diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index fb0d33b8f..fcfadeb1f 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.12** - [ ] 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 2019.07.02 + [debug] youtube-dl version 2019.07.12 [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 3c95565a6..7e1a3d1c0 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.12** - [ ] 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 7410776d7..71782a104 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.12** - [ ] 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 cc52bcca6..6bcfde1f8 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.12** - [ ] 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 2019.07.02 + [debug] youtube-dl version 2019.07.12 [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 bbd421b1a..89d9c63aa 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.12** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 5ce78b07a..45cb2746e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,29 @@ +version 2019.07.12 + +Core ++ [adobepass] Add support for AT&T U-verse (mso ATT) (#13938, #21016) + +Extractors ++ [mgtv] Pass Referer HTTP header for format URLs (#21726) ++ [beeg] Add support for api/v6 v2 URLs without t argument (#21701) +* [voxmedia:volume] Improvevox embed extraction (#16846) +* [funnyordie] Move extraction to VoxMedia extractor (#16846) +* [gameinformer] Fix extraction (#8895, #15363, #17206) +* [funk] Fix extraction (#17915) +* [packtpub] Relax lesson URL regular expression (#21695) +* [packtpub] Fix extraction (#21268) +* [philharmoniedeparis] Relax URL regular expression (#21672) +* [peertube] Detect embed URLs in generic extraction (#21666) +* [mixer:vod] Relax URL regular expression (#21657, #21658) ++ [lecturio] Add support id based URLs (#21630) ++ [go] Add site info for disneynow (#21613) +* [ted] Restrict info regular expression (#21631) +* [twitch:vod] Actualize m3u8 URL (#21538, #21607) +* [vzaar] Fix videos with empty title (#21606) +* [tvland] Fix extraction (#21384) +* [arte] Clean extractor (#15583, #21614) + + version 2019.07.02 Core diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 55ae43144..4e664336d 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -58,16 +58,8 @@ - **ARD:mediathek** - **ARDBetaMediathek** - **Arkena** - - **arte.tv** - **arte.tv:+7** - - **arte.tv:cinema** - - **arte.tv:concert** - - **arte.tv:creative** - - **arte.tv:ddc** - **arte.tv:embed** - - **arte.tv:future** - - **arte.tv:info** - - **arte.tv:magazine** - **arte.tv:playlist** - **AsianCrush** - **AsianCrushPlaylist** @@ -313,9 +305,7 @@ - **FrontendMastersCourse** - **FrontendMastersLesson** - **Funimation** - - **FunkChannel** - - **FunkMix** - - **FunnyOrDie** + - **Funk** - **Fusion** - **Fux** - **FXNetworks** @@ -896,7 +886,6 @@ - **TF1** - **TFO** - **TheIntercept** - - **theoperaplatform** - **ThePlatform** - **ThePlatformFeed** - **TheScene** diff --git a/youtube_dl/extractor/abcnews.py b/youtube_dl/extractor/abcnews.py index cd29aca77..8b407bf9c 100644 --- a/youtube_dl/extractor/abcnews.py +++ b/youtube_dl/extractor/abcnews.py @@ -15,10 +15,13 @@ class AbcNewsVideoIE(AMPIE): IE_NAME = 'abcnews:video' _VALID_URL = r'''(?x) https?:// - abcnews\.go\.com/ (?: - [^/]+/video/(?P[0-9a-z-]+)-| - video/embed\?.*?\bid= + abcnews\.go\.com/ + (?: + [^/]+/video/(?P[0-9a-z-]+)-| + video/embed\?.*?