diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index d82ff9111..d29d5366f 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 **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.06.16.1** - [ ] 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 2020.03.08 + [debug] youtube-dl version 2020.06.16.1 [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 04b350f76..ee882f98c 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 **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.06.16.1** - [ ] 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 6f17ad7bc..23033fe13 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 **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.06.16.1** - [ ] 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 efb179ea5..597531330 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 **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.06.16.1** - [ ] 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 2020.03.08 + [debug] youtube-dl version 2020.06.16.1 [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 cf4874bcc..5cfcb9318 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 **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.06.16.1** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index ac759ddc4..58ab3a4b8 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -153,7 +153,7 @@ 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/ChangeLog b/ChangeLog index 84b43c642..07d6ccd69 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,7 +1,145 @@ +version 2020.06.16.1 + +Extractors +* [youtube] Force old layout (#25682, #25683, #25680, #25686) +* [youtube] Fix categories and improve tags extraction + + +version 2020.06.16 + +Extractors +* [youtube] Fix uploader id and uploader URL extraction +* [youtube] Improve view count extraction +* [youtube] Fix upload date extraction (#25677) +* [youtube] Fix thumbnails extraction (#25676) +* [youtube] Fix playlist and feed extraction (#25675) ++ [facebook] Add support for single-video ID links ++ [youtube] Extract chapters from JSON (#24819) ++ [kaltura] Add support for multiple embeds on a webpage (#25523) + + +version 2020.06.06 + +Extractors +* [tele5] Bypass geo restriction ++ [jwplatform] Add support for bypass geo restriction +* [tele5] Prefer jwplatform over nexx (#25533) +* [twitch:stream] Expect 400 and 410 HTTP errors from API +* [twitch:stream] Fix extraction (#25528) +* [twitch] Fix thumbnails extraction (#25531) ++ [twitch] Pass v5 Accept HTTP header (#25531) +* [brightcove] Fix subtitles extraction (#25540) ++ [malltv] Add support for sk.mall.tv (#25445) +* [periscope] Fix untitled broadcasts (#25482) +* [jwplatform] Improve embeds extraction (#25467) + + +version 2020.05.29 + +Core +* [postprocessor/ffmpeg] Embed series metadata with --add-metadata +* [utils] Fix file permissions in write_json_file (#12471, #25122) + +Extractors +* [ard:beta] Extend URL regular expression (#25405) ++ [youtube] Add support for more invidious instances (#25417) +* [giantbomb] Extend URL regular expression (#25222) +* [ard] Improve URL regular expression (#25134, #25198) +* [redtube] Improve formats extraction and extract m3u8 formats (#25311, + #25321) +* [indavideo] Switch to HTTPS for API request (#25191) +* [redtube] Improve title extraction (#25208) +* [vimeo] Improve format extraction and sorting (#25285) +* [soundcloud] Reduce API playlist page limit (#25274) ++ [youtube] Add support for yewtu.be (#25226) +* [mailru] Fix extraction (#24530, #25239) +* [bellator] Fix mgid extraction (#25195) + + +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 ++ [utils] Add support for cookie files with spaces used instead of tabs Extractors + [pornhub] Add support for pornhubpremium.com (#24288) diff --git a/README.md b/README.md index 4f54a5240..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) @@ -1032,7 +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 02bc088ab..35c1050e5 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -98,6 +98,7 @@ - **BiliBili** - **BilibiliAudio** - **BilibiliAudioAlbum** + - **BiliBiliPlayer** - **BioBioChileTV** - **BIQLE** - **BitChute** @@ -496,6 +497,7 @@ - **MNetTV** - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net - **Mofosex** + - **MofosexEmbed** - **Mojvideo** - **Morningstar**: morningstar.com - **Motherless** @@ -618,11 +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** 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_chapters.py b/test/test_youtube_chapters.py index 324ca8525..e69c57377 100644 --- a/test/test_youtube_chapters.py +++ b/test/test_youtube_chapters.py @@ -267,7 +267,7 @@ class TestYoutubeChapters(unittest.TestCase): for description, duration, expected_chapters in self._TEST_CASES: ie = YoutubeIE() expect_value( - self, ie._extract_chapters(description, duration), + self, ie._extract_chapters_from_description(description, duration), expected_chapters, None) 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/compat.py b/youtube_dl/compat.py index d1b86bd13..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 @@ -2987,6 +2998,7 @@ __all__ = [ 'compat_basestring', 'compat_chr', 'compat_cookiejar', + 'compat_cookiejar_Cookie', 'compat_cookies', 'compat_ctypes_WINFUNCTYPE', 'compat_etree_Element', 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/ard.py b/youtube_dl/extractor/ard.py index 2f47e21c3..5b7b2dd6d 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -249,7 +249,7 @@ class ARDMediathekIE(ARDMediathekBaseIE): class ARDIE(InfoExtractor): - _VALID_URL = r'(?Phttps?://(www\.)?daserste\.de/[^?#]+/videos/(?P[^/?#]+)-(?P[0-9]+))\.html' + _VALID_URL = r'(?Phttps?