diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 27257ee0a..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 *2016.07.28*. 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 Issues with outdated version will be rejected.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 **2016.07.28** +### 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 Issues with outdated version will be rejected.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 2016.07.28 +[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/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 6ee4ba4eb..354052c50 100644 --- a/Makefile +++ b/Makefile @@ -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 a9f3001a6..640625212 100644 --- a/README.md +++ b/README.md @@ -424,7 +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 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\\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself. +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/youtube-dl.conf`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\\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: ``` diff --git a/devscripts/release.sh b/devscripts/release.sh index f8d466ba8..ca6ae1b49 100755 --- a/devscripts/release.sh +++ b/devscripts/release.sh @@ -71,9 +71,12 @@ 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//$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 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..." diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 88e8ff904..a98305c74 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -48,6 +48,9 @@ class TestInfoExtractor(unittest.TestCase): self.assertEqual(ie._og_search_property('foobar', html), 'Foo') self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar') self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar') + self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar') + self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True) + self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True) def test_html_search_meta(self): ie = self.ie diff --git a/test/test_verbose_output.py b/test/test_verbose_output.py new file mode 100644 index 000000000..4c77df242 --- /dev/null +++ b/test/test_verbose_output.py @@ -0,0 +1,70 @@ +#!/usr/bin/env python +# coding: utf-8 + +from __future__ import unicode_literals + +import unittest + +import sys +import os +import subprocess +sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) + +rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + + +class TestVerboseOutput(unittest.TestCase): + def test_private_info_arg(self): + outp = subprocess.Popen( + [ + sys.executable, 'youtube_dl/__main__.py', '-v', + '--username', 'johnsmith@gmail.com', + '--password', 'secret', + ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + sout, serr = outp.communicate() + self.assertTrue('--username' in serr) + self.assertTrue('johnsmith' not in serr) + self.assertTrue('--password' in serr) + self.assertTrue('secret' not in serr) + + def test_private_info_shortarg(self): + outp = subprocess.Popen( + [ + sys.executable, 'youtube_dl/__main__.py', '-v', + '-u', 'johnsmith@gmail.com', + '-p', 'secret', + ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + sout, serr = outp.communicate() + self.assertTrue('-u' in serr) + self.assertTrue('johnsmith' not in serr) + self.assertTrue('-p' in serr) + self.assertTrue('secret' not in serr) + + def test_private_info_eq(self): + outp = subprocess.Popen( + [ + sys.executable, 'youtube_dl/__main__.py', '-v', + '--username=johnsmith@gmail.com', + '--password=secret', + ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + sout, serr = outp.communicate() + self.assertTrue('--username' in serr) + self.assertTrue('johnsmith' not in serr) + self.assertTrue('--password' in serr) + self.assertTrue('secret' not in serr) + + def test_private_info_shortarg_eq(self): + outp = subprocess.Popen( + [ + sys.executable, 'youtube_dl/__main__.py', '-v', + '-u=johnsmith@gmail.com', + '-p=secret', + ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + sout, serr = outp.communicate() + self.assertTrue('-u' in serr) + self.assertTrue('johnsmith' not in serr) + self.assertTrue('-p' in serr) + self.assertTrue('secret' not in serr) + +if __name__ == '__main__': + unittest.main() 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.+?)