diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index ad52c8900..6bc7d0366 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.01.07*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.01.07** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.01.14*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.01.14** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2018.01.07 +[debug] youtube-dl version 2018.01.14 [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/AUTHORS b/AUTHORS index 5a090a3ef..40215a5cf 100644 --- a/AUTHORS +++ b/AUTHORS @@ -232,3 +232,4 @@ Tatsuyuki Ishi Daniel Weber Kay Bouché Yang Hongbo +Lei Wang diff --git a/ChangeLog b/ChangeLog index 51825ccfe..bfafaca6a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,8 +1,22 @@ -version +version 2018.01.14 Extractors +* [youtube] Fix live streams extraction (#15202) +* [wdr] Bypass geo restriction +* [wdr] Rework extractors (#14598) ++ [wdr] Add support for wdrmaus.de/elefantenseite (#14598) ++ [gamestar] Add support for gamepro.de (#3384) +* [viafree] Skip rtmp formats (#15232) ++ [pandoratv] Add support for mobile URLs (#12441) ++ [pandoratv] Add support for new URL format (#15131) ++ [ximalaya] Add support for ximalaya.com (#14687) ++ [digg] Add support for digg.com (#15214) +* [limelight] Tolerate empty pc formats (#15150, #15151, #15207) +* [ndr:embed:base] Make separate formats extraction non fatal (#15203) + [weibo] Add extractor (#15079) -* [bilibili] fix extraction (#15188) ++ [ok] Add support for live streams +* [canalplus] Fix extraction (#15072) +* [bilibili] Fix extraction (#15188) version 2018.01.07 diff --git a/README.md b/README.md index 267ad86ea..7787a3f17 100644 --- a/README.md +++ b/README.md @@ -46,7 +46,7 @@ Or with [MacPorts](https://www.macports.org/): Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html). # DESCRIPTION -**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. +**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. youtube-dl [OPTIONS] URL [URL...] @@ -878,7 +878,7 @@ Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox). -Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, Mac OS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. +Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, macOS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare). diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 79b343048..c04a75b88 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -128,7 +128,7 @@ - **CamdemyFolder** - **CamWithHer** - **canalc2.tv** - - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv + - **Canalplus**: mycanal.fr and piwiplus.fr - **Canvas** - **CanvasEen**: canvas.be and een.be - **CarambaTV** @@ -210,6 +210,7 @@ - **defense.gouv.fr** - **democracynow** - **DHM**: Filmarchiv - Deutsches Historisches Museum + - **Digg** - **DigitallySpeaking** - **Digiteka** - **Discovery** @@ -773,7 +774,6 @@ - **Sport5** - **SportBoxEmbed** - **SportDeutschland** - - **Sportschau** - **Sprout** - **sr:mediathek**: Saarländischer Rundfunk - **SRGSSR** @@ -1002,10 +1002,14 @@ - **WatchIndianPorn**: Watch Indian Porn - **WDR** - **wdr:mobile** + - **WDRElefant** + - **WDRPage** - **Webcaster** - **WebcasterFeed** - **WebOfStories** - **WebOfStoriesPlaylist** + - **Weibo** + - **WeiboMobile** - **WeiqiTV**: WQTV - **wholecloud**: WholeCloud - **Wimp** @@ -1025,6 +1029,8 @@ - **xiami:artist**: 虾米音乐 - 歌手 - **xiami:collection**: 虾米音乐 - 精选集 - **xiami:song**: 虾米音乐 + - **ximalaya**: 喜马拉雅FM + - **ximalaya:album**: 喜马拉雅FM 专辑 - **XMinus** - **XNXX** - **Xstream** diff --git a/youtube_dl/extractor/digg.py b/youtube_dl/extractor/digg.py new file mode 100644 index 000000000..913c1750f --- /dev/null +++ b/youtube_dl/extractor/digg.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import js_to_json + + +class DiggIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?digg\.com/video/(?P[^/?