From 33a4446c892128076a3102c0b24d500867100fef Mon Sep 17 00:00:00 2001 From: jbuzzard Date: Fri, 13 May 2016 16:08:26 -0700 Subject: [PATCH 01/13] add "--no-generic-extractor" flag which excludes usage of the generic extractor when processing a url. --- youtube_dl/YoutubeDL.py | 9 +++++++-- youtube_dl/__init__.py | 1 + youtube_dl/options.py | 4 ++++ 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 03a6a1890..5611aacd3 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -150,6 +150,7 @@ class YoutubeDL(object): restrictfilenames: Do not allow "&" and spaces in file names ignoreerrors: Do not stop on download errors. force_generic_extractor: Force downloader to use the generic extractor + no_generic_extractor: Prevent usage of the generic extractor nooverwrites: Prevent overwriting files. playliststart: Playlist item to start at. playlistend: Playlist item to end at. @@ -648,7 +649,7 @@ class YoutubeDL(object): info_dict.setdefault(key, value) def extract_info(self, url, download=True, ie_key=None, extra_info={}, - process=True, force_generic_extractor=False): + process=True, force_generic_extractor=False, no_generic_extractor=False): ''' Returns a list with a dictionary for each video we find. If 'download', also downloads the videos. @@ -664,6 +665,8 @@ class YoutubeDL(object): ies = self._ies for ie in ies: + if(ie.ie_key() == "Generic" and no_generic_extractor): + continue if not ie.suitable(url): continue @@ -1733,7 +1736,9 @@ class YoutubeDL(object): try: # It also downloads the videos res = self.extract_info( - url, force_generic_extractor=self.params.get('force_generic_extractor', False)) + url, + force_generic_extractor=self.params.get('force_generic_extractor', False), + no_generic_extractor=self.params.get('no_generic_extractor', False)) except UnavailableVideoError: self.report_error('unable to download video') except MaxDownloadsReached: diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 5df965191..135356e0a 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -305,6 +305,7 @@ def _real_main(argv=None): 'restrictfilenames': opts.restrictfilenames, 'ignoreerrors': opts.ignoreerrors, 'force_generic_extractor': opts.force_generic_extractor, + 'no_generic_extractor': opts.no_generic_extractor, 'ratelimit': opts.ratelimit, 'nooverwrites': opts.nooverwrites, 'retries': opts.retries, diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 38efd292d..c6378cb22 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -154,6 +154,10 @@ def parseOpts(overrideArguments=None): '--force-generic-extractor', action='store_true', dest='force_generic_extractor', default=False, help='Force extraction to use the generic extractor') + general.add_option( + '--no-generic-extractor', + action='store_true', dest='no_generic_extractor', default=False, + help='prevent extraction from using the generic extractor') general.add_option( '--default-search', dest='default_search', metavar='PREFIX', From aa9c2c158d19b42a00b353ac46e84c82cc949095 Mon Sep 17 00:00:00 2001 From: jbuzzard Date: Tue, 17 May 2016 11:16:11 -0700 Subject: [PATCH 02/13] Make first character of command line option description upper case --- youtube_dl/options.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/options.py b/youtube_dl/options.py index c6378cb22..9d63be88f 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -157,7 +157,7 @@ def parseOpts(overrideArguments=None): general.add_option( '--no-generic-extractor', action='store_true', dest='no_generic_extractor', default=False, - help='prevent extraction from using the generic extractor') + help='Prevent extraction from using the generic extractor') general.add_option( '--default-search', dest='default_search', metavar='PREFIX', From 215d827a48b5177082d244bd2ada1dcc433e8bb8 Mon Sep 17 00:00:00 2001 From: jbuzzard Date: Tue, 17 May 2016 11:17:31 -0700 Subject: [PATCH 03/13] It's idiomatic not to use parentheses in if statement. Also use single quotes consistently. --- youtube_dl/YoutubeDL.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 5611aacd3..8afcd30fc 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -665,7 +665,7 @@ class YoutubeDL(object): ies = self._ies for ie in ies: - if(ie.ie_key() == "Generic" and no_generic_extractor): + if ie.ie_key() == 'Generic' and no_generic_extractor: continue if not ie.suitable(url): continue From c1613a9814a22da604cfb2c159a36ea416747a89 Mon Sep 17 00:00:00 2001 From: jbuzzard Date: Fri, 3 Jun 2016 11:25:42 -0700 Subject: [PATCH 04/13] Update --no-generic-extractor flag description to better describe its behavior --- youtube_dl/options.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 9d63be88f..29b07f00d 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -157,7 +157,7 @@ def parseOpts(overrideArguments=None): general.add_option( '--no-generic-extractor', action='store_true', dest='no_generic_extractor', default=False, - help='Prevent extraction from using the generic extractor') + help='Omit generic extractor from extractor search') general.add_option( '--default-search', dest='default_search', metavar='PREFIX', From 67d2737c23e23949908c2c9a3f2434f123a02b1f Mon Sep 17 00:00:00 2001 From: jbuzzard Date: Mon, 1 Aug 2016 13:17:17 -0700 Subject: [PATCH 05/13] Synchronized with upsteam repository --- .github/ISSUE_TEMPLATE.md | 6 +- .github/PULL_REQUEST_TEMPLATE.md | 22 + .gitignore | 6 +- .travis.yml | 4 - AUTHORS | 7 + CONTRIBUTING.md | 154 +- ChangeLog | 271 +++ Makefile | 8 +- README.md | 229 +- devscripts/buildserver.py | 75 +- devscripts/create-github-release.py | 111 + devscripts/gh-pages/generate-download.py | 4 - devscripts/install_srelay.sh | 8 - devscripts/make_lazy_extractors.py | 47 +- devscripts/prepare_manpage.py | 61 +- devscripts/release.sh | 56 +- devscripts/show-downloads-statistics.py | 47 + docs/supportedsites.md | 99 +- setup.py | 62 +- test/test_InfoExtractor.py | 7 +- test/test_YoutubeDL.py | 34 + test/test_all_urls.py | 12 +- test/test_compat.py | 8 + test/test_http.py | 73 +- test/test_socks.py | 11 + test/test_utils.py | 116 +- youtube_dl/YoutubeDL.py | 77 +- youtube_dl/__init__.py | 11 +- youtube_dl/compat.py | 2274 +++++++++++++++++++- youtube_dl/downloader/external.py | 3 +- youtube_dl/downloader/f4m.py | 13 +- youtube_dl/downloader/hls.py | 90 +- youtube_dl/extractor/abcnews.py | 135 ++ youtube_dl/extractor/adobetv.py | 5 +- youtube_dl/extractor/aenetworks.py | 208 +- youtube_dl/extractor/afreecatv.py | 133 ++ youtube_dl/extractor/aftonbladet.py | 4 +- youtube_dl/extractor/amp.py | 20 +- youtube_dl/extractor/animeondemand.py | 110 +- youtube_dl/extractor/anvato.py | 224 ++ youtube_dl/extractor/appletrailers.py | 53 +- youtube_dl/extractor/ard.py | 69 +- youtube_dl/extractor/arkena.py | 115 + youtube_dl/extractor/arte.py | 205 +- youtube_dl/extractor/audiomack.py | 3 +- youtube_dl/extractor/azubu.py | 19 +- youtube_dl/extractor/bandcamp.py | 8 +- youtube_dl/extractor/bbc.py | 106 +- youtube_dl/extractor/bet.py | 96 +- youtube_dl/extractor/bigflix.py | 4 +- youtube_dl/extractor/bilibili.py | 205 +- youtube_dl/extractor/biobiochiletv.py | 53 +- youtube_dl/extractor/bloomberg.py | 19 +- youtube_dl/extractor/br.py | 9 +- youtube_dl/extractor/brightcove.py | 56 +- youtube_dl/extractor/buzzfeed.py | 32 +- youtube_dl/extractor/byutv.py | 4 +- youtube_dl/extractor/camdemy.py | 64 +- youtube_dl/extractor/canalplus.py | 86 +- youtube_dl/extractor/carambatv.py | 88 + youtube_dl/extractor/cbc.py | 139 +- youtube_dl/extractor/cbs.py | 83 +- youtube_dl/extractor/cbsinteractive.py | 5 +- youtube_dl/extractor/cbslocal.py | 84 + youtube_dl/extractor/cbsnews.py | 44 +- youtube_dl/extractor/cbssports.py | 40 +- youtube_dl/extractor/cda.py | 6 +- youtube_dl/extractor/channel9.py | 123 +- youtube_dl/extractor/cinemassacre.py | 119 - youtube_dl/extractor/cliphunter.py | 17 +- youtube_dl/extractor/cliprs.py | 73 +- youtube_dl/extractor/closertotruth.py | 92 + youtube_dl/extractor/cloudy.py | 48 +- youtube_dl/extractor/cmt.py | 22 + youtube_dl/extractor/collegehumor.py | 101 - youtube_dl/extractor/comedycentral.py | 290 +-- youtube_dl/extractor/common.py | 314 ++- youtube_dl/extractor/coub.py | 143 ++ youtube_dl/extractor/cspan.py | 5 +- youtube_dl/extractor/ctv.py | 30 + youtube_dl/extractor/ctvnews.py | 65 + youtube_dl/extractor/cwtv.py | 8 +- youtube_dl/extractor/dailymail.py | 15 +- youtube_dl/extractor/dailymotion.py | 19 +- youtube_dl/extractor/daum.py | 20 +- youtube_dl/extractor/dbtv.py | 69 +- youtube_dl/extractor/dcn.py | 45 +- youtube_dl/extractor/dreisat.py | 6 +- youtube_dl/extractor/dw.py | 29 +- youtube_dl/extractor/eagleplatform.py | 8 + youtube_dl/extractor/ellentv.py | 50 +- youtube_dl/extractor/eporner.py | 92 +- youtube_dl/extractor/espn.py | 6 +- youtube_dl/extractor/extractors.py | 128 +- youtube_dl/extractor/eyedotv.py | 64 + youtube_dl/extractor/facebook.py | 43 +- youtube_dl/extractor/flipagram.py | 115 + youtube_dl/extractor/formula1.py | 26 + youtube_dl/extractor/foxsports.py | 20 +- youtube_dl/extractor/francetv.py | 28 +- youtube_dl/extractor/fusion.py | 35 + youtube_dl/extractor/gamespot.py | 98 +- youtube_dl/extractor/gametrailers.py | 62 - youtube_dl/extractor/generic.py | 449 +++- youtube_dl/extractor/godtv.py | 66 + youtube_dl/extractor/groupon.py | 35 +- youtube_dl/extractor/hearthisat.py | 40 +- youtube_dl/extractor/howcast.py | 4 +- youtube_dl/extractor/hrti.py | 202 ++ youtube_dl/extractor/imdb.py | 8 +- youtube_dl/extractor/indavideo.py | 3 +- youtube_dl/extractor/instagram.py | 73 +- youtube_dl/extractor/iqiyi.py | 369 +--- youtube_dl/extractor/jwplatform.py | 53 +- youtube_dl/extractor/kaltura.py | 75 +- youtube_dl/extractor/kamcord.py | 71 + youtube_dl/extractor/kuwo.py | 15 +- youtube_dl/extractor/la7.py | 83 +- youtube_dl/extractor/lcp.py | 90 + youtube_dl/extractor/learnr.py | 33 + youtube_dl/extractor/leeco.py | 155 +- youtube_dl/extractor/libraryofcongress.py | 143 ++ youtube_dl/extractor/lifenews.py | 64 +- youtube_dl/extractor/limelight.py | 93 +- youtube_dl/extractor/livestream.py | 7 +- youtube_dl/extractor/localnews8.py | 47 + youtube_dl/extractor/lynda.py | 135 +- youtube_dl/extractor/m6.py | 35 +- youtube_dl/extractor/matchtv.py | 25 +- youtube_dl/extractor/meta.py | 73 + youtube_dl/extractor/metacafe.py | 89 +- youtube_dl/extractor/mgtv.py | 14 +- youtube_dl/extractor/miomio.py | 59 +- youtube_dl/extractor/mitele.py | 162 +- youtube_dl/extractor/mixcloud.py | 4 +- youtube_dl/extractor/msn.py | 122 ++ youtube_dl/extractor/mtv.py | 71 +- youtube_dl/extractor/nationalgeographic.py | 15 +- youtube_dl/extractor/nbc.py | 180 +- youtube_dl/extractor/ndtv.py | 40 +- youtube_dl/extractor/nextmovie.py | 30 - youtube_dl/extractor/nfb.py | 111 +- youtube_dl/extractor/nick.py | 30 +- youtube_dl/extractor/ninecninemedia.py | 55 + youtube_dl/extractor/ninenow.py | 72 + youtube_dl/extractor/nintendo.py | 46 + youtube_dl/extractor/nrk.py | 34 +- youtube_dl/extractor/odatv.py | 50 + youtube_dl/extractor/onet.py | 169 ++ youtube_dl/extractor/onionstudios.py | 59 +- youtube_dl/extractor/ooyala.py | 118 +- youtube_dl/extractor/openload.py | 7 +- youtube_dl/extractor/ora.py | 9 +- youtube_dl/extractor/orf.py | 29 +- youtube_dl/extractor/pbs.py | 7 +- youtube_dl/extractor/periscope.py | 35 +- youtube_dl/extractor/pladform.py | 2 +- youtube_dl/extractor/playvid.py | 17 +- youtube_dl/extractor/playwire.py | 39 +- youtube_dl/extractor/polskieradio.py | 99 + youtube_dl/extractor/pornhd.py | 58 +- youtube_dl/extractor/pornhub.py | 69 +- youtube_dl/extractor/prosiebensat1.py | 167 +- youtube_dl/extractor/r7.py | 95 +- youtube_dl/extractor/radiocanada.py | 148 ++ youtube_dl/extractor/radiojavan.py | 2 +- youtube_dl/extractor/rai.py | 286 ++- youtube_dl/extractor/rds.py | 27 +- youtube_dl/extractor/reuters.py | 69 + youtube_dl/extractor/revision3.py | 132 +- youtube_dl/extractor/rockstargames.py | 69 + youtube_dl/extractor/roosterteeth.py | 148 ++ youtube_dl/extractor/rtve.py | 42 +- youtube_dl/extractor/rtvnh.py | 32 +- youtube_dl/extractor/rudo.py | 53 + youtube_dl/extractor/safari.py | 14 +- youtube_dl/extractor/sandia.py | 100 +- youtube_dl/extractor/seeker.py | 57 + youtube_dl/extractor/sendtonews.py | 86 + youtube_dl/extractor/shahid.py | 75 +- youtube_dl/extractor/shared.py | 20 +- youtube_dl/extractor/sixplay.py | 64 + youtube_dl/extractor/skynewsarabia.py | 2 +- youtube_dl/extractor/skysports.py | 33 + youtube_dl/extractor/slideshare.py | 5 +- youtube_dl/extractor/smotri.py | 99 +- youtube_dl/extractor/sohu.py | 16 +- youtube_dl/extractor/soundcloud.py | 6 + youtube_dl/extractor/southpark.py | 34 +- youtube_dl/extractor/spankwire.py | 24 +- youtube_dl/extractor/spiegel.py | 22 +- youtube_dl/extractor/spike.py | 31 +- youtube_dl/extractor/sportschau.py | 38 + youtube_dl/extractor/srmediathek.py | 7 +- youtube_dl/extractor/stitcher.py | 2 +- youtube_dl/extractor/streamable.py | 98 + youtube_dl/extractor/streamcloud.py | 39 +- youtube_dl/extractor/svt.py | 112 +- youtube_dl/extractor/syfy.py | 80 +- youtube_dl/extractor/teachingchannel.py | 3 +- youtube_dl/extractor/teamcoco.py | 2 +- youtube_dl/extractor/telecinco.py | 85 +- youtube_dl/extractor/telegraaf.py | 7 +- youtube_dl/extractor/telewebion.py | 55 + youtube_dl/extractor/tf1.py | 4 +- youtube_dl/extractor/theplatform.py | 186 +- youtube_dl/extractor/thesixtyone.py | 6 +- youtube_dl/extractor/threeqsdn.py | 142 ++ youtube_dl/extractor/tmz.py | 28 +- youtube_dl/extractor/toutv.py | 71 +- youtube_dl/extractor/tv2.py | 26 +- youtube_dl/extractor/tvland.py | 55 +- youtube_dl/extractor/tvp.py | 106 +- youtube_dl/extractor/tvplay.py | 123 +- youtube_dl/extractor/tweakers.py | 49 +- youtube_dl/extractor/twentyfourvideo.py | 3 +- youtube_dl/extractor/twitch.py | 63 +- youtube_dl/extractor/twitter.py | 33 +- youtube_dl/extractor/udemy.py | 4 +- youtube_dl/extractor/udn.py | 62 +- youtube_dl/extractor/urplay.py | 67 + youtube_dl/extractor/veoh.py | 1 + youtube_dl/extractor/vessel.py | 32 +- youtube_dl/extractor/vice.py | 3 + youtube_dl/extractor/vidbit.py | 84 + youtube_dl/extractor/vidio.py | 73 + youtube_dl/extractor/vidzi.py | 12 +- youtube_dl/extractor/viewlift.py | 4 + youtube_dl/extractor/viki.py | 33 +- youtube_dl/extractor/vimeo.py | 296 ++- youtube_dl/extractor/vine.py | 9 +- youtube_dl/extractor/vk.py | 228 +- youtube_dl/extractor/vlive.py | 30 +- youtube_dl/extractor/voicerepublic.py | 11 +- youtube_dl/extractor/voxmedia.py | 14 +- youtube_dl/extractor/vporn.py | 10 +- youtube_dl/extractor/vrt.py | 61 +- youtube_dl/extractor/vuclip.py | 43 +- youtube_dl/extractor/vulture.py | 69 - youtube_dl/extractor/washingtonpost.py | 144 +- youtube_dl/extractor/wat.py | 119 +- youtube_dl/extractor/wdr.py | 423 ++-- youtube_dl/extractor/weibo.py | 49 - youtube_dl/extractor/wimp.py | 33 +- youtube_dl/extractor/wistia.py | 52 +- youtube_dl/extractor/wrzuta.py | 94 +- youtube_dl/extractor/xfileshare.py | 47 +- youtube_dl/extractor/xhamster.py | 73 +- youtube_dl/extractor/xnxx.py | 22 +- youtube_dl/extractor/xtube.py | 45 +- youtube_dl/extractor/xuite.py | 31 +- youtube_dl/extractor/xvideos.py | 43 +- youtube_dl/extractor/yahoo.py | 10 +- youtube_dl/extractor/yandexmusic.py | 28 +- youtube_dl/extractor/youjizz.py | 9 +- youtube_dl/extractor/youku.py | 63 +- youtube_dl/extractor/youporn.py | 12 +- youtube_dl/extractor/youtube.py | 127 +- youtube_dl/jsinterp.py | 2 +- youtube_dl/options.py | 27 +- youtube_dl/socks.py | 2 +- youtube_dl/update.py | 9 +- youtube_dl/utils.py | 347 ++- youtube_dl/version.py | 2 +- 264 files changed, 14620 insertions(+), 5035 deletions(-) create mode 100644 .github/PULL_REQUEST_TEMPLATE.md create mode 100644 ChangeLog create mode 100644 devscripts/create-github-release.py delete mode 100755 devscripts/install_srelay.sh create mode 100644 devscripts/show-downloads-statistics.py create mode 100644 youtube_dl/extractor/abcnews.py create mode 100644 youtube_dl/extractor/afreecatv.py create mode 100644 youtube_dl/extractor/anvato.py create mode 100644 youtube_dl/extractor/arkena.py create mode 100644 youtube_dl/extractor/carambatv.py create mode 100644 youtube_dl/extractor/cbslocal.py delete mode 100644 youtube_dl/extractor/cinemassacre.py create mode 100644 youtube_dl/extractor/closertotruth.py delete mode 100644 youtube_dl/extractor/collegehumor.py create mode 100644 youtube_dl/extractor/coub.py create mode 100644 youtube_dl/extractor/ctv.py create mode 100644 youtube_dl/extractor/ctvnews.py create mode 100644 youtube_dl/extractor/eyedotv.py create mode 100644 youtube_dl/extractor/flipagram.py create mode 100644 youtube_dl/extractor/formula1.py create mode 100644 youtube_dl/extractor/fusion.py delete mode 100644 youtube_dl/extractor/gametrailers.py create mode 100644 youtube_dl/extractor/godtv.py create mode 100644 youtube_dl/extractor/hrti.py create mode 100644 youtube_dl/extractor/kamcord.py create mode 100644 youtube_dl/extractor/lcp.py create mode 100644 youtube_dl/extractor/learnr.py create mode 100644 youtube_dl/extractor/libraryofcongress.py create mode 100644 youtube_dl/extractor/localnews8.py create mode 100644 youtube_dl/extractor/meta.py create mode 100644 youtube_dl/extractor/msn.py delete mode 100644 youtube_dl/extractor/nextmovie.py create mode 100644 youtube_dl/extractor/ninecninemedia.py create mode 100644 youtube_dl/extractor/ninenow.py create mode 100644 youtube_dl/extractor/nintendo.py create mode 100644 youtube_dl/extractor/odatv.py create mode 100644 youtube_dl/extractor/onet.py create mode 100644 youtube_dl/extractor/polskieradio.py create mode 100644 youtube_dl/extractor/radiocanada.py create mode 100644 youtube_dl/extractor/reuters.py create mode 100644 youtube_dl/extractor/rockstargames.py create mode 100644 youtube_dl/extractor/roosterteeth.py create mode 100644 youtube_dl/extractor/rudo.py create mode 100644 youtube_dl/extractor/seeker.py create mode 100644 youtube_dl/extractor/sendtonews.py create mode 100644 youtube_dl/extractor/sixplay.py create mode 100644 youtube_dl/extractor/skysports.py create mode 100644 youtube_dl/extractor/sportschau.py create mode 100644 youtube_dl/extractor/streamable.py create mode 100644 youtube_dl/extractor/telewebion.py create mode 100644 youtube_dl/extractor/threeqsdn.py create mode 100644 youtube_dl/extractor/urplay.py create mode 100644 youtube_dl/extractor/vidbit.py create mode 100644 youtube_dl/extractor/vidio.py delete mode 100644 youtube_dl/extractor/vulture.py delete mode 100644 youtube_dl/extractor/weibo.py diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 1fb878b59..9d15b6a89 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 *2016.05.10*. 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 **2016.05.10** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.08.01*. 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 **2016.08.01** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ $ 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 2016.05.10 +[debug] youtube-dl version 2016.08.01 [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/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 000000000..f24bb4b09 --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,22 @@ +## Please follow the guide below + +- You will be asked some questions, please read them **carefully** and answer honestly +- Put an `x` into all the boxes [ ] relevant to your *pull request* (like that [x]) +- Use *Preview* tab to see how your *pull request* will actually look like + +--- + +### Before submitting a *pull request* make sure you have: +- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/rg3/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/rg3/youtube-dl#youtube-dl-coding-conventions) sections +- [ ] [Searched](https://github.com/rg3/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests + +### What is the purpose of your *pull request*? +- [ ] Bug fix +- [ ] New extractor +- [ ] New feature + +--- + +### Description of your *pull request* and other information + +Explanation of your *pull request* in arbitrary form goes here. Please make sure the description explains the purpose and effect of your *pull request* and is worded well enough to be understood. Provide as much context and examples as possible. diff --git a/.gitignore b/.gitignore index d5f216b5f..a802c75a1 100644 --- a/.gitignore +++ b/.gitignore @@ -28,12 +28,16 @@ updates_key.pem *.mp4 *.m4a *.m4v +*.mp3 *.part *.swp test/testdata test/local_parameters.json .tox youtube-dl.zsh + +# IntelliJ related files .idea -.idea/* +*.iml + tmp/ diff --git a/.travis.yml b/.travis.yml index 998995845..c74c9cc12 100644 --- a/.travis.yml +++ b/.travis.yml @@ -7,14 +7,10 @@ python: - "3.4" - "3.5" sudo: false -install: - - bash ./devscripts/install_srelay.sh - - export PATH=$PATH:$(pwd)/tmp/srelay-0.4.8b6 script: nosetests test --verbose notifications: email: - filippo.valsorda@gmail.com - - phihag@phihag.de - yasoob.khld@gmail.com # irc: # channels: diff --git a/AUTHORS b/AUTHORS index 5ca71ace7..890c827a0 100644 --- a/AUTHORS +++ b/AUTHORS @@ -172,3 +172,10 @@ blahgeek Kevin Deldycke inondle Tomáš Čech +Déstin Reed +Roman Tsiupa +Artur Krysiak +Jakub Adam Wieczorek +Aleksandar Topuzović +Nehal Patel +Rob van Bekkum diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index c83b8655a..fbf0ab7e8 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -97,9 +97,17 @@ If you want to add support for a new site, first of all **make sure** this site After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork) -2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git` -3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor` +2. Check out the source code with: + + git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git + +3. Start a new git branch with + + cd youtube-dl + git checkout -b yourextractor + 4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`: + ```python # coding: utf-8 from __future__ import unicode_literals @@ -142,17 +150,149 @@ After you have ensured this site is distributing it's content legally, you can f ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want. -8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`. -9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). -10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! +## youtube-dl coding conventions + +This section introduces a guide lines for writing idiomatic, robust and future-proof extractor code. + +Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hoster out of your control and this layout tend to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize code dependency on source's layout changes and even to make the code foresee potential future changes and be ready for that. This is important because it will allow extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with fix incorporated all the previous version become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say some may never receive an update at all that is possible for non rolling release distros. + +### Mandatory and optional metafields + +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in *info dict* are considered mandatory for successful extraction process by youtube-dl: + + - `id` (media identifier) + - `title` (media title) + - `url` (media download URL) or `formats` + +In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` to be mandatory. Thus aforementioned metafields are the critical data the extraction does not make any sense without and if any of them fail to be extracted then extractor is considered completely broken. + +[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. + +#### Example + +Say you have some source dictionary `meta` that you've fetched as JSON with HTTP request and it has a key `summary`: + +```python +meta = self._download_json(url, video_id) +``` + +Assume at this point `meta`'s layout is: + +```python +{ + ... + "summary": "some fancy summary text", + ... +} +``` + +Assume you want to extract `summary` and put into resulting info dict as `description`. Since `description` is optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like: + +```python +description = meta.get('summary') # correct +``` + +and not like: + +```python +description = meta['summary'] # incorrect +``` + +The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some time later but with former approach extraction will just go ahead with `description` set to `None` that is perfectly fine (remember `None` is equivalent for absence of data). + +Similarly, you should pass `fatal=False` when extracting optional data from a webpage with `_search_regex`, `_html_search_regex` or similar methods, for instance: + +```python +description = self._search_regex( + r']+id="title"[^>]*>([^<]+)<', + webpage, 'description', fatal=False) +``` + +With `fatal` set to `False` if `_search_regex` fails to extract `description` it will emit a warning and continue extraction. + +You can also pass `default=`, for example: + +```python +description = self._search_regex( + r']+id="title"[^>]*>([^<]+)<', + webpage, 'description', default=None) +``` + +On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that are known to may or may not be present. + +### Provide fallbacks + +When extracting metadata try to provide several scenarios for that. For example if `title` is present in several places/sources try extracting from at least some of them. This would make it more future-proof in case some of the sources became unavailable. + +#### Example + +Say `meta` from previous example has a `title` and you are about to extract it. Since `title` is mandatory meta field you should end up with something like: + +```python +title = meta['title'] +``` + +If `title` disappeares from `meta` in future due to some changes on hoster's side the extraction would fail since `title` is mandatory. That's expected. + +Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario: + +```python +title = meta.get('title') or self._og_search_title(webpage) +``` + +This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. + +### Make regular expressions flexible + +When using regular expressions try to write them fuzzy and flexible. + +#### Example + +Say you need to extract `title` from the following HTML code: + +```html +some fancy title +``` + +The code for that task should look similar to: + +```python +title = self._search_regex( + r']+class="title"[^>]*>([^<]+)', webpage, 'title') +``` + +Or even better: + +```python +title = self._search_regex( + r']+class=(["\'])title\1[^>]*>(?P[^<]+)', + webpage, 'title', group='title') +``` + +Note how you tolerate potential changes in `style` attribute's value or switch from using double quotes to single for `class` attribute: + +The code definitely should not look like: + +```python +title = self._search_regex( + r'<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">(.*?)</span>', + webpage, 'title', group='title') +``` + +### Use safe conversion functions + +Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + diff --git a/ChangeLog b/ChangeLog new file mode 100644 index 000000000..f3c752e66 --- /dev/null +++ b/ChangeLog @@ -0,0 +1,271 @@ +version 2016.08.01 + +Fixed/improved extractors +- [yandexmusic:track] Adapt to changes in track location JSON (#10193) +- [bloomberg] Support another form of player (#10187) +- [limelight] Skip DRM protected videos +- [safari] Relax regular expressions for URL matching (#10202) +- [cwtv] Add support for cwtvpr.com (#10196) + +version 2016.07.30 + +Fixed/improved extractors +- [twitch:clips] Sort formats +- [tv2] Use m3u8_native +- [tv2:article] Fix video detection (#10188) +- rtve (#10076) +- [dailymotion:playlist] Optimize download archive processing (#10180) + + +version 2016.07.28 + +Fixed/improved extractors +- shared (#10170) +- soundcloud (#10179) +- twitch (#9767) + + +version 2016.07.26.2 + +Fixed/improved extractors +- smotri +- camdemy +- mtv +- comedycentral +- cmt +- cbc +- mgtv +- orf + + +version 2016.07.24 + +New extractors +- arkena (#8682) +- lcp (#8682) + +Fixed/improved extractors +- facebook (#10151) +- dailymail +- telegraaf +- dcn +- onet +- tvp + +Miscellaneous +- Support $Time$ in DASH manifests + + +version 2016.07.22 + +New extractors +- odatv (#9285) + +Fixed/improved extractors +- bbc +- youjizz (#10131) +- youtube (#10140) +- pornhub (#10138) +- eporner (#10139) + + +version 2016.07.17 + +New extractors +- nintendo (#9986) +- streamable (#9122) + +Fixed/improved extractors +- ard (#10095) +- mtv +- comedycentral (#10101) +- viki (#10098) +- spike (#10106) + +Miscellaneous +- Improved twitter player detection (#10090) + + +version 2016.07.16 + +New extractors +- ninenow (#5181) + +Fixed/improved extractors +- rtve (#10076) +- brightcove +- 3qsdn +- syfy (#9087, #3820, #2388) +- youtube (#10083) + +Miscellaneous +- Fix subtitle embedding for video-only and audio-only files (#10081) + + +version 2016.07.13 + +New extractors +- rudo + +Fixed/improved extractors +- biobiochiletv +- tvplay +- dbtv +- brightcove +- tmz +- youtube (#10059) +- shahid (#10062) +- vk +- ellentv (#10067) + + +version 2016.07.11 + +New Extractors +- roosterteeth (#9864) + +Fixed/improved extractors +- miomio (#9605) +- vuclip +- youtube +- vidzi (#10058) + + +version 2016.07.09.2 + +Fixed/improved extractors +- vimeo (#1638) +- facebook (#10048) +- lynda (#10047) +- animeondemand + +Fixed/improved features +- Embedding subtitles no longer throws an error with problematic inputs (#9063) + + +version 2016.07.09.1 + +Fixed/improved extractors +- youtube +- ard +- srmediatek (#9373) + + +version 2016.07.09 + +New extractors +- Flipagram (#9898) + +Fixed/improved extractors +- telecinco +- toutv +- radiocanada +- tweakers (#9516) +- lynda +- nick (#7542) +- polskieradio (#10028) +- le +- facebook (#9851) +- mgtv +- animeondemand (#10031) + +Fixed/improved features +- `--postprocessor-args` and `--downloader-args` now accepts non-ASCII inputs + on non-Windows systems + + +version 2016.07.07 + +New extractors +- kamcord (#10001) + +Fixed/improved extractors +- spiegel (#10018) +- metacafe (#8539, #3253) +- onet (#9950) +- francetv (#9955) +- brightcove (#9965) +- daum (#9972) + + +version 2016.07.06 + +Fixed/improved extractors +- youtube (#10007, #10009) +- xuite +- stitcher +- spiegel +- slideshare +- sandia +- rtvnh +- prosiebensat1 +- onionstudios + + +version 2016.07.05 + +Fixed/improved extractors +- brightcove +- yahoo (#9995) +- pornhub (#9997) +- iqiyi +- kaltura (#5557) +- la7 +- Changed features +- Rename --cn-verfication-proxy to --geo-verification-proxy +Miscellaneous +- Add script for displaying downloads statistics + + +version 2016.07.03.1 + +Fixed/improved extractors +- theplatform +- aenetworks +- nationalgeographic +- hrti (#9482) +- facebook (#5701) +- buzzfeed (#5701) +- rai (#8617, #9157, #9232, #8552, #8551) +- nationalgeographic (#9991) +- iqiyi + + +version 2016.07.03 + +New extractors +- hrti (#9482) + +Fixed/improved extractors +- vk (#9981) +- facebook (#9938) +- xtube (#9953, #9961) + + +version 2016.07.02 + +New extractors +- fusion (#9958) + +Fixed/improved extractors +- twitch (#9975) +- vine (#9970) +- periscope (#9967) +- pornhub (#8696) + + +version 2016.07.01 + +New extractors +- 9c9media +- ctvnews (#2156) +- ctv (#4077) + +Fixed/Improved extractors +- rds +- meta (#8789) +- pornhub (#9964) +- sixplay (#2183) + +New features +- Accept quoted strings across multiple lines (#9940) diff --git a/Makefile b/Makefile index 5d7cd5a7e..354052c50 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites clean: - rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi *.mkv *.webm CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe + rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe find . -name "*.pyc" -delete find . -name "*.class" -delete @@ -69,7 +69,7 @@ README.txt: README.md pandoc -f markdown -t plain README.md -o README.txt youtube-dl.1: README.md - $(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md + $(PYTHON) devscripts/prepare_manpage.py youtube-dl.1.temp.md pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1 rm -f youtube-dl.1.temp.md @@ -94,7 +94,7 @@ _EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'la youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES) $(PYTHON) devscripts/make_lazy_extractors.py $@ -youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish +youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog @tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \ --exclude '*.DS_Store' \ --exclude '*.kate-swp' \ @@ -107,7 +107,7 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash- --exclude 'docs/_build' \ -- \ bin devscripts test youtube_dl docs \ - LICENSE README.md README.txt \ + ChangeLog LICENSE README.md README.txt \ Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \ youtube-dl.zsh youtube-dl.fish setup.py \ youtube-dl diff --git a/README.md b/README.md index 4ef6b6d5a..a9f3001a6 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms To install it right away for all UNIX users (Linux, OS X, etc.), type: - sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl + sudo curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/local/bin/youtube-dl sudo chmod a+rx /usr/local/bin/youtube-dl If you do not have curl, you can alternatively use a recent wget: @@ -25,20 +25,26 @@ If you do not have curl, you can alternatively use a recent wget: sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl sudo chmod a+rx /usr/local/bin/youtube-dl -Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29). - -OS X users can install **youtube-dl** with [Homebrew](http://brew.sh/). - - brew install youtube-dl +Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in any location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29) except for `%SYSTEMROOT%\System32` (e.g. **do not** put in `C:\Windows\System32`). You can also use pip: - sudo pip install youtube-dl + sudo pip install --upgrade youtube-dl + +This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information. + +OS X users can install youtube-dl with [Homebrew](http://brew.sh/): + + brew install youtube-dl + +Or with [MacPorts](https://www.macports.org/): + + sudo port install youtube-dl 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 small command-line program to download videos from +**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, @@ -73,8 +79,8 @@ which means you can modify it, redistribute it or use it however you like. repairs broken URLs, but emits an error if this is not possible instead of searching. --ignore-config Do not read configuration files. When given - in the global configuration file /etc - /youtube-dl.conf: Do not read the user + in the global configuration file + /etc/youtube-dl.conf: Do not read the user configuration in ~/.config/youtube- dl/config (%APPDATA%/youtube-dl/config.txt on Windows) @@ -97,9 +103,9 @@ which means you can modify it, redistribute it or use it however you like. (experimental) -6, --force-ipv6 Make all connections via IPv6 (experimental) - --cn-verification-proxy URL Use this proxy to verify the IP address for - some Chinese sites. The default proxy - specified by --proxy (or none, if the + --geo-verification-proxy URL Use this proxy to verify the IP address for + some geo-restricted sites. The default + proxy specified by --proxy (or none, if the options is not present) is used for the actual downloading. (experimental) @@ -162,7 +168,7 @@ which means you can modify it, redistribute it or use it however you like. (experimental) ## Download Options: - -r, --rate-limit LIMIT Maximum download rate in bytes per second + -r, --limit-rate RATE Maximum download rate in bytes per second (e.g. 50K or 4.2M) -R, --retries RETRIES Number of retries (default is 10), or "infinite". @@ -249,18 +255,19 @@ which means you can modify it, redistribute it or use it however you like. --write-info-json Write video metadata to a .info.json file --write-annotations Write video annotations to a .annotations.xml file - --load-info FILE JSON file containing the video information + --load-info-json FILE JSON file containing the video information (created with the "--write-info-json" option) --cookies FILE File to read cookies from and dump cookie jar in --cache-dir DIR Location in the filesystem where youtube-dl can store some downloaded information - permanently. By default $XDG_CACHE_HOME - /youtube-dl or ~/.cache/youtube-dl . At the - moment, only YouTube player files (for - videos with obfuscated signatures) are - cached, but that may change. + permanently. By default + $XDG_CACHE_HOME/youtube-dl or + ~/.cache/youtube-dl . At the moment, only + YouTube player files (for videos with + obfuscated signatures) are cached, but that + may change. --no-cache-dir Disable filesystem caching --rm-cache-dir Delete all filesystem cache files @@ -417,7 +424,7 @@ which means you can modify it, redistribute it or use it however you like. # CONFIGURATION -You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. +You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and OS X, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory: ``` @@ -425,6 +432,7 @@ For example, with the following configuration file youtube-dl will always extrac --no-mtime --proxy 127.0.0.1:3128 -o ~/Movies/%(title)s.%(ext)s +# Lines starting with # are comments ``` Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`. @@ -433,7 +441,7 @@ You can use `--ignore-config` if you want to disable the configuration file for ### Authentication with `.netrc` file -You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only: +You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a `.netrc` file in your `$HOME` and restrict permissions to read/write by you only: ``` touch $HOME/.netrc chmod a-rwx,u+rw $HOME/.netrc @@ -504,6 +512,9 @@ The basic usage is not to set any template arguments when downloading a single f - `autonumber`: Five-digit number that will be increased with each download, starting at zero - `playlist`: Name or id of the playlist that contains the video - `playlist_index`: Index of the video in the playlist padded with leading zeros according to the total length of the playlist + - `playlist_id`: Playlist identifier + - `playlist_title`: Playlist title + Available for the video that belongs to some logical chapter or section: - `chapter`: Name or title of the chapter the video belongs to @@ -543,6 +554,10 @@ The current default template is `%(title)s-%(id)s.%(ext)s`. In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title: +#### Output template and Windows batch files + +If you are using output template inside a Windows batch file then you must escape plain percent characters (`%`) by doubling, so that `-o "%(title)s-%(id)s.%(ext)s"` should become `-o "%%(title)s-%%(id)s.%%(ext)s"`. However you should not touch `%`'s that are not plain characters, e.g. environment variables for expansion should stay intact: `-o "C:\%HOMEPATH%\Desktop\%%(title)s.%%(ext)s"`. + #### Output template examples Note on Windows you may need to use double quotes instead of single. @@ -693,6 +708,10 @@ hash -r Again, from then on you'll be able to update with `sudo youtube-dl -U`. +### youtube-dl is extremely slow to start on Windows + +Add a file exclusion for `youtube-dl.exe` in Windows Defender settings. + ### I'm getting an error `Unable to extract OpenGraph title` on YouTube playlists YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos. @@ -780,9 +799,9 @@ means you're using an outdated version of Python. Please update to Python 2.6 or Since June 2012 ([#342](https://github.com/rg3/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`. -### The exe throws a *Runtime error from Visual C++* +### The exe throws an error due to missing `MSVCR100.dll` -To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29). +To run the exe you need to install first the [Microsoft Visual C++ 2010 Redistributable Package (x86)](https://www.microsoft.com/en-US/download/details.aspx?id=5555). ### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files? @@ -837,6 +856,12 @@ It is *not* possible to detect whether a URL is supported or not. That's because If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program. +# Why do I need to go through that much red tape when filing bugs? + +Before we had the issue template, despite our extensive [bug reporting instructions](#bugs), about 80% of the issue reports we got were useless, for instance because people used ancient versions hundreds of releases old, because of simple syntactic errors (not in youtube-dl but in general shell usage), because the problem was alrady reported multiple times before, because people did not actually read an error message, even if it said "please install ffmpeg", because people did not mention the URL they were trying to download and many more simple, easy-to-avoid problems, many of whom were totally unrelated to youtube-dl. + +youtube-dl is an open-source project manned by too few volunteers, so we'd rather spend time fixing bugs where we are certain none of those simple problems apply, and where we can be reasonably confident to be able to reproduce the issue without asking the reporter repeatedly. As such, the output of `youtube-dl -v YOUR_URL_HERE` is really all that's required to file an issue. The issue template also guides you through some basic steps you can do, such as checking that your version of youtube-dl is current. + # DEVELOPER INSTRUCTIONS Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution. @@ -866,9 +891,17 @@ If you want to add support for a new site, first of all **make sure** this site After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`): 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork) -2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git` -3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor` +2. Check out the source code with: + + git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git + +3. Start a new git branch with + + cd youtube-dl + git checkout -b yourextractor + 4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`: + ```python # coding: utf-8 from __future__ import unicode_literals @@ -911,20 +944,152 @@ After you have ensured this site is distributing it's content legally, you can f ``` 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py). 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. -7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want. -8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`. -9. Check the code with [flake8](https://pypi.python.org/pypi/flake8). -10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: +7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L74-L252). Add tests and code for as many as you want. +8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://pypi.python.org/pypi/flake8). Also make sure your code works under all [Python](http://www.python.org/) versions claimed supported by youtube-dl, namely 2.6, 2.7, and 3.2+. +9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this: $ git add youtube_dl/extractor/extractors.py $ git add youtube_dl/extractor/yourextractor.py $ git commit -m '[yourextractor] Add new extractor' $ git push origin yourextractor -11. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. +10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it. In any case, thank you very much for your contributions! +## youtube-dl coding conventions + +This section introduces a guide lines for writing idiomatic, robust and future-proof extractor code. + +Extractors are very fragile by nature since they depend on the layout of the source data provided by 3rd party media hoster out of your control and this layout tend to change. As an extractor implementer your task is not only to write code that will extract media links and metadata correctly but also to minimize code dependency on source's layout changes and even to make the code foresee potential future changes and be ready for that. This is important because it will allow extractor not to break on minor layout changes thus keeping old youtube-dl versions working. Even though this breakage issue is easily fixed by emitting a new version of youtube-dl with fix incorporated all the previous version become broken in all repositories and distros' packages that may not be so prompt in fetching the update from us. Needless to say some may never receive an update at all that is possible for non rolling release distros. + +### Mandatory and optional metafields + +For extraction to work youtube-dl relies on metadata your extractor extracts and provides to youtube-dl expressed by [information dictionary](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L75-L257) or simply *info dict*. Only the following meta fields in *info dict* are considered mandatory for successful extraction process by youtube-dl: + + - `id` (media identifier) + - `title` (media title) + - `url` (media download URL) or `formats` + +In fact only the last option is technically mandatory (i.e. if you can't figure out the download location of the media the extraction does not make any sense). But by convention youtube-dl also treats `id` and `title` to be mandatory. Thus aforementioned metafields are the critical data the extraction does not make any sense without and if any of them fail to be extracted then extractor is considered completely broken. + +[Any field](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L149-L257) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. + +#### Example + +Say you have some source dictionary `meta` that you've fetched as JSON with HTTP request and it has a key `summary`: + +```python +meta = self._download_json(url, video_id) +``` + +Assume at this point `meta`'s layout is: + +```python +{ + ... + "summary": "some fancy summary text", + ... +} +``` + +Assume you want to extract `summary` and put into resulting info dict as `description`. Since `description` is optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like: + +```python +description = meta.get('summary') # correct +``` + +and not like: + +```python +description = meta['summary'] # incorrect +``` + +The latter will break extraction process with `KeyError` if `summary` disappears from `meta` at some time later but with former approach extraction will just go ahead with `description` set to `None` that is perfectly fine (remember `None` is equivalent for absence of data). + +Similarly, you should pass `fatal=False` when extracting optional data from a webpage with `_search_regex`, `_html_search_regex` or similar methods, for instance: + +```python +description = self._search_regex( + r'<span[^>]+id="title"[^>]*>([^<]+)<', + webpage, 'description', fatal=False) +``` + +With `fatal` set to `False` if `_search_regex` fails to extract `description` it will emit a warning and continue extraction. + +You can also pass `default=<some fallback value>`, for example: + +```python +description = self._search_regex( + r'<span[^>]+id="title"[^>]*>([^<]+)<', + webpage, 'description', default=None) +``` + +On failure this code will silently continue the extraction with `description` set to `None`. That is useful for metafields that are known to may or may not be present. + +### Provide fallbacks + +When extracting metadata try to provide several scenarios for that. For example if `title` is present in several places/sources try extracting from at least some of them. This would make it more future-proof in case some of the sources became unavailable. + +#### Example + +Say `meta` from previous example has a `title` and you are about to extract it. Since `title` is mandatory meta field you should end up with something like: + +```python +title = meta['title'] +``` + +If `title` disappeares from `meta` in future due to some changes on hoster's side the extraction would fail since `title` is mandatory. That's expected. + +Assume that you have some another source you can extract `title` from, for example `og:title` HTML meta of a `webpage`. In this case you can provide a fallback scenario: + +```python +title = meta.get('title') or self._og_search_title(webpage) +``` + +This code will try to extract from `meta` first and if it fails it will try extracting `og:title` from a `webpage`. + +### Make regular expressions flexible + +When using regular expressions try to write them fuzzy and flexible. + +#### Example + +Say you need to extract `title` from the following HTML code: + +```html +<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">some fancy title</span> +``` + +The code for that task should look similar to: + +```python +title = self._search_regex( + r'<span[^>]+class="title"[^>]*>([^<]+)', webpage, 'title') +``` + +Or even better: + +```python +title = self._search_regex( + r'<span[^>]+class=(["\'])title\1[^>]*>(?P<title>[^<]+)', + webpage, 'title', group='title') +``` + +Note how you tolerate potential changes in `style` attribute's value or switch from using double quotes to single for `class` attribute: + +The code definitely should not look like: + +```python +title = self._search_regex( + r'<span style="position: absolute; left: 910px; width: 90px; float: right; z-index: 9999;" class="title">(.*?)</span>', + webpage, 'title', group='title') +``` + +### Use safe conversion functions + +Wrap all extracted numeric data into safe functions from `utils`: `int_or_none`, `float_or_none`. Use them for string to number conversions as well. + # EMBEDDING YOUTUBE-DL youtube-dl makes the best effort to be a good command-line program, and thus should be callable from any programming language. If you encounter any problems parsing its output, feel free to [create a report](https://github.com/rg3/youtube-dl/issues/new). @@ -940,7 +1105,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl: ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc']) ``` -Most likely, you'll want to use various options. For a list of what can be done, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L121-L269). For a start, if you want to intercept youtube-dl's output, set a `logger` object. +Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L128-L278). For a start, if you want to intercept youtube-dl's output, set a `logger` object. Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file: diff --git a/devscripts/buildserver.py b/devscripts/buildserver.py index 7c2f49f8b..fc99c3213 100644 --- a/devscripts/buildserver.py +++ b/devscripts/buildserver.py @@ -1,17 +1,38 @@ #!