release 2016.10.12

Closes #10901

Seems all videos use player V5 syntax now

.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 *2016.09.27*. 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 Issues with outdated version will be rejected.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 **2016.09.27**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.10.12*. 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 Issues with outdated version will be rejected.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 **2016.10.12**
 
 ### 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 <your command line>
 [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 2016.09.27
+[debug] youtube-dl version 2016.10.12
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

AUTHORS

@@ -26,7 +26,7 @@ Albert Kim
 Pierre Rudloff
 Huarong Huo
 Ismael Mejía
-Steffan 'Ruirize' James
+Steffan Donal
 Andras Elso
 Jelle van der Waa
 Marcin Cieślak

CONTRIBUTING.md

@@ -85,7 +85,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make (both GNU make and BSD make are supported)
+* make (only GNU make is supported)
 * pandoc
 * zip
 * nosetests

ChangeLog

@@ -1,4 +1,67 @@
-vesion 2016.09.27
+version 2016.10.12
+
+Core
++ Support HTML media elements without child nodes
+* [Makefile] Support for GNU make < 4 is fixed; BSD make dropped (#9387)
+
+Extractors
+* [dailymotion] Fix extraction (#10901)
+* [vimeo:review] Fix extraction (#10900)
+* [nhl] Correctly handle invalid formats (#10713)
+* [footyroom] Fix extraction (#10810)
+* [abc.net.au:iview] Fix for standalone (non series) videos (#10895)
++ [hbo] Add support for episode pages (#10892)
+* [allocine] Fix extraction (#10860)
++ [nextmedia] Recognize action news on AppleDaily
+* [lego] Improve info extraction and bypass geo restriction (#10872)
+
+
+version 2016.10.07
+
+Extractors
++ [iprima] Detect geo restriction
+* [facebook] Fix video extraction (#10846)
++ [commonprotocols] Support direct MMS links (#10838)
++ [generic] Add support for multiple vimeo embeds (#10862)
++ [nzz] Add support for nzz.ch (#4407)
++ [npo] Detect geo restriction
++ [npo] Add support for 2doc.nl (#10842)
++ [lego] Add support for lego.com (#10369)
++ [tonline] Add support for t-online.de (#10376)
+* [techtalks] Relax URL regular expression (#10840)
+* [youtube:live] Extend URL regular expression (#10839)
++ [theweatherchannel] Add support for weather.com (#7188)
++ [thisoldhouse] Add support for thisoldhouse.com (#10837)
++ [nhl] Add support for wch2016.com (#10833)
+* [pornoxo] Use JWPlatform to improve metadata extraction
+
+
+version 2016.10.02
+
+Core
+* Fix possibly lost extended attributes during post-processing
++ Support pyxattr as well as python-xattr for --xattrs and
+  --xattr-set-filesize (#9054)
+
+Extractors
++ [jwplatform] Support DASH streams in JWPlayer
++ [jwplatform] Support old-style JWPlayer playlists
++ [byutv:event] Add extractor
+* [periscope:user] Fix extraction (#10820)
+* [dctp] Fix extraction (#10734)
++ [instagram] Extract video dimensions (#10790)
++ [tvland] Extend URL regular expression (#10812)
++ [vgtv] Add support for tv.aftonbladet.se (#10800)
+- [aftonbladet] Remove extractor
+* [vk] Fix timestamp and view count extraction (#10760)
++ [vk] Add support for running and finished live streams (#10799)
++ [leeco] Recognize more Le Sports URLs (#10794)
++ [instagram] Extract comments (#10788)
++ [ketnet] Extract mzsource formats (#10770)
+* [limelight:media] Improve HTTP formats extraction
+
+
+version 2016.09.27
 
 Core
 + Add hdcore query parameter to akamai f4m formats

Makefile

@@ -12,7 +12,7 @@ SHAREDIR ?= $(PREFIX)/share
 PYTHON ?= /usr/bin/env python
 
 # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
-SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
+SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi)
 
 install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	install -d $(DESTDIR)$(BINDIR)
@@ -90,7 +90,7 @@ fish-completion: youtube-dl.fish
 
 lazy-extractors: youtube_dl/extractor/lazy_extractors.py
 
-_EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py'
+_EXTRACTOR_FILES = $(shell find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py')
 youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 

README.md

@@ -923,7 +923,7 @@ To run the test, simply invoke your favorite test runner, or execute a test file
 If you want to create a build of youtube-dl yourself, you'll need
 
 * python
-* make (both GNU make and BSD make are supported)
+* make (only GNU make is supported)
 * pandoc
 * zip
 * nosetests

devscripts/lazy_load_template.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

docs/conf.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 #
 # youtube-dl documentation build configuration file, created by
 # sphinx-quickstart on Fri Mar 14 21:05:43 2014.

docs/supportedsites.md

@@ -34,7 +34,6 @@
  - **AdultSwim**
  - **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
  - **AfreecaTV**: afreecatv.com
- - **Aftonbladet**
  - **AirMozilla**
  - **AlJazeera**
  - **Allocine**
@@ -112,6 +111,7 @@
  - **bt:vestlendingen**: Bergens Tidende - Vestlendingen
  - **BuzzFeed**
  - **BYUtv**
+ - **BYUtvEvent**
  - **Camdemy**
  - **CamdemyFolder**
  - **CamWithHer**
@@ -289,6 +289,7 @@
  - **Groupon**
  - **Hark**
  - **HBO**
+ - **HBOEpisode**
  - **HearThisAt**
  - **Heise**
  - **HellPorno**
@@ -364,6 +365,7 @@
  - **Le**: 乐视网
  - **Learnr**
  - **Lecture2Go**
+ - **LEGO**
  - **Lemonde**
  - **LePlaylist**
  - **LetvCloud**: 乐视云
@@ -507,6 +509,7 @@
  - **Nuvid**
  - **NYTimes**
  - **NYTimesArticle**
+ - **NZZ**
  - **ocw.mit.edu**
  - **OdaTV**
  - **Odnoklassniki**
@@ -692,6 +695,7 @@
  - **SWRMediathek**
  - **Syfy**
  - **SztvHu**
+ - **t-online.de**
  - **Tagesschau**
  - **tagesschau:player**
  - **Tass**
@@ -721,8 +725,10 @@
  - **TheScene**
  - **TheSixtyOne**
  - **TheStar**
+ - **TheWeatherChannel**
  - **ThisAmericanLife**
  - **ThisAV**
+ - **ThisOldHouse**
  - **tinypic**: tinypic.com videos
  - **tlc.de**
  - **TMZ**

setup.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import print_function
 

test/test_http.py

@@ -87,7 +87,7 @@ class TestHTTP(unittest.TestCase):
 
         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)
+        self.assertEqual(r['entries'][0]['url'], 'http://localhost:%d/vid.mp4' % self.port)
 
 
 class TestHTTPS(unittest.TestCase):
@@ -111,7 +111,7 @@ class TestHTTPS(unittest.TestCase):
 
         ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
         r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
-        self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
+        self.assertEqual(r['entries'][0]['url'], 'https://localhost:%d/vid.mp4' % self.port)
 
 
 def _build_proxy_handler(name):

test/test_utils.py

@@ -292,6 +292,7 @@ class TestUtil(unittest.TestCase):
         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)
+        self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
 
     def test_unified_timestamps(self):
         self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
@@ -312,6 +313,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
         self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
         self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
+        self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
 
     def test_determine_ext(self):
         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')

youtube_dl/YoutubeDL.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import absolute_import, unicode_literals
 

youtube_dl/__init__.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import unicode_literals
 