\bid= + )| + fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/ ) (?P\d+) ''' diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index c15a0ac8f..5788d13ba 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -32,6 +32,10 @@ class BeegIE(InfoExtractor): # api/v6 v2 'url': 'https://beeg.com/1941093077?t=911-1391', 'only_matching': True, + }, { + # api/v6 v2 w/o t + 'url': 'https://beeg.com/1277207756', + 'only_matching': True, }, { 'url': 'https://beeg.porn/video/5416503', 'only_matching': True, @@ -49,14 +53,17 @@ class BeegIE(InfoExtractor): r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', default='1546225636701') - qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - t = qs.get('t', [''])[0].split('-') - if len(t) > 1: + if len(video_id) >= 10: query = { 'v': 2, - 's': t[0], - 'e': t[1], } + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + t = qs.get('t', [''])[0].split('-') + if len(t) > 1: + query.update({ + 's': t[0], + 'e': t[1], + }) else: query = {'v': 1} diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index 8cc9bd165..6cf05e6da 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -216,17 +216,14 @@ class FiveThirtyEightIE(InfoExtractor): _TEST = { 'url': 'http://fivethirtyeight.com/features/how-the-6-8-raiders-can-still-make-the-playoffs/', 'info_dict': { - 'id': '21846851', - 'ext': 'mp4', + 'id': '56032156', + 'ext': 'flv', 'title': 'FiveThirtyEight: The Raiders can still make the playoffs', 'description': 'Neil Paine breaks down the simplest scenario that will put the Raiders into the playoffs at 8-8.', - 'timestamp': 1513960621, - 'upload_date': '20171222', }, 'params': { 'skip_download': True, }, - 'expected_warnings': ['Unable to download f4m manifest'], } def _real_extract(self, url): @@ -234,9 +231,8 @@ class FiveThirtyEightIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - video_id = self._search_regex( - r'data-video-id=["\'](?P\d+)', - webpage, 'video id', group='id') + embed_url = self._search_regex( + r']+src=["\'](https?://fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/\d+)', + webpage, 'embed url') - return self.url_result( - 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key()) + return self.url_result(embed_url, 'AbcNewsVideo') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 02f17cf0d..555fadfaf 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -395,11 +395,7 @@ from .frontendmasters import ( FrontendMastersCourseIE ) from .funimation import FunimationIE -from .funk import ( - FunkMixIE, - FunkChannelIE, -) -from .funnyordie import FunnyOrDieIE +from .funk import FunkIE from .fusion import FusionIE from .fxnetworks import FXNetworksIE from .gaia import GaiaIE diff --git a/youtube_dl/extractor/fivetv.py b/youtube_dl/extractor/fivetv.py index 9f9863746..c4c0f1b3d 100644 --- a/youtube_dl/extractor/fivetv.py +++ b/youtube_dl/extractor/fivetv.py @@ -9,7 +9,7 @@ from ..utils import int_or_none class FiveTVIE(InfoExtractor): _VALID_URL = r'''(?x) - http:// + https?:// (?:www\.)?5-tv\.ru/ (?: (?:[^/]+/)+(?P\d+)| @@ -39,6 +39,7 @@ class FiveTVIE(InfoExtractor): 'duration': 180, }, }, { + # redirect to https://www.5-tv.ru/projects/1000095/izvestia-glavnoe/ 'url': 'http://www.5-tv.ru/glavnoe/#itemDetails', 'info_dict': { 'id': 'glavnoe', @@ -46,6 +47,7 @@ class FiveTVIE(InfoExtractor): 'title': r're:^Итоги недели с \d+ по \d+ \w+ \d{4} года$', 'thumbnail': r're:^https?://.*\.jpg$', }, + 'skip': 'redirect to «Известия. Главное» project page', }, { 'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/', 'only_matching': True, @@ -70,7 +72,7 @@ class FiveTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( - [r']+?class="flowplayer[^>]+?data-href="([^"]+)"', + [r']+?class="(?:flow)?player[^>]+?data-href="([^"]+)"', r']+?href="([^"]+)"[^>]+?class="videoplayer"'], webpage, 'video url') diff --git a/youtube_dl/extractor/funk.py b/youtube_dl/extractor/funk.py index 7e1af95e0..81d1949fd 100644 --- a/youtube_dl/extractor/funk.py +++ b/youtube_dl/extractor/funk.py @@ -1,89 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals -import itertools import re from .common import InfoExtractor from .nexx