#&]+)' + _TESTS = [{ + # JWPlatform via provider + 'url': 'http://digg.com/video/sci-fi-short-jonah-daniel-kaluuya-get-out', + 'info_dict': { + 'id': 'LcqvmS0b', + 'ext': 'mp4', + 'title': "'Get Out' Star Daniel Kaluuya Goes On 'Moby Dick'-Like Journey In Sci-Fi Short 'Jonah'", + 'description': 'md5:541bb847648b6ee3d6514bc84b82efda', + 'upload_date': '20180109', + 'timestamp': 1515530551, + }, + 'params': { + 'skip_download': True, + }, + }, { + # Youtube via provider + 'url': 'http://digg.com/video/dog-boat-seal-play', + 'only_matching': True, + }, { + # vimeo as regular embed + 'url': 'http://digg.com/video/dream-girl-short-film', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + info = self._parse_json( + self._search_regex( + r'(?s)video_info\s*=\s*({.+?});\n', webpage, 'video info', + default='{}'), display_id, transform_source=js_to_json, + fatal=False) + + video_id = info.get('video_id') + + if video_id: + provider = info.get('provider_name') + if provider == 'youtube': + return self.url_result( + video_id, ie='Youtube', video_id=video_id) + elif provider == 'jwplayer': + return self.url_result( + 'jwplatform:%s' % video_id, ie='JWPlatform', + video_id=video_id) + + return self.url_result(url, 'Generic') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a3ad4df1f..c82614bf9 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -259,6 +259,7 @@ from .deezer import DeezerPlaylistIE from .democracynow import DemocracynowIE from .dfb import DFBIE from .dhm import DHMIE +from .digg import DiggIE from .dotsub import DotsubIE from .douyutv import ( DouyuShowIE, @@ -990,7 +991,6 @@ from .stitcher import StitcherIE from .sport5 import Sport5IE from .sportbox import SportBoxEmbedIE from .sportdeutschland import SportDeutschlandIE -from .sportschau import SportschauIE from .sprout import SproutIE from .srgssr import ( SRGSSRIE, @@ -1288,6 +1288,8 @@ from .watchbox import WatchBoxIE from .watchindianporn import WatchIndianPornIE from .wdr import ( WDRIE, + WDRPageIE, + WDRElefantIE, WDRMobileIE, ) from .webcaster import ( @@ -1327,6 +1329,10 @@ from .xiami import ( XiamiArtistIE, XiamiCollectionIE ) +from .ximalaya import ( + XimalayaIE, + XimalayaAlbumIE +) from .xminus import XMinusIE from .xnxx import XNXXIE from .xstream import XstreamIE diff --git a/youtube_dl/extractor/gamestar.py b/youtube_dl/extractor/gamestar.py index e607d6ab8..f00dab2f3 100644 --- a/youtube_dl/extractor/gamestar.py +++ b/youtube_dl/extractor/gamestar.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( int_or_none, @@ -9,27 +11,34 @@ from ..utils import ( class GameStarIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gamestar\.de/videos/.*,(?P[0-9]+)\.html' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?game(?Ppro|star)\.de/videos/.*,(?P[0-9]+)\.html' + _TESTS = [{ 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html', - 'md5': '96974ecbb7fd8d0d20fca5a00810cea7', + 'md5': 'ee782f1f8050448c95c5cacd63bc851c', 'info_dict': { 'id': '76110', 'ext': 'mp4', 'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil', 'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...', 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1406542020, + 'timestamp': 1406542380, 'upload_date': '20140728', - 'duration': 17 + 'duration': 17, } - } + }, { + 'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html', + 'only_matching': True, + }, { + 'url': 'http://www.gamestar.