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P[^/?#]+)-(?P[0-9]+))\.html' _TESTS = [{ # available till 14.02.2019 'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html', @@ -263,6 +263,9 @@ class ARDIE(InfoExtractor): 'upload_date': '20180214', 'thumbnail': r're:^https?://.*\.jpg$', }, + }, { + 'url': 'https://www.daserste.de/information/reportage-dokumentation/erlebnis-erde/videosextern/woelfe-und-herdenschutzhunde-ungleiche-brueder-102.html', + 'only_matching': True, }, { 'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html', 'only_matching': True, @@ -310,9 +313,9 @@ class ARDIE(InfoExtractor): class ARDBetaMediathekIE(ARDMediathekBaseIE): - _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/(?P[^/]+)/(?:player|live)/(?P[a-zA-Z0-9]+)(?:/(?P[^/?#]+))?' + _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P[^/]+)/(?:player|live|video)/(?P(?:[^/]+/)*)(?P[a-zA-Z0-9]+)' _TESTS = [{ - 'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita', + 'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', 'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f', 'info_dict': { 'display_id': 'die-robuste-roswita', @@ -325,6 +328,15 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE): 'upload_date': '20191222', 'ext': 'mp4', }, + }, { + 'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', + 'only_matching': True, + }, { + 'url': 'https://ardmediathek.de/ard/video/saartalk/saartalk-gesellschaftsgift-haltung-gegen-hass/sr-fernsehen/Y3JpZDovL3NyLW9ubGluZS5kZS9TVF84MTY4MA/', + 'only_matching': True, + }, { + 'url': 'https://www.ardmediathek.de/ard/video/trailer/private-eyes-s01-e01/one/Y3JpZDovL3dkci5kZS9CZWl0cmFnLTE1MTgwYzczLWNiMTEtNGNkMS1iMjUyLTg5MGYzOWQxZmQ1YQ/', + 'only_matching': True, }, { 'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/', 'only_matching': True, @@ -336,7 +348,11 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') - display_id = mobj.group('display_id') or video_id + display_id = mobj.group('display_id') + if display_id: + display_id = display_id.rstrip('/') + if not display_id: + display_id = video_id player_page = self._download_json( 'https://api.ardmediathek.de/public-gateway', 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/bellmedia.py b/youtube_dl/extractor/bellmedia.py index 485173774..9f9de96c6 100644 --- a/youtube_dl/extractor/bellmedia.py +++ b/youtube_dl/extractor/bellmedia.py @@ -25,8 +25,8 @@ class BellMediaIE(InfoExtractor): etalk| marilyn )\.ca| - much\.com - )/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P[0-9]{6,})''' + (?:much|cp24)\.com + )/.*?(?:\b(?:vid(?:eoid)?|clipId)=|-vid|~|%7E|/(?:episode)?)(?P[0-9]{6,})''' _TESTS = [{ 'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070', 'md5': '36d3ef559cfe8af8efe15922cd3ce950', @@ -62,6 +62,9 @@ class BellMediaIE(InfoExtractor): }, { 'url': 'http://www.etalk.ca/video?videoid=663455', 'only_matching': True, + }, { + 'url': 'https://www.cp24.com/video?clipId=1982548', + 'only_matching': True, }] _DOMAINS = { 'thecomedynetwork': 'comedy', 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/brightcove.py b/youtube_dl/extractor/brightcove.py index 85001b3ad..2aa9f4782 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -5,32 +5,34 @@ import base64 import re import struct -from .common import InfoExtractor from .adobepass import AdobePassIE +from .common import InfoExtractor from ..compat import ( compat_etree_fromstring, + compat_HTTPError, compat_parse_qs, compat_urllib_parse_urlparse, compat_urlparse, compat_xml_parse_error, - compat_HTTPError, ) from ..utils import ( - ExtractorError, + clean_html, extract_attributes, + ExtractorError, find_xpath_attr, fix_xml_ampersands, float_or_none, - js_to_json, int_or_none, + js_to_json, + mimetype2ext, parse_iso8601, smuggle_url, + str_or_none, unescapeHTML, unsmuggle_url, - update_url_query, - clean_html, - mimetype2ext, UnsupportedError, + update_url_query, + url_or_none, ) @@ -424,7 +426,7 @@ class BrightcoveNewIE(AdobePassIE): # [2] looks like: for video, script_tag, account_id, player_id, embed in re.findall( r'''(?isx) - (]*\bdata-video-id\s*=\s*['"]?[^>]+>) + (]*\bdata-video-id\s*=\s*['"]?[^>]+>) (?:.*? (]+ src=["\'](?:https?:)?//players\.brightcove\.net/ @@ -553,10 +555,16 @@ class BrightcoveNewIE(AdobePassIE): subtitles = {} for text_track in json_data.get('text_tracks', []): - if text_track.get('src'): - subtitles.setdefault(text_track.get('srclang'), []).append({ - 'url': text_track['src'], - }) + if text_track.get('kind') != 'captions': + continue + text_track_url = url_or_none(text_track.get('src')) + if not text_track_url: + continue + lang = (str_or_none(text_track.get('srclang')) + or str_or_none(text_track.get('label')) or 'en').lower() + subtitles.setdefault(lang, []).append({ + 'url': text_track_url, + }) is_live = False duration = float_or_none(json_data.get('duration'), 1000) 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/extractors.py b/youtube_dl/extractor/extractors.py index 5496e5667..14fa306a9 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 ( @@ -635,7 +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 ( @@ -800,6 +804,16 @@ from .orf import ( ORFFM4IE, ORFFM4StoryIE, ORFOE1IE, + ORFOE3IE, + ORFNOEIE, + ORFWIEIE, + ORFBGLIE, + ORFOOEIE, + ORFSTMIE, + ORFKTNIE, + ORFSBGIE, + ORFTIRIE, + ORFVBGIE, ORFIPTVIE, ) from .outsidetv import OutsideTVIE diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index ce64e2683..610d66745 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -466,15 +466,18 @@ class FacebookIE(InfoExtractor): return info_dict if '/posts/' in url: - entries = [ - self.url_result('facebook:%s' % vid, FacebookIE.ie_key()) - for