import NexxIE -from ..compat import compat_str from ..utils import ( int_or_none, - try_get, + str_or_none, ) -class FunkBaseIE(InfoExtractor): - _HEADERS = { - 'Accept': '*/*', - 'Accept-Language': 'en-US,en;q=0.9,ru;q=0.8', - 'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4', - } - _AUTH = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4' - - @staticmethod - def _make_headers(referer): - headers = FunkBaseIE._HEADERS.copy() - headers['Referer'] = referer - return headers - - def _make_url_result(self, video): - return { - '_type': 'url_transparent', - 'url': 'nexx:741:%s' % video['sourceId'], - 'ie_key': NexxIE.ie_key(), - 'id': video['sourceId'], - 'title': video.get('title'), - 'description': video.get('description'), - 'duration': int_or_none(video.get('duration')), - 'season_number': int_or_none(video.get('seasonNr')), - 'episode_number': int_or_none(video.get('episodeNr')), - } - - -class FunkMixIE(FunkBaseIE): - _VALID_URL = r'https?://(?:www\.)?funk\.net/mix/(?P[^/]+)/(?P[^/?#&]+)' +class FunkIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?funk\.net/(?:channel|playlist)/[^/]+/(?P[0-9a-z-]+)-(?P\d+)' _TESTS = [{ - 'url': 'https://www.funk.net/mix/59d65d935f8b160001828b5b/die-realste-kifferdoku-aller-zeiten', - 'md5': '8edf617c2f2b7c9847dfda313f199009', - 'info_dict': { - 'id': '123748', - 'ext': 'mp4', - 'title': '"Die realste Kifferdoku aller Zeiten"', - 'description': 'md5:c97160f5bafa8d47ec8e2e461012aa9d', - 'timestamp': 1490274721, - 'upload_date': '20170323', - }, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - mix_id = mobj.group('id') - alias = mobj.group('alias') - - lists = self._download_json( - 'https://www.funk.net/api/v3.1/curation/curatedLists/', - mix_id, headers=self._make_headers(url), query={ - 'size': 100, - })['_embedded']['curatedListList'] - - metas = next( - l for l in lists - if mix_id in (l.get('entityId'), l.get('alias')))['videoMetas'] - video = next( - meta['videoDataDelegate'] - for meta in metas - if try_get( - meta, lambda x: x['videoDataDelegate']['alias'], - compat_str) == alias) - - return self._make_url_result(video) - - -class FunkChannelIE(FunkBaseIE): - _VALID_URL = r'https?://(?:www\.)?funk\.net/channel/(?P[^/]+)/(?P[^/?#&]+)' - _TESTS = [{ - 'url': 'https://www.funk.net/channel/ba/die-lustigsten-instrumente-aus-dem-internet-teil-2', + 'url': 'https://www.funk.net/channel/ba-793/die-lustigsten-instrumente-aus-dem-internet-teil-2-1155821', + 'md5': '8dd9d9ab59b4aa4173b3197f2ea48e81', 'info_dict': { 'id': '1155821', 'ext': 'mp4', @@ -92,83 +24,26 @@ class FunkChannelIE(FunkBaseIE): 'timestamp': 1514507395, 'upload_date': '20171229', }, - 'params': { - 'skip_download': True, - }, + }, { - # only available via byIdList API - 'url': 'https://www.funk.net/channel/informr/martin-sonneborn-erklaert-die-eu', - 'info_dict': { - 'id': '205067', - 'ext': 'mp4', - 'title': 'Martin Sonneborn erklärt die EU', - 'description': 'md5:050f74626e4ed87edf4626d2024210c0', - 'timestamp': 1494424042, - 'upload_date': '20170510', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'https://www.funk.net/channel/59d5149841dca100012511e3/mein-erster-job-lovemilla-folge-1/lovemilla/', + 'url': 'https://www.funk.net/playlist/neuesteVideos/kameras-auf-dem-fusion-festival-1618699', 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - alias = mobj.group('alias') - - headers = self._make_headers(url) - - video = None - - # Id-based channels are currently broken on their side: webplayer - # tries to process them via byChannelAlias endpoint and fails - # predictably. - for page_num in itertools.count(): - by_channel_alias = self._download_json( - 'https://www.funk.net/api/v3.1/webapp/videos/byChannelAlias/%s' - % channel_id, - 'Downloading byChannelAlias JSON page %d' % (page_num + 1), - headers=headers, query={ - 'filterFsk': 'false', - 'sort': 'creationDate,desc', - 'size': 100, - 'page': page_num, - }, fatal=False) - if not by_channel_alias: - break - video_list = try_get( - by_channel_alias, lambda x: x['_embedded']['videoList'], list) - if not video_list: - break - try: - video = next(r for r in video_list if r.get('alias') == alias) - break - except StopIteration: - pass - if not try_get( - by_channel_alias, lambda x: x['_links']['next']): - break - - if not video: - by_id_list = self._download_json( - 'https://www.funk.net/api/v3.0/content/videos/byIdList', - channel_id, 'Downloading byIdList JSON', headers=headers, - query={ - 'ids': alias, - }, fatal=False) - if by_id_list: - video = try_get(by_id_list, lambda x: x['result'][0], dict) - - if not video: - results = self._download_json( - 'https://www.funk.net/api/v3.0/content/videos/filter', - channel_id, 'Downloading filter JSON', headers=headers, query={ - 'channelId': channel_id, - 'size': 100, - })['result'] - video = next(r for r in results if r.get('alias') == alias) - - return self._make_url_result(video) + display_id, nexx_id = re.match(self._VALID_URL, url).groups() + video = self._download_json( + 'https://www.funk.net/api/v4.0/videos/' + nexx_id, nexx_id) + return { + '_type': 'url_transparent', + 'url': 'nexx:741:' + nexx_id, + 'ie_key': NexxIE.ie_key(), + 'id': nexx_id, + 'title': video.get('title'), + 'description': video.get('description'), + 'duration': int_or_none(video.get('duration')), + 'channel_id': str_or_none(video.get('channelId')), + 'display_id': display_id, + 'tags': video.get('tags'), + 'thumbnail': video.get('imageUrlLandscape'), + } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py deleted file mode 100644 index f85e7de14..000000000 --- a/youtube_dl/extractor/funnyordie.py +++ /dev/null @@ -1,162 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - float_or_none, - int_or_none, - unified_timestamp, -) - - -class FunnyOrDieIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?Pembed|articles|videos)/(?P[0-9a-f]+)(?:$|[?#/])' - _TESTS = [{ - 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', - 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9', - 'info_dict': { - 'id': '0732f586d7', - 'ext': 'mp4', - 'title': 'Heart-Shaped Box: Literal Video Version', - 'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338', - 'thumbnail': r're:^http:.*\.jpg$', - 'uploader': 'DASjr', - 'timestamp': 1317904928, - 'upload_date': '20111006', - 'duration': 318.3, - }, - }, { - 'url': 'http://www.funnyordie.com/embed/e402820827', - 'info_dict': { - 'id': 'e402820827', - 'ext': 'mp4', - 'title': 'Please Use This Song (Jon Lajoie)', - 'description': 'Please use this to sell something. www.jonlajoie.com', - 'thumbnail': r're:^http:.*\.jpg$', - 'timestamp': 1398988800, - 'upload_date': '20140502', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - - links = re.findall(r']+src=(["\'])(?P.+?/master\.m3u8[^"\']*)\1', - webpage, 'm3u8 url', group='url') - - formats = [] - - m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False) - source_formats = list(filter( - lambda f: f.get('vcodec') != 'none', m3u8_formats)) - - bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)] - bitrates.sort() - - if source_formats: - self._sort_formats(source_formats) - - for bitrate, f in zip(bitrates, source_formats or [{}] * len(bitrates)): - for path, ext in links: - ff = f.copy() - if ff: - if ext != 'mp4': - ff = dict( - [(k, v) for k, v in ff.items() - if k in ('height', 'width', 'format_id')]) - ff.update({ - 'format_id': ff['format_id'].replace('hls', ext), - 'ext': ext, - 'protocol': 'http', - }) - else: - ff.update({ - 'format_id': '%s-%d' % (ext, bitrate), - 'vbr': bitrate, - }) - ff['url'] = self._proto_relative_url( - '%s%d.