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html', + 'only_matching': True, + }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') + video_id = mobj.group('id') - url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id + webpage = self._download_webpage(url, video_id) # TODO: there are multiple ld+json objects in the webpage, # while _search_json_ld finds only the first one @@ -37,16 +46,17 @@ class GameStarIE(InfoExtractor): r'(?s)]+type=(["\'])application/ld\+json\1[^>]*>(?P[^<]+VideoObject[^<]+)', webpage, 'JSON-LD', group='json_ld'), video_id) info_dict = self._json_ld(json_ld, video_id) - info_dict['title'] = remove_end(info_dict['title'], ' - GameStar') + info_dict['title'] = remove_end( + info_dict['title'], ' - Game%s' % site.title()) - view_count = json_ld.get('interactionCount') + view_count = int_or_none(json_ld.get('interactionCount')) comment_count = int_or_none(self._html_search_regex( - r'([0-9]+) Kommentare', webpage, 'comment_count', - fatal=False)) + r'Kommentare\s*]+class=["\']count[^>]+>\s*\(\s*([0-9]+)', + webpage, 'comment count', fatal=False)) info_dict.update({ 'id': video_id, - 'url': url, + 'url': 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id, 'ext': 'mp4', 'view_count': view_count, 'comment_count': comment_count diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index ad65b2759..2803d7e8d 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -10,6 +10,7 @@ from ..utils import ( float_or_none, int_or_none, smuggle_url, + try_get, unsmuggle_url, ExtractorError, ) @@ -220,6 +221,12 @@ class LimelightBaseIE(InfoExtractor): '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' @@ -282,10 +289,7 @@ class LimelightMediaIE(LimelightBaseIE): 'getMobilePlaylistByMediaId', 'properties', smuggled_data.get('source_url')) - return self._extract_info( - pc['playlistItems'][0].get('streams', []), - mobile['mediaList'][0].get('mobileUrls', []) if mobile else [], - metadata) + return self._extract_info_helper(pc, mobile, 0, metadata) class LimelightChannelIE(LimelightBaseIE): @@ -326,10 +330,7 @@ class LimelightChannelIE(LimelightBaseIE): 'media', smuggled_data.get('source_url')) entries = [ - self._extract_info( - pc['playlistItems'][i].get('streams', []), - mobile['mediaList'][i].get('mobileUrls', []) if mobile else [], - medias['media_list'][i]) + self._extract_info_helper(pc, mobile, i, medias['media_list'][i]) for i in range(len(medias['media_list']))] return self.playlist_result(entries, channel_id, pc['title']) diff --git a/youtube_dl/extractor/pandoratv.py b/youtube_dl/extractor/pandoratv.py index fc7bd3411..538738c09 100644 --- a/youtube_dl/extractor/pandoratv.py +++ b/youtube_dl/extractor/pandoratv.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_str, @@ -18,7 +20,14 @@ from ..utils import ( class PandoraTVIE(InfoExtractor): IE_NAME = 'pandora.tv' IE_DESC = '판도라TV' - _VALID_URL = r'https?://(?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?pandora\.tv/view/(?P[^/]+)/(?P\d+)| # new format + (?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?| # old format + m\.pandora\.tv/?\? # mobile + ) + ''' _TESTS = [{ 'url': 'http://jp.channel.pandora.tv/channel/video.ptv?c1=&prgid=53294230&ch_userid=mikakim&ref=main&lot=cate_01_2', 'info_dict': { @@ -53,14 +62,25 @@ class PandoraTVIE(InfoExtractor): # Test metadata only 'skip_download': True, }, + }, { + 'url': 'http://www.pandora.tv/view/mikakim/53294230#36797454_new', + 'only_matching': True, + }, { + 'url': 'http://m.pandora.tv/?c=view&ch_userid=mikakim&prgid=54600346', + 'only_matching': True, }] def _real_extract(self, url): - qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - video_id = qs.get('prgid', [None])[0] - user_id = qs.get('ch_userid', [None])[0] - if any(not f for f in (video_id, user_id,)): - raise ExtractorError('Invalid URL', expected=True) + mobj = re.match(self._VALID_URL, url) + user_id = mobj.group('user_id') + video_id = mobj.group('id') + + if not user_id or not video_id: + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + video_id = qs.get('prgid', [None])[0] + user_id = qs.get('ch_userid', [None])[0] + if any(not f for f in (video_id, user_id,)): + raise ExtractorError('Invalid URL', expected=True) data = self._download_json( 'http://m.pandora.tv/?c=view&m=viewJsonApi&ch_userid=%s&prgid=%s' diff --git a/youtube_dl/extractor/sportschau.py b/youtube_dl/extractor/sportschau.py deleted file mode 100644 index 0d7925a08..000000000 --- a/youtube_dl/extractor/sportschau.py +++ /dev/null @@ -1,38 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .wdr import WDRBaseIE -from ..utils import get_element_by_attribute - - -class SportschauIE(WDRBaseIE): - IE_NAME = 'Sportschau' - _VALID_URL = r'https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video-?