vid in self._parse_json( - self._search_regex( - r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', - webpage, 'video ids', group='ids'), - video_id)] + video_id_json = self._search_regex( + r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', webpage, 'video ids', group='ids', + default='') + if video_id_json: + entries = [ + self.url_result('facebook:%s' % vid, FacebookIE.ie_key()) + for vid in self._parse_json(video_id_json, video_id)] + return self.playlist_result(entries, video_id) - return self.playlist_result(entries, video_id) + # Single Video? + video_id = self._search_regex(r'video_id:\s*"([0-9]+)"', webpage, 'single video id') + return self.url_result('facebook:%s' % video_id, FacebookIE.ie_key()) else: _, info_dict = self._extract_from_url( self._VIDEO_PAGE_TEMPLATE % video_id, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index d1ec56be9..355067a50 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 @@ -1705,6 +1708,15 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Kaltura'], }, + { + # multiple kaltura embeds, nsfw + 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html', + 'info_dict': { + 'id': 'kamila-avec-video-jaime-sadomie', + 'title': "Kamila avec vídeo “J'aime sadomie”", + }, + 'playlist_count': 8, + }, { # Non-standard Vimeo embed 'url': 'https://openclassrooms.com/courses/understanding-the-web', @@ -2536,6 +2548,11 @@ 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_urls = WistiaIE._extract_urls(webpage) if wistia_urls: @@ -2710,6 +2727,21 @@ 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) @@ -2821,9 +2853,12 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'Zapiks') # Look for Kaltura embeds - kaltura_url = KalturaIE._extract_url(webpage) - if kaltura_url: - return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key()) + kaltura_urls = KalturaIE._extract_urls(webpage) + if kaltura_urls: + return self.playlist_from_matches( + kaltura_urls, video_id, video_title, + getter=lambda x: smuggle_url(x, {'source_url': url}), + ie=KalturaIE.ie_key()) # Look for EaglePlatform embeds eagleplatform_url = EaglePlatformIE._extract_url(webpage) @@ -3141,10 +3176,6 @@ 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/giantbomb.py b/youtube_dl/extractor/giantbomb.py index 6a1b1e96e..c6477958d 100644 --- a/youtube_dl/extractor/giantbomb.py +++ b/youtube_dl/extractor/giantbomb.py @@ -13,10 +13,10 @@ from ..utils import ( class GiantBombIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/videos/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/(?:videos|shows)/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)' + _TESTS = [{ 'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/', - 'md5': 'c8ea694254a59246a42831155dec57ac', + 'md5': '132f5a803e7e0ab0e274d84bda1e77ae', 'info_dict': { 'id': '2300-9782', 'display_id': 'quick-look-destiny-the-dark-below', @@ -26,7 +26,10 @@ class GiantBombIE(InfoExtractor): 'duration': 2399, 'thumbnail': r're:^https?://.*\.jpg$', } - } + }, { + 'url': 'https://www.giantbomb.com/shows/ben-stranding/2970-20212', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/indavideo.py b/youtube_dl/extractor/indavideo.py index 2b5b2b5b0..4c16243ec 100644 --- a/youtube_dl/extractor/indavideo.py +++ b/youtube_dl/extractor/indavideo.py @@ -58,7 +58,7 @@ class IndavideoEmbedIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id, + 'https://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id, video_id)['data'] title = video['title'] 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'<h1>([^<]+)', webpage, 'title') + video_id = self._search_regex( (r'<iframe[^>]+\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/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 2aabd98b5..c34b5f5e6 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import unsmuggle_url class JWPlatformIE(InfoExtractor): @@ -32,10 +33,14 @@ class JWPlatformIE(InfoExtractor): @staticmethod def _extract_urls(webpage): return re.findall( - r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//content\.jwplatform\.com/players/[a-zA-Z0-9]{8})', + r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})', webpage) 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) json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id) return self._parse_jwplayer_data(json_data, video_id) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 2d38b758b..49d13460d 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -113,9 +113,14 @@ class KalturaIE(InfoExtractor): @staticmethod def _extract_url(webpage): + urls = KalturaIE._extract_urls(webpage) + return urls[0] if urls else None + + @staticmethod + def _extract_urls(webpage): # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site - mobj = ( - re.search( + finditer = ( + re.finditer( r"""(?xs) kWidget\.(?:thumb)?[Ee]mbed\( \{.*? @@ -124,7 +129,7 @@ class KalturaIE(InfoExtractor): (?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s* (?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\}) """, webpage) - or re.search( + or re.finditer( r'''(?xs) (?P<q1>["']) (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)* @@ -138,7 +143,7 @@ class KalturaIE(InfoExtractor): ) (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3) ''', webpage) - or re.search( + or re.finditer( r'''(?xs) <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["']) (?