/usr/bin/python3 -from http.server import HTTPServer, BaseHTTPRequestHandler -from socketserver import ThreadingMixIn import argparse import ctypes import functools +import shutil +import subprocess import sys +import tempfile import threading import traceback import os.path +sys.path.insert(0, os.path.dirname(os.path.dirname((os.path.abspath(__file__))))) +from youtube_dl.compat import ( + compat_input, + compat_http_server, + compat_str, + compat_urlparse, +) -class BuildHTTPServer(ThreadingMixIn, HTTPServer): +# These are not used outside of buildserver.py thus not in compat.py + +try: + import winreg as compat_winreg +except ImportError: # Python 2 + import _winreg as compat_winreg + +try: + import socketserver as compat_socketserver +except ImportError: # Python 2 + import SocketServer as compat_socketserver + + +class BuildHTTPServer(compat_socketserver.ThreadingMixIn, compat_http_server.HTTPServer): allow_reuse_address = True @@ -191,7 +212,7 @@ def main(args=None): action='store_const', dest='action', const='service', help='Run as a Windows service') parser.add_argument('-b', '--bind', metavar='<host:port>', - action='store', default='localhost:8142', + action='store', default='0.0.0.0:8142', help='Bind to host:port (default %default)') options = parser.parse_args(args=args) @@ -216,7 +237,7 @@ def main(args=None): srv = BuildHTTPServer((host, port), BuildHTTPRequestHandler) thr = threading.Thread(target=srv.serve_forever) thr.start() - input('Press ENTER to shut down') + compat_input('Press ENTER to shut down') srv.shutdown() thr.join() @@ -231,8 +252,6 @@ def rmtree(path): os.remove(fname) os.rmdir(path) -#============================================================================== - class BuildError(Exception): def __init__(self, output, code=500): @@ -249,15 +268,25 @@ class HTTPError(BuildError): class PythonBuilder(object): def __init__(self, **kwargs): - pythonVersion = kwargs.pop('python', '2.7') - try: - key = _winreg.OpenKey(_winreg.HKEY_LOCAL_MACHINE, r'SOFTWARE\Python\PythonCore\%s\InstallPath' % pythonVersion) + python_version = kwargs.pop('python', '3.4') + python_path = None + for node in ('Wow6432Node\\', ''): try: - self.pythonPath, _ = _winreg.QueryValueEx(key, '') - finally: - _winreg.CloseKey(key) - except Exception: - raise BuildError('No such Python version: %s' % pythonVersion) + key = compat_winreg.OpenKey( + compat_winreg.HKEY_LOCAL_MACHINE, + r'SOFTWARE\%sPython\PythonCore\%s\InstallPath' % (node, python_version)) + try: + python_path, _ = compat_winreg.QueryValueEx(key, '') + finally: + compat_winreg.CloseKey(key) + break + except Exception: + pass + + if not python_path: + raise BuildError('No such Python version: %s' % python_version) + + self.pythonPath = python_path super(PythonBuilder, self).__init__(**kwargs) @@ -305,8 +334,10 @@ class YoutubeDLBuilder(object): def build(self): try: - subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], - cwd=self.buildPath) + proc = subprocess.Popen([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], stdin=subprocess.PIPE, cwd=self.buildPath) + proc.wait() + #subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], + # cwd=self.buildPath) except subprocess.CalledProcessError as e: raise BuildError(e.output) @@ -369,12 +400,12 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea pass -class BuildHTTPRequestHandler(BaseHTTPRequestHandler): +class BuildHTTPRequestHandler(compat_http_server.BaseHTTPRequestHandler): actionDict = {'build': Builder, 'download': Builder} # They're the same, no more caching. def do_GET(self): - path = urlparse.urlparse(self.path) - paramDict = dict([(key, value[0]) for key, value in urlparse.parse_qs(path.query).items()]) + path = compat_urlparse.urlparse(self.path) + paramDict = dict([(key, value[0]) for key, value in compat_urlparse.parse_qs(path.query).items()]) action, _, path = path.path.strip('/').partition('/') if path: path = path.split('/') @@ -388,7 +419,7 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler): builder.close() except BuildError as e: self.send_response(e.code) - msg = unicode(e).encode('UTF-8') + msg = compat_str(e).encode('UTF-8') self.send_header('Content-Type', 'text/plain; charset=UTF-8') self.send_header('Content-Length', len(msg)) self.end_headers() @@ -400,7 +431,5 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler): else: self.send_response(500, 'Malformed URL') -#============================================================================== - if __name__ == '__main__': main() diff --git a/devscripts/create-github-release.py b/devscripts/create-github-release.py new file mode 100644 index 000000000..3b8021e74 --- /dev/null +++ b/devscripts/create-github-release.py @@ -0,0 +1,111 @@ +#!/usr/bin/env python +from __future__ import unicode_literals + +import base64 +import json +import mimetypes +import netrc +import optparse +import os +import sys + +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.compat import ( + compat_basestring, + compat_input, + compat_getpass, + compat_print, + compat_urllib_request, +) +from youtube_dl.utils import ( + make_HTTPS_handler, + sanitized_Request, +) + + +class GitHubReleaser(object): + _API_URL = 'https://api.github.com/repos/rg3/youtube-dl/releases' + _UPLOADS_URL = 'https://uploads.github.com/repos/rg3/youtube-dl/releases/%s/assets?name=%s' + _NETRC_MACHINE = 'github.com' + + def __init__(self, debuglevel=0): + self._init_github_account() + https_handler = make_HTTPS_handler({}, debuglevel=debuglevel) + self._opener = compat_urllib_request.build_opener(https_handler) + + def _init_github_account(self): + try: + info = netrc.netrc().authenticators(self._NETRC_MACHINE) + if info is not None: + self._username = info[0] + self._password = info[2] + compat_print('Using GitHub credentials found in .netrc...') + return + else: + compat_print('No GitHub credentials found in .netrc') + except (IOError, netrc.NetrcParseError): + compat_print('Unable to parse .netrc') + self._username = compat_input( + 'Type your GitHub username or email address and press [Return]: ') + self._password = compat_getpass( + 'Type your GitHub password and press [Return]: ') + + def _call(self, req): + if isinstance(req, compat_basestring): + req = sanitized_Request(req) + # Authorizing manually since GitHub does not response with 401 with + # WWW-Authenticate header set (see + # https://developer.github.com/v3/#basic-authentication) + b64 = base64.b64encode( + ('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii') + req.add_header('Authorization', 'Basic %s' % b64) + response = self._opener.open(req).read().decode('utf-8') + return json.loads(response) + + def list_releases(self): + return self._call(self._API_URL) + + def create_release(self, tag_name, name=None, body='', draft=False, prerelease=False): + data = { + 'tag_name': tag_name, + 'target_commitish': 'master', + 'name': name, + 'body': body, + 'draft': draft, + 'prerelease': prerelease, + } + req = sanitized_Request(self._API_URL, json.dumps(data).encode('utf-8')) + return self._call(req) + + def create_asset(self, release_id, asset): + asset_name = os.path.basename(asset) + url = self._UPLOADS_URL % (release_id, asset_name) + # Our files are small enough to be loaded directly into memory. + data = open(asset, 'rb').read() + req = sanitized_Request(url, data) + mime_type, _ = mimetypes.guess_type(asset_name) + req.add_header('Content-Type', mime_type or 'application/octet-stream') + return self._call(req) + + +def main(): + parser = optparse.OptionParser(usage='%prog VERSION BUILDPATH') + options, args = parser.parse_args() + if len(args) != 2: + parser.error('Expected a version and a build directory') + + version, build_path = args + + releaser = GitHubReleaser() + + new_release = releaser.create_release(version, name='youtube-dl %s' % version) + release_id = new_release['id'] + + for asset in os.listdir(build_path): + compat_print('Uploading %s...' % asset) + releaser.create_asset(release_id, os.path.join(build_path, asset)) + + +if __name__ == '__main__': + main() diff --git a/devscripts/gh-pages/generate-download.py b/devscripts/gh-pages/generate-download.py index 392e3ba21..fcd7e1dff 100755 --- a/devscripts/gh-pages/generate-download.py +++ b/devscripts/gh-pages/generate-download.py @@ -15,13 +15,9 @@ data = urllib.request.urlopen(URL).read() with open('download.html.in', 'r', encoding='utf-8') as tmplf: template = tmplf.read() -md5sum = hashlib.md5(data).hexdigest() -sha1sum = hashlib.sha1(data).hexdigest() sha256sum = hashlib.sha256(data).hexdigest() template = template.replace('@PROGRAM_VERSION@', version) template = template.replace('@PROGRAM_URL@', URL) -template = template.replace('@PROGRAM_MD5SUM@', md5sum) -template = template.replace('@PROGRAM_SHA1SUM@', sha1sum) template = template.replace('@PROGRAM_SHA256SUM@', sha256sum) template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0]) template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1]) diff --git a/devscripts/install_srelay.sh b/devscripts/install_srelay.sh deleted file mode 100755 index 33ce8a3f7..000000000 --- a/devscripts/install_srelay.sh +++ /dev/null @@ -1,8 +0,0 @@ -#!/bin/bash - -mkdir -p tmp && cd tmp -wget -N http://downloads.sourceforge.net/project/socks-relay/socks-relay/srelay-0.4.8/srelay-0.4.8b6.tar.gz -tar zxvf srelay-0.4.8b6.tar.gz -cd srelay-0.4.8b6 -./configure -make diff --git a/devscripts/make_lazy_extractors.py b/devscripts/make_lazy_extractors.py index b5a8b9190..9a79c2bc5 100644 --- a/devscripts/make_lazy_extractors.py +++ b/devscripts/make_lazy_extractors.py @@ -14,15 +14,17 @@ if os.path.exists(lazy_extractors_filename): os.remove(lazy_extractors_filename) from youtube_dl.extractor import _ALL_CLASSES -from youtube_dl.extractor.common import InfoExtractor +from youtube_dl.extractor.common import InfoExtractor, SearchInfoExtractor with open('devscripts/lazy_load_template.py', 'rt') as f: module_template = f.read() -module_contents = [module_template + '\n' + getsource(InfoExtractor.suitable)] +module_contents = [ + module_template + '\n' + getsource(InfoExtractor.suitable) + '\n', + 'class LazyLoadSearchExtractor(LazyLoadExtractor):\n pass\n'] ie_template = ''' -class {name}(LazyLoadExtractor): +class {name}({bases}): _VALID_URL = {valid_url!r} _module = '{module}' ''' @@ -34,10 +36,20 @@ make_valid_template = ''' ''' +def get_base_name(base): + if base is InfoExtractor: + return 'LazyLoadExtractor' + elif base is SearchInfoExtractor: + return 'LazyLoadSearchExtractor' + else: + return base.__name__ + + def build_lazy_ie(ie, name): valid_url = getattr(ie, '_VALID_URL', None) s = ie_template.format( name=name, + bases=', '.join(map(get_base_name, ie.__bases__)), valid_url=valid_url, module=ie.__module__) if ie.suitable.__func__ is not InfoExtractor.suitable.__func__: @@ -47,12 +59,35 @@ def build_lazy_ie(ie, name): s += make_valid_template.format(valid_url=ie._make_valid_url()) return s +# find the correct sorting and add the required base classes so that sublcasses +# can be correctly created +classes = _ALL_CLASSES[:-1] +ordered_cls = [] +while classes: + for c in classes[:]: + bases = set(c.__bases__) - set((object, InfoExtractor, SearchInfoExtractor)) + stop = False + for b in bases: + if b not in classes and b not in ordered_cls: + if b.__name__ == 'GenericIE': + exit() + classes.insert(0, b) + stop = True + if stop: + break + if all(b in ordered_cls for b in bases): + ordered_cls.append(c) + classes.remove(c) + break +ordered_cls.append(_ALL_CLASSES[-1]) + names = [] -for ie in list(sorted(_ALL_CLASSES[:-1], key=lambda cls: cls.ie_key())) + _ALL_CLASSES[-1:]: - name = ie.ie_key() + 'IE' +for ie in ordered_cls: + name = ie.__name__ src = build_lazy_ie(ie, name) module_contents.append(src) - names.append(name) + if ie in _ALL_CLASSES: + names.append(name) module_contents.append( '_ALL_CLASSES = [{0}]'.format(', '.join(names))) diff --git a/devscripts/prepare_manpage.py b/devscripts/prepare_manpage.py index 776e6556e..e3f6339b5 100644 --- a/devscripts/prepare_manpage.py +++ b/devscripts/prepare_manpage.py @@ -1,13 +1,46 @@ from __future__ import unicode_literals import io +import optparse import os.path -import sys import re ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) README_FILE = os.path.join(ROOT_DIR, 'README.md') +PREFIX = '''%YOUTUBE-DL(1) + +# NAME + +youtube\-dl \- download videos from youtube.com or other video platforms + +# SYNOPSIS + +**youtube-dl** \[OPTIONS\] URL [URL...] + +''' + + +def main(): + parser = optparse.OptionParser(usage='%prog OUTFILE.md') + options, args = parser.parse_args() + if len(args) != 1: + parser.error('Expected an output filename') + + outfile, = args + + with io.open(README_FILE, encoding='utf-8') as f: + readme = f.read() + + readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme) + readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme) + readme = PREFIX + readme + + readme = filter_options(readme) + + with io.open(outfile, 'w', encoding='utf-8') as outf: + outf.write(readme) + def filter_options(readme): ret = '' @@ -37,27 +70,5 @@ def filter_options(readme): return ret -with io.open(README_FILE, encoding='utf-8') as f: - readme = f.read() - -PREFIX = '''%YOUTUBE-DL(1) - -# NAME - -youtube\-dl \- download videos from youtube.com or other video platforms - -# SYNOPSIS - -**youtube-dl** \[OPTIONS\] URL [URL...] - -''' -readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme) -readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme) -readme = PREFIX + readme - -readme = filter_options(readme) - -if sys.version_info < (3, 0): - print(readme.encode('utf-8')) -else: - print(readme) +if __name__ == '__main__': + main() diff --git a/devscripts/release.sh b/devscripts/release.sh index 8dea55dbb..ca6ae1b49 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -6,7 +6,7 @@ # * the git config user.signingkey is properly set # You will need -# pip install coverage nose rsa +# pip install coverage nose rsa wheel # TODO # release notes @@ -15,10 +15,33 @@ set -e skip_tests=true -if [ "$1" = '--run-tests' ]; then - skip_tests=false - shift -fi +gpg_sign_commits="" +buildserver='localhost:8142' + +while true +do +case "$1" in + --run-tests) + skip_tests=false + shift + ;; + --gpg-sign-commits|-S) + gpg_sign_commits="-S" + shift + ;; + --buildserver) + buildserver="$2" + shift 2 + ;; + --*) + echo "ERROR: unknown option $1" + exit 1 + ;; + *) + break + ;; +esac +done if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi version="$1" @@ -33,6 +56,9 @@ if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: th useless_files=$(find youtube_dl -type f -not -name '*.py') if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $useless_files"; exit 1; fi if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi +if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; exit 1; fi +if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi +if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi /bin/echo -e "\n### First of all, testing..." make clean @@ -45,10 +71,13 @@ fi /bin/echo -e "\n### Changing version in version.py..." sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py +/bin/echo -e "\n### Changing version in ChangeLog..." +sed -i "s/<unreleased>/$version/" ChangeLog + /bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..." make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites -git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py -git commit -m "release $version" +git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py ChangeLog +git commit $gpg_sign_commits -m "release $version" /bin/echo -e "\n### Now tagging, signing and pushing..." git tag -s -m "Release $version" "$version" @@ -64,7 +93,7 @@ git push origin "$version" REV=$(git rev-parse HEAD) make youtube-dl youtube-dl.tar.gz read -p "VM running? (y/n) " -n 1 -wget "http://localhost:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe +wget "http://$buildserver/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe mkdir -p "build/$version" mv youtube-dl youtube-dl.exe "build/$version" mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz" @@ -74,15 +103,16 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz" (cd build/$version/ && sha256sum $RELEASE_FILES > SHA2-256SUMS) (cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS) -/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..." +/bin/echo -e "\n### Signing and uploading the new binaries to GitHub..." for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done -scp -r "build/$version" ytdl@yt-dl.org:html/tmp/ -ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/" + +ROOT=$(pwd) +python devscripts/create-github-release.py $version "$ROOT/build/$version" + ssh ytdl@yt-dl.org "sh html/update_latest.sh $version" /bin/echo -e "\n### Now switching to gh-pages..." git clone --branch gh-pages --single-branch . build/gh-pages -ROOT=$(pwd) ( set -e ORIGIN_URL=$(git config --get remote.origin.url) @@ -94,7 +124,7 @@ ROOT=$(pwd) "$ROOT/devscripts/gh-pages/update-copyright.py" "$ROOT/devscripts/gh-pages/update-sites.py" git add *.html *.html.in update - git commit -m "release $version" + git commit $gpg_sign_commits -m "release $version" git push "$ROOT" gh-pages git push "$ORIGIN_URL" gh-pages ) diff --git a/devscripts/show-downloads-statistics.py b/devscripts/show-downloads-statistics.py new file mode 100644 index 000000000..e25d28411 --- /dev/null +++ b/devscripts/show-downloads-statistics.py @@ -0,0 +1,47 @@ +#!/usr/bin/env python +from __future__ import unicode_literals + +import itertools +import json +import os +import re +import sys + +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +from youtube_dl.compat import ( + compat_print, + compat_urllib_request, +) +from youtube_dl.utils import format_bytes + + +def format_size(bytes): + return '%s (%d bytes)' % (format_bytes(bytes), bytes) + + +total_bytes = 0 + +for page in itertools.count(1): + releases = json.loads(compat_urllib_request.urlopen( + 'https://api.github.com/repos/rg3/youtube-dl/releases?page=%s' % page + ).read().decode('utf-8')) + + if not releases: + break + + for release in releases: + compat_print(release['name']) + for asset in release['assets']: + asset_name = asset['name'] + total_bytes += asset['download_count'] * asset['size'] + if all(not re.match(p, asset_name) for p in ( + r'^youtube-dl$', + r'^youtube-dl-\d{4}\.\d{2}\.\d{2}(?:\.\d+)?\.tar\.gz$', + r'^youtube-dl\.exe$')): + continue + compat_print( + ' %s size: %s downloads: %d' + % (asset_name, format_size(asset['size']), asset['download_count'])) + +compat_print('total downloads traffic: %s' % format_size(total_bytes)) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index de84e5c84..1f89b1c14 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -6,6 +6,7 @@ - **22tracks:genre** - **22tracks:track** - **24video** + - **3qsdn**: 3Q SDN - **3sat** - **4tube** - **56.com** @@ -13,8 +14,11 @@ - **8tracks** - **91porn** - **9gag** + - **9now.com.au** - **abc.net.au** - **Abc7News** + - **abcnews** + - **abcnews:video** - **AcademicEarth:Course** - **acast** - **acast:channel** @@ -25,6 +29,7 @@ - **AdobeTVVideo** - **AdultSwim** - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network + - **AfreecaTV**: afreecatv.com - **Aftonbladet** - **AirMozilla** - **AlJazeera** @@ -40,8 +45,8 @@ - **appletrailers:section** - **archive.org**: archive.org videos - **ARD** - - **ARD:mediathek**: Saarländischer Rundfunk - **ARD:mediathek** + - **Arkena** - **arte.tv** - **arte.tv:+7** - **arte.tv:cinema** @@ -52,6 +57,7 @@ - **arte.tv:future** - **arte.tv:info** - **arte.tv:magazine** + - **arte.tv:playlist** - **AtresPlayer** - **ATTTechChannel** - **AudiMedia** @@ -69,6 +75,8 @@ - **bbc**: BBC - **bbc.co.uk**: BBC iPlayer - **bbc.co.uk:article**: BBC articles + - **bbc.co.uk:iplayer:playlist** + - **bbc.co.uk:playlist** - **BeatportPro** - **Beeg** - **BehindKink** @@ -99,10 +107,13 @@ - **canalc2.tv** - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv - **Canvas** + - **CarambaTV** + - **CarambaTVPage** - **CBC** - **CBCPlayer** - **CBS** - **CBSInteractive** + - **CBSLocal** - **CBSNews**: CBS News - **CBSNewsLiveVideo**: CBS News Live Videos - **CBSSports** @@ -114,11 +125,11 @@ - **chirbit** - **chirbit:profile** - **Cinchcast** - - **Cinemassacre** - **Clipfish** - **cliphunter** - **ClipRs** - **Clipsyndicate** + - **CloserToTruth** - **cloudtime**: CloudTime - **Cloudy** - **Clubic** @@ -128,12 +139,12 @@ - **CNN** - **CNNArticle** - **CNNBlogs** - - **CollegeHumor** - **CollegeRama** - **ComCarCoff** - **ComedyCentral** - - **ComedyCentralShows**: The Daily Show / The Colbert Report + - **ComedyCentralTV** - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED + - **Coub** - **Cracked** - **Crackle** - **Criterion** @@ -143,6 +154,8 @@ - **CSNNE** - **CSpan**: C-SPAN - **CtsNews**: 華視新聞 + - **CTV** + - **CTVNews** - **culturebox.francetvinfo.fr** - **CultureUnplugged** - **CWTV** @@ -203,6 +216,7 @@ - **exfm**: ex.fm - **ExpoTV** - **ExtremeTube** + - **EyedoTV** - **facebook** - **faz.net** - **fc2** @@ -212,8 +226,10 @@ - **Firstpost** - **FiveTV** - **Flickr** + - **Flipagram** - **Folketinget**: Folketinget (ft.dk; Danish parliament) - **FootyRoom** + - **Formula1** - **FOX** - **Foxgay** - **FoxNews**: Fox News and Fox Business Video @@ -229,6 +245,7 @@ - **FreeVideo** - **Funimation** - **FunnyOrDie** + - **Fusion** - **GameInformer** - **Gamekings** - **GameOne** @@ -236,7 +253,6 @@ - **Gamersyde** - **GameSpot** - **GameStar** - - **Gametrailers** - **Gazeta** - **GDCVault** - **generic**: Generic downloader that works on some sites @@ -247,6 +263,7 @@ - **Globo** - **GloboArticle** - **GodTube** + - **GodTV** - **GoldenMoustache** - **Golem** - **GoogleDrive** @@ -261,6 +278,7 @@ - **Helsinki**: helsinki.fi - **HentaiStigma** - **HistoricFilms** + - **history:topic**: History.com Topic - **hitbox** - **hitbox:live** - **HornBunny** @@ -268,6 +286,8 @@ - **HotStar** - **Howcast** - **HowStuffWorks** + - **HRTi** + - **HRTiPlaylist** - **HuffPost**: Huffington Post - **Hypem** - **Iconosquare** @@ -295,6 +315,7 @@ - **jpopsuki.tv** - **JWPlatform** - **Kaltura** + - **Kamcord** - **KanalPlay**: Kanal 5/9/11 Play - **Kankan** - **Karaoketv** @@ -314,16 +335,19 @@ - **kuwo:mv**: 酷我音乐 - MV - **kuwo:singer**: 酷我音乐 - 歌手 - **kuwo:song**: 酷我音乐 - - **la7.tv** + - **la7.it** - **Laola1Tv** + - **Lcp** + - **LcpPlay** - **Le**: 乐视网 + - **Learnr** - **Lecture2Go** - **Lemonde** - **LePlaylist** - **LetvCloud**: 乐视云 - **Libsyn** + - **life**: Life.ru - **life:embed** - - **lifenews**: LIFE | NEWS - **limelight** - **limelight:channel** - **limelight:channel_list** @@ -332,6 +356,8 @@ - **livestream** - **livestream:original** - **LnkGo** + - **loc**: Library of Congress + - **LocalNews8** - **LoveHomePorn** - **lrt.lt** - **lynda**: lynda.com videos @@ -344,6 +370,7 @@ - **MatchTV** - **MDR**: MDR.DE and KiKA - **media.ccc.de** + - **META** - **metacafe** - **Metacritic** - **Mgoon** @@ -370,10 +397,9 @@ - **MovieFap** - **Moviezine** - **MPORA** - - **MSNBC** + - **MSN** - **MTV** - **mtv.de** - - **mtviggy.com** - **mtvservices:embedded** - **MuenchenTV**: münchen.tv - **MusicPlayOn** @@ -413,7 +439,6 @@ - **Newstube** - **NextMedia**: 蘋果日報 - **NextMediaActionNews**: 蘋果日報 - 動新聞 - - **nextmovie.com** - **nfb**: National Film Board of Canada - **nfl.com** - **nhl.com** @@ -421,8 +446,11 @@ - **nhl.com:videocenter** - **nhl.com:videocenter:category**: NHL videocenter category - **nick.com** + - **nick.de** - **niconico**: ニコニコ動画 - **NiconicoPlaylist** + - **NineCNineMedia** + - **Nintendo** - **njoy**: N-JOY - **njoy:embed** - **Noco** @@ -450,9 +478,12 @@ - **NYTimes** - **NYTimesArticle** - **ocw.mit.edu** + - **OdaTV** - **Odnoklassniki** - **OktoberfestTV** - **on.aol.com** + - **onet.tv** + - **onet.tv:channel** - **OnionStudios** - **Ooyala** - **OoyalaExternal** @@ -486,8 +517,9 @@ - **plus.google**: Google Plus - **pluzz.francetv.fr** - **podomatic** + - **PolskieRadio** - **PornHd** - - **PornHub** + - **PornHub**: PornHub and Thumbzilla - **PornHubPlaylist** - **PornHubUserVideos** - **Pornotube** @@ -505,8 +537,11 @@ - **qqmusic:singer**: QQ音乐 - 歌手 - **qqmusic:toplist**: QQ音乐 - 排行榜 - **R7** + - **R7Article** - **radio.de** - **radiobremen** + - **radiocanada** + - **RadioCanadaAudioVideo** - **radiofrance** - **RadioJavan** - **Rai** @@ -516,10 +551,14 @@ - **RedTube** - **RegioTV** - **Restudy** + - **Reuters** - **ReverbNation** - - **Revision3** + - **revision** + - **revision3:embed** - **RICE** - **RingTV** + - **RockstarGames** + - **RoosterTeeth** - **RottenTomatoes** - **Roxwel** - **RTBF** @@ -532,7 +571,9 @@ - **rtve.es:alacarta**: RTVE a la carta - **rtve.es:infantil**: RTVE infantil - **rtve.es:live**: RTVE.es live streams + - **rtve.es:television** - **RTVNH** + - **Rudo** - **RUHD** - **RulePorn** - **rutube**: Rutube videos @@ -556,15 +597,19 @@ - **ScreencastOMatic** - **ScreenJunkies** - **ScreenwaveMedia** + - **Seeker** - **SenateISVP** + - **SendtoNews** - **ServingSys** - **Sexu** - **Shahid** - **Shared**: shared.sx and vivo.sx - **ShareSix** - **Sina** + - **SixPlay** + - **skynewsarabia:article** - **skynewsarabia:video** - - **skynewsarabia:video** + - **SkySports** - **Slideshare** - **Slutload** - **smotri**: Smotri.com @@ -596,12 +641,14 @@ - **SportBoxEmbed** - **SportDeutschland** - **Sportschau** + - **sr:mediathek**: Saarländischer Rundfunk - **SRGSSR** - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites - **SSA** - **stanfordoc**: Stanford Open ClassRoom - **Steam** - **Stitcher** + - **Streamable** - **streamcloud.eu** - **StreamCZ** - **StreetVoice** @@ -630,6 +677,7 @@ - **Telegraaf** - **TeleMB** - **TeleTask** + - **Telewebion** - **TF1** - **TheIntercept** - **ThePlatform** @@ -648,6 +696,7 @@ - **TNAFlix** - **TNAFlixNetworkEmbed** - **toggle** + - **Tosh**: Tosh.0 - **tou.tv** - **Toypics**: Toypics user profile - **ToypicsUser**: Toypics user profile @@ -676,12 +725,12 @@ - **TVCArticle** - **tvigle**: Интернет-телевидение Tvigle.ru - **tvland.com** - - **tvp.pl** - - **tvp.pl:Series** + - **tvp**: Telewizja Polska + - **tvp:series** - **TVPlay**: TV3Play and related services - **Tweakers** - - **twitch:bookmarks** - **twitch:chapter** + - **twitch:clips** - **twitch:past_broadcasts** - **twitch:profile** - **twitch:stream** @@ -695,10 +744,12 @@ - **UDNEmbed**: 聯合影音 - **Unistra** - **Urort**: NRK P3 Urørt + - **URPlay** - **USAToday** - **ustream** - **ustream:channel** - - **Ustudio** + - **ustudio** + - **ustudio:embed** - **Varzesh3** - **Vbox7** - **VeeHD** @@ -711,6 +762,7 @@ - **vh1.com** - **Vice** - **ViceShow** + - **Vidbit** - **Viddler** - **video.google:search**: Google Video search - **video.mit.edu** @@ -723,6 +775,7 @@ - **VideoPremium** - **VideoTt**: video.tt - Your True Tube (Currently broken) - **videoweed**: VideoWeed + - **Vidio** - **vidme** - **vidme:user** - **vidme:user:likes** @@ -749,6 +802,7 @@ - **vine:user** - **vk**: VK - **vk:uservideos**: VK - User's Videos + - **vk:wallpost** - **vlive** - **Vodlocker** - **VoiceRepublic** @@ -758,17 +812,15 @@ - **VRT** - **vube**: Vube.com - **VuClip** - - **vulture.com** - **Walla** - - **WashingtonPost** + - **washingtonpost** + - **washingtonpost:article** - **wat.tv** - **WatchIndianPorn**: Watch Indian Porn - **WDR** - **wdr:mobile** - - **WDRMaus**: Sendung mit der Maus - **WebOfStories** - **WebOfStoriesPlaylist** - - **Weibo** - **WeiqiTV**: WQTV - **wholecloud**: WholeCloud - **Wimp** @@ -776,10 +828,11 @@ - **WNL** - **WorldStarHipHop** - **wrzuta.pl** + - **wrzuta.pl:playlist** - **WSJ**: Wall Street Journal - **XBef** - **XboxClips** - - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To + - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE - **XHamster** - **XHamsterEmbed** - **xiami:album**: 虾米音乐 - 专辑 @@ -804,6 +857,7 @@ - **Ynet** - **YouJizz** - **youku**: 优酷 + - **youku:show** - **YouPorn** - **YourUpload** - **youtube**: YouTube.com @@ -817,6 +871,7 @@ - **youtube:search**: YouTube.com searches - **youtube:search:date**: YouTube.com searches, newest videos first - **youtube:search_url**: YouTube.com search URLs + - **youtube:shared** - **youtube:show**: YouTube.com (multi-season) shows - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication) - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword) diff --git a/setup.py b/setup.py index 9444d403d..508b27f37 100644 --- a/setup.py +++ b/setup.py @@ -21,25 +21,37 @@ try: import py2exe except ImportError: if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe': - print("Cannot import py2exe", file=sys.stderr) + print('Cannot import py2exe', file=sys.stderr) exit(1) py2exe_options = { - "bundle_files": 1, - "compressed": 1, - "optimize": 2, - "dist_dir": '.', - "dll_excludes": ['w9xpopen.exe', 'crypt32.dll'], + 'bundle_files': 1, + 'compressed': 1, + 'optimize': 2, + 'dist_dir': '.', + 'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'], } +# Get the version from youtube_dl/version.py without importing the package +exec(compile(open('youtube_dl/version.py').read(), + 'youtube_dl/version.py', 'exec')) + +DESCRIPTION = 'YouTube video downloader' +LONG_DESCRIPTION = 'Command-line program to download videos from YouTube.com and other video sites' + py2exe_console = [{ - "script": "./youtube_dl/__main__.py", - "dest_base": "youtube-dl", + 'script': './youtube_dl/__main__.py', + 'dest_base': 'youtube-dl', + 'version': __version__, + 'description': DESCRIPTION, + 'comments': LONG_DESCRIPTION, + 'product_name': 'youtube-dl', + 'product_version': __version__, }] py2exe_params = { 'console': py2exe_console, - 'options': {"py2exe": py2exe_options}, + 'options': {'py2exe': py2exe_options}, 'zipfile': None } @@ -72,7 +84,7 @@ else: params['scripts'] = ['bin/youtube-dl'] class build_lazy_extractors(Command): - description = "Build the extractor lazy loading module" + description = 'Build the extractor lazy loading module' user_options = [] def initialize_options(self): @@ -87,16 +99,11 @@ class build_lazy_extractors(Command): dry_run=self.dry_run, ) -# Get the version from youtube_dl/version.py without importing the package -exec(compile(open('youtube_dl/version.py').read(), - 'youtube_dl/version.py', 'exec')) - setup( name='youtube_dl', version=__version__, - description='YouTube video downloader', - long_description='Small command-line program to download videos from' - ' YouTube.com and other video sites.', + description=DESCRIPTION, + long_description=LONG_DESCRIPTION, url='https://github.com/rg3/youtube-dl', author='Ricardo Garcia', author_email='ytdl@yt-dl.org', @@ -112,16 +119,17 @@ setup( # test_requires = ['nosetest'], classifiers=[ - "Topic :: Multimedia :: Video", - "Development Status :: 5 - Production/Stable", - "Environment :: Console", - "License :: Public Domain", - "Programming Language :: Python :: 2.6", - "Programming Language :: Python :: 2.7", - "Programming Language :: Python :: 3", - "Programming Language :: Python :: 3.2", - "Programming Language :: Python :: 3.3", - "Programming Language :: Python :: 3.4", + 'Topic :: Multimedia :: Video', + 'Development Status :: 5 - Production/Stable', + 'Environment :: Console', + 'License :: Public Domain', + 'Programming Language :: Python :: 2.6', + 'Programming Language :: Python :: 2.7', + 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.2', + 'Programming Language :: Python :: 3.3', + 'Programming Language :: Python :: 3.4', + 'Programming Language :: Python :: 3.5', ], cmdclass={'build_lazy_extractors': build_lazy_extractors}, diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 6404ac89f..88e8ff904 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -11,7 +11,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import FakeYDL from youtube_dl.extractor.common import InfoExtractor from youtube_dl.extractor import YoutubeIE, get_info_extractor -from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError +from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError class TestIE(InfoExtractor): @@ -66,6 +66,11 @@ class TestInfoExtractor(unittest.TestCase): self.assertEqual(ie._html_search_meta('d', html), '4') self.assertEqual(ie._html_search_meta('e', html), '5') self.assertEqual(ie._html_search_meta('f', html), '6') + self.assertEqual(ie._html_search_meta(('a', 'b', 'c'), html), '1') + self.assertEqual(ie._html_search_meta(('c', 'b', 'a'), html), '3') + self.assertEqual(ie._html_search_meta(('z', 'x', 'c'), html), '3') + self.assertRaises(RegexNotFoundError, ie._html_search_meta, 'z', html, None, fatal=True) + self.assertRaises(RegexNotFoundError, ie._html_search_meta, ('z', 'x'), html, None, fatal=True) def test_download_json(self): uri = encode_data_uri(b'{"foo": "blah"}', 'application/json') diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index ca25025e2..0dfe25c00 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -335,6 +335,40 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], f1['format_id']) + def test_audio_only_extractor_format_selection(self): + # For extractors with incomplete formats (all formats are audio-only or + # video-only) best and worst should fallback to corresponding best/worst + # video-only or audio-only formats (as per + # https://github.com/rg3/youtube-dl/pull/5556) + formats = [ + {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL}, + {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL}, + ] + info_dict = _make_result(formats) + + ydl = YDL({'format': 'best'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'high') + + ydl = YDL({'format': 'worst'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'low') + + def test_format_not_available(self): + formats = [ + {'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL}, + {'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL}, + ] + info_dict = _make_result(formats) + + # This must fail since complete video-audio format does not match filter + # and extractor does not provide incomplete only formats (i.e. only + # video-only or audio-only). + ydl = YDL({'format': 'best[height>360]'}) + self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) + def test_invalid_format_specs(self): def assert_syntax_error(format_spec): ydl = YDL({'format': format_spec}) diff --git a/test/test_all_urls.py b/test/test_all_urls.py index f5af184e6..cd1cd4b24 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -6,6 +6,7 @@ from __future__ import unicode_literals import os import sys import unittest +import collections sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) @@ -100,8 +101,6 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch(':ytsubs', ['youtube:subscriptions']) self.assertMatch(':ytsubscriptions', ['youtube:subscriptions']) self.assertMatch(':ythistory', ['youtube:history']) - self.assertMatch(':thedailyshow', ['ComedyCentralShows']) - self.assertMatch(':tds', ['ComedyCentralShows']) def test_vimeo_matching(self): self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel']) @@ -130,6 +129,15 @@ class TestAllURLsMatching(unittest.TestCase): 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html', ['Yahoo']) + def test_no_duplicated_ie_names(self): + name_accu = collections.defaultdict(list) + for ie in self.ies: + name_accu[ie.IE_NAME.lower()].append(type(ie).__name__) + for (ie_name, ie_list) in name_accu.items(): + self.assertEqual( + len(ie_list), 1, + 'Multiple extractors with the same IE_NAME "%s" (%s)' % (ie_name, ', '.join(ie_list))) + if __name__ == '__main__': unittest.main() diff --git a/test/test_compat.py b/test/test_compat.py index 539b30540..b57424948 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -87,6 +87,8 @@ class TestCompat(unittest.TestCase): def test_compat_shlex_split(self): self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two']) + self.assertEqual(compat_shlex_split('-option "one\ntwo" \n -flag'), ['-option', 'one\ntwo', '-flag']) + self.assertEqual(compat_shlex_split('-val 中文'), ['-val', '中文']) def test_compat_etree_fromstring(self): xml = ''' @@ -103,6 +105,12 @@ class TestCompat(unittest.TestCase): self.assertTrue(isinstance(doc.find('chinese').text, compat_str)) self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str)) + def test_compat_etree_fromstring_doctype(self): + xml = '''<?xml version="1.0"?> +<!DOCTYPE smil PUBLIC "-//W3C//DTD SMIL 2.0//EN" "http://www.w3.org/2001/SMIL20/SMIL20.dtd"> +<smil xmlns="http://www.w3.org/2001/SMIL20/Language"></smil>''' + compat_etree_fromstring(xml) + def test_struct_unpack(self): self.assertEqual(compat_struct_unpack('!B', b'\x00'), (0,)) diff --git a/test/test_http.py b/test/test_http.py index 15e0ad369..fdc68ccb4 100644 --- a/test/test_http.py +++ b/test/test_http.py @@ -16,6 +16,15 @@ import threading TEST_DIR = os.path.dirname(os.path.abspath(__file__)) +def http_server_port(httpd): + if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): + # In Jython SSLSocket is not a subclass of socket.socket + sock = httpd.socket.sock + else: + sock = httpd.socket + return sock.getsockname()[1] + + class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): def log_message(self, format, *args): pass @@ -31,6 +40,22 @@ class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler): self.send_header('Content-Type', 'video/mp4') self.end_headers() self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]') + elif self.path == '/302': + if sys.version_info[0] == 3: + # XXX: Python 3 http server does not allow non-ASCII header values + self.send_response(404) + self.end_headers() + return + + new_url = 'http://localhost:%d/中文.html' % http_server_port(self.server) + self.send_response(302) + self.send_header(b'Location', new_url.encode('utf-8')) + self.end_headers() + elif self.path == '/%E4%B8%AD%E6%96%87.html': + self.send_response(200) + self.send_header('Content-Type', 'text/html; charset=utf-8') + self.end_headers() + self.wfile.write(b'<html><video src="/vid.mp4" /></html>') else: assert False @@ -47,18 +72,32 @@ class FakeLogger(object): class TestHTTP(unittest.TestCase): + def setUp(self): + self.httpd = compat_http_server.HTTPServer( + ('localhost', 0), HTTPTestRequestHandler) + self.port = http_server_port(self.httpd) + self.server_thread = threading.Thread(target=self.httpd.serve_forever) + self.server_thread.daemon = True + self.server_thread.start() + + def test_unicode_path_redirection(self): + # XXX: Python 3 http server does not allow non-ASCII header values + if sys.version_info[0] == 3: + return + + ydl = YoutubeDL({'logger': FakeLogger()}) + r = ydl.extract_info('http://localhost:%d/302' % self.port) + self.assertEqual(r['url'], 'http://localhost:%d/vid.mp4' % self.port) + + +class TestHTTPS(unittest.TestCase): def setUp(self): certfn = os.path.join(TEST_DIR, 'testcert.pem') self.httpd = compat_http_server.HTTPServer( ('localhost', 0), HTTPTestRequestHandler) self.httpd.socket = ssl.wrap_socket( self.httpd.socket, certfile=certfn, server_side=True) - if os.name == 'java': - # In Jython SSLSocket is not a subclass of socket.socket - sock = self.httpd.socket.sock - else: - sock = self.httpd.socket - self.port = sock.getsockname()[1] + self.port = http_server_port(self.httpd) self.server_thread = threading.Thread(target=self.httpd.serve_forever) self.server_thread.daemon = True self.server_thread.start() @@ -94,32 +133,32 @@ class TestProxy(unittest.TestCase): def setUp(self): self.proxy = compat_http_server.HTTPServer( ('localhost', 0), _build_proxy_handler('normal')) - self.port = self.proxy.socket.getsockname()[1] + self.port = http_server_port(self.proxy) self.proxy_thread = threading.Thread(target=self.proxy.serve_forever) self.proxy_thread.daemon = True self.proxy_thread.start() - self.cn_proxy = compat_http_server.HTTPServer( - ('localhost', 0), _build_proxy_handler('cn')) - self.cn_port = self.cn_proxy.socket.getsockname()[1] - self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever) - self.cn_proxy_thread.daemon = True - self.cn_proxy_thread.start() + self.geo_proxy = compat_http_server.HTTPServer( + ('localhost', 0), _build_proxy_handler('geo')) + self.geo_port = http_server_port(self.geo_proxy) + self.geo_proxy_thread = threading.Thread(target=self.geo_proxy.serve_forever) + self.geo_proxy_thread.daemon = True + self.geo_proxy_thread.start() def test_proxy(self): - cn_proxy = 'localhost:{0}'.format(self.cn_port) + geo_proxy = 'localhost:{0}'.format(self.geo_port) ydl = YoutubeDL({ 'proxy': 'localhost:{0}'.format(self.port), - 'cn_verification_proxy': cn_proxy, + 'geo_verification_proxy': geo_proxy, }) url = 'http://foo.com/bar' response = ydl.urlopen(url).read().decode('utf-8') self.assertEqual(response, 'normal: {0}'.format(url)) req = compat_urllib_request.Request(url) - req.add_header('Ytdl-request-proxy', cn_proxy) + req.add_header('Ytdl-request-proxy', geo_proxy) response = ydl.urlopen(req).read().decode('utf-8') - self.assertEqual(response, 'cn: {0}'.format(url)) + self.assertEqual(response, 'geo: {0}'.format(url)) def test_proxy_with_idn(self): ydl = YoutubeDL({ diff --git a/test/test_socks.py b/test/test_socks.py index d07003ceb..1e68eb0da 100644 --- a/test/test_socks.py +++ b/test/test_socks.py @@ -77,17 +77,28 @@ class TestMultipleSocks(unittest.TestCase): class TestSocks(unittest.TestCase): + _SKIP_SOCKS_TEST = True + def setUp(self): + if self._SKIP_SOCKS_TEST: + return + self.port = random.randint(20000, 30000) self.server_process = subprocess.Popen([ 'srelay', '-f', '-i', '127.0.0.1:%d' % self.port], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) def tearDown(self): + if self._SKIP_SOCKS_TEST: + return + self.server_process.terminate() self.server_process.communicate() def _get_ip(self, protocol): + if self._SKIP_SOCKS_TEST: + return '127.0.0.1' + ydl = FakeYDL({ 'proxy': '%s://127.0.0.1:%d' % (protocol, self.port), }) diff --git a/test/test_utils.py b/test/test_utils.py index ca254779f..2273b5a10 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -33,6 +33,7 @@ from youtube_dl.utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, + get_element_by_class, InAdvancePagedList, intlist_to_bytes, is_html, @@ -50,6 +51,8 @@ from youtube_dl.utils import ( sanitize_path, prepend_extension, replace_extension, + remove_start, + remove_end, remove_quotes, shell_quote, smuggle_url, @@ -58,11 +61,13 @@ from youtube_dl.utils import ( timeconvert, unescapeHTML, unified_strdate, + unified_timestamp, unsmuggle_url, uppercase_escape, lowercase_escape, url_basename, urlencode_postdata, + urshift, update_url_query, version_tuple, xpath_with_ns, @@ -76,6 +81,7 @@ from youtube_dl.utils import ( cli_option, cli_valueless_option, cli_bool_option, + parse_codecs, ) from youtube_dl.compat import ( compat_chr, @@ -155,8 +161,8 @@ class TestUtil(unittest.TestCase): self.assertTrue(sanitize_filename(':', restricted=True) != '') self.assertEqual(sanitize_filename( - 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØŒÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøœùúûüýþÿ', restricted=True), - 'AAAAAAAECEEEEIIIIDNOOOOOOOEUUUUYPssaaaaaaaeceeeeiiiionoooooooeuuuuypy') + 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True), + 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy') def test_sanitize_ids(self): self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw') @@ -215,6 +221,16 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_remove_start(self): + self.assertEqual(remove_start(None, 'A - '), None) + self.assertEqual(remove_start('A - B', 'A - '), 'B') + self.assertEqual(remove_start('B - A', 'A - '), 'B - A') + + def test_remove_end(self): + self.assertEqual(remove_end(None, ' - B'), None) + self.assertEqual(remove_end('A - B', ' - B'), 'A') + self.assertEqual(remove_end('B - A', ' - B'), 'B - A') + def test_remove_quotes(self): self.assertEqual(remove_quotes(None), None) self.assertEqual(remove_quotes('"'), '"') @@ -237,6 +253,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(unescapeHTML('/'), '/') self.assertEqual(unescapeHTML('é'), 'é') self.assertEqual(unescapeHTML('�'), '�') + # HTML5 entities + self.assertEqual(unescapeHTML('.''), '.\'') def test_date_from_str(self): self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day')) @@ -269,8 +287,28 @@ class TestUtil(unittest.TestCase): '20150202') self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214') self.assertEqual(unified_strdate('25-09-2014'), '20140925') + self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227') self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None) + def test_unified_timestamps(self): + self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600) + self.assertEqual(unified_timestamp('8/7/2009'), 1247011200) + self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200) + self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598) + self.assertEqual(unified_timestamp('1968 12 10'), -33436800) + self.assertEqual(unified_timestamp('1968-12-10'), -33436800) + self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200) + self.assertEqual( + unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False), + 1417001400) + self.assertEqual( + unified_timestamp('2/2/2015 6:47:40 PM', day_first=False), + 1422902860) + self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900) + self.assertEqual(unified_timestamp('25-09-2014'), 1411603200) + self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200) + self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None) + def test_determine_ext(self): self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4') self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None) @@ -369,6 +407,12 @@ class TestUtil(unittest.TestCase): self.assertEqual(res_url, url) self.assertEqual(res_data, None) + smug_url = smuggle_url(url, {'a': 'b'}) + smug_smug_url = smuggle_url(smug_url, {'c': 'd'}) + res_url, res_data = unsmuggle_url(smug_smug_url) + self.assertEqual(res_url, url) + self.assertEqual(res_data, {'a': 'b', 'c': 'd'}) + def test_shell_quote(self): args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')] self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""") @@ -565,6 +609,29 @@ class TestUtil(unittest.TestCase): limit_length('foo bar baz asd', 12).startswith('foo bar')) self.assertTrue('...' in limit_length('foo bar baz asd', 12)) + def test_parse_codecs(self): + self.assertEqual(parse_codecs(''), {}) + self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), { + 'vcodec': 'avc1.77.30', + 'acodec': 'mp4a.40.2', + }) + self.assertEqual(parse_codecs('mp4a.40.2'), { + 'vcodec': 'none', + 'acodec': 'mp4a.40.2', + }) + self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), { + 'vcodec': 'avc1.42001e', + 'acodec': 'mp4a.40.5', + }) + self.assertEqual(parse_codecs('avc3.640028'), { + 'vcodec': 'avc3.640028', + 'acodec': 'none', + }) + self.assertEqual(parse_codecs(', h264,,newcodec,aac'), { + 'vcodec': 'h264', + 'acodec': 'aac', + }) + def test_escape_rfc3986(self): reserved = "!*'();:@&=+$,/?