%s' % (path, bitrate, ext)) - formats.append(ff) - self._check_formats(formats, video_id) - - formats.extend(m3u8_formats) - self._sort_formats( - formats, field_preference=('height', 'width', 'tbr', 'format_id')) - - subtitles = {} - for src, src_lang in re.findall(r']+\bclass=["\']channel-preview-name[^>]+>(.+?).+)\.aspx' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P[^.?&#]+)' + _TESTS = [{ + # normal Brightcove embed code extracted with BrightcoveNewIE._extract_url 'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx', 'md5': '292f26da1ab4beb4c9099f1304d2b071', 'info_dict': { @@ -18,16 +25,25 @@ class GameInformerIE(InfoExtractor): 'upload_date': '20150928', 'uploader_id': '694940074001', }, - } + }, { + # Brightcove id inside unique element with field--name-field-brightcove-video-id class + 'url': 'https://www.gameinformer.com/video-feature/new-gameplay-today/2019/07/09/new-gameplay-today-streets-of-rogue', + 'info_dict': { + 'id': '6057111913001', + 'ext': 'mp4', + 'title': 'New Gameplay Today – Streets Of Rogue', + 'timestamp': 1562699001, + 'upload_date': '20190709', + 'uploader_id': '694940074001', + + }, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s' def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage( url, display_id, headers=self.geo_verification_headers()) - brightcove_id = self._search_regex( - [r'<[^>]+\bid=["\']bc_(\d+)', r"getVideo\('[^']+video_id=(\d+)"], - webpage, 'brightcove id') - return self.url_result( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', - brightcove_id) + brightcove_id = clean_html(get_element_by_class('field--name-field-brightcove-video-id', webpage) or get_element_by_id('video-source-content', webpage)) + brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id if brightcove_id else BrightcoveNewIE._extract_url(self, webpage) + return self.url_result(brightcove_url, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/mgtv.py b/youtube_dl/extractor/mgtv.py index 84137df50..7ae2e3c3b 100644 --- a/youtube_dl/extractor/mgtv.py +++ b/youtube_dl/extractor/mgtv.py @@ -79,6 +79,9 @@ class MGTVIE(InfoExtractor): 'ext': 'mp4', 'tbr': tbr, 'protocol': 'm3u8_native', + 'http_headers': { + 'Referer': url, + }, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/packtpub.py b/youtube_dl/extractor/packtpub.py index 1324137df..11ad3b3b8 100644 --- a/youtube_dl/extractor/packtpub.py +++ b/youtube_dl/extractor/packtpub.py @@ -5,26 +5,27 @@ import re from .common import InfoExtractor from ..compat import ( - compat_str, + # compat_str, compat_HTTPError, ) from ..utils import ( clean_html, ExtractorError, - remove_end, + # remove_end, + str_or_none, strip_or_none, unified_timestamp, - urljoin, + # urljoin, ) class PacktPubBaseIE(InfoExtractor): - _PACKT_BASE = 'https://www.packtpub.com' - _MAPT_REST = '%s/mapt-rest' % _PACKT_BASE + # _PACKT_BASE = 'https://www.packtpub.com' + _STATIC_PRODUCTS_BASE = 'https://static.packt-cdn.com/products/' class PacktPubIE(PacktPubBaseIE): - _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+)/(?P\d+)/(?P\d+)' + _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P\d+)/(?P[^/]+)/(?P[^/]+)(?:/(?P[^/?&#]+))?' _TESTS = [{ 'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro', @@ -40,6 +41,9 @@ class PacktPubIE(PacktPubBaseIE): }, { 'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro', 'only_matching': True, + }, { + 'url': 'https://subscription.packtpub.com/video/programming/9781838988906/p1/video1_1/business-card-project', + 'only_matching': True, }] _NETRC_MACHINE = 'packtpub' _TOKEN = None @@ -50,9 +54,9 @@ class PacktPubIE(PacktPubBaseIE): return try: self._TOKEN = self._download_json( - self._MAPT_REST + '/users/tokens', None, + 'https://services.packtpub.com/auth-v1/users/tokens', None, 