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+) @@ -148,7 +153,8 @@ class KalturaIE(InfoExtractor): (?P=q1) ''', webpage) ) - if mobj: + urls = [] + for mobj in finditer: embed_info = mobj.groupdict() for k, v in embed_info.items(): if v: @@ -160,7 +166,8 @@ class KalturaIE(InfoExtractor): webpage) if service_mobj: url = smuggle_url(url, {'service_url': service_mobj.group('id')}) - return url + urls.append(url) + return urls def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs): params = actions[0] 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/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/malltv.py b/youtube_dl/extractor/malltv.py index e13c2e11a..6f4fd927f 100644 --- a/youtube_dl/extractor/malltv.py +++ b/youtube_dl/extractor/malltv.py @@ -8,7 +8,7 @@ from ..utils import merge_dicts class MallTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', 'md5': '1c4a37f080e1f3023103a7b43458e518', @@ -26,6 +26,9 @@ class MallTVIE(InfoExtractor): }, { 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', 'only_matching': True, + }, { + 'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka', + 'only_matching': True, }] def _real_extract(self, url): 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<id>\d+)' + _TESTS = [{ + 'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+\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)<div[^>]+\bclass=["\']media-meta-title[^>]+>(.+?)</div>', + r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title') video_url = (self._html_search_regex( (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', r'fileurl\s*=\s*(["\'])(?P<url>(?:(?!\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'<strong>Views</strong>\s+([^<]+)<', + (r'>(\d+)\s+Views<', r'<strong>Views</strong>\s+([^<]+)<'), webpage, 'view count', fatal=False)) like_count = str_to_int(self._html_search_regex( - r'<strong>Favorited</strong>\s+([^<]+)<', + (r'>(\d+)\s+Favorites<', r'<strong>Favorited</strong>\s+([^<]+)<'), webpage, 'like count', fatal=False)) upload_date = self._html_search_regex( - r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date') + (r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<', + r'<strong>Uploaded</strong>\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/nova.py b/youtube_dl/extractor/nova.py index 2850af5db..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, @@ -33,42 +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): - 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(), + + 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( @@ -81,7 +116,8 @@ class NovaEmbedIE(InfoExtractor): r'poster\s*:\s*(["\'])(?P<value>(?:(?!\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, 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?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\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?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\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?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)' + _API_STATION = 'oe1' + _LOOP_STATION = 'oe1' _TEST = { 'url': 'http://oe1.orf.at/player/20170108/456544', diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py index c02e34aba..b15906390 100644 --- a/youtube_dl/extractor/periscope.py +++ b/youtube_dl/extractor/periscope.py @@ -18,7 +18,7 @@ class PeriscopeBaseIE(InfoExtractor): item_id, query=query) def _parse_broadcast_data(self, broadcast, video_id): - title = broadcast['status'] + title = broadcast.get('status') or 'Periscope Broadcast' uploader = broadcast.get('user_display_name') or broadcast.get('username') title = '%s - %s' % (uploader, title) if uploader else title is_live = broadcast.get('state').lower() == 'running' 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/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/redtube.py b/youtube_dl/extractor/redtube.py index b1bde1e81..2d2f6a98c 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + determine_ext, ExtractorError, int_or_none, merge_dicts, @@ -57,7 +58,7 @@ class RedTubeIE(InfoExtractor): if not info.get('title'): info['title'] = self._html_search_regex( - (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>', + (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle|video_title)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>', r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',), webpage, 'title', group='title', default=None) or self._og_search_title(webpage) @@ -77,7 +78,7 @@ class RedTubeIE(InfoExtractor): }) medias = self._parse_json( self._search_regex( - r'mediaDefinition\s*:\s*(\[.+?\])', webpage, + r'mediaDefinition["\']?\s*:\s*(\[.+?}\s*\])', webpage, 'media definitions', default='{}'), video_id, fatal=False) if medias and isinstance(medias, list): @@ -85,6 +86,12 @@ class RedTubeIE(InfoExtractor): format_url = url_or_none(media.get('videoUrl')) if not format_url: continue + if media.get('format') == 'hls' or determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + continue format_id = media.get('quality') formats.append({ 'url': format_url, diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index a1372d389..d37c52543 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): @@ -590,7 +559,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): class SoundcloudPagedPlaylistBaseIE(SoundcloudIE): def _extract_playlist(self, base_url, playlist_id, playlist_title): COMMON_QUERY = { - 'limit': 2000000000, + 'limit': 80000, 'linked_partitioning': '1', } 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 4316a6962..a75369dbe 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -7,7 +7,9 @@ from .wistia import WistiaIE from ..utils import ( clean_html, ExtractorError, + int_or_none, get_element_by_class, + strip_or_none, urlencode_postdata, urljoin, ) @@ -19,8 +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', @@ -109,27 +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, }] @@ -173,11 +177,34 @@ class TeachableIE(TeachableBaseIE): title = self._og_search_title(webpage, default=None) + 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) @@ -192,20 +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..3e1a7a9e6 100644 --- a/youtube_dl/extractor/tele5.py +++ b/youtube_dl/extractor/tele5.py @@ -1,13 +1,21 @@ # 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 ..utils import ( + NO_DEFAULT, + smuggle_url, +) class Tele5IE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _GEO_COUNTRIES = ['DE'] _TESTS = [{ 'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416', 'info_dict': { @@ -20,6 +28,21 @@ class Tele5IE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # jwplatform, nexx unavailable + 'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/', + 'info_dict': { + 'id': 'WJuiOlUp', + 'ext': 'mp4', + 'upload_date': '20200603', + 'timestamp': 1591214400, + 'title': 'Ghoul - Das Geheimnis des Friedhofmonsters', + 'description': 'md5:42002af1d887ff3d5b2b3ca1f8137d97', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [JWPlatformIE.ie_key()], }, { 'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191', 'only_matching': True, @@ -44,14 +67,42 @@ 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') return self.url_result( - 'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id, - ie=NexxIE.ie_key(), video_id=video_id) + smuggle_url( + 'jwplatform:%s' % jwplatform_id, + {'geo_countries': self._GEO_COUNTRIES}), + ie=JWPlatformIE.ie_key(), video_id=jwplatform_id) 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 387f955ee..a3d9b4017 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -31,6 +31,10 @@ class ThisOldHouseIE(InfoExtractor): }, { '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' @@ -38,6 +42,6 @@ class ThisOldHouseIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - r'<iframe[^>]+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})', + 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/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/twitch.py b/youtube_dl/extractor/twitch.py index 0db2dca41..e211cd4c8 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -21,6 +21,8 @@ from ..utils import ( orderedSet, parse_duration, parse_iso8601, + qualities, + str_or_none, try_get, unified_timestamp, update_url_query, @@ -50,8 +52,14 @@ class TwitchBaseIE(InfoExtractor): def _call_api(self, path, item_id, *args, **kwargs): headers = kwargs.get('headers', {}).copy() - headers['Client-ID'] = self._CLIENT_ID - kwargs['headers'] = headers + headers.update({ + 'Accept': 'application/vnd.twitchtv.v5+json; charset=UTF-8', + 'Client-ID': self._CLIENT_ID, + }) + kwargs.update({ + 'headers': headers, + 'expected_status': (400, 410), + }) response = self._download_json( '%s/%s' % (self._API_BASE, path), item_id, *args, **compat_kwargs(kwargs)) @@ -186,12 +194,27 @@ class TwitchItemBaseIE(TwitchBaseIE): is_live = False else: is_live = None + _QUALITIES = ('small', 'medium', 'large') + quality_key = qualities(_QUALITIES) + thumbnails = [] + preview = info.get('preview') + if isinstance(preview, dict): + for thumbnail_id, thumbnail_url in preview.items(): + thumbnail_url = url_or_none(thumbnail_url) + if not thumbnail_url: + continue + if thumbnail_id not in _QUALITIES: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'preference': quality_key(thumbnail_id), + }) return { 'id': info['_id'], 'title': info.get('title') or 'Untitled Broadcast', 'description': info.get('description'), 'duration': int_or_none(info.get('length')), - 'thumbnail': info.get('preview'), + 'thumbnails': thumbnails, 'uploader': info.get('channel', {}).get('display_name'), 'uploader_id': info.get('channel', {}).get('name'), 'timestamp': parse_iso8601(info.get('recorded_at')), @@ -572,10 +595,18 @@ class TwitchStreamIE(TwitchBaseIE): else super(TwitchStreamIE, cls).suitable(url)) def _real_extract(self, url): - channel_id = self._match_id(url) + channel_name = self._match_id(url) + + access_token = self._call_api( + 'api/channels/%s/access_token' % channel_name, channel_name, + 'Downloading access token JSON') + + token = access_token['token'] + channel_id = compat_str(self._parse_json( + token, channel_name)['channel_id']) stream = self._call_api( - 'kraken/streams/%s?stream_type=all' % channel_id.lower(), + 'kraken/streams/%s?stream_type=all' % channel_id, channel_id, 'Downloading stream JSON').get('stream') if not stream: @@ -585,11 +616,9 @@ class TwitchStreamIE(TwitchBaseIE): # (e.g. http://www.twitch.tv/TWITCHPLAYSPOKEMON) that will lead to constructing # an invalid m3u8 URL. Working around by use of original channel name from stream # JSON and fallback to lowercase if it's not available. - channel_id = stream.get('channel', {}).get('name') or channel_id.lower() - - access_token = self._call_api( - 'api/channels/%s/access_token' % channel_id, channel_id, - 'Downloading channel access token') + channel_name = try_get( + stream, lambda x: x['channel']['name'], + compat_str) or channel_name.lower() query = { 'allow_source': 'true', @@ -600,11 +629,11 @@ class TwitchStreamIE(TwitchBaseIE): 'playlist_include_framerate': 'true', 'segment_preference': '4', 'sig': access_token['sig'].encode('utf-8'), - 'token': access_token['token'].encode('utf-8'), + 'token': token.encode('utf-8'), } formats = self._extract_m3u8_formats( '%s/api/channel/hls/%s.m3u8?