - 'url': 'https://vimeo.com' + tt['url'], + 'url': urljoin('https://vimeo.com', tt['url']), }] thumbnails = [] @@ -591,7 +592,7 @@ class VimeoIE(VimeoBaseInfoExtractor): # Retrieve video webpage to extract further information webpage, urlh = self._download_webpage_handle( url, video_id, headers=headers) - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: errmsg = ee.cause.read() diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 085514d47..168e5e901 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -45,22 +45,23 @@ class WistiaIE(InfoExtractor): # https://wistia.com/support/embed-and-share/video-on-your-website @staticmethod def _extract_url(webpage): - match = re.search( - r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage) - if match: - return unescapeHTML(match.group('url')) + urls = WistiaIE._extract_urls(webpage) + return urls[0] if urls else None - match = re.search( - r'''(?sx) - <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? - <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2 - ''', webpage) - if match: - return 'wistia:%s' % match.group('id') - - match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage) - if match: - return 'wistia:%s' % match.group('id') + @staticmethod + def _extract_urls(webpage): + urls = [] + for match in re.finditer( + r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage): + urls.append(unescapeHTML(match.group('url'))) + for match in re.finditer( + r'''(?sx) + <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2 + ''', webpage): + urls.append('wistia:%s' % match.group('id')) + for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage): + urls.append('wistia:%s' % match.group('id')) + return urls def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index a5b94d279..0f7be6a7d 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -113,7 +113,7 @@ class XHamsterIE(InfoExtractor): display_id = mobj.group('display_id') or mobj.group('display_id_2') desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) - webpage = self._download_webpage(desktop_url, video_id) + webpage, urlh = self._download_webpage_handle(desktop_url, video_id) error = self._html_search_regex( r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>', @@ -161,6 +161,9 @@ class XHamsterIE(InfoExtractor): 'ext': determine_ext(format_url, 'mp4'), 'height': get_height(quality), 'filesize': filesize, + 'http_headers': { + 'Referer': urlh.geturl(), + }, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index c6c0b3291..01b253dcb 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -47,7 +47,7 @@ class XTubeIE(InfoExtractor): 'display_id': 'A-Super-Run-Part-1-YT', 'ext': 'flv', 'title': 'A Super Run - Part 1 (YT)', - 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93', + 'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616', 'uploader': 'tshirtguy59', 'duration': 579, 'view_count': int, @@ -87,10 +87,24 @@ class XTubeIE(InfoExtractor): 'Cookie': 'age_verified=1; cookiesAccepted=1', }) - sources = self._parse_json(self._search_regex( - r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),', - webpage, 'sources', group='sources'), video_id, - transform_source=js_to_json) + title, thumbnail, duration = [None] * 3 + + config = self._parse_json(self._search_regex( + r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config', + default='{}'), video_id, transform_source=js_to_json, fatal=False) + if config: + config = config.get('mainRoll') + if isinstance(config, dict): + title = config.get('title') + thumbnail = config.get('poster') + duration = int_or_none(config.get('duration')) + sources = config.get('sources') or config.get('format') + + if not isinstance(sources, dict): + sources = self._parse_json(self._search_regex( + r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),', + webpage, 'sources', group='sources'), video_id, + transform_source=js_to_json) formats = [] for format_id, format_url in sources.items(): @@ -102,20 +116,25 @@ class XTubeIE(InfoExtractor): self._remove_duplicate_formats(formats) self._sort_formats(formats) - title = self._search_regex( - (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), - webpage, 'title', group='title') - description = self._search_regex( + if not title: + title = self._search_regex( + (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + webpage, 'title', group='title') + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage, default=None) or self._search_regex( r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) uploader = self._search_regex( (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"', r'<span[^>]+class="nickname"[^>]*>([^<]+)'), webpage, 'uploader', fatal=False) - duration = parse_duration(self._search_regex( - r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', - webpage, 'duration', fatal=False)) + if not duration: + duration = parse_duration(self._search_regex( + r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', + webpage, 'duration', fatal=False)) view_count = str_to_int(self._search_regex( - r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>', + (r'["\']viewsCount["\'][^>]*>(\d+)\s+views', + r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'), webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( r'>Comments? \(([\d,\.]+)\)<', @@ -126,6 +145,7 @@ class XTubeIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'thumbnail': thumbnail, 'uploader': uploader, 'duration': duration, 'view_count': view_count, @@ -144,7 +164,7 @@ class XTubeUserIE(InfoExtractor): 'id': 'greenshowers-4056496', 'age_limit': 18, }, - 'playlist_mincount': 155, + 'playlist_mincount': 154, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 238d9cea0..e4615376c 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -12,6 +12,7 @@ from ..compat import ( ) from ..utils import ( clean_html, + ExtractorError, int_or_none, mimetype2ext, parse_iso8601, @@ -368,31 +369,47 @@ class YahooGyaOPlayerIE(InfoExtractor): 'url': 'https://gyao.yahoo.co.jp/episode/%E3%81%8D%E3%81%AE%E3%81%86%E4%BD%95%E9%A3%9F%E3%81%B9%E3%81%9F%EF%BC%9F%20%E7%AC%AC2%E8%A9%B1%202019%2F4%2F12%E6%94%BE%E9%80%81%E5%88%86/5cb02352-b725-409e-9f8d-88f947a9f682', 'only_matching': True, }] + _GEO_BYPASS = False def _real_extract(self, url): video_id = self._match_id(url).replace('/', ':') - video = self._download_json( - 'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id, - video_id, query={ - 'fields': 'longDescription,title,videoId', - }, headers={ - 'X-User-Agent': 'Unknown Pc GYAO!/2.0.0 Web', - }) + headers = self.geo_verification_headers() + headers['Accept'] = 'application/json' + resp = self._download_json( + 'https://gyao.yahoo.co.jp/apis/playback/graphql', video_id, query={ + 'appId': 'dj00aiZpPUNJeDh2cU1RazU3UCZzPWNvbnN1bWVyc2VjcmV0Jng9NTk-', + 'query': '''{ + content(parameter: {contentId: "%s", logicaAgent: PC_WEB}) { + video { + delivery { + id + } + title + } + } +}''' % video_id, + }, headers=headers) + content = resp['data']['content'] + if not content: + msg = resp['errors'][0]['message'] + if msg == 'not in japan': + self.raise_geo_restricted(countries=['JP']) + raise ExtractorError(msg) + video = content['video'] return { '_type': 'url_transparent', 'id': video_id, 'title': video['title'], 'url': smuggle_url( - 'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video['videoId'], + 'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video['delivery']['id'], {'geo_countries': ['JP']}), - 'description': video.get('longDescription'), 'ie_key': BrightcoveNewIE.ie_key(), } class YahooGyaOIE(InfoExtractor): IE_NAME = 'yahoo:gyao' - _VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/(?:p|title/[^/]+)|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' + _VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/(?:p|title(?:/[^/]+)?)|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' _TESTS = [{ 'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/', 'info_dict': { @@ -405,6 +422,9 @@ class YahooGyaOIE(InfoExtractor): }, { 'url': 'https://gyao.yahoo.co.jp/title/%E3%81%97%E3%82%83%E3%81%B9%E3%81%8F%E3%82%8A007/5b025a49-b2e5-4dc7-945c-09c6634afacf', 'only_matching': True, + }, { + 'url': 'https://gyao.yahoo.co.jp/title/5b025a49-b2e5-4dc7-945c-09c6634afacf', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index dff69fcb7..88aabd272 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -44,7 +44,7 @@ class YouJizzIE(InfoExtractor): encodings = self._parse_json( self._search_regex( - r'encodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', + r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', default='[]'), video_id, fatal=False) for encoding in encodings: diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index d4eccb4b2..e7fca22de 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..utils import ( int_or_none, - sanitized_Request, str_to_int, unescapeHTML, unified_strdate, @@ -15,7 +14,7 @@ from ..aes import aes_decrypt_text class YouPornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?' _TESTS = [{ 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', 'md5': '3744d24c50438cf5b6f6d59feb5055c2', @@ -57,16 +56,28 @@ class YouPornIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/', + 'only_matching': True, + }, { + 'url': 'http://www.youporn.com/watch/505835', + 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)', + webpage) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') or video_id - request = sanitized_Request(url) - request.