#[]" unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~' @@ -617,6 +684,18 @@ class TestUtil(unittest.TestCase): json_code = js_to_json(inp) self.assertEqual(json.loads(json_code), json.loads(inp)) + inp = '''{ + 0:{src:'skipped', type: 'application/dash+xml'}, + 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'}, + }''' + self.assertEqual(js_to_json(inp), '''{ + "0":{"src":"skipped", "type": "application/dash+xml"}, + "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"} + }''') + + inp = '''{"foo":101}''' + self.assertEqual(js_to_json(inp), '''{"foo":101}''') + def test_js_to_json_edgecases(self): on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}") self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"}) @@ -640,6 +719,27 @@ class TestUtil(unittest.TestCase): on = js_to_json('{"abc": "def",}') self.assertEqual(json.loads(on), {'abc': 'def'}) + on = js_to_json('{ 0: /* " \n */ ",]" , }') + self.assertEqual(json.loads(on), {'0': ',]'}) + + on = js_to_json(r'["<p>x<\/p>"]') + self.assertEqual(json.loads(on), ['<p>x</p>']) + + on = js_to_json(r'["\xaa"]') + self.assertEqual(json.loads(on), ['\u00aa']) + + on = js_to_json("['a\\\nb']") + self.assertEqual(json.loads(on), ['ab']) + + on = js_to_json('{0xff:0xff}') + self.assertEqual(json.loads(on), {'255': 255}) + + on = js_to_json('{077:077}') + self.assertEqual(json.loads(on), {'63': 63}) + + on = js_to_json('{42:42}') + self.assertEqual(json.loads(on), {'42': 42}) + def test_extract_attributes(self): self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}) self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'}) @@ -912,5 +1012,17 @@ The first line self.assertRaises(ValueError, encode_base_n, 0, 70) self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table) + def test_urshift(self): + self.assertEqual(urshift(3, 1), 1) + self.assertEqual(urshift(-3, 1), 2147483646) + + def test_get_element_by_class(self): + html = ''' + <span class="foo bar">nice</span> + ''' + + self.assertEqual(get_element_by_class('foo', html), 'nice') + self.assertEqual(get_element_by_class('no-such-class', html), None) + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 8afcd30fc..1af6e4ef5 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -5,6 +5,7 @@ from __future__ import absolute_import, unicode_literals import collections import contextlib +import copy import datetime import errno import fileinput @@ -197,8 +198,8 @@ class YoutubeDL(object): prefer_insecure: Use HTTP instead of HTTPS to retrieve information. At the moment, this is only supported by YouTube. proxy: URL of the proxy server to use - cn_verification_proxy: URL of the proxy to use for IP address verification - on Chinese sites. (Experimental) + geo_verification_proxy: URL of the proxy to use for IP address verification + on geo-restricted sites. (Experimental) socket_timeout: Time to wait for unresponsive hosts, in seconds bidi_workaround: Work around buggy terminals without bidirectional text support, using fridibi @@ -305,6 +306,11 @@ class YoutubeDL(object): self.params.update(params) self.cache = Cache(self) + if self.params.get('cn_verification_proxy') is not None: + self.report_warning('--cn-verification-proxy is deprecated. Use --geo-verification-proxy instead.') + if self.params.get('geo_verification_proxy') is None: + self.params['geo_verification_proxy'] = self.params['cn_verification_proxy'] + if params.get('bidi_workaround', False): try: import pty @@ -327,7 +333,7 @@ class YoutubeDL(object): ['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs) self._output_channel = os.fdopen(master, 'rb') except OSError as ose: - if ose.errno == 2: + if ose.errno == errno.ENOENT: self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.') else: raise @@ -1049,9 +1055,9 @@ class YoutubeDL(object): if isinstance(selector, list): fs = [_build_selector_function(s) for s in selector] - def selector_function(formats): + def selector_function(ctx): for f in fs: - for format in f(formats): + for format in f(ctx): yield format return selector_function elif selector.type == GROUP: @@ -1059,17 +1065,17 @@ class YoutubeDL(object): elif selector.type == PICKFIRST: fs = [_build_selector_function(s) for s in selector.selector] - def selector_function(formats): + def selector_function(ctx): for f in fs: - picked_formats = list(f(formats)) + picked_formats = list(f(ctx)) if picked_formats: return picked_formats return [] elif selector.type == SINGLE: format_spec = selector.selector - def selector_function(formats): - formats = list(formats) + def selector_function(ctx): + formats = list(ctx['formats']) if not formats: return if format_spec == 'all': @@ -1082,9 +1088,10 @@ class YoutubeDL(object): if f.get('vcodec') != 'none' and f.get('acodec') != 'none'] if audiovideo_formats: yield audiovideo_formats[format_idx] - # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format - elif (all(f.get('acodec') != 'none' for f in formats) or - all(f.get('vcodec') != 'none' for f in formats)): + # for extractors with incomplete formats (audio only (soundcloud) + # or video only (imgur)) we will fallback to best/worst + # {video,audio}-only format + elif ctx['incomplete_formats']: yield formats[format_idx] elif format_spec == 'bestaudio': audio_formats = [ @@ -1158,17 +1165,18 @@ class YoutubeDL(object): } video_selector, audio_selector = map(_build_selector_function, selector.selector) - def selector_function(formats): - formats = list(formats) - for pair in itertools.product(video_selector(formats), audio_selector(formats)): + def selector_function(ctx): + for pair in itertools.product( + video_selector(copy.deepcopy(ctx)), audio_selector(copy.deepcopy(ctx))): yield _merge(pair) filters = [self._build_format_filter(f) for f in selector.filters] - def final_selector(formats): + def final_selector(ctx): + ctx_copy = copy.deepcopy(ctx) for _filter in filters: - formats = list(filter(_filter, formats)) - return selector_function(formats) + ctx_copy['formats'] = list(filter(_filter, ctx_copy['formats'])) + return selector_function(ctx_copy) return final_selector stream = io.BytesIO(format_spec.encode('utf-8')) @@ -1226,6 +1234,10 @@ class YoutubeDL(object): if 'title' not in info_dict: raise ExtractorError('Missing "title" field in extractor result') + if not isinstance(info_dict['id'], compat_str): + self.report_warning('"id" field is not a string - forcing string conversion') + info_dict['id'] = compat_str(info_dict['id']) + if 'playlist' not in info_dict: # It isn't part of a playlist info_dict['playlist'] = None @@ -1371,7 +1383,34 @@ class YoutubeDL(object): req_format_list.append('best') req_format = '/'.join(req_format_list) format_selector = self.build_format_selector(req_format) - formats_to_download = list(format_selector(formats)) + + # While in format selection we may need to have an access to the original + # format set in order to calculate some metrics or do some processing. + # For now we need to be able to guess whether original formats provided + # by extractor are incomplete or not (i.e. whether extractor provides only + # video-only or audio-only formats) for proper formats selection for + # extractors with such incomplete formats (see + # https://github.com/rg3/youtube-dl/pull/5556). + # Since formats may be filtered during format selection and may not match + # the original formats the results may be incorrect. Thus original formats + # or pre-calculated metrics should be passed to format selection routines + # as well. + # We will pass a context object containing all necessary additional data + # instead of just formats. + # This fixes incorrect format selection issue (see + # https://github.com/rg3/youtube-dl/issues/10083). + incomplete_formats = ( + # All formats are video-only or + all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or + # all formats are audio-only + all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats)) + + ctx = { + 'formats': formats, + 'incomplete_formats': incomplete_formats, + } + + formats_to_download = list(format_selector(ctx)) if not formats_to_download: raise ExtractorError('requested format not available', expected=True) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 135356e0a..428f538b3 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -18,7 +18,6 @@ from .options import ( from .compat import ( compat_expanduser, compat_getpass, - compat_print, compat_shlex_split, workaround_optparse_bug9161, ) @@ -76,7 +75,7 @@ def _real_main(argv=None): # Dump user agent if opts.dump_user_agent: - compat_print(std_headers['User-Agent']) + write_string(std_headers['User-Agent'] + '\n', out=sys.stdout) sys.exit(0) # Batch file verification @@ -101,10 +100,10 @@ def _real_main(argv=None): if opts.list_extractors: for ie in list_extractors(opts.age_limit): - compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) + write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout) matchedUrls = [url for url in all_urls if ie.suitable(url)] for mu in matchedUrls: - compat_print(' ' + mu) + write_string(' ' + mu + '\n', out=sys.stdout) sys.exit(0) if opts.list_extractor_descriptions: for ie in list_extractors(opts.age_limit): @@ -117,7 +116,7 @@ def _real_main(argv=None): _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow') _COUNTS = ('', '5', '10', 'all') desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) - compat_print(desc) + write_string(desc + '\n', out=sys.stdout) sys.exit(0) # Conflicting, missing and erroneous options @@ -384,6 +383,8 @@ def _real_main(argv=None): 'external_downloader_args': external_downloader_args, 'postprocessor_args': postprocessor_args, 'cn_verification_proxy': opts.cn_verification_proxy, + 'geo_verification_proxy': opts.geo_verification_proxy, + } with YoutubeDL(ydl_opts) as ydl: diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 1392361a1..b8aaf5a46 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import binascii @@ -63,6 +64,2244 @@ try: except ImportError: # Python 2 import htmlentitydefs as compat_html_entities +try: # Python >= 3.3 + compat_html_entities_html5 = compat_html_entities.html5 +except AttributeError: + # Copied from CPython 3.5.1 html/entities.py + compat_html_entities_html5 = { + 'Aacute': '\xc1', + 'aacute': '\xe1', + 'Aacute;': '\xc1', + 'aacute;': '\xe1', + 'Abreve;': '\u0102', + 'abreve;': '\u0103', + 'ac;': '\u223e', + 'acd;': '\u223f', + 'acE;': '\u223e\u0333', + 'Acirc': '\xc2', + 'acirc': '\xe2', + 'Acirc;': '\xc2', + 'acirc;': '\xe2', + 'acute': '\xb4', + 'acute;': '\xb4', + 'Acy;': '\u0410', + 'acy;': '\u0430', + 'AElig': '\xc6', + 'aelig': '\xe6', + 'AElig;': '\xc6', + 'aelig;': '\xe6', + 'af;': '\u2061', + 'Afr;': '\U0001d504', + 'afr;': '\U0001d51e', + 'Agrave': '\xc0', + 'agrave': '\xe0', + 'Agrave;': '\xc0', + 'agrave;': '\xe0', + 'alefsym;': '\u2135', + 'aleph;': '\u2135', + 'Alpha;': '\u0391', + 'alpha;': '\u03b1', + 'Amacr;': '\u0100', + 'amacr;': '\u0101', + 'amalg;': '\u2a3f', + 'AMP': '&', + 'amp': '&', + 'AMP;': '&', + 'amp;': '&', + 'And;': '\u2a53', + 'and;': '\u2227', + 'andand;': '\u2a55', + 'andd;': '\u2a5c', + 'andslope;': '\u2a58', + 'andv;': '\u2a5a', + 'ang;': '\u2220', + 'ange;': '\u29a4', + 'angle;': '\u2220', + 'angmsd;': '\u2221', + 'angmsdaa;': '\u29a8', + 'angmsdab;': '\u29a9', + 'angmsdac;': '\u29aa', + 'angmsdad;': '\u29ab', + 'angmsdae;': '\u29ac', + 'angmsdaf;': '\u29ad', + 'angmsdag;': '\u29ae', + 'angmsdah;': '\u29af', + 'angrt;': '\u221f', + 'angrtvb;': '\u22be', + 'angrtvbd;': '\u299d', + 'angsph;': '\u2222', + 'angst;': '\xc5', + 'angzarr;': '\u237c', + 'Aogon;': '\u0104', + 'aogon;': '\u0105', + 'Aopf;': '\U0001d538', + 'aopf;': '\U0001d552', + 'ap;': '\u2248', + 'apacir;': '\u2a6f', + 'apE;': '\u2a70', + 'ape;': '\u224a', + 'apid;': '\u224b', + 'apos;': "'", + 'ApplyFunction;': '\u2061', + 'approx;': '\u2248', + 'approxeq;': '\u224a', + 'Aring': '\xc5', + 'aring': '\xe5', + 'Aring;': '\xc5', + 'aring;': '\xe5', + 'Ascr;': '\U0001d49c', + 'ascr;': '\U0001d4b6', + 'Assign;': '\u2254', + 'ast;': '*', + 'asymp;': '\u2248', + 'asympeq;': '\u224d', + 'Atilde': '\xc3', + 'atilde': '\xe3', + 'Atilde;': '\xc3', + 'atilde;': '\xe3', + 'Auml': '\xc4', + 'auml': '\xe4', + 'Auml;': '\xc4', + 'auml;': '\xe4', + 'awconint;': '\u2233', + 'awint;': '\u2a11', + 'backcong;': '\u224c', + 'backepsilon;': '\u03f6', + 'backprime;': '\u2035', + 'backsim;': '\u223d', + 'backsimeq;': '\u22cd', + 'Backslash;': '\u2216', + 'Barv;': '\u2ae7', + 'barvee;': '\u22bd', + 'Barwed;': '\u2306', + 'barwed;': '\u2305', + 'barwedge;': '\u2305', + 'bbrk;': '\u23b5', + 'bbrktbrk;': '\u23b6', + 'bcong;': '\u224c', + 'Bcy;': '\u0411', + 'bcy;': '\u0431', + 'bdquo;': '\u201e', + 'becaus;': '\u2235', + 'Because;': '\u2235', + 'because;': '\u2235', + 'bemptyv;': '\u29b0', + 'bepsi;': '\u03f6', + 'bernou;': '\u212c', + 'Bernoullis;': '\u212c', + 'Beta;': '\u0392', + 'beta;': '\u03b2', + 'beth;': '\u2136', + 'between;': '\u226c', + 'Bfr;': '\U0001d505', + 'bfr;': '\U0001d51f', + 'bigcap;': '\u22c2', + 'bigcirc;': '\u25ef', + 'bigcup;': '\u22c3', + 'bigodot;': '\u2a00', + 'bigoplus;': '\u2a01', + 'bigotimes;': '\u2a02', + 'bigsqcup;': '\u2a06', + 'bigstar;': '\u2605', + 'bigtriangledown;': '\u25bd', + 'bigtriangleup;': '\u25b3', + 'biguplus;': '\u2a04', + 'bigvee;': '\u22c1', + 'bigwedge;': '\u22c0', + 'bkarow;': '\u290d', + 'blacklozenge;': '\u29eb', + 'blacksquare;': '\u25aa', + 'blacktriangle;': '\u25b4', + 'blacktriangledown;': '\u25be', + 'blacktriangleleft;': '\u25c2', + 'blacktriangleright;': '\u25b8', + 'blank;': '\u2423', + 'blk12;': '\u2592', + 'blk14;': '\u2591', + 'blk34;': '\u2593', + 'block;': '\u2588', + 'bne;': '=\u20e5', + 'bnequiv;': '\u2261\u20e5', + 'bNot;': '\u2aed', + 'bnot;': '\u2310', + 'Bopf;': '\U0001d539', + 'bopf;': '\U0001d553', + 'bot;': '\u22a5', + 'bottom;': '\u22a5', + 'bowtie;': '\u22c8', + 'boxbox;': '\u29c9', + 'boxDL;': '\u2557', + 'boxDl;': '\u2556', + 'boxdL;': '\u2555', + 'boxdl;': '\u2510', + 'boxDR;': '\u2554', + 'boxDr;': '\u2553', + 'boxdR;': '\u2552', + 'boxdr;': '\u250c', + 'boxH;': '\u2550', + 'boxh;': '\u2500', + 'boxHD;': '\u2566', + 'boxHd;': '\u2564', + 'boxhD;': '\u2565', + 'boxhd;': '\u252c', + 'boxHU;': '\u2569', + 'boxHu;': '\u2567', + 'boxhU;': '\u2568', + 'boxhu;': '\u2534', + 'boxminus;': '\u229f', + 'boxplus;': '\u229e', + 'boxtimes;': '\u22a0', + 'boxUL;': '\u255d', + 'boxUl;': '\u255c', + 'boxuL;': '\u255b', + 'boxul;': '\u2518', + 'boxUR;': '\u255a', + 'boxUr;': '\u2559', + 'boxuR;': '\u2558', + 'boxur;': '\u2514', + 'boxV;': '\u2551', + 'boxv;': '\u2502', + 'boxVH;': '\u256c', + 'boxVh;': '\u256b', + 'boxvH;': '\u256a', + 'boxvh;': '\u253c', + 'boxVL;': '\u2563', + 'boxVl;': '\u2562', + 'boxvL;': '\u2561', + 'boxvl;': '\u2524', + 'boxVR;': '\u2560', + 'boxVr;': '\u255f', + 'boxvR;': '\u255e', + 'boxvr;': '\u251c', + 'bprime;': '\u2035', + 'Breve;': '\u02d8', + 'breve;': '\u02d8', + 'brvbar': '\xa6', + 'brvbar;': '\xa6', + 'Bscr;': '\u212c', + 'bscr;': '\U0001d4b7', + 'bsemi;': '\u204f', + 'bsim;': '\u223d', + 'bsime;': '\u22cd', + 'bsol;': '\\', + 'bsolb;': '\u29c5', + 'bsolhsub;': '\u27c8', + 'bull;': '\u2022', + 'bullet;': '\u2022', + 'bump;': '\u224e', + 'bumpE;': '\u2aae', + 'bumpe;': '\u224f', + 'Bumpeq;': '\u224e', + 'bumpeq;': '\u224f', + 'Cacute;': '\u0106', + 'cacute;': '\u0107', + 'Cap;': '\u22d2', + 'cap;': '\u2229', + 'capand;': '\u2a44', + 'capbrcup;': '\u2a49', + 'capcap;': '\u2a4b', + 'capcup;': '\u2a47', + 'capdot;': '\u2a40', + 'CapitalDifferentialD;': '\u2145', + 'caps;': '\u2229\ufe00', + 'caret;': '\u2041', + 'caron;': '\u02c7', + 'Cayleys;': '\u212d', + 'ccaps;': '\u2a4d', + 'Ccaron;': '\u010c', + 'ccaron;': '\u010d', + 'Ccedil': '\xc7', + 'ccedil': '\xe7', + 'Ccedil;': '\xc7', + 'ccedil;': '\xe7', + 'Ccirc;': '\u0108', + 'ccirc;': '\u0109', + 'Cconint;': '\u2230', + 'ccups;': '\u2a4c', + 'ccupssm;': '\u2a50', + 'Cdot;': '\u010a', + 'cdot;': '\u010b', + 'cedil': '\xb8', + 'cedil;': '\xb8', + 'Cedilla;': '\xb8', + 'cemptyv;': '\u29b2', + 'cent': '\xa2', + 'cent;': '\xa2', + 'CenterDot;': '\xb7', + 'centerdot;': '\xb7', + 'Cfr;': '\u212d', + 'cfr;': '\U0001d520', + 'CHcy;': '\u0427', + 'chcy;': '\u0447', + 'check;': '\u2713', + 'checkmark;': '\u2713', + 'Chi;': '\u03a7', + 'chi;': '\u03c7', + 'cir;': '\u25cb', + 'circ;': '\u02c6', + 'circeq;': '\u2257', + 'circlearrowleft;': '\u21ba', + 'circlearrowright;': '\u21bb', + 'circledast;': '\u229b', + 'circledcirc;': '\u229a', + 'circleddash;': '\u229d', + 'CircleDot;': '\u2299', + 'circledR;': '\xae', + 'circledS;': '\u24c8', + 'CircleMinus;': '\u2296', + 'CirclePlus;': '\u2295', + 'CircleTimes;': '\u2297', + 'cirE;': '\u29c3', + 'cire;': '\u2257', + 'cirfnint;': '\u2a10', + 'cirmid;': '\u2aef', + 'cirscir;': '\u29c2', + 'ClockwiseContourIntegral;': '\u2232', + 'CloseCurlyDoubleQuote;': '\u201d', + 'CloseCurlyQuote;': '\u2019', + 'clubs;': '\u2663', + 'clubsuit;': '\u2663', + 'Colon;': '\u2237', + 'colon;': ':', + 'Colone;': '\u2a74', + 'colone;': '\u2254', + 'coloneq;': '\u2254', + 'comma;': ',', + 'commat;': '@', + 'comp;': '\u2201', + 'compfn;': '\u2218', + 'complement;': '\u2201', + 'complexes;': '\u2102', + 'cong;': '\u2245', + 'congdot;': '\u2a6d', + 'Congruent;': '\u2261', + 'Conint;': '\u222f', + 'conint;': '\u222e', + 'ContourIntegral;': '\u222e', + 'Copf;': '\u2102', + 'copf;': '\U0001d554', + 'coprod;': '\u2210', + 'Coproduct;': '\u2210', + 'COPY': '\xa9', + 'copy': '\xa9', + 'COPY;': '\xa9', + 'copy;': '\xa9', + 'copysr;': '\u2117', + 'CounterClockwiseContourIntegral;': '\u2233', + 'crarr;': '\u21b5', + 'Cross;': '\u2a2f', + 'cross;': '\u2717', + 'Cscr;': '\U0001d49e', + 'cscr;': '\U0001d4b8', + 'csub;': '\u2acf', + 'csube;': '\u2ad1', + 'csup;': '\u2ad0', + 'csupe;': '\u2ad2', + 'ctdot;': '\u22ef', + 'cudarrl;': '\u2938', + 'cudarrr;': '\u2935', + 'cuepr;': '\u22de', + 'cuesc;': '\u22df', + 'cularr;': '\u21b6', + 'cularrp;': '\u293d', + 'Cup;': '\u22d3', + 'cup;': '\u222a', + 'cupbrcap;': '\u2a48', + 'CupCap;': '\u224d', + 'cupcap;': '\u2a46', + 'cupcup;': '\u2a4a', + 'cupdot;': '\u228d', + 'cupor;': '\u2a45', + 'cups;': '\u222a\ufe00', + 'curarr;': '\u21b7', + 'curarrm;': '\u293c', + 'curlyeqprec;': '\u22de', + 'curlyeqsucc;': '\u22df', + 'curlyvee;': '\u22ce', + 'curlywedge;': '\u22cf', + 'curren': '\xa4', + 'curren;': '\xa4', + 'curvearrowleft;': '\u21b6', + 'curvearrowright;': '\u21b7', + 'cuvee;': '\u22ce', + 'cuwed;': '\u22cf', + 'cwconint;': '\u2232', + 'cwint;': '\u2231', + 'cylcty;': '\u232d', + 'Dagger;': '\u2021', + 'dagger;': '\u2020', + 'daleth;': '\u2138', + 'Darr;': '\u21a1', + 'dArr;': '\u21d3', + 'darr;': '\u2193', + 'dash;': '\u2010', + 'Dashv;': '\u2ae4', + 'dashv;': '\u22a3', + 'dbkarow;': '\u290f', + 'dblac;': '\u02dd', + 'Dcaron;': '\u010e', + 'dcaron;': '\u010f', + 'Dcy;': '\u0414', + 'dcy;': '\u0434', + 'DD;': '\u2145', + 'dd;': '\u2146', + 'ddagger;': '\u2021', + 'ddarr;': '\u21ca', + 'DDotrahd;': '\u2911', + 'ddotseq;': '\u2a77', + 'deg': '\xb0', + 'deg;': '\xb0', + 'Del;': '\u2207', + 'Delta;': '\u0394', + 'delta;': '\u03b4', + 'demptyv;': '\u29b1', + 'dfisht;': '\u297f', + 'Dfr;': '\U0001d507', + 'dfr;': '\U0001d521', + 'dHar;': '\u2965', + 'dharl;': '\u21c3', + 'dharr;': '\u21c2', + 'DiacriticalAcute;': '\xb4', + 'DiacriticalDot;': '\u02d9', + 'DiacriticalDoubleAcute;': '\u02dd', + 'DiacriticalGrave;': '`', + 'DiacriticalTilde;': '\u02dc', + 'diam;': '\u22c4', + 'Diamond;': '\u22c4', + 'diamond;': '\u22c4', + 'diamondsuit;': '\u2666', + 'diams;': '\u2666', + 'die;': '\xa8', + 'DifferentialD;': '\u2146', + 'digamma;': '\u03dd', + 'disin;': '\u22f2', + 'div;': '\xf7', + 'divide': '\xf7', + 'divide;': '\xf7', + 'divideontimes;': '\u22c7', + 'divonx;': '\u22c7', + 'DJcy;': '\u0402', + 'djcy;': '\u0452', + 'dlcorn;': '\u231e', + 'dlcrop;': '\u230d', + 'dollar;': '$', + 'Dopf;': '\U0001d53b', + 'dopf;': '\U0001d555', + 'Dot;': '\xa8', + 'dot;': '\u02d9', + 'DotDot;': '\u20dc', + 'doteq;': '\u2250', + 'doteqdot;': '\u2251', + 'DotEqual;': '\u2250', + 'dotminus;': '\u2238', + 'dotplus;': '\u2214', + 'dotsquare;': '\u22a1', + 'doublebarwedge;': '\u2306', + 'DoubleContourIntegral;': '\u222f', + 'DoubleDot;': '\xa8', + 'DoubleDownArrow;': '\u21d3', + 'DoubleLeftArrow;': '\u21d0', + 'DoubleLeftRightArrow;': '\u21d4', + 'DoubleLeftTee;': '\u2ae4', + 'DoubleLongLeftArrow;': '\u27f8', + 'DoubleLongLeftRightArrow;': '\u27fa', + 'DoubleLongRightArrow;': '\u27f9', + 'DoubleRightArrow;': '\u21d2', + 'DoubleRightTee;': '\u22a8', + 'DoubleUpArrow;': '\u21d1', + 'DoubleUpDownArrow;': '\u21d5', + 'DoubleVerticalBar;': '\u2225', + 'DownArrow;': '\u2193', + 'Downarrow;': '\u21d3', + 'downarrow;': '\u2193', + 'DownArrowBar;': '\u2913', + 'DownArrowUpArrow;': '\u21f5', + 'DownBreve;': '\u0311', + 'downdownarrows;': '\u21ca', + 'downharpoonleft;': '\u21c3', + 'downharpoonright;': '\u21c2', + 'DownLeftRightVector;': '\u2950', + 'DownLeftTeeVector;': '\u295e', + 'DownLeftVector;': '\u21bd', + 'DownLeftVectorBar;': '\u2956', + 'DownRightTeeVector;': '\u295f', + 'DownRightVector;': '\u21c1', + 'DownRightVectorBar;': '\u2957', + 'DownTee;': '\u22a4', + 'DownTeeArrow;': '\u21a7', + 'drbkarow;': '\u2910', + 'drcorn;': '\u231f', + 'drcrop;': '\u230c', + 'Dscr;': '\U0001d49f', + 'dscr;': '\U0001d4b9', + 'DScy;': '\u0405', + 'dscy;': '\u0455', + 'dsol;': '\u29f6', + 'Dstrok;': '\u0110', + 'dstrok;': '\u0111', + 'dtdot;': '\u22f1', + 'dtri;': '\u25bf', + 'dtrif;': '\u25be', + 'duarr;': '\u21f5', + 'duhar;': '\u296f', + 'dwangle;': '\u29a6', + 'DZcy;': '\u040f', + 'dzcy;': '\u045f', + 'dzigrarr;': '\u27ff', + 'Eacute': '\xc9', + 'eacute': '\xe9', + 'Eacute;': '\xc9', + 'eacute;': '\xe9', + 'easter;': '\u2a6e', + 'Ecaron;': '\u011a', + 'ecaron;': '\u011b', + 'ecir;': '\u2256', + 'Ecirc': '\xca', + 'ecirc': '\xea', + 'Ecirc;': '\xca', + 'ecirc;': '\xea', + 'ecolon;': '\u2255', + 'Ecy;': '\u042d', + 'ecy;': '\u044d', + 'eDDot;': '\u2a77', + 'Edot;': '\u0116', + 'eDot;': '\u2251', + 'edot;': '\u0117', + 'ee;': '\u2147', + 'efDot;': '\u2252', + 'Efr;': '\U0001d508', + 'efr;': '\U0001d522', + 'eg;': '\u2a9a', + 'Egrave': '\xc8', + 'egrave': '\xe8', + 'Egrave;': '\xc8', + 'egrave;': '\xe8', + 'egs;': '\u2a96', + 'egsdot;': '\u2a98', + 'el;': '\u2a99', + 'Element;': '\u2208', + 'elinters;': '\u23e7', + 'ell;': '\u2113', + 'els;': '\u2a95', + 'elsdot;': '\u2a97', + 'Emacr;': '\u0112', + 'emacr;': '\u0113', + 'empty;': '\u2205', + 'emptyset;': '\u2205', + 'EmptySmallSquare;': '\u25fb', + 'emptyv;': '\u2205', + 'EmptyVerySmallSquare;': '\u25ab', + 'emsp13;': '\u2004', + 'emsp14;': '\u2005', + 'emsp;': '\u2003', + 'ENG;': '\u014a', + 'eng;': '\u014b', + 'ensp;': '\u2002', + 'Eogon;': '\u0118', + 'eogon;': '\u0119', + 'Eopf;': '\U0001d53c', + 'eopf;': '\U0001d556', + 'epar;': '\u22d5', + 'eparsl;': '\u29e3', + 'eplus;': '\u2a71', + 'epsi;': '\u03b5', + 'Epsilon;': '\u0395', + 'epsilon;': '\u03b5', + 'epsiv;': '\u03f5', + 'eqcirc;': '\u2256', + 'eqcolon;': '\u2255', + 'eqsim;': '\u2242', + 'eqslantgtr;': '\u2a96', + 'eqslantless;': '\u2a95', + 'Equal;': '\u2a75', + 'equals;': '=', + 'EqualTilde;': '\u2242', + 'equest;': '\u225f', + 'Equilibrium;': '\u21cc', + 'equiv;': '\u2261', + 'equivDD;': '\u2a78', + 'eqvparsl;': '\u29e5', + 'erarr;': '\u2971', + 'erDot;': '\u2253', + 'Escr;': '\u2130', + 'escr;': '\u212f', + 'esdot;': '\u2250', + 'Esim;': '\u2a73', + 'esim;': '\u2242', + 'Eta;': '\u0397', + 'eta;': '\u03b7', + 'ETH': '\xd0', + 'eth': '\xf0', + 'ETH;': '\xd0', + 'eth;': '\xf0', + 'Euml': '\xcb', + 'euml': '\xeb', + 'Euml;': '\xcb', + 'euml;': '\xeb', + 'euro;': '\u20ac', + 'excl;': '!', + 'exist;': '\u2203', + 'Exists;': '\u2203', + 'expectation;': '\u2130', + 'ExponentialE;': '\u2147', + 'exponentiale;': '\u2147', + 'fallingdotseq;': '\u2252', + 'Fcy;': '\u0424', + 'fcy;': '\u0444', + 'female;': '\u2640', + 'ffilig;': '\ufb03', + 'fflig;': '\ufb00', + 'ffllig;': '\ufb04', + 'Ffr;': '\U0001d509', + 'ffr;': '\U0001d523', + 'filig;': '\ufb01', + 'FilledSmallSquare;': '\u25fc', + 'FilledVerySmallSquare;': '\u25aa', + 'fjlig;': 'fj', + 'flat;': '\u266d', + 'fllig;': '\ufb02', + 'fltns;': '\u25b1', + 'fnof;': '\u0192', + 'Fopf;': '\U0001d53d', + 'fopf;': '\U0001d557', + 'ForAll;': '\u2200', + 'forall;': '\u2200', + 'fork;': '\u22d4', + 'forkv;': '\u2ad9', + 'Fouriertrf;': '\u2131', + 'fpartint;': '\u2a0d', + 'frac12': '\xbd', + 'frac12;': '\xbd', + 'frac13;': '\u2153', + 'frac14': '\xbc', + 'frac14;': '\xbc', + 'frac15;': '\u2155', + 'frac16;': '\u2159', + 'frac18;': '\u215b', + 'frac23;': '\u2154', + 'frac25;': '\u2156', + 'frac34': '\xbe', + 'frac34;': '\xbe', + 'frac35;': '\u2157', + 'frac38;': '\u215c', + 'frac45;': '\u2158', + 'frac56;': '\u215a', + 'frac58;': '\u215d', + 'frac78;': '\u215e', + 'frasl;': '\u2044', + 'frown;': '\u2322', + 'Fscr;': '\u2131', + 'fscr;': '\U0001d4bb', + 'gacute;': '\u01f5', + 'Gamma;': '\u0393', + 'gamma;': '\u03b3', + 'Gammad;': '\u03dc', + 'gammad;': '\u03dd', + 'gap;': '\u2a86', + 'Gbreve;': '\u011e', + 'gbreve;': '\u011f', + 'Gcedil;': '\u0122', + 'Gcirc;': '\u011c', + 'gcirc;': '\u011d', + 'Gcy;': '\u0413', + 'gcy;': '\u0433', + 'Gdot;': '\u0120', + 'gdot;': '\u0121', + 'gE;': '\u2267', + 'ge;': '\u2265', + 'gEl;': '\u2a8c', + 'gel;': '\u22db', + 'geq;': '\u2265', + 'geqq;': '\u2267', + 'geqslant;': '\u2a7e', + 'ges;': '\u2a7e', + 'gescc;': '\u2aa9', + 'gesdot;': '\u2a80', + 'gesdoto;': '\u2a82', + 'gesdotol;': '\u2a84', + 'gesl;': '\u22db\ufe00', + 'gesles;': '\u2a94', + 'Gfr;': '\U0001d50a', + 'gfr;': '\U0001d524', + 'Gg;': '\u22d9', + 'gg;': '\u226b', + 'ggg;': '\u22d9', + 'gimel;': '\u2137', + 'GJcy;': '\u0403', + 'gjcy;': '\u0453', + 'gl;': '\u2277', + 'gla;': '\u2aa5', + 'glE;': '\u2a92', + 'glj;': '\u2aa4', + 'gnap;': '\u2a8a', + 'gnapprox;': '\u2a8a', + 'gnE;': '\u2269', + 'gne;': '\u2a88', + 'gneq;': '\u2a88', + 'gneqq;': '\u2269', + 'gnsim;': '\u22e7', + 'Gopf;': '\U0001d53e', + 'gopf;': '\U0001d558', + 'grave;': '`', + 'GreaterEqual;': '\u2265', + 'GreaterEqualLess;': '\u22db', + 'GreaterFullEqual;': '\u2267', + 'GreaterGreater;': '\u2aa2', + 'GreaterLess;': '\u2277', + 'GreaterSlantEqual;': '\u2a7e', + 'GreaterTilde;': '\u2273', + 'Gscr;': '\U0001d4a2', + 'gscr;': '\u210a', + 'gsim;': '\u2273', + 'gsime;': '\u2a8e', + 'gsiml;': '\u2a90', + 'GT': '>', + 'gt': '>', + 'GT;': '>', + 'Gt;': '\u226b', + 'gt;': '>', + 'gtcc;': '\u2aa7', + 'gtcir;': '\u2a7a', + 'gtdot;': '\u22d7', + 'gtlPar;': '\u2995', + 'gtquest;': '\u2a7c', + 'gtrapprox;': '\u2a86', + 'gtrarr;': '\u2978', + 'gtrdot;': '\u22d7', + 'gtreqless;': '\u22db', + 'gtreqqless;': '\u2a8c', + 'gtrless;': '\u2277', + 'gtrsim;': '\u2273', + 'gvertneqq;': '\u2269\ufe00', + 'gvnE;': '\u2269\ufe00', + 'Hacek;': '\u02c7', + 'hairsp;': '\u200a', + 'half;': '\xbd', + 'hamilt;': '\u210b', + 'HARDcy;': '\u042a', + 'hardcy;': '\u044a', + 'hArr;': '\u21d4', + 'harr;': '\u2194', + 'harrcir;': '\u2948', + 'harrw;': '\u21ad', + 'Hat;': '^', + 'hbar;': '\u210f', + 'Hcirc;': '\u0124', + 'hcirc;': '\u0125', + 'hearts;': '\u2665', + 'heartsuit;': '\u2665', + 'hellip;': '\u2026', + 'hercon;': '\u22b9', + 'Hfr;': '\u210c', + 'hfr;': '\U0001d525', + 'HilbertSpace;': '\u210b', + 'hksearow;': '\u2925', + 'hkswarow;': '\u2926', + 'hoarr;': '\u21ff', + 'homtht;': '\u223b', + 'hookleftarrow;': '\u21a9', + 'hookrightarrow;': '\u21aa', + 'Hopf;': '\u210d', + 'hopf;': '\U0001d559', + 'horbar;': '\u2015', + 'HorizontalLine;': '\u2500', + 'Hscr;': '\u210b', + 'hscr;': '\U0001d4bd', + 'hslash;': '\u210f', + 'Hstrok;': '\u0126', + 'hstrok;': '\u0127', + 'HumpDownHump;': '\u224e', + 'HumpEqual;': '\u224f', + 'hybull;': '\u2043', + 'hyphen;': '\u2010', + 'Iacute': '\xcd', + 'iacute': '\xed', + 'Iacute;': '\xcd', + 'iacute;': '\xed', + 'ic;': '\u2063', + 'Icirc': '\xce', + 'icirc': '\xee', + 'Icirc;': '\xce', + 'icirc;': '\xee', + 'Icy;': '\u0418', + 'icy;': '\u0438', + 'Idot;': '\u0130', + 'IEcy;': '\u0415', + 'iecy;': '\u0435', + 'iexcl': '\xa1', + 'iexcl;': '\xa1', + 'iff;': '\u21d4', + 'Ifr;': '\u2111', + 'ifr;': '\U0001d526', + 'Igrave': '\xcc', + 'igrave': '\xec', + 'Igrave;': '\xcc', + 'igrave;': '\xec', + 'ii;': '\u2148', + 'iiiint;': '\u2a0c', + 'iiint;': '\u222d', + 'iinfin;': '\u29dc', + 'iiota;': '\u2129', + 'IJlig;': '\u0132', + 'ijlig;': '\u0133', + 'Im;': '\u2111', + 'Imacr;': '\u012a', + 'imacr;': '\u012b', + 'image;': '\u2111', + 'ImaginaryI;': '\u2148', + 'imagline;': '\u2110', + 'imagpart;': '\u2111', + 'imath;': '\u0131', + 'imof;': '\u22b7', + 'imped;': '\u01b5', + 'Implies;': '\u21d2', + 'in;': '\u2208', + 'incare;': '\u2105', + 'infin;': '\u221e', + 'infintie;': '\u29dd', + 'inodot;': '\u0131', + 'Int;': '\u222c', + 'int;': '\u222b', + 'intcal;': '\u22ba', + 'integers;': '\u2124', + 'Integral;': '\u222b', + 'intercal;': '\u22ba', + 'Intersection;': '\u22c2', + 'intlarhk;': '\u2a17', + 'intprod;': '\u2a3c', + 'InvisibleComma;': '\u2063', + 'InvisibleTimes;': '\u2062', + 'IOcy;': '\u0401', + 'iocy;': '\u0451', + 'Iogon;': '\u012e', + 'iogon;': '\u012f', + 'Iopf;': '\U0001d540', + 'iopf;': '\U0001d55a', + 'Iota;': '\u0399', + 'iota;': '\u03b9', + 'iprod;': '\u2a3c', + 'iquest': '\xbf', + 'iquest;': '\xbf', + 'Iscr;': '\u2110', + 'iscr;': '\U0001d4be', + 'isin;': '\u2208', + 'isindot;': '\u22f5', + 'isinE;': '\u22f9', + 'isins;': '\u22f4', + 'isinsv;': '\u22f3', + 'isinv;': '\u2208', + 'it;': '\u2062', + 'Itilde;': '\u0128', + 'itilde;': '\u0129', + 'Iukcy;': '\u0406', + 'iukcy;': '\u0456', + 'Iuml': '\xcf', + 'iuml': '\xef', + 'Iuml;': '\xcf', + 'iuml;': '\xef', + 'Jcirc;': '\u0134', + 'jcirc;': '\u0135', + 'Jcy;': '\u0419', + 'jcy;': '\u0439', + 'Jfr;': '\U0001d50d', + 'jfr;': '\U0001d527', + 'jmath;': '\u0237', + 'Jopf;': '\U0001d541', + 'jopf;': '\U0001d55b', + 'Jscr;': '\U0001d4a5', + 'jscr;': '\U0001d4bf', + 'Jsercy;': '\u0408', + 'jsercy;': '\u0458', + 'Jukcy;': '\u0404', + 'jukcy;': '\u0454', + 'Kappa;': '\u039a', + 'kappa;': '\u03ba', + 'kappav;': '\u03f0', + 'Kcedil;': '\u0136', + 'kcedil;': '\u0137', + 'Kcy;': '\u041a', + 'kcy;': '\u043a', + 'Kfr;': '\U0001d50e', + 'kfr;': '\U0001d528', + 'kgreen;': '\u0138', + 'KHcy;': '\u0425', + 'khcy;': '\u0445', + 'KJcy;': '\u040c', + 'kjcy;': '\u045c', + 'Kopf;': '\U0001d542', + 'kopf;': '\U0001d55c', + 'Kscr;': '\U0001d4a6', + 'kscr;': '\U0001d4c0', + 'lAarr;': '\u21da', + 'Lacute;': '\u0139', + 'lacute;': '\u013a', + 'laemptyv;': '\u29b4', + 'lagran;': '\u2112', + 'Lambda;': '\u039b', + 'lambda;': '\u03bb', + 'Lang;': '\u27ea', + 'lang;': '\u27e8', + 'langd;': '\u2991', + 'langle;': '\u27e8', + 'lap;': '\u2a85', + 'Laplacetrf;': '\u2112', + 'laquo': '\xab', + 'laquo;': '\xab', + 'Larr;': '\u219e', + 'lArr;': '\u21d0', + 'larr;': '\u2190', + 'larrb;': '\u21e4', + 'larrbfs;': '\u291f', + 'larrfs;': '\u291d', + 'larrhk;': '\u21a9', + 'larrlp;': '\u21ab', + 'larrpl;': '\u2939', + 'larrsim;': '\u2973', + 'larrtl;': '\u21a2', + 'lat;': '\u2aab', + 'lAtail;': '\u291b', + 'latail;': '\u2919', + 'late;': '\u2aad', + 'lates;': '\u2aad\ufe00', + 'lBarr;': '\u290e', + 'lbarr;': '\u290c', + 'lbbrk;': '\u2772', + 'lbrace;': '{', + 'lbrack;': '[', + 'lbrke;': '\u298b', + 'lbrksld;': '\u298f', + 'lbrkslu;': '\u298d', + 'Lcaron;': '\u013d', + 'lcaron;': '\u013e', + 'Lcedil;': '\u013b', + 'lcedil;': '\u013c', + 'lceil;': '\u2308', + 'lcub;': '{', + 'Lcy;': '\u041b', + 'lcy;': '\u043b', + 'ldca;': '\u2936', + 'ldquo;': '\u201c', + 'ldquor;': '\u201e', + 'ldrdhar;': '\u2967', + 'ldrushar;': '\u294b', + 'ldsh;': '\u21b2', + 'lE;': '\u2266', + 'le;': '\u2264', + 'LeftAngleBracket;': '\u27e8', + 'LeftArrow;': '\u2190', + 'Leftarrow;': '\u21d0', + 'leftarrow;': '\u2190', + 'LeftArrowBar;': '\u21e4', + 'LeftArrowRightArrow;': '\u21c6', + 'leftarrowtail;': '\u21a2', + 'LeftCeiling;': '\u2308', + 'LeftDoubleBracket;': '\u27e6', + 'LeftDownTeeVector;': '\u2961', + 'LeftDownVector;': '\u21c3', + 'LeftDownVectorBar;': '\u2959', + 'LeftFloor;': '\u230a', + 'leftharpoondown;': '\u21bd', + 'leftharpoonup;': '\u21bc', + 'leftleftarrows;': '\u21c7', + 'LeftRightArrow;': '\u2194', + 'Leftrightarrow;': '\u21d4', + 'leftrightarrow;': '\u2194', + 'leftrightarrows;': '\u21c6', + 'leftrightharpoons;': '\u21cb', + 'leftrightsquigarrow;': '\u21ad', + 'LeftRightVector;': '\u294e', + 'LeftTee;': '\u22a3', + 'LeftTeeArrow;': '\u21a4', + 'LeftTeeVector;': '\u295a', + 'leftthreetimes;': '\u22cb', + 'LeftTriangle;': '\u22b2', + 'LeftTriangleBar;': '\u29cf', + 'LeftTriangleEqual;': '\u22b4', + 'LeftUpDownVector;': '\u2951', + 'LeftUpTeeVector;': '\u2960', + 'LeftUpVector;': '\u21bf', + 'LeftUpVectorBar;': '\u2958', + 'LeftVector;': '\u21bc', + 'LeftVectorBar;': '\u2952', + 'lEg;': '\u2a8b', + 'leg;': '\u22da', + 'leq;': '\u2264', + 'leqq;': '\u2266', + 'leqslant;': '\u2a7d', + 'les;': '\u2a7d', + 'lescc;': '\u2aa8', + 'lesdot;': '\u2a7f', + 'lesdoto;': '\u2a81', + 'lesdotor;': '\u2a83', + 'lesg;': '\u22da\ufe00', + 'lesges;': '\u2a93', + 'lessapprox;': '\u2a85', + 'lessdot;': '\u22d6', + 'lesseqgtr;': '\u22da', + 'lesseqqgtr;': '\u2a8b', + 'LessEqualGreater;': '\u22da', + 'LessFullEqual;': '\u2266', + 'LessGreater;': '\u2276', + 'lessgtr;': '\u2276', + 'LessLess;': '\u2aa1', + 'lesssim;': '\u2272', + 'LessSlantEqual;': '\u2a7d', + 'LessTilde;': '\u2272', + 'lfisht;': '\u297c', + 'lfloor;': '\u230a', + 'Lfr;': '\U0001d50f', + 'lfr;': '\U0001d529', + 'lg;': '\u2276', + 'lgE;': '\u2a91', + 'lHar;': '\u2962', + 'lhard;': '\u21bd', + 'lharu;': '\u21bc', + 'lharul;': '\u296a', + 'lhblk;': '\u2584', + 'LJcy;': '\u0409', + 'ljcy;': '\u0459', + 'Ll;': '\u22d8', + 'll;': '\u226a', + 'llarr;': '\u21c7', + 'llcorner;': '\u231e', + 'Lleftarrow;': '\u21da', + 'llhard;': '\u296b', + 'lltri;': '\u25fa', + 'Lmidot;': '\u013f', + 'lmidot;': '\u0140', + 'lmoust;': '\u23b0', + 'lmoustache;': '\u23b0', + 'lnap;': '\u2a89', + 'lnapprox;': '\u2a89', + 'lnE;': '\u2268', + 'lne;': '\u2a87', + 'lneq;': '\u2a87', + 'lneqq;': '\u2268', + 'lnsim;': '\u22e6', + 'loang;': '\u27ec', + 'loarr;': '\u21fd', + 'lobrk;': '\u27e6', + 'LongLeftArrow;': '\u27f5', + 'Longleftarrow;': '\u27f8', + 'longleftarrow;': '\u27f5', + 'LongLeftRightArrow;': '\u27f7', + 'Longleftrightarrow;': '\u27fa', + 'longleftrightarrow;': '\u27f7', + 'longmapsto;': '\u27fc', + 'LongRightArrow;': '\u27f6', + 'Longrightarrow;': '\u27f9', + 'longrightarrow;': '\u27f6', + 'looparrowleft;': '\u21ab', + 'looparrowright;': '\u21ac', + 'lopar;': '\u2985', + 'Lopf;': '\U0001d543', + 'lopf;': '\U0001d55d', + 'loplus;': '\u2a2d', + 'lotimes;': '\u2a34', + 'lowast;': '\u2217', + 'lowbar;': '_', + 'LowerLeftArrow;': '\u2199', + 'LowerRightArrow;': '\u2198', + 'loz;': '\u25ca', + 'lozenge;': '\u25ca', + 'lozf;': '\u29eb', + 'lpar;': '(', + 'lparlt;': '\u2993', + 'lrarr;': '\u21c6', + 'lrcorner;': '\u231f', + 'lrhar;': '\u21cb', + 'lrhard;': '\u296d', + 'lrm;': '\u200e', + 'lrtri;': '\u22bf', + 'lsaquo;': '\u2039', + 'Lscr;': '\u2112', + 'lscr;': '\U0001d4c1', + 'Lsh;': '\u21b0', + 'lsh;': '\u21b0', + 'lsim;': '\u2272', + 'lsime;': '\u2a8d', + 'lsimg;': '\u2a8f', + 'lsqb;': '[', + 'lsquo;': '\u2018', + 'lsquor;': '\u201a', + 'Lstrok;': '\u0141', + 'lstrok;': '\u0142', + 'LT': '<', + 'lt': '<', + 'LT;': '<', + 'Lt;': '\u226a', + 'lt;': '<', + 'ltcc;': '\u2aa6', + 'ltcir;': '\u2a79', + 'ltdot;': '\u22d6', + 'lthree;': '\u22cb', + 'ltimes;': '\u22c9', + 'ltlarr;': '\u2976', + 'ltquest;': '\u2a7b', + 'ltri;': '\u25c3', + 'ltrie;': '\u22b4', + 'ltrif;': '\u25c2', + 'ltrPar;': '\u2996', + 'lurdshar;': '\u294a', + 'luruhar;': '\u2966', + 'lvertneqq;': '\u2268\ufe00', + 'lvnE;': '\u2268\ufe00', + 'macr': '\xaf', + 'macr;': '\xaf', + 'male;': '\u2642', + 'malt;': '\u2720', + 'maltese;': '\u2720', + 'Map;': '\u2905', + 'map;': '\u21a6', + 'mapsto;': '\u21a6', + 'mapstodown;': '\u21a7', + 'mapstoleft;': '\u21a4', + 'mapstoup;': '\u21a5', + 'marker;': '\u25ae', + 'mcomma;': '\u2a29', + 'Mcy;': '\u041c', + 'mcy;': '\u043c', + 'mdash;': '\u2014', + 'mDDot;': '\u223a', + 'measuredangle;': '\u2221', + 'MediumSpace;': '\u205f', + 'Mellintrf;': '\u2133', + 'Mfr;': '\U0001d510', + 'mfr;': '\U0001d52a', + 'mho;': '\u2127', + 'micro': '\xb5', + 'micro;': '\xb5', + 'mid;': '\u2223', + 'midast;': '*', + 'midcir;': '\u2af0', + 'middot': '\xb7', + 'middot;': '\xb7', + 'minus;': '\u2212', + 'minusb;': '\u229f', + 'minusd;': '\u2238', + 'minusdu;': '\u2a2a', + 'MinusPlus;': '\u2213', + 'mlcp;': '\u2adb', + 'mldr;': '\u2026', + 'mnplus;': '\u2213', + 'models;': '\u22a7', + 'Mopf;': '\U0001d544', + 'mopf;': '\U0001d55e', + 'mp;': '\u2213', + 'Mscr;': '\u2133', + 'mscr;': '\U0001d4c2', + 'mstpos;': '\u223e', + 'Mu;': '\u039c', + 'mu;': '\u03bc', + 'multimap;': '\u22b8', + 'mumap;': '\u22b8', + 'nabla;': '\u2207', + 'Nacute;': '\u0143', + 'nacute;': '\u0144', + 'nang;': '\u2220\u20d2', + 'nap;': '\u2249', + 'napE;': '\u2a70\u0338', + 'napid;': '\u224b\u0338', + 'napos;': '\u0149', + 'napprox;': '\u2249', + 'natur;': '\u266e', + 'natural;': '\u266e', + 'naturals;': '\u2115', + 'nbsp': '\xa0', + 'nbsp;': '\xa0', + 'nbump;': '\u224e\u0338', + 'nbumpe;': '\u224f\u0338', + 'ncap;': '\u2a43', + 'Ncaron;': '\u0147', + 'ncaron;': '\u0148', + 'Ncedil;': '\u0145', + 'ncedil;': '\u0146', + 'ncong;': '\u2247', + 'ncongdot;': '\u2a6d\u0338', + 'ncup;': '\u2a42', + 'Ncy;': '\u041d', + 'ncy;': '\u043d', + 'ndash;': '\u2013', + 'ne;': '\u2260', + 'nearhk;': '\u2924', + 'neArr;': '\u21d7', + 'nearr;': '\u2197', + 'nearrow;': '\u2197', + 'nedot;': '\u2250\u0338', + 'NegativeMediumSpace;': '\u200b', + 'NegativeThickSpace;': '\u200b', + 'NegativeThinSpace;': '\u200b', + 'NegativeVeryThinSpace;': '\u200b', + 'nequiv;': '\u2262', + 'nesear;': '\u2928', + 'nesim;': '\u2242\u0338', + 'NestedGreaterGreater;': '\u226b', + 'NestedLessLess;': '\u226a', + 'NewLine;': '\n', + 'nexist;': '\u2204', + 'nexists;': '\u2204', + 'Nfr;': '\U0001d511', + 'nfr;': '\U0001d52b', + 'ngE;': '\u2267\u0338', + 'nge;': '\u2271', + 'ngeq;': '\u2271', + 'ngeqq;': '\u2267\u0338', + 'ngeqslant;': '\u2a7e\u0338', + 'nges;': '\u2a7e\u0338', + 'nGg;': '\u22d9\u0338', + 'ngsim;': '\u2275', + 'nGt;': '\u226b\u20d2', + 'ngt;': '\u226f', + 'ngtr;': '\u226f', + 'nGtv;': '\u226b\u0338', + 'nhArr;': '\u21ce', + 'nharr;': '\u21ae', + 'nhpar;': '\u2af2', + 'ni;': '\u220b', + 'nis;': '\u22fc', + 'nisd;': '\u22fa', + 'niv;': '\u220b', + 'NJcy;': '\u040a', + 'njcy;': '\u045a', + 'nlArr;': '\u21cd', + 'nlarr;': '\u219a', + 'nldr;': '\u2025', + 'nlE;': '\u2266\u0338', + 'nle;': '\u2270', + 'nLeftarrow;': '\u21cd', + 'nleftarrow;': '\u219a', + 'nLeftrightarrow;': '\u21ce', + 'nleftrightarrow;': '\u21ae', + 'nleq;': '\u2270', + 'nleqq;': '\u2266\u0338', + 'nleqslant;': '\u2a7d\u0338', + 'nles;': '\u2a7d\u0338', + 'nless;': '\u226e', + 'nLl;': '\u22d8\u0338', + 'nlsim;': '\u2274', + 'nLt;': '\u226a\u20d2', + 'nlt;': '\u226e', + 'nltri;': '\u22ea', + 'nltrie;': '\u22ec', + 'nLtv;': '\u226a\u0338', + 'nmid;': '\u2224', + 'NoBreak;': '\u2060', + 'NonBreakingSpace;': '\xa0', + 'Nopf;': '\u2115', + 'nopf;': '\U0001d55f', + 'not': '\xac', + 'Not;': '\u2aec', + 'not;': '\xac', + 'NotCongruent;': '\u2262', + 'NotCupCap;': '\u226d', + 'NotDoubleVerticalBar;': '\u2226', + 'NotElement;': '\u2209', + 'NotEqual;': '\u2260', + 'NotEqualTilde;': '\u2242\u0338', + 'NotExists;': '\u2204', + 'NotGreater;': '\u226f', + 'NotGreaterEqual;': '\u2271', + 'NotGreaterFullEqual;': '\u2267\u0338', + 'NotGreaterGreater;': '\u226b\u0338', + 'NotGreaterLess;': '\u2279', + 'NotGreaterSlantEqual;': '\u2a7e\u0338', + 'NotGreaterTilde;': '\u2275', + 'NotHumpDownHump;': '\u224e\u0338', + 'NotHumpEqual;': '\u224f\u0338', + 'notin;': '\u2209', + 'notindot;': '\u22f5\u0338', + 'notinE;': '\u22f9\u0338', + 'notinva;': '\u2209', + 'notinvb;': '\u22f7', + 'notinvc;': '\u22f6', + 'NotLeftTriangle;': '\u22ea', + 'NotLeftTriangleBar;': '\u29cf\u0338', + 'NotLeftTriangleEqual;': '\u22ec', + 'NotLess;': '\u226e', + 'NotLessEqual;': '\u2270', + 'NotLessGreater;': '\u2278', + 'NotLessLess;': '\u226a\u0338', + 'NotLessSlantEqual;': '\u2a7d\u0338', + 'NotLessTilde;': '\u2274', + 'NotNestedGreaterGreater;': '\u2aa2\u0338', + 'NotNestedLessLess;': '\u2aa1\u0338', + 'notni;': '\u220c', + 'notniva;': '\u220c', + 'notnivb;': '\u22fe', + 'notnivc;': '\u22fd', + 'NotPrecedes;': '\u2280', + 'NotPrecedesEqual;': '\u2aaf\u0338', + 'NotPrecedesSlantEqual;': '\u22e0', + 'NotReverseElement;': '\u220c', + 'NotRightTriangle;': '\u22eb', + 'NotRightTriangleBar;': '\u29d0\u0338', + 'NotRightTriangleEqual;': '\u22ed', + 'NotSquareSubset;': '\u228f\u0338', + 'NotSquareSubsetEqual;': '\u22e2', + 'NotSquareSuperset;': '\u2290\u0338', + 'NotSquareSupersetEqual;': '\u22e3', + 'NotSubset;': '\u2282\u20d2', + 'NotSubsetEqual;': '\u2288', + 'NotSucceeds;': '\u2281', + 'NotSucceedsEqual;': '\u2ab0\u0338', + 'NotSucceedsSlantEqual;': '\u22e1', + 'NotSucceedsTilde;': '\u227f\u0338', + 'NotSuperset;': '\u2283\u20d2', + 'NotSupersetEqual;': '\u2289', + 'NotTilde;': '\u2241', + 'NotTildeEqual;': '\u2244', + 'NotTildeFullEqual;': '\u2247', + 'NotTildeTilde;': '\u2249', + 'NotVerticalBar;': '\u2224', + 'npar;': '\u2226', + 'nparallel;': '\u2226', + 'nparsl;': '\u2afd\u20e5', + 'npart;': '\u2202\u0338', + 'npolint;': '\u2a14', + 'npr;': '\u2280', + 'nprcue;': '\u22e0', + 'npre;': '\u2aaf\u0338', + 'nprec;': '\u2280', + 'npreceq;': '\u2aaf\u0338', + 'nrArr;': '\u21cf', + 'nrarr;': '\u219b', + 'nrarrc;': '\u2933\u0338', + 'nrarrw;': '\u219d\u0338', + 'nRightarrow;': '\u21cf', + 'nrightarrow;': '\u219b', + 'nrtri;': '\u22eb', + 'nrtrie;': '\u22ed', + 'nsc;': '\u2281', + 'nsccue;': '\u22e1', + 'nsce;': '\u2ab0\u0338', + 'Nscr;': '\U0001d4a9', + 'nscr;': '\U0001d4c3', + 'nshortmid;': '\u2224', + 'nshortparallel;': '\u2226', + 'nsim;': '\u2241', + 'nsime;': '\u2244', + 'nsimeq;': '\u2244', + 'nsmid;': '\u2224', + 'nspar;': '\u2226', + 'nsqsube;': '\u22e2', + 'nsqsupe;': '\u22e3', + 'nsub;': '\u2284', + 'nsubE;': '\u2ac5\u0338', + 'nsube;': '\u2288', + 'nsubset;': '\u2282\u20d2', + 'nsubseteq;': '\u2288', + 'nsubseteqq;': '\u2ac5\u0338', + 'nsucc;': '\u2281', + 'nsucceq;': '\u2ab0\u0338', + 'nsup;': '\u2285', + 'nsupE;': '\u2ac6\u0338', + 'nsupe;': '\u2289', + 'nsupset;': '\u2283\u20d2', + 'nsupseteq;': '\u2289', + 'nsupseteqq;': '\u2ac6\u0338', + 'ntgl;': '\u2279', + 'Ntilde': '\xd1', + 'ntilde': '\xf1', + 'Ntilde;': '\xd1', + 'ntilde;': '\xf1', + 'ntlg;': '\u2278', + 'ntriangleleft;': '\u22ea', + 'ntrianglelefteq;': '\u22ec', + 'ntriangleright;': '\u22eb', + 'ntrianglerighteq;': '\u22ed', + 'Nu;': '\u039d', + 'nu;': '\u03bd', + 'num;': '#', + 'numero;': '\u2116', + 'numsp;': '\u2007', + 'nvap;': '\u224d\u20d2', + 'nVDash;': '\u22af', + 'nVdash;': '\u22ae', + 'nvDash;': '\u22ad', + 'nvdash;': '\u22ac', + 'nvge;': '\u2265\u20d2', + 'nvgt;': '>\u20d2', + 'nvHarr;': '\u2904', + 'nvinfin;': '\u29de', + 'nvlArr;': '\u2902', + 'nvle;': '\u2264\u20d2', + 'nvlt;': '<\u20d2', + 'nvltrie;': '\u22b4\u20d2', + 'nvrArr;': '\u2903', + 'nvrtrie;': '\u22b5\u20d2', + 'nvsim;': '\u223c\u20d2', + 'nwarhk;': '\u2923', + 'nwArr;': '\u21d6', + 'nwarr;': '\u2196', + 'nwarrow;': '\u2196', + 'nwnear;': '\u2927', + 'Oacute': '\xd3', + 'oacute': '\xf3', + 'Oacute;': '\xd3', + 'oacute;': '\xf3', + 'oast;': '\u229b', + 'ocir;': '\u229a', + 'Ocirc': '\xd4', + 'ocirc': '\xf4', + 'Ocirc;': '\xd4', + 'ocirc;': '\xf4', + 'Ocy;': '\u041e', + 'ocy;': '\u043e', + 'odash;': '\u229d', + 'Odblac;': '\u0150', + 'odblac;': '\u0151', + 'odiv;': '\u2a38', + 'odot;': '\u2299', + 'odsold;': '\u29bc', + 'OElig;': '\u0152', + 'oelig;': '\u0153', + 'ofcir;': '\u29bf', + 'Ofr;': '\U0001d512', + 'ofr;': '\U0001d52c', + 'ogon;': '\u02db', + 'Ograve': '\xd2', + 'ograve': '\xf2', + 'Ograve;': '\xd2', + 'ograve;': '\xf2', + 'ogt;': '\u29c1', + 'ohbar;': '\u29b5', + 'ohm;': '\u03a9', + 'oint;': '\u222e', + 'olarr;': '\u21ba', + 'olcir;': '\u29be', + 'olcross;': '\u29bb', + 'oline;': '\u203e', + 'olt;': '\u29c0', + 'Omacr;': '\u014c', + 'omacr;': '\u014d', + 'Omega;': '\u03a9', + 'omega;': '\u03c9', + 'Omicron;': '\u039f', + 'omicron;': '\u03bf', + 'omid;': '\u29b6', + 'ominus;': '\u2296', + 'Oopf;': '\U0001d546', + 'oopf;': '\U0001d560', + 'opar;': '\u29b7', + 'OpenCurlyDoubleQuote;': '\u201c', + 'OpenCurlyQuote;': '\u2018', + 'operp;': '\u29b9', + 'oplus;': '\u2295', + 'Or;': '\u2a54', + 'or;': '\u2228', + 'orarr;': '\u21bb', + 'ord;': '\u2a5d', + 'order;': '\u2134', + 'orderof;': '\u2134', + 'ordf': '\xaa', + 'ordf;': '\xaa', + 'ordm': '\xba', + 'ordm;': '\xba', + 'origof;': '\u22b6', + 'oror;': '\u2a56', + 'orslope;': '\u2a57', + 'orv;': '\u2a5b', + 'oS;': '\u24c8', + 'Oscr;': '\U0001d4aa', + 'oscr;': '\u2134', + 'Oslash': '\xd8', + 'oslash': '\xf8', + 'Oslash;': '\xd8', + 'oslash;': '\xf8', + 'osol;': '\u2298', + 'Otilde': '\xd5', + 'otilde': '\xf5', + 'Otilde;': '\xd5', + 'otilde;': '\xf5', + 'Otimes;': '\u2a37', + 'otimes;': '\u2297', + 'otimesas;': '\u2a36', + 'Ouml': '\xd6', + 'ouml': '\xf6', + 'Ouml;': '\xd6', + 'ouml;': '\xf6', + 'ovbar;': '\u233d', + 'OverBar;': '\u203e', + 'OverBrace;': '\u23de', + 'OverBracket;': '\u23b4', + 'OverParenthesis;': '\u23dc', + 'par;': '\u2225', + 'para': '\xb6', + 'para;': '\xb6', + 'parallel;': '\u2225', + 'parsim;': '\u2af3', + 'parsl;': '\u2afd', + 'part;': '\u2202', + 'PartialD;': '\u2202', + 'Pcy;': '\u041f', + 'pcy;': '\u043f', + 'percnt;': '%', + 'period;': '.', + 'permil;': '\u2030', + 'perp;': '\u22a5', + 'pertenk;': '\u2031', + 'Pfr;': '\U0001d513', + 'pfr;': '\U0001d52d', + 'Phi;': '\u03a6', + 'phi;': '\u03c6', + 'phiv;': '\u03d5', + 'phmmat;': '\u2133', + 'phone;': '\u260e', + 'Pi;': '\u03a0', + 'pi;': '\u03c0', + 'pitchfork;': '\u22d4', + 'piv;': '\u03d6', + 'planck;': '\u210f', + 'planckh;': '\u210e', + 'plankv;': '\u210f', + 'plus;': '+', + 'plusacir;': '\u2a23', + 'plusb;': '\u229e', + 'pluscir;': '\u2a22', + 'plusdo;': '\u2214', + 'plusdu;': '\u2a25', + 'pluse;': '\u2a72', + 'PlusMinus;': '\xb1', + 'plusmn': '\xb1', + 'plusmn;': '\xb1', + 'plussim;': '\u2a26', + 'plustwo;': '\u2a27', + 'pm;': '\xb1', + 'Poincareplane;': '\u210c', + 'pointint;': '\u2a15', + 'Popf;': '\u2119', + 'popf;': '\U0001d561', + 'pound': '\xa3', + 'pound;': '\xa3', + 'Pr;': '\u2abb', + 'pr;': '\u227a', + 'prap;': '\u2ab7', + 'prcue;': '\u227c', + 'prE;': '\u2ab3', + 'pre;': '\u2aaf', + 'prec;': '\u227a', + 'precapprox;': '\u2ab7', + 'preccurlyeq;': '\u227c', + 'Precedes;': '\u227a', + 'PrecedesEqual;': '\u2aaf', + 'PrecedesSlantEqual;': '\u227c', + 'PrecedesTilde;': '\u227e', + 'preceq;': '\u2aaf', + 'precnapprox;': '\u2ab9', + 'precneqq;': '\u2ab5', + 'precnsim;': '\u22e8', + 'precsim;': '\u227e', + 'Prime;': '\u2033', + 'prime;': '\u2032', + 'primes;': '\u2119', + 'prnap;': '\u2ab9', + 'prnE;': '\u2ab5', + 'prnsim;': '\u22e8', + 'prod;': '\u220f', + 'Product;': '\u220f', + 'profalar;': '\u232e', + 'profline;': '\u2312', + 'profsurf;': '\u2313', + 'prop;': '\u221d', + 'Proportion;': '\u2237', + 'Proportional;': '\u221d', + 'propto;': '\u221d', + 'prsim;': '\u227e', + 'prurel;': '\u22b0', + 'Pscr;': '\U0001d4ab', + 'pscr;': '\U0001d4c5', + 'Psi;': '\u03a8', + 'psi;': '\u03c8', + 'puncsp;': '\u2008', + 'Qfr;': '\U0001d514', + 'qfr;': '\U0001d52e', + 'qint;': '\u2a0c', + 'Qopf;': '\u211a', + 'qopf;': '\U0001d562', + 'qprime;': '\u2057', + 'Qscr;': '\U0001d4ac', + 'qscr;': '\U0001d4c6', + 'quaternions;': '\u210d', + 'quatint;': '\u2a16', + 'quest;': '?', + 'questeq;': '\u225f', + 'QUOT': '"', + 'quot': '"', + 'QUOT;': '"', + 'quot;': '"', + 'rAarr;': '\u21db', + 'race;': '\u223d\u0331', + 'Racute;': '\u0154', + 'racute;': '\u0155', + 'radic;': '\u221a', + 'raemptyv;': '\u29b3', + 'Rang;': '\u27eb', + 'rang;': '\u27e9', + 'rangd;': '\u2992', + 'range;': '\u29a5', + 'rangle;': '\u27e9', + 'raquo': '\xbb', + 'raquo;': '\xbb', + 'Rarr;': '\u21a0', + 'rArr;': '\u21d2', + 'rarr;': '\u2192', + 'rarrap;': '\u2975', + 'rarrb;': '\u21e5', + 'rarrbfs;': '\u2920', + 'rarrc;': '\u2933', + 'rarrfs;': '\u291e', + 'rarrhk;': '\u21aa', + 'rarrlp;': '\u21ac', + 'rarrpl;': '\u2945', + 'rarrsim;': '\u2974', + 'Rarrtl;': '\u2916', + 'rarrtl;': '\u21a3', + 'rarrw;': '\u219d', + 'rAtail;': '\u291c', + 'ratail;': '\u291a', + 'ratio;': '\u2236', + 'rationals;': '\u211a', + 'RBarr;': '\u2910', + 'rBarr;': '\u290f', + 'rbarr;': '\u290d', + 'rbbrk;': '\u2773', + 'rbrace;': '}', + 'rbrack;': ']', + 'rbrke;': '\u298c', + 'rbrksld;': '\u298e', + 'rbrkslu;': '\u2990', + 'Rcaron;': '\u0158', + 'rcaron;': '\u0159', + 'Rcedil;': '\u0156', + 'rcedil;': '\u0157', + 'rceil;': '\u2309', + 'rcub;': '}', + 'Rcy;': '\u0420', + 'rcy;': '\u0440', + 'rdca;': '\u2937', + 'rdldhar;': '\u2969', + 'rdquo;': '\u201d', + 'rdquor;': '\u201d', + 'rdsh;': '\u21b3', + 'Re;': '\u211c', + 'real;': '\u211c', + 'realine;': '\u211b', + 'realpart;': '\u211c', + 'reals;': '\u211d', + 'rect;': '\u25ad', + 'REG': '\xae', + 'reg': '\xae', + 'REG;': '\xae', + 'reg;': '\xae', + 'ReverseElement;': '\u220b', + 'ReverseEquilibrium;': '\u21cb', + 'ReverseUpEquilibrium;': '\u296f', + 'rfisht;': '\u297d', + 'rfloor;': '\u230b', + 'Rfr;': '\u211c', + 'rfr;': '\U0001d52f', + 'rHar;': '\u2964', + 'rhard;': '\u21c1', + 'rharu;': '\u21c0', + 'rharul;': '\u296c', + 'Rho;': '\u03a1', + 'rho;': '\u03c1', + 'rhov;': '\u03f1', + 'RightAngleBracket;': '\u27e9', + 'RightArrow;': '\u2192', + 'Rightarrow;': '\u21d2', + 'rightarrow;': '\u2192', + 'RightArrowBar;': '\u21e5', + 'RightArrowLeftArrow;': '\u21c4', + 'rightarrowtail;': '\u21a3', + 'RightCeiling;': '\u2309', + 'RightDoubleBracket;': '\u27e7', + 'RightDownTeeVector;': '\u295d', + 'RightDownVector;': '\u21c2', + 'RightDownVectorBar;': '\u2955', + 'RightFloor;': '\u230b', + 'rightharpoondown;': '\u21c1', + 'rightharpoonup;': '\u21c0', + 'rightleftarrows;': '\u21c4', + 'rightleftharpoons;': '\u21cc', + 'rightrightarrows;': '\u21c9', + 'rightsquigarrow;': '\u219d', + 'RightTee;': '\u22a2', + 'RightTeeArrow;': '\u21a6', + 'RightTeeVector;': '\u295b', + 'rightthreetimes;': '\u22cc', + 'RightTriangle;': '\u22b3', + 'RightTriangleBar;': '\u29d0', + 'RightTriangleEqual;': '\u22b5', + 'RightUpDownVector;': '\u294f', + 'RightUpTeeVector;': '\u295c', + 'RightUpVector;': '\u21be', + 'RightUpVectorBar;': '\u2954', + 'RightVector;': '\u21c0', + 'RightVectorBar;': '\u2953', + 'ring;': '\u02da', + 'risingdotseq;': '\u2253', + 'rlarr;': '\u21c4', + 'rlhar;': '\u21cc', + 'rlm;': '\u200f', + 'rmoust;': '\u23b1', + 'rmoustache;': '\u23b1', + 'rnmid;': '\u2aee', + 'roang;': '\u27ed', + 'roarr;': '\u21fe', + 'robrk;': '\u27e7', + 'ropar;': '\u2986', + 'Ropf;': '\u211d', + 'ropf;': '\U0001d563', + 'roplus;': '\u2a2e', + 'rotimes;': '\u2a35', + 'RoundImplies;': '\u2970', + 'rpar;': ')', + 'rpargt;': '\u2994', + 'rppolint;': '\u2a12', + 'rrarr;': '\u21c9', + 'Rrightarrow;': '\u21db', + 'rsaquo;': '\u203a', + 'Rscr;': '\u211b', + 'rscr;': '\U0001d4c7', + 'Rsh;': '\u21b1', + 'rsh;': '\u21b1', + 'rsqb;': ']', + 'rsquo;': '\u2019', + 'rsquor;': '\u2019', + 'rthree;': '\u22cc', + 'rtimes;': '\u22ca', + 'rtri;': '\u25b9', + 'rtrie;': '\u22b5', + 'rtrif;': '\u25b8', + 'rtriltri;': '\u29ce', + 'RuleDelayed;': '\u29f4', + 'ruluhar;': '\u2968', + 'rx;': '\u211e', + 'Sacute;': '\u015a', + 'sacute;': '\u015b', + 'sbquo;': '\u201a', + 'Sc;': '\u2abc', + 'sc;': '\u227b', + 'scap;': '\u2ab8', + 'Scaron;': '\u0160', + 'scaron;': '\u0161', + 'sccue;': '\u227d', + 'scE;': '\u2ab4', + 'sce;': '\u2ab0', + 'Scedil;': '\u015e', + 'scedil;': '\u015f', + 'Scirc;': '\u015c', + 'scirc;': '\u015d', + 'scnap;': '\u2aba', + 'scnE;': '\u2ab6', + 'scnsim;': '\u22e9', + 'scpolint;': '\u2a13', + 'scsim;': '\u227f', + 'Scy;': '\u0421', + 'scy;': '\u0441', + 'sdot;': '\u22c5', + 'sdotb;': '\u22a1', + 'sdote;': '\u2a66', + 'searhk;': '\u2925', + 'seArr;': '\u21d8', + 'searr;': '\u2198', + 'searrow;': '\u2198', + 'sect': '\xa7', + 'sect;': '\xa7', + 'semi;': ';', + 'seswar;': '\u2929', + 'setminus;': '\u2216', + 'setmn;': '\u2216', + 'sext;': '\u2736', + 'Sfr;': '\U0001d516', + 'sfr;': '\U0001d530', + 'sfrown;': '\u2322', + 'sharp;': '\u266f', + 'SHCHcy;': '\u0429', + 'shchcy;': '\u0449', + 'SHcy;': '\u0428', + 'shcy;': '\u0448', + 'ShortDownArrow;': '\u2193', + 'ShortLeftArrow;': '\u2190', + 'shortmid;': '\u2223', + 'shortparallel;': '\u2225', + 'ShortRightArrow;': '\u2192', + 'ShortUpArrow;': '\u2191', + 'shy': '\xad', + 'shy;': '\xad', + 'Sigma;': '\u03a3', + 'sigma;': '\u03c3', + 'sigmaf;': '\u03c2', + 'sigmav;': '\u03c2', + 'sim;': '\u223c', + 'simdot;': '\u2a6a', + 'sime;': '\u2243', + 'simeq;': '\u2243', + 'simg;': '\u2a9e', + 'simgE;': '\u2aa0', + 'siml;': '\u2a9d', + 'simlE;': '\u2a9f', + 'simne;': '\u2246', + 'simplus;': '\u2a24', + 'simrarr;': '\u2972', + 'slarr;': '\u2190', + 'SmallCircle;': '\u2218', + 'smallsetminus;': '\u2216', + 'smashp;': '\u2a33', + 'smeparsl;': '\u29e4', + 'smid;': '\u2223', + 'smile;': '\u2323', + 'smt;': '\u2aaa', + 'smte;': '\u2aac', + 'smtes;': '\u2aac\ufe00', + 'SOFTcy;': '\u042c', + 'softcy;': '\u044c', + 'sol;': '/', + 'solb;': '\u29c4', + 'solbar;': '\u233f', + 'Sopf;': '\U0001d54a', + 'sopf;': '\U0001d564', + 'spades;': '\u2660', + 'spadesuit;': '\u2660', + 'spar;': '\u2225', + 'sqcap;': '\u2293', + 'sqcaps;': '\u2293\ufe00', + 'sqcup;': '\u2294', + 'sqcups;': '\u2294\ufe00', + 'Sqrt;': '\u221a', + 'sqsub;': '\u228f', + 'sqsube;': '\u2291', + 'sqsubset;': '\u228f', + 'sqsubseteq;': '\u2291', + 'sqsup;': '\u2290', + 'sqsupe;': '\u2292', + 'sqsupset;': '\u2290', + 'sqsupseteq;': '\u2292', + 'squ;': '\u25a1', + 'Square;': '\u25a1', + 'square;': '\u25a1', + 'SquareIntersection;': '\u2293', + 'SquareSubset;': '\u228f', + 'SquareSubsetEqual;': '\u2291', + 'SquareSuperset;': '\u2290', + 'SquareSupersetEqual;': '\u2292', + 'SquareUnion;': '\u2294', + 'squarf;': '\u25aa', + 'squf;': '\u25aa', + 'srarr;': '\u2192', + 'Sscr;': '\U0001d4ae', + 'sscr;': '\U0001d4c8', + 'ssetmn;': '\u2216', + 'ssmile;': '\u2323', + 'sstarf;': '\u22c6', + 'Star;': '\u22c6', + 'star;': '\u2606', + 'starf;': '\u2605', + 'straightepsilon;': '\u03f5', + 'straightphi;': '\u03d5', + 'strns;': '\xaf', + 'Sub;': '\u22d0', + 'sub;': '\u2282', + 'subdot;': '\u2abd', + 'subE;': '\u2ac5', + 'sube;': '\u2286', + 'subedot;': '\u2ac3', + 'submult;': '\u2ac1', + 'subnE;': '\u2acb', + 'subne;': '\u228a', + 'subplus;': '\u2abf', + 'subrarr;': '\u2979', + 'Subset;': '\u22d0', + 'subset;': '\u2282', + 'subseteq;': '\u2286', + 'subseteqq;': '\u2ac5', + 'SubsetEqual;': '\u2286', + 'subsetneq;': '\u228a', + 'subsetneqq;': '\u2acb', + 'subsim;': '\u2ac7', + 'subsub;': '\u2ad5', + 'subsup;': '\u2ad3', + 'succ;': '\u227b', + 'succapprox;': '\u2ab8', + 'succcurlyeq;': '\u227d', + 'Succeeds;': '\u227b', + 'SucceedsEqual;': '\u2ab0', + 'SucceedsSlantEqual;': '\u227d', + 'SucceedsTilde;': '\u227f', + 'succeq;': '\u2ab0', + 'succnapprox;': '\u2aba', + 'succneqq;': '\u2ab6', + 'succnsim;': '\u22e9', + 'succsim;': '\u227f', + 'SuchThat;': '\u220b', + 'Sum;': '\u2211', + 'sum;': '\u2211', + 'sung;': '\u266a', + 'sup1': '\xb9', + 'sup1;': '\xb9', + 'sup2': '\xb2', + 'sup2;': '\xb2', + 'sup3': '\xb3', + 'sup3;': '\xb3', + 'Sup;': '\u22d1', + 'sup;': '\u2283', + 'supdot;': '\u2abe', + 'supdsub;': '\u2ad8', + 'supE;': '\u2ac6', + 'supe;': '\u2287', + 'supedot;': '\u2ac4', + 'Superset;': '\u2283', + 'SupersetEqual;': '\u2287', + 'suphsol;': '\u27c9', + 'suphsub;': '\u2ad7', + 'suplarr;': '\u297b', + 'supmult;': '\u2ac2', + 'supnE;': '\u2acc', + 'supne;': '\u228b', + 'supplus;': '\u2ac0', + 'Supset;': '\u22d1', + 'supset;': '\u2283', + 'supseteq;': '\u2287', + 'supseteqq;': '\u2ac6', + 'supsetneq;': '\u228b', + 'supsetneqq;': '\u2acc', + 'supsim;': '\u2ac8', + 'supsub;': '\u2ad4', + 'supsup;': '\u2ad6', + 'swarhk;': '\u2926', + 'swArr;': '\u21d9', + 'swarr;': '\u2199', + 'swarrow;': '\u2199', + 'swnwar;': '\u292a', + 'szlig': '\xdf', + 'szlig;': '\xdf', + 'Tab;': '\t', + 'target;': '\u2316', + 'Tau;': '\u03a4', + 'tau;': '\u03c4', + 'tbrk;': '\u23b4', + 'Tcaron;': '\u0164', + 'tcaron;': '\u0165', + 'Tcedil;': '\u0162', + 'tcedil;': '\u0163', + 'Tcy;': '\u0422', + 'tcy;': '\u0442', + 'tdot;': '\u20db', + 'telrec;': '\u2315', + 'Tfr;': '\U0001d517', + 'tfr;': '\U0001d531', + 'there4;': '\u2234', + 'Therefore;': '\u2234', + 'therefore;': '\u2234', + 'Theta;': '\u0398', + 'theta;': '\u03b8', + 'thetasym;': '\u03d1', + 'thetav;': '\u03d1', + 'thickapprox;': '\u2248', + 'thicksim;': '\u223c', + 'ThickSpace;': '\u205f\u200a', + 'thinsp;': '\u2009', + 'ThinSpace;': '\u2009', + 'thkap;': '\u2248', + 'thksim;': '\u223c', + 'THORN': '\xde', + 'thorn': '\xfe', + 'THORN;': '\xde', + 'thorn;': '\xfe', + 