(?P[^/#?]+)\.html' - _TEST = { - 'url': 'http://www.sportschau.de/uefaeuro2016/videos/video-dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100.html', - 'info_dict': { - 'id': 'mdb-1140188', - 'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100', - 'ext': 'mp4', - 'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen', - 'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.', - 'upload_date': '20160615', - }, - 'skip': 'Geo-restricted to Germany', - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - title = get_element_by_attribute('class', 'headline', webpage) - description = self._html_search_meta('description', webpage, 'description') - - info = self._extract_wdr_video(webpage, video_id) - - info.update({ - 'title': title, - 'description': description, - }) - - return info diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 46132eda1..84597b55e 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -273,6 +273,8 @@ class TVPlayIE(InfoExtractor): 'ext': ext, } if video_url.startswith('rtmp'): + if smuggled_data.get('skip_rtmp'): + continue m = re.search( r'^(?Prtmp://[^/]+/(?P[^/]+))/(?P.+)$', video_url) if not m: @@ -434,6 +436,10 @@ class ViafreeIE(InfoExtractor): return self.url_result( smuggle_url( 'mtg:%s' % video_id, - {'geo_countries': [ - compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]]}), + { + '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) diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 621de1e1e..cf6f7c7ed 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -4,49 +4,50 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urlparse, +) from ..utils import ( determine_ext, ExtractorError, js_to_json, strip_jsonp, + try_get, unified_strdate, update_url_query, urlhandle_detect_ext, ) -class WDRBaseIE(InfoExtractor): - def _extract_wdr_video(self, webpage, display_id): - # for wdr.de the data-extension is in a tag with the class "mediaLink" - # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn" - # for wdrmaus, in a tag with the class "videoButton" (previously a link - # to the page in a multiline "videoLink"-tag) - json_metadata = self._html_search_regex( - r'''(?sx)class= - (?: - (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+| - (["\'])videoLink\b.*?\2[\s]*>\n[^\n]* - )data-extension=(["\'])(?P(?:(?!\3).)+)\3 - ''', - webpage, 'media link', default=None, group='data') +class WDRIE(InfoExtractor): + _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P\d+)\.js' + _GEO_COUNTRIES = ['DE'] + _TEST = { + 'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js', + 'info_dict': { + 'id': 'mdb-1557833', + 'ext': 'mp4', + 'title': 'Biathlon-Staffel verpasst Podest bei Olympia-Generalprobe', + 'upload_date': '20180112', + }, + } - if not json_metadata: - return - - media_link_obj = self._parse_json(json_metadata, display_id, - transform_source=js_to_json) - jsonp_url = media_link_obj['mediaObj']['url'] + def _real_extract(self, url): + video_id = self._match_id(url) metadata = self._download_json( - jsonp_url, display_id, transform_source=strip_jsonp) + url, video_id, transform_source=strip_jsonp) - metadata_tracker_data = metadata['trackerData'] - metadata_media_resource = metadata['mediaResource'] + is_live = metadata.get('mediaType') == 'live' + + tracker_data = metadata['trackerData'] + media_resource = metadata['mediaResource'] formats = [] # check if the metadata contains a direct URL to a file - for kind, media_resource in metadata_media_resource.items(): + for kind, media_resource