%s' - % (self._USHER_BASE, channel_id, compat_urllib_parse_urlencode(query)), + % (self._USHER_BASE, channel_name, compat_urllib_parse_urlencode(query)), channel_id, 'mp4') self._prefer_source(formats) @@ -627,8 +656,8 @@ class TwitchStreamIE(TwitchBaseIE): }) return { - 'id': compat_str(stream['_id']), - 'display_id': channel_id, + 'id': str_or_none(stream.get('_id')) or channel_id, + 'display_id': channel_name, 'title': title, 'description': description, 'thumbnails': thumbnails, @@ -643,7 +672,14 @@ 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 +705,12 @@ 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/twitter.py b/youtube_dl/extractor/twitter.py index 01468981c..4284487db 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -578,6 +578,18 @@ class TwitterBroadcastIE(TwitterBaseIE, PeriscopeBaseIE): IE_NAME = 'twitter:broadcast' _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/broadcasts/(?P<id>[0-9a-zA-Z]{13})' + _TEST = { + # untitled Periscope video + 'url': 'https://twitter.com/i/broadcasts/1yNGaQLWpejGj', + 'info_dict': { + 'id': '1yNGaQLWpejGj', + 'ext': 'mp4', + 'title': 'Andrea May Sahouri - Periscope Broadcast', + 'uploader': 'Andrea May Sahouri', + 'uploader_id': '1PXEdBZWpGwKe', + }, + } + def _real_extract(self, url): broadcast_id = self._match_id(url) broadcast = self._call_api( 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 8cd611e1e..421795b94 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -140,28 +140,28 @@ class VimeoBaseInfoExtractor(InfoExtractor): }) # TODO: fix handling of 308 status code returned for live archive manifest requests + sep_pattern = r'/sep/video/' for files_type in ('hls', 'dash'): for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items(): manifest_url = cdn_data.get('url') if not manifest_url: continue format_id = '%s-%s' % (files_type, cdn_name) - if files_type == 'hls': - formats.extend(self._extract_m3u8_formats( - manifest_url, video_id, 'mp4', - 'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id, - note='Downloading %s m3u8 information' % cdn_name, - fatal=False)) - elif files_type == 'dash': - mpd_pattern = r'/%s/(?:sep/)?video/' % video_id - mpd_manifest_urls = [] - if re.search(mpd_pattern, manifest_url): - for suffix, repl in (('', 'video'), ('_sep', 'sep/video')): - mpd_manifest_urls.append((format_id + suffix, re.sub( - mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url))) - else: - mpd_manifest_urls = [(format_id, manifest_url)] - for f_id, m_url in mpd_manifest_urls: + sep_manifest_urls = [] + if re.search(sep_pattern, manifest_url): + for suffix, repl in (('', 'video'), ('_sep', 'sep/video')): + sep_manifest_urls.append((format_id + suffix, re.sub( + sep_pattern, '/%s/' % repl, manifest_url))) + else: + sep_manifest_urls = [(format_id, manifest_url)] + for f_id, m_url in sep_manifest_urls: + if files_type == 'hls': + formats.extend(self._extract_m3u8_formats( + m_url, video_id, 'mp4', + 'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id, + note='Downloading %s m3u8 information' % cdn_name, + fatal=False)) + elif files_type == 'dash': if 'json=1' in m_url: real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url') if real_m_url: @@ -170,11 +170,6 @@ class VimeoBaseInfoExtractor(InfoExtractor): m_url.replace('/master.json', '/master.mpd'), video_id, f_id, 'Downloading %s MPD information' % cdn_name, fatal=False) - for f in mpd_formats: - if f.get('vcodec') == 'none': - f['preference'] = -50 - elif f.get('acodec') == 'none': - f['preference'] = -40 formats.extend(mpd_formats) live_archive = live_event.get('archive') or {} @@ -186,6 +181,12 @@ class VimeoBaseInfoExtractor(InfoExtractor): 'preference': 1, }) + for f in formats: + if f.get('vcodec') == 'none': + f['preference'] = -50 + elif f.get('acodec') == 'none': + f['preference'] = -40 + subtitles = {} text_tracks = config['request'].get('text_tracks') if text_tracks: 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/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 908defecd..43c5eff1f 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -70,9 +70,14 @@ class YoutubeBaseInfoExtractor(InfoExtractor): _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}' + _YOUTUBE_CLIENT_HEADERS = { + 'x-youtube-client-name': '1', + 'x-youtube-client-version': '1.20200609.04.02', + } + def _set_language(self): self._set_cookie( - '.youtube.com', 'PREF', 'f1=50000000&hl=en', + '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en', # YouTube sets the expire time to about two months expire_time=time.time() + 2 * 30 * 24 * 3600) @@ -301,7 +306,8 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): 'https://youtube.com/%s' % mobj.group('more'), playlist_id, 'Downloading page #%s%s' % (page_num, ' (retry #%d)' % count if count else ''), - transform_source=uppercase_escape) + transform_source=uppercase_escape, + headers=self._YOUTUBE_CLIENT_HEADERS) break except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503): @@ -388,8 +394,15 @@ 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\.)?invidious\.ggc-project\.de/| + (?:www\.)?yt\.maisputain\.ovh/| + (?:www\.)?invidious\.13ad\.de/| + (?:www\.)?invidious\.toot\.koeln/| + (?:www\.)?invidious\.fdn\.fr/| + (?:www\.)?watch\.nettohikari\.com/| (?:www\.)?kgg2m7yk5aybusll\.onion/| (?:www\.)