'Tilde;': '\u223c', + 'tilde;': '\u02dc', + 'TildeEqual;': '\u2243', + 'TildeFullEqual;': '\u2245', + 'TildeTilde;': '\u2248', + 'times': '\xd7', + 'times;': '\xd7', + 'timesb;': '\u22a0', + 'timesbar;': '\u2a31', + 'timesd;': '\u2a30', + 'tint;': '\u222d', + 'toea;': '\u2928', + 'top;': '\u22a4', + 'topbot;': '\u2336', + 'topcir;': '\u2af1', + 'Topf;': '\U0001d54b', + 'topf;': '\U0001d565', + 'topfork;': '\u2ada', + 'tosa;': '\u2929', + 'tprime;': '\u2034', + 'TRADE;': '\u2122', + 'trade;': '\u2122', + 'triangle;': '\u25b5', + 'triangledown;': '\u25bf', + 'triangleleft;': '\u25c3', + 'trianglelefteq;': '\u22b4', + 'triangleq;': '\u225c', + 'triangleright;': '\u25b9', + 'trianglerighteq;': '\u22b5', + 'tridot;': '\u25ec', + 'trie;': '\u225c', + 'triminus;': '\u2a3a', + 'TripleDot;': '\u20db', + 'triplus;': '\u2a39', + 'trisb;': '\u29cd', + 'tritime;': '\u2a3b', + 'trpezium;': '\u23e2', + 'Tscr;': '\U0001d4af', + 'tscr;': '\U0001d4c9', + 'TScy;': '\u0426', + 'tscy;': '\u0446', + 'TSHcy;': '\u040b', + 'tshcy;': '\u045b', + 'Tstrok;': '\u0166', + 'tstrok;': '\u0167', + 'twixt;': '\u226c', + 'twoheadleftarrow;': '\u219e', + 'twoheadrightarrow;': '\u21a0', + 'Uacute': '\xda', + 'uacute': '\xfa', + 'Uacute;': '\xda', + 'uacute;': '\xfa', + 'Uarr;': '\u219f', + 'uArr;': '\u21d1', + 'uarr;': '\u2191', + 'Uarrocir;': '\u2949', + 'Ubrcy;': '\u040e', + 'ubrcy;': '\u045e', + 'Ubreve;': '\u016c', + 'ubreve;': '\u016d', + 'Ucirc': '\xdb', + 'ucirc': '\xfb', + 'Ucirc;': '\xdb', + 'ucirc;': '\xfb', + 'Ucy;': '\u0423', + 'ucy;': '\u0443', + 'udarr;': '\u21c5', + 'Udblac;': '\u0170', + 'udblac;': '\u0171', + 'udhar;': '\u296e', + 'ufisht;': '\u297e', + 'Ufr;': '\U0001d518', + 'ufr;': '\U0001d532', + 'Ugrave': '\xd9', + 'ugrave': '\xf9', + 'Ugrave;': '\xd9', + 'ugrave;': '\xf9', + 'uHar;': '\u2963', + 'uharl;': '\u21bf', + 'uharr;': '\u21be', + 'uhblk;': '\u2580', + 'ulcorn;': '\u231c', + 'ulcorner;': '\u231c', + 'ulcrop;': '\u230f', + 'ultri;': '\u25f8', + 'Umacr;': '\u016a', + 'umacr;': '\u016b', + 'uml': '\xa8', + 'uml;': '\xa8', + 'UnderBar;': '_', + 'UnderBrace;': '\u23df', + 'UnderBracket;': '\u23b5', + 'UnderParenthesis;': '\u23dd', + 'Union;': '\u22c3', + 'UnionPlus;': '\u228e', + 'Uogon;': '\u0172', + 'uogon;': '\u0173', + 'Uopf;': '\U0001d54c', + 'uopf;': '\U0001d566', + 'UpArrow;': '\u2191', + 'Uparrow;': '\u21d1', + 'uparrow;': '\u2191', + 'UpArrowBar;': '\u2912', + 'UpArrowDownArrow;': '\u21c5', + 'UpDownArrow;': '\u2195', + 'Updownarrow;': '\u21d5', + 'updownarrow;': '\u2195', + 'UpEquilibrium;': '\u296e', + 'upharpoonleft;': '\u21bf', + 'upharpoonright;': '\u21be', + 'uplus;': '\u228e', + 'UpperLeftArrow;': '\u2196', + 'UpperRightArrow;': '\u2197', + 'Upsi;': '\u03d2', + 'upsi;': '\u03c5', + 'upsih;': '\u03d2', + 'Upsilon;': '\u03a5', + 'upsilon;': '\u03c5', + 'UpTee;': '\u22a5', + 'UpTeeArrow;': '\u21a5', + 'upuparrows;': '\u21c8', + 'urcorn;': '\u231d', + 'urcorner;': '\u231d', + 'urcrop;': '\u230e', + 'Uring;': '\u016e', + 'uring;': '\u016f', + 'urtri;': '\u25f9', + 'Uscr;': '\U0001d4b0', + 'uscr;': '\U0001d4ca', + 'utdot;': '\u22f0', + 'Utilde;': '\u0168', + 'utilde;': '\u0169', + 'utri;': '\u25b5', + 'utrif;': '\u25b4', + 'uuarr;': '\u21c8', + 'Uuml': '\xdc', + 'uuml': '\xfc', + 'Uuml;': '\xdc', + 'uuml;': '\xfc', + 'uwangle;': '\u29a7', + 'vangrt;': '\u299c', + 'varepsilon;': '\u03f5', + 'varkappa;': '\u03f0', + 'varnothing;': '\u2205', + 'varphi;': '\u03d5', + 'varpi;': '\u03d6', + 'varpropto;': '\u221d', + 'vArr;': '\u21d5', + 'varr;': '\u2195', + 'varrho;': '\u03f1', + 'varsigma;': '\u03c2', + 'varsubsetneq;': '\u228a\ufe00', + 'varsubsetneqq;': '\u2acb\ufe00', + 'varsupsetneq;': '\u228b\ufe00', + 'varsupsetneqq;': '\u2acc\ufe00', + 'vartheta;': '\u03d1', + 'vartriangleleft;': '\u22b2', + 'vartriangleright;': '\u22b3', + 'Vbar;': '\u2aeb', + 'vBar;': '\u2ae8', + 'vBarv;': '\u2ae9', + 'Vcy;': '\u0412', + 'vcy;': '\u0432', + 'VDash;': '\u22ab', + 'Vdash;': '\u22a9', + 'vDash;': '\u22a8', + 'vdash;': '\u22a2', + 'Vdashl;': '\u2ae6', + 'Vee;': '\u22c1', + 'vee;': '\u2228', + 'veebar;': '\u22bb', + 'veeeq;': '\u225a', + 'vellip;': '\u22ee', + 'Verbar;': '\u2016', + 'verbar;': '|', + 'Vert;': '\u2016', + 'vert;': '|', + 'VerticalBar;': '\u2223', + 'VerticalLine;': '|', + 'VerticalSeparator;': '\u2758', + 'VerticalTilde;': '\u2240', + 'VeryThinSpace;': '\u200a', + 'Vfr;': '\U0001d519', + 'vfr;': '\U0001d533', + 'vltri;': '\u22b2', + 'vnsub;': '\u2282\u20d2', + 'vnsup;': '\u2283\u20d2', + 'Vopf;': '\U0001d54d', + 'vopf;': '\U0001d567', + 'vprop;': '\u221d', + 'vrtri;': '\u22b3', + 'Vscr;': '\U0001d4b1', + 'vscr;': '\U0001d4cb', + 'vsubnE;': '\u2acb\ufe00', + 'vsubne;': '\u228a\ufe00', + 'vsupnE;': '\u2acc\ufe00', + 'vsupne;': '\u228b\ufe00', + 'Vvdash;': '\u22aa', + 'vzigzag;': '\u299a', + 'Wcirc;': '\u0174', + 'wcirc;': '\u0175', + 'wedbar;': '\u2a5f', + 'Wedge;': '\u22c0', + 'wedge;': '\u2227', + 'wedgeq;': '\u2259', + 'weierp;': '\u2118', + 'Wfr;': '\U0001d51a', + 'wfr;': '\U0001d534', + 'Wopf;': '\U0001d54e', + 'wopf;': '\U0001d568', + 'wp;': '\u2118', + 'wr;': '\u2240', + 'wreath;': '\u2240', + 'Wscr;': '\U0001d4b2', + 'wscr;': '\U0001d4cc', + 'xcap;': '\u22c2', + 'xcirc;': '\u25ef', + 'xcup;': '\u22c3', + 'xdtri;': '\u25bd', + 'Xfr;': '\U0001d51b', + 'xfr;': '\U0001d535', + 'xhArr;': '\u27fa', + 'xharr;': '\u27f7', + 'Xi;': '\u039e', + 'xi;': '\u03be', + 'xlArr;': '\u27f8', + 'xlarr;': '\u27f5', + 'xmap;': '\u27fc', + 'xnis;': '\u22fb', + 'xodot;': '\u2a00', + 'Xopf;': '\U0001d54f', + 'xopf;': '\U0001d569', + 'xoplus;': '\u2a01', + 'xotime;': '\u2a02', + 'xrArr;': '\u27f9', + 'xrarr;': '\u27f6', + 'Xscr;': '\U0001d4b3', + 'xscr;': '\U0001d4cd', + 'xsqcup;': '\u2a06', + 'xuplus;': '\u2a04', + 'xutri;': '\u25b3', + 'xvee;': '\u22c1', + 'xwedge;': '\u22c0', + 'Yacute': '\xdd', + 'yacute': '\xfd', + 'Yacute;': '\xdd', + 'yacute;': '\xfd', + 'YAcy;': '\u042f', + 'yacy;': '\u044f', + 'Ycirc;': '\u0176', + 'ycirc;': '\u0177', + 'Ycy;': '\u042b', + 'ycy;': '\u044b', + 'yen': '\xa5', + 'yen;': '\xa5', + 'Yfr;': '\U0001d51c', + 'yfr;': '\U0001d536', + 'YIcy;': '\u0407', + 'yicy;': '\u0457', + 'Yopf;': '\U0001d550', + 'yopf;': '\U0001d56a', + 'Yscr;': '\U0001d4b4', + 'yscr;': '\U0001d4ce', + 'YUcy;': '\u042e', + 'yucy;': '\u044e', + 'yuml': '\xff', + 'Yuml;': '\u0178', + 'yuml;': '\xff', + 'Zacute;': '\u0179', + 'zacute;': '\u017a', + 'Zcaron;': '\u017d', + 'zcaron;': '\u017e', + 'Zcy;': '\u0417', + 'zcy;': '\u0437', + 'Zdot;': '\u017b', + 'zdot;': '\u017c', + 'zeetrf;': '\u2128', + 'ZeroWidthSpace;': '\u200b', + 'Zeta;': '\u0396', + 'zeta;': '\u03b6', + 'Zfr;': '\u2128', + 'zfr;': '\U0001d537', + 'ZHcy;': '\u0416', + 'zhcy;': '\u0436', + 'zigrarr;': '\u21dd', + 'Zopf;': '\u2124', + 'zopf;': '\U0001d56b', + 'Zscr;': '\U0001d4b5', + 'zscr;': '\U0001d4cf', + 'zwj;': '\u200d', + 'zwnj;': '\u200c', + } + try: import http.client as compat_http_client except ImportError: # Python 2 @@ -83,7 +2322,6 @@ try: except ImportError: # Python 2 from HTMLParser import HTMLParser as compat_HTMLParser - try: from subprocess import DEVNULL compat_subprocess_get_DEVNULL = lambda: DEVNULL @@ -245,13 +2483,20 @@ try: except ImportError: # Python 2.6 from xml.parsers.expat import ExpatError as compat_xml_parse_error + +etree = xml.etree.ElementTree + + +class _TreeBuilder(etree.TreeBuilder): + def doctype(self, name, pubid, system): + pass + if sys.version_info[0] >= 3: - compat_etree_fromstring = xml.etree.ElementTree.fromstring + def compat_etree_fromstring(text): + return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder())) else: # python 2.x tries to encode unicode strings with ascii (see the # XMLParser._fixtext method) - etree = xml.etree.ElementTree - try: _etree_iter = etree.Element.iter except AttributeError: # Python <=2.6 @@ -265,7 +2510,7 @@ else: # 2.7 source def _XML(text, parser=None): if not parser: - parser = etree.XMLParser(target=etree.TreeBuilder()) + parser = etree.XMLParser(target=_TreeBuilder()) parser.feed(text) return parser.close() @@ -277,7 +2522,7 @@ else: return el def compat_etree_fromstring(text): - doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory))) + doc = _XML(text, parser=etree.XMLParser(target=_TreeBuilder(element_factory=_element_factory))) for el in _etree_iter(doc): if el.text is not None and isinstance(el.text, bytes): el.text = el.text.decode('utf-8') @@ -350,15 +2595,19 @@ except ImportError: # Python < 3.3 return "'" + s.replace("'", "'\"'\"'") + "'" -if sys.version_info >= (2, 7, 3): +try: + args = shlex.split('中文') + assert (isinstance(args, list) and + isinstance(args[0], compat_str) and + args[0] == '中文') compat_shlex_split = shlex.split -else: +except (AssertionError, UnicodeEncodeError): # Working around shlex issue with unicode strings on some python 2 # versions (see http://bugs.python.org/issue1548891) def compat_shlex_split(s, comments=False, posix=True): if isinstance(s, compat_str): s = s.encode('utf-8') - return shlex.split(s, comments, posix) + return list(map(lambda s: s.decode('utf-8'), shlex.split(s, comments, posix))) def compat_ord(c): @@ -475,6 +2724,11 @@ if sys.version_info < (3, 0) and sys.platform == 'win32': else: compat_getpass = getpass.getpass +try: + compat_input = raw_input +except NameError: # Python 3 + compat_input = input + # Python < 2.6.5 require kwargs to be bytes try: def _testfunc(x): @@ -614,8 +2868,10 @@ __all__ = [ 'compat_getenv', 'compat_getpass', 'compat_html_entities', + 'compat_html_entities_html5', 'compat_http_client', 'compat_http_server', + 'compat_input', 'compat_itertools_count', 'compat_kwargs', 'compat_ord', diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index 3a73cee1c..fae245024 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -85,7 +85,7 @@ class ExternalFD(FileDownloader): cmd, stderr=subprocess.PIPE) _, stderr = p.communicate() if p.returncode != 0: - self.to_stderr(stderr) + self.to_stderr(stderr.decode('utf-8', 'replace')) return p.returncode @@ -210,6 +210,7 @@ class FFmpegFD(ExternalFD): # args += ['-http_proxy', proxy] env = os.environ.copy() compat_setenv('HTTP_PROXY', proxy, env=env) + compat_setenv('http_proxy', proxy, env=env) protocol = info_dict.get('protocol') diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 314def4cb..80c21d40b 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -196,6 +196,11 @@ def build_fragments_list(boot_info): first_frag_number = fragment_run_entry_table[0]['first'] fragments_counter = itertools.count(first_frag_number) for segment, fragments_count in segment_run_table['segment_run']: + # In some live HDS streams (for example Rai), `fragments_count` is + # abnormal and causing out-of-memory errors. It's OK to change the + # number of fragments for live streams as they are updated periodically + if fragments_count == 4294967295 and boot_info['live']: + fragments_count = 2 for _ in range(fragments_count): res.append((segment, next(fragments_counter))) @@ -319,7 +324,7 @@ class F4mFD(FragmentFD): doc = compat_etree_fromstring(manifest) formats = [(int(f.attrib.get('bitrate', -1)), f) for f in self._get_unencrypted_media(doc)] - if requested_bitrate is None: + if requested_bitrate is None or len(formats) == 1: # get the best format formats = sorted(formats, key=lambda f: f[0]) rate, media = formats[-1] @@ -329,7 +334,11 @@ class F4mFD(FragmentFD): base_url = compat_urlparse.urljoin(man_url, media.attrib['url']) bootstrap_node = doc.find(_add_ns('bootstrapInfo')) - boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, base_url) + # From Adobe F4M 3.0 spec: + # The <baseURL> element SHALL be the base URL for all relative + # (HTTP-based) URLs in the manifest. If <baseURL> is not present, said + # URLs should be relative to the location of the containing document. + boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, man_url) live = boot_info['live'] metadata_node = media.find(_add_ns('metadata')) if metadata_node is not None: diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 62136ee54..3b7bb3508 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -2,14 +2,24 @@ from __future__ import unicode_literals import os.path import re +import binascii +try: + from Crypto.Cipher import AES + can_decrypt_frag = True +except ImportError: + can_decrypt_frag = False from .fragment import FragmentFD from .external import FFmpegFD -from ..compat import compat_urlparse +from ..compat import ( + compat_urlparse, + compat_struct_pack, +) from ..utils import ( encodeFilename, sanitize_open, + parse_m3u8_attributes, ) @@ -21,19 +31,27 @@ class HlsFD(FragmentFD): @staticmethod def can_download(manifest): UNSUPPORTED_FEATURES = ( - r'#EXT-X-KEY:METHOD=(?!NONE)', # encrypted streams [1] + r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1] r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2] + # Live streams heuristic does not always work (e.g. geo restricted to Germany # http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0) # r'#EXT-X-MEDIA-SEQUENCE:(?!0$)', # live streams [3] - r'#EXT-X-PLAYLIST-TYPE:EVENT', # media segments may be appended to the end of - # event media playlists [4] + + # This heuristic also is not correct since segments may not be appended as well. + # Twitch vods of finished streams have EXT-X-PLAYLIST-TYPE:EVENT despite + # no segments will definitely be appended to the end of the playlist. + # r'#EXT-X-PLAYLIST-TYPE:EVENT', # media segments may be appended to the end of + # # event media playlists [4] + # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.4 # 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2 # 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2 # 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5 ) - return all(not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES) + check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES] + check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest) + return all(check_results) def real_download(self, filename, info_dict): man_url = info_dict['url'] @@ -51,36 +69,60 @@ class HlsFD(FragmentFD): fd.add_progress_hook(ph) return fd.real_download(filename, info_dict) - fragment_urls = [] + total_frags = 0 for line in s.splitlines(): line = line.strip() if line and not line.startswith('#'): - segment_url = ( - line - if re.match(r'^https?://', line) - else compat_urlparse.urljoin(man_url, line)) - fragment_urls.append(segment_url) - # We only download the first fragment during the test - if self.params.get('test', False): - break + total_frags += 1 ctx = { 'filename': filename, - 'total_frags': len(fragment_urls), + 'total_frags': total_frags, } self._prepare_and_start_frag_download(ctx) + i = 0 + media_sequence = 0 + decrypt_info = {'METHOD': 'NONE'} frags_filenames = [] - for i, frag_url in enumerate(fragment_urls): - frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i) - success = ctx['dl'].download(frag_filename, {'url': frag_url}) - if not success: - return False - down, frag_sanitized = sanitize_open(frag_filename, 'rb') - ctx['dest_stream'].write(down.read()) - down.close() - frags_filenames.append(frag_sanitized) + for line in s.splitlines(): + line = line.strip() + if line: + if not line.startswith('#'): + frag_url = ( + line + if re.match(r'^https?://', line) + else compat_urlparse.urljoin(man_url, line)) + frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i) + success = ctx['dl'].download(frag_filename, {'url': frag_url}) + if not success: + return False + down, frag_sanitized = sanitize_open(frag_filename, 'rb') + frag_content = down.read() + down.close() + if decrypt_info['METHOD'] == 'AES-128': + iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence) + frag_content = AES.new( + decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content) + ctx['dest_stream'].write(frag_content) + frags_filenames.append(frag_sanitized) + # We only download the first fragment during the test + if self.params.get('test', False): + break + i += 1 + media_sequence += 1 + elif line.startswith('#EXT-X-KEY'): + decrypt_info = parse_m3u8_attributes(line[11:]) + if decrypt_info['METHOD'] == 'AES-128': + if 'IV' in decrypt_info: + decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:]) + if not re.match(r'^https?://', decrypt_info['URI']): + decrypt_info['URI'] = compat_urlparse.urljoin( + man_url, decrypt_info['URI']) + decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read() + elif line.startswith('#EXT-X-MEDIA-SEQUENCE'): + media_sequence = int(line[22:]) self._finish_frag_download(ctx) diff --git a/youtube_dl/extractor/abcnews.py b/youtube_dl/extractor/abcnews.py new file mode 100644 index 000000000..b61a6327c --- /dev/null +++ b/youtube_dl/extractor/abcnews.py @@ -0,0 +1,135 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import calendar +import re +import time + +from .amp import AMPIE +from .common import InfoExtractor +from ..compat import compat_urlparse + + +class AbcNewsVideoIE(AMPIE): + IE_NAME = 'abcnews:video' + _VALID_URL = 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)' + + _TESTS = [{ + 'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932', + 'info_dict': { + 'id': '20411932', + 'ext': 'mp4', + 'display_id': 'week-exclusive-irans-foreign-minister-zarif', + 'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif', + 'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.', + 'duration': 180, + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + video_id = mobj.group('id') + info_dict = self._extract_feed_info( + 'http://abcnews.go.com/video/itemfeed?id=%s' % video_id) + info_dict.update({ + 'id': video_id, + 'display_id': display_id, + }) + return info_dict + + +class AbcNewsIE(InfoExtractor): + IE_NAME = 'abcnews' + _VALID_URL = 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)' + + _TESTS = [{ + 'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY', + 'info_dict': { + 'id': '10498713', + 'ext': 'flv', + 'display_id': 'dramatic-video-rare-death-job-america', + 'title': 'Occupational Hazards', + 'description': 'Nightline investigates the dangers that lurk at various jobs.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20100428', + 'timestamp': 1272412800, + }, + 'add_ie': ['AbcNewsVideo'], + }, { + 'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818', + 'info_dict': { + 'id': '39125818', + 'ext': 'mp4', + 'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016', + 'title': 'Justin Timberlake Drops Hints For Secret Single', + 'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.', + 'upload_date': '20160515', + 'timestamp': 1463329500, + }, + 'params': { + # m3u8 download + 'skip_download': True, + # The embedded YouTube video is blocked due to copyright issues + 'playlist_items': '1', + }, + 'add_ie': ['AbcNewsVideo'], + }, { + 'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex( + r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL') + full_video_url = compat_urlparse.urljoin(url, video_url) + + youtube_url = self._html_search_regex( + r'<iframe[^>]+src="(https://www\.youtube\.com/embed/[^"]+)"', + webpage, 'YouTube URL', default=None) + + timestamp = None + date_str = self._html_search_regex( + r'<span[^>]+class="timestamp">([^<]+)</span>', + webpage, 'timestamp', fatal=False) + if date_str: + tz_offset = 0 + if date_str.endswith(' ET'): # Eastern Time + tz_offset = -5 + date_str = date_str[:-3] + date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p'] + for date_format in date_formats: + try: + timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format)) + except ValueError: + continue + if timestamp is not None: + timestamp -= tz_offset * 3600 + + entry = { + '_type': 'url_transparent', + 'ie_key': AbcNewsVideoIE.ie_key(), + 'url': full_video_url, + 'id': video_id, + 'display_id': display_id, + 'timestamp': timestamp, + } + + if youtube_url: + entries = [entry, self.url_result(youtube_url, 'Youtube')] + return self.playlist_result(entries) + + return entry diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 8753ee2cf..5ae16fa16 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -156,7 +156,10 @@ class AdobeTVVideoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_json(url + '?format=json', video_id) + webpage = self._download_webpage(url, video_id) + + video_data = self._parse_json(self._search_regex( + r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id) formats = [{ 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')), diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index 1bbfe2641..8f53050c9 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -2,23 +2,137 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor +from .theplatform import ThePlatformIE from ..utils import ( smuggle_url, update_url_query, unescapeHTML, + extract_attributes, + get_element_by_attribute, +) +from ..compat import ( + compat_urlparse, ) -class AENetworksIE(InfoExtractor): +class AENetworksBaseIE(ThePlatformIE): + _THEPLATFORM_KEY = 'crazyjava' + _THEPLATFORM_SECRET = 's3cr3t' + + +class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' - _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?P<type>[^/]+)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])' + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)/full-movie)' + _TESTS = [{ + 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', + 'md5': '8ff93eb073449f151d6b90c0ae1ef0c7', + 'info_dict': { + 'id': '22253814', + 'ext': 'mp4', + 'title': 'Winter Is Coming', + 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74', + 'timestamp': 1338306241, + 'upload_date': '20120529', + 'uploader': 'AENE-NEW', + }, + 'add_ie': ['ThePlatform'], + }, { + 'url': 'http://www.history.com/shows/ancient-aliens/season-1', + 'info_dict': { + 'id': '71889446852', + }, + 'playlist_mincount': 5, + }, { + 'url': 'http://www.mylifetime.com/shows/atlanta-plastic', + 'info_dict': { + 'id': 'SERIES4317', + 'title': 'Atlanta Plastic', + }, + 'playlist_mincount': 2, + }, { + 'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1', + 'only_matching': True + }, { + 'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8', + 'only_matching': True + }, { + 'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6', + 'only_matching': True + }, { + 'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie', + 'only_matching': True + }] + _DOMAIN_TO_REQUESTOR_ID = { + 'history.com': 'HISTORY', + 'aetv.com': 'AETV', + 'mylifetime.com': 'LIFETIME', + 'fyi.tv': 'FYI', + } + def _real_extract(self, url): + domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups() + display_id = show_path or movie_display_id + webpage = self._download_webpage(url, display_id) + if show_path: + url_parts = show_path.split('/') + url_parts_len = len(url_parts) + if url_parts_len == 1: + entries = [] + for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage): + entries.append(self.url_result( + compat_urlparse.urljoin(url, season_url_path), 'AENetworks')) + return self.playlist_result( + entries, self._html_search_meta('aetn:SeriesId', webpage), + self._html_search_meta('aetn:SeriesTitle', webpage)) + elif url_parts_len == 2: + entries = [] + for episode_item in re.findall(r'(?s)<div[^>]+class="[^"]*episode-item[^"]*"[^>]*>', webpage): + episode_attributes = extract_attributes(episode_item) + episode_url = compat_urlparse.urljoin( + url, episode_attributes['data-canonical']) + entries.append(self.url_result( + episode_url, 'AENetworks', + episode_attributes['data-videoid'])) + return self.playlist_result( + entries, self._html_search_meta('aetn:SeasonId', webpage)) + + query = { + 'mbr': 'true', + 'assetTypes': 'medium_video_s3' + } + video_id = self._html_search_meta('aetn:VideoID', webpage) + media_url = self._search_regex( + r"media_url\s*=\s*'([^']+)'", webpage, 'video url') + theplatform_metadata = self._download_theplatform_metadata(self._search_regex( + r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id) + info = self._parse_theplatform_metadata(theplatform_metadata) + if theplatform_metadata.get('AETN$isBehindWall'): + requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain] + resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>%s%s%s%s' % (requestor_id, theplatform_metadata['title'], theplatform_metadata['AETN$PPL_pplProgramId'], theplatform_metadata['ratings'][0]['rating']) + query['auth'] = self._extract_mvpd_auth( + url, video_id, requestor_id, resource) + info.update(self._search_json_ld(webpage, video_id, fatal=False)) + media_url = update_url_query(media_url, query) + media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET) + formats, subtitles = self._extract_theplatform_smil(media_url, video_id) + self._sort_formats(formats) + info.update({ + 'id': video_id, + 'formats': formats, + 'subtitles': subtitles, + }) + return info + + +class HistoryTopicIE(AENetworksBaseIE): + IE_NAME = 'history:topic' + IE_DESC = 'History.com Topic' + _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P[^/]+)(?:/[^/]+(?:/(?P[^/?#]+))?)?' _TESTS = [{ 'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false', 'info_dict': { - 'id': 'g12m5Gyt3fdR', + 'id': '40700995724', 'ext': 'mp4', 'title': "Bet You Didn't Know: Valentine's Day", 'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7', @@ -31,57 +145,61 @@ class AENetworksIE(InfoExtractor): 'skip_download': True, }, 'add_ie': ['ThePlatform'], - 'expected_warnings': ['JSON-LD'], }, { - 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', - 'md5': '8ff93eb073449f151d6b90c0ae1ef0c7', - 'info_dict': { - 'id': 'eg47EERs_JsZ', - 'ext': 'mp4', - 'title': 'Winter Is Coming', - 'description': 'md5:641f424b7a19d8e24f26dea22cf59d74', - 'timestamp': 1338306241, - 'upload_date': '20120529', - 'uploader': 'AENE-NEW', + 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos', + 'info_dict': + { + 'id': 'world-war-i-history', + 'title': 'World War I History', }, - 'add_ie': ['ThePlatform'], + 'playlist_mincount': 24, }, { - 'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry', - 'only_matching': True + 'url': 'http://www.history.com/topics/world-war-i-history/videos', + 'only_matching': True, }, { - 'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage', - 'only_matching': True + 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history', + 'only_matching': True, }, { - 'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients', - 'only_matching': True + 'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches', + 'only_matching': True, }] - def _real_extract(self, url): - page_type, video_id = re.match(self._VALID_URL, url).groups() - - webpage = self._download_webpage(url, video_id) - - video_url_re = [ - r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id, - r"media_url\s*=\s*'([^']+)'" - ] - video_url = unescapeHTML(self._search_regex(video_url_re, webpage, 'video url')) - query = {'mbr': 'true'} - if page_type == 'shows': - query['assetTypes'] = 'medium_video_s3' - if 'switch=hds' in video_url: - query['switch'] = 'hls' - - info = self._search_json_ld(webpage, video_id, fatal=False) - info.update({ + def theplatform_url_result(self, theplatform_url, video_id, query): + return { '_type': 'url_transparent', + 'id': video_id, 'url': smuggle_url( - update_url_query(video_url, query), + update_url_query(theplatform_url, query), { 'sig': { - 'key': 'crazyjava', - 'secret': 's3cr3t'}, + 'key': self._THEPLATFORM_KEY, + 'secret': self._THEPLATFORM_SECRET, + }, 'force_smil_url': True }), - }) - return info + 'ie_key': 'ThePlatform', + } + + def _real_extract(self, url): + topic_id, video_display_id = re.match(self._VALID_URL, url).groups() + if video_display_id: + webpage = self._download_webpage(url, video_display_id) + release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups() + release_url = unescapeHTML(release_url) + + return self.theplatform_url_result( + release_url, video_id, { + 'mbr': 'true', + 'switch': 'hls' + }) + else: + webpage = self._download_webpage(url, topic_id) + entries = [] + for episode_item in re.findall(r']*>', webpage): + video_attributes = extract_attributes(episode_item) + entries.append(self.theplatform_url_result( + video_attributes['data-release-url'], video_attributes['data-id'], { + 'mbr': 'true', + 'switch': 'hls' + })) + return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage)) diff --git a/youtube_dl/extractor/afreecatv.py b/youtube_dl/extractor/afreecatv.py new file mode 100644 index 000000000..518c61f67 --- /dev/null +++ b/youtube_dl/extractor/afreecatv.py @@ -0,0 +1,133 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse_urlparse, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + int_or_none, + xpath_element, + xpath_text, +) + + +class AfreecaTVIE(InfoExtractor): + IE_DESC = 'afreecatv.com' + _VALID_URL = r'''(?x)^ + https?://(?:(live|afbbs|www)\.)?afreeca(?:tv)?\.com(?::\d+)? + (?: + /app/(?:index|read_ucc_bbs)\.cgi| + /player/[Pp]layer\.(?:swf|html)) + \?.*?\bnTitleNo=(?P\d+)''' + _TESTS = [{ + 'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=', + 'md5': 'f72c89fe7ecc14c1b5ce506c4996046e', + 'info_dict': { + 'id': '36164052', + 'ext': 'mp4', + 'title': '데일리 에이프릴 요정들의 시상식!', + 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', + 'uploader': 'dailyapril', + 'uploader_id': 'dailyapril', + 'upload_date': '20160503', + } + }, { + 'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867', + 'info_dict': { + 'id': '36153164', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$', + 'uploader': 'dailyapril', + 'uploader_id': 'dailyapril', + }, + 'playlist_count': 2, + 'playlist': [{ + 'md5': 'd8b7c174568da61d774ef0203159bf97', + 'info_dict': { + 'id': '36153164_1', + 'ext': 'mp4', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'upload_date': '20160502', + }, + }, { + 'md5': '58f2ce7f6044e34439ab2d50612ab02b', + 'info_dict': { + 'id': '36153164_2', + 'ext': 'mp4', + 'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'", + 'upload_date': '20160502', + }, + }], + }, { + 'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652', + 'only_matching': True, + }] + + @staticmethod + def parse_video_key(key): + video_key = {} + m = re.match(r'^(?P\d{8})_\w+_(?P\d+)$', key) + if m: + video_key['upload_date'] = m.group('upload_date') + video_key['part'] = m.group('part') + return video_key + + def _real_extract(self, url): + video_id = self._match_id(url) + parsed_url = compat_urllib_parse_urlparse(url) + info_url = compat_urlparse.urlunparse(parsed_url._replace( + netloc='afbbs.afreecatv.com:8080', + path='/api/video/get_video_info.php')) + video_xml = self._download_xml(info_url, video_id) + + if xpath_element(video_xml, './track/video/file') is None: + raise ExtractorError('Specified AfreecaTV video does not exist', + expected=True) + + title = xpath_text(video_xml, './track/title', 'title') + uploader = xpath_text(video_xml, './track/nickname', 'uploader') + uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id') + duration = int_or_none(xpath_text(video_xml, './track/duration', + 'duration')) + thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail') + + entries = [] + for i, video_file in enumerate(video_xml.findall('./track/video/file')): + video_key = self.parse_video_key(video_file.get('key', '')) + if not video_key: + continue + entries.append({ + 'id': '%s_%s' % (video_id, video_key.get('part', i + 1)), + 'title': title, + 'upload_date': video_key.get('upload_date'), + 'duration': int_or_none(video_file.get('duration')), + 'url': video_file.text, + }) + + info = { + 'id': video_id, + 'title': title, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'duration': duration, + 'thumbnail': thumbnail, + } + + if len(entries) > 1: + info['_type'] = 'multi_video' + info['entries'] = entries + elif len(entries) == 1: + info['url'] = entries[0]['url'] + info['upload_date'] = entries[0].get('upload_date') + else: + raise ExtractorError( + 'No files found for the specified AfreecaTV video, either' + ' the URL is incorrect or the video has been made private.', + expected=True) + + return info diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py index d548592fe..5766b4fe8 100644 --- a/youtube_dl/extractor/aftonbladet.py +++ b/youtube_dl/extractor/aftonbladet.py @@ -24,10 +24,10 @@ class AftonbladetIE(InfoExtractor): webpage = self._download_webpage(url, video_id) # find internal video meta data - meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' + meta_url = 'http://aftonbladet-play-metadata.cdn.drvideo.aptoma.no/video/%s.json' player_config = self._parse_json(self._html_search_regex( r'data-player-config="([^"]+)"', webpage, 'player config'), video_id) - internal_meta_id = player_config['videoId'] + internal_meta_id = player_config['aptomaVideoId'] internal_meta_url = meta_url % internal_meta_id internal_meta_json = self._download_json( internal_meta_url, video_id, 'Downloading video meta data') diff --git a/youtube_dl/extractor/amp.py b/youtube_dl/extractor/amp.py index 138fa0808..e8e40126b 100644 --- a/youtube_dl/extractor/amp.py +++ b/youtube_dl/extractor/amp.py @@ -5,6 +5,8 @@ from .common import InfoExtractor from ..utils import ( int_or_none, parse_iso8601, + mimetype2ext, + determine_ext, ) @@ -50,21 +52,25 @@ class AMPIE(InfoExtractor): if isinstance(media_content, dict): media_content = [media_content] for media_data in media_content: - media = media_data['@attributes'] - media_type = media['type'] - if media_type == 'video/f4m': + media = media_data.get('@attributes', {}) + media_url = media.get('url') + if not media_url: + continue + ext = mimetype2ext(media.get('type')) or determine_ext(media_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( - media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', + media_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id, f4m_id='hds', fatal=False)) - elif media_type == 'application/x-mpegURL': + elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False)) + media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) else: formats.append({ - 'format_id': media_data['media-category']['@attributes']['label'], + 'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'), 'url': media['url'], 'tbr': int_or_none(media.get('bitrate')), 'filesize': int_or_none(media.get('fileSize')), + 'ext': ext, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py index 9b01e38f5..9e28f2579 100644 --- a/youtube_dl/extractor/animeondemand.py +++ b/youtube_dl/extractor/animeondemand.py @@ -22,6 +22,7 @@ class AnimeOnDemandIE(InfoExtractor): _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply' _NETRC_MACHINE = 'animeondemand' _TESTS = [{ + # jap, OmU 'url': 'https://www.anime-on-demand.de/anime/161', 'info_dict': { 'id': '161', @@ -30,17 +31,21 @@ class AnimeOnDemandIE(InfoExtractor): }, 'playlist_mincount': 4, }, { - # Film wording is used instead of Episode + # Film wording is used instead of Episode, ger/jap, Dub/OmU 'url': 'https://www.anime-on-demand.de/anime/39', 'only_matching': True, }, { - # Episodes without titles + # Episodes without titles, jap, OmU 'url': 'https://www.anime-on-demand.de/anime/162', 'only_matching': True, }, { # ger/jap, Dub/OmU, account required 'url': 'https://www.anime-on-demand.de/anime/169', 'only_matching': True, + }, { + # Full length film, non-series, ger/jap, Dub/OmU, account required + 'url': 'https://www.anime-on-demand.de/anime/185', + 'only_matching': True, }] def _login(self): @@ -110,35 +115,12 @@ class AnimeOnDemandIE(InfoExtractor): entries = [] - for num, episode_html in enumerate(re.findall( - r'(?s)]+class="episodebox-title".+?>Episodeninhalt<', webpage), 1): - episodebox_title = self._search_regex( - (r'class="episodebox-title"[^>]+title=(["\'])(?P.+?)\1', - r'class="episodebox-title"[^>]+>(?P<title>.+?)<'), - episode_html, 'episodebox title', default=None, group='title') - if not episodebox_title: - continue - - episode_number = int(self._search_regex( - r'(?:Episode|Film)\s*(\d+)', - episodebox_title, 'episode number', default=num)) - episode_title = self._search_regex( - r'(?:Episode|Film)\s*\d+\s*-\s*(.+)', - episodebox_title, 'episode title', default=None) - - video_id = 'episode-%d' % episode_number - - common_info = { - 'id': video_id, - 'series': anime_title, - 'episode': episode_title, - 'episode_number': episode_number, - } - + def extract_info(html, video_id, num=None): + title, description = [None] * 2 formats = [] for input_ in re.findall( - r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', episode_html): + r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', html): attributes = extract_attributes(input_) playlist_urls = [] for playlist_key in ('data-playlist', 'data-otherplaylist'): @@ -161,7 +143,7 @@ class AnimeOnDemandIE(InfoExtractor): format_id_list.append(lang) if kind: format_id_list.append(kind) - if not format_id_list: + if not format_id_list and num is not None: format_id_list.append(compat_str(num)) format_id = '-'.join(format_id_list) format_note = ', '.join(filter(None, (kind, lang_note))) @@ -215,28 +197,74 @@ class AnimeOnDemandIE(InfoExtractor): }) formats.extend(file_formats) - if formats: - self._sort_formats(formats) + return { + 'title': title, + 'description': description, + 'formats': formats, + } + + def extract_entries(html, video_id, common_info, num=None): + info = extract_info(html, video_id, num) + + if info['formats']: + self._sort_formats(info['formats']) f = common_info.copy() - f.update({ - 'title': title, - 'description': description, - 'formats': formats, - }) + f.update(info) entries.append(f) - # Extract teaser only when full episode is not available - if not formats: + # Extract teaser/trailer only when full episode is not available + if not info['formats']: m = re.search( - r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<', - episode_html) + r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>(?P<kind>Teaser|Trailer)<', + html) if m: f = common_info.copy() f.update({ - 'id': '%s-teaser' % f['id'], + 'id': '%s-%s' % (f['id'], m.group('kind').lower()), 'title': m.group('title'), 'url': compat_urlparse.urljoin(url, m.group('href')), }) entries.append(f) + def extract_episodes(html): + for num, episode_html in enumerate(re.findall( + r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', html), 1): + episodebox_title = self._search_regex( + (r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1', + r'class="episodebox-title"[^>]+>(?P<title>.+?)<'), + episode_html, 'episodebox title', default=None, group='title') + if not episodebox_title: + continue + + episode_number = int(self._search_regex( + r'(?:Episode|Film)\s*(\d+)', + episodebox_title, 'episode number', default=num)) + episode_title = self._search_regex( + r'(?:Episode|Film)\s*\d+\s*-\s*(.+)', + episodebox_title, 'episode title', default=None) + + video_id = 'episode-%d' % episode_number + + common_info = { + 'id': video_id, + 'series': anime_title, + 'episode': episode_title, + 'episode_number': episode_number, + } + + extract_entries(episode_html, video_id, common_info) + + def extract_film(html, video_id): + common_info = { + 'id': anime_id, + 'title': anime_title, + 'description': anime_description, + } + extract_entries(html, video_id, common_info) + + extract_episodes(webpage) + + if not entries: + extract_film(webpage, anime_id) + return self.playlist_result(entries, anime_id, anime_title, anime_description) diff --git a/youtube_dl/extractor/anvato.py b/youtube_dl/extractor/anvato.py new file mode 100644 index 000000000..cb29cf111 --- /dev/null +++ b/youtube_dl/extractor/anvato.py @@ -0,0 +1,224 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import base64 +import hashlib +import json +import random +import time + +from .common import InfoExtractor +from ..aes import aes_encrypt +from ..compat import compat_str +from ..utils import ( + bytes_to_intlist, + determine_ext, + intlist_to_bytes, + int_or_none, + strip_jsonp, +) + + +def md5_text(s): + if not isinstance(s, compat_str): + s = compat_str(s) + return hashlib.md5(s.encode('utf-8')).hexdigest() + + +class AnvatoIE(InfoExtractor): + # Copied from anvplayer.min.js + _ANVACK_TABLE = { + 'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ', + 'nbcu_nbcd_desktop_web_qa_1a6f01bdd0dc45a439043b694c8a031d': 'eSxJUbA2UUKBTXryyQ2d6NuM8oEqaPySvaPzfKNA', + 'nbcu_nbcd_desktop_web_acc_eb2ff240a5d4ae9a63d4c297c32716b6c523a129': '89JR3RtUGbvKuuJIiKOMK0SoarLb5MUx8v89RcbP', + 'nbcu_nbcd_watchvod_web_prod_e61107507180976724ec8e8319fe24ba5b4b60e1': 'Uc7dFt7MJ9GsBWB5T7iPvLaMSOt8BBxv4hAXk5vv', + 'nbcu_nbcd_watchvod_web_qa_42afedba88a36203db5a4c09a5ba29d045302232': 'T12oDYVFP2IaFvxkmYMy5dKxswpLHtGZa4ZAXEi7', + 'nbcu_nbcd_watchvod_web_acc_9193214448e2e636b0ffb78abacfd9c4f937c6ca': 'MmobcxUxMedUpohNWwXaOnMjlbiyTOBLL6d46ZpR', + 'nbcu_local_monitor_web_acc_f998ad54eaf26acd8ee033eb36f39a7b791c6335': 'QvfIoPYrwsjUCcASiw3AIkVtQob2LtJHfidp9iWg', + 'nbcu_cable_monitor_web_acc_a413759603e8bedfcd3c61b14767796e17834077': 'uwVPJLShvJWSs6sWEIuVem7MTF8A4IknMMzIlFto', + 'nbcu_nbcd_mcpstage_web_qa_4c43a8f6e95a88dbb40276c0630ba9f693a63a4e': 'PxVYZVwjhgd5TeoPRxL3whssb5OUPnM3zyAzq8GY', + 'nbcu_comcast_comcast_web_prod_074080762ad4ce956b26b43fb22abf153443a8c4': 'afnaRZfDyg1Z3WZHdupKfy6xrbAG2MHqe3VfuSwh', + 'nbcu_comcast_comcast_web_qa_706103bb93ead3ef70b1de12a0e95e3c4481ade0': 'DcjsVbX9b3uoPlhdriIiovgFQZVxpISZwz0cx1ZK', + 'nbcu_comcast_comcastcable_web_prod_669f04817536743563d7331c9293e59fbdbe3d07': '0RwMN2cWy10qhAhOscq3eK7aEe0wqnKt3vJ0WS4D', + 'nbcu_comcast_comcastcable_web_qa_3d9d2d66219094127f0f6b09cc3c7bb076e3e1ca': '2r8G9DEya7PCqBceKZgrn2XkXgASjwLMuaFE1Aad', + 'hearst_hearst_demo_web_stage_960726dfef3337059a01a78816e43b29ec04dfc7': 'cuZBPXTR6kSdoTCVXwk5KGA8rk3NrgGn4H6e9Dsp', + 'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922': 'IOaaLQ8ymqVyem14QuAvE5SndQynTcH5CrLkU2Ih', + 'anvato_nextmedia_demo_web_stage_9787d56a02ff6b9f43e9a2b0920d8ca88beb5818': 'Pqu9zVzI1ApiIzbVA3VkGBEQHvdKSUuKpD6s2uaR', + 'anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a': 'du1ccmn7RxzgizwbWU7hyUaGodNlJn7HtXI0WgXW', + 'anvato_scripps_app_web_stage_360797e00fe2826be142155c4618cc52fce6c26c': '2PMrQ0BRoqCWl7nzphj0GouIMEh2mZYivAT0S1Su', + 'fs2go_fs2go_go_all_prod_21934911ccfafc03a075894ead2260d11e2ddd24': 'RcuHlKikW2IJw6HvVoEkqq2UsuEJlbEl11pWXs4Q', + 'fs2go_fs2go_go_web_prod_ead4b0eec7460c1a07783808db21b49cf1f2f9a7': '4K0HTT2u1zkQA2MaGaZmkLa1BthGSBdr7jllrhk5', + 'fs2go_fs2go_go_web_stage_407585454a4400355d4391691c67f361': 'ftnc37VKRJBmHfoGGi3kT05bHyeJzilEzhKJCyl3', + 'fs2go_fs2go_go_android_stage_44b714db6f8477f29afcba15a41e1d30': 'CtxpPvVpo6AbZGomYUhkKs7juHZwNml9b9J0J2gI', + 'anvato_cbslocal_app_web_prod_547f3e49241ef0e5d30c79b2efbca5d92c698f67': 'Pw0XX5KBDsyRnPS0R2JrSrXftsy8Jnz5pAjaYC8s', + 'anvato_cbslocal_app_web_stage_547a5f096594cd3e00620c6f825cad1096d28c80': '37OBUhX2uwNyKhhrNzSSNHSRPZpApC3trdqDBpuz', + 'fs2go_att_att_web_prod_1042dddd089a05438b6a08f972941176f699ffd8': 'JLcF20JwYvpv6uAGcLWIaV12jKwaL1R8us4b6Zkg', + 'fs2go_att_att_web_stage_807c5001955fc114a3331fe027ddc76e': 'gbu1oO1y0JiOFh4SUipt86P288JHpyjSqolrrT1x', + 'fs2go_fs2go_tudor_web_prod_a7dd8e5a7cdc830cae55eae6f3e9fee5ee49eb9b': 'ipcp87VCEZXPPe868j3orLqzc03oTy7DXsGkAXXH', + 'anvato_mhz_app_web_prod_b808218b30de7fdf60340cbd9831512bc1bf6d37': 'Stlm5Gs6BEhJLRTZHcNquyzxGqr23EuFmE5DCgjX', + 'fs2go_charter_charter_web_stage_c2c6e5a68375a1bf00fff213d3ff8f61a835a54c': 'Lz4hbJp1fwL6jlcz4M2PMzghM4jp4aAmybtT5dPc', + 'fs2go_charter_charter_web_prod_ebfe3b10f1af215a7321cd3d629e0b81dfa6fa8c': 'vUJsK345A1bVmyYDRhZX0lqFIgVXuqhmuyp1EtPK', + 'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b': 'GDKq1ixvX3MoBNdU5IOYmYa2DTUXYOozPjrCJnW7', + 'anvato_epfox_app_web_stage_a3c2ce60f8f83ef374a88b68ee73a950f8ab87ce': '2jz2NH4BsXMaDsoJ5qkHMbcczAfIReo2eFYuVC1C', + 'fs2go_verizon_verizon_web_stage_08e6df0354a4803f1b1f2428b5a9a382e8dbcd62': 'rKTVapNaAcmnUbGL4ZcuOoY4SE7VmZSQsblPFr7e', + 'fs2go_verizon_verizon_web_prod_f909564cb606eff1f731b5e22e0928676732c445': 'qLSUuHerM3u9eNPzaHyUK52obai5MvE4XDJfqYe1', + 'fs2go_foxcom_synd_web_stage_f7b9091f00ea25a4fdaaae77fca5b54cdc7e7043': '96VKF2vLd24fFiDfwPFpzM5llFN4TiIGAlodE0Re', + 'fs2go_foxcom_synd_web_prod_0f2cdd64d87e4ab6a1d54aada0ff7a7c8387a064': 'agiPjbXEyEZUkbuhcnmVPhe9NNVbDjCFq2xkcx51', + 'anvato_own_app_web_stage_1214ade5d28422c4dae9d03c1243aba0563c4dba': 'mzhamNac3swG4WsJAiUTacnGIODi6SWeVWk5D7ho', + 'anvato_own_app_web_prod_944e162ed927ec3e9ed13eb68ed2f1008ee7565e': '9TSxh6G2TXOLBoYm9ro3LdNjjvnXpKb8UR8KoIP9', + 'anvato_scripps_app_ftv_prod_a10a10468edd5afb16fb48171c03b956176afad1': 'COJ2i2UIPK7xZqIWswxe7FaVBOVgRkP1F6O6qGoH', + 'anvato_scripps_app_ftv_stage_77d3ad2bdb021ec37ca2e35eb09acd396a974c9a': 'Q7nnopNLe2PPfGLOTYBqxSaRpl209IhqaEuDZi1F', + 'anvato_univision_app_web_stage_551236ef07a0e17718c3995c35586b5ed8cb5031': 'D92PoLS6UitwxDRA191HUGT9OYcOjV6mPMa5wNyo', + 'anvato_univision_app_web_prod_039a5c0a6009e637ae8ac906718a79911e0e65e1': '5mVS5u4SQjtw6NGw2uhMbKEIONIiLqRKck5RwQLR', + 'nbcu_cnbc_springfield_ios_prod_670207fae43d6e9a94c351688851a2ce': 'M7fqCCIP9lW53oJbHs19OlJlpDrVyc2OL8gNeuTa', + 'nbcu_cnbc_springfieldvod_ios_prod_7a5f04b1ceceb0e9c9e2264a44aa236e08e034c2': 'Yia6QbJahW0S7K1I0drksimhZb4UFq92xLBmmMvk', + 'anvato_cox_app_web_prod_ce45cda237969f93e7130f50ee8bb6280c1484ab': 'cc0miZexpFtdoqZGvdhfXsLy7FXjRAOgb9V0f5fZ', + 'anvato_cox_app_web_stage_c23dbe016a8e9d8c7101d10172b92434f6088bf9': 'yivU3MYHd2eDZcOfmLbINVtqxyecKTOp8OjOuoGJ', + 'anvato_chnzero_app_web_stage_b1164d1352b579e792e542fddf13ee34c0eeb46b': 'A76QkXMmVH8lTCfU15xva1mZnSVcqeY4Xb22Kp7m', + 'anvato_chnzero_app_web_prod_253d358928dc08ec161eda2389d53707288a730c': 'OA5QI3ZWZZkdtUEDqh28AH8GedsF6FqzJI32596b', + 'anvato_discovery_vodpoc_web_stage_9fa7077b5e8af1f8355f65d4fb8d2e0e9d54e2b7': 'q3oT191tTQ5g3JCP67PkjLASI9s16DuWZ6fYmry3', + 'anvato_discovery_vodpoc_web_prod_688614983167a1af6cdf6d76343fda10a65223c1': 'qRvRQCTVHd0VVOHsMvvfidyWmlYVrTbjby7WqIuK', + 'nbcu_cnbc_springfieldvod_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua', + 'nbcu_cnbc_springfield_ftv_stage_826040aad1925a46ac5dfb4b3c5143e648c6a30d': 'JQaSb5a8Tz0PT4ti329DNmzDO30TnngTHmvX8Vua', + 'nbcu_nbcd_capture_web_stage_4dd9d585bfb984ebf856dee35db027b2465cc4ae': '0j1Ov4Vopyi2HpBZJYdL2m8ERJVGYh3nNpzPiO8F', + 'nbcu_nbcd_watch3_android_prod_7712ca5fcf1c22f19ec1870a9650f9c37db22dcf': '3LN2UB3rPUAMu7ZriWkHky9vpLMXYha8JbSnxBlx', + 'nbcu_nbcd_watchvod3_android_prod_0910a3a4692d57c0b5ff4316075bc5d096be45b9': 'mJagcQ2II30vUOAauOXne7ERwbf5S9nlB3IP17lQ', + 'anvato_scripps_app_atv_prod_790deda22e16e71e83df58f880cd389908a45d52': 'CB6trI1mpoDIM5o54DNTsji90NDBQPZ4z4RqBNSH', + 'nbcu_nbcd_watchv4_android_prod_ff67cef9cb409158c6f8c3533edddadd0b750507': 'j8CHQCUWjlYERj4NFRmUYOND85QNbHViH09UwuKm', + 'nbcu_nbcd_watchvodv4_android_prod_a814d781609989dea6a629d50ae4c7ad8cc8e907': 'rkVnUXxdA9rawVLUlDQtMue9Y4Q7lFEaIotcUhjt', + 'rvVKpA50qlOPLFxMjrCGf5pdkdQDm7qn': '1J7ZkY5Qz5lMLi93QOH9IveE7EYB3rLl', + 'nbcu_dtv_local_web_prod_b266cf49defe255fd4426a97e27c09e513e9f82f': 'HuLnJDqzLa4saCzYMJ79zDRSQpEduw1TzjMNQu2b', + 'nbcu_att_local_web_prod_4cef038b2d969a6b7d700a56a599040b6a619f67': 'Q0Em5VDc2KpydUrVwzWRXAwoNBulWUxCq2faK0AV', + 'nbcu_dish_local_web_prod_c56dcaf2da2e9157a4266c82a78195f1dd570f6b': 'bC1LWmRz9ayj2AlzizeJ1HuhTfIaJGsDBnZNgoRg', + 'nbcu_verizon_local_web_prod_88bebd2ce006d4ed980de8133496f9a74cb9b3e1': 'wzhDKJZpgvUSS1EQvpCQP8Q59qVzcPixqDGJefSk', + 'nbcu_charter_local_web_prod_9ad90f7fc4023643bb718f0fe0fd5beea2382a50': 'PyNbxNhEWLzy1ZvWEQelRuIQY88Eub7xbSVRMdfT', + 'nbcu_suddenlink_local_web_prod_20fb711725cac224baa1c1cb0b1c324d25e97178': '0Rph41lPXZbb3fqeXtHjjbxfSrNbtZp1Ygq7Jypa', + 'nbcu_wow_local_web_prod_652d9ce4f552d9c2e7b5b1ed37b8cb48155174ad': 'qayIBZ70w1dItm2zS42AptXnxW15mkjRrwnBjMPv', + 'nbcu_centurylink_local_web_prod_2034402b029bf3e837ad46814d9e4b1d1345ccd5': 'StePcPMkjsX51PcizLdLRMzxMEl5k2FlsMLUNV4k', + 'nbcu_atlanticbrd_local_web_prod_8d5f5ecbf7f7b2f5e6d908dd75d90ae3565f682e': 'NtYLb4TFUS0pRs3XTkyO5sbVGYjVf17bVbjaGscI', + 'nbcu_nbcd_watchvod_web_dev_08bc05699be47c4f31d5080263a8cfadc16d0f7c': 'hwxi2dgDoSWgfmVVXOYZm14uuvku4QfopstXckhr', + 'anvato_nextmedia_app_web_prod_a4fa8c7204aa65e71044b57aaf63711980cfe5a0': 'tQN1oGPYY1nM85rJYePWGcIb92TG0gSqoVpQTWOw', + 'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749': 'GUXNf5ZDX2jFUpu4WT2Go4DJ5nhUCzpnwDRRUx1K', + 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa': 'bLDYF8JqfG42b7bwKEgQiU9E2LTIAtnKzSgYpFUH', + 'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a': 'icgGoYGipQMMSEvhplZX1pwbN69srwKYWksz3xWK', + 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336': 'fA2iQdI7RDpynqzQYIpXALVS83NTPr8LLFK4LFsu', + 'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg', + 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900': 'rMOUZqe9lwcGq2mNgG3EDusm6lKgsUnczoOX3mbg', + 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99': 'P3uXJ0fXXditBPCGkfvlnVScpPEfKmc64Zv7ZgbK', + 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe': 'mGPvo5ZA5SgjOFAPEPXv7AnOpFUICX8hvFQVz69n', + 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582': 'qyT6PXXLjVNCrHaRVj0ugAhalNRS7Ee9BP7LUokD', + 'nbcu_nbcd_watchvodv4_web_stage_4108362fba2d4ede21f262fea3c4162cbafd66c7': 'DhaU5lj0W2gEdcSSsnxURq8t7KIWtJfD966crVDk', + 'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn', + 'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W', + 'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ', + 'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ' + } + + _AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce' + + def __init__(self, *args, **kwargs): + super(AnvatoIE, self).__init__(*args, **kwargs) + self.__server_time = None + + def _server_time(self, access_key, video_id): + if self.__server_time is not None: + return self.__server_time + + self.__server_time = int(self._download_json( + self._api_prefix(access_key) + 'server_time?anvack=' + access_key, video_id, + note='Fetching server time')['server_time']) + + return self.