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(request, display_id) + webpage = self._download_webpage( + 'http://www.youporn.com/watch/%s' % video_id, display_id, + headers={'Cookie': 'age_verified=1'}) title = self._html_search_regex( r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>', diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index eacaa5ecd..2cf79e74d 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -29,7 +29,6 @@ from ..compat import ( from ..utils import ( bool_or_none, clean_html, - dict_get, error_to_compat_str, extract_attributes, ExtractorError, @@ -389,6 +388,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?invidious\.drycat\.fr/| (?:www\.)?tube\.poal\.co/| (?:www\.)?vid\.wxzm\.sx/| + (?:www\.)?yewtu\.be/| (?:www\.)?yt\.elukerio\.org/| (?:www\.)?yt\.lelux\.fi/| (?:www\.)?kgg2m7yk5aybusll\.onion/| @@ -427,6 +427,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?(1).+)? # if we found the ID, everything can follow $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' + _PLAYER_INFO_RE = ( + r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.(?P<ext>[a-z]+)$', + r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.(?P<ext>[a-z]+)$', + ) _formats = { '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, @@ -570,7 +574,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20120506', 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', 'alt_title': 'I Love It (feat. Charli XCX)', - 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8', + 'description': 'md5:19a2f98d9032b9311e686ed039564f63', 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', 'iconic ep', 'iconic', 'love', 'it'], @@ -685,12 +689,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', - 'description': 'md5:bec2185232c05479482cb5a9b82719bf', + 'description': 'md5:307195cd21ff7fa352270fe884570ef0', 'duration': 242, 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', - 'creator': 'Taylor Swift', }, 'params': { 'youtube_include_dash_manifest': True, @@ -755,11 +758,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20100430', 'uploader_id': 'deadmau5', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', - 'creator': 'deadmau5', + 'creator': 'Dada Life, deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', 'title': 'Deadmau5 - Some Chords (HD)', - 'alt_title': 'Some Chords', + 'alt_title': 'This Machine Kills Some Chords', }, 'expected_warnings': [ 'DASH manifest missing', @@ -1135,6 +1138,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'skip_download': True, 'youtube_include_dash_manifest': False, }, + 'skip': 'not actual anymore', }, { # Youtube Music Auto-generated description @@ -1145,8 +1149,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'Voyeur Girl', 'description': 'md5:7ae382a65843d6df2685993e90a8628f', 'upload_date': '20190312', - 'uploader': 'Various Artists - Topic', - 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw', + 'uploader': 'Stephen - Topic', + 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', 'artist': 'Stephen', 'track': 'Voyeur Girl', 'album': 'it\'s too much love to know my dear', @@ -1210,7 +1214,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': '-hcAI0g-f5M', 'ext': 'mp4', 'title': 'Put It On Me', - 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e', + 'description': 'md5:f6422397c07c4c907c6638e1fee380a5', 'upload_date': '20180426', 'uploader': 'Matt Maeson - Topic', 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ', @@ -1228,6 +1232,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', 'only_matching': True, }, + { + # invalid -> valid video id redirection + 'url': 'DJztXj2GPfl', + 'info_dict': { + 'id': 'DJztXj2GPfk', + 'ext': 'mp4', + 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', + 'description': 'md5:bf577a41da97918e94fa9798d9228825', + 'upload_date': '20090125', + 'uploader': 'Prochorowka', + 'uploader_id': 'Prochorowka', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', + 'artist': 'Panjabi MC', + 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', + 'album': 'Beware of the Boys (Mundian To Bach Ke)', + }, + 