'Downloading Authorization Token', data=json.dumps({ - 'email': username, + 'username': username, 'password': password, }).encode())['data']['access'] except ExtractorError as e: @@ -61,54 +65,40 @@ class PacktPubIE(PacktPubBaseIE): raise ExtractorError(message, expected=True) raise - def _handle_error(self, response): - if response.get('status') != 'success': - raise ExtractorError( - '% said: %s' % (self.IE_NAME, response['message']), - expected=True) - - def _download_json(self, *args, **kwargs): - response = super(PacktPubIE, self)._download_json(*args, **kwargs) - self._handle_error(response) - return response - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - course_id, chapter_id, video_id = mobj.group( - 'course_id', 'chapter_id', 'id') + course_id, chapter_id, video_id, display_id = re.match(self._VALID_URL, url).groups() headers = {} if self._TOKEN: headers['Authorization'] = 'Bearer ' + self._TOKEN - video = self._download_json( - '%s/users/me/products/%s/chapters/%s/sections/%s' - % (self._MAPT_REST, course_id, chapter_id, video_id), video_id, - 'Downloading JSON video', headers=headers)['data'] + try: + video_url = self._download_json( + 'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id, + 'Downloading JSON video', headers=headers)['data'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + self.raise_login_required('This video is locked') + raise - content = video.get('content') - if not content: - self.raise_login_required('This video is locked') + # TODO: find a better way to avoid duplicating course requests + # metadata = self._download_json( + # '%s/products/%s/chapters/%s/sections/%s/metadata' + # % (self._MAPT_REST, course_id, chapter_id, video_id), + # video_id)['data'] - video_url = content['file'] - - metadata = self._download_json( - '%s/products/%s/chapters/%s/sections/%s/metadata' - % (self._MAPT_REST, course_id, chapter_id, video_id), - video_id)['data'] - - title = metadata['pageTitle'] - course_title = metadata.get('title') - if course_title: - title = remove_end(title, ' - %s' % course_title) - timestamp = unified_timestamp(metadata.get('publicationDate')) - thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath')) + # title = metadata['pageTitle'] + # course_title = metadata.get('title') + # if course_title: + # title = remove_end(title, ' - %s' % course_title) + # timestamp = unified_timestamp(metadata.get('publicationDate')) + # thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath')) return { 'id': video_id, 'url': video_url, - 'title': title, - 'thumbnail': thumbnail, - 'timestamp': timestamp, + 'title': display_id or video_id, # title, + # 'thumbnail': thumbnail, + # 'timestamp': timestamp, } @@ -119,6 +109,7 @@ class PacktPubCourseIE(PacktPubBaseIE): 'info_dict': { 'id': '9781787122215', 'title': 'Learn Nodejs by building 12 projects [Video]', + 'description': 'md5:489da8d953f416e51927b60a1c7db0aa', }, 'playlist_count': 90, }, { @@ -136,35 +127,38 @@ class PacktPubCourseIE(PacktPubBaseIE): url, course_id = mobj.group('url', 'id') course = self._download_json( - '%s/products/%s/metadata' % (self._MAPT_REST, course_id), - course_id)['data'] + self._STATIC_PRODUCTS_BASE + '%s/toc' % course_id, course_id) + metadata = self._download_json( + self._STATIC_PRODUCTS_BASE + '%s/summary' % course_id, + course_id, fatal=False) or {} entries = [] - for chapter_num, chapter in enumerate(course['tableOfContents'], 1): - if chapter.get('type') != 'chapter': - continue - children = chapter.get('children') - if not isinstance(children, list): + for chapter_num, chapter in enumerate(course['chapters'], 1): + chapter_id = str_or_none(chapter.get('id')) + sections = chapter.get('sections') + if not chapter_id or not isinstance(sections, list): continue