__server_time + + def _api_prefix(self, access_key): + return 'https://tkx2-%s.anvato.net/rest/v2/' % ('prod' if 'prod' in access_key else 'stage') + + def _get_video_json(self, access_key, video_id): + # See et() in anvplayer.min.js, which is an alias of getVideoJSON() + video_data_url = self._api_prefix(access_key) + 'mcp/video/%s?anvack=%s' % (video_id, access_key) + server_time = self._server_time(access_key, video_id) + input_data = '%d~%s~%s' % (server_time, md5_text(video_data_url), md5_text(server_time)) + + auth_secret = intlist_to_bytes(aes_encrypt( + bytes_to_intlist(input_data[:64]), bytes_to_intlist(self._AUTH_KEY))) + + video_data_url += '&X-Anvato-Adst-Auth=' + base64.b64encode(auth_secret).decode('ascii') + anvrid = md5_text(time.time() * 1000 * random.random())[:30] + payload = { + 'api': { + 'anvrid': anvrid, + 'anvstk': md5_text('%s|%s|%d|%s' % ( + access_key, anvrid, server_time, self._ANVACK_TABLE[access_key])), + 'anvts': server_time, + }, + } + + return self._download_json( + video_data_url, video_id, transform_source=strip_jsonp, + data=json.dumps(payload).encode('utf-8')) + + def _extract_anvato_videos(self, webpage, video_id): + anvplayer_data = self._parse_json(self._html_search_regex( + r'<script[^>]+data-anvp=\'([^\']+)\'', webpage, + 'Anvato player data'), video_id) + + video_id = anvplayer_data['video'] + access_key = anvplayer_data['accessKey'] + + video_data = self._get_video_json(access_key, video_id) + + formats = [] + for published_url in video_data['published_urls']: + video_url = published_url['embed_url'] + ext = determine_ext(video_url) + + if ext == 'smil': + formats.extend(self._extract_smil_formats(video_url, video_id)) + continue + + tbr = int_or_none(published_url.get('kbps')) + a_format = { + 'url': video_url, + 'format_id': ('-'.join(filter(None, ['http', published_url.get('cdn_name')]))).lower(), + 'tbr': tbr if tbr != 0 else None, + } + + if ext == 'm3u8': + # Not using _extract_m3u8_formats here as individual media + # playlists are also included in published_urls. + if tbr is None: + formats.append(self._m3u8_meta_format(video_url, ext='mp4', m3u8_id='hls')) + continue + else: + a_format.update({ + 'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])), + 'ext': 'mp4', + }) + elif ext == 'mp3': + a_format['vcodec'] = 'none' + else: + a_format.update({ + 'width': int_or_none(published_url.get('width')), + 'height': int_or_none(published_url.get('height')), + }) + formats.append(a_format) + + self._sort_formats(formats) + + subtitles = {} + for caption in video_data.get('captions', []): + a_caption = { + 'url': caption['url'], + 'ext': 'tt' if caption.get('format') == 'SMPTE-TT' else None + } + subtitles.setdefault(caption['language'], []).append(a_caption) + + return { + 'id': video_id, + 'formats': formats, + 'title': video_data.get('def_title'), + 'description': video_data.get('def_description'), + 'categories': video_data.get('categories'), + 'thumbnail': video_data.get('thumbnail'), + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index be40f85b4..a6801f3d4 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -7,6 +7,8 @@ from .common import InfoExtractor from ..compat import compat_urlparse from ..utils import ( int_or_none, + parse_duration, + unified_strdate, ) @@ -16,7 +18,8 @@ class AppleTrailersIE(InfoExtractor): _TESTS = [{ 'url': 'http://trailers.apple.com/trailers/wb/manofsteel/', 'info_dict': { - 'id': 'manofsteel', + 'id': '5111', + 'title': 'Man of Steel', }, 'playlist': [ { @@ -70,6 +73,15 @@ class AppleTrailersIE(InfoExtractor): 'id': 'blackthorn', }, 'playlist_mincount': 2, + 'expected_warnings': ['Unable to download JSON metadata'], + }, { + # json data only available from http://trailers.apple.com/trailers/feeds/data/15881.json + 'url': 'http://trailers.apple.com/trailers/fox/kungfupanda3/', + 'info_dict': { + 'id': '15881', + 'title': 'Kung Fu Panda 3', + }, + 'playlist_mincount': 4, }, { 'url': 'http://trailers.apple.com/ca/metropole/autrui/', 'only_matching': True, @@ -85,6 +97,45 @@ class AppleTrailersIE(InfoExtractor): movie = mobj.group('movie') uploader_id = mobj.group('company') + webpage = self._download_webpage(url, movie) + film_id = self._search_regex(r"FilmId\s*=\s*'(\d+)'", webpage, 'film id') + film_data = self._download_json( + 'http://trailers.apple.com/trailers/feeds/data/%s.json' % film_id, + film_id, fatal=False) + + if film_data: + entries = [] + for clip in film_data.get('clips', []): + clip_title = clip['title'] + + formats = [] + for version, version_data in clip.get('versions', {}).items(): + for size, size_data in version_data.get('sizes', {}).items(): + src = size_data.get('src') + if not src: + continue + formats.append({ + 'format_id': '%s-%s' % (version, size), + 'url': re.sub(r'_(\d+p.mov)', r'_h\1', src), + 'width': int_or_none(size_data.get('width')), + 'height': int_or_none(size_data.get('height')), + 'language': version[:2], + }) + self._sort_formats(formats) + + entries.append({ + 'id': movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', clip_title).lower(), + 'formats': formats, + 'title': clip_title, + 'thumbnail': clip.get('screen') or clip.get('thumb'), + 'duration': parse_duration(clip.get('runtime') or clip.get('faded')), + 'upload_date': unified_strdate(clip.get('posted')), + 'uploader_id': uploader_id, + }) + + page_data = film_data.get('page', {}) + return self.playlist_result(entries, film_id, page_data.get('movie_title')) + playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') def fix_html(s): diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 26446c2fe..07e67dd33 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -8,19 +8,19 @@ from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, - get_element_by_attribute, qualities, int_or_none, parse_duration, unified_strdate, xpath_text, + update_url_query, ) from ..compat import compat_etree_fromstring class ARDMediathekIE(InfoExtractor): IE_NAME = 'ARD:mediathek' - _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' + _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ 'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114', @@ -35,6 +35,7 @@ class ARDMediathekIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916', 'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e', @@ -45,6 +46,7 @@ class ARDMediathekIE(InfoExtractor): 'description': 'md5:196392e79876d0ac94c94e8cdb2875f1', 'duration': 5252, }, + 'skip': 'HTTP Error 404: Not Found', }, { # audio 'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086', @@ -56,9 +58,22 @@ class ARDMediathekIE(InfoExtractor): 'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef', 'duration': 3240, }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', 'only_matching': True, + }, { + # audio + 'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158', + 'md5': '4e8f00631aac0395fee17368ac0e9867', + 'info_dict': { + 'id': '30796318', + 'ext': 'mp3', + 'title': 'Vor dem Fest', + 'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb', + 'duration': 3287, + }, + 'skip': 'Video is no longer available', }] def _extract_media_info(self, media_info_url, webpage, video_id): @@ -114,11 +129,14 @@ class ARDMediathekIE(InfoExtractor): continue if ext == 'f4m': formats.extend(self._extract_f4m_formats( - stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', - video_id, preference=-1, f4m_id='hds', fatal=False)) + update_url_query(stream_url, { + 'hdcore': '3.1.1', + 'plugin': 'aasp-3.1.1.69.124' + }), + video_id, f4m_id='hds', fatal=False)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - stream_url, video_id, 'mp4', preference=1, m3u8_id='hls', fatal=False)) + stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) else: if server and server.startswith('rtmp'): f = { @@ -232,7 +250,8 @@ class ARDIE(InfoExtractor): 'title': 'Die Story im Ersten: Mission unter falscher Flagge', 'upload_date': '20140804', 'thumbnail': 're:^https?://.*\.jpg$', - } + }, + 'skip': 'HTTP Error 404: Not Found', } def _real_extract(self, url): @@ -274,41 +293,3 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } - - -class SportschauIE(ARDMediathekIE): - IE_NAME = 'Sportschau' - _VALID_URL = r'(?P<baseurl>https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P<id>[^/#?]+))\.html' - _TESTS = [{ - 'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html', - 'info_dict': { - 'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100', - 'ext': 'mp4', - 'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"', - 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - base_url = mobj.group('baseurl') - - 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_media_info( - base_url + '-mc_defaultQuality-h.json', webpage, video_id) - - info.update({ - 'title': title, - 'description': description, - }) - - return info diff --git a/youtube_dl/extractor/arkena.py b/youtube_dl/extractor/arkena.py new file mode 100644 index 000000000..d45cae301 --- /dev/null +++ b/youtube_dl/extractor/arkena.py @@ -0,0 +1,115 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + float_or_none, + int_or_none, + mimetype2ext, + parse_iso8601, + strip_jsonp, +) + + +class ArkenaIE(InfoExtractor): + _VALID_URL = r'https?://play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)' + _TESTS = [{ + 'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411', + 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365', + 'info_dict': { + 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe', + 'ext': 'mp4', + 'title': 'Big Buck Bunny', + 'description': 'Royalty free test video', + 'timestamp': 1432816365, + 'upload_date': '20150528', + 'is_live': False, + }, + }, { + 'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893', + 'only_matching': True, + }, { + 'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972', + 'only_matching': True, + }, { + 'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/', + 'only_matching': True, + }] + + @staticmethod + def _extract_url(webpage): + # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1', + webpage) + if mobj: + return mobj.group('url') + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + account_id = mobj.group('account_id') + + playlist = self._download_json( + 'https://play.arkena.com/config/avp/v2/player/media/%s/0/%s/?callbackMethod=_' + % (video_id, account_id), + video_id, transform_source=strip_jsonp)['Playlist'][0] + + media_info = playlist['MediaInfo'] + title = media_info['Title'] + media_files = playlist['MediaFiles'] + + is_live = False + formats = [] + for kind_case, kind_formats in media_files.items(): + kind = kind_case.lower() + for f in kind_formats: + f_url = f.get('Url') + if not f_url: + continue + is_live = f.get('Live') == 'true' + exts = (mimetype2ext(f.get('Type')), determine_ext(f_url, None)) + if kind == 'm3u8' or 'm3u8' in exts: + formats.extend(self._extract_m3u8_formats( + f_url, video_id, 'mp4', + entry_protocol='m3u8' if is_live else 'm3u8_native', + m3u8_id=kind, fatal=False, live=is_live)) + elif kind == 'flash' or 'f4m' in exts: + formats.extend(self._extract_f4m_formats( + f_url, video_id, f4m_id=kind, fatal=False)) + elif kind == 'dash' or 'mpd' in exts: + formats.extend(self._extract_mpd_formats( + f_url, video_id, mpd_id=kind, fatal=False)) + elif kind == 'silverlight': + # TODO: process when ism is supported (see + # https://github.com/rg3/youtube-dl/issues/8118) + continue + else: + tbr = float_or_none(f.get('Bitrate'), 1000) + formats.append({ + 'url': f_url, + 'format_id': '%s-%d' % (kind, tbr) if tbr else kind, + 'tbr': tbr, + }) + self._sort_formats(formats) + + description = media_info.get('Description') + video_id = media_info.get('VideoId') or video_id + timestamp = parse_iso8601(media_info.get('PublishDate')) + thumbnails = [{ + 'url': thumbnail['Url'], + 'width': int_or_none(thumbnail.get('Size')), + } for thumbnail in (media_info.get('Poster') or []) if thumbnail.get('Url')] + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'is_live': is_live, + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index e37fdae13..e0c5c1804 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -61,10 +61,7 @@ class ArteTvIE(InfoExtractor): } -class ArteTVPlus7IE(InfoExtractor): - IE_NAME = 'arte.tv:+7' - _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)' - +class ArteTVBaseIE(InfoExtractor): @classmethod def _extract_url_info(cls, url): mobj = re.match(cls._VALID_URL, url) @@ -78,60 +75,6 @@ class ArteTVPlus7IE(InfoExtractor): video_id = mobj.group('id') return video_id, lang - def _real_extract(self, url): - video_id, lang = self._extract_url_info(url) - webpage = self._download_webpage(url, video_id) - return self._extract_from_webpage(webpage, video_id, lang) - - def _extract_from_webpage(self, webpage, video_id, lang): - patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']') - ids = (video_id, '') - # some pages contain multiple videos (like - # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D), - # so we first try to look for json URLs that contain the video id from - # the 'vid' parameter. - patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates] - json_url = self._html_search_regex( - patterns, webpage, 'json vp url', default=None) - if not json_url: - def find_iframe_url(webpage, default=NO_DEFAULT): - return self._html_search_regex( - r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1', - webpage, 'iframe url', group='url', default=default) - - iframe_url = find_iframe_url(webpage, None) - if not iframe_url: - embed_url = self._html_search_regex( - r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None) - if embed_url: - player = self._download_json( - embed_url, video_id, 'Downloading player page') - iframe_url = find_iframe_url(player['html']) - # en and es URLs produce react-based pages with different layout (e.g. - # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world) - if not iframe_url: - program = self._search_regex( - r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n', - webpage, 'program', default=None) - if program: - embed_html = self._parse_json(program, video_id) - if embed_html: - iframe_url = find_iframe_url(embed_html['embed_html']) - if iframe_url: - json_url = compat_parse_qs( - compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] - if json_url: - title = self._search_regex( - r'<h3[^>]+title=(["\'])(?P<title>.+?)\1', - webpage, 'title', default=None, group='title') - return self._extract_from_json_url(json_url, video_id, lang, title=title) - # Different kind of embed URL (e.g. - # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) - embed_url = self._search_regex( - r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', - webpage, 'embed url', group='url') - return self.url_result(embed_url) - def _extract_from_json_url(self, json_url, video_id, lang, title=None): info = self._download_json(json_url, video_id) player_info = info['videoJsonPlayer'] @@ -235,28 +178,94 @@ class ArteTVPlus7IE(InfoExtractor): return info_dict +class ArteTVPlus7IE(ArteTVBaseIE): + IE_NAME = 'arte.tv:+7' + _VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)' + + _TESTS = [{ + 'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D', + 'only_matching': True, + }, { + 'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url) + + def _real_extract(self, url): + video_id, lang = self._extract_url_info(url) + webpage = self._download_webpage(url, video_id) + return self._extract_from_webpage(webpage, video_id, lang) + + def _extract_from_webpage(self, webpage, video_id, lang): + patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']') + ids = (video_id, '') + # some pages contain multiple videos (like + # http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D), + # so we first try to look for json URLs that contain the video id from + # the 'vid' parameter. + patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates] + json_url = self._html_search_regex( + patterns, webpage, 'json vp url', default=None) + if not json_url: + def find_iframe_url(webpage, default=NO_DEFAULT): + return self._html_search_regex( + r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1', + webpage, 'iframe url', group='url', default=default) + + iframe_url = find_iframe_url(webpage, None) + if not iframe_url: + embed_url = self._html_search_regex( + r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None) + if embed_url: + player = self._download_json( + embed_url, video_id, 'Downloading player page') + iframe_url = find_iframe_url(player['html']) + # en and es URLs produce react-based pages with different layout (e.g. + # http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world) + if not iframe_url: + program = self._search_regex( + r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n', + webpage, 'program', default=None) + if program: + embed_html = self._parse_json(program, video_id) + if embed_html: + iframe_url = find_iframe_url(embed_html['embed_html']) + if iframe_url: + json_url = compat_parse_qs( + compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] + if json_url: + title = self._search_regex( + r'<h3[^>]+title=(["\'])(?P<title>.+?)\1', + webpage, 'title', default=None, group='title') + return self._extract_from_json_url(json_url, video_id, lang, title=title) + # Different kind of embed URL (e.g. + # http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium) + entries = [ + self.url_result(url) + for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)] + return self.playlist_result(entries) + + # It also uses the arte_vp_url url from the webpage to extract the information class ArteTVCreativeIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:creative' _VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ - 'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design', + 'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1', 'info_dict': { - 'id': '72176', + 'id': '057405-001-A', 'ext': 'mp4', - 'title': 'Folge 2 - Corporate Design', - 'upload_date': '20131004', + 'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)', + 'upload_date': '20150716', }, }, { 'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion', - 'info_dict': { - 'id': '160676', - 'ext': 'mp4', - 'title': 'Monty Python live (mostly)', - 'description': 'Événement ! Quarante-cinq ans après leurs premiers succès, les légendaires Monty Python remontent sur scène.\n', - 'upload_date': '20140805', - } + 'playlist_count': 11, + 'add_ie': ['Youtube'], }, { 'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde', 'only_matching': True, @@ -267,7 +276,7 @@ class ArteTVInfoIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:info' _VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere', 'info_dict': { 'id': '067528-000-A', @@ -275,7 +284,7 @@ class ArteTVInfoIE(ArteTVPlus7IE): 'title': 'Service civique, un cache misère ?', 'upload_date': '20160403', }, - } + }] class ArteTVFutureIE(ArteTVPlus7IE): @@ -300,6 +309,8 @@ class ArteTVDDCIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:ddc' _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)' + _TESTS = [] + def _real_extract(self, url): video_id, lang = self._extract_url_info(url) if lang == 'folge': @@ -318,7 +329,7 @@ class ArteTVConcertIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:concert' _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde', 'md5': '9ea035b7bd69696b67aa2ccaaa218161', 'info_dict': { @@ -328,24 +339,23 @@ class ArteTVConcertIE(ArteTVPlus7IE): 'upload_date': '20140128', 'description': 'md5:486eb08f991552ade77439fe6d82c305', }, - } + }] class ArteTVCinemaIE(ArteTVPlus7IE): IE_NAME = 'arte.tv:cinema' _VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)' - _TEST = { - 'url': 'http://cinema.arte.tv/de/node/38291', - 'md5': '6b275511a5107c60bacbeeda368c3aa1', + _TESTS = [{ + 'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck', + 'md5': 'a5b9dd5575a11d93daf0e3f404f45438', 'info_dict': { - 'id': '055876-000_PWA12025-D', + 'id': '062494-000-A', 'ext': 'mp4', - 'title': 'Tod auf dem Nil', - 'upload_date': '20160122', - 'description': 'md5:7f749bbb77d800ef2be11d54529b96bc', + 'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck', + 'upload_date': '20150807', }, - } + }] class ArteTVMagazineIE(ArteTVPlus7IE): @@ -390,9 +400,42 @@ class ArteTVEmbedIE(ArteTVPlus7IE): ) ''' + _TESTS = [] + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') lang = mobj.group('lang') json_url = mobj.group('json_url') return self._extract_from_json_url(json_url, video_id, lang) + + +class ArteTVPlaylistIE(ArteTVBaseIE): + IE_NAME = 'arte.tv:playlist' + _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)' + + _TESTS = [{ + 'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV', + 'info_dict': { + 'id': 'PL-013263', + 'title': 'Areva & Uramin', + 'description': 'md5:a1dc0312ce357c262259139cfd48c9bf', + }, + 'playlist_mincount': 6, + }, { + 'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV', + 'only_matching': True, + }] + + def _real_extract(self, url): + playlist_id, lang = self._extract_url_info(url) + collection = self._download_json( + 'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos' + % (lang, playlist_id), playlist_id) + title = collection.get('title') + description = collection.get('shortDescription') or collection.get('teaserText') + entries = [ + self._extract_from_json_url( + video['jsonUrl'], video.get('programId') or playlist_id, lang) + for video in collection['videos'] if video.get('jsonUrl')] + return self.playlist_result(entries, playlist_id, title, description) diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py index a52d26cec..f3bd4d444 100644 --- a/youtube_dl/extractor/audiomack.py +++ b/youtube_dl/extractor/audiomack.py @@ -6,6 +6,7 @@ import time from .common import InfoExtractor from .soundcloud import SoundcloudIE +from ..compat import compat_str from ..utils import ( ExtractorError, url_basename, @@ -136,7 +137,7 @@ class AudiomackAlbumIE(InfoExtractor): result[resultkey] = api_response[apikey] song_id = url_basename(api_response['url']).rpartition('.')[0] result['entries'].append({ - 'id': api_response.get('id', song_id), + 'id': compat_str(api_response.get('id', song_id)), 'uploader': api_response.get('artist'), 'title': api_response.get('title', song_id), 'url': api_response['url'], diff --git a/youtube_dl/extractor/azubu.py b/youtube_dl/extractor/azubu.py index efa624de1..a813eb429 100644 --- a/youtube_dl/extractor/azubu.py +++ b/youtube_dl/extractor/azubu.py @@ -46,6 +46,7 @@ class AzubuIE(InfoExtractor): 'uploader_id': 272749, 'view_count': int, }, + 'skip': 'Channel offline', }, ] @@ -56,22 +57,26 @@ class AzubuIE(InfoExtractor): 'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data'] title = data['title'].strip() - description = data['description'] - thumbnail = data['thumbnail'] - view_count = data['view_count'] - uploader = data['user']['username'] - uploader_id = data['user']['id'] + description = data.get('description') + thumbnail = data.get('thumbnail') + view_count = data.get('view_count') + user = data.get('user', {}) + uploader = user.get('username') + uploader_id = user.get('id') stream_params = json.loads(data['stream_params']) - timestamp = float_or_none(stream_params['creationDate'], 1000) - duration = float_or_none(stream_params['length'], 1000) + timestamp = float_or_none(stream_params.get('creationDate'), 1000) + duration = float_or_none(stream_params.get('length'), 1000) renditions = stream_params.get('renditions') or [] video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength') if video: renditions.append(video) + if not renditions and not user.get('channel', {}).get('is_live', True): + raise ExtractorError('%s said: channel is offline.' % self.IE_NAME, expected=True) + formats = [{ 'url': fmt['url'], 'width': fmt['frameWidth'], diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index c1ef8051d..991ab0676 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -29,7 +29,7 @@ class BandcampIE(InfoExtractor): '_skip': 'There is a limit of 200 free downloads / month for the test song' }, { 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', - 'md5': '2b68e5851514c20efdff2afc5603b8b4', + 'md5': '73d0b3171568232574e45652f8720b5c', 'info_dict': { 'id': '2650410135', 'ext': 'mp3', @@ -48,6 +48,10 @@ class BandcampIE(InfoExtractor): if m_trackinfo: json_code = m_trackinfo.group(1) data = json.loads(json_code)[0] + track_id = compat_str(data['id']) + + if not data.get('file'): + raise ExtractorError('Not streamable', video_id=track_id, expected=True) formats = [] for format_id, format_url in data['file'].items(): @@ -64,7 +68,7 @@ class BandcampIE(InfoExtractor): self._sort_formats(formats) return { - 'id': compat_str(data['id']), + 'id': track_id, 'title': data['title'], 'formats': formats, 'duration': float_or_none(data.get('duration')), diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 74c4510f9..9cb7630a1 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -31,7 +31,7 @@ class BBCCoUkIE(InfoExtractor): music/clips[/#]| radio/player/ ) - (?P<id>%s) + (?P<id>%s)(?!/(?:episodes|broadcasts|clips)) ''' % _ID_REGEX _MEDIASELECTOR_URLS = [ @@ -192,6 +192,7 @@ class BBCCoUkIE(InfoExtractor): # rtmp download 'skip_download': True, }, + 'skip': 'Now it\'s really geo-restricted', }, { # compact player (https://github.com/rg3/youtube-dl/issues/8147) 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player', @@ -588,7 +589,8 @@ class BBCIE(BBCCoUkIE): 'info_dict': { 'id': '150615_telabyad_kentin_cogu', 'ext': 'mp4', - 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", + 'title': "Tel Abyad'da IŞİD bayrağı indirildi YPG bayrağı çekildi", + 'description': 'md5:33a4805a855c9baf7115fcbde57e7025', 'timestamp': 1434397334, 'upload_date': '20150615', }, @@ -602,6 +604,7 @@ class BBCIE(BBCCoUkIE): 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', 'ext': 'mp4', 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', + 'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8', 'timestamp': 1434713142, 'upload_date': '20150619', }, @@ -698,7 +701,9 @@ class BBCIE(BBCCoUkIE): @classmethod def suitable(cls, url): - return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url) + EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE) + return (False if any(ie.suitable(url) for ie in EXCLUDE_IE) + else super(BBCIE, cls).suitable(url)) def _extract_from_media_meta(self, media_meta, video_id): # Direct links to media in media metadata (e.g. @@ -815,8 +820,20 @@ class BBCIE(BBCCoUkIE): # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani) playlist = data_playable.get('otherSettings', {}).get('playlist', {}) if playlist: - entries.append(self._extract_from_playlist_sxml( - playlist.get('progressiveDownloadUrl'), playlist_id, timestamp)) + for key in ('progressiveDownload', 'streaming'): + playlist_url = playlist.get('%sUrl' % key) + if not playlist_url: + continue + try: + entries.append(self._extract_from_playlist_sxml( + playlist_url, playlist_id, timestamp)) + except Exception as e: + # Some playlist URL may fail with 500, at the same time + # the other one may work fine (e.g. + # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500: + continue + raise if entries: return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) @@ -975,3 +992,82 @@ class BBCCoUkArticleIE(InfoExtractor): r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)] return self.playlist_result(entries, playlist_id, title, description) + + +class BBCCoUkPlaylistBaseIE(InfoExtractor): + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key()) + for video_id in re.findall( + self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)] + + title, description = self._extract_title_and_description(webpage) + + return self.playlist_result(entries, playlist_id, title, description) + + +class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE): + IE_NAME = 'bbc.co.uk:iplayer:playlist' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX + _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s' + _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)' + _TESTS = [{ + 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v', + 'info_dict': { + 'id': 'b05rcz9v', + 'title': 'The Disappearance', + 'description': 'French thriller serial about a missing teenager.', + }, + 'playlist_mincount': 6, + 'skip': 'This programme is not currently available on BBC iPlayer', + }, { + # Available for over a year unlike 30 days for most other programmes + 'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32', + 'info_dict': { + 'id': 'p02tcc32', + 'title': 'Bohemian Icons', + 'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7', + }, + 'playlist_mincount': 10, + }] + + def _extract_title_and_description(self, webpage): + title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False) + description = self._search_regex( + r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>', + webpage, 'description', fatal=False, group='value') + return title, description + + +class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE): + IE_NAME = 'bbc.co.uk:playlist' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX + _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s' + _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)' + _TESTS = [{ + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', + 'info_dict': { + 'id': 'b05rcz9v', + 'title': 'The Disappearance - Clips - BBC Four', + 'description': 'French thriller serial about a missing teenager.', + }, + 'playlist_mincount': 7, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player', + 'only_matching': True, + }] + + def _extract_title_and_description(self, webpage): + title = self._og_search_title(webpage, fatal=False) + description = self._og_search_description(webpage) + return title, description diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py index 986245bf0..bd3ee2e2e 100644 --- a/youtube_dl/extractor/bet.py +++ b/youtube_dl/extractor/bet.py @@ -1,31 +1,27 @@ from __future__ import unicode_literals -from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote -from ..utils import ( - xpath_text, - xpath_with_ns, - int_or_none, - parse_iso8601, -) +from .mtv import MTVServicesInfoExtractor +from ..utils import unified_strdate +from ..compat import compat_urllib_parse_urlencode -class BetIE(InfoExtractor): +class BetIE(MTVServicesInfoExtractor): _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html' _TESTS = [ { 'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html', 'info_dict': { - 'id': 'news/national/2014/a-conversation-with-president-obama', + 'id': '07e96bd3-8850-3051-b856-271b457f0ab8', 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism', 'ext': 'flv', 'title': 'A Conversation With President Obama', - 'description': 'md5:699d0652a350cf3e491cd15cc745b5da', + 'description': 'President Obama urges persistence in confronting racism and bias.', 'duration': 1534, - 'timestamp': 1418075340, 'upload_date': '20141208', - 'uploader': 'admin', 'thumbnail': 're:(?i)^https?://.*\.jpg$', + 'subtitles': { + 'en': 'mincount:2', + } }, 'params': { # rtmp download @@ -35,16 +31,17 @@ class BetIE(InfoExtractor): { 'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html', 'info_dict': { - 'id': 'news/national/2014/justice-for-ferguson-a-community-reacts', + 'id': '9f516bf1-7543-39c4-8076-dd441b459ba9', 'display_id': 'justice-for-ferguson-a-community-reacts', 'ext': 'flv', 'title': 'Justice for Ferguson: A Community Reacts', 'description': 'A BET News special.', 'duration': 1696, - 'timestamp': 1416942360, 'upload_date': '20141125', - 'uploader': 'admin', 'thumbnail': 're:(?i)^https?://.*\.jpg$', + 'subtitles': { + 'en': 'mincount:2', + } }, 'params': { # rtmp download @@ -53,57 +50,32 @@ class BetIE(InfoExtractor): } ] + _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player" + + def _get_feed_query(self, uri): + return compat_urllib_parse_urlencode({ + 'uuid': uri, + }) + + def _extract_mgid(self, webpage): + return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid') + def _real_extract(self, url): display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + mgid = self._extract_mgid(webpage) + videos_info = self._get_videos_info(mgid) - media_url = compat_urllib_parse_unquote(self._search_regex( - [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"], - webpage, 'media URL')) + info_dict = videos_info['entries'][0] - video_id = self._search_regex( - r'/video/(.*)/_jcr_content/', media_url, 'video id') + upload_date = unified_strdate(self._html_search_meta('date', webpage)) + description = self._html_search_meta('description', webpage) - mrss = self._download_xml(media_url, display_id) - - item = mrss.find('./channel/item') - - NS_MAP = { - 'dc': 'http://purl.org/dc/elements/1.1/', - 'media': 'http://search.yahoo.com/mrss/', - 'ka': 'http://kickapps.com/karss', - } - - title = xpath_text(item, './title', 'title') - description = xpath_text( - item, './description', 'description', fatal=False) - - timestamp = parse_iso8601(xpath_text( - item, xpath_with_ns('./dc:date', NS_MAP), - 'upload date', fatal=False)) - uploader = xpath_text( - item, xpath_with_ns('./dc:creator', NS_MAP), - 'uploader', fatal=False) - - media_content = item.find( - xpath_with_ns('./media:content', NS_MAP)) - duration = int_or_none(media_content.get('duration')) - smil_url = media_content.get('url') - - thumbnail = media_content.find( - xpath_with_ns('./media:thumbnail', NS_MAP)).get('url') - - formats = self._extract_smil_formats(smil_url, display_id) - self._sort_formats(formats) - - return { - 'id': video_id, + info_dict.update({ 'display_id': display_id, - 'title': title, 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'uploader': uploader, - 'duration': duration, - 'formats': formats, - } + 'upload_date': upload_date, + }) + + return info_dict diff --git a/youtube_dl/extractor/bigflix.py b/youtube_dl/extractor/bigflix.py index 33762ad93..b19f35b5d 100644 --- a/youtube_dl/extractor/bigflix.py +++ b/youtube_dl/extractor/bigflix.py @@ -12,7 +12,7 @@ class BigflixIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)' _TESTS = [{ 'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537', - 'md5': 'ec76aa9b1129e2e5b301a474e54fab74', + 'md5': 'dc1b4aebb46e3a7077ecc0d9f43f61e3', 'info_dict': { 'id': '16537', 'ext': 'mp4', @@ -26,7 +26,7 @@ class BigflixIE(InfoExtractor): 'id': '16070', 'ext': 'mp4', 'title': 'Madarasapatinam', - 'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca', + 'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b', 'formats': 'mincount:2', }, 'params': { diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 8baff2041..b17047b39 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -1,34 +1,42 @@ # coding: utf-8 from __future__ import unicode_literals +import calendar +import datetime import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_etree_fromstring, + compat_str, + compat_parse_qs, + compat_xml_parse_error, +) from ..utils import ( - int_or_none, - unescapeHTML, ExtractorError, + int_or_none, + float_or_none, xpath_text, ) class BiliBiliIE(InfoExtractor): - _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?' + _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)' _TESTS = [{ 'url': 'http://www.bilibili.tv/video/av1074402/', - 'md5': '2c301e4dab317596e837c3e7633e7d86', + 'md5': '5f7d29e1a2872f3df0cf76b1f87d3788', 'info_dict': { 'id': '1554319', 'ext': 'flv', 'title': '【金坷垃】金泡沫', - 'duration': 308313, + 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', + 'duration': 308.067, + 'timestamp': 1398012660, 'upload_date': '20140420', 'thumbnail': 're:^https?://.+\.jpg', - 'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923', - 'timestamp': 1397983878, 'uploader': '菊子桑', + 'uploader_id': '156160', }, }, { 'url': 'http://www.bilibili.com/video/av1041170/', @@ -36,75 +44,186 @@ class BiliBiliIE(InfoExtractor): 'id': '1041170', 'title': '【BD1080P】刀语【诸神&异域】', 'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~', - 'uploader': '枫叶逝去', - 'timestamp': 1396501299, }, 'playlist_count': 9, + }, { + 'url': 'http://www.bilibili.com/video/av4808130/', + 'info_dict': { + 'id': '4808130', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + }, + 'playlist': [{ + 'md5': '55cdadedf3254caaa0d5d27cf20a8f9c', + 'info_dict': { + 'id': '4808130_part1', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }, { + 'md5': '926f9f67d0c482091872fbd8eca7ea3d', + 'info_dict': { + 'id': '4808130_part2', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }, { + 'md5': '4b7b225b968402d7c32348c646f1fd83', + 'info_dict': { + 'id': '4808130_part3', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }, { + 'md5': '7b795e214166501e9141139eea236e91', + 'info_dict': { + 'id': '4808130_part4', + 'ext': 'flv', + 'title': '【长篇】哆啦A梦443【钉铛】', + 'description': '(2016.05.27)来组合客人的脸吧&amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;illust_id=56912929', + 'timestamp': 1464564180, + 'upload_date': '20160529', + 'uploader': '喜欢拉面', + 'uploader_id': '151066', + }, + }], + }, { + # Missing upload time + 'url': 'http://www.bilibili.com/video/av1867637/', + 'info_dict': { + 'id': '2880301', + 'ext': 'flv', + 'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】', + 'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】', + 'uploader': '黑夜为猫', + 'uploader_id': '610729', + }, + 'params': { + # Just to test metadata extraction + 'skip_download': True, + }, + 'expected_warnings': ['upload time'], }] + # BiliBili blocks keys from time to time. The current key is extracted from + # the Android client + # TODO: find the sign algorithm used in the flash player + _APP_KEY = '86385cdc024c0f6c' + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - page_num = mobj.group('page_num') or '1' - view_data = self._download_json( - 'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num), - video_id) - if 'error' in view_data: - raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True) + webpage = self._download_webpage(url, video_id) - cid = view_data['cid'] - title = unescapeHTML(view_data['title']) + params = compat_parse_qs(self._search_regex( + [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)', + r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'], + webpage, 'player parameters')) + cid = params['cid'][0] - doc = self._download_xml( - 'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid, - cid, - 'Downloading page %s/%s' % (page_num, view_data['pages']) - ) + info_xml_str = self._download_webpage( + 'http://interface.bilibili.com/v_cdn_play', + cid, query={'appkey': self._APP_KEY, 'cid': cid}, + note='Downloading video info page') - if xpath_text(doc, './result') == 'error': - raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True) + err_msg = None + durls = None + info_xml = None + try: + info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8')) + except compat_xml_parse_error: + info_json = self._parse_json(info_xml_str, video_id, fatal=False) + err_msg = (info_json or {}).get('error_text') + else: + err_msg = xpath_text(info_xml, './message') + + if info_xml is not None: + durls = info_xml.findall('./durl') + if not durls: + if err_msg: + raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True) + else: + raise ExtractorError('No videos found!') entries = [] - for durl in doc.findall('./durl'): + for durl in durls: size = xpath_text(durl, ['./filesize', './size']) formats = [{ 'url': durl.find('./url').text, 'filesize': int_or_none(size), - 'ext': 'flv', }] - backup_urls = durl.find('./backup_url') - if backup_urls is not None: - for backup_url in backup_urls.findall('./url'): - formats.append({'url': backup_url.text}) - formats.reverse() + for backup_url in durl.findall('./backup_url/url'): + formats.append({ + 'url': backup_url.text, + # backup URLs have lower priorities + 'preference': -2 if 'hd.mp4' in backup_url.text else -3, + }) + + self._sort_formats(formats) entries.append({ 'id': '%s_part%s' % (cid, xpath_text(durl, './order')), - 'title': title, 'duration': int_or_none(xpath_text(durl, './length'), 1000), 'formats': formats, }) + title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title') + description = self._html_search_meta('description', webpage) + datetime_str = self._html_search_regex( + r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False) + timestamp = None + if datetime_str: + timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple()) + + # TODO 'view_count' requires deobfuscating Javascript info = { 'id': compat_str(cid), 'title': title, - 'description': view_data.get('description'), - 'thumbnail': view_data.get('pic'), - 'uploader': view_data.get('author'), - 'timestamp': int_or_none(view_data.get('created')), - 'view_count': int_or_none(view_data.get('play')), - 'duration': int_or_none(xpath_text(doc, './timelength')), + 'description': description, + 'timestamp': timestamp, + 'thumbnail': self._html_search_meta('thumbnailUrl', webpage), + 'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000), } + uploader_mobj = re.search( + r'<a[^>]+href="https?://space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"', + webpage) + if uploader_mobj: + info.update({ + 'uploader': uploader_mobj.group('name'), + 'uploader_id': uploader_mobj.group('id'), + }) + + for entry in entries: + entry.update(info) + if len(entries) == 1: - entries[0].update(info) return entries[0] else: - info.update({ + for idx, entry in enumerate(entries): + entry['id'] = '%s_part%d' % (video_id, (idx + 1)) + + return { '_type': 'multi_video', 'id': video_id, + 'title': title, + 'description': description, 'entries': entries, - }) - return info + } diff --git a/youtube_dl/extractor/biobiochiletv.py b/youtube_dl/extractor/biobiochiletv.py index 133228133..7608c0a08 100644 --- a/youtube_dl/extractor/biobiochiletv.py +++ b/youtube_dl/extractor/biobiochiletv.py @@ -2,11 +2,15 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import remove_end +from ..utils import ( + ExtractorError, + remove_end, +) +from .rudo import RudoIE class BioBioChileTVIE(InfoExtractor): - _VALID_URL = r'https?://tv\.biobiochile\.cl/notas/(?:[^/]+/)+(?P<id>[^/]+)\.shtml' + _VALID_URL = r'https?://(?:tv|www)\.biobiochile\.cl/(?:notas|noticias)/(?:[^/]+/)+(?P<id>[^/]+)\.shtml' _TESTS = [{ 'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml', @@ -18,6 +22,7 @@ class BioBioChileTVIE(InfoExtractor): 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'Fernando Atria', }, + 'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html', }, { # different uploader layout 'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml', @@ -32,6 +37,16 @@ class BioBioChileTVIE(InfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html', + }, { + 'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml', + 'info_dict': { + 'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos', + 'ext': 'mp4', + 'uploader': '(none)', + 'upload_date': '20160708', + 'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos', + }, }, { 'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml', 'only_matching': True, @@ -45,42 +60,22 @@ class BioBioChileTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + rudo_url = RudoIE._extract_url(webpage) + if not rudo_url: + raise ExtractorError('No videos found') + title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV') - file_url = self._search_regex( - r'loadFWPlayerVideo\([^,]+,\s*(["\'])(?P<url>.+?)\1', - webpage, 'file url', group='url') - - base_url = self._search_regex( - r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*fileURL', webpage, - 'base url', default='http://unlimited2-cl.digitalproserver.com/bbtv/', - group='url') - - formats = self._extract_m3u8_formats( - '%s%s/playlist.m3u8' % (base_url, file_url), video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) - f = { - 'url': '%s%s' % (base_url, file_url), - 'format_id': 'http', - 'protocol': 'http', - 'preference': 1, - } - if formats: - f_copy = formats[-1].copy() - f_copy.update(f) - f = f_copy - formats.append(f) - self._sort_formats(formats) - thumbnail = self._og_search_thumbnail(webpage) uploader = self._html_search_regex( - r'<a[^>]+href=["\']https?://busca\.biobiochile\.cl/author[^>]+>(.+?)</a>', + r'<a[^>]+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>', webpage, 'uploader', fatal=False) return { + '_type': 'url_transparent', + 'url': rudo_url, 'id': video_id, 'title': title, 'thumbnail': thumbnail, 'uploader': uploader, - 'formats': formats, } diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index bd538be50..2a8cd64b9 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -20,6 +21,18 @@ class BloombergIE(InfoExtractor): 'params': { 'format': 'best[format_id^=hds]', }, + }, { + # video ID in BPlayer(...) + 'url': 'http://www.bloomberg.com/features/2016-hello-world-new-zealand/', + 'info_dict': { + 'id': '938c7e72-3f25-4ddb-8b85-a9be731baa74', + 'ext': 'flv', + 'title': 'Meet the Real-Life Tech Wizards of Middle Earth', + 'description': 'Hello World, Episode 1: New Zealand’s freaky AI babies, robot exoskeletons, and a virtual you.', + }, + 'params': { + 'format': 'best[format_id^=hds]', + }, }, { 'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets', 'only_matching': True, @@ -33,7 +46,11 @@ class BloombergIE(InfoExtractor): webpage = self._download_webpage(url, name) video_id = self._search_regex( r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1', - webpage, 'id', group='url') + webpage, 'id', group='url', default=None) + if not video_id: + bplayer_data = self._parse_json(self._search_regex( + r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name) + video_id = bplayer_data['id'] title = re.sub(': Video$', '', self._og_search_title(webpage)) embed_info = self._download_json( diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 11cf49851..ff0aa11b1 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -29,7 +29,8 @@ class BRIE(InfoExtractor): 'duration': 180, 'uploader': 'Reinhard Weber', 'upload_date': '20150422', - } + }, + 'skip': '404 not found', }, { 'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html', @@ -40,7 +41,8 @@ class BRIE(InfoExtractor): 'title': 'Manfred Schreiber ist tot', 'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97', 'duration': 26, - } + }, + 'skip': '404 not found', }, { 'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html', @@ -51,7 +53,8 @@ class BRIE(InfoExtractor): 'title': 'Kurzweilig und sehr bewegend', 'description': 'md5:0351996e3283d64adeb38ede91fac54e', 'duration': 296, - } + }, + 'skip': '404 not found', }, { 'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html', diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index fc7fc5b16..aeb22be16 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -26,6 +26,8 @@ from ..utils import ( unescapeHTML, unsmuggle_url, update_url_query, + clean_html, + mimetype2ext, ) @@ -90,6 +92,7 @@ class BrightcoveLegacyIE(InfoExtractor): 'description': 'md5:363109c02998fee92ec02211bd8000df', 'uploader': 'National Ballet of Canada', }, + 'skip': 'Video gone', }, { # test flv videos served by akamaihd.net @@ -108,7 +111,7 @@ class BrightcoveLegacyIE(InfoExtractor): }, }, { - # playlist test + # playlist with 'videoList' # from http://support.brightcove.com/en/video-cloud/docs/playlist-support-single-video-players 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=3550052898001&playerKey=AQ%7E%7E%2CAAABmA9XpXk%7E%2C-Kp7jNgisre1fG5OdqpAFUTcs0lP_ZoL', 'info_dict': { @@ -117,6 +120,15 @@ class BrightcoveLegacyIE(InfoExtractor): }, 'playlist_mincount': 7, }, + { + # playlist with 'playlistTab' (https://github.com/rg3/youtube-dl/issues/9965) + 'url': 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=AQ%7E%7E,AAABXlLMdok%7E,NJ4EoMlZ4rZdx9eU1rkMVd8EaYPBBUlg', + 'info_dict': { + 'id': '1522758701001', + 'title': 'Lesson 08', + }, + 'playlist_mincount': 10, + }, ] FLV_VCODECS = { 1: 'SORENSON', @@ -298,13 +310,19 @@ class BrightcoveLegacyIE(InfoExtractor): info_url, player_key, 'Downloading playlist information') json_data = json.loads(playlist_info) - if 'videoList' not in json_data: + if 'videoList' in json_data: + playlist_info = json_data['videoList'] + playlist_dto = playlist_info['mediaCollectionDTO'] + elif 'playlistTabs' in json_data: + playlist_info = json_data['playlistTabs'] + playlist_dto = playlist_info['lineupListDTO']['playlistDTOs'][0] + else: raise ExtractorError('Empty playlist') - playlist_info = json_data['videoList'] - videos = [self._extract_video_info(video_info) for video_info in playlist_info['mediaCollectionDTO']['videoDTOs']] + + videos = [self._extract_video_info(video_info) for video_info in playlist_dto['videoDTOs']] return self.playlist_result(videos, playlist_id='%s' % playlist_info['id'], - playlist_title=playlist_info['mediaCollectionDTO']['displayName']) + playlist_title=playlist_dto['displayName']) def _extract_video_info(self, video_info): video_id = compat_str(video_info['id']) @@ -444,6 +462,10 @@ class BrightcoveNewIE(InfoExtractor): # non numeric ref: prefixed video id 'url': 'http://players.brightcove.net/710858724001/default_default/index.html?videoId=ref:event-stream-356', 'only_matching': True, + }, { + # unavailable video without message but with error_code + 'url': 'http://players.brightcove.net/1305187701/c832abfb-641b-44eb-9da0-2fe76786505f_default/index.html?videoId=4377407326001', + 'only_matching': True, }] @staticmethod @@ -514,8 +536,9 @@ class BrightcoveNewIE(InfoExtractor): }) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - json_data = self._parse_json(e.cause.read().decode(), video_id) - raise ExtractorError(json_data[0]['message'], expected=True) + json_data = self._parse_json(e.cause.read().decode(), video_id)[0] + raise ExtractorError( + json_data.get('message') or json_data['error_code'], expected=True) raise title = json_data['name'].strip() @@ -523,14 +546,16 @@ class BrightcoveNewIE(InfoExtractor): formats = [] for source in json_data.get('sources', []): container = source.get('container') - source_type = source.get('type') + ext = mimetype2ext(source.get('type')) src = source.get('src') - if source_type == 'application/x-mpegURL' or container == 'M2TS': + if ext == 'ism': + continue + elif ext == 'm3u8' or container == 'M2TS': if not src: continue formats.extend(self._extract_m3u8_formats( src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - elif source_type == 'application/dash+xml': + elif ext == 'mpd': if not src: continue formats.extend(self._extract_mpd_formats(src, video_id, 'dash', fatal=False)) @@ -546,7 +571,7 @@ class BrightcoveNewIE(InfoExtractor): 'tbr': tbr, 'filesize': int_or_none(source.get('size')), 'container': container, - 'ext': container.lower(), + 'ext': ext or container.lower(), } if width == 0 and height == 0: f.update({ @@ -580,6 +605,13 @@ class BrightcoveNewIE(InfoExtractor): 'format_id': build_format_id('rtmp'), }) formats.append(f) + + errors = json_data.get('errors') + if not formats and errors: + error = errors[0] + raise ExtractorError( + error.get('message') or error.get('error_subcode') or error['error_code'], expected=True) + self._sort_formats(formats) subtitles = {} @@ -592,7 +624,7 @@ class BrightcoveNewIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'description': json_data.get('description'), + 'description': clean_html(json_data.get('description')), 'thumbnail': json_data.get('thumbnail') or json_data.get('poster'), 'duration': float_or_none(json_data.get('duration'), 1000), 'timestamp': parse_iso8601(json_data.get('published_at')), diff --git a/youtube_dl/extractor/buzzfeed.py b/youtube_dl/extractor/buzzfeed.py index df503ecc0..75fa92d7c 100644 --- a/youtube_dl/extractor/buzzfeed.py +++ b/youtube_dl/extractor/buzzfeed.py @@ -5,6 +5,7 @@ import json import re from .common import InfoExtractor +from .facebook import FacebookIE class BuzzFeedIE(InfoExtractor): @@ -20,11 +21,11 @@ class BuzzFeedIE(InfoExtractor): 'info_dict': { 'id': 'aVCR29aE_OQ', 'ext': 'mp4', + 'title': 'Angry Ram destroys a punching bag..', + 'description': 'md5:c59533190ef23fd4458a5e8c8c872345', 'upload_date': '20141024', 'uploader_id': 'Buddhanz1', - 'description': 'He likes to stay in shape with his heavy bag, he wont stop until its on the ground\n\nFollow Angry Ram on Facebook for regular updates -\nhttps://www.facebook.com/pages/Angry-Ram/1436897249899558?ref=hl', - 'uploader': 'Buddhanz', - 'title': 'Angry Ram destroys a punching bag', + 'uploader': 'Angry Ram', } }] }, { @@ -41,13 +42,30 @@ class BuzzFeedIE(InfoExtractor): 'info_dict': { 'id': 'mVmBL8B-In0', 'ext': 'mp4', + 'title': 're:Munchkin the Teddy Bear gets her exercise', + 'description': 'md5:28faab95cda6e361bcff06ec12fc21d8', 'upload_date': '20141124', 'uploader_id': 'CindysMunchkin', - 'description': 're:© 2014 Munchkin the', 'uploader': 're:^Munchkin the', - 'title': 're:Munchkin the Teddy Bear gets her exercise', }, }] + }, { + 'url': 'http://www.buzzfeed.com/craigsilverman/the-most-adorable-crash-landing-ever#.eq7pX0BAmK', + 'info_dict': { + 'id': 'the-most-adorable-crash-landing-ever', + 'title': 'Watch This Baby Goose Make The Most Adorable Crash Landing', + 'description': 'This gosling knows how to stick a landing.', + }, + 'playlist': [{ + 'md5': '763ca415512f91ca62e4621086900a23', + 'info_dict': { + 'id': '971793786185728', + 'ext': 'mp4', + 'title': 'We set up crash pads so that the goslings on our roof would have a safe landi...', + 'uploader': 'Calgary Outdoor Centre-University of Calgary', + }, + }], + 'add_ie': ['Facebook'], }] def _real_extract(self, url): @@ -66,6 +84,10 @@ class BuzzFeedIE(InfoExtractor): continue entries.append(self.url_result(video['url'])) + facebook_url = FacebookIE._extract_url(webpage) + if facebook_url: + entries.append(self.url_result(facebook_url)) + return { '_type': 'playlist', 'id': playlist_id, diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index dda98059e..3aec601f8 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -11,6 +11,7 @@ class BYUtvIE(InfoExtractor): _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)' _TEST = { 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5', + 'md5': '05850eb8c749e2ee05ad5a1c34668493', 'info_dict': { 'id': 'studio-c-season-5-episode-5', 'ext': 'mp4', @@ -21,7 +22,8 @@ class BYUtvIE(InfoExtractor): }, 'params': { 'skip_download': True, - } + }, + 'add_ie': ['Ooyala'], } def _real_extract(self, url): diff --git a/youtube_dl/extractor/camdemy.py b/youtube_dl/extractor/camdemy.py index 6ffbeabd3..268c34392 100644 --- a/youtube_dl/extractor/camdemy.py +++ b/youtube_dl/extractor/camdemy.py @@ -1,7 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import datetime import re from .common import InfoExtractor @@ -10,8 +9,10 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( - parse_iso8601, + clean_html, + parse_duration, str_to_int, + unified_strdate, ) @@ -26,14 +27,14 @@ class CamdemyIE(InfoExtractor): 'ext': 'mp4', 'title': 'Ch1-1 Introduction, Signals (02-23-2012)', 'thumbnail': 're:^https?://.