'params': { + 'skip_download': True, + }, + } ] def __init__(self, *args, **kwargs): @@ -1254,14 +1278,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor): """ Return a string representation of a signature """ return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) - 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]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', - player_url) - if not id_m: + @classmethod + def _extract_player_info(cls, player_url): + for player_re in cls._PLAYER_INFO_RE: + id_m = re.search(player_re, player_url) + if id_m: + break + else: raise ExtractorError('Cannot identify player %r' % player_url) - player_type = id_m.group('ext') - player_id = id_m.group('id') + return id_m.group('ext'), id_m.group('id') + + def _extract_signature_function(self, video_id, player_url, example_sig): + player_type, player_id = self._extract_player_info(player_url) # Read from filesystem cache func_id = '%s_%s_%s' % ( @@ -1679,7 +1707,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # Get video webpage url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id - video_webpage = self._download_webpage(url, video_id) + video_webpage, urlh = self._download_webpage_handle(url, video_id) + + qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query) + video_id = qs.get('v', [None])[0] or video_id # Attempt to extract SWF player URL mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) @@ -1708,9 +1739,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def extract_view_count(v_info): return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) - def extract_token(v_info): - return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token')) - def extract_player_response(player_response, video_id): pl_response = str_or_none(player_response) if not pl_response: @@ -1723,6 +1751,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): player_response = {} # Get video info + video_info = {} embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: age_gate = True @@ -1737,19 +1766,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor): r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data - video_info_webpage = self._download_webpage( - video_info_url, video_id, - note='Refetching age-gated info webpage', - errnote='unable to download video info webpage') - video_info = compat_parse_qs(video_info_webpage) - pl_response = video_info.get('player_response', [None])[0] - player_response = extract_player_response(pl_response, video_id) - add_dash_mpd(video_info) - view_count = extract_view_count(video_info) + try: + video_info_webpage = self._download_webpage( + video_info_url, video_id, + note='Refetching age-gated info webpage', + errnote='unable to download video info webpage') + except ExtractorError: + video_info_webpage = None + if video_info_webpage: + video_info = compat_parse_qs(video_info_webpage) + pl_response = video_info.get('player_response', [None])[0] + player_response = extract_player_response(pl_response, video_id) + add_dash_mpd(video_info) + view_count = extract_view_count(video_info) else: age_gate = False - video_info = None - sts = None # Try looking directly into the video webpage ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) if ytplayer_config: @@ -1766,61 +1797,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) if args.get('livestream') == '1' or args.get('live_playback') == 1: is_live = True - sts = ytplayer_config.get('sts') if not player_response: player_response = extract_player_response(args.get('player_response'), video_id) 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 - # manifest pointed by get_video_info's dashmpd). - # The general idea is to take a union of itags of both DASH manifests (for example - # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093) - self.report_video_info_webpage_download(video_id) - for el in ('embedded', 'detailpage', 'vevo', ''): - query = { - 'video_id': video_id, - 'ps': 'default', - 'eurl': '', - 'gl': 'US', - 'hl': 'en', - } - if el: - query['el'] = el - if sts: - query['sts'] = sts - video_info_webpage = self._download_webpage( - '%s://www.youtube.com/get_video_info' % proto, - video_id, note=False, - errnote='unable to download video info webpage', - fatal=False, query=query) - if not video_info_webpage: - continue - get_video_info = compat_parse_qs(video_info_webpage) - if not player_response: - pl_response = get_video_info.get('player_response', [None])[0] - player_response = extract_player_response(pl_response, video_id) - add_dash_mpd(get_video_info) - if