?qklhadlycap4cnod\.onion/| (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/| @@ -397,6 +410,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/| (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/| (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/| + (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: @@ -426,6 +440,10 @@ 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]+)$', + ) _formats = { '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, @@ -1227,6 +1245,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', 'only_matching': True, }, + { + # invalid -> valid video id redirection + 'url': 'DJztXj2GPfl', + 'info_dict': { + 'id': 'DJztXj2GPfk', + 'ext': 'mp4', + 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', + 'description': 'md5:bf577a41da97918e94fa9798d9228825', + 'upload_date': '20090125', + 'uploader': 'Prochorowka', + 'uploader_id': 'Prochorowka', + 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', + 'artist': 'Panjabi MC', + 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', + 'album': 'Beware of the Boys (Mundian To Bach Ke)', + }, + 'params': { + 'skip_download': True, + }, + } ] def __init__(self, *args, **kwargs): @@ -1253,14 +1291,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor): """ Return a string representation of a signature """ return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) - def _extract_signature_function(self, video_id, player_url, example_sig): - id_m = re.match( - r'.*?[-.](?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', - 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' % ( @@ -1616,8 +1658,63 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_id = mobj.group(2) return video_id + def _extract_chapters_from_json(self, webpage, video_id, duration): + if not webpage: + return + player = self._parse_json( + self._search_regex( + r'RELATED_PLAYER_ARGS["\']\s*:\s*({.+})\s*,?\s*\n', webpage, + 'player args', default='{}'), + video_id, fatal=False) + if not player or not isinstance(player, dict): + return + watch_next_response = player.get('watch_next_response') + if not isinstance(watch_next_response, compat_str): + return + response = self._parse_json(watch_next_response, video_id, fatal=False) + if not response or not isinstance(response, dict): + return + chapters_list = try_get( + response, + lambda x: x['playerOverlays'] + ['playerOverlayRenderer'] + ['decoratedPlayerBarRenderer'] + ['decoratedPlayerBarRenderer'] + ['playerBar'] + ['chapteredPlayerBarRenderer'] + ['chapters'], + list) + if not chapters_list: + return + + def chapter_time(chapter): + return float_or_none( + try_get( + chapter, + lambda x: x['chapterRenderer']['timeRangeStartMillis'], + int), + scale=1000) + chapters = [] + for next_num, chapter in enumerate(chapters_list, start=1): + start_time = chapter_time(chapter) + if start_time is None: + continue + end_time = (chapter_time(chapters_list[next_num]) + if next_num < len(chapters_list) else duration) + if end_time is None: + continue + title = try_get( + chapter, lambda x: x['chapterRenderer']['title']['simpleText'], + compat_str) + chapters.append({ + 'start_time': start_time, + 'end_time': end_time, + 'title': title, + }) + return chapters + @staticmethod - def _extract_chapters(description, duration): + def _extract_chapters_from_description(description, duration): if not description: return None chapter_lines = re.findall( @@ -1651,6 +1748,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): }) return chapters + def _extract_chapters(self, webpage, description, video_id, duration): + return (self._extract_chapters_from_json(webpage, video_id, duration) + or self._extract_chapters_from_description(description, duration)) + def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) @@ -1678,7 +1779,10 @@ 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) @@ -1794,6 +1898,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_details = try_get( player_response, lambda x: x['videoDetails'], dict) or {} + microformat = try_get( + player_response, lambda x: x['microformat']['playerMicroformatRenderer'], dict) or {} + video_title = video_info.get('title', [None])[0] or video_details.get('title') if not video_title: self._downloader.report_warning('Unable to extract video title') @@ -1840,15 +1947,26 @@ 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)) @@ -1860,6 +1978,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): view_count = extract_view_count(video_info) if view_count is None and video_details: view_count = int_or_none(video_details.get('viewCount')) + if view_count is None and microformat: + view_count = int_or_none(microformat.get('viewCount')) if is_live is None: is_live = bool_or_none(video_details.get('isLive')) @@ -1919,12 +2039,12 @@ 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) @@ -1975,22 +2095,10 @@ 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)) @@ -2123,7 +2231,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_uploader_id = mobj.group('uploader_id') video_uploader_url = mobj.group('uploader_url') else: - self._downloader.report_warning('unable to extract uploader nickname') + owner_profile_url = url_or_none(microformat.get('ownerProfileUrl')) + if owner_profile_url: + video_uploader_id = self._search_regex( + r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id', + default=None) + video_uploader_url = owner_profile_url channel_id = ( str_or_none(video_details.get('channelId')) @@ -2134,17 +2247,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_webpage, 'channel id', default=None, group='id')) channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None - # thumbnail image - # We try first to get a high quality image: - m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', - video_webpage, re.DOTALL) - if m_thumb is not None: - video_thumbnail = m_thumb.group(1) - elif 'thumbnail_url' not in video_info: - self._downloader.report_warning('unable to extract video thumbnail') + thumbnails = [] + thumbnails_list = try_get( + video_details, lambda x: x['thumbnail']['thumbnails'], list) or [] + for t in thumbnails_list: + if not isinstance(t, dict): + continue + thumbnail_url = url_or_none(t.get('url')) + if not thumbnail_url: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'width': int_or_none(t.get('width')), + 'height': int_or_none(t.get('height')), + }) + + if not thumbnails: video_thumbnail = None - else: # don't panic if we can't find it - video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0]) + # We try first to get a high quality image: + m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', + video_webpage, re.DOTALL) + if m_thumb is not None: + video_thumbnail = m_thumb.group(1) + thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url'][0], compat_str) + if thumbnail_url: + video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url) + if video_thumbnail: + thumbnails.append({'url': video_thumbnail}) # upload date upload_date = self._html_search_meta( @@ -2154,6 +2283,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): [r'(?s)id="eow-date.