@@ -266,8 +266,6 @@ def _real_main(argv=None):
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
         })
-    if opts.xattrs:
-        postprocessors.append({'key': 'XAttrMetadata'})
     if opts.embedthumbnail:
         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
         postprocessors.append({
@@ -276,6 +274,10 @@ def _real_main(argv=None):
         })
         if not already_have_thumbnail:
             opts.writethumbnail = True
+    # XAttrMetadataPP should be run after post-processors that may change file
+    # contents
+    if opts.xattrs:
+        postprocessors.append({'key': 'XAttrMetadata'})
     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
@@ -283,12 +285,6 @@ def _real_main(argv=None):
             'key': 'ExecAfterDownload',
             'exec_cmd': opts.exec_cmd,
         })
-    if opts.xattr_set_filesize:
-        try:
-            import xattr
-            xattr  # Confuse flake8
-        except ImportError:
-            parser.error('setting filesize xattr requested but python-xattr is not available')
     external_downloader_args = None
     if opts.external_downloader_args:
         external_downloader_args = compat_shlex_split(opts.external_downloader_args)

youtube_dl/downloader/common.py

@@ -346,7 +346,6 @@ class FileDownloader(object):
         min_sleep_interval = self.params.get('sleep_interval')
         if min_sleep_interval:
             max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
-            print(min_sleep_interval, max_sleep_interval)
             sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
             self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
             time.sleep(sleep_interval)

youtube_dl/downloader/http.py

@@ -13,6 +13,9 @@ from ..utils import (
     encodeFilename,
     sanitize_open,
     sanitized_Request,
+    write_xattr,
+    XAttrMetadataError,
+    XAttrUnavailableError,
 )
 
 
@@ -179,9 +182,8 @@ class HttpFD(FileDownloader):
 
                 if self.params.get('xattr_set_filesize', False) and data_len is not None:
                     try:
-                        import xattr
-                        xattr.setxattr(tmpfilename, 'user.ytdl.filesize', str(data_len))
-                    except(OSError, IOError, ImportError) as err:
+                        write_xattr(tmpfilename, 'user.ytdl.filesize', str(data_len).encode('utf-8'))
+                    except (XAttrUnavailableError, XAttrMetadataError) as err:
                         self.report_error('unable to set filesize xattr: %s' % str(err))
 
             try:

youtube_dl/extractor/abc.py

@@ -102,16 +102,16 @@ class ABCIViewIE(InfoExtractor):
 
     # ABC iview programs are normally available for 14 days only.
     _TESTS = [{
-        'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
-        'md5': '979d10b2939101f0d27a06b79edad536',
+        'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00',
+        'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
         'info_dict': {
-            'id': 'FA1505V024S00',
+            'id': 'ZX9735A001S00',
             'ext': 'mp4',
-            'title': 'Series 27 Ep 24',
-            'description': 'md5:b28baeae7504d1148e1d2f0e3ed3c15d',
-            'upload_date': '20160820',
-            'uploader_id': 'abc1',
-            'timestamp': 1471719600,
+            'title': 'Diaries Of A Broken Mind',
+            'description': 'md5:7de3903874b7a1be279fe6b68718fc9e',
+            'upload_date': '20161010',
+            'uploader_id': 'abc2',
+            'timestamp': 1476064920,
         },
         'skip': 'Video gone',
     }]
@@ -121,7 +121,7 @@ class ABCIViewIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         video_params = self._parse_json(self._search_regex(
             r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
-        title = video_params['title']
+        title = video_params.get('title') or video_params['seriesTitle']
         stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
 
         formats = self._extract_akamai_formats(stream['hds-unmetered'], video_id)
@@ -144,8 +144,8 @@ class ABCIViewIE(InfoExtractor):
             'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
             'series': video_params.get('seriesTitle'),
             'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
-            'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage)),
-            'episode': self._html_search_meta('episode_title', webpage),
+            'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage, default=None)),
+            'episode': self._html_search_meta('episode_title', webpage, default=None),
             'uploader_id': video_params.get('channel'),
             'formats': formats,
             'subtitles': subtitles,

youtube_dl/extractor/adobepass.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/aftonbladet.py

@@ -1,64 +0,0 @@
-# encoding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import int_or_none
-
-
-class AftonbladetIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
-        'info_dict': {
-            'id': '36015',
-            'ext': 'mp4',
-            'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
-            'description': 'Jupiters måne mest aktiv av alla himlakroppar',
-            'timestamp': 1394142732,
-            'upload_date': '20140306',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        # find internal video meta data
-        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['aptomaVideoId']
-        internal_meta_url = meta_url % internal_meta_id
-        internal_meta_json = self._download_json(
-            internal_meta_url, video_id, 'Downloading video meta data')
-
-        # find internal video formats
-        format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
-        internal_video_id = internal_meta_json['videoId']
-        internal_formats_url = format_url % internal_video_id
-        internal_formats_json = self._download_json(
-            internal_formats_url, video_id, 'Downloading video formats')
-
-        formats = []
-        for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
-            p = fmt['paths'][0]
-            formats.append({
-                'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
-                'ext': 'mp4',
-                'width': int_or_none(fmt.get('width')),
-                'height': int_or_none(fmt.get('height')),
-                'tbr': int_or_none(fmt.get('bitrate')),
-                'protocol': 'http',
-            })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': internal_meta_json['title'],
-            'formats': formats,
-            'thumbnail': internal_meta_json.get('imageUrl'),
-            'description': internal_meta_json.get('shortPreamble'),
-            'timestamp': int_or_none(internal_meta_json.get('timePublished')),
-            'duration': int_or_none(internal_meta_json.get('duration')),
-            'view_count': int_or_none(internal_meta_json.get('views')),
-        }

youtube_dl/extractor/allocine.py

@@ -1,29 +1,26 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
+    remove_end,
     qualities,
-    unescapeHTML,
-    xpath_element,
+    url_basename,
 )
 
 
 class AllocineIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
+    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
 
     _TESTS = [{
         'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
         'md5': '0c9fcf59a841f65635fa300ac43d8269',
         'info_dict': {
             'id': '19546517',
+            'display_id': '18635087',
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
-            'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',
+            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
@@ -31,64 +28,82 @@ class AllocineIE(InfoExtractor):
         'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
         'info_dict': {
             'id': '19540403',
+            'display_id': '19540403',
             'ext': 'mp4',
             'title': 'Planes 2 Bande-annonce VF',
             'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
-        'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html',
+        'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
         'md5': '101250fb127ef9ca3d73186ff22a47ce',
         'info_dict': {
             'id': '19544709',
+            'display_id': '19544709',
             'ext': 'mp4',
             'title': 'Dragons 2 - Bande annonce finale VF',
-            'description': 'md5:601d15393ac40f249648ef000720e7e3',
+            'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.allocine.fr/video/video-19550147/',
-        'only_matching': True,
+        'md5': '3566c0668c0235e2d224fd8edb389f67',
+        'info_dict': {
+            'id': '19550147',
+            'ext': 'mp4',
+            'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
+            'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
+            'thumbnail': 're:http://.*\.jpg',
+        },
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        typ = mobj.group('typ')
-        display_id = mobj.group('id')
+        display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 
-        if typ == 'film':
-            video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
-        else:
-            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player', default=None)
-            if player:
-                player_data = json.loads(player)
-                video_id = compat_str(player_data['refMedia'])
-            else:
-                model = self._search_regex(r'data-model="([^"]+)">', webpage, 'data model')
-                model_data = self._parse_json(unescapeHTML(model), display_id)
-                video_id = compat_str(model_data['id'])
-
-        xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
-
-        video = xpath_element(xml, './/AcVisionVideo').attrib
+        formats = []
         quality = qualities(['ld', 'md', 'hd'])
 