\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$', '', self._og_search_title(webpage)) embed_info = self._download_json( diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py index c76909e48..88346dde7 100644 --- a/youtube_dl/extractor/comedycentral.py +++ b/youtube_dl/extractor/comedycentral.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .mtv import MTVServicesInfoExtractor +from .common import InfoExtractor class ComedyCentralIE(MTVServicesInfoExtractor): @@ -96,3 +97,22 @@ class ComedyCentralTVIE(MTVServicesInfoExtractor): webpage, 'mrss url', group='url') return self._get_videos_info_from_url(mrss_url, video_id) + + +class ComedyCentralShortnameIE(InfoExtractor): + _VALID_URL = r'^:(?Ptds|thedailyshow)$' + _TESTS = [{ + 'url': ':tds', + 'only_matching': True, + }, { + 'url': ':thedailyshow', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + shortcut_map = { + 'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', + 'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', + } + return self.url_result(shortcut_map[video_id]) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 53c28f016..3b6a5491d 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -727,9 +727,14 @@ class InfoExtractor(object): [^>]+?content=(["\'])(?P.*?)\2''' % re.escape(prop) def _og_search_property(self, prop, html, name=None, **kargs): + if not isinstance(prop, (list, tuple)): + prop = [prop] if name is None: - name = 'OpenGraph %s' % prop - escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs) + name = 'OpenGraph %s' % prop[0] + og_regexes = [] + for p in prop: + og_regexes.extend(self._og_regexes(p)) + escaped = self._search_regex(og_regexes, html, name, flags=re.DOTALL, **kargs) if escaped is None: return None return unescapeHTML(escaped) 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[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[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/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 1f92823b7..496883d15 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -331,7 +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/extractors.py b/youtube_dl/extractor/extractors.py index 53fab1a31..86c48ff54 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -159,6 +159,7 @@ from .coub import CoubIE from .collegerama import CollegeRamaIE from .comedycentral import ( ComedyCentralIE, + ComedyCentralShortnameIE, ComedyCentralTVIE, ToshIE, ) diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 5d2c3e256..efe1437e0 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -37,11 +37,12 @@ class LimelightBaseIE(InfoExtractor): for stream in streams: stream_url = stream.get('url') - if not stream_url: + if not stream_url or stream.get('drmProtected'): continue - if '.f4m' in stream_url: + ext = determine_ext(stream_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( - stream_url, video_id, fatal=False)) + stream_url, video_id, f4m_id='hds', fatal=False)) else: fmt = { 'url': stream_url, @@ -50,7 +51,7 @@ class LimelightBaseIE(InfoExtractor): 'fps': float_or_none(stream.get('videoFrameRate')), 'width': int_or_none(stream.get('videoWidthInPixels')), 'height': int_or_none(stream.get('videoHeightInPixels')), - 'ext': determine_ext(stream_url) + 'ext': ext, } rtmp = re.search(r'^(?Prtmpe?://[^/]+/(?P.+))/(?Pmp4:.+)$', stream_url) if rtmp: @@ -68,18 +69,23 @@ class LimelightBaseIE(InfoExtractor): for mobile_url in mobile_urls: media_url = mobile_url.get('mobileUrl') - if not media_url: - continue format_id = mobile_url.get('targetMediaPlatform') - if determine_ext(media_url) == 'm3u8': + if not media_url or format_id == 'Widevine': + continue + ext = determine_ext(media_url) + if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( media_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False)) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + stream_url, video_id, f4m_id=format_id, fatal=False)) else: formats.append({ 'url': media_url, 'format_id': format_id, 'preference': -1, + 'ext': ext, }) self._sort_formats(formats) @@ -145,7 +151,7 @@ class LimelightMediaIE(LimelightBaseIE): 'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86', 'info_dict': { 'id': '3ffd040b522b4485b6d84effc750cd86', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'HaP and the HB Prince Trailer', 'description': 'md5:8005b944181778e313d95c1237ddb640', 'thumbnail': 're:^https?://.