in media_resource.items(): if kind not in ('dflt', 'alt'): continue @@ -57,13 +58,13 @@ class WDRBaseIE(InfoExtractor): ext = determine_ext(medium_url) if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - medium_url, display_id, 'mp4', 'm3u8_native', + medium_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')) elif ext == 'f4m': manifest_url = update_url_query( medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'}) formats.extend(self._extract_f4m_formats( - manifest_url, display_id, f4m_id='hds', fatal=False)) + manifest_url, video_id, f4m_id='hds', fatal=False)) elif ext == 'smil': formats.extend(self._extract_smil_formats( medium_url, 'stream', fatal=False)) @@ -73,7 +74,7 @@ class WDRBaseIE(InfoExtractor): } if ext == 'unknown_video': urlh = self._request_webpage( - medium_url, display_id, note='Determining extension') + medium_url, video_id, note='Determining extension') ext = urlhandle_detect_ext(urlh) a_format['ext'] = ext formats.append(a_format) @@ -81,30 +82,30 @@ class WDRBaseIE(InfoExtractor): self._sort_formats(formats) subtitles = {} - caption_url = metadata_media_resource.get('captionURL') + caption_url = media_resource.get('captionURL') if caption_url: subtitles['de'] = [{ 'url': caption_url, 'ext': 'ttml', }] - title = metadata_tracker_data['trackerClipTitle'] + title = tracker_data['trackerClipTitle'] return { - 'id': metadata_tracker_data.get('trackerClipId', display_id), - 'display_id': display_id, - 'title': title, - 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'), + 'id': tracker_data.get('trackerClipId', video_id), + 'title': self._live_title(title) if is_live else title, + 'alt_title': tracker_data.get('trackerClipSubcategory'), 'formats': formats, 'subtitles': subtitles, - 'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')), + 'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')), + 'is_live': is_live, } -class WDRIE(WDRBaseIE): +class WDRPageIE(InfoExtractor): _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5' - _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P[^/]+)/(?P.+)\.html' - _VALID_URL = r'(?Phttps?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL + _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P[^/]+)\.html' + _VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL _TESTS = [ { @@ -124,6 +125,7 @@ class WDRIE(WDRBaseIE): 'ext': 'ttml', }]}, }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html', @@ -139,19 +141,17 @@ class WDRIE(WDRBaseIE): 'is_live': False, 'subtitles': {} }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://www1.wdr.de/mediathek/video/live/index.html', 'info_dict': { - 'id': 'mdb-103364', + 'id': 'mdb-1406149', 'ext': 'mp4', - 'display_id': 'index', - 'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'title': r're:^WDR Fernsehen im Livestream \(nur in Deutschland erreichbar\) [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'alt_title': 'WDR Fernsehen Live', - 'upload_date': None, - 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', + 'upload_date': '20150101', 'is_live': True, - 'subtitles': {} }, 'params': { 'skip_download': True, # m3u8 download @@ -159,19 +159,18 @@ class WDRIE(WDRBaseIE): }, { 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html', - 'playlist_mincount': 8, + 'playlist_mincount': 7, 'info_dict': { - 'id': 'aktuelle-stunde/aktuelle-stunde-120', + 'id': 'aktuelle-stunde-120', }, }, { 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5', 'info_dict': { - 'id': 'mdb-1323501', + 'id': 'mdb-1552552', 'ext': 'mp4', 'upload_date': 're:^[0-9]{8}$', 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$', - 'description': 'Die Seite mit der Maus -', }, 'skip': 'The id changes from week to week because of the new episode' }, @@ -183,7 +182,6 @@ class WDRIE(WDRBaseIE): 'ext': 'mp4', 'upload_date': '20130919', 'title': 'Sachgeschichte - Achterbahn ', - 'description': 'Die