view_count is None: - view_count = extract_view_count(get_video_info) - if not video_info: - video_info = get_video_info - get_token = extract_token(get_video_info) - if get_token: - # Different get_video_info requests may report different results, e.g. - # some may report video unavailability, but some may serve it without - # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362, - # the original webpage as well as el=info and el=embedded get_video_info - # requests report video unavailability due to geo restriction while - # el=detailpage succeeds and returns valid data). This is probably - # due to YouTube measures against IP ranges of hosting providers. - # Working around by preferring the first succeeded video_info containing - # the token if no such video_info yet was found. - token = extract_token(video_info) - if not token: - video_info = get_video_info - break def extract_unavailable_message(): messages = [] @@ -1833,13 +1813,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if messages: return '\n'.join(messages) - if not video_info: + if not video_info and not player_response: unavailable_message = extract_unavailable_message() if not unavailable_message: unavailable_message = 'Unable to extract video data' raise ExtractorError( 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id) + if not isinstance(video_info, dict): + video_info = {} + video_details = try_get( player_response, lambda x: x['videoDetails'], dict) or {} @@ -1889,15 +1872,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # fields may contain comma as well (see # https://github.com/ytdl-org/youtube-dl/issues/8536) feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) + + def feed_entry(name): + return try_get(feed_data, lambda x: x[name][0], compat_str) + + feed_id = feed_entry('id') + if not feed_id: + continue + feed_title = feed_entry('title') + title = video_title + if feed_title: + title += ' (%s)' % feed_title entries.append({ '_type': 'url_transparent', 'ie_key': 'Youtube', 'url': smuggle_url( '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), {'force_singlefeed': True}), - 'title': '%s (%s)' % (video_title, feed_data['title'][0]), + 'title': title, }) - feed_ids.append(feed_data['id'][0]) + feed_ids.append(feed_id) self.to_screen( 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' % (', '.join(feed_ids), video_id)) @@ -1968,12 +1962,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): } for fmt in streaming_formats: - if fmt.get('drm_families'): + if fmt.get('drmFamilies') or fmt.get('drm_families'): continue url = url_or_none(fmt.get('url')) if not url: - cipher = fmt.get('cipher') + cipher = fmt.get('cipher') or fmt.get('signatureCipher') if not cipher: continue url_data = compat_parse_qs(cipher) @@ -2024,22 +2018,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if self._downloader.params.get('verbose'): if player_url is None: - player_version = 'unknown' player_desc = 'unknown' else: - if player_url.endswith('swf'): - player_version = self._search_regex( - r'-(.+?)(?:/watch_as3)?\.swf$', player_url, - 'flash player', fatal=False) - player_desc = 'flash player %s' % player_version - else: - player_version = self._search_regex( - [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.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 - + player_type, player_version = self._extract_player_info(player_url) + player_desc = '%s player %s' % ('flash' if player_type == 'swf' else 'html5', player_version) parts_sizes = self._signature_cache_id(encrypted_sig) self.to_screen('{%s} signature length %s, %s' % (format_id, parts_sizes, player_desc)) @@ -2392,30 +2374,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor): f['stretched_ratio'] = ratio if not formats: - token = extract_token(video_info) - if not token: - if 'reason' in video_info: - if 'The uploader has not made this video available in your country.' in video_info['reason']: - regions_allowed = self._html_search_meta( - 'regionsAllowed', video_webpage, default=None) - countries = regions_allowed.split(',') if regions_allowed else None - self.raise_geo_restricted( - msg=video_info['reason'][0], countries=countries) - reason = video_info['reason'][0] - if 'Invalid parameters' in reason: - unavailable_message = extract_unavailable_message() - if unavailable_message: - reason = unavailable_message - raise ExtractorError( - 'YouTube said: %s' % reason, - expected=True, video_id=video_id) - else: - raise ExtractorError( - '"token" parameter not in