-        formats = []
-        for k, v in video.items():
-            if re.match(r'.+_path', k):
-                format_id = k.split('_')[0]
+        model = self._html_search_regex(
+            r'data-model="([^"]+)"', webpage, 'data model', default=None)
+        if model:
+            model_data = self._parse_json(model, display_id)
+
+            for video_url in model_data['sources'].values():
+                video_id, format_id = url_basename(video_url).split('_')[:2]
                 formats.append({
                     'format_id': format_id,
                     'quality': quality(format_id),
-                    'url': v,
+                    'url': video_url,
                 })
+
+            title = model_data['title']
+        else:
+            video_id = display_id
+            media_data = self._download_json(
+                'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
+            for key, value in media_data['video'].items():
+                if not key.endswith('Path'):
+                    continue
+
+                format_id = key[:-len('Path')]
+                formats.append({
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'url': value,
+                })
+
+            title = remove_end(self._html_search_regex(
+                r'(?s)<title>(.+?)</title>', webpage, 'title'
+            ).strip(), ' - AlloCiné')
+
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': video['videoTitle'],
+            'display_id': display_id,
+            'title': title,
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'description': self._og_search_description(webpage),

youtube_dl/extractor/amcnetworks.py

@@ -28,6 +28,7 @@ class AMCNetworksIE(ThePlatformIE):
             # m3u8 download
             'skip_download': True,
         },
+        'skip': 'Requires TV provider accounts',
     }, {
         'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
         'only_matching': True,

youtube_dl/extractor/arte.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/brightcove.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/byutv.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -8,15 +7,15 @@ from ..utils import ExtractorError
 
 
 class BYUtvIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
+    _TESTS = [{
         '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',
+            'id': '6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
+            'display_id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'title': 'Season 5 Episode 5',
+            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
             'thumbnail': 're:^https?://.*\.jpg$',
             'duration': 1486.486,
         },
@@ -24,28 +23,71 @@ class BYUtvIE(InfoExtractor):
             'skip_download': True,
         },
         'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
+        '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
+
+        webpage = self._download_webpage(url, display_id)
+        episode_code = self._search_regex(
+            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
+
+        ep = self._parse_json(
+            episode_code, display_id, transform_source=lambda s:
+            re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
+
+        if ep['providerType'] != 'Ooyala':
+            raise ExtractorError('Unsupported provider %s' % ep['provider'])
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % ep['providerId'],
+            'id': video_id,
+            'display_id': display_id,
+            'title': ep['title'],
+            'description': ep.get('description'),
+            'thumbnail': ep.get('imageThumbnail'),
+        }
+
+
+class BYUtvEventIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/event/(?P<id>[0-9a-f-]+)'
+    _TEST = {
+        'url': 'http://www.byutv.org/watch/event/29941b9b-8bf6-48d2-aebf-7a87add9e34b',
+        'info_dict': {
+            'id': '29941b9b-8bf6-48d2-aebf-7a87add9e34b',
+            'ext': 'mp4',
+            'title': 'Toledo vs. BYU (9/30/16)',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Ooyala'],
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        episode_code = self._search_regex(
-            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
-        episode_json = re.sub(
-            r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
-        ep = json.loads(episode_json)
 
-        if ep['providerType'] == 'Ooyala':
-            return {
-                '_type': 'url_transparent',
-                'ie_key': 'Ooyala',
-                'url': 'ooyala:%s' % ep['providerId'],
-                'id': video_id,
-                'title': ep['title'],
-                'description': ep.get('description'),
-                'thumbnail': ep.get('imageThumbnail'),
-            }
-        else:
-            raise ExtractorError('Unsupported provider %s' % ep['provider'])
+        ooyala_id = self._search_regex(
+            r'providerId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+            webpage, 'ooyala id', group='id')
+
+        title = self._search_regex(
+            r'class=["\']description["\'][^>]*>\s*<h1>([^<]+)</h1>', webpage,
+            'title').strip()
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'Ooyala',
+            'url': 'ooyala:%s' % ooyala_id,
+            'id': video_id,
+            'title': title,
+        }

youtube_dl/extractor/canalplus.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/cbsnews.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/ceskatelevize.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/clubic.py

@@ -1,9 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
@@ -30,16 +27,14 @@ class ClubicIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id
         player_page = self._download_webpage(player_url, video_id)
 
-        config_json = self._search_regex(
+        config = self._parse_json(self._search_regex(
             r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page,
-            'configuration')
-        config = json.loads(config_json)
+            'configuration'), video_id)
 
         video_info = config['videoInfo']
         sources = config['sources']

youtube_dl/extractor/comcarcoff.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/common.py

@@ -21,6 +21,7 @@ from ..compat import (
     compat_os_name,
     compat_str,
     compat_urllib_error,
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlencode,
     compat_urllib_request,
     compat_urlparse,
@@ -1801,7 +1802,11 @@ class InfoExtractor(object):
             return is_plain_url, formats
 
         entries = []
-        for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage):
+        media_tags = [(media_tag, media_type, '')
+                      for media_tag, media_type
+                      in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)]
+        media_tags.extend(re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage))
+        for media_tag, media_type, media_content in media_tags:
             media_info = {
                 'formats': [],
                 'subtitles': {},
@@ -2020,6 +2025,12 @@ class InfoExtractor(object):
             headers['Ytdl-request-proxy'] = geo_verification_proxy
         return headers
 
+    def _generic_id(self, url):
+        return compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+
+    def _generic_title(self, url):
+        return compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/commonprotocols.py

@@ -1,13 +1,9 @@
 from __future__ import unicode_literals
 
-import os
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_unquote,
     compat_urlparse,
 )
-from ..utils import url_basename
 
 
 class RtmpIE(InfoExtractor):
@@ -23,8 +19,8 @@ class RtmpIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
-        title = compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
         return {
             'id': video_id,
             'title': title,
@@ -34,3 +30,31 @@ class RtmpIE(InfoExtractor):
                 'format_id': compat_urlparse.urlparse(url).scheme,
             }],
         }
+
+
+class MmsIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)mms://.+'
+
+    _TEST = {
+        # Direct MMS link
+        'url': 'mms://kentro.kaist.ac.kr/200907/MilesReid(0709).wmv',
+        'info_dict': {
+            'id': 'MilesReid(0709)',
+            'ext': 'wmv',
+            'title': 'MilesReid(0709)',
+        },
+        'params': {
+            'skip_download': True,  # rtsp downloads, requiring mplayer or mpv
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+        }

youtube_dl/extractor/criterion.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -16,20 +14,20 @@ class CriterionIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Le Samouraï',
             'description': 'md5:a2b4b116326558149bef81f76dcbb93f',
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         final_url = self._search_regex(
-            r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
+            r'so\.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
         title = self._og_search_title(webpage)
         description = self._html_search_meta('description', webpage)
         thumbnail = self._search_regex(
-            r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
+            r'so\.addVariable\("thumbnailURL", "(.+?)"\)\;',
             webpage, 'thumbnail url')
 
         return {

youtube_dl/extractor/crunchyroll.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/dailymotion.py