Seite mit der Maus -', }, }, { @@ -191,52 +189,114 @@ class WDRIE(WDRBaseIE): # Live stream, MD5 unstable 'info_dict': { 'id': 'mdb-869971', - 'ext': 'flv', - 'title': 'COSMO Livestream', - 'description': 'md5:2309992a6716c347891c045be50992e4', + 'ext': 'mp4', + 'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'upload_date': '20160101', }, + 'params': { + 'skip_download': True, # m3u8 download + } + }, + { + 'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html', + 'info_dict': { + 'id': 'mdb-1556012', + 'ext': 'mp4', + 'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"', + 'upload_date': '20180111', + }, + 'params': { + 'skip_download': True, + }, + }, + { + 'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html', + 'only_matching': True, } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - url_type = mobj.group('type') - page_url = mobj.group('page_url') display_id = mobj.group('display_id') webpage = self._download_webpage(url, display_id) - info_dict = self._extract_wdr_video(webpage, display_id) + entries = [] - if not info_dict: + # Article with several videos + + # for wdr.de the data-extension is in a tag with the class "mediaLink" + # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn" + # for wdrmaus, in a tag with the class "videoButton" (previously a link + # to the page in a multiline "videoLink"-tag) + for mobj in re.finditer( + r'''(?sx)class= + (?: + (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+| + (["\'])videoLink\b.*?\2[\s]*>\n[^\n]* + )data-extension=(["\'])(?P(?:(?!\3).)+)\3 + ''', webpage): + media_link_obj = self._parse_json( + mobj.group('data'), display_id, transform_source=js_to_json, + fatal=False) + if not media_link_obj: + continue + jsonp_url = try_get( + media_link_obj, lambda x: x['mediaObj']['url'], compat_str) + if jsonp_url: + entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key())) + + # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html) + if not entries: entries = [ - self.url_result(page_url + href[0], 'WDR') - for href in re.findall( - r']+data-extension=' % self._PAGE_REGEX, - webpage) + self.url_result( + compat_urlparse.urljoin(url, mobj.group('href')), + ie=WDRPageIE.ie_key()) + for mobj in re.finditer( + r']+\bhref=(["\'])(?P(?:(?!\1).)+)\1[^>]+\bdata-extension=', + webpage) if re.match(self._PAGE_REGEX, mobj.group('href')) ] - if entries: # Playlist page - return self.playlist_result(entries, playlist_id=display_id) + return self.playlist_result(entries, playlist_id=display_id) - raise ExtractorError('No downloadable streams found', expected=True) - is_live = url_type == 'live' +class WDRElefantIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P.+)' + _TEST = { + 'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015', + 'info_dict': { + 'title': 'Folge Oster-Spezial 2015', + 'id': 'mdb-1088195', + 'ext': 'mp4', + 'age_limit': None, + 'upload_date': '20150406' + }, + 'params': { + 'skip_download': True, + }, + } - if is_live: - info_dict.update({ - 'title': self._live_title(info_dict['title']), - 'upload_date': None, - }) - elif 'upload_date' not in info_dict: - info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date')) + def _real_extract(self, url): + display_id = self._match_id(url) - info_dict.update({ - 'description': self._html_search_meta('Description', webpage), - 'is_live': is_live, - }) - - return info_dict + # Table of Contents seems to always be at this address, so fetch it directly. + # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5. + table_of_contents = self._download_json( + 'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5', + display_id) + if display_id not in table_of_contents: + raise ExtractorError( + 'No entry in site\'s table of contents for this URL. ' + 'Is the fragment part of the URL (after the #) correct?', + expected=True) + xml_metadata_path = table_of_contents[display_id]['xmlPath'] + xml_metadata = self._download_xml( + 'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path, + display_id) + zmdb_url_element = xml_metadata.find('./movie/zmdb_url') + if zmdb_url_element is None: + raise ExtractorError( + '%s is not a video' % display_id, expected=True) + return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key()) class WDRMobileIE(InfoExtractor): diff --git a/youtube_dl/extractor/ximalaya.py b/youtube_dl/extractor/ximalaya.py new file mode 100644 index 000000000..a912e54b8 --- /dev/null +++ b/youtube_dl/extractor/ximalaya.py @@ -0,0 +1,233 @@ +# coding: utf-8 + +from __future__ import unicode_literals + +import itertools +import re + +from .common import InfoExtractor + + +class XimalayaBaseIE(InfoExtractor): + _GEO_COUNTRIES = ['CN'] + + +class XimalayaIE(XimalayaBaseIE): + IE_NAME = 'ximalaya' + IE_DESC = '喜马拉雅FM' + _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?P[0-9]+)/sound/(?P[0-9]+)' + _USER_URL_FORMAT = '%s://www.ximalaya.com/zhubo/%i/' + _TESTS = [ + { + 'url': 'http://www.ximalaya.com/61425525/sound/47740352/', + 'info_dict': { + 'id': '47740352', + 'ext': 'm4a', + 'uploader': '小彬彬爱听书', + 'uploader_id': 61425525, + 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/', + 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白', + 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。", + 'thumbnails': [ + { + 'name': 'cover_url', + 'url': r're:^https?://.*\.jpg$', + }, + { + 'name': 'cover_url_142', + 'url': r're:^https?://.*\.jpg$', + 'width': 180, + 'height': 180 + } + ], + 'categories': ['renwen', '人文'], + 'duration': 93, + 'view_count': int, + 'like_count': int, + } + }, + { + 'url': 'http://m.ximalaya.com/61425525/sound/47740352/', + 'info_dict': { + 'id': '47740352', + 'ext': 'm4a', + 'uploader': '小彬彬爱听书', + 'uploader_id': 61425525, + 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/', + 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白', + 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。", + 'thumbnails': [ + { + 'name': 'cover_url', + 'url': r're:^https?://.*\.jpg$', + }, + { + 'name': 'cover_url_142', + 'url': r're:^https?://.*\.jpg$', + 'width': 180, + 'height': 180 + } + ], + 'categories': ['renwen', '人文'], + 'duration': 93, + 'view_count': int, + 'like_count': int, + } + }, + { + 'url': 'https://www.ximalaya.com/11045267/sound/15705996/', + 'info_dict': { + 'id': '15705996', + 'ext': 'm4a', + 'uploader': '李延隆老师', + 'uploader_id': 11045267, + 'uploader_url': 'https://www.ximalaya.com/zhubo/11045267/', + 'title': 'Lesson 1 Excuse me!', + 'description': "contains:Listen to the tape then answer\xa0this question. Whose handbag is it?\n" + "听录音，然后回答问题，这是谁的手袋？", + 'thumbnails': [ + { + 'name': 'cover_url', + 'url': r're:^https?://.*\.jpg$', + }, + { + 'name': 'cover_url_142', + 'url': r're:^https?://.*\.jpg$', + 'width': 180, + 'height': 180 + } + ], + 'categories': ['train', '外语'], + 'duration': 40, + 'view_count': int, + 'like_count': int, + } + }, + ] + + def _real_extract(self, url): + + is_m = 'm.ximalaya' in url + scheme = 'https' if url.startswith('https') else 'http' + + audio_id = self._match_id(url) + webpage = self._download_webpage(url, audio_id, + note='Download sound page for %s' % audio_id, + errnote='Unable to get sound page') + + audio_info_file = '%s://m.ximalaya.com/tracks/%s.json' % (scheme, audio_id) + audio_info = self._download_json(audio_info_file, audio_id, + 'Downloading info json %s' % audio_info_file, + 'Unable to download info file') + + formats = [] + for bps, k in (('24k', 'play_path_32'), ('64k', 'play_path_64')): + if audio_info.get(k): + formats.append({ + 'format_id': bps, + 'url': audio_info[k], + }) + + thumbnails = [] + for k in audio_info.keys(): + # cover pics kyes like: cover_url', 'cover_url_142' + if k.startswith('cover_url'): + thumbnail = {'name': k, 'url': audio_info[k]} + if k == 'cover_url_142': + thumbnail['width'] = 180 + thumbnail['height'] = 180 + thumbnails.append(thumbnail) + + audio_uploader_id = audio_info.get('uid') + + if is_m: + audio_description = self._html_search_regex(r'(?s)]+>(.