*?>(.*?)</span>', r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'], video_webpage, 'upload date', default=None) + if not upload_date: + upload_date = microformat.get('publishDate') or microformat.get('uploadDate') upload_date = unified_strdate(upload_date) video_license = self._html_search_regex( @@ -2225,17 +2356,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor): m_cat_container = self._search_regex( r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', video_webpage, 'categories', default=None) + category = None if m_cat_container: category = self._html_search_regex( r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', default=None) - video_categories = None if category is None else [category] - else: - video_categories = None + if not category: + category = try_get( + microformat, lambda x: x['category'], compat_str) + video_categories = None if category is None else [category] video_tags = [ unescapeHTML(m.group('content')) for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] + if not video_tags: + video_tags = try_get(video_details, lambda x: x['keywords'], list) def _extract_count(count_name): return str_to_int(self._search_regex( @@ -2286,7 +2421,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): errnote='Unable to download video annotations', fatal=False, data=urlencode_postdata({xsrf_field_name: xsrf_token})) - chapters = self._extract_chapters(description_original, video_duration) + chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration) # Look for the DASH manifest if self._downloader.params.get('youtube_include_dash_manifest', True): @@ -2377,7 +2512,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'creator': video_creator or artist, 'title': video_title, 'alt_title': video_alt_title or track, - 'thumbnail': video_thumbnail, + 'thumbnails': thumbnails, 'description': video_description, 'categories': video_categories, 'tags': video_tags, @@ -2981,7 +3116,7 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor): class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): IE_DESC = 'YouTube.com user/channel playlists' - _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists' + _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists' IE_NAME = 'youtube:playlists' _TESTS = [{ @@ -3007,6 +3142,9 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): 'title': 'Chem Player', }, 'skip': 'Blocked', + }, { + 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', + 'only_matching': True, }] @@ -3153,7 +3291,8 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): more = self._download_json( 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, 'Downloading page #%s' % page_num, - transform_source=uppercase_escape) + transform_source=uppercase_escape, + headers=self._YOUTUBE_CLIENT_HEADERS) content_html = more['content_html'] more_widget_html = more['load_more_widget_html'] diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 8826b382c..6d5ac62b3 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -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/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index fd3f921a8..5f7298345 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -447,6 +447,13 @@ class FFmpegMetadataPP(FFmpegPostProcessor): metadata[meta_f] = info[info_f] break + # See [1-4] for some info on media metadata/metadata supported + # by ffmpeg. + # 1. https://kdenlive.org/en/project/adding-meta-data-to-mp4-video/ + # 2. https://wiki.multimedia.cx/index.php/FFmpeg_Metadata + # 3. https://kodi.wiki/view/Video_file_tagging + # 4. http://atomicparsley.sourceforge.net/mpeg-4files.html + add('title', ('track', 'title')) add('date', 'upload_date') add(('description', 'comment'), 'description') @@ -457,6 +464,10 @@ class FFmpegMetadataPP(FFmpegPostProcessor): add('album') add('album_artist') add('disc', 'disc_number') + add('show', 'series') + add('season_number') + add('episode_id', ('episode', 'episode_id')) + add('episode_sort', 'episode_number') if not metadata: self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add') diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 38262bee4..d1eca3760 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 @@ -1835,6 +1837,12 @@ def write_json_file(obj, fn): os.unlink(fn) except OSError: pass + try: + mask = os.umask(0) + os.umask(mask) + os.chmod(tf.name, 0o666 & ~mask) + except OSError: + pass os.rename(tf.name, fn) except Exception: try: @@ -2735,14 +2743,66 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): 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.""" @@ -2752,12 +2812,30 @@ 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 diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0f768f7c1..6b88eb38c 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.03.08' +__version__ = '2020.06.16.1'