*\.jpg$', - 'description': '', 'creator': 'ss11spring', + 'duration': 1591, 'upload_date': '20130114', - 'timestamp': 1358154556, 'view_count': int, } }, { # With non-empty description + # webpage returns "No permission or not login" 'url': 'http://www.camdemy.com/media/13885', 'md5': '4576a3bb2581f86c61044822adbd1249', 'info_dict': { @@ -41,64 +42,71 @@ class CamdemyIE(InfoExtractor): 'ext': 'mp4', 'title': 'EverCam + Camdemy QuickStart', 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'md5:050b62f71ed62928f8a35f1a41e186c9', + 'description': 'md5:2a9f989c2b153a2342acee579c6e7db6', 'creator': 'evercam', - 'upload_date': '20140620', - 'timestamp': 1403271569, + 'duration': 318, } }, { - # External source + # External source (YouTube) 'url': 'http://www.camdemy.com/media/14842', - 'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7', 'info_dict': { 'id': '2vsYQzNIsJo', 'ext': 'mp4', + 'title': 'Excel 2013 Tutorial - How to add Password Protection', + 'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection', 'upload_date': '20130211', 'uploader': 'Hun Kim', - 'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection', 'uploader_id': 'hunkimtutorials', - 'title': 'Excel 2013 Tutorial - How to add Password Protection', - } + }, + 'params': { + 'skip_download': True, + }, }] def _real_extract(self, url): video_id = self._match_id(url) - page = self._download_webpage(url, video_id) + + webpage = self._download_webpage(url, video_id) src_from = self._html_search_regex( - r"<div class='srcFrom'>Source: <a title='([^']+)'", page, - 'external source', default=None) + r"class=['\"]srcFrom['\"][^>]*>Sources?(?:\s+from)?\s*:\s*<a[^>]+(?:href|title)=(['\"])(?P<url>(?:(?!\1).)+)\1", + webpage, 'external source', default=None, group='url') if src_from: return self.url_result(src_from) oembed_obj = self._download_json( 'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id) + title = oembed_obj['title'] thumb_url = oembed_obj['thumbnail_url'] video_folder = compat_urlparse.urljoin(thumb_url, 'video/') file_list_doc = self._download_xml( compat_urlparse.urljoin(video_folder, 'fileList.xml'), - video_id, 'Filelist XML') + video_id, 'Downloading filelist XML') file_name = file_list_doc.find('./video/item/fileName').text video_url = compat_urlparse.urljoin(video_folder, file_name) - timestamp = parse_iso8601(self._html_search_regex( - r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<", - page, 'creation time', fatal=False), - delimiter=' ', timezone=datetime.timedelta(hours=8)) - view_count = str_to_int(self._html_search_regex( - r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<", - page, 'view count', fatal=False)) + # Some URLs return "No permission or not login" in a webpage despite being + # freely available via oembed JSON URL (e.g. http://www.camdemy.com/media/13885) + upload_date = unified_strdate(self._search_regex( + r'>published on ([^<]+)<', webpage, + 'upload date', default=None)) + view_count = str_to_int(self._search_regex( + r'role=["\']viewCnt["\'][^>]*>([\d,.]+) views', + webpage, 'view count', default=None)) + description = self._html_search_meta( + 'description', webpage, default=None) or clean_html( + oembed_obj.get('description')) return { 'id': video_id, 'url': video_url, - 'title': oembed_obj['title'], + 'title': title, 'thumbnail': thumb_url, - 'description': self._html_search_meta('description', page), - 'creator': oembed_obj['author_name'], - 'duration': oembed_obj['duration'], - 'timestamp': timestamp, + 'description': description, + 'creator': oembed_obj.get('author_name'), + 'duration': parse_duration(oembed_obj.get('duration')), + 'upload_date': upload_date, 'view_count': view_count, } diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 25b2d4efe..61463f249 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -4,11 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_urlparse from ..utils import ( ExtractorError, HEADRequest, unified_strdate, - url_basename, qualities, int_or_none, ) @@ -16,24 +16,38 @@ from ..utils import ( class CanalplusIE(InfoExtractor): IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv' - _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))' + _VALID_URL = r'''(?x) + https?:// + (?: + (?: + (?:(?:www|m)\.)?canalplus\.fr| + (?:www\.)?piwiplus\.fr| + (?:www\.)?d8\.tv| + (?:www\.)?d17\.tv| + (?:www\.)?itele\.fr + )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?| + player\.canalplus\.fr/#/(?P<id>\d+) + ) + + ''' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json' _SITE_ID_MAP = { - 'canalplus.fr': 'cplus', - 'piwiplus.fr': 'teletoon', - 'd8.tv': 'd8', - 'itele.fr': 'itele', + 'canalplus': 'cplus', + 'piwiplus': 'teletoon', + 'd8': 'd8', + 'd17': 'd17', + 'itele': 'itele', } _TESTS = [{ - 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092', - 'md5': '12164a6f14ff6df8bd628e8ba9b10b78', + 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814', + 'md5': '41f438a4904f7664b91b4ed0dec969dc', 'info_dict': { - 'id': '1263092', + 'id': '1192814', 'ext': 'mp4', - 'title': 'Le Zapping - 13/05/15', - 'description': 'md5:09738c0d06be4b5d06a0940edb0da73f', - 'upload_date': '20150513', + 'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014", + 'description': "Toute l'année 2014 dans un Zapping exceptionnel !", + 'upload_date': '20150105', }, }, { 'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190', @@ -46,35 +60,45 @@ class CanalplusIE(InfoExtractor): }, 'skip': 'Only works from France', }, { - 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html', + 'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231', 'info_dict': { - 'id': '966289', - 'ext': 'flv', - 'title': 'Campagne intime - Documentaire exceptionnel', - 'description': 'md5:d2643b799fb190846ae09c61e59a859f', - 'upload_date': '20131108', - }, - 'skip': 'videos get deleted after a while', - }, { - 'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559', - 'md5': '38b8f7934def74f0d6f3ba6c036a5f82', - 'info_dict': { - 'id': '1213714', + 'id': '1390231', 'ext': 'mp4', - 'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45', - 'description': 'md5:8216206ec53426ea6321321f3b3c16db', - 'upload_date': '20150211', + 'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité", + 'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6', + 'upload_date': '20160512', }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224', + 'info_dict': { + 'id': '1398334', + 'ext': 'mp4', + 'title': "L'invité de Bruce Toussaint du 07/06/2016 - ", + 'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324', + 'upload_date': '20160607', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://m.canalplus.fr/?vid=1398231', + 'only_matching': True, + }, { + 'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.groupdict().get('id') + video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid') - site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal'] + site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]] # Beware, some subclasses do not define an id group - display_id = url_basename(mobj.group('path')) + display_id = mobj.group('display_id') or video_id if video_id is None: webpage = self._download_webpage(url, display_id) diff --git a/youtube_dl/extractor/carambatv.py b/youtube_dl/extractor/carambatv.py new file mode 100644 index 000000000..5797fb951 --- /dev/null +++ b/youtube_dl/extractor/carambatv.py @@ -0,0 +1,88 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + float_or_none, + int_or_none, + try_get, +) + + +class CarambaTVIE(InfoExtractor): + _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://video1.carambatv.ru/v/191910501', + 'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a', + 'info_dict': { + 'id': '191910501', + 'ext': 'mp4', + 'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 2678.31, + }, + }, { + 'url': 'carambatv:191910501', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + 'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id, + video_id) + + title = video['title'] + + base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id + + formats = [{ + 'url': base_url + f['fn'], + 'height': int_or_none(f.get('height')), + 'format_id': '%sp' % f['height'] if f.get('height') else None, + } for f in video['qualities'] if f.get('fn')] + self._sort_formats(formats) + + thumbnail = video.get('splash') + duration = float_or_none(try_get( + video, lambda x: x['annotations'][0]['end_time'], compat_str)) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + } + + +class CarambaTVPageIE(InfoExtractor): + _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/', + 'md5': '', + 'info_dict': { + 'id': '191910501', + 'ext': 'mp4', + 'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 2678.31, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_url = self._og_search_property('video:iframe', webpage, default=None) + + if not video_url: + video_id = self._search_regex( + r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)', + webpage, 'video id') + video_url = 'carambatv:%s' % video_id + + return self.url_result(video_url, CarambaTVIE.ie_key()) diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index 68a0633b6..a87e97140 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -4,65 +4,83 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import js_to_json +from ..compat import compat_str +from ..utils import ( + js_to_json, + smuggle_url, + try_get, +) class CBCIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:[^/]+/)+(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)' _TESTS = [{ # with mediaId 'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs', + 'md5': '97e24d09672fc4cf56256d6faa6c25bc', 'info_dict': { 'id': '2682904050', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Don Cherry – All-Stars', 'description': 'Don Cherry has a bee in his bonnet about AHL player John Scott because that guy’s got heart.', - 'timestamp': 1454475540, + 'timestamp': 1454463000, 'upload_date': '20160203', - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # with clipId - 'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live', - 'info_dict': { - 'id': '2487345465', - 'ext': 'flv', - 'title': 'Robin Williams freestyles on 90 Minutes Live', - 'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.', - 'upload_date': '19700101', 'uploader': 'CBCC-NEW', }, - 'params': { - # rtmp download - 'skip_download': True, + 'skip': 'Geo-restricted to Canada', + }, { + # with clipId, feed available via tpfeed.cbc.ca and feed.theplatform.com + 'url': 'http://www.cbc.ca/22minutes/videos/22-minutes-update/22-minutes-update-episode-4', + 'md5': '162adfa070274b144f4fdc3c3b8207db', + 'info_dict': { + 'id': '2414435309', + 'ext': 'mp4', + 'title': '22 Minutes Update: What Not To Wear Quebec', + 'description': "This week's latest Canadian top political story is What Not To Wear Quebec.", + 'upload_date': '20131025', + 'uploader': 'CBCC-NEW', + 'timestamp': 1382717907, + }, + }, { + # with clipId, feed only available via tpfeed.cbc.ca + 'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live', + 'md5': '0274a90b51a9b4971fe005c63f592f12', + 'info_dict': { + 'id': '2487345465', + 'ext': 'mp4', + 'title': 'Robin Williams freestyles on 90 Minutes Live', + 'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.', + 'upload_date': '19780210', + 'uploader': 'CBCC-NEW', + 'timestamp': 255977160, }, }, { # multiple iframes 'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot', 'playlist': [{ + 'md5': '377572d0b49c4ce0c9ad77470e0b96b4', 'info_dict': { 'id': '2680832926', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'An Eagle\'s-Eye View Off Burrard Bridge', 'description': 'Hercules the eagle flies from Vancouver\'s Burrard Bridge down to a nearby park with a mini-camera strapped to his back.', - 'upload_date': '19700101', + 'upload_date': '20160201', + 'timestamp': 1454342820, + 'uploader': 'CBCC-NEW', }, }, { + 'md5': '415a0e3f586113894174dfb31aa5bb1a', 'info_dict': { 'id': '2658915080', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Fly like an eagle!', 'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower', - 'upload_date': '19700101', + 'upload_date': '20150315', + 'timestamp': 1426443984, + 'uploader': 'CBCC-NEW', }, }], - 'params': { - # rtmp download - 'skip_download': True, - }, + 'skip': 'Geo-restricted to Canada', }] @classmethod @@ -80,9 +98,15 @@ class CBCIE(InfoExtractor): media_id = player_info.get('mediaId') if not media_id: clip_id = player_info['clipId'] - media_id = self._download_json( - 'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id, - clip_id)['entries'][0]['id'].split('/')[-1] + feed = self._download_json( + 'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id, + clip_id, fatal=False) + if feed: + media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str) + if not media_id: + media_id = self._download_json( + 'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id, + clip_id)['entries'][0]['id'].split('/')[-1] return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) else: entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)] @@ -91,24 +115,55 @@ class CBCIE(InfoExtractor): class CBCPlayerIE(InfoExtractor): _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.cbc.ca/player/play/2683190193', + 'md5': '64d25f841ddf4ddb28a235338af32e2c', 'info_dict': { 'id': '2683190193', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Gerry Runs a Sweat Shop', 'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0', - 'timestamp': 1455067800, + 'timestamp': 1455071400, 'upload_date': '20160210', + 'uploader': 'CBCC-NEW', }, - 'params': { - # rtmp download - 'skip_download': True, + 'skip': 'Geo-restricted to Canada', + }, { + # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/ + 'url': 'http://www.cbc.ca/player/play/2657631896', + 'md5': 'e5e708c34ae6fca156aafe17c43e8b75', + 'info_dict': { + 'id': '2657631896', + 'ext': 'mp3', + 'title': 'CBC Montreal is organizing its first ever community hackathon!', + 'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.', + 'timestamp': 1425704400, + 'upload_date': '20150307', + 'uploader': 'CBCC-NEW', }, - } + }, { + # available only when we add `formats=MPEG4,FLV,MP3` to theplatform url + 'url': 'http://www.cbc.ca/player/play/2164402062', + 'md5': '17a61eb813539abea40618d6323a7f82', + 'info_dict': { + 'id': '2164402062', + 'ext': 'flv', + 'title': 'Cancer survivor four times over', + 'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.', + 'timestamp': 1320410746, + 'upload_date': '20111104', + 'uploader': 'CBCC-NEW', + }, + }] def _real_extract(self, url): video_id = self._match_id(url) - return self.url_result( - 'http://feed.theplatform.com/f/ExhSPC/vms_5akSXx4Ng_Zn?byGuid=%s' % video_id, - 'ThePlatformFeed', video_id) + return { + '_type': 'url_transparent', + 'ie_key': 'ThePlatform', + 'url': smuggle_url( + 'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/%s?mbr=true&formats=MPEG4,FLV,MP3' % video_id, { + 'force_smil_url': True + }), + 'id': video_id, + } diff --git a/youtube_dl/extractor/cbs.py b/youtube_dl/extractor/cbs.py index 051d783a2..a23173d6f 100644 --- a/youtube_dl/extractor/cbs.py +++ b/youtube_dl/extractor/cbs.py @@ -1,15 +1,13 @@ from __future__ import unicode_literals -from .theplatform import ThePlatformIE +from .theplatform import ThePlatformFeedIE from ..utils import ( - xpath_text, - xpath_element, int_or_none, find_xpath_attr, ) -class CBSBaseIE(ThePlatformIE): +class CBSBaseIE(ThePlatformFeedIE): def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'): closed_caption_e = find_xpath_attr(smil, self._xpath_ns('.//param', namespace), 'name', 'ClosedCaptionURL') return { @@ -19,9 +17,22 @@ class CBSBaseIE(ThePlatformIE): }] } if closed_caption_e is not None and closed_caption_e.attrib.get('value') else [] + def _extract_video_info(self, filter_query, video_id): + return self._extract_feed_info( + 'dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id, lambda entry: { + 'series': entry.get('cbs$SeriesTitle'), + 'season_number': int_or_none(entry.get('cbs$SeasonNumber')), + 'episode': entry.get('cbs$EpisodeTitle'), + 'episode_number': int_or_none(entry.get('cbs$EpisodeNumber')), + }, { + 'StreamPack': { + 'manifest': 'm3u', + } + }) + class CBSIE(CBSBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/[^/]+/(?P<id>[^/]+)' + _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)' _TESTS = [{ 'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/', @@ -36,25 +47,7 @@ class CBSIE(CBSBaseIE): 'upload_date': '20131127', 'uploader': 'CBSI-NEW', }, - 'params': { - # rtmp download - 'skip_download': True, - }, - '_skip': 'Blocked outside the US', - }, { - 'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/', - 'info_dict': { - 'id': 'WWF_5KqY3PK1', - 'display_id': 'st-vincent', - 'ext': 'flv', - 'title': 'Live on Letterman - St. Vincent', - 'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.', - 'duration': 3221, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, + 'expected_warnings': ['Failed to download m3u8 information'], '_skip': 'Blocked outside the US', }, { 'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/', @@ -66,43 +59,5 @@ class CBSIE(CBSBaseIE): TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - content_id = self._search_regex( - [r"video\.settings\.content_id\s*=\s*'([^']+)';", r"cbsplayer\.contentId\s*=\s*'([^']+)';"], - webpage, 'content id') - items_data = self._download_xml( - 'http://can.cbs.com/thunder/player/videoPlayerService.php', - content_id, query={'partner': 'cbs', 'contentId': content_id}) - video_data = xpath_element(items_data, './/item') - title = xpath_text(video_data, 'videoTitle', 'title', True) - - subtitles = {} - formats = [] - for item in items_data.findall('.//item'): - pid = xpath_text(item, 'pid') - if not pid: - continue - tp_release_url = self.TP_RELEASE_URL_TEMPLATE % pid - if '.m3u8' in xpath_text(item, 'contentUrl', default=''): - tp_release_url += '&manifest=m3u' - tp_formats, tp_subtitles = self._extract_theplatform_smil( - tp_release_url, content_id, 'Downloading %s SMIL data' % pid) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - info = self.get_metadata('dJ5BDC/media/guid/2198311517/%s' % content_id, content_id) - info.update({ - 'id': content_id, - 'display_id': display_id, - 'title': title, - 'series': xpath_text(video_data, 'seriesTitle'), - 'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')), - 'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')), - 'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000), - 'thumbnail': xpath_text(video_data, 'previewImageURL'), - 'formats': formats, - 'subtitles': subtitles, - }) - return info + content_id = self._match_id(url) + return self._extract_video_info('byGuid=%s' % content_id, content_id) diff --git a/youtube_dl/extractor/cbsinteractive.py b/youtube_dl/extractor/cbsinteractive.py index 0011c3029..821db20b2 100644 --- a/youtube_dl/extractor/cbsinteractive.py +++ b/youtube_dl/extractor/cbsinteractive.py @@ -80,9 +80,6 @@ class CBSInteractiveIE(ThePlatformIE): media_guid_path = 'media/guid/%d/%s' % (self.MPX_ACCOUNTS[site], vdata['mpxRefId']) formats, subtitles = [], {} - if site == 'cnet': - formats, subtitles = self._extract_theplatform_smil( - self.TP_RELEASE_URL_TEMPLATE % media_guid_path, video_id) for (fkey, vid) in vdata['files'].items(): if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']: continue @@ -94,7 +91,7 @@ class CBSInteractiveIE(ThePlatformIE): subtitles = self._merge_subtitles(subtitles, tp_subtitles) self._sort_formats(formats) - info = self.get_metadata('kYEXFC/%s' % media_guid_path, video_id) + info = self._extract_theplatform_metadata('kYEXFC/%s' % media_guid_path, video_id) info.update({ 'id': video_id, 'display_id': display_id, diff --git a/youtube_dl/extractor/cbslocal.py b/youtube_dl/extractor/cbslocal.py new file mode 100644 index 000000000..74adb38a6 --- /dev/null +++ b/youtube_dl/extractor/cbslocal.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import calendar +import datetime + +from .anvato import AnvatoIE +from .sendtonews import SendtoNewsIE +from ..compat import compat_urlparse + + +class CBSLocalIE(AnvatoIE): + _VALID_URL = r'https?://[a-z]+\.cbslocal\.com/\d+/\d+/\d+/(?P<id>[0-9a-z-]+)' + + _TESTS = [{ + # Anvato backend + 'url': 'http://losangeles.cbslocal.com/2016/05/16/safety-advocates-say-fatal-car-seat-failures-are-public-health-crisis', + 'md5': 'f0ee3081e3843f575fccef901199b212', + 'info_dict': { + 'id': '3401037', + 'ext': 'mp4', + 'title': 'Safety Advocates Say Fatal Car Seat Failures Are \'Public Health Crisis\'', + 'description': 'Collapsing seats have been the focus of scrutiny for decades, though experts say remarkably little has been done to address the issue. Randy Paige reports.', + 'thumbnail': 're:^https?://.*', + 'timestamp': 1463440500, + 'upload_date': '20160516', + 'subtitles': { + 'en': 'mincount:5', + }, + 'categories': [ + 'Stations\\Spoken Word\\KCBSTV', + 'Syndication\\MSN', + 'Syndication\\NDN', + 'Syndication\\AOL', + 'Syndication\\Yahoo', + 'Syndication\\Tribune', + 'Syndication\\Curb.tv', + 'Content\\News' + ], + }, + }, { + # SendtoNews embed + 'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/', + 'info_dict': { + 'id': 'GxfCe0Zo7D-175909-5588', + 'ext': 'mp4', + 'title': 'Recap: CLE 15, CIN 6', + 'description': '5/16/16: Indians\' bats explode for 15 runs in a win', + 'upload_date': '20160516', + 'timestamp': 1463433840, + 'duration': 49, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + sendtonews_url = SendtoNewsIE._extract_url(webpage) + if sendtonews_url: + info_dict = { + '_type': 'url_transparent', + 'url': compat_urlparse.urljoin(url, sendtonews_url), + } + else: + info_dict = self._extract_anvato_videos(webpage, display_id) + + time_str = self._html_search_regex( + r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False) + timestamp = None + if time_str: + timestamp = calendar.timegm(datetime.datetime.strptime( + time_str, '%b %d, %Y %I:%M %p').timetuple()) + + info_dict.update({ + 'display_id': display_id, + 'timestamp': timestamp, + }) + + return info_dict diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 79ddc20a0..9328e3e20 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -26,13 +26,17 @@ class CBSNewsIE(CBSBaseIE): # rtmp download 'skip_download': True, }, + 'skip': 'Subscribers only', }, { 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/', 'info_dict': { - 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack', + 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y', 'ext': 'mp4', 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack', + 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7', + 'upload_date': '19700101', + 'uploader': 'CBSI-NEW', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 205, 'subtitles': { @@ -58,37 +62,15 @@ class CBSNewsIE(CBSBaseIE): webpage, 'video JSON info'), video_id) item = video_info['item'] if 'item' in video_info else video_info - title = item.get('articleTitle') or item.get('hed') - duration = item.get('duration') - thumbnail = item.get('mediaImage') or item.get('thumbnail') - - subtitles = {} - formats = [] - for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']: - pid = item.get('media' + format_id) - if not pid: - continue - release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid - tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid) - formats.extend(tp_formats) - subtitles = self._merge_subtitles(subtitles, tp_subtitles) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } + guid = item['mpxRefId'] + return self._extract_video_info('byGuid=%s' % guid, guid) class CBSNewsLiveVideoIE(InfoExtractor): IE_DESC = 'CBS News Live Videos' _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/', 'info_dict': { 'id': 'clinton-sanders-prepare-to-face-off-in-nh', @@ -96,7 +78,15 @@ class CBSNewsLiveVideoIE(InfoExtractor): 'title': 'Clinton, Sanders Prepare To Face Off In NH', 'duration': 334, }, - } + 'skip': 'Video gone, redirected to http://www.cbsnews.com/live/', + }, { + 'url': 'http://www.cbsnews.com/live/video/video-shows-intense-paragliding-accident/', + 'info_dict': { + 'id': 'video-shows-intense-paragliding-accident', + 'ext': 'flv', + 'title': 'Video Shows Intense Paragliding Accident', + }, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/cbssports.py b/youtube_dl/extractor/cbssports.py index 549ae32f3..78ca44b02 100644 --- a/youtube_dl/extractor/cbssports.py +++ b/youtube_dl/extractor/cbssports.py @@ -1,30 +1,28 @@ from __future__ import unicode_literals -import re - -from .common import InfoExtractor +from .cbs import CBSBaseIE -class CBSSportsIE(InfoExtractor): - _VALID_URL = r'https?://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)' +class CBSSportsIE(CBSBaseIE): + _VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)' - _TEST = { - 'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s', + _TESTS = [{ + 'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast', 'info_dict': { - 'id': '_d5_GbO8p1sT', - 'ext': 'flv', - 'title': 'US Open flashbacks: 1990s', - 'description': 'Bill Macatee relives the best moments in US Open history from the 1990s.', + 'id': '708337219968', + 'ext': 'mp4', + 'title': 'Ben Simmons the next LeBron? Not so fast', + 'description': 'md5:854294f627921baba1f4b9a990d87197', + 'timestamp': 1466293740, + 'upload_date': '20160618', + 'uploader': 'CBSI-NEW', }, - } + 'params': { + # m3u8 download + 'skip_download': True, + } + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - section = mobj.group('section') - video_id = mobj.group('id') - all_videos = self._download_json( - 'http://www.cbssports.com/data/video/player/getVideos/%s?as=json' % section, - video_id) - # The json file contains the info of all the videos in the section - video_info = next(v for v in all_videos if v['pcid'] == video_id) - return self.url_result('theplatform:%s' % video_info['pid'], 'ThePlatform') + video_id = self._match_id(url) + return self._extract_video_info('byId=%s' % video_id, video_id) diff --git a/youtube_dl/extractor/cda.py b/youtube_dl/extractor/cda.py index 498d2c0d8..8af318703 100755 --- a/youtube_dl/extractor/cda.py +++ b/youtube_dl/extractor/cda.py @@ -58,7 +58,8 @@ class CDAIE(InfoExtractor): def extract_format(page, version): unpacked = decode_packed_codes(page) format_url = self._search_regex( - r"url:\\'(.+?)\\'", unpacked, '%s url' % version, fatal=False) + r"(?:file|url)\s*:\s*(\\?[\"'])(?P<url>http.+?)\1", unpacked, + '%s url' % version, fatal=False, group='url') if not format_url: return f = { @@ -75,7 +76,8 @@ class CDAIE(InfoExtractor): info_dict['formats'].append(f) if not info_dict['duration']: info_dict['duration'] = parse_duration(self._search_regex( - r"duration:\\'(.+?)\\'", unpacked, 'duration', fatal=False)) + r"duration\s*:\s*(\\?[\"'])(?P<duration>.+?)\1", + unpacked, 'duration', fatal=False, group='duration')) extract_format(webpage, 'default') diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index c74553dcf..34d4e6156 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -20,54 +20,64 @@ class Channel9IE(InfoExtractor): ''' IE_DESC = 'Channel 9' IE_NAME = 'channel9' - _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?' + _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)' - _TESTS = [ - { - 'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002', - 'md5': 'bbd75296ba47916b754e73c3a4bbdf10', - 'info_dict': { - 'id': 'Events/TechEd/Australia/2013/KOS002', - 'ext': 'mp4', - 'title': 'Developer Kick-Off Session: Stuff We Love', - 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f', - 'duration': 4576, - 'thumbnail': 're:http://.*\.jpg', - 'session_code': 'KOS002', - 'session_day': 'Day 1', - 'session_room': 'Arena 1A', - 'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', 'Mads Kristensen'], - }, + _TESTS = [{ + 'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002', + 'md5': 'bbd75296ba47916b754e73c3a4bbdf10', + 'info_dict': { + 'id': 'Events/TechEd/Australia/2013/KOS002', + 'ext': 'mp4', + 'title': 'Developer Kick-Off Session: Stuff We Love', + 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f', + 'duration': 4576, + 'thumbnail': 're:http://.*\.jpg', + 'session_code': 'KOS002', + 'session_day': 'Day 1', + 'session_room': 'Arena 1A', + 'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug', + 'Mads Kristensen'], }, - { - 'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', - 'md5': 'b43ee4529d111bc37ba7ee4f34813e68', - 'info_dict': { - 'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing', - 'ext': 'mp4', - 'title': 'Self-service BI with Power BI - nuclear testing', - 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', - 'duration': 1540, - 'thumbnail': 're:http://.*\.jpg', - 'authors': ['Mike Wilmot'], - }, + }, { + 'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', + 'md5': 'b43ee4529d111bc37ba7ee4f34813e68', + 'info_dict': { + 'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing', + 'ext': 'mp4', + 'title': 'Self-service BI with Power BI - nuclear testing', + 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b', + 'duration': 1540, + 'thumbnail': 're:http://.*\.jpg', + 'authors': ['Mike Wilmot'], }, - { - # low quality mp4 is best - 'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', - 'info_dict': { - 'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', - 'ext': 'mp4', - 'title': 'Ranges for the Standard Library', - 'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d', - 'duration': 5646, - 'thumbnail': 're:http://.*\.jpg', - }, - 'params': { - 'skip_download': True, - }, - } - ] + }, { + # low quality mp4 is best + 'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', + 'info_dict': { + 'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library', + 'ext': 'mp4', + 'title': 'Ranges for the Standard Library', + 'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d', + 'duration': 5646, + 'thumbnail': 're:http://.*\.jpg', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS', + 'info_dict': { + 'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b', + 'title': 'Channel 9', + }, + 'playlist_count': 2, + }, { + 'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS', + 'only_matching': True, + }, { + 'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman', + 'only_matching': True, + }] _RSS_URL = 'http://channel9.msdn.com/%s/RSS' @@ -254,22 +264,30 @@ class Channel9IE(InfoExtractor): return self.playlist_result(contents) - def _extract_list(self, content_path): - rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS') + def _extract_list(self, video_id, rss_url=None): + if not rss_url: + rss_url = self._RSS_URL % video_id + rss = self._download_xml(rss_url, video_id, 'Downloading RSS') entries = [self.url_result(session_url.text, 'Channel9') for session_url in rss.findall('./channel/item/link')] title_text = rss.find('./channel/title').text - return self.playlist_result(entries, content_path, title_text) + return self.playlist_result(entries, video_id, title_text) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) content_path = mobj.group('contentpath') + rss = mobj.group('rss') - webpage = self._download_webpage(url, content_path, 'Downloading web page') + if rss: + return self._extract_list(content_path, url) - page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage) - if page_type_m is not None: - page_type = page_type_m.group('pagetype') + webpage = self._download_webpage( + url, content_path, 'Downloading web page') + + page_type = self._search_regex( + r'<meta[^>]+name=(["\'])WT\.entryid\1[^>]+content=(["\'])(?P<pagetype>[^:]+).+?\2', + webpage, 'page type', default=None, group='pagetype') + if page_type: if page_type == 'Entry': # Any 'item'-like page, may contain downloadable content return self._extract_entry_item(webpage, content_path) elif page_type == 'Session': # Event session page, may contain downloadable content @@ -278,6 +296,5 @@ class Channel9IE(InfoExtractor): return self._extract_list(content_path) else: raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True) - else: # Assuming list return self._extract_list(content_path) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py deleted file mode 100644 index 042c4f2f1..000000000 --- a/youtube_dl/extractor/cinemassacre.py +++ /dev/null @@ -1,119 +0,0 @@ -# encoding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ExtractorError -from .screenwavemedia import ScreenwaveMediaIE - - -class CinemassacreIE(InfoExtractor): - _VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)' - _TESTS = [ - { - 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/', - 'md5': 'fde81fbafaee331785f58cd6c0d46190', - 'info_dict': { - 'id': 'Cinemassacre-19911', - 'ext': 'mp4', - 'upload_date': '20121110', - 'title': '“Angry Video Game Nerd: The Movie” – Trailer', - 'description': 'md5:fb87405fcb42a331742a0dce2708560b', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940', - 'md5': 'd72f10cd39eac4215048f62ab477a511', - 'info_dict': { - 'id': 'Cinemassacre-521be8ef82b16', - 'ext': 'mp4', - 'upload_date': '20131002', - 'title': 'The Mummy’s Hand (1940)', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, - { - # Youtube embedded video - 'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/', - 'md5': 'ec9838a5520ef5409b3e4e42fcb0a3b9', - 'info_dict': { - 'id': 'OEVzPCY2T-g', - 'ext': 'webm', - 'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles', - 'upload_date': '20061207', - 'uploader': 'Cinemassacre', - 'uploader_id': 'JamesNintendoNerd', - 'description': 'md5:784734696c2b8b7f4b8625cc799e07f6', - } - }, - { - # Youtube embedded video - 'url': 'http://cinemassacre.com/2006/09/01/mckids/', - 'md5': '7393c4e0f54602ad110c793eb7a6513a', - 'info_dict': { - 'id': 'FnxsNhuikpo', - 'ext': 'webm', - 'upload_date': '20060901', - 'uploader': 'Cinemassacre Extra', - 'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53', - 'uploader_id': 'Cinemassacre', - 'title': 'AVGN: McKids', - } - }, - { - 'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/', - 'md5': '1376908e49572389e7b06251a53cdd08', - 'info_dict': { - 'id': 'Cinemassacre-555779690c440', - 'ext': 'mp4', - 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!', - 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays', - 'upload_date': '20150525', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d') - - webpage = self._download_webpage(url, display_id) - - playerdata_url = self._search_regex( - [ - ScreenwaveMediaIE.EMBED_PATTERN, - r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', - ], - webpage, 'player data URL', default=None, group='url') - if not playerdata_url: - raise ExtractorError('Unable to find player data') - - video_title = self._html_search_regex( - r'<title>(?P<title>.+?)\|', webpage, 'title') - video_description = self._html_search_regex( - r'<div class="entry-content">(?P<description>.+?)</div>', - webpage, 'description', flags=re.DOTALL, fatal=False) - video_thumbnail = self._og_search_thumbnail(webpage) - - return { - '_type': 'url_transparent', - 'display_id': display_id, - 'title': video_title, - 'description': video_description, - 'upload_date': video_date, - 'thumbnail': video_thumbnail, - 'url': playerdata_url, - } diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 19f8b397e..252c2e846 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -23,7 +23,7 @@ class CliphunterIE(InfoExtractor): (?P<id>[0-9]+)/ (?P<seo>.+?)(?:$|[#\?]) ''' - _TEST = { + _TESTS = [{ 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', 'md5': 'b7c9bbd4eb3a226ab91093714dcaa480', 'info_dict': { @@ -32,8 +32,19 @@ class CliphunterIE(InfoExtractor): 'title': 'Fun Jynx Maze solo', 'thumbnail': 're:^https?://.*\.jpg$', 'age_limit': 18, - } - } + }, + 'skip': 'Video gone', + }, { + 'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz', + 'md5': '55a723c67bfc6da6b0cfa00d55da8a27', + 'info_dict': { + 'id': '2019449', + 'ext': 'mp4', + 'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz', + 'thumbnail': 're:^https?://.*\.jpg$', + 'age_limit': 18, + }, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/cliprs.py b/youtube_dl/extractor/cliprs.py index 4f9320ea5..d55b26d59 100644 --- a/youtube_dl/extractor/cliprs.py +++ b/youtube_dl/extractor/cliprs.py @@ -1,16 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - float_or_none, - int_or_none, - parse_iso8601, -) +from .onet import OnetBaseIE -class ClipRsIE(InfoExtractor): +class ClipRsIE(OnetBaseIE): _VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+' _TEST = { 'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732', @@ -27,64 +21,13 @@ class ClipRsIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + display_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id') + mvp_id = self._search_mvp_id(webpage) - response = self._download_json( - 'http://qi.ckm.onetapi.pl/', video_id, - query={ - 'body[id]': video_id, - 'body[jsonrpc]': '2.0', - 'body[method]': 'get_asset_detail', - 'body[params][ID_Publikacji]': video_id, - 'body[params][Service]': 'www.onet.pl', - 'content-type': 'application/jsonp', - 'x-onet-app': 'player.front.onetapi.pl', - }) + info_dict = self._extract_from_id(mvp_id, webpage) + info_dict['display_id'] = display_id - error = response.get('error') - if error: - raise ExtractorError( - '%s said: %s' % (self.IE_NAME, error['message']), expected=True) - - video = response['result'].get('0') - - formats = [] - for _, formats_dict in video['formats'].items(): - if not isinstance(formats_dict, dict): - continue - for format_id, format_list in formats_dict.items(): - if not isinstance(format_list, list): - continue - for f in format_list: - if not f.get('url'): - continue - formats.append({ - 'url': f['url'], - 'format_id': format_id, - 'height': int_or_none(f.get('vertical_resolution')), - 'width': int_or_none(f.get('horizontal_resolution')), - 'abr': float_or_none(f.get('audio_bitrate')), - 'vbr': float_or_none(f.get('video_bitrate')), - }) - self._sort_formats(formats) - - meta = video.get('meta', {}) - - title = self._og_search_title(webpage, default=None) or meta['title'] - description = self._og_search_description(webpage, default=None) or meta.get('description') - duration = meta.get('length') or meta.get('lenght') - timestamp = parse_iso8601(meta.get('addDate'), ' ') - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - } + return info_dict diff --git a/youtube_dl/extractor/closertotruth.py b/youtube_dl/extractor/closertotruth.py new file mode 100644 index 000000000..26243d52d --- /dev/null +++ b/youtube_dl/extractor/closertotruth.py @@ -0,0 +1,92 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class CloserToTruthIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688', + 'info_dict': { + 'id': '0_zof1ktre', + 'display_id': 'solutions-the-mind-body-problem', + 'ext': 'mov', + 'title': 'Solutions to the Mind-Body Problem?', + 'upload_date': '20140221', + 'timestamp': 1392956007, + 'uploader_id': 'CTTXML' + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://closertotruth.com/episodes/how-do-brains-work', + 'info_dict': { + 'id': '0_iuxai6g6', + 'display_id': 'how-do-brains-work', + 'ext': 'mov', + 'title': 'How do Brains Work?', + 'upload_date': '20140221', + 'timestamp': 1392956024, + 'uploader_id': 'CTTXML' + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://closertotruth.com/interviews/1725', + 'info_dict': { + 'id': '1725', + 'title': 'AyaFr-002', + }, + 'playlist_mincount': 2, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + partner_id = self._search_regex( + r'<script[^>]+src=["\'].*?\b(?:partner_id|p)/(\d+)', + webpage, 'kaltura partner_id') + + title = self._search_regex( + r'<title>(.+?)\s*\|\s*.+?', webpage, 'video title') + + select = self._search_regex( + r'(?s)]+id="select-version"[^>]*>(.+?)', + webpage, 'select version', default=None) + if select: + entry_ids = set() + entries = [] + for mobj in re.finditer( + r']+value=(["\'])(?P[0-9a-z_]+)(?:#.+?)?\1[^>]*>(?P[^<]+)', + webpage): + entry_id = mobj.group('id') + if entry_id in entry_ids: + continue + entry_ids.add(entry_id) + entries.append({ + '_type': 'url_transparent', + 'url': 'kaltura:%s:%s' % (partner_id, entry_id), + 'ie_key': 'Kaltura', + 'title': mobj.group('title'), + }) + if entries: + return self.playlist_result(entries, display_id, title) + + entry_id = self._search_regex( + r'<a[^>]+id=(["\'])embed-kaltura\1[^>]+data-kaltura=(["\'])(?P<id>[0-9a-z_]+)\2', + webpage, 'kaltura entry_id', group='id') + + return { + '_type': 'url_transparent', + 'display_id': display_id, + 'url': 'kaltura:%s:%s' % (partner_id, entry_id), + 'ie_key': 'Kaltura', + 'title': title + } diff --git a/youtube_dl/extractor/cloudy.py b/youtube_dl/extractor/cloudy.py index 9a28ef354..ae5ba0015 100644 --- a/youtube_dl/extractor/cloudy.py +++ b/youtube_dl/extractor/cloudy.py @@ -6,7 +6,6 @@ import re from .common import InfoExtractor from ..compat import ( compat_parse_qs, - compat_urllib_parse_urlencode, compat_HTTPError, ) from ..utils import ( @@ -17,37 +16,26 @@ from ..utils import ( class CloudyIE(InfoExtractor): - _IE_DESC = 'cloudy.ec and videoraj.ch' + _IE_DESC = 'cloudy.ec' _VALID_URL = r'''(?x) - https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.(?:ch|to))/ + https?://(?:www\.)?cloudy\.ec/ (?:v/|embed\.php\?id=) (?P<id>[A-Za-z0-9]+) ''' - _EMBED_URL = 'http://www.%s/embed.php?id=%s' - _API_URL = 'http://www.%s/api/player.api.php?%s' + _EMBED_URL = 'http://www.cloudy.ec/embed.php?id=%s' + _API_URL = 'http://www.cloudy.ec/api/player.api.php' _MAX_TRIES = 2 - _TESTS = [ - { - 'url': 'https://www.cloudy.ec/v/af511e2527aac', - 'md5': '5cb253ace826a42f35b4740539bedf07', - 'info_dict': { - 'id': 'af511e2527aac', - 'ext': 'flv', - 'title': 'Funny Cats and Animals Compilation june 2013', - } - }, - { - 'url': 'http://www.videoraj.to/v/47f399fd8bb60', - 'md5': '7d0f8799d91efd4eda26587421c3c3b0', - 'info_dict': { - 'id': '47f399fd8bb60', - 'ext': 'flv', - 'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?', - } + _TEST = { + 'url': 'https://www.cloudy.ec/v/af511e2527aac', + 'md5': '5cb253ace826a42f35b4740539bedf07', + 'info_dict': { + 'id': 'af511e2527aac', + 'ext': 'flv', + 'title': 'Funny Cats and Animals Compilation june 2013', } - ] + } - def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0): + def _extract_video(self, video_id, file_key, error_url=None, try_num=0): if try_num > self._MAX_TRIES - 1: raise ExtractorError('Unable to extract video URL', expected=True) @@ -64,9 +52,8 @@ class CloudyIE(InfoExtractor): 'errorUrl': error_url, }) - data_url = self._API_URL % (video_host, compat_urllib_parse_urlencode(form)) player_data = self._download_webpage( - data_url, video_id, 'Downloading player data') + self._API_URL, video_id, 'Downloading player data', query=form) data = compat_parse_qs(player_data) try_num += 1 @@ -88,7 +75,7 @@ class CloudyIE(InfoExtractor): except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]: self.report_warning('Invalid video URL, requesting another', video_id) - return self._extract_video(video_host, video_id, file_key, video_url, try_num) + return self._extract_video(video_id, file_key, video_url, try_num) return { 'id': video_id, @@ -98,14 +85,13 @@ class CloudyIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_host = mobj.group('host') video_id = mobj.group('id') - url = self._EMBED_URL % (video_host, video_id) + url = self._EMBED_URL % video_id webpage = self._download_webpage(url, video_id) file_key = self._search_regex( [r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'], webpage, 'file_key') - return self._extract_video(video_host, video_id, file_key) + return self._extract_video(video_id, file_key) diff --git a/youtube_dl/extractor/cmt.py b/youtube_dl/extractor/cmt.py index f1311b14f..f24568dcc 100644 --- a/youtube_dl/extractor/cmt.py +++ b/youtube_dl/extractor/cmt.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals + from .mtv import MTVIE +from ..utils import ExtractorError class CMTIE(MTVIE): @@ -16,7 +18,27 @@ class CMTIE(MTVIE): 'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"', 'description': 'Blame It All On My Roots', }, + 'skip': 'Video not available', + }, { + 'url': 'http://www.cmt.com/videos/misc/1504699/still-the-king-ep-109-in-3-minutes.jhtml#id=1739908', + 'md5': 'e61a801ca4a183a466c08bd98dccbb1c', + 'info_dict': { + 'id': '1504699', + 'ext': 'mp4', + 'title': 'Still The King Ep. 109 in 3 Minutes', + 'description': 'Relive or catch up with Still The King by watching this recap of season 1, episode 9. New episodes Sundays 9/8c.', + 'timestamp': 1469421000.0, + 'upload_date': '20160725', + }, }, { 'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172', 'only_matching': True, }] + + @classmethod + def _transform_rtmp_url(cls, rtmp_video_url): + if 'error_not_available.swf' in rtmp_video_url: + raise ExtractorError( + '%s said: video is not available' % cls.IE_NAME, expected=True) + + return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url) diff --git a/youtube_dl/extractor/collegehumor.py b/youtube_dl/extractor/collegehumor.py deleted file mode 100644 index 002b24037..000000000 --- a/youtube_dl/extractor/collegehumor.py +++ /dev/null @@ -1,101 +0,0 @@ -from __future__ import unicode_literals - -import json -import re - -from .common import InfoExtractor -from ..utils import int_or_none - - -class CollegeHumorIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$' - - _TESTS = [ - { - 'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', - 'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd', - 'info_dict': { - 'id': '6902724', - 'ext': 'mp4', - 'title': 'Comic-Con Cosplay Catastrophe', - 'description': "Fans get creative this year at San Diego. Too creative. And yes, that's really Joss Whedon.", - 'age_limit': 13, - 'duration': 187, - }, - }, { - 'url': 'http://www.collegehumor.com/video/3505939/font-conference', - 'md5': '72fa701d8ef38664a4dbb9e2ab721816', - 'info_dict': { - 'id': '3505939', - 'ext': 'mp4', - 'title': 'Font Conference', - 'description': "This video wasn't long enough, so we made it double-spaced.", - 'age_limit': 10, - 'duration': 179, - }, - }, { - # embedded youtube video - 'url': 'http://www.collegehumor.com/embed/6950306', - 'info_dict': { - 'id': 'Z-bao9fg6Yc', - 'ext': 'mp4', - 'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!', - 'uploader': 'Mark Dice', - 'uploader_id': 'MarkDice', - 'description': 'md5:62c3dab9351fac7bb44b53b69511d87f', - 'upload_date': '20140127', - }, - 'params': { - 'skip_download': True, - }, - 'add_ie': ['Youtube'], - }, - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - - jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json' - data = json.loads(self._download_webpage( - jsonUrl, video_id, 'Downloading info JSON')) - vdata = data['video'] - if vdata.get('youtubeId') is not None: - return { - '_type': 'url', - 'url': vdata['youtubeId'], - 'ie_key': 'Youtube', - } - - AGE_LIMITS = {'nc17': 18, 'r': 18, 'pg13': 13, 'pg': 10, 'g': 0} - rating = vdata.get('rating') - if rating: - age_limit = AGE_LIMITS.get(rating.lower()) - else: - age_limit = None # None = No idea - - PREFS = {'high_quality': 2, 'low_quality': 0} - formats = [] - for format_key in ('mp4', 'webm'): - for qname, qurl in vdata.get(format_key, {}).items(): - formats.append({ - 'format_id': format_key + '_' + qname, - 'url': qurl, - 'format': format_key, - 'preference': PREFS.get(qname), - }) - self._sort_formats(formats) - - duration = int_or_none(vdata.get('duration'), 1000) - like_count = int_or_none(vdata.get('likes')) - - return { - 'id': video_id, - 'title': vdata['title'], - 'description': vdata.get('description'), - 'thumbnail': vdata.get('thumbnail'), - 'formats': formats, - 'age_limit': age_limit, - 'duration': duration, - 'like_count': like_count, - } diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index 0c59102e0..c76909e48 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -1,17 +1,6 @@ from __future__ import unicode_literals -import re - from .mtv import MTVServicesInfoExtractor -from ..compat import ( - compat_str, - compat_urllib_parse_urlencode, -) -from ..utils import ( - ExtractorError, - float_or_none, - unified_strdate, -) class ComedyCentralIE(MTVServicesInfoExtractor): @@ -26,8 +15,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor): 'info_dict': { 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', 'ext': 'mp4', - 'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother', + 'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother', 'description': 'After a certain point, breastfeeding becomes c**kblocking.', + 'timestamp': 1376798400, + 'upload_date': '20130818', }, }, { 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', @@ -35,238 +26,73 @@ class ComedyCentralIE(MTVServicesInfoExtractor): }] -class ComedyCentralShowsIE(MTVServicesInfoExtractor): - IE_DESC = 'The Daily Show / The Colbert Report' - # urls can be abbreviations like :thedailyshow - # urls for episodes like: - # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day - # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news - # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 - _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow) - |https?://(:www\.)