video info for unknown reason', - video_id=video_id) - - if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])): - raise ExtractorError('This video is DRM protected.', expected=True) + if 'reason' in video_info: + if 'The uploader has not made this video available in your country.' in video_info['reason']: + regions_allowed = self._html_search_meta( + 'regionsAllowed', video_webpage, default=None) + countries = regions_allowed.split(',') if regions_allowed else None + self.raise_geo_restricted( + msg=video_info['reason'][0], countries=countries) + reason = video_info['reason'][0] + if 'Invalid parameters' in reason: + unavailable_message = extract_unavailable_message() + if unavailable_message: + reason = unavailable_message + raise ExtractorError( + 'YouTube said: %s' % reason, + expected=True, video_id=video_id) + if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']): + raise ExtractorError('This video is DRM protected.', expected=True) self._sort_formats(formats) @@ -2495,20 +2470,23 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' IE_NAME = 'youtube:playlist' _TESTS = [{ - 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', 'info_dict': { - 'title': 'ytdl test PL', - 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'title': 'youtube-dl public playlist', }, - 'playlist_count': 3, + 'playlist_count': 1, }, { - 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', 'info_dict': { - 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', - 'title': 'YDL_Empty_List', + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', + 'title': 'youtube-dl empty playlist', }, 'playlist_count': 0, - 'skip': 'This playlist is private', }, { 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', @@ -2518,7 +2496,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'uploader': 'Christiaan008', 'uploader_id': 'ChRiStIaAn008', }, - 'playlist_count': 95, + 'playlist_count': 96, }, { 'note': 'issue #673', 'url': 'PLBB231211A4F62143', diff --git a/youtube_dl/extractor/zapiks.py b/youtube_dl/extractor/zapiks.py index bacb82eee..f6496f516 100644 --- a/youtube_dl/extractor/zapiks.py +++ b/youtube_dl/extractor/zapiks.py @@ -29,7 +29,6 @@ class ZapiksIE(InfoExtractor): 'timestamp': 1359044972, 'upload_date': '20130124', 'view_count': int, - 'comment_count': int, }, }, { diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 145c123a4..656864b2e 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -244,14 +244,14 @@ class ZDFChannelIE(ZDFBaseIE): 'id': 'das-aktuelle-sportstudio', 'title': 'das aktuelle sportstudio | ZDF', }, - 'playlist_count': 21, + 'playlist_mincount': 23, }, { 'url': 'https://www.zdf.de/dokumentation/planet-e', 'info_dict': { 'id': 'planet-e', 'title': 'planet e.', }, - 'playlist_count': 4, + 'playlist_mincount': 50, }, { 'url': 'https://www.zdf.de/filme/taunuskrimi/', 'only_matching': True, diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 1ffabc62b..6d5ac62b3 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -134,7 +134,7 @@ def parseOpts(overrideArguments=None): action='help', help='Print this help text and exit') general.add_option( - '-v', '--version', + '--version', action='version', help='Print program version and exit') general.add_option( @@ -853,7 +853,7 @@ def parseOpts(overrideArguments=None): postproc.add_option( '--exec', metavar='CMD', dest='exec_cmd', - help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'') + help='Execute a command on the file after downloading and post-processing, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'') postproc.add_option( '--convert-subs', '--convert-subtitles', metavar='FORMAT', dest='convertsubtitles', default=None, diff --git a/youtube_dl/update.py b/youtube_dl/update.py index 002ea7f33..84c964617 100644 --- a/youtube_dl/update.py +++ b/youtube_dl/update.py @@ -9,6 +9,7 @@ import subprocess import sys from zipimport import zipimporter +from .compat import compat_realpath from .utils import encode_compat_str from .version import __version__ @@ -84,7 +85,9 @@ def update_self(to_screen, verbose, opener): print_notes(to_screen, versions_info['versions']) # sys.executable is set to the full pathname of the exe-file for py2exe - filename = sys.executable if hasattr(sys, 'frozen') else sys.argv[0] + # though symlinks are not followed so that we need to do this manually + # with help of realpath + filename = compat_realpath(sys.executable if hasattr(sys, 'frozen') else sys.argv[0]) if not os.access(filename, os.W_OK): to_screen('ERROR: no write permissions on %s' % filename) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index f6204692a..112279ed7 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -7,6 +7,7 @@ import base64 import binascii import calendar import codecs +import collections import contextlib import ctypes import datetime @@ -30,6 +31,7 @@ import ssl import subprocess import sys import tempfile +import time import traceback import xml.etree.ElementTree import zlib @@ -2729,15 +2731,72 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): + """ + See [1] for cookie file format. + + 1. https://curl.haxx.se/docs/http-cookies.html + """ _HTTPONLY_PREFIX = '#HttpOnly_' + _ENTRY_LEN = 7 + _HEADER = '''# Netscape HTTP Cookie File +# This file is generated by youtube-dl. Do not edit. + +''' + _CookieFileEntry = collections.namedtuple( + 'CookieFileEntry', + ('domain_name', 'include_subdomains', 'path', 'https_only', 'expires_at', 'name', 'value')) def save(self, filename=None, ignore_discard=False, ignore_expires=False): + """ + Save cookies to a file. + + Most of the code is taken from CPython 3.8 and slightly adapted + to support cookie files with UTF-8 in both python 2 and 3. + """ + if filename is None: + if self.filename is not None: + filename = self.filename + else: + raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT) + # Store session cookies with `expires` set to 0 instead of an empty # string for cookie in self: if cookie.expires is None: cookie.expires = 0 - compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires) + + with io.open(filename, 'w', encoding='utf-8') as f: + f.write(self._HEADER) + now = time.time() + for cookie in self: + if not ignore_discard and cookie.discard: + continue + if not ignore_expires and cookie.is_expired(now): + continue + if cookie.secure: + secure = 'TRUE' + else: + secure = 'FALSE' + if cookie.domain.startswith('.'): + initial_dot = 'TRUE' + else: + initial_dot = 'FALSE' + if cookie.expires is not None: + expires = compat_str(cookie.expires) + else: + expires = '' + if cookie.value is None: + # cookies.txt regards 'Set-Cookie: foo' as a cookie + # with no name, whereas http.cookiejar regards it as a + # cookie with no value. + name = '' + value = cookie.name + else: + name = cookie.name + value = cookie.value + f.write( + '\t'.join([cookie.domain, initial_dot, cookie.path, + secure, expires, name, value]) + '\n') def load(self, filename=None, ignore_discard=False, ignore_expires=False): """Load cookies from a file.""" @@ -2747,12 +2806,30 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): else: raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT) + def prepare_line(line): + if line.startswith(self._HTTPONLY_PREFIX): + line = line[len(self._HTTPONLY_PREFIX):] + # comments and empty lines are fine + if line.startswith('#') or not line.strip(): + return line + cookie_list = line.split('\t') + if len(cookie_list) != self._ENTRY_LEN: + raise compat_cookiejar.LoadError('invalid length %d' % len(cookie_list)) + cookie = self._CookieFileEntry(*cookie_list) + if cookie.expires_at and not cookie.expires_at.isdigit(): + raise compat_cookiejar.LoadError('invalid expires at %s' % cookie.expires_at) + return line + cf = io.StringIO() - with open(filename) as f: + with io.open(filename, encoding='utf-8') as f: for line in f: - if line.startswith(self._HTTPONLY_PREFIX): - line = line[len(self._HTTPONLY_PREFIX):] - cf.write(compat_str(line)) + try: + cf.write(prepare_line(line)) + except compat_cookiejar.LoadError as e: + write_string( + 'WARNING: skipping cookie file entry due to %s: %r\n' + % (e, line), sys.stderr) + continue cf.seek(0) self._really_load(cf, filename, ignore_discard, ignore_expires) # Session cookies are denoted by either `expires` field set to @@ -2795,6 +2872,15 @@ class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor): https_response = http_response +class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler): + if sys.version_info[0] < 3: + def redirect_request(self, req, fp, code, msg, headers, newurl): + # On python 2 urlh.geturl() may sometimes return redirect URL + # as byte string instead of unicode. This workaround allows + # to force it always return unicode. + return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl)) + + def extract_timezone(date_str): m = re.search( r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)', diff --git a/youtube_dl/version.py b/youtube_dl/version.py index fa6f7289a..b08ee126e 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.01.24' +__version__ = '2020.05.08'