@@ -94,7 +94,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
                 'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
                 'uploader': 'HotWaves1012',
                 'age_limit': 18,
-            }
+            },
+            'skip': 'video gone',
         },
         # geo-restricted, player v5
         {
@@ -144,7 +145,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
         player_v5 = self._search_regex(
             [r'buildPlayer\(({.+?})\);\n',  # See https://github.com/rg3/youtube-dl/issues/7826
              r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
-             r'buildPlayer\(({.+?})\);'],
+             r'buildPlayer\(({.+?})\);',
+             r'var\s+config\s*=\s*({.+?});'],
             webpage, 'player v5', default=None)
         if player_v5:
             player = self._parse_json(player_v5, video_id)

youtube_dl/extractor/daum.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 
 from __future__ import unicode_literals
 

youtube_dl/extractor/dctp.py

@@ -1,61 +1,54 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..utils import unified_strdate
 
 
 class DctpTvIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dctp\.tv/(#/)?filme/(?P<id>.+?)/$'
     _TEST = {
         'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
+        'md5': '174dd4a8a6225cf5655952f969cfbe24',
         'info_dict': {
-            'id': '1324',
+            'id': '95eaa4f33dad413aa17b4ee613cccc6c',
             'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
-            'ext': 'flv',
-            'title': 'Videoinstallation für eine Kaufhausfassade'
+            'ext': 'mp4',
+            'title': 'Videoinstallation für eine Kaufhausfassade',
+            'description': 'Kurzfilm',
+            'upload_date': '20110407',
+            'thumbnail': 're:^https?://.*\.jpg$',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        base_url = 'http://dctp-ivms2-restapi.s3.amazonaws.com/'
-        version_json = self._download_json(
-            base_url + 'version.json',
-            video_id, note='Determining file version')
-        version = version_json['version_name']
-        info_json = self._download_json(
-            '{0}{1}/restapi/slugs/{2}.json'.format(base_url, version, video_id),
-            video_id, note='Fetching object ID')
-        object_id = compat_str(info_json['object_id'])
-        meta_json = self._download_json(
-            '{0}{1}/restapi/media/{2}.json'.format(base_url, version, object_id),
-            video_id, note='Downloading metadata')
-        uuid = meta_json['uuid']
-        title = meta_json['title']
-        wide = meta_json['is_wide']
-        if wide:
-            ratio = '16x9'
-        else:
-            ratio = '4x3'
-        play_path = 'mp4:{0}_dctp_0500_{1}.m4v'.format(uuid, ratio)
+        webpage = self._download_webpage(url, video_id)
+
+        object_id = self._html_search_meta('DC.identifier', webpage)
 
         servers_json = self._download_json(
-            'http://www.dctp.tv/streaming_servers/',
+            'http://www.dctp.tv/elastic_streaming_client/get_streaming_server/',
             video_id, note='Downloading server list')
-        url = servers_json[0]['endpoint']
+        server = servers_json[0]['server']
+        m3u8_path = self._search_regex(
+            r'\'([^\'"]+/playlist\.m3u8)"', webpage, 'm3u8 path')
+        formats = self._extract_m3u8_formats(
+            'http://%s%s' % (server, m3u8_path), video_id, ext='mp4',
+            entry_protocol='m3u8_native')
+
+        title = self._og_search_title(webpage)
+        description = self._html_search_meta('DC.description', webpage)
+        upload_date = unified_strdate(
+            self._html_search_meta('DC.date.created', webpage))
+        thumbnail = self._og_search_thumbnail(webpage)
 
         return {
             'id': object_id,
             'title': title,
-            'format': 'rtmp',
-            'url': url,
-            'play_path': play_path,
-            'rtmp_real_time': True,
-            'ext': 'flv',
-            'display_id': video_id
+            'formats': formats,
+            'display_id': video_id,
+            'description': description,
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/dramafever.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import itertools

youtube_dl/extractor/eitb.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/embedly.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/extractors.py

@@ -31,7 +31,6 @@ from .aenetworks import (
     HistoryTopicIE,
 )
 from .afreecatv import AfreecaTVIE
-from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
@@ -117,7 +116,10 @@ from .brightcove import (
     BrightcoveNewIE,
 )
 from .buzzfeed import BuzzFeedIE
-from .byutv import BYUtvIE
+from .byutv import (
+    BYUtvIE,
+    BYUtvEventIE,
+)
 from .c56 import C56IE
 from .camdemy import (
     CamdemyIE,
@@ -184,7 +186,10 @@ from .comedycentral import (
 )
 from .comcarcoff import ComCarCoffIE
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
-from .commonprotocols import RtmpIE
+from .commonprotocols import (
+    MmsIE,
+    RtmpIE,
+)
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .crackle import CrackleIE
@@ -343,7 +348,10 @@ from .goshgay import GoshgayIE
 from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
 from .hark import HarkIE
-from .hbo import HBOIE
+from .hbo import (
+    HBOIE,
+    HBOEpisodeIE,
+)
 from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
 from .hellporno import HellPornoIE
@@ -435,6 +443,7 @@ from .lcp import (
 )
 from .learnr import LearnrIE
 from .lecture2go import Lecture2GoIE
+from .lego import LEGOIE
 from .lemonde import LemondeIE
 from .leeco import (
     LeIE,
@@ -635,6 +644,7 @@ from .nytimes import (
     NYTimesArticleIE,
 )
 from .nuvid import NuvidIE
+from .nzz import NZZIE
 from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
@@ -888,8 +898,10 @@ from .theplatform import (
 from .thescene import TheSceneIE
 from .thesixtyone import TheSixtyOneIE
 from .thestar import TheStarIE
+from .theweatherchannel import TheWeatherChannelIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
+from .thisoldhouse import ThisOldHouseIE
 from .threeqsdn import ThreeQSDNIE
 from .tinypic import TinyPicIE
 from .tlc import TlcDeIE
@@ -904,6 +916,7 @@ from .tnaflix import (
     MovieFapIE,
 )
 from .toggle import ToggleIE
+from .tonline import TOnlineIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE

youtube_dl/extractor/facebook.py

@@ -258,7 +258,7 @@ class FacebookIE(InfoExtractor):
 
         if not video_data:
             server_js_data = self._parse_json(self._search_regex(
-                r'handleServerJS\(({.+})\);', webpage, 'server js data', default='{}'), video_id)
+                r'handleServerJS\(({.+})(?:\);|,")', webpage, 'server js data', default='{}'), video_id)
             for item in server_js_data.get('instances', []):
                 if item[1][0] == 'VideoConfig':
                     video_data = video_data_list2dict(item[2][0]['videoData'])

youtube_dl/extractor/faz.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/firsttv.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/folketinget.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/footyroom.py