chapter_info = { 'chapter': chapter.get('title'), 'chapter_number': chapter_num, - 'chapter_id': chapter.get('id'), + 'chapter_id': chapter_id, } - for section in children: - if section.get('type') != 'section': - continue - section_url = section.get('seoUrl') - if not isinstance(section_url, compat_str): + for section in sections: + section_id = str_or_none(section.get('id')) + if not section_id or section.get('contentType') != 'video': continue entry = { '_type': 'url_transparent', - 'url': urljoin(url + '/', section_url), + 'url': '/'.join([url, chapter_id, section_id]), 'title': strip_or_none(section.get('title')), 'description': clean_html(section.get('summary')), + 'thumbnail': metadata.get('coverImage'), + 'timestamp': unified_timestamp(metadata.get('publicationDate')), 'ie_key': PacktPubIE.ie_key(), } entry.update(chapter_info) entries.append(entry) - return self.playlist_result(entries, course_id, course.get('title')) + return self.playlist_result( + entries, course_id, metadata.get('title'), + clean_html(metadata.get('about'))) diff --git a/youtube_dl/extractor/voxmedia.py b/youtube_dl/extractor/voxmedia.py index c7a0a88fe..b318e15d4 100644 --- a/youtube_dl/extractor/voxmedia.py +++ b/youtube_dl/extractor/voxmedia.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals from .common import InfoExtractor from .once import OnceIE from ..compat import compat_urllib_parse_unquote -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, +) class VoxMediaVolumeIE(OnceIE): @@ -13,18 +16,43 @@ class VoxMediaVolumeIE(OnceIE): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_data = self._parse_json(self._search_regex( - r'Volume\.createVideo\(({.+})\s*,\s*{.*}\s*,\s*\[.*\]\s*,\s*{.*}\);', webpage, 'video data'), video_id) + + setup = self._parse_json(self._search_regex( + r'setup\s*=\s*({.+});', webpage, 'setup'), video_id) + video_data = setup.get('video') or {} + info = { + 'id': video_id, + 'title': video_data.get('title_short'), + 'description': video_data.get('description_long') or video_data.get('description_short'), + 'thumbnail': video_data.get('brightcove_thumbnail') + } + asset = setup.get('asset') or setup.get('params') or {} + + formats = [] + hls_url = asset.get('hls_url') + if hls_url: + formats.extend(self._extract_m3u8_formats( + hls_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + mp4_url = asset.get('mp4_url') + if mp4_url: + tbr = self._search_regex(r'-(\d+)k\.', mp4_url, 'bitrate', default=None) + format_id = 'http' + if tbr: + format_id += '-' + tbr + formats.append({ + 'format_id': format_id, + 'url': mp4_url, + 'tbr': int_or_none(tbr), + }) + if formats: + self._sort_formats(formats) + info['formats'] = formats + return info + for provider_video_type in ('ooyala', 'youtube', 'brightcove'): provider_video_id = video_data.get('%s_id' % provider_video_type) if not provider_video_id: continue - info = { - 'id': video_id, - 'title': video_data.get('title_short'), - 'description': video_data.get('description_long') or video_data.get('description_short'), - 'thumbnail': video_data.get('brightcove_thumbnail') - } if provider_video_type == 'brightcove': info['formats'] = self._extract_once_formats(provider_video_id) self._sort_formats(info['formats']) @@ -39,46 +67,49 @@ class VoxMediaVolumeIE(OnceIE): class VoxMediaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:(?:theverge|vox|sbnation|eater|polygon|curbed|racked)\.com|recode\.net)/(?:[^/]+/)*(?P[^/?]+)' + _VALID_URL = r'https?://(?:www\.)?(?:(?:theverge|vox|sbnation|eater|polygon|curbed|racked|funnyordie)\.com|recode\.net)/(?:[^/]+/)*(?P[^/?]