? - (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/ - ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)| - (?P<clip> - (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+)) - |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?)) - |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)) - )| - (?P<interview> - extended-interviews/(?P<interID>[0-9a-z]+)/ - (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?) - (?:/[^/?#]?|[?#]|$)))) - ''' +class ToshIE(MTVServicesInfoExtractor): + IE_DESC = 'Tosh.0' + _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)' + _FEED_URL = 'http://tosh.cc.com/feeds/mrss' + _TESTS = [{ - 'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart', - 'md5': '4e2f5cb088a83cd8cdb7756132f9739d', + 'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans', 'info_dict': { - 'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55', - 'ext': 'mp4', - 'upload_date': '20121213', - 'description': 'Kristen Stewart learns to let loose in "On the Road."', - 'uploader': 'thedailyshow', - 'title': 'thedailyshow kristen-stewart part 1', - } - }, { - 'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview', - 'info_dict': { - 'id': 'sarah-chayes-extended-interview', - 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."', - 'title': 'thedailyshow Sarah Chayes Extended Interview', + 'description': 'Tosh asked fans to share their summer plans.', + 'title': 'Twitter Users Share Summer Plans', }, - 'playlist': [ - { - 'info_dict': { - 'id': '0baad492-cbec-4ec1-9e50-ad91c291127f', - 'ext': 'mp4', - 'upload_date': '20150129', - 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."', - 'uploader': 'thedailyshow', - 'title': 'thedailyshow sarah-chayes-extended-interview part 1', + 'playlist': [{ + 'md5': 'f269e88114c1805bb6d7653fecea9e06', + 'info_dict': { + 'id': '90498ec2-ed00-11e0-aca6-0026b9414f30', + 'ext': 'mp4', + 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans', + 'description': 'Tosh asked fans to share their summer plans.', + 'thumbnail': 're:^https?://.*\.jpg', + # It's really reported to be published on year 2077 + 'upload_date': '20770610', + 'timestamp': 3390510600, + 'subtitles': { + 'en': 'mincount:3', }, }, - { - 'info_dict': { - 'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283', - 'ext': 'mp4', - 'upload_date': '20150129', - 'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."', - 'uploader': 'thedailyshow', - 'title': 'thedailyshow sarah-chayes-extended-interview part 2', - }, - }, - ], - 'params': { - 'skip_download': True, - }, + }] }, { - 'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview', - 'only_matching': True, - }, { - 'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news', - 'only_matching': True, - }, { - 'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114', - 'only_matching': True, - }, { - 'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3', - 'only_matching': True, - }, { - 'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary', - 'only_matching': True, - }, { - 'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall', - 'only_matching': True, - }, { - 'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights', - 'only_matching': True, - }, { - 'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo', - 'only_matching': True, - }, { - 'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food', - 'only_matching': True, - }, { - 'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel', + 'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp', 'only_matching': True, }] - _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] + @classmethod + def _transform_rtmp_url(cls, rtmp_video_url): + new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url) + new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm') + return new_urls - _video_extensions = { - '3500': 'mp4', - '2200': 'mp4', - '1700': 'mp4', - '1200': 'mp4', - '750': 'mp4', - '400': 'mp4', - } - _video_dimensions = { - '3500': (1280, 720), - '2200': (960, 540), - '1700': (768, 432), - '1200': (640, 360), - '750': (512, 288), - '400': (384, 216), - } + +class ComedyCentralTVIE(MTVServicesInfoExtractor): + _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4', + 'info_dict': { + 'id': 'local_playlist-f99b626bdfe13568579a', + 'ext': 'flv', + 'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + 'url': 'http://www.comedycentral.tv/shows/1074-workaholics', + 'only_matching': True, + }, { + 'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + video_id = self._match_id(url) - if mobj.group('shortname'): - return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes') + webpage = self._download_webpage(url, video_id) - if mobj.group('clip'): - if mobj.group('videotitle'): - epTitle = mobj.group('videotitle') - elif mobj.group('showname') == 'thedailyshow': - epTitle = mobj.group('tdstitle') - else: - epTitle = mobj.group('cntitle') - dlNewest = False - elif mobj.group('interview'): - epTitle = mobj.group('interview_title') - dlNewest = False - else: - dlNewest = not mobj.group('episode') - if dlNewest: - epTitle = mobj.group('showname') - else: - epTitle = mobj.group('episode') - show_name = mobj.group('showname') + mrss_url = self._search_regex( + r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage, 'mrss url', group='url') - webpage, htmlHandle = self._download_webpage_handle(url, epTitle) - if dlNewest: - url = htmlHandle.geturl() - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - raise ExtractorError('Invalid redirected URL: ' + url) - if mobj.group('episode') == '': - raise ExtractorError('Redirected URL is still not specific: ' + url) - epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1] - - mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage) - if len(mMovieParams) == 0: - # The Colbert Report embeds the information in a without - # a URL prefix; so extract the alternate reference - # and then add the URL prefix manually. - - altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage) - if len(altMovieParams) == 0: - raise ExtractorError('unable to find Flash URL in webpage ' + url) - else: - mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])] - - uri = mMovieParams[0][1] - # Correct cc.com in uri - uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri) - - index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse_urlencode({'uri': uri})) - idoc = self._download_xml( - index_url, epTitle, - 'Downloading show index', 'Unable to download episode index') - - title = idoc.find('./channel/title').text - description = idoc.find('./channel/description').text - - entries = [] - item_els = idoc.findall('.//item') - for part_num, itemEl in enumerate(item_els): - upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text) - thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url') - - content = itemEl.find('.//{http://search.yahoo.com/mrss/}content') - duration = float_or_none(content.attrib.get('duration')) - mediagen_url = content.attrib['url'] - guid = itemEl.find('./guid').text.rpartition(':')[-1] - - cdoc = self._download_xml( - mediagen_url, epTitle, - 'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els))) - - turls = [] - for rendition in cdoc.findall('.//rendition'): - finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text) - turls.append(finfo) - - formats = [] - for format, rtmp_video_url in turls: - w, h = self._video_dimensions.get(format, (None, None)) - formats.append({ - 'format_id': 'vhttp-%s' % format, - 'url': self._transform_rtmp_url(rtmp_video_url), - 'ext': self._video_extensions.get(format, 'mp4'), - 'height': h, - 'width': w, - }) - formats.append({ - 'format_id': 'rtmp-%s' % format, - 'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'), - 'ext': self._video_extensions.get(format, 'mp4'), - 'height': h, - 'width': w, - }) - self._sort_formats(formats) - - subtitles = self._extract_subtitles(cdoc, guid) - - virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1) - entries.append({ - 'id': guid, - 'title': virtual_id, - 'formats': formats, - 'uploader': show_name, - 'upload_date': upload_date, - 'duration': duration, - 'thumbnail': thumbnail, - 'description': description, - 'subtitles': subtitles, - }) - - return { - '_type': 'playlist', - 'id': epTitle, - 'entries': entries, - 'title': show_name + ' ' + title, - 'description': description, - } + return self._get_videos_info_from_url(mrss_url, video_id) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 0843d89af..53c28f016 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -44,7 +44,9 @@ from ..utils import ( sanitized_Request, unescapeHTML, unified_strdate, + unified_timestamp, url_basename, + xpath_element, xpath_text, xpath_with_ns, determine_protocol, @@ -52,6 +54,9 @@ from ..utils import ( mimetype2ext, update_Request, update_url_query, + parse_m3u8_attributes, + extract_attributes, + parse_codecs, ) @@ -159,6 +164,7 @@ class InfoExtractor(object): * "height" (optional, int) * "resolution" (optional, string "{width}x{height"}, deprecated) + * "filesize" (optional, int) thumbnail: Full URL to a video thumbnail image. description: Full video description. uploader: Full name of the video uploader. @@ -747,10 +753,12 @@ class InfoExtractor(object): return self._og_search_property('url', html, **kargs) def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs): + if not isinstance(name, (list, tuple)): + name = [name] if display_name is None: - display_name = name + display_name = name[0] return self._html_search_regex( - self._meta_regex(name), + [self._meta_regex(n) for n in name], html, display_name, fatal=fatal, group='content', **kwargs) def _dc_search_uploader(self, html): @@ -799,15 +807,17 @@ class InfoExtractor(object): return self._html_search_meta('twitter:player', html, 'twitter card player') - def _search_json_ld(self, html, video_id, **kwargs): + def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): json_ld = self._search_regex( r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>', html, 'JSON-LD', group='json_ld', **kwargs) if not json_ld: return {} - return self._json_ld(json_ld, video_id, fatal=kwargs.get('fatal', True)) + return self._json_ld( + json_ld, video_id, fatal=kwargs.get('fatal', True), + expected_type=expected_type) - def _json_ld(self, json_ld, video_id, fatal=True): + def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None): if isinstance(json_ld, compat_str): json_ld = self._parse_json(json_ld, video_id, fatal=fatal) if not json_ld: @@ -815,6 +825,8 @@ class InfoExtractor(object): info = {} if json_ld.get('@context') == 'http://schema.org': item_type = json_ld.get('@type') + if expected_type is not None and expected_type != item_type: + return info if item_type == 'TVEpisode': info.update({ 'episode': unescapeHTML(json_ld.get('name')), @@ -833,6 +845,19 @@ class InfoExtractor(object): 'title': unescapeHTML(json_ld.get('headline')), 'description': unescapeHTML(json_ld.get('articleBody')), }) + elif item_type == 'VideoObject': + info.update({ + 'url': json_ld.get('contentUrl'), + 'title': unescapeHTML(json_ld.get('name')), + 'description': unescapeHTML(json_ld.get('description')), + 'thumbnail': json_ld.get('thumbnailUrl'), + 'duration': parse_duration(json_ld.get('duration')), + 'timestamp': unified_timestamp(json_ld.get('uploadDate')), + 'filesize': float_or_none(json_ld.get('contentSize')), + 'tbr': int_or_none(json_ld.get('bitrate')), + 'width': int_or_none(json_ld.get('width')), + 'height': int_or_none(json_ld.get('height')), + }) return dict((k, v) for k, v in info.items() if v is not None) @staticmethod @@ -874,7 +899,11 @@ class InfoExtractor(object): f['ext'] = determine_ext(f['url']) if isinstance(field_preference, (list, tuple)): - return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference) + return tuple( + f.get(field) + if f.get(field) is not None + else ('' if field == 'format_id' else -1) + for field in field_preference) preference = f.get('preference') if preference is None: @@ -987,7 +1016,7 @@ class InfoExtractor(object): def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), - fatal=True): + fatal=True, m3u8_id=None): manifest = self._download_xml( manifest_url, video_id, 'Downloading f4m manifest', 'Unable to download f4m manifest', @@ -1001,11 +1030,11 @@ class InfoExtractor(object): return self._parse_f4m_formats( manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id, - transform_source=transform_source, fatal=fatal) + transform_source=transform_source, fatal=fatal, m3u8_id=m3u8_id) def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), - fatal=True): + fatal=True, m3u8_id=None): # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0') if akamai_pv is not None and ';' in akamai_pv.text: @@ -1029,9 +1058,26 @@ class InfoExtractor(object): 'base URL', default=None) if base_url: base_url = base_url.strip() + + bootstrap_info = xpath_element( + manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'], + 'bootstrap info', default=None) + for i, media_el in enumerate(media_nodes): - if manifest_version == '2.0': - media_url = media_el.attrib.get('href') or media_el.attrib.get('url') + tbr = int_or_none(media_el.attrib.get('bitrate')) + width = int_or_none(media_el.attrib.get('width')) + height = int_or_none(media_el.attrib.get('height')) + format_id = '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])) + # If <bootstrapInfo> is present, the specified f4m is a + # stream-level manifest, and only set-level manifests may refer to + # external resources. See section 11.4 and section 4 of F4M spec + if bootstrap_info is None: + media_url = None + # @href is introduced in 2.0, see section 11.6 of F4M spec + if manifest_version == '2.0': + media_url = media_el.attrib.get('href') + if media_url is None: + media_url = media_el.attrib.get('url') if not media_url: continue manifest_url = ( @@ -1041,29 +1087,43 @@ class InfoExtractor(object): # since bitrates in parent manifest (this one) and media_url manifest # may differ leading to inability to resolve the format by requested # bitrate in f4m downloader - if determine_ext(manifest_url) == 'f4m': - formats.extend(self._extract_f4m_formats( + ext = determine_ext(manifest_url) + if ext == 'f4m': + f4m_formats = self._extract_f4m_formats( manifest_url, video_id, preference=preference, f4m_id=f4m_id, - transform_source=transform_source, fatal=fatal)) + transform_source=transform_source, fatal=fatal) + # Sometimes stream-level manifest contains single media entry that + # does not contain any quality metadata (e.g. http://matchtv.ru/#live-player). + # At the same time parent's media entry in set-level manifest may + # contain it. We will copy it from parent in such cases. + if len(f4m_formats) == 1: + f = f4m_formats[0] + f.update({ + 'tbr': f.get('tbr') or tbr, + 'width': f.get('width') or width, + 'height': f.get('height') or height, + 'format_id': f.get('format_id') if not tbr else format_id, + }) + formats.extend(f4m_formats) + continue + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + manifest_url, video_id, 'mp4', preference=preference, + m3u8_id=m3u8_id, fatal=fatal)) continue - tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ - 'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])), + 'format_id': format_id, 'url': manifest_url, - 'ext': 'flv', + 'ext': 'flv' if bootstrap_info is not None else None, 'tbr': tbr, - 'width': int_or_none(media_el.attrib.get('width')), - 'height': int_or_none(media_el.attrib.get('height')), + 'width': width, + 'height': height, 'preference': preference, }) return formats - def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, - entry_protocol='m3u8', preference=None, - m3u8_id=None, note=None, errnote=None, - fatal=True, live=False): - - formats = [{ + def _m3u8_meta_format(self, m3u8_url, ext=None, preference=None, m3u8_id=None): + return { 'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])), 'url': m3u8_url, 'ext': ext, @@ -1071,7 +1131,14 @@ class InfoExtractor(object): 'preference': preference - 1 if preference else -1, 'resolution': 'multiple', 'format_note': 'Quality selection URL', - }] + } + + def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, + entry_protocol='m3u8', preference=None, + m3u8_id=None, note=None, errnote=None, + fatal=True, live=False): + + formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)] format_url = lambda u: ( u @@ -1111,23 +1178,11 @@ class InfoExtractor(object): }] last_info = None last_media = None - kv_rex = re.compile( - r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)') for line in m3u8_doc.splitlines(): if line.startswith('#EXT-X-STREAM-INF:'): - last_info = {} - for m in kv_rex.finditer(line): - v = m.group('val') - if v.startswith('"'): - v = v[1:-1] - last_info[m.group('key')] = v + last_info = parse_m3u8_attributes(line) elif line.startswith('#EXT-X-MEDIA:'): - last_media = {} - for m in kv_rex.finditer(line): - v = m.group('val') - if v.startswith('"'): - v = v[1:-1] - last_media[m.group('key')] = v + last_media = parse_m3u8_attributes(line) elif line.startswith('#') or not line.strip(): continue else: @@ -1138,17 +1193,21 @@ class InfoExtractor(object): format_id = [] if m3u8_id: format_id.append(m3u8_id) - last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') != 'SUBTITLES' else None + last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') not in ('SUBTITLES', 'CLOSED-CAPTIONS') else None + # Despite specification does not mention NAME attribute for + # EXT-X-STREAM-INF it still sometimes may be present + stream_name = last_info.get('NAME') or last_media_name # Bandwidth of live streams may differ over time thus making # format_id unpredictable. So it's better to keep provided # format_id intact. if not live: - format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats))) + format_id.append(stream_name if stream_name else '%d' % (tbr if tbr else len(formats))) f = { 'format_id': '-'.join(format_id), 'url': format_url(line.strip()), 'tbr': tbr, 'ext': ext, + 'fps': float_or_none(last_info.get('FRAME-RATE')), 'protocol': entry_protocol, 'preference': preference, } @@ -1157,24 +1216,17 @@ class InfoExtractor(object): width_str, height_str = resolution.split('x') f['width'] = int(width_str) f['height'] = int(height_str) - codecs = last_info.get('CODECS') - if codecs: - vcodec, acodec = [None] * 2 - va_codecs = codecs.split(',') - if len(va_codecs) == 1: - # Audio only entries usually come with single codec and - # no resolution. For more robustness we also check it to - # be mp4 audio. - if not resolution and va_codecs[0].startswith('mp4a'): - vcodec, acodec = 'none', va_codecs[0] - else: - vcodec = va_codecs[0] - else: - vcodec, acodec = va_codecs[:2] + # Unified Streaming Platform + mobj = re.search( + r'audio.*?(?:%3D|=)(\d+)(?:-video.*?(?:%3D|=)(\d+))?', f['url']) + if mobj: + abr, vbr = mobj.groups() + abr, vbr = float_or_none(abr, 1000), float_or_none(vbr, 1000) f.update({ - 'acodec': acodec, - 'vcodec': vcodec, + 'vbr': vbr, + 'abr': abr, }) + f.update(parse_codecs(last_info.get('CODECS'))) if last_media is not None: f['m3u8_media'] = last_media last_media = None @@ -1275,21 +1327,21 @@ class InfoExtractor(object): m3u8_count = 0 srcs = [] - videos = smil.findall(self._xpath_ns('.//video', namespace)) - for video in videos: - src = video.get('src') + media = smil.findall(self._xpath_ns('.//video', namespace)) + smil.findall(self._xpath_ns('.//audio', namespace)) + for medium in media: + src = medium.get('src') if not src or src in srcs: continue srcs.append(src) - bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) - filesize = int_or_none(video.get('size') or video.get('fileSize')) - width = int_or_none(video.get('width')) - height = int_or_none(video.get('height')) - proto = video.get('proto') - ext = video.get('ext') + bitrate = float_or_none(medium.get('system-bitrate') or medium.get('systemBitrate'), 1000) + filesize = int_or_none(medium.get('size') or medium.get('fileSize')) + width = int_or_none(medium.get('width')) + height = int_or_none(medium.get('height')) + proto = medium.get('proto') + ext = medium.get('ext') src_ext = determine_ext(src) - streamer = video.get('streamer') or base + streamer = medium.get('streamer') or base if proto == 'rtmp' or streamer.startswith('rtmp'): rtmp_count += 1 @@ -1429,6 +1481,13 @@ class InfoExtractor(object): compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict) def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}): + """ + Parse formats from MPD manifest. + References: + 1. MPEG-DASH Standard, ISO/IEC 23009-1:2014(E), + http://standards.iso.org/ittf/PubliclyAvailableStandards/c065274_ISO_IEC_23009-1_2014.zip + 2. https://en.wikipedia.org/wiki/Dynamic_Adaptive_Streaming_over_HTTP + """ if mpd_doc.get('type') == 'dynamic': return [] @@ -1461,8 +1520,16 @@ class InfoExtractor(object): s_e = segment_timeline.findall(_add_ns('S')) if s_e: ms_info['total_number'] = 0 + ms_info['s'] = [] for s in s_e: - ms_info['total_number'] += 1 + int(s.get('r', '0')) + r = int(s.get('r', 0)) + ms_info['total_number'] += 1 + r + ms_info['s'].append({ + 't': int(s.get('t', 0)), + # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60]) + 'd': int(s.attrib['d']), + 'r': r, + }) else: timescale = segment_template.get('timescale') if timescale: @@ -1499,7 +1566,7 @@ class InfoExtractor(object): continue representation_attrib = adaptation_set.attrib.copy() representation_attrib.update(representation.attrib) - # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory + # According to [1, 5.3.7.2, Table 9, page 41], @mimeType is mandatory mime_type = representation_attrib['mimeType'] content_type = mime_type.split('/')[0] if content_type == 'text': @@ -1543,16 +1610,40 @@ class InfoExtractor(object): representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration)) media_template = representation_ms_info['media_template'] media_template = media_template.replace('$RepresentationID$', representation_id) - media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template) - media_template = re.sub(r'\$(Number|Bandwidth)%([^$]+)\$', r'%(\1)\2', media_template) + media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template) + media_template = re.sub(r'\$(Number|Bandwidth|Time)%([^$]+)\$', r'%(\1)\2', media_template) media_template.replace('$$', '$') - representation_ms_info['segment_urls'] = [ - media_template % { - 'Number': segment_number, - 'Bandwidth': representation_attrib.get('bandwidth')} - for segment_number in range( - representation_ms_info['start_number'], - representation_ms_info['total_number'] + representation_ms_info['start_number'])] + + # As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$ + # can't be used at the same time + if '%(Number' in media_template: + representation_ms_info['segment_urls'] = [ + media_template % { + 'Number': segment_number, + 'Bandwidth': representation_attrib.get('bandwidth'), + } + for segment_number in range( + representation_ms_info['start_number'], + representation_ms_info['total_number'] + representation_ms_info['start_number'])] + else: + representation_ms_info['segment_urls'] = [] + segment_time = 0 + + def add_segment_url(): + representation_ms_info['segment_urls'].append( + media_template % { + 'Time': segment_time, + 'Bandwidth': representation_attrib.get('bandwidth'), + } + ) + + for num, s in enumerate(representation_ms_info['s']): + segment_time = s.get('t') or segment_time + add_segment_url() + for r in range(s.get('r', 0)): + segment_time += s['d'] + add_segment_url() + segment_time += s['d'] if 'segment_urls' in representation_ms_info: f.update({ 'segment_urls': representation_ms_info['segment_urls'], @@ -1579,6 +1670,62 @@ class InfoExtractor(object): self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) return formats + def _parse_html5_media_entries(self, base_url, webpage): + def absolute_url(video_url): + return compat_urlparse.urljoin(base_url, video_url) + + def parse_content_type(content_type): + if not content_type: + return {} + ctr = re.search(r'(?P<mimetype>[^/]+/[^;]+)(?:;\s*codecs="?(?P<codecs>[^"]+))?', content_type) + if ctr: + mimetype, codecs = ctr.groups() + f = parse_codecs(codecs) + f['ext'] = mimetype2ext(mimetype) + return f + return {} + + entries = [] + for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage): + media_info = { + 'formats': [], + 'subtitles': {}, + } + media_attributes = extract_attributes(media_tag) + src = media_attributes.get('src') + if src: + media_info['formats'].append({ + 'url': absolute_url(src), + 'vcodec': 'none' if media_type == 'audio' else None, + }) + media_info['thumbnail'] = media_attributes.get('poster') + if media_content: + for source_tag in re.findall(r'<source[^>]+>', media_content): + source_attributes = extract_attributes(source_tag) + src = source_attributes.get('src') + if not src: + continue + f = parse_content_type(source_attributes.get('type')) + f.update({ + 'url': absolute_url(src), + 'vcodec': 'none' if media_type == 'audio' else None, + }) + media_info['formats'].append(f) + for track_tag in re.findall(r'<track[^>]+>', media_content): + track_attributes = extract_attributes(track_tag) + kind = track_attributes.get('kind') + if not kind or kind == 'subtitles': + src = track_attributes.get('src') + if not src: + continue + lang = track_attributes.get('srclang') or track_attributes.get('lang') or track_attributes.get('label') + media_info['subtitles'].setdefault(lang, []).append({ + 'url': absolute_url(src), + }) + if media_info['formats']: + entries.append(media_info) + return entries + def _live_title(self, name): """ Generate the title for a live video """ now = datetime.datetime.now() @@ -1639,7 +1786,7 @@ class InfoExtractor(object): any_restricted = False for tc in self.get_testcases(include_onlymatching=False): - if 'playlist' in tc: + if tc.get('playlist', []): tc = tc['playlist'][0] is_restricted = age_restricted( tc.get('info_dict', {}).get('age_limit'), age_limit) @@ -1692,6 +1839,13 @@ class InfoExtractor(object): def _mark_watched(self, *args, **kwargs): raise NotImplementedError('This method must be implemented by subclasses') + def geo_verification_headers(self): + headers = {} + geo_verification_proxy = self._downloader.params.get('geo_verification_proxy') + if geo_verification_proxy: + headers['Ytdl-request-proxy'] = geo_verification_proxy + return headers + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/coub.py b/youtube_dl/extractor/coub.py new file mode 100644 index 000000000..a901b8d22 --- /dev/null +++ b/youtube_dl/extractor/coub.py @@ -0,0 +1,143 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + float_or_none, + int_or_none, + parse_iso8601, + qualities, +) + + +class CoubIE(InfoExtractor): + _VALID_URL = r'(?:coub:|https?://(?:coub\.com/(?:view|embed|coubs)/|c-cdn\.coub\.com/fb-player\.swf\?.*\bcoub(?:ID|id)=))(?P<id>[\da-z]+)' + + _TESTS = [{ + 'url': 'http://coub.com/view/5u5n1', + 'info_dict': { + 'id': '5u5n1', + 'ext': 'mp4', + 'title': 'The Matrix Moonwalk', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 4.6, + 'timestamp': 1428527772, + 'upload_date': '20150408', + 'uploader': 'Артём Лоскутников', + 'uploader_id': 'artyom.loskutnikov', + 'view_count': int, + 'like_count': int, + 'repost_count': int, + 'comment_count': int, + 'age_limit': 0, + }, + }, { + 'url': 'http://c-cdn.coub.com/fb-player.swf?bot_type=vk&coubID=7w5a4', + 'only_matching': True, + }, { + 'url': 'coub:5u5n1', + 'only_matching': True, + }, { + # longer video id + 'url': 'http://coub.com/view/237d5l5h', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + coub = self._download_json( + 'http://coub.com/api/v2/coubs/%s.json' % video_id, video_id) + + if coub.get('error'): + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, coub['error']), expected=True) + + title = coub['title'] + + file_versions = coub['file_versions'] + + QUALITIES = ('low', 'med', 'high') + + MOBILE = 'mobile' + IPHONE = 'iphone' + HTML5 = 'html5' + + SOURCE_PREFERENCE = (MOBILE, IPHONE, HTML5) + + quality_key = qualities(QUALITIES) + preference_key = qualities(SOURCE_PREFERENCE) + + formats = [] + + for kind, items in file_versions.get(HTML5, {}).items(): + if kind not in ('video', 'audio'): + continue + if not isinstance(items, dict): + continue + for quality, item in items.items(): + if not isinstance(item, dict): + continue + item_url = item.get('url') + if not item_url: + continue + formats.append({ + 'url': item_url, + 'format_id': '%s-%s-%s' % (HTML5, kind, quality), + 'filesize': int_or_none(item.get('size')), + 'vcodec': 'none' if kind == 'audio' else None, + 'quality': quality_key(quality), + 'preference': preference_key(HTML5), + }) + + iphone_url = file_versions.get(IPHONE, {}).get('url') + if iphone_url: + formats.append({ + 'url': iphone_url, + 'format_id': IPHONE, + 'preference': preference_key(IPHONE), + }) + + mobile_url = file_versions.get(MOBILE, {}).get('audio_url') + if mobile_url: + formats.append({ + 'url': mobile_url, + 'format_id': '%s-audio' % MOBILE, + 'preference': preference_key(MOBILE), + }) + + self._sort_formats(formats) + + thumbnail = coub.get('picture') + duration = float_or_none(coub.get('duration')) + timestamp = parse_iso8601(coub.get('published_at') or coub.get('created_at')) + uploader = coub.get('channel', {}).get('title') + uploader_id = coub.get('channel', {}).get('permalink') + + view_count = int_or_none(coub.get('views_count') or coub.get('views_increase_count')) + like_count = int_or_none(coub.get('likes_count')) + repost_count = int_or_none(coub.get('recoubs_count')) + comment_count = int_or_none(coub.get('comments_count')) + + age_restricted = coub.get('age_restricted', coub.get('age_restricted_by_admin')) + if age_restricted is not None: + age_limit = 18 if age_restricted is True else 0 + else: + age_limit = None + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'like_count': like_count, + 'repost_count': repost_count, + 'comment_count': comment_count, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 84b36f44c..7e5d4f227 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -51,8 +51,11 @@ class CSpanIE(InfoExtractor): 'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers', 'info_dict': { 'id': 'judiciary031715', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Immigration Reforms Needed to Protect Skilled American Workers', + }, + 'params': { + 'skip_download': True, # m3u8 downloads } }] diff --git a/youtube_dl/extractor/ctv.py b/youtube_dl/extractor/ctv.py new file mode 100644 index 000000000..5807fbac9 --- /dev/null +++ b/youtube_dl/extractor/ctv.py @@ -0,0 +1,30 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class CTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ctv\.ca/video/player\?vid=(?P<id>[0-9.]+)' + _TESTS = [{ + 'url': 'http://www.ctv.ca/video/player?vid=706966', + 'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0', + 'info_dict': { + 'id': '706966', + 'ext': 'mp4', + 'title': 'Larry Day and Richard Jutras on the TIFF red carpet of \'Stonewall\'', + 'description': 'etalk catches up with Larry Day and Richard Jutras on the TIFF red carpet of "Stonewall”.', + 'upload_date': '20150919', + 'timestamp': 1442624700, + }, + 'expected_warnings': ['HTTP Error 404'], + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + return { + '_type': 'url_transparent', + 'id': video_id, + 'url': '9c9media:ctv_web:%s' % video_id, + 'ie_key': 'NineCNineMedia', + } diff --git a/youtube_dl/extractor/ctvnews.py b/youtube_dl/extractor/ctvnews.py new file mode 100644 index 000000000..1023b6130 --- /dev/null +++ b/youtube_dl/extractor/ctvnews.py @@ -0,0 +1,65 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import orderedSet + + +class CTVNewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)' + _TESTS = [{ + 'url': 'http://www.ctvnews.ca/video?clipId=901995', + 'md5': '10deb320dc0ccb8d01d34d12fc2ea672', + 'info_dict': { + 'id': '901995', + 'ext': 'mp4', + 'title': 'Extended: \'That person cannot be me\' Johnson says', + 'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285', + 'timestamp': 1467286284, + 'upload_date': '20160630', + } + }, { + 'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224', + 'info_dict': + { + 'id': '1.2966224', + }, + 'playlist_mincount': 19, + }, { + 'url': 'http://www.ctvnews.ca/video?binId=1.2876780', + 'info_dict': + { + 'id': '1.2876780', + }, + 'playlist_mincount': 100, + }, { + 'url': 'http://www.ctvnews.ca/1.810401', + 'only_matching': True, + }, { + 'url': 'http://www.ctvnews.ca/canadiens-send-p-k-subban-to-nashville-in-blockbuster-trade-1.2967231', + 'only_matching': True, + }] + + def _real_extract(self, url): + page_id = self._match_id(url) + + def ninecninemedia_url_result(clip_id): + return { + '_type': 'url_transparent', + 'id': clip_id, + 'url': '9c9media:ctvnews_web:%s' % clip_id, + 'ie_key': 'NineCNineMedia', + } + + if page_id.isdigit(): + return ninecninemedia_url_result(page_id) + else: + webpage = self._download_webpage('http://www.ctvnews.ca/%s' % page_id, page_id, query={ + 'ot': 'example.AjaxPageLayout.ot', + 'maxItemsPerPage': 1000000, + }) + entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet( + re.findall(r'clip\.id\s*=\s*(\d+);', webpage))] + return self.playlist_result(entries, page_id) diff --git a/youtube_dl/extractor/cwtv.py b/youtube_dl/extractor/cwtv.py index ebd14cb16..c66c359cf 100644 --- a/youtube_dl/extractor/cwtv.py +++ b/youtube_dl/extractor/cwtv.py @@ -9,7 +9,7 @@ from ..utils import ( class CWTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/(?:shows/)?(?:[^/]+/){2}\?.*\bplay=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})' + _VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})' _TESTS = [{ 'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63', 'info_dict': { @@ -51,6 +51,12 @@ class CWTVIE(InfoExtractor): }, { 'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6', 'only_matching': True, + }, { + 'url': 'http://cwtvpr.com/the-cw/video?watch=9eee3f60-ef4e-440b-b3b2-49428ac9c54e', + 'only_matching': True, + }, { + 'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?watch=6b15e985-9345-4f60-baf8-56e96be57c63', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/dailymail.py b/youtube_dl/extractor/dailymail.py index b60a1d813..98c835bf1 100644 --- a/youtube_dl/extractor/dailymail.py +++ b/youtube_dl/extractor/dailymail.py @@ -5,19 +5,20 @@ from .common import InfoExtractor from ..utils import ( int_or_none, determine_protocol, + unescapeHTML, ) class DailyMailIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)' _TEST = { - 'url': 'http://www.dailymail.co.uk/video/sciencetech/video-1288527/Turn-video-impressionist-masterpiece.html', - 'md5': '2f639d446394f53f3a33658b518b6615', + 'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html', + 'md5': 'f6129624562251f628296c3a9ffde124', 'info_dict': { - 'id': '1288527', + 'id': '1295863', 'ext': 'mp4', - 'title': 'Turn any video into an impressionist masterpiece', - 'description': 'md5:88ddbcb504367987b2708bb38677c9d2', + 'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'', + 'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84', } } @@ -26,7 +27,7 @@ class DailyMailIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_data = self._parse_json(self._search_regex( r"data-opts='({.+?})'", webpage, 'video data'), video_id) - title = video_data['title'] + title = unescapeHTML(video_data['title']) video_sources = self._download_json(video_data.get( 'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id, video_id) @@ -55,7 +56,7 @@ class DailyMailIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'description': video_data.get('descr'), + 'description': unescapeHTML(video_data.get('descr')), 'thumbnail': video_data.get('poster') or video_data.get('thumbnail'), 'formats': formats, } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 2e6226ea0..496883d15 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -16,6 +16,7 @@ from ..utils import ( sanitized_Request, str_to_int, unescapeHTML, + mimetype2ext, ) @@ -111,6 +112,13 @@ class DailymotionIE(DailymotionBaseInfoExtractor): } ] + @staticmethod + def _extract_urls(webpage): + # Look for embedded Dailymotion player + matches = re.findall( + r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) + return list(map(lambda m: unescapeHTML(m[1]), matches)) + def _real_extract(self, url): video_id = self._match_id(url) @@ -153,18 +161,19 @@ class DailymotionIE(DailymotionBaseInfoExtractor): type_ = media.get('type') if type_ == 'application/vnd.lumberjack.manifest': continue - ext = determine_ext(media_url) - if type_ == 'application/x-mpegURL' or ext == 'm3u8': + ext = mimetype2ext(type_) or determine_ext(media_url) + if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( media_url, video_id, 'mp4', preference=-1, m3u8_id='hls', fatal=False)) - elif type_ == 'application/f4m' or ext == 'f4m': + elif ext == 'f4m': formats.extend(self._extract_f4m_formats( media_url, video_id, preference=-1, f4m_id='hds', fatal=False)) else: f = { 'url': media_url, 'format_id': 'http-%s' % quality, + 'ext': ext, } m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url) if m: @@ -322,7 +331,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): for video_id in re.findall(r'data-xid="(.+?)"', webpage): if video_id not in video_ids: - yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') + yield self.url_result( + 'http://www.dailymotion.com/video/%s' % video_id, + DailymotionIE.ie_key(), video_id) video_ids.add(video_id) if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 86024a745..b5c310ccb 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -66,22 +66,32 @@ class DaumIE(InfoExtractor): 'view_count': int, 'comment_count': int, }, + }, { + # Requires dte_type=WEB (#9972) + 'url': 'http://tvpot.daum.net/v/s3794Uf1NZeZ1qMpGpeqeRU', + 'md5': 'a8917742069a4dd442516b86e7d66529', + 'info_dict': { + 'id': 's3794Uf1NZeZ1qMpGpeqeRU', + 'ext': 'mp4', + 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611', + 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회', + 'upload_date': '20160611', + }, }] def _real_extract(self, url): video_id = compat_urllib_parse_unquote(self._match_id(url)) - query = compat_urllib_parse_urlencode({'vid': video_id}) movie_data = self._download_json( - 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json?' + query, - video_id, 'Downloading video formats info') + 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json', + video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'}) # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id): return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id) info = self._download_xml( - 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id, - 'Downloading video info') + 'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id, + 'Downloading video info', query={'vid': video_id}) formats = [] for format_el in movie_data['output_list']['output_list']: diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py index 133cdc50b..caff8842e 100644 --- a/youtube_dl/extractor/dbtv.py +++ b/youtube_dl/extractor/dbtv.py @@ -4,78 +4,47 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - float_or_none, - int_or_none, - clean_html, -) class DBTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?' + _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:[^/]+/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?' _TESTS = [{ 'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', - 'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc', + 'md5': '2e24f67936517b143a234b4cadf792ec', 'info_dict': { - 'id': '33100', + 'id': '3649835190001', 'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', 'ext': 'mp4', 'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen', 'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0', - 'thumbnail': 're:https?://.*\.jpg$', - 'timestamp': 1404039863.438, + 'thumbnail': 're:https?://.*\.jpg', + 'timestamp': 1404039863, 'upload_date': '20140629', 'duration': 69.544, - 'view_count': int, - 'categories': list, - } + 'uploader_id': '1027729757001', + }, + 'add_ie': ['BrightcoveNew'] }, { 'url': 'http://dbtv.no/3649835190001', 'only_matching': True, }, { 'url': 'http://www.dbtv.no/lazyplayer/4631135248001', 'only_matching': True, + }, { + 'url': 'http://dbtv.no/vice/5000634109001', + 'only_matching': True, + }, { + 'url': 'http://dbtv.no/filmtrailer/3359293614001', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') or video_id - - data = self._download_json( - 'http://api.dbtv.no/discovery/%s' % video_id, display_id) - - video = data['playlist'][0] - - formats = [{ - 'url': f['URL'], - 'vcodec': f.get('container'), - 'width': int_or_none(f.get('width')), - 'height': int_or_none(f.get('height')), - 'vbr': float_or_none(f.get('rate'), 1000), - 'filesize': int_or_none(f.get('size')), - } for f in video['renditions'] if 'URL' in f] - - if not formats: - for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]: - if url_key in video: - formats.append({ - 'url': video[url_key], - 'format_id': format_id, - }) - - self._sort_formats(formats) + video_id, display_id = re.match(self._VALID_URL, url).groups() return { - 'id': compat_str(video['id']), + '_type': 'url_transparent', + 'url': 'http://players.brightcove.net/1027729757001/default_default/index.html?videoId=%s' % video_id, + 'id': video_id, 'display_id': display_id, - 'title': video['title'], - 'description': clean_html(video['desc']), - 'thumbnail': video.get('splash') or video.get('thumb'), - 'timestamp': float_or_none(video.get('publishedAt'), 1000), - 'duration': float_or_none(video.get('length'), 1000), - 'view_count': int_or_none(video.get('views')), - 'categories': video.get('tags'), - 'formats': formats, + 'ie_key': 'BrightcoveNew', } diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py index 5deff5f30..b8542820a 100644 --- a/youtube_dl/extractor/dcn.py +++ b/youtube_dl/extractor/dcn.py @@ -20,7 +20,7 @@ from ..utils import ( class DCNIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?' + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?' def _real_extract(self, url): show_id, video_id, season_id = re.match(self._VALID_URL, url).groups() @@ -55,30 +55,30 @@ class DCNBaseIE(InfoExtractor): 'is_live': is_live, } - def _extract_video_formats(self, webpage, video_id, entry_protocol): + def _extract_video_formats(self, webpage, video_id, m3u8_entry_protocol): formats = [] - m3u8_url = self._html_search_regex( - r'file\s*:\s*"([^"]+)', webpage, 'm3u8 url', fatal=False) - if m3u8_url: - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=None)) - - rtsp_url = self._search_regex( - r'<a[^>]+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False) - if rtsp_url: - formats.append({ - 'url': rtsp_url, - 'format_id': 'rtsp', - }) - + format_url_base = 'http' + self._html_search_regex( + [ + r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8', + r'<a[^>]+href="rtsp(://[^"]+)"' + ], webpage, 'format url') + formats.extend(self._extract_mpd_formats( + format_url_base + '/manifest.mpd', + video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_m3u8_formats( + format_url_base + '/playlist.m3u8', video_id, 'mp4', + m3u8_entry_protocol, m3u8_id='hls', fatal=False)) + formats.extend(self._extract_f4m_formats( + format_url_base + '/manifest.f4m', + video_id, f4m_id='hds', fatal=False)) self._sort_formats(formats) return formats class DCNVideoIE(DCNBaseIE): IE_NAME = 'dcn:video' - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/[^/]+|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)' + _TESTS = [{ 'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375', 'info_dict': { @@ -94,7 +94,10 @@ class DCNVideoIE(DCNBaseIE): # m3u8 download 'skip_download': True, }, - } + }, { + 'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -120,7 +123,7 @@ class DCNVideoIE(DCNBaseIE): class DCNLiveIE(DCNBaseIE): IE_NAME = 'dcn:live' - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?live/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)' def _real_extract(self, url): channel_id = self._match_id(url) @@ -147,7 +150,7 @@ class DCNLiveIE(DCNBaseIE): class DCNSeasonIE(InfoExtractor): IE_NAME = 'dcn:season' - _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))' + _VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))' _TEST = { 'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A', 'info_dict': diff --git a/youtube_dl/extractor/dreisat.py b/youtube_dl/extractor/dreisat.py index 0040e70d4..908c9e514 100644 --- a/youtube_dl/extractor/dreisat.py +++ b/youtube_dl/extractor/dreisat.py @@ -17,8 +17,12 @@ class DreiSatIE(ZDFIE): 'ext': 'mp4', 'title': 'Waidmannsheil', 'description': 'md5:cce00ca1d70e21425e72c86a98a56817', - 'uploader': '3sat', + 'uploader': 'SCHWEIZWEIT', + 'uploader_id': '100000210', 'upload_date': '20140913' + }, + 'params': { + 'skip_download': True, # m3u8 downloads } }, { diff --git a/youtube_dl/extractor/dw.py b/youtube_dl/extractor/dw.py index ae7c571bd..d740652f1 100644 --- a/youtube_dl/extractor/dw.py +++ b/youtube_dl/extractor/dw.py @@ -2,13 +2,16 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + unified_strdate, +) from ..compat import compat_urlparse class DWIE(InfoExtractor): IE_NAME = 'dw' - _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)' _TESTS = [{ # video 'url': 'http://www.dw.com/en/intelligent-light/av-19112290', @@ -31,6 +34,18 @@ class DWIE(InfoExtractor): 'description': 'md5:bc9ca6e4e063361e21c920c53af12405', 'upload_date': '20160311', } + }, { + # DW documentaries, only last for one or two weeks + 'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798', + 'md5': '56b6214ef463bfb9a3b71aeb886f3cf1', + 'info_dict': { + 'id': '19274438', + 'ext': 'mp4', + 'title': 'Welcome to the 90s – Hip Hop', + 'description': 'Welcome to the 90s - The Golden Decade of Hip Hop', + 'upload_date': '20160521', + }, + 'skip': 'Video removed', }] def _real_extract(self, url): @@ -38,6 +53,7 @@ class DWIE(InfoExtractor): webpage = self._download_webpage(url, media_id) hidden_inputs = self._hidden_inputs(webpage) title = hidden_inputs['media_title'] + media_id = hidden_inputs.get('media_id') or media_id if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1': formats = self._extract_smil_formats( @@ -49,13 +65,20 @@ class DWIE(InfoExtractor): else: formats = [{'url': hidden_inputs['file_name']}] + upload_date = hidden_inputs.get('display_date') + if not upload_date: + upload_date = self._html_search_regex( + r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage, + 'upload date', default=None) + upload_date = unified_strdate(upload_date) + return { 'id': media_id, 'title': title, 'description': self._og_search_description(webpage), 'thumbnail': hidden_inputs.get('preview_image'), 'duration': int_or_none(hidden_inputs.get('file_duration')), - 'upload_date': hidden_inputs.get('display_date'), + 'upload_date': upload_date, 'formats': formats, } diff --git a/youtube_dl/extractor/eagleplatform.py b/youtube_dl/extractor/eagleplatform.py index 113a4966f..12d28d3b9 100644 --- a/youtube_dl/extractor/eagleplatform.py +++ b/youtube_dl/extractor/eagleplatform.py @@ -50,6 +50,14 @@ class EaglePlatformIE(InfoExtractor): 'skip': 'Georestricted', }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1', + webpage) + if mobj is not None: + return mobj.group('url') + @staticmethod def _handle_error(response): status = int_or_none(response.get('status', 200)) diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py index 4c8190d68..74bbc5c51 100644 --- a/youtube_dl/extractor/ellentv.py +++ b/youtube_dl/extractor/ellentv.py @@ -6,12 +6,13 @@ import json from .common import InfoExtractor from ..utils import ( ExtractorError, + NO_DEFAULT, ) class EllenTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.ellentv.com/videos/0-ipq1gsai/', 'md5': '4294cf98bc165f218aaa0b89e0fd8042', 'info_dict': { @@ -22,24 +23,47 @@ class EllenTVIE(InfoExtractor): 'timestamp': 1428035648, 'upload_date': '20150403', 'uploader_id': 'batchUser', - } - } + }, + }, { + # not available via http://widgets.ellentube.com/ + 'url': 'http://www.ellentv.com/videos/1-szkgu2m2/', + 'info_dict': { + 'id': '1_szkgu2m2', + 'ext': 'flv', + 'title': "Ellen's Amazingly Talented Audience", + 'description': 'md5:86ff1e376ff0d717d7171590e273f0a5', + 'timestamp': 1255140900, + 'upload_date': '20091010', + 'uploader_id': 'ellenkaltura@gmail.com', + }, + 'params': { + 'skip_download': True, + }, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'http://widgets.ellentube.com/videos/%s' % video_id, - video_id) + URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url) - partner_id = self._search_regex( - r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id') + for num, url_ in enumerate(URLS, 1): + webpage = self._download_webpage( + url_, video_id, fatal=num == len(URLS)) - kaltura_id = self._search_regex( - [r'id="kaltura_player_([^"]+)"', - r"_wb_entry_id\s*:\s*'([^']+)", - r'data-kaltura-entry-id="([^"]+)'], - webpage, 'kaltura id') + default = NO_DEFAULT if num == len(URLS) else None + + partner_id = self._search_regex( + r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id', + default=default) + + kaltura_id = self._search_regex( + [r'id="kaltura_player_([^"]+)"', + r"_wb_entry_id\s*:\s*'([^']+)", + r'data-kaltura-entry-id="([^"]+)'], + webpage, 'kaltura id', default=default) + + if partner_id and kaltura_id: + break return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura') diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index e006921ec..f3734e9f8 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -4,54 +4,100 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( + encode_base_n, + ExtractorError, + int_or_none, parse_duration, str_to_int, ) class EpornerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?' + _TESTS = [{ 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', 'md5': '39d486f046212d8e1b911c52ab4691f8', 'info_dict': { - 'id': '95008', + 'id': 'qlDUmNsj6VS', 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', 'ext': 'mp4', 'title': 'Infamous Tiffany Teen Strip Tease Video', 'duration': 1838, 'view_count': int, 'age_limit': 18, - } - } + }, + }, { + # New (May 2016) URL layout + 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/', + 'only_matching': True, + }, { + 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0', + 'only_matching': True, + }] 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 - webpage = self._download_webpage(url, display_id) - title = self._html_search_regex( - r'<title>(.