@@ -2,25 +2,27 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .streamable import StreamableIE
 
 
 class FootyRoomIE(InfoExtractor):
-    _VALID_URL = r'https?://footyroom\.com/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://footyroom\.com/matches/(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/',
+        'url': 'http://footyroom.com/matches/79922154/hull-city-vs-chelsea/review',
         'info_dict': {
-            'id': 'schalke-04-0-2-real-madrid-2015-02',
-            'title': 'Schalke 04 0 – 2 Real Madrid',
+            'id': '79922154',
+            'title': 'VIDEO Hull City 0 - 2 Chelsea',
         },
-        'playlist_count': 3,
-        'skip': 'Video for this match is not available',
+        'playlist_count': 2,
+        'add_ie': [StreamableIE.ie_key()],
     }, {
-        'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/',
+        'url': 'http://footyroom.com/matches/75817984/georgia-vs-germany/review',
         'info_dict': {
-            'id': 'georgia-0-2-germany-2015-03',
-            'title': 'Georgia 0 – 2 Germany',
+            'id': '75817984',
+            'title': 'VIDEO Georgia 0 - 2 Germany',
         },
         'playlist_count': 1,
+        'add_ie': ['Playwire']
     }]
 
     def _real_extract(self, url):
@@ -28,9 +30,8 @@ class FootyRoomIE(InfoExtractor):
 
         webpage = self._download_webpage(url, playlist_id)
 
-        playlist = self._parse_json(
-            self._search_regex(
-                r'VideoSelector\.load\((\[.+?\])\);', webpage, 'video selector'),
+        playlist = self._parse_json(self._search_regex(
+            r'DataStore\.media\s*=\s*([^;]+)', webpage, 'media data'),
             playlist_id)
 
         playlist_title = self._og_search_title(webpage)
@@ -40,11 +41,16 @@ class FootyRoomIE(InfoExtractor):
             payload = video.get('payload')
             if not payload:
                 continue
-            playwire_url = self._search_regex(
+            playwire_url = self._html_search_regex(
                 r'data-config="([^"]+)"', payload,
                 'playwire url', default=None)
             if playwire_url:
                 entries.append(self.url_result(self._proto_relative_url(
                     playwire_url, 'http:'), 'Playwire'))
 
+            streamable_url = StreamableIE._extract_url(payload)
+            if streamable_url:
+                entries.append(self.url_result(
+                    streamable_url, StreamableIE.ie_key()))
+
         return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/francetv.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 
 from __future__ import unicode_literals
 

youtube_dl/extractor/generic.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 
 from __future__ import unicode_literals
 
@@ -27,7 +27,6 @@ from ..utils import (
     unified_strdate,
     unsmuggle_url,
     UnsupportedError,
-    url_basename,
     xpath_text,
 )
 from .brightcove import (
@@ -1549,7 +1548,7 @@ class GenericIE(InfoExtractor):
             force_videoid = smuggled_data['force_videoid']
             video_id = force_videoid
         else:
-            video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
+            video_id = self._generic_id(url)
 
         self.to_screen('%s: Requesting header' % video_id)
 
@@ -1578,7 +1577,7 @@ class GenericIE(InfoExtractor):
 
         info_dict = {
             'id': video_id,
-            'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
+            'title': self._generic_title(url),
             'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
         }
 
@@ -1754,9 +1753,9 @@ class GenericIE(InfoExtractor):
         if matches:
             return _playlist_from_matches(matches, ie='RtlNl')
 
-        vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
-        if vimeo_url is not None:
-            return self.url_result(vimeo_url)
+        vimeo_urls = VimeoIE._extract_urls(url, webpage)
+        if vimeo_urls:
+            return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
 
         vid_me_embed_url = self._search_regex(
             r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
@@ -2332,12 +2331,23 @@ class GenericIE(InfoExtractor):
             info_dict.update(json_ld)
             return info_dict
 
+        # Look for HTML5 media
+        entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
+        if entries:
+            for entry in entries:
+                entry.update({
+                    'id': video_id,
+                    'title': video_title,
+                })
+                self._sort_formats(entry['formats'])
+            return self.playlist_result(entries)
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
-            return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
+            return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
 
         def filter_video(urls):
             return list(filter(check_video, urls))
@@ -2387,9 +2397,6 @@ class GenericIE(InfoExtractor):
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
-        if not found:
-            # HTML5 video
-            found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
             REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
             found = re.search(

youtube_dl/extractor/goshgay.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/hark.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/hbo.py

@@ -12,17 +12,7 @@ from ..utils import (
 )
 
 
-class HBOIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
-        'md5': '1c33253f0c7782142c993c0ba62a8753',
-        'info_dict': {
-            'id': '1437839',
-            'ext': 'mp4',
-            'title': 'Ep. 64 Clip: Encryption',
-        }
-    }
+class HBOBaseIE(InfoExtractor):
     _FORMATS_INFO = {
         '1920': {
             'width': 1280,
@@ -50,8 +40,7 @@ class HBOIE(InfoExtractor):
         },
     }
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
+    def _extract_from_id(self, video_id):
         video_data = self._download_xml(
             'http://render.lv3.hbo.com/data/content/global/videos/data/%s.xml' % video_id, video_id)
         title = xpath_text(video_data, 'title', 'title', True)
@@ -116,7 +105,60 @@ class HBOIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'duration': parse_duration(xpath_element(video_data, 'duration/tv14')),
+            'duration': parse_duration(xpath_text(video_data, 'duration/tv14')),
             'formats': formats,
             'thumbnails': thumbnails,
         }
+
+
+class HBOIE(HBOBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
+        'md5': '1c33253f0c7782142c993c0ba62a8753',
+        'info_dict': {
+            'id': '1437839',
+            'ext': 'mp4',
+            'title': 'Ep. 64 Clip: Encryption',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 1072,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_from_id(video_id)
+
+
+class HBOEpisodeIE(HBOBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?hbo\.com/(?!video)([^/]+/)+video/(?P<id>[0-9a-z-]+)\.html'
+
+    _TESTS = [{
+        'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
+        'md5': '689132b253cc0ab7434237fc3a293210',
+        'info_dict': {
+            'id': '1439518',
+            'display_id': 'ep-52-inside-the-episode',
+            'ext': 'mp4',
+            'title': 'Ep. 52: Inside the Episode',
+            'thumbnail': 're:https?://.*\.jpg$',
+            'duration': 240,
+        },
+    }, {
+        'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._search_regex(
+            r'(?P<q1>[\'"])videoId(?P=q1)\s*:\s*(?P<q2>[\'"])(?P<video_id>\d+)(?P=q2)',
+            webpage, 'video ID', group='video_id')
+
+        info_dict = self._extract_from_id(video_id)
+        info_dict['display_id'] = display_id
+
+        return info_dict

youtube_dl/extractor/helsinki.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import unicode_literals
 

youtube_dl/extractor/ina.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/instagram.py

@@ -29,6 +29,7 @@ class InstagramIE(InfoExtractor):
             'uploader': 'Naomi Leonor Phan-Quang',
             'like_count': int,
             'comment_count': int,
+            'comments': list,
         },
     }, {
         # missing description
@@ -44,6 +45,7 @@ class InstagramIE(InfoExtractor):
             'uploader': 'Britney Spears',
             'like_count': int,
             'comment_count': int,
+            'comments': list,
         },
         'params': {
             'skip_download': True,
@@ -82,7 +84,7 @@ class InstagramIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         (video_url, description, thumbnail, timestamp, uploader,
-         uploader_id, like_count, comment_count) = [None] * 8
+         uploader_id, like_count, comment_count, height, width) = [None] * 10
 
         shared_data = self._parse_json(
             self._search_regex(
@@ -94,6 +96,8 @@ class InstagramIE(InfoExtractor):
                 shared_data, lambda x: x['entry_data']['PostPage'][0]['media'], dict)
             if media:
                 video_url = media.get('video_url')
+                height = int_or_none(media.get('dimensions', {}).get('height'))
+                width = int_or_none(media.get('dimensions', {}).get('width'))
                 description = media.get('caption')
                 thumbnail = media.get('display_src')
                 timestamp = int_or_none(media.get('date'))
@@ -101,10 +105,24 @@ class InstagramIE(InfoExtractor):
                 uploader_id = media.get('owner', {}).get('username')
                 like_count = int_or_none(media.get('likes', {}).get('count'))
                 comment_count = int_or_none(media.get('comments', {}).get('count'))
+                comments = [{
+                    'author': comment.get('user', {}).get('username'),
+                    'author_id': comment.get('user', {}).get('id'),
+                    'id': comment.get('id'),
+                    'text': comment.get('text'),
+                    'timestamp': int_or_none(comment.get('created_at')),
+                } for comment in media.get(
+                    'comments', {}).get('nodes', []) if comment.get('text')]
 
         if not video_url:
             video_url = self._og_search_video_url(webpage, secure=False)
 