*\.jpeg$', @@ -154,7 +160,7 @@ class LimelightMediaIE(LimelightBaseIE): 'upload_date': '20090604', }, 'params': { - # rtmp download + # m3u8 download 'skip_download': True, }, }, { @@ -164,7 +170,6 @@ class LimelightMediaIE(LimelightBaseIE): 'id': 'a3e00274d4564ec4a9b29b9466432335', 'ext': 'flv', 'title': '3Play Media Overview Video', - 'description': '', 'thumbnail': 're:^https?://.*\.jpeg$', 'duration': 78.101, 'timestamp': 1338929955, diff --git a/youtube_dl/extractor/ntvru.py b/youtube_dl/extractor/ntvru.py index 0895d7ea4..e8702ebcd 100644 --- a/youtube_dl/extractor/ntvru.py +++ b/youtube_dl/extractor/ntvru.py @@ -11,70 +11,64 @@ from ..utils import ( class NTVRuIE(InfoExtractor): IE_NAME = 'ntv.ru' - _VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?P.+)' + _VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?:[^/]+/)*(?P[^/?#&]+)' - _TESTS = [ - { - 'url': 'http://www.ntv.ru/novosti/863142/', - 'md5': 'ba7ea172a91cb83eb734cad18c10e723', - 'info_dict': { - 'id': '746000', - 'ext': 'mp4', - 'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', - 'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', - 'thumbnail': 're:^http://.*\.jpg', - 'duration': 136, - }, + _TESTS = [{ + 'url': 'http://www.ntv.ru/novosti/863142/', + 'md5': 'ba7ea172a91cb83eb734cad18c10e723', + 'info_dict': { + 'id': '746000', + 'ext': 'mp4', + 'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', + 'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины', + 'thumbnail': 're:^http://.*\.jpg', + 'duration': 136, }, - { - 'url': 'http://www.ntv.ru/video/novosti/750370/', - 'md5': 'adecff79691b4d71e25220a191477124', - 'info_dict': { - 'id': '750370', - 'ext': 'mp4', - 'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', - 'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', - 'thumbnail': 're:^http://.*\.jpg', - 'duration': 172, - }, + }, { + 'url': 'http://www.ntv.ru/video/novosti/750370/', + 'md5': 'adecff79691b4d71e25220a191477124', + 'info_dict': { + 'id': '750370', + 'ext': 'mp4', + 'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', + 'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход', + 'thumbnail': 're:^http://.*\.jpg', + 'duration': 172, }, - { - 'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416', - 'md5': '82dbd49b38e3af1d00df16acbeab260c', - 'info_dict': { - 'id': '747480', - 'ext': 'mp4', - 'title': '«Сегодня». 21 марта 2014 года. 16:00', - 'description': '«Сегодня». 21 марта 2014 года. 16:00', - 'thumbnail': 're:^http://.*\.jpg', - 'duration': 1496, - }, + }, { + 'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416', + 'md5': '82dbd49b38e3af1d00df16acbeab260c', + 'info_dict': { + 'id': '747480', + 'ext': 'mp4', + 'title': '«Сегодня». 21 марта 2014 года. 16:00', + 'description': '«Сегодня». 21 марта 2014 года. 16:00', + 'thumbnail': 're:^http://.*\.jpg', + 'duration': 1496, }, - { - 'url': 'http://www.ntv.ru/kino/Koma_film', - 'md5': 'f825770930937aa7e5aca0dc0d29319a', - 'info_dict': { - 'id': '1007609', - 'ext': 'mp4', - 'title': 'Остросюжетный фильм «Кома»', - 'description': 'Остросюжетный фильм «Кома»', - 'thumbnail': 're:^http://.*\.jpg', - 'duration': 5592, - }, + }, { + 'url': 'http://www.ntv.ru/kino/Koma_film', + 'md5': 'f825770930937aa7e5aca0dc0d29319a', + 'info_dict': { + 'id': '1007609', + 'ext': 'mp4', + 'title': 'Остросюжетный фильм «Кома»', + 'description': 'Остросюжетный фильм «Кома»', + 'thumbnail': 're:^http://.*\.jpg', + 'duration': 5592, }, - { - 'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/', - 'md5': '9320cd0e23f3ea59c330dc744e06ff3b', - 'info_dict': { - 'id': '751482', - 'ext': 'mp4', - 'title': '«Дело врачей»: «Деревце жизни»', - 'description': '«Дело врачей»: «Деревце жизни»', - 'thumbnail': 're:^http://.*\.jpg', - 'duration': 2590, - }, + }, { + 'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/', + 'md5': '9320cd0e23f3ea59c330dc744e06ff3b', + 'info_dict': { + 'id': '751482', + 'ext': 'mp4', + 'title': '«Дело врачей»: «Деревце жизни»', + 'description': '«Дело врачей»: «Деревце жизни»', + 'thumbnail': 're:^http://.*\.jpg', + 'duration': 2590, }, - ] + }] _VIDEO_ID_REGEXES = [ r'' + ('|'.join(re.escape(po) for po in PRIVATE_OPTS)) + ')=.+$') + + def _scrub_eq(o): + m = eqre.match(o) + if m: + return m.group('key') + '=PRIVATE' + else: + return o + + opts = list(map(_scrub_eq, opts)) + for private_opt in PRIVATE_OPTS: try: i = opts.index(private_opt) opts[i + 1] = 'PRIVATE' diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 2cfa406d9..27f97b213 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2016.07.28' +__version__ = '2016.08.01'