+)' _TESTS = [{ + # Volume embed, Youtube 'url': 'http://www.theverge.com/2014/6/27/5849272/material-world-how-google-discovered-what-software-is-made-of', 'info_dict': { - 'id': '11eXZobjrG8DCSTgrNjVinU-YmmdYjhe', + 'id': 'j4mLW6x17VM', 'ext': 'mp4', - 'title': 'Google\'s new material design direction', - 'description': 'md5:2f44f74c4d14a1f800ea73e1c6832ad2', + 'title': 'Material world: how Google discovered what software is made of', + 'description': 'md5:dfc17e7715e3b542d66e33a109861382', + 'upload_date': '20190710', + 'uploader_id': 'TheVerge', + 'uploader': 'The Verge', }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['Ooyala'], + 'add_ie': ['Youtube'], }, { - # data-ooyala-id + # Volume embed, Youtube 'url': 'http://www.theverge.com/2014/10/21/7025853/google-nexus-6-hands-on-photos-video-android-phablet', - 'md5': 'd744484ff127884cd2ba09e3fa604e4b', + 'md5': '4c8f4a0937752b437c3ebc0ed24802b5', 'info_dict': { - 'id': 'RkZXU4cTphOCPDMZg5oEounJyoFI0g-B', + 'id': 'Gy8Md3Eky38', 'ext': 'mp4', 'title': 'The Nexus 6: hands-on with Google\'s phablet', - 'description': 'md5:87a51fe95ff8cea8b5bdb9ac7ae6a6af', + 'description': 'md5:d9f0216e5fb932dd2033d6db37ac3f1d', + 'uploader_id': 'TheVerge', + 'upload_date': '20141021', + 'uploader': 'The Verge', }, - 'add_ie': ['Ooyala'], - 'skip': 'Video Not Found', + 'add_ie': ['Youtube'], + 'skip': 'similar to the previous test', }, { - # volume embed + # Volume embed, Youtube 'url': 'http://www.vox.com/2016/3/31/11336640/mississippi-lgbt-religious-freedom-bill', 'info_dict': { - 'id': 'wydzk3dDpmRz7PQoXRsTIX6XTkPjYL0b', + 'id': 'YCjDnX-Xzhg', 'ext': 'mp4', - 'title': 'The new frontier of LGBTQ civil rights, explained', - 'description': 'md5:0dc58e94a465cbe91d02950f770eb93f', + 'title': "Mississippi's laws are so bad that its anti-LGBTQ law isn't needed to allow discrimination", + 'description': 'md5:fc1317922057de31cd74bce91eb1c66c', + 'uploader_id': 'voxdotcom', + 'upload_date': '20150915', + 'uploader': 'Vox', }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['Ooyala'], + 'add_ie': ['Youtube'], + 'skip': 'similar to the previous test', }, { # youtube embed 'url': 'http://www.vox.com/2016/3/24/11291692/robot-dance', @@ -93,6 +124,7 @@ class VoxMediaIE(InfoExtractor): 'uploader': 'Vox', }, 'add_ie': ['Youtube'], + 'skip': 'Page no longer contain videos', }, { # SBN.VideoLinkset.entryGroup multiple ooyala embeds 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok', @@ -118,10 +150,11 @@ class VoxMediaIE(InfoExtractor): 'description': 'md5:e02d56b026d51aa32c010676765a690d', }, }], + 'skip': 'Page no longer contain videos', }, { # volume embed, Brightcove Once 'url': 'https://www.recode.net/2014/6/17/11628066/post-post-pc-ceo-the-full-code-conference-video-of-microsofts-satya', - 'md5': '01571a896281f77dc06e084138987ea2', + 'md5': '2dbc77b8b0bff1894c2fce16eded637d', 'info_dict': { 'id': '1231c973d', 'ext': 'mp4', diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index b570d5bae..8a3c502ba 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -27,6 +27,7 @@ from ..compat import ( compat_str, ) from ..utils import ( + bool_or_none, clean_html, dict_get, error_to_compat_str, @@ -116,6 +117,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor): 'f.req': json.dumps(f_req), 'flowName': 'GlifWebSignIn', 'flowEntry': 'ServiceLogin', + # TODO: reverse actual botguard identifier generation algo + 'bgRequest': '["identifier",""]', }) return self._download_json( url, None, note=note, errnote=errnote, @@ -1888,6 +1891,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if view_count is None and video_details: view_count = int_or_none(video_details.get('viewCount')) + if is_live is None: + is_live = bool_or_none(dict_get( + video_details, ('isLive', 'isLiveContent'), + skip_false_values=False)) + # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 78fe54326..18bcb33e2 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.07.02' +__version__ = '2019.07.12'