+        formats = [{
+            'url': video_url,
+            'width': width,
+            'height': height,
+        }]
+
         if not uploader_id:
             uploader_id = self._search_regex(
                 r'"owner"\s*:\s*{\s*"username"\s*:\s*"(.+?)"',
@@ -121,7 +139,7 @@ class InstagramIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'url': video_url,
+            'formats': formats,
             'ext': 'mp4',
             'title': 'Video by %s' % uploader_id,
             'description': description,
@@ -131,6 +149,7 @@ class InstagramIE(InfoExtractor):
             'uploader': uploader,
             'like_count': like_count,
             'comment_count': comment_count,
+            'comments': comments,
         }
 
 

youtube_dl/extractor/iprima.py

@@ -81,6 +81,9 @@ class IPrimaIE(InfoExtractor):
             for _, src in re.findall(r'src["\']\s*:\s*(["\'])(.+?)\1', playerpage):
                 extract_formats(src)
 
+        if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
+            self.raise_geo_restricted()
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/jpopsukitv.py

@@ -1,4 +1,4 @@
-# coding=utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/jwplatform.py

@@ -32,13 +32,20 @@ class JWPlatformBaseIE(InfoExtractor):
         return self._parse_jwplayer_data(
             jwplayer_data, video_id, *args, **kwargs)
 
-    def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True, m3u8_id=None, rtmp_params=None, base_url=None):
+    def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True,
+                             m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
         # JWPlayer backward compatibility: flattened playlists
         # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
         if 'playlist' not in jwplayer_data:
             jwplayer_data = {'playlist': [jwplayer_data]}
 
         entries = []
+
+        # JWPlayer backward compatibility: single playlist item
+        # https://github.com/jwplayer/jwplayer/blob/v7.7.0/src/js/playlist/playlist.js#L10
+        if not isinstance(jwplayer_data['playlist'], list):
+            jwplayer_data['playlist'] = [jwplayer_data['playlist']]
+
         for video_data in jwplayer_data['playlist']:
             # JWPlayer backward compatibility: flattened sources
             # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
@@ -57,6 +64,9 @@ class JWPlatformBaseIE(InfoExtractor):
                 if source_type == 'hls' or ext == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
                         source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
+                elif ext == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        source_url, this_video_id, mpd_id=mpd_id, fatal=False))
                 # https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
                 elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
                     formats.append({

youtube_dl/extractor/ketnet.py

@@ -21,6 +21,10 @@ class KetnetIE(InfoExtractor):
     }, {
         'url': 'https://www.ketnet.be/achter-de-schermen/sien-repeteert-voor-stars-for-life',
         'only_matching': True,
+    }, {
+        # mzsource, geo restricted to Belgium
+        'url': 'https://www.ketnet.be/kijken/nachtwacht/de-bermadoe',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -36,9 +40,25 @@ class KetnetIE(InfoExtractor):
 
         title = config['title']
 
-        formats = self._extract_m3u8_formats(
-            config['source']['hls'], video_id, 'mp4',
-            entry_protocol='m3u8_native', m3u8_id='hls')
+        formats = []
+        for source_key in ('', 'mz'):
+            source = config.get('%ssource' % source_key)
+            if not isinstance(source, dict):
+                continue
+            for format_id, format_url in source.items():
+                if format_id == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id=format_id,
+                        fatal=False))
+                elif format_id == 'hds':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url, video_id, f4m_id=format_id, fatal=False))
+                else:
+                    formats.append({
+                        'url': format_url,
+                        'format_id': format_id,
+                    })
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/kickstarter.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/kontrtube.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/krasview.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import json

youtube_dl/extractor/leeco.py

@@ -29,7 +29,7 @@ from ..utils import (
 
 class LeIE(InfoExtractor):
     IE_DESC = '乐视网'
-    _VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|sports\.le\.com/video)/(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|(?:sports\.le|(?:www\.)?lesports)\.com/(?:match|video))/(?P<id>\d+)\.html'
 
     _URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
 
@@ -73,6 +73,12 @@ class LeIE(InfoExtractor):
     }, {
         'url': 'http://sports.le.com/video/25737697.html',
         'only_matching': True,
+    }, {
+        'url': 'http://www.lesports.com/match/1023203003.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://sports.le.com/match/1023203003.html',
+        'only_matching': True,
     }]
 
     # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf

youtube_dl/extractor/lego.py

@@ -0,0 +1,128 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    unescapeHTML,
+    parse_duration,
+    get_element_by_class,
+)
+
+
+class LEGOIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
+    _TESTS = [{
+        'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
+        'md5': 'f34468f176cfd76488767fc162c405fa',
+        'info_dict': {
+            'id': '55492d823b1b4d5e985787fa8c2973b1',
+            'ext': 'mp4',
+            'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
+            'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
+        },
+    }, {
+        # geo-restricted but the contentUrl contain a valid url
+        'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399',
+        'md5': '4c3fec48a12e40c6e5995abc3d36cc2e',
+        'info_dict': {
+            'id': '13bdc2299ab24d9685701a915b3d71e7',
+            'ext': 'mp4',
+            'title': 'Aflevering 20 - Helden van het koninkrijk',
+            'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
+        },
+    }, {
+        # special characters in title
+        'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d',
+        'info_dict': {
+            'id': '9685ee9d12e84ff38e84b4e3d0db533d',
+            'ext': 'mp4',
+            'title': 'Force Surprise – LEGO® Star Wars™ Microfighters',
+            'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+    _BITRATES = [256, 512, 1024, 1536, 2560]
+
+    def _real_extract(self, url):
+        locale, video_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, video_id)
+        title = get_element_by_class('video-header', webpage).strip()
+        progressive_base = 'https://lc-mediaplayerns-live-s.legocdn.com/'
+        streaming_base = 'http://legoprod-f.akamaihd.net/'
+        content_url = self._html_search_meta('contentUrl', webpage)
+        path = self._search_regex(
+            r'(?:https?:)?//[^/]+/(?:[iz]/s/)?public/(.+)_[0-9,]+\.(?:mp4|webm)',
+            content_url, 'video path', default=None)
+        if not path:
+            player_url = self._proto_relative_url(self._search_regex(
+                r'<iframe[^>]+src="((?:https?)?//(?:www\.)?lego\.com/[^/]+/mediaplayer/video/[^"]+)',
+                webpage, 'player url', default=None))
+            if not player_url:
+                base_url = self._proto_relative_url(self._search_regex(
+                    r'data-baseurl="([^"]+)"', webpage, 'base url',
+                    default='http://www.lego.com/%s/mediaplayer/video/' % locale))
+                player_url = base_url + video_id
+            player_webpage = self._download_webpage(player_url, video_id)
+            video_data = self._parse_json(unescapeHTML(self._search_regex(
+                r"video='([^']+)'", player_webpage, 'video data')), video_id)
+            progressive_base = self._search_regex(
+                r'data-video-progressive-url="([^"]+)"',
+                player_webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
+            streaming_base = self._search_regex(
+                r'data-video-streaming-url="([^"]+)"',
+                player_webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
+            item_id = video_data['ItemId']
+
+            net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
+            base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
+            path = '/'.join([net_storage_path, base_path])
+        streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES))
+
+        formats = self._extract_akamai_formats(
+            '%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id)
+        m3u8_formats = list(filter(
+            lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            formats))
+        if len(m3u8_formats) == len(self._BITRATES):
+            self._sort_formats(m3u8_formats)
+            for bitrate, m3u8_format in zip(self._BITRATES, m3u8_formats):
+                progressive_base_url = '%spublic/%s_%d.' % (progressive_base, path, bitrate)
+                mp4_f = m3u8_format.copy()
+                mp4_f.update({
+                    'url': progressive_base_url + 'mp4',
+                    'format_id': m3u8_format['format_id'].replace('hls', 'mp4'),
+                    'protocol': 'http',
+                })
+                web_f = {
+                    'url': progressive_base_url + 'webm',
+                    'format_id': m3u8_format['format_id'].replace('hls', 'webm'),
+                    'width': m3u8_format['width'],
+                    'height': m3u8_format['height'],
+                    'tbr': m3u8_format.get('tbr'),
+                    'ext': 'webm',
+                }
+                formats.extend([web_f, mp4_f])
+        else:
+            for bitrate in self._BITRATES:
+                for ext in ('web', 'mp4'):
+                    formats.append({
+                        'format_id': '%s-%s' % (ext, bitrate),
+                        'url': '%spublic/%s_%d.%s' % (progressive_base, path, bitrate, ext),
+                        'tbr': bitrate,
+                        'ext': ext,
+                    })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta('description', webpage),
+            'thumbnail': self._html_search_meta('thumbnail', webpage),
+            'duration': parse_duration(self._html_search_meta('duration', webpage)),
+            'formats': formats,
+        }