+?)', + webpage, 'audio_description', fatal=False) + else: + audio_description = self._html_search_regex(r'(?s)]*>(.+?)', + webpage, 'audio_description', fatal=False) + + if not audio_description: + audio_description_file = '%s://www.ximalaya.com/sounds/%s/rich_intro' % (scheme, audio_id) + audio_description = self._download_webpage(audio_description_file, audio_id, + note='Downloading description file %s' % audio_description_file, + errnote='Unable to download descrip file', + fatal=False) + audio_description = audio_description.strip() if audio_description else None + + return { + 'id': audio_id, + 'uploader': audio_info.get('nickname'), + 'uploader_id': audio_uploader_id, + 'uploader_url': self._USER_URL_FORMAT % (scheme, audio_uploader_id) if audio_uploader_id else None, + 'title': audio_info['title'], + 'thumbnails': thumbnails, + 'description': audio_description, + 'categories': list(filter(None, (audio_info.get('category_name'), audio_info.get('category_title')))), + 'duration': audio_info.get('duration'), + 'view_count': audio_info.get('play_count'), + 'like_count': audio_info.get('favorites_count'), + 'formats': formats, + } + + +class XimalayaAlbumIE(XimalayaBaseIE): + IE_NAME = 'ximalaya:album' + IE_DESC = '喜马拉雅FM 专辑' + _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?P[0-9]+)/album/(?P[0-9]+)' + _TEMPLATE_URL = '%s://www.ximalaya.com/%s/album/%s/' + _BASE_URL_TEMPL = '%s://www.ximalaya.com%s' + _LIST_VIDEO_RE = r']+?href="(?P/%s/sound/(?P\d+)/?)"[^>]+?title="(?P[^>]+)">' + _TESTS = [{ + 'url': 'http://www.ximalaya.com/61425525/album/5534601/', + 'info_dict': { + 'title': '唐诗三百首（含赏析）', + 'id': '5534601', + }, + 'playlist_count': 312, + }, { + 'url': 'http://m.ximalaya.com/61425525/album/5534601', + 'info_dict': { + 'title': '唐诗三百首（含赏析）', + 'id': '5534601', + }, + 'playlist_count': 312, + }, + ] + + def _real_extract(self, url): + self.scheme = scheme = 'https' if url.startswith('https') else 'http' + + mobj = re.match(self._VALID_URL, url) + uid, playlist_id = mobj.group('uid'), mobj.group('id') + + webpage = self._download_webpage(self._TEMPLATE_URL % (scheme, uid, playlist_id), playlist_id, + note='Download album page for %s' % playlist_id, + errnote='Unable to get album info') + + title = self._html_search_regex(r'detailContent_title[^>]*><h1(?:[^>]+)?>([^<]+)</h1>', + webpage, 'title', fatal=False) + + return self.playlist_result(self._entries(webpage, playlist_id, uid), playlist_id, title) + + def _entries(self, page, playlist_id, uid): + html = page + for page_num in itertools.count(1): + for entry in self._process_page(html, uid): + yield entry + + next_url = self._search_regex(r'<a\s+href=(["\'])(?P<more>[\S]+)\1[^>]+rel=(["\'])next\3', + html, 'list_next_url', default=None, group='more') + if not next_url: + break + + next_full_url = self._BASE_URL_TEMPL % (self.scheme, next_url) + html = self._download_webpage(next_full_url, playlist_id) + + def _process_page(self, html, uid): + find_from = html.index('album_soundlist') + for mobj in re.finditer(self._LIST_VIDEO_RE % uid, html[find_from:]): + yield self.url_result(self._BASE_URL_TEMPL % (self.scheme, mobj.group('url')), + XimalayaIE.ie_key(), + mobj.group('id'), + mobj.group('title')) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 0919bef0e..a01ec1436 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1810,7 +1810,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': video_info['conn'][0], 'player_url': player_url, }] - elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: + elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 9030e2415..498149110 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2018.01.07' +__version__ = '2018.01.14'