*?) - EPORNER', webpage, 'title') + webpage, urlh = self._download_webpage_handle(url, display_id) - redirect_url = 'http://www.eporner.com/config5/%s' % video_id - player_code = self._download_webpage( - redirect_url, display_id, note='Downloading player config') + video_id = self._match_id(compat_str(urlh.geturl())) - sources = self._search_regex( - r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources') + hash = self._search_regex( + r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash') + + title = self._og_search_title(webpage, default=None) or self._html_search_regex( + r'<title>(.+?) - EPORNER', webpage, 'title') + + # Reverse engineered from vjs.js + def calc_hash(s): + return ''.join((encode_base_n(int(s[lb:lb + 8], 16), 36) for lb in range(0, 32, 8))) + + video = self._download_json( + 'http://www.eporner.com/xhr/video/%s' % video_id, + display_id, note='Downloading video JSON', + query={ + 'hash': calc_hash(hash), + 'device': 'generic', + 'domain': 'www.eporner.com', + 'fallback': 'false', + }) + + if video.get('available') is False: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, video['message']), expected=True) + + sources = video['sources'] formats = [] - for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources): - fmt = { - 'url': video_url, - 'format_id': format_id, - } - m = re.search(r'^(\d+)', format_id) - if m: - fmt['height'] = int(m.group(1)) - formats.append(fmt) + for kind, formats_dict in sources.items(): + if not isinstance(formats_dict, dict): + continue + for format_id, format_dict in formats_dict.items(): + if not isinstance(format_dict, dict): + continue + src = format_dict.get('src') + if not isinstance(src, compat_str) or not src.startswith('http'): + continue + if kind == 'hls': + formats.extend(self._extract_m3u8_formats( + src, display_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id=kind, fatal=False)) + else: + height = int_or_none(self._search_regex( + r'(\d+)[pP]', format_id, 'height', default=None)) + fps = int_or_none(self._search_regex( + r'(\d+)fps', format_id, 'fps', default=None)) + + formats.append({ + 'url': src, + 'format_id': format_id, + 'height': height, + 'fps': fps, + }) self._sort_formats(formats) duration = parse_duration(self._html_search_meta('duration', webpage)) diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index db4b263bc..66c08bec4 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -8,6 +8,7 @@ class ESPNIE(InfoExtractor): _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://espn.go.com/video/clip?id=10365079', + 'md5': '60e5d097a523e767d06479335d1bdc58', 'info_dict': { 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', 'ext': 'mp4', @@ -15,21 +16,22 @@ class ESPNIE(InfoExtractor): 'description': None, }, 'params': { - # m3u8 download 'skip_download': True, }, + 'add_ie': ['OoyalaExternal'], }, { # intl video, from http://www.espnfc.us/video/mls-highlights/150/video/2743663/must-see-moments-best-of-the-mls-season 'url': 'http://espn.go.com/video/clip?id=2743663', + 'md5': 'f4ac89b59afc7e2d7dbb049523df6768', 'info_dict': { 'id': '50NDFkeTqRHB0nXBOK-RGdSG5YQPuxHg', 'ext': 'mp4', 'title': 'Must-See Moments: Best of the MLS season', }, 'params': { - # m3u8 download 'skip_download': True, }, + 'add_ie': ['OoyalaExternal'], }, { 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', 'only_matching': True, diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 50d2204f2..53fab1a31 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -3,6 +3,10 @@ from __future__ import unicode_literals from .abc import ABCIE from .abc7news import Abc7NewsIE +from .abcnews import ( + AbcNewsIE, + AbcNewsVideoIE, +) from .academicearth import AcademicEarthCourseIE from .acast import ( ACastIE, @@ -16,7 +20,11 @@ from .adobetv import ( AdobeTVVideoIE, ) from .adultswim import AdultSwimIE -from .aenetworks import AENetworksIE +from .aenetworks import ( + AENetworksIE, + HistoryTopicIE, +) +from .afreecatv import AfreecaTVIE from .aftonbladet import AftonbladetIE from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE @@ -36,10 +44,10 @@ from .appletrailers import ( AppleTrailersSectionIE, ) from .archiveorg import ArchiveOrgIE +from .arkena import ArkenaIE from .ard import ( ARDIE, ARDMediathekIE, - SportschauIE, ) from .arte import ( ArteTvIE, @@ -52,6 +60,7 @@ from .arte import ( ArteTVDDCIE, ArteTVMagazineIE, ArteTVEmbedIE, + ArteTVPlaylistIE, ) from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE @@ -65,6 +74,8 @@ from .bandcamp import BandcampIE, BandcampAlbumIE from .bbc import ( BBCCoUkIE, BBCCoUkArticleIE, + BBCCoUkIPlayerPlaylistIE, + BBCCoUkPlaylistIE, BBCIE, ) from .beeg import BeegIE @@ -102,11 +113,16 @@ from .camwithher import CamWithHerIE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .canvas import CanvasIE +from .carambatv import ( + CarambaTVIE, + CarambaTVPageIE, +) from .cbc import ( CBCIE, CBCPlayerIE, ) from .cbs import CBSIE +from .cbslocal import CBSLocalIE from .cbsinteractive import CBSInteractiveIE from .cbsnews import ( CBSNewsIE, @@ -124,11 +140,11 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE -from .cinemassacre import CinemassacreIE -from .cliprs import ClipRsIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE +from .cliprs import ClipRsIE from .clipsyndicate import ClipsyndicateIE +from .closertotruth import CloserToTruthIE from .cloudy import CloudyIE from .clubic import ClubicIE from .clyp import ClypIE @@ -139,9 +155,13 @@ from .cnn import ( CNNBlogsIE, CNNArticleIE, ) -from .collegehumor import CollegeHumorIE +from .coub import CoubIE from .collegerama import CollegeRamaIE -from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE +from .comedycentral import ( + ComedyCentralIE, + ComedyCentralTVIE, + ToshIE, +) from .comcarcoff import ComCarCoffIE from .commonmistakes import CommonMistakesIE, UnicodeBOMIE from .commonprotocols import RtmpIE @@ -156,6 +176,8 @@ from .crunchyroll import ( ) from .cspan import CSpanIE from .ctsnews import CtsNewsIE +from .ctv import CTVIE +from .ctvnews import CTVNewsIE from .cultureunplugged import CultureUnpluggedIE from .cwtv import CWTVIE from .dailymail import DailyMailIE @@ -228,6 +250,7 @@ from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .expotv import ExpoTVIE from .extremetube import ExtremeTubeIE +from .eyedotv import EyedoTVIE from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE @@ -238,8 +261,10 @@ from .fivemin import FiveMinIE from .fivetv import FiveTVIE from .fktv import FKTVIE from .flickr import FlickrIE +from .flipagram import FlipagramIE from .folketinget import FolketingetIE from .footyroom import FootyRoomIE +from .formula1 import Formula1IE from .fourtube import FourTubeIE from .fox import FOXIE from .foxgay import FoxgayIE @@ -262,6 +287,7 @@ from .freespeech import FreespeechIE from .freevideo import FreeVideoIE from .funimation import FunimationIE from .funnyordie import FunnyOrDieIE +from .fusion import FusionIE from .gameinformer import GameInformerIE from .gamekings import GamekingsIE from .gameone import ( @@ -271,7 +297,6 @@ from .gameone import ( from .gamersyde import GamersydeIE from .gamespot import GameSpotIE from .gamestar import GameStarIE -from .gametrailers import GametrailersIE from .gazeta import GazetaIE from .gdcvault import GDCVaultIE from .generic import GenericIE @@ -284,6 +309,7 @@ from .globo import ( GloboArticleIE, ) from .godtube import GodTubeIE +from .godtv import GodTVIE from .goldenmoustache import GoldenMoustacheIE from .golem import GolemIE from .googledrive import GoogleDriveIE @@ -306,6 +332,10 @@ from .hotnewhiphop import HotNewHipHopIE from .hotstar import HotStarIE from .howcast import HowcastIE from .howstuffworks import HowStuffWorksIE +from .hrti import ( + HRTiIE, + HRTiPlaylistIE, +) from .huffpost import HuffPostIE from .hypem import HypemIE from .iconosquare import IconosquareIE @@ -344,6 +374,7 @@ from .jove import JoveIE from .jwplatform import JWPlatformIE from .jpopsukitv import JpopsukiIE from .kaltura import KalturaIE +from .kamcord import KamcordIE from .kanalplay import KanalPlayIE from .kankan import KankanIE from .karaoketv import KaraoketvIE @@ -367,6 +398,11 @@ from .kuwo import ( ) from .la7 import LA7IE from .laola1tv import Laola1TvIE +from .lcp import ( + LcpPlayIE, + LcpIE, +) +from .learnr import LearnrIE from .lecture2go import Lecture2GoIE from .lemonde import LemondeIE from .leeco import ( @@ -374,6 +410,7 @@ from .leeco import ( LePlaylistIE, LetvCloudIE, ) +from .libraryofcongress import LibraryOfCongressIE from .libsyn import LibsynIE from .lifenews import ( LifeNewsIE, @@ -392,6 +429,7 @@ from .livestream import ( LivestreamShortenerIE, ) from .lnkgo import LnkGoIE +from .localnews8 import LocalNews8IE from .lovehomeporn import LoveHomePornIE from .lrt import LRTIE from .lynda import ( @@ -405,6 +443,7 @@ from .makerschannel import MakersChannelIE from .makertv import MakerTVIE from .matchtv import MatchTVIE from .mdr import MDRIE +from .meta import METAIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE from .mgoon import MgoonIE @@ -437,10 +476,10 @@ from .motherless import MotherlessIE from .motorsport import MotorsportIE from .movieclips import MovieClipsIE from .moviezine import MoviezineIE +from .msn import MSNIE from .mtv import ( MTVIE, MTVServicesEmbeddedIE, - MTVIggyIE, MTVDEIE, ) from .muenchentv import MuenchenTVIE @@ -463,7 +502,6 @@ from .nbc import ( NBCNewsIE, NBCSportsIE, NBCSportsVPlayerIE, - MSNBCIE, ) from .ndr import ( NDRIE, @@ -491,7 +529,6 @@ from .nextmedia import ( NextMediaActionNewsIE, AppleDailyIE, ) -from .nextmovie import NextMovieIE from .nfb import NFBIE from .nfl import NFLIE from .nhl import ( @@ -500,9 +537,15 @@ from .nhl import ( NHLVideocenterCategoryIE, NHLIE, ) -from .nick import NickIE +from .nick import ( + NickIE, + NickDeIE, +) from .niconico import NiconicoIE, NiconicoPlaylistIE +from .ninecninemedia import NineCNineMediaIE from .ninegag import NineGagIE +from .ninenow import NineNowIE +from .nintendo import NintendoIE from .noco import NocoIE from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE @@ -547,8 +590,13 @@ from .nytimes import ( NYTimesArticleIE, ) from .nuvid import NuvidIE +from .odatv import OdaTVIE from .odnoklassniki import OdnoklassnikiIE from .oktoberfesttv import OktoberfestTVIE +from .onet import ( + OnetIE, + OnetChannelIE, +) from .onionstudios import OnionStudiosIE from .ooyala import ( OoyalaIE, @@ -587,6 +635,7 @@ from .pluralsight import ( PluralsightCourseIE, ) from .podomatic import PodomaticIE +from .polskieradio import PolskieRadioIE from .porn91 import Porn91IE from .pornhd import PornHdIE from .pornhub import ( @@ -610,7 +659,14 @@ from .qqmusic import ( QQMusicToplistIE, QQMusicPlaylistIE, ) -from .r7 import R7IE +from .r7 import ( + R7IE, + R7ArticleIE, +) +from .radiocanada import ( + RadioCanadaIE, + RadioCanadaAudioVideoIE, +) from .radiode import RadioDeIE from .radiojavan import RadioJavanIE from .radiobremen import RadioBremenIE @@ -624,11 +680,17 @@ from .rds import RDSIE from .redtube import RedTubeIE from .regiotv import RegioTVIE from .restudy import RestudyIE +from .reuters import ReutersIE from .reverbnation import ReverbNationIE -from .revision3 import Revision3IE +from .revision3 import ( + Revision3EmbedIE, + Revision3IE, +) from .rice import RICEIE from .ringtv import RingTVIE from .ro220 import Ro220IE +from .rockstargames import RockstarGamesIE +from .roosterteeth import RoosterTeethIE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE from .rtbf import RTBFIE @@ -637,8 +699,9 @@ from .rtlnl import RtlNlIE from .rtl2 import RTL2IE from .rtp import RTPIE from .rts import RTSIE -from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE +from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE from .rtvnh import RTVNHIE +from .rudo import RudoIE from .ruhd import RUHDIE from .ruleporn import RulePornIE from .rutube import ( @@ -664,17 +727,21 @@ from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE from .screenjunkies import ScreenJunkiesIE from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE +from .seeker import SeekerIE from .senateisvp import SenateISVPIE +from .sendtonews import SendtoNewsIE from .servingsys import ServingSysIE from .sexu import SexuIE from .shahid import ShahidIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE +from .sixplay import SixPlayIE from .skynewsarabia import ( SkyNewsArabiaIE, SkyNewsArabiaArticleIE, ) +from .skysports import SkySportsIE from .slideshare import SlideshareIE from .slutload import SlutloadIE from .smotri import ( @@ -715,6 +782,7 @@ from .sportbox import ( SportBoxEmbedIE, ) from .sportdeutschland import SportDeutschlandIE +from .sportschau import SportschauIE from .srgssr import ( SRGSSRIE, SRGSSRPlayIE, @@ -723,6 +791,7 @@ from .srmediathek import SRMediathekIE from .ssa import SSAIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE +from .streamable import StreamableIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE @@ -755,6 +824,7 @@ from .telecinco import TelecincoIE from .telegraaf import TelegraafIE from .telemb import TeleMBIE from .teletask import TeleTaskIE +from .telewebion import TelewebionIE from .testurl import TestURLIE from .tf1 import TF1IE from .theintercept import TheInterceptIE @@ -767,6 +837,7 @@ from .thesixtyone import TheSixtyOneIE from .thestar import TheStarIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE +from .threeqsdn import ThreeQSDNIE from .tinypic import TinyPicIE from .tlc import TlcDeIE from .tmz import ( @@ -819,7 +890,10 @@ from .tvc import ( ) from .tvigle import TvigleIE from .tvland import TVLandIE -from .tvp import TvpIE, TvpSeriesIE +from .tvp import ( + TVPIE, + TVPSeriesIE, +) from .tvplay import TVPlayIE from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE @@ -835,6 +909,7 @@ from .twitch import ( TwitchProfileIE, TwitchPastBroadcastsIE, TwitchStreamIE, + TwitchClipsIE, ) from .twitter import ( TwitterCardIE, @@ -849,6 +924,7 @@ from .udn import UDNEmbedIE from .digiteka import DigitekaIE from .unistra import UnistraIE from .urort import UrortIE +from .urplay import URPlayIE from .usatoday import USATodayIE from .ustream import UstreamIE, UstreamChannelIE from .ustudio import ( @@ -875,6 +951,7 @@ from .vice import ( ViceIE, ViceShowIE, ) +from .vidbit import VidbitIE from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE @@ -886,6 +963,7 @@ from .videomore import ( ) from .videopremium import VideoPremiumIE from .videott import VideoTtIE +from .vidio import VidioIE from .vidme import ( VidmeIE, VidmeUserIE, @@ -922,6 +1000,7 @@ from .viki import ( from .vk import ( VKIE, VKUserVideosIE, + VKWallPostIE, ) from .vlive import VLiveIE from .vodlocker import VodlockerIE @@ -931,26 +1010,29 @@ from .vporn import VpornIE from .vrt import VRTIE from .vube import VubeIE from .vuclip import VuClipIE -from .vulture import VultureIE from .walla import WallaIE -from .washingtonpost import WashingtonPostIE +from .washingtonpost import ( + WashingtonPostIE, + WashingtonPostArticleIE, +) from .wat import WatIE from .watchindianporn import WatchIndianPornIE from .wdr import ( WDRIE, WDRMobileIE, - WDRMausIE, ) from .webofstories import ( WebOfStoriesIE, WebOfStoriesPlaylistIE, ) -from .weibo import WeiboIE from .weiqitv import WeiqiTVIE from .wimp import WimpIE from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE -from .wrzuta import WrzutaIE +from .wrzuta import ( + WrzutaIE, + WrzutaPlaylistIE, +) from .wsj import WSJIE from .xbef import XBefIE from .xboxclips import XboxClipsIE @@ -986,7 +1068,10 @@ from .yesjapan import YesJapanIE from .yinyuetai import YinYueTaiIE from .ynet import YnetIE from .youjizz import YouJizzIE -from .youku import YoukuIE +from .youku import ( + YoukuIE, + YoukuShowIE, +) from .youporn import YouPornIE from .yourupload import YourUploadIE from .youtube import ( @@ -1001,6 +1086,7 @@ from .youtube import ( YoutubeSearchDateIE, YoutubeSearchIE, YoutubeSearchURLIE, + YoutubeSharedVideoIE, YoutubeShowIE, YoutubeSubscriptionsIE, YoutubeTruncatedIDIE, diff --git a/youtube_dl/extractor/eyedotv.py b/youtube_dl/extractor/eyedotv.py new file mode 100644 index 000000000..2f3035147 --- /dev/null +++ b/youtube_dl/extractor/eyedotv.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + xpath_text, + parse_duration, + ExtractorError, +) + + +class EyedoTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?eyedo\.tv/[^/]+/(?:#!/)?Live/Detail/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://www.eyedo.tv/en-US/#!/Live/Detail/16301', + 'md5': 'ba14f17995cdfc20c36ba40e21bf73f7', + 'info_dict': { + 'id': '16301', + 'ext': 'mp4', + 'title': 'Journée du conseil scientifique de l\'Afnic 2015', + 'description': 'md5:4abe07293b2f73efc6e1c37028d58c98', + 'uploader': 'Afnic Live', + 'uploader_id': '8023', + } + } + _ROOT_URL = 'http://live.eyedo.net:1935/' + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._download_xml('http://eyedo.tv/api/live/GetLive/%s' % video_id, video_id) + + def _add_ns(path): + return self._xpath_ns(path, 'http://schemas.datacontract.org/2004/07/EyeDo.Core.Implementation.Web.ViewModels.Api') + + title = xpath_text(video_data, _add_ns('Titre'), 'title', True) + state_live_code = xpath_text(video_data, _add_ns('StateLiveCode'), 'title', True) + if state_live_code == 'avenir': + raise ExtractorError( + '%s said: We\'re sorry, but this video is not yet available.' % self.IE_NAME, + expected=True) + + is_live = state_live_code == 'live' + m3u8_url = None + # http://eyedo.tv/Content/Html5/Scripts/html5view.js + if is_live: + if xpath_text(video_data, 'Cdn') == 'true': + m3u8_url = 'http://rrr.sz.xlcdn.com/?account=eyedo&file=A%s&type=live&service=wowza&protocol=http&output=playlist.m3u8' % video_id + else: + m3u8_url = self._ROOT_URL + 'w/%s/eyedo_720p/playlist.m3u8' % video_id + else: + m3u8_url = self._ROOT_URL + 'replay-w/%s/mp4:%s.mp4/playlist.m3u8' % (video_id, video_id) + + return { + 'id': video_id, + 'title': title, + 'formats': self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8' if is_live else 'm3u8_native'), + 'description': xpath_text(video_data, _add_ns('Description')), + 'duration': parse_duration(xpath_text(video_data, _add_ns('Duration'))), + 'uploader': xpath_text(video_data, _add_ns('Createur')), + 'uploader_id': xpath_text(video_data, _add_ns('CreateurId')), + 'chapter': xpath_text(video_data, _add_ns('ChapitreTitre')), + 'chapter_id': xpath_text(video_data, _add_ns('ChapitreId')), + } diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index f5bbd39d2..0fb781a73 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -27,7 +27,7 @@ class FacebookIE(InfoExtractor): _VALID_URL = r'''(?x) (?: https?:// - (?:\w+\.)?facebook\.com/ + (?:[\w-]+\.)?facebook\.com/ (?:[^#]*?\#!/)? (?: (?: @@ -127,8 +127,26 @@ class FacebookIE(InfoExtractor): }, { 'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/', 'only_matching': True, + }, { + 'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/', + 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage) + if mobj is not None: + return mobj.group('url') + + # Facebook API embed + # see https://developers.facebook.com/docs/plugins/embedded-video-player + mobj = re.search(r'''(?x)<div[^>]+ + class=(?P<q1>[\'"])[^\'"]*\bfb-(?:video|post)\b[^\'"]*(?P=q1)[^>]+ + data-href=(?P<q2>[\'"])(?P<url>(?:https?:)?//(?:www\.)?facebook.com/.+?)(?P=q2)''', webpage) + if mobj is not None: + return mobj.group('url') + def _login(self): (useremail, password) = self._get_login_info() if useremail is None: @@ -204,12 +222,25 @@ class FacebookIE(InfoExtractor): BEFORE = '{swf.addParam(param[0], param[1]);});' AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});' - m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage) - if m: - swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"') + PATTERN = re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER) + + for m in re.findall(PATTERN, webpage): + swf_params = m.replace('\\\\', '\\').replace('\\"', '"') data = dict(json.loads(swf_params)) params_raw = compat_urllib_parse_unquote(data['params']) - video_data = json.loads(params_raw)['video_data'] + video_data_candidate = json.loads(params_raw)['video_data'] + for _, f in video_data_candidate.items(): + if not f: + continue + if isinstance(f, dict): + f = [f] + if not isinstance(f, list): + continue + if f[0].get('video_id') == video_id: + video_data = video_data_candidate + break + if video_data: + break def video_data_list2dict(video_data): ret = {} @@ -239,6 +270,8 @@ class FacebookIE(InfoExtractor): formats = [] for format_id, f in video_data.items(): + if f and isinstance(f, dict): + f = [f] if not f or not isinstance(f, list): continue for quality in ('sd', 'hd'): diff --git a/youtube_dl/extractor/flipagram.py b/youtube_dl/extractor/flipagram.py new file mode 100644 index 000000000..acb6133ff --- /dev/null +++ b/youtube_dl/extractor/flipagram.py @@ -0,0 +1,115 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + float_or_none, + try_get, + unified_timestamp, +) + + +class FlipagramIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P<id>[^/?#&]+)' + _TEST = { + 'url': 'https://flipagram.com/f/nyvTSJMKId', + 'md5': '888dcf08b7ea671381f00fab74692755', + 'info_dict': { + 'id': 'nyvTSJMKId', + 'ext': 'mp4', + 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction', + 'description': 'md5:d55e32edc55261cae96a41fa85ff630e', + 'duration': 35.571, + 'timestamp': 1461244995, + 'upload_date': '20160421', + 'uploader': 'kitty juria', + 'uploader_id': 'sjuria101', + 'creator': 'kitty juria', + 'view_count': int, + 'like_count': int, + 'repost_count': int, + 'comment_count': int, + 'comments': list, + 'formats': 'mincount:2', + }, + } + + 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'window\.reactH2O\s*=\s*({.+});', webpage, 'video data'), + video_id) + + flipagram = video_data['flipagram'] + video = flipagram['video'] + + json_ld = self._search_json_ld(webpage, video_id, default=False) + title = json_ld.get('title') or flipagram['captionText'] + description = json_ld.get('description') or flipagram.get('captionText') + + formats = [{ + 'url': video['url'], + 'width': int_or_none(video.get('width')), + 'height': int_or_none(video.get('height')), + 'filesize': int_or_none(video_data.get('size')), + }] + + preview_url = try_get( + flipagram, lambda x: x['music']['track']['previewUrl'], compat_str) + if preview_url: + formats.append({ + 'url': preview_url, + 'ext': 'm4a', + 'vcodec': 'none', + }) + + self._sort_formats(formats) + + counts = flipagram.get('counts', {}) + user = flipagram.get('user', {}) + video_data = flipagram.get('video', {}) + + thumbnails = [{ + 'url': self._proto_relative_url(cover['url']), + 'width': int_or_none(cover.get('width')), + 'height': int_or_none(cover.get('height')), + 'filesize': int_or_none(cover.get('size')), + } for cover in flipagram.get('covers', []) if cover.get('url')] + + # Note that this only retrieves comments that are initally loaded. + # For videos with large amounts of comments, most won't be retrieved. + comments = [] + for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []): + text = comment.get('comment') + if not text or not isinstance(text, list): + continue + comments.append({ + 'author': comment.get('user', {}).get('name'), + 'author_id': comment.get('user', {}).get('username'), + 'id': comment.get('id'), + 'text': text[0], + 'timestamp': unified_timestamp(comment.get('created')), + }) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': float_or_none(flipagram.get('duration'), 1000), + 'thumbnails': thumbnails, + 'timestamp': unified_timestamp(flipagram.get('iso8601Created')), + 'uploader': user.get('name'), + 'uploader_id': user.get('username'), + 'creator': user.get('name'), + 'view_count': int_or_none(counts.get('plays')), + 'like_count': int_or_none(counts.get('likes')), + 'repost_count': int_or_none(counts.get('reflips')), + 'comment_count': int_or_none(counts.get('comments')), + 'comments': comments, + 'formats': formats, + } diff --git a/youtube_dl/extractor/formula1.py b/youtube_dl/extractor/formula1.py new file mode 100644 index 000000000..322c41e5a --- /dev/null +++ b/youtube_dl/extractor/formula1.py @@ -0,0 +1,26 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class Formula1IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?formula1\.com/content/fom-website/en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html' + _TEST = { + 'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html', + 'md5': '8c79e54be72078b26b89e0e111c0502b', + 'info_dict': { + 'id': 'JvYXJpMzE6pArfHWm5ARp5AiUmD-gibV', + 'ext': 'flv', + 'title': 'Race highlights - Spain 2016', + }, + 'add_ie': ['Ooyala'], + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + ooyala_embed_code = self._search_regex( + r'data-videoid="([^"]+)"', webpage, 'ooyala embed code') + return self.url_result( + 'ooyala:%s' % ooyala_embed_code, 'Ooyala', ooyala_embed_code) diff --git a/youtube_dl/extractor/foxsports.py b/youtube_dl/extractor/foxsports.py index df7665176..a3bb98377 100644 --- a/youtube_dl/extractor/foxsports.py +++ b/youtube_dl/extractor/foxsports.py @@ -1,7 +1,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import smuggle_url +from ..utils import ( + smuggle_url, + update_url_query, +) class FoxSportsIE(InfoExtractor): @@ -9,11 +12,15 @@ class FoxSportsIE(InfoExtractor): _TEST = { 'url': 'http://www.foxsports.com/video?vid=432609859715', + 'md5': 'b49050e955bebe32c301972e4012ac17', 'info_dict': { - 'id': 'gA0bHB3Ladz3', - 'ext': 'flv', + 'id': 'i0qKWsk3qJaM', + 'ext': 'mp4', 'title': 'Courtney Lee on going up 2-0 in series vs. Blazers', 'description': 'Courtney Lee talks about Memphis being focused.', + 'upload_date': '20150423', + 'timestamp': 1429761109, + 'uploader': 'NEWA-FNG-FOXSPORTS', }, 'add_ie': ['ThePlatform'], } @@ -28,5 +35,8 @@ class FoxSportsIE(InfoExtractor): r"data-player-config='([^']+)'", webpage, 'data player config'), video_id) - return self.url_result(smuggle_url( - config['releaseURL'] + '&manifest=f4m', {'force_smil_url': True})) + return self.url_result(smuggle_url(update_url_query( + config['releaseURL'], { + 'mbr': 'true', + 'switch': 'http', + }), {'force_smil_url': True})) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index ad94e31f3..7653975e3 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -14,7 +14,10 @@ from ..utils import ( parse_duration, determine_ext, ) -from .dailymotion import DailymotionCloudIE +from .dailymotion import ( + DailymotionIE, + DailymotionCloudIE, +) class FranceTVBaseInfoExtractor(InfoExtractor): @@ -188,6 +191,21 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): 'params': { 'skip_download': True, }, + }, { + # Dailymotion embed + 'url': 'http://www.francetvinfo.fr/politique/notre-dame-des-landes/video-sur-france-inter-cecile-duflot-denonce-le-regard-meprisant-de-patrick-cohen_1520091.html', + 'md5': 'ee7f1828f25a648addc90cb2687b1f12', + 'info_dict': { + 'id': 'x4iiko0', + 'ext': 'mp4', + 'title': 'NDDL, référendum, Brexit : Cécile Duflot répond à Patrick Cohen', + 'description': 'Au lendemain de la victoire du "oui" au référendum sur l\'aéroport de Notre-Dame-des-Landes, l\'ancienne ministre écologiste est l\'invitée de Patrick Cohen. Plus d\'info : https://www.franceinter.fr/emissions/le-7-9/le-7-9-27-juin-2016', + 'timestamp': 1467011958, + 'upload_date': '20160627', + 'uploader': 'France Inter', + 'uploader_id': 'x2q2ez', + }, + 'add_ie': ['Dailymotion'], }] def _real_extract(self, url): @@ -197,7 +215,13 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) if dmcloud_url: - return self.url_result(dmcloud_url, 'DailymotionCloud') + return self.url_result(dmcloud_url, DailymotionCloudIE.ie_key()) + + dailymotion_urls = DailymotionIE._extract_urls(webpage) + if dailymotion_urls: + return self.playlist_result([ + self.url_result(dailymotion_url, DailymotionIE.ie_key()) + for dailymotion_url in dailymotion_urls]) video_id, catalogue = self._search_regex( (r'id-video=([^@]+@[^"]+)', diff --git a/youtube_dl/extractor/fusion.py b/youtube_dl/extractor/fusion.py new file mode 100644 index 000000000..b4ab4cbb7 --- /dev/null +++ b/youtube_dl/extractor/fusion.py @@ -0,0 +1,35 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from .ooyala import OoyalaIE + + +class FusionIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fusion\.net/video/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://fusion.net/video/201781/u-s-and-panamanian-forces-work-together-to-stop-a-vessel-smuggling-drugs/', + 'info_dict': { + 'id': 'ZpcWNoMTE6x6uVIIWYpHh0qQDjxBuq5P', + 'ext': 'mp4', + 'title': 'U.S. and Panamanian forces work together to stop a vessel smuggling drugs', + 'description': 'md5:0cc84a9943c064c0f46b128b41b1b0d7', + 'duration': 140.0, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Ooyala'], + }, { + 'url': 'http://fusion.net/video/201781', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + ooyala_code = self._search_regex( + r'data-video-id=(["\'])(?P<code>.+?)\1', + webpage, 'ooyala code', group='code') + + return OoyalaIE._build_url_result(ooyala_code) diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 4ffdd7515..4e859e09a 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -1,19 +1,19 @@ from __future__ import unicode_literals import re -import json -from .common import InfoExtractor +from .once import OnceIE from ..compat import ( compat_urllib_parse_unquote, - compat_urlparse, ) from ..utils import ( unescapeHTML, + url_basename, + dict_get, ) -class GameSpotIE(InfoExtractor): +class GameSpotIE(OnceIE): _VALID_URL = r'https?://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?' _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', @@ -28,10 +28,13 @@ class GameSpotIE(InfoExtractor): 'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/', 'info_dict': { 'id': 'gs-2300-6424837', - 'ext': 'flv', - 'title': 'The Witcher 3: Wild Hunt [Xbox ONE] - Now Playing', + 'ext': 'mp4', + 'title': 'Now Playing - The Witcher 3: Wild Hunt', 'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.', }, + 'params': { + 'skip_download': True, # m3u8 downloads + }, }] def _real_extract(self, url): @@ -39,29 +42,73 @@ class GameSpotIE(InfoExtractor): webpage = self._download_webpage(url, page_id) data_video_json = self._search_regex( r'data-video=["\'](.*?)["\']', webpage, 'data video') - data_video = json.loads(unescapeHTML(data_video_json)) + data_video = self._parse_json(unescapeHTML(data_video_json), page_id) streams = data_video['videoStreams'] + manifest_url = None formats = [] f4m_url = streams.get('f4m_stream') - if f4m_url is not None: - # Transform the manifest url to a link to the mp4 files - # they are used in mobile devices. - f4m_path = compat_urlparse.urlparse(f4m_url).path - QUALITIES_RE = r'((,\d+)+,?)' - qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',') - http_path = f4m_path[1:].split('/', 1)[1] - http_template = re.sub(QUALITIES_RE, r'%s', http_path) - http_template = http_template.replace('.csmil/manifest.f4m', '') - http_template = compat_urlparse.urljoin( - 'http://video.gamespotcdn.com/', http_template) - for q in qualities: - formats.append({ - 'url': http_template % q, - 'ext': 'mp4', - 'format_id': q, - }) - else: + if f4m_url: + manifest_url = f4m_url + formats.extend(self._extract_f4m_formats( + f4m_url + '?hdcore=3.7.0', page_id, f4m_id='hds', fatal=False)) + m3u8_url = streams.get('m3u8_stream') + if m3u8_url: + manifest_url = m3u8_url + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, page_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + formats.extend(m3u8_formats) + progressive_url = dict_get( + streams, ('progressive_hd', 'progressive_high', 'progressive_low')) + if progressive_url and manifest_url: + qualities_basename = self._search_regex( + '/([^/]+)\.csmil/', + manifest_url, 'qualities basename', default=None) + if qualities_basename: + QUALITIES_RE = r'((,\d+)+,?)' + qualities = self._search_regex( + QUALITIES_RE, qualities_basename, + 'qualities', default=None) + if qualities: + qualities = list(map(lambda q: int(q), qualities.strip(',').split(','))) + qualities.sort() + http_template = re.sub(QUALITIES_RE, r'%d', qualities_basename) + http_url_basename = url_basename(progressive_url) + if m3u8_formats: + self._sort_formats(m3u8_formats) + m3u8_formats = list(filter( + lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', + m3u8_formats)) + if len(qualities) == len(m3u8_formats): + for q, m3u8_format in zip(qualities, m3u8_formats): + f = m3u8_format.copy() + f.update({ + 'url': progressive_url.replace( + http_url_basename, http_template % q), + 'format_id': f['format_id'].replace('hls', 'http'), + 'protocol': 'http', + }) + formats.append(f) + else: + for q in qualities: + formats.append({ + 'url': progressive_url.replace( + http_url_basename, http_template % q), + 'ext': 'mp4', + 'format_id': 'http-%d' % q, + 'tbr': q, + }) + + onceux_json = self._search_regex( + r'data-onceux-options=["\'](.*?)["\']', webpage, 'data video', default=None) + if onceux_json: + onceux_url = self._parse_json(unescapeHTML(onceux_json), page_id).get('metadataUri') + if onceux_url: + formats.extend(self._extract_once_formats(re.sub( + r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url).replace('ads/vmap/', ''))) + + if not formats: for quality in ['sd', 'hd']: # It's actually a link to a flv file flv_url = streams.get('f4m_{0}'.format(quality)) @@ -71,6 +118,7 @@ class GameSpotIE(InfoExtractor): 'ext': 'flv', 'format_id': quality, }) + self._sort_formats(formats) return { 'id': data_video['guid'], diff --git a/youtube_dl/extractor/gametrailers.py b/youtube_dl/extractor/gametrailers.py deleted file mode 100644 index 1e7948ab8..000000000 --- a/youtube_dl/extractor/gametrailers.py +++ /dev/null @@ -1,62 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - parse_age_limit, - url_basename, -) - - -class GametrailersIE(InfoExtractor): - _VALID_URL = r'https?://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)' - - _TEST = { - 'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review', - 'md5': 'f28c4efa0bdfaf9b760f6507955b6a6a', - 'info_dict': { - 'id': '2983958', - 'ext': 'mp4', - 'display_id': '116437-Just-Cause-3-Review', - 'title': 'Just Cause 3 - Review', - 'description': 'It\'s a lot of fun to shoot at things and then watch them explode in Just Cause 3, but should there be more to the experience than that?', - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - title = self._html_search_regex( - r'<title>(.+?)\|', webpage, 'title').strip() - embed_url = self._proto_relative_url( - self._search_regex( - r'src=\'(//embed.gametrailers.com/embed/[^\']+)\'', webpage, - 'embed url'), - scheme='http:') - video_id = url_basename(embed_url) - embed_page = self._download_webpage(embed_url, video_id) - embed_vars_json = self._search_regex( - r'(?s)var embedVars = (\{.*?\})\s*</script>', embed_page, - 'embed vars') - info = self._parse_json(embed_vars_json, video_id) - - formats = [] - for media in info['media']: - if media['mediaPurpose'] == 'play': - formats.append({ - 'url': media['uri'], - 'height': media['height'], - 'width:': media['width'], - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'formats': formats, - 'thumbnail': info.get('thumbUri'), - 'description': self._og_search_description(webpage), - 'duration': int_or_none(info.get('videoLengthInSeconds')), - 'age_limit': parse_age_limit(info.get('audienceRating')), - } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 0f1eb7fa6..5364f0b19 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -49,7 +49,10 @@ from .pornhub import PornHubIE from .xhamster import XHamsterEmbedIE from .tnaflix import TNAFlixNetworkEmbedIE from .vimeo import VimeoIE -from .dailymotion import DailymotionCloudIE +from .dailymotion import ( + DailymotionIE, + DailymotionCloudIE, +) from .onionstudios import OnionStudiosIE from .viewlift import ViewLiftEmbedIE from .screenwavemedia import ScreenwaveMediaIE @@ -59,8 +62,16 @@ from .videomore import VideomoreIE from .googledrive import GoogleDriveIE from .jwplatform import JWPlatformIE from .digiteka import DigitekaIE +from .arkena import ArkenaIE from .instagram import InstagramIE from .liveleak import LiveLeakIE +from .threeqsdn import ThreeQSDNIE +from .theplatform import ThePlatformIE +from .vessel import VesselIE +from .kaltura import KalturaIE +from .eagleplatform import EaglePlatformIE +from .facebook import FacebookIE +from .soundcloud import SoundcloudIE class GenericIE(InfoExtractor): @@ -464,7 +475,7 @@ class GenericIE(InfoExtractor): 'url': 'http://www.vestifinance.ru/articles/25753', 'info_dict': { 'id': '25753', - 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"', + 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"', }, 'playlist': [{ 'info_dict': { @@ -624,13 +635,15 @@ class GenericIE(InfoExtractor): }, # MTVSercices embed { - 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too', - 'md5': '35727f82f58c76d996fc188f9755b0d5', + 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html', + 'md5': 'ca1aef97695ef2c1d6973256a57e5252', 'info_dict': { - 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9', + 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1', 'ext': 'mp4', - 'title': 'Review', - 'description': 'Mario\'s life in the fast lane has never looked so good.', + 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored', + 'description': 'Two valets share their love for movie star Liam Neesons.', + 'timestamp': 1349922600, + 'upload_date': '20121011', }, }, # YouTube embed via <data-embed-url=""> @@ -716,15 +729,18 @@ class GenericIE(InfoExtractor): }, # Wistia embed { - 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', - 'md5': '8788b683c777a5cf25621eaf286d0c23', + 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', + 'md5': '1953f3a698ab51cfc948ed3992a0b7ff', 'info_dict': { - 'id': '1cfaf6b7ea', + 'id': '6e2wtrbdaf', 'ext': 'mov', - 'title': 'md5:51364a8d3d009997ba99656004b5e20d', - 'duration': 643.0, - 'filesize': 182808282, - 'uploader': 'education-portal.com', + 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england', + 'description': 'a Paywall Videos video from Remilon', + 'duration': 644.072, + 'uploader': 'study.com', + 'timestamp': 1459678540, + 'upload_date': '20160403', + 'filesize': 24687186, }, }, { @@ -733,14 +749,30 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': 'uxjb0lwrcz', 'ext': 'mp4', - 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', + 'title': 'Conversation about Hexagonal Rails Part 1', 'description': 'a Martin Fowler video from ThoughtWorks', 'duration': 1715.0, 'uploader': 'thoughtworks.wistia.com', - 'upload_date': '20140603', 'timestamp': 1401832161, + 'upload_date': '20140603', }, }, + # Wistia standard embed (async) + { + 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/', + 'info_dict': { + 'id': '807fafadvk', + 'ext': 'mp4', + 'title': 'Drip Brennan Dunn Workshop', + 'description': 'a JV Webinars video from getdrip-1', + 'duration': 4986.95, + 'timestamp': 1463607249, + 'upload_date': '20160518', + }, + 'params': { + 'skip_download': True, + } + }, # Soundcloud embed { 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/', @@ -753,6 +785,15 @@ class GenericIE(InfoExtractor): 'upload_date': '20141029', } }, + # Soundcloud multiple embeds + { + 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809', + 'info_dict': { + 'id': '52809', + 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO', + }, + 'playlist_mincount': 7, + }, # Livestream embed { 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast', @@ -763,6 +804,19 @@ class GenericIE(InfoExtractor): 'title': 'Rosetta #CometLanding webcast HL 10', } }, + # Another Livestream embed, without 'new.' in URL + { + 'url': 'https://www.freespeech.org/', + 'info_dict': { + 'id': '123537347', + 'ext': 'mp4', + 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + }, + 'params': { + # Live stream + 'skip_download': True, + }, + }, # LazyYT { 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986', @@ -815,6 +869,7 @@ class GenericIE(InfoExtractor): 'description': 'md5:601cb790edd05908957dae8aaa866465', 'upload_date': '20150220', }, + 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/', }, # jwplayer YouTube { @@ -847,18 +902,6 @@ class GenericIE(InfoExtractor): 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !', } }, - # Kaltura embed - { - 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15', - 'info_dict': { - 'id': '1_eergr3h1', - 'ext': 'mp4', - 'upload_date': '20150226', - 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com', - 'timestamp': int, - 'title': 'John Carlson Postgame 2/25/15', - }, - }, # Kaltura embed (different embed code) { 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014', @@ -884,6 +927,37 @@ class GenericIE(InfoExtractor): 'uploader_id': 'echojecka', }, }, + # Kaltura embed with single quotes + { + 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY', + 'info_dict': { + 'id': '0_izeg5utt', + 'ext': 'mp4', + 'title': '35871', + 'timestamp': 1355743100, + 'upload_date': '20121217', + 'uploader_id': 'batchUser', + }, + 'add_ie': ['Kaltura'], + }, + { + # Kaltura embedded via quoted entry_id + 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures', + 'info_dict': { + 'id': '0_utuok90b', + 'ext': 'mp4', + 'title': '06_matthew_brender_raj_dutt', + 'timestamp': 1466638791, + 'upload_date': '20160622', + }, + 'add_ie': ['Kaltura'], + 'expected_warnings': [ + 'Could not send HEAD request' + ], + 'params': { + 'skip_download': True, + } + }, # Eagle.Platform embed (generic URL) { 'url': 'http://lenta.ru/news/2015/03/06/navalny/', @@ -996,16 +1070,31 @@ class GenericIE(InfoExtractor): 'timestamp': 1389118457, }, }, + # NBC News embed + { + 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html', + 'md5': '1aa589c675898ae6d37a17913cf68d66', + 'info_dict': { + 'id': '701714499682', + 'ext': 'mp4', + 'title': 'PREVIEW: On Assignment: David Letterman', + 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.', + }, + }, # UDN embed { - 'url': 'http://www.udn.com/news/story/7314/822787', + 'url': 'https://video.udn.com/news/300346', 'md5': 'fd2060e988c326991037b9aff9df21a6', 'info_dict': { 'id': '300346', 'ext': 'mp4', 'title': '中一中男師變性 全校師生力挺', 'thumbnail': 're:^https?://.*\.jpg$', - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, # Ooyala embed { @@ -1022,20 +1111,6 @@ class GenericIE(InfoExtractor): 'skip_download': True, } }, - # Contains a SMIL manifest - { - 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html', - 'info_dict': { - 'id': 'file', - 'ext': 'flv', - 'title': '+ Football: Lottery Champions League Europe', - 'uploader': 'www.telewebion.com', - }, - 'params': { - # rtmpe downloads - 'skip_download': True, - } - }, # Brightcove URL in single quotes { 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/', @@ -1054,12 +1129,17 @@ class GenericIE(InfoExtractor): # Dailymotion Cloud video { 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910', - 'md5': '49444254273501a64675a7e68c502681', + 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38', 'info_dict': { - 'id': '5585de919473990de4bee11b', + 'id': 'x2uy8t3', 'ext': 'mp4', - 'title': 'Le débat', + 'title': 'Sauvons les abeilles ! - Le débat', + 'description': 'md5:d9082128b1c5277987825d684939ca26', 'thumbnail': 're:^https?://.*\.jpe?g$', + 'timestamp': 1434970506, + 'upload_date': '20150622', + 'uploader': 'Public Sénat', + 'uploader_id': 'xa9gza', } }, # OnionStudios embed @@ -1173,6 +1253,143 @@ class GenericIE(InfoExtractor): 'uploader': 'Lake8737', } }, + # Duplicated embedded video URLs + { + 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443', + 'info_dict': { + 'id': '149298443_480_16c25b74_2', + 'ext': 'mp4', + 'title': 'vs. Blue Orange Spring Game', + 'uploader': 'www.hudl.com', + }, + }, + # twitter:player:stream embed + { + 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288', + 'info_dict': { + 'id': 'master', + 'ext': 'mp4', + 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine', + 'uploader': 'www.rtl.be', + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + }, + }, + # twitter:player embed + { + 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/', + 'md5': 'a3e0df96369831de324f0778e126653c', + 'info_dict': { + 'id': '4909620399001', + 'ext': 'mp4', + 'title': 'What Do Black Holes Sound Like?', + 'description': 'what do black holes sound like', + 'upload_date': '20160524', + 'uploader_id': '29913724001', + 'timestamp': 1464107587, + 'uploader': 'TheAtlantic', + }, + 'add_ie': ['BrightcoveLegacy'], + }, + # Facebook <iframe> embed + { + 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html', + 'md5': 'fbcde74f534176ecb015849146dd3aee', + 'info_dict': { + 'id': '599637780109885', + 'ext': 'mp4', + 'title': 'Facebook video #599637780109885', + }, + }, + # Facebook API embed + { + 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/', + 'md5': 'a47372ee61b39a7b90287094d447d94e', + 'info_dict': { + 'id': '10153467542406923', + 'ext': 'mp4', + 'title': 'Facebook video #10153467542406923', + }, + }, + # Wordpress "YouTube Video Importer" plugin + { + 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/', + 'md5': 'd16797741b560b485194eddda8121b48', + 'info_dict': { + 'id': 'HNTXWDXV9Is', + 'ext': 'mp4', + 'title': 'Blue Devils Drumline Stanford lot 2016', + 'upload_date': '20160627', + 'uploader_id': 'GENOCIDE8GENERAL10', + 'uploader': 'cylus cyrus', + }, + }, + { + # video stored on custom kaltura server + 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv', + 'md5': '537617d06e64dfed891fa1593c4b30cc', + 'info_dict': { + 'id': '0_1iotm5bh', + 'ext': 'mp4', + 'title': 'Elecciones británicas: 5 lecciones para Rajoy', + 'description': 'md5:435a89d68b9760b92ce67ed227055f16', + 'uploader_id': 'videos.expansion@el-mundo.net', + 'upload_date': '20150429', + 'timestamp': 1430303472, + }, + 'add_ie': ['Kaltura'], + }, + { + # Non-standard Vimeo embed + 'url': 'https://openclassrooms.com/courses/understanding-the-web', + 'md5': '64d86f1c7d369afd9a78b38cbb88d80a', + 'info_dict': { + 'id': '148867247', + 'ext': 'mp4', + 'title': 'Understanding the web - Teaser', + 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.', + 'upload_date': '20151214', + 'uploader': 'OpenClassrooms', + 'uploader_id': 'openclassrooms', + }, + 'add_ie': ['Vimeo'], + }, + { + 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video', + 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365', + 'info_dict': { + 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe', + 'ext': 'mp4', + 'title': 'Big Buck Bunny', + 'description': 'Royalty free test video', + 'timestamp': 1432816365, + 'upload_date': '20150528', + 'is_live': False, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [ArkenaIE.ie_key()], + }, + # { + # # TODO: find another test + # # http://schema.org/VideoObject + # 'url': 'https://flipagram.com/f/nyvTSJMKId', + # 'md5': '888dcf08b7ea671381f00fab74692755', + # 'info_dict': { + # 'id': 'nyvTSJMKId', + # 'ext': 'mp4', + # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction', + # 'description': '#love for cats.', + # 'timestamp': 1461244995, + # 'upload_date': '20160421', + # }, + # 'params': { + # 'force_generic_extractor': True, + # }, + # } ] def report_following_redirect(self, new_url): @@ -1427,7 +1644,8 @@ class GenericIE(InfoExtractor): # Site Name | Video Title # Video Title - Tagline | Site Name # and so on and so forth; it's just not practical - video_title = self._html_search_regex( + video_title = self._og_search_title( + webpage, default=None) or self._html_search_regex( r'(?s)<title>(.*?)', webpage, 'video title', default='video') @@ -1445,6 +1663,9 @@ class GenericIE(InfoExtractor): video_uploader = self._search_regex( r'^(?:https?://)?([^/]*)/.*', url, 'video uploader') + video_description = self._og_search_description(webpage, default=None) + video_thumbnail = self._og_search_thumbnail(webpage, default=None) + # Helper method def _playlist_from_matches(matches, getter=None, ie=None): urlrs = orderedSet( @@ -1475,6 +1696,16 @@ class GenericIE(InfoExtractor): if bc_urls: return _playlist_from_matches(bc_urls, ie='BrightcoveNew') + # Look for ThePlatform embeds + tp_urls = ThePlatformIE._extract_urls(webpage) + if tp_urls: + return _playlist_from_matches(tp_urls, ie='ThePlatform') + + # Look for Vessel embeds + vessel_urls = VesselIE._extract_urls(webpage) + if vessel_urls: + return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key()) + # Look for embedded rtl.nl player matches = re.findall( r']+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"', @@ -1515,12 +1746,16 @@ class GenericIE(InfoExtractor): if matches: return _playlist_from_matches(matches, lambda m: unescapeHTML(m)) - # Look for embedded Dailymotion player - matches = re.findall( - r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) + # Look for Wordpress "YouTube Video Importer" plugin + matches = re.findall(r'''(?x)]+ + class=(?P[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ + data-video_id=(?P[\'"])([^\'"]+)(?P=q2)''', webpage) if matches: - return _playlist_from_matches( - matches, lambda m: unescapeHTML(m[1])) + return _playlist_from_matches(matches, lambda m: m[-1]) + + matches = DailymotionIE._extract_urls(webpage) + if matches: + return _playlist_from_matches(matches) # Look for embedded Dailymotion playlist player (#3822) m = re.search( @@ -1543,21 +1778,26 @@ class GenericIE(InfoExtractor): 'url': embed_url, 'ie_key': 'Wistia', 'uploader': video_uploader, - 'title': video_title, - 'id': video_id, } match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P[^"\']+)', webpage) if match: return { '_type': 'url_transparent', - 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), + 'url': 'wistia:%s' % match.group('id'), 'ie_key': 'Wistia', 'uploader': video_uploader, - 'title': video_title, - 'id': match.group('id') } + match = re.search( + r'''(?sx) + ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? + ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]+)\b.*?\2 + ''', webpage) + if match: + return self.url_result(self._proto_relative_url( + 'wistia:%s' % match.group('id')), 'Wistia') + # Look for SVT player svt_url = SVTIE._extract_url(webpage) if svt_url: @@ -1652,10 +1892,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url')) # Look for embedded Facebook player - mobj = re.search( - r']+?src=(["\'])(?Phttps://www\.facebook\.com/video/embed.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Facebook') + facebook_url = FacebookIE._extract_url(webpage) + if facebook_url is not None: + return self.url_result(facebook_url, 'Facebook') # Look for embedded VK player mobj = re.search(r']+?src=(["\'])(?Phttps?://vk\.com/video_ext\.php.+?)\1', webpage) @@ -1770,20 +2009,9 @@ class GenericIE(InfoExtractor): return self.url_result(myvi_url) # Look for embedded soundcloud player - mobj = re.search( - r'https?://(?:w\.)?soundcloud\.com/player[^"]+)"', - webpage) - if mobj is not None: - url = unescapeHTML(mobj.group('url')) - return self.url_result(url) - - # Look for embedded vulture.com player - mobj = re.search( - r'