youtube_dl/extractor/lifenews.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/limelight.py

@@ -59,7 +59,7 @@ class LimelightBaseIE(InfoExtractor):
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):
                         format_id += '-%d' % int_or_none(stream['videoBitRate'])
-                    http_url = 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:])
+                    http_url = 'http://cpl.delvenetworks.com/' + rtmp.group('playpath')[4:]
                     urls.append(http_url)
                     http_fmt = fmt.copy()
                     http_fmt.update({

youtube_dl/extractor/m6.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/mailru.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/moviezine.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/musicplayon.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/myspace.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/naver.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/newstube.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/nextmedia.py

@@ -93,7 +93,7 @@ class NextMediaActionNewsIE(NextMediaIE):
 
 class AppleDailyIE(NextMediaIE):
     IE_DESC = '臺灣蘋果日報'
-    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews|actionnews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
@@ -154,6 +154,9 @@ class AppleDailyIE(NextMediaIE):
             'description': 'md5:7b859991a6a4fedbdf3dd3b66545c748',
             'upload_date': '20140417',
         },
+    }, {
+        'url': 'http://www.appledaily.com.tw/actionnews/appledaily/7/20161003/960588/',
+        'only_matching': True,
     }]
 
     _URL_PATTERN = r'\{url: \'(.+)\'\}'

youtube_dl/extractor/nhl.py

@@ -245,7 +245,11 @@ class NHLVideocenterCategoryIE(NHLBaseInfoExtractor):
 
 class NHLIE(InfoExtractor):
     IE_NAME = 'nhl.com'
-    _VALID_URL = r'https?://(?:www\.)?nhl\.com/([^/]+/)*c-(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>nhl|wch2016)\.com/(?:[^/]+/)*c-(?P<id>\d+)'
+    _SITES_MAP = {
+        'nhl': 'nhl',
+        'wch2016': 'wch',
+    }
     _TESTS = [{
         # type=video
         'url': 'https://www.nhl.com/video/anisimov-cleans-up-mess/t-277752844/c-43663503',
@@ -270,13 +274,32 @@ class NHLIE(InfoExtractor):
             'upload_date': '20160204',
             'timestamp': 1454544904,
         },
+    }, {
+        # Some m3u8 URLs are invalid (https://github.com/rg3/youtube-dl/issues/10713)
+        'url': 'https://www.nhl.com/predators/video/poile-laviolette-on-subban-trade/t-277437416/c-44315003',
+        'md5': '50b2bb47f405121484dda3ccbea25459',
+        'info_dict': {
+            'id': '44315003',
+            'ext': 'mp4',
+            'title': 'Poile, Laviolette on Subban trade',
+            'description': 'General manager David Poile and head coach Peter Laviolette share their thoughts on acquiring P.K. Subban from Montreal (06/29/16)',
+            'timestamp': 1467242866,
+            'upload_date': '20160629',
+        },
+    }, {
+        'url': 'https://www.wch2016.com/video/caneur-best-of-game-2-micd-up/t-281230378/c-44983703',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.wch2016.com/news/3-stars-team-europe-vs-team-canada/c-282195068',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        tmp_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        tmp_id, site = mobj.group('id'), mobj.group('site')
         video_data = self._download_json(
-            'https://nhl.bamcontent.com/nhl/id/v1/%s/details/web-v1.json' % tmp_id,
-            tmp_id)
+            'https://nhl.bamcontent.com/%s/id/v1/%s/details/web-v1.json'
+            % (self._SITES_MAP[site], tmp_id), tmp_id)
         if video_data.get('type') == 'article':
             video_data = video_data['media']
 
@@ -290,9 +313,11 @@ class NHLIE(InfoExtractor):
                 continue
             ext = determine_ext(playback_url)
             if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
+                m3u8_formats = self._extract_m3u8_formats(
                     playback_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id=playback.get('name', 'hls'), fatal=False))
+                    m3u8_id=playback.get('name', 'hls'), fatal=False)
+                self._check_formats(m3u8_formats, video_id)
+                formats.extend(m3u8_formats)
             else:
                 height = int_or_none(playback.get('height'))
                 formats.append({

youtube_dl/extractor/niconico.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/noco.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/normalboots.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/nova.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/nowness.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .brightcove import (

youtube_dl/extractor/npo.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
     fix_xml_ampersands,
     orderedSet,
@@ -10,6 +11,7 @@ from ..utils import (
     qualities,
     strip_jsonp,
     unified_strdate,
+    ExtractorError,
 )
 
 
@@ -181,9 +183,16 @@ class NPOIE(NPOBaseIE):
                     continue
                 streams = format_info.get('streams')
                 if streams:
-                    video_info = self._download_json(
-                        streams[0] + '&type=json',
-                        video_id, 'Downloading %s stream JSON' % format_id)
+                    try:
+                        video_info = self._download_json(
+                            streams[0] + '&type=json',
+                            video_id, 'Downloading %s stream JSON' % format_id)
+                    except ExtractorError as ee:
+                        if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
+                            error = (self._parse_json(ee.cause.read().decode(), video_id, fatal=False) or {}).get('errorstring')
+                            if error:
+                                raise ExtractorError(error, expected=True)
+                        raise
                 else:
                     video_info = format_info
                 video_url = video_info.get('url')
@@ -459,8 +468,9 @@ class NPOPlaylistBaseIE(NPOIE):
 
 class VPROIE(NPOPlaylistBaseIE):
     IE_NAME = 'vpro'
-    _VALID_URL = r'https?://(?:www\.)?(?:tegenlicht\.)?vpro\.nl/(?:[^/]+/){2,}(?P<id>[^/]+)\.html'
-    _PLAYLIST_TITLE_RE = r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
+    _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
+                          r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
     _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
 
     _TESTS = [
@@ -492,6 +502,27 @@ class VPROIE(NPOPlaylistBaseIE):
                 'title': 'education education',
             },
             'playlist_count': 2,
+        },
+        {
+            'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
+            'info_dict': {
+                'id': 'de-tegenprestatie',
+                'title': 'De Tegenprestatie',
+            },
+            'playlist_count': 2,
+        }, {
+            'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
+            'info_dict': {
+                'id': 'VARA_101375237',
+                'ext': 'm4v',
+                'title': 'MH17: Het verdriet van Nederland',
+                'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
+                'upload_date': '20150716',
+            },
+            'params': {
+                # Skip because of m3u8 download
+                'skip_download': True
+            },
         }
     ]
 

youtube_dl/extractor/nrk.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/ntvru.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/nuevo.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/nzz.py

@@ -0,0 +1,36 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+)
+
+
+class NZZIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153',
+        'info_dict': {
+            'id': '9153',
+        },
+        'playlist_mincount': 6,
+    }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        entries = []
+        for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage):
+            player_params = extract_attributes(player_element)
+            if player_params.get('data-type') not in ('kaltura_singleArticle',):
+                self.report_warning('Unsupported player type')
+                continue
+            entry_id = player_params['data-id']
+            entries.append(self.url_result(
+                'kaltura:1750922:' + entry_id, 'Kaltura', entry_id))
+
+        return self.playlist_result(entries, page_id)

youtube_dl/extractor/oktoberfesttv.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/pandoratv.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/patreon.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/periscope.py

@@ -132,7 +132,7 @@ class PeriscopeUserIE(PeriscopeBaseIE):
 
         user = list(data_store['UserCache']['users'].values())[0]['user']
         user_id = user['id']
-        session_id = data_store['SessionToken']['broadcastHistory']['token']['session_id']
+        session_id = data_store['SessionToken']['public']['broadcastHistory']['token']['session_id']
 
         broadcasts = self._call_api(
             'getUserBroadcastsPublic',

youtube_dl/extractor/porn91.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from ..compat import (

youtube_dl/extractor/pornoxo.py

@@ -2,13 +2,13 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .jwplatform import JWPlatformBaseIE
 from ..utils import (
     str_to_int,
 )
 
 
-class PornoXOIE(InfoExtractor):
+class PornoXOIE(JWPlatformBaseIE):
     _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
     _TEST = {
         'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',
@@ -17,7 +17,8 @@ class PornoXOIE(InfoExtractor):
             'id': '7564',
             'ext': 'flv',
             'title': 'Striptease From Sexy Secretary!',
-            'description': 'Striptease From Sexy Secretary!',
+            'display_id': 'striptease-from-sexy-secretary',
+            'description': 'md5:0ee35252b685b3883f4a1d38332f9980',
             'categories': list,  # NSFW
             'thumbnail': 're:https?://.*\.jpg$',
             'age_limit': 18,
@@ -26,23 +27,14 @@ class PornoXOIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id, display_id = mobj.groups()
 
         webpage = self._download_webpage(url, video_id)
-
-        video_url = self._html_search_regex(
-            r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url')
+        video_data = self._extract_jwplayer_data(webpage, video_id, require_title=False)
 
         title = self._html_search_regex(
             r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title')
 
-        description = self._html_search_regex(
-            r'<meta name="description" content="([^"]+)\s*featuring',
-            webpage, 'description', fatal=False)
-
-        thumbnail = self._html_search_regex(
-            r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
-
         view_count = str_to_int(self._html_search_regex(
             r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False))
 
@@ -53,13 +45,14 @@ class PornoXOIE(InfoExtractor):
             None if categories_str is None
             else categories_str.split(','))
 
-        return {
+        video_data.update({
             'id': video_id,
-            'url': video_url,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
+            'display_id': display_id,
+            'description': self._html_search_meta('description', webpage),
             'categories': categories,
             'view_count': view_count,
             'age_limit': 18,
-        }
+        })
+
+        return video_data

youtube_dl/extractor/prosiebensat1.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/puls4.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .prosiebensat1 import ProSiebenSat1BaseIE

youtube_dl/extractor/radiobremen.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 
 from __future__ import unicode_literals
 

youtube_dl/extractor/reverbnation.py

@@ -1,29 +1,29 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import str_or_none
+from ..utils import (
+    qualities,
+    str_or_none,
+)
 
 
 class ReverbNationIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P<id>\d+).*?$'
     _TESTS = [{
         'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa',
-        'md5': '3da12ebca28c67c111a7f8b262d3f7a7',
+        'md5': 'c0aaf339bcee189495fdf5a8c8ba8645',
         'info_dict': {
             'id': '16965047',
             'ext': 'mp3',
             'title': 'MONA LISA',
             'uploader': 'ALKILADOS',
             'uploader_id': '216429',
-            'thumbnail': 're:^https://gp1\.wac\.edgecastcdn\.net/.*?\.jpg$'
+            'thumbnail': 're:^https?://.*\.jpg',
         },
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group('id')
+        song_id = self._match_id(url)
 
         api_res = self._download_json(
             'https://api.reverbnation.com/song/%s' % song_id,
@@ -31,14 +31,23 @@ class ReverbNationIE(InfoExtractor):
             note='Downloading information of song %s' % song_id
         )
 
+        THUMBNAILS = ('thumbnail', 'image')
+        quality = qualities(THUMBNAILS)
+        thumbnails = []
+        for thumb_key in THUMBNAILS:
+            if api_res.get(thumb_key):
+                thumbnails.append({
+                    'url': api_res[thumb_key],
+                    'preference': quality(thumb_key)
+                })
+
         return {
             'id': song_id,
-            'title': api_res.get('name'),
-            'url': api_res.get('url'),
+            'title': api_res['name'],
+            'url': api_res['url'],
             'uploader': api_res.get('artist', {}).get('name'),
             'uploader_id': str_or_none(api_res.get('artist', {}).get('id')),
-            'thumbnail': self._proto_relative_url(
-                api_res.get('image', api_res.get('thumbnail'))),
+            'thumbnails': thumbnails,
             'ext': 'mp3',
             'vcodec': 'none',
         }

youtube_dl/extractor/rmcdecouverte.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/rtl2.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/rtve.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import base64

youtube_dl/extractor/rudo.py

@@ -43,7 +43,7 @@ class RudoIE(JWPlatformBaseIE):
             transform_source=lambda s: js_to_json(re.sub(r'encodeURI\([^)]+\)', '""', s)))
 
         info_dict = self._parse_jwplayer_data(
-            jwplayer_data, video_id, require_title=False, m3u8_id='hls')
+            jwplayer_data, video_id, require_title=False, m3u8_id='hls', mpd_id='dash')
 
         info_dict.update({
             'title': self._og_search_title(webpage),

youtube_dl/extractor/ruhd.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

youtube_dl/extractor/rutube.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re

youtube_dl/extractor/rutv.py

@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re