release 2016.07.13

SOCKS tests never run on Travis CI due to unknown reasons, and
downloading them broke some tests (e.g.
https://travis-ci.org/rg3/youtube-dl/builds/144306425)

.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 *2016.07.07*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.07.07**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.07.13*. 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 Issues with outdated version will be rejected.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 **2016.07.13**
 
 ### 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 2016.07.07
+[debug] youtube-dl version 2016.07.13
 [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: {}

.travis.yml

@@ -7,9 +7,6 @@ python:
   - "3.4"
   - "3.5"
 sudo: false
-install:
-  - bash ./devscripts/install_srelay.sh
-  - export PATH=$PATH:$(pwd)/tmp/srelay-0.4.8b6
 script: nosetests test --verbose
 notifications:
   email:

AUTHORS

@@ -177,3 +177,4 @@ Roman Tsiupa
 Artur Krysiak
 Jakub Adam Wieczorek
 Aleksandar Topuzović
+Nehal Patel

README.md

@@ -432,6 +432,7 @@ For example, with the following configuration file youtube-dl will always extrac
 --no-mtime
 --proxy 127.0.0.1:3128
 -o ~/Movies/%(title)s.%(ext)s
+# Lines starting with # are comments
 ```
 
 Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.

devscripts/gh-pages/generate-download.py

@@ -15,13 +15,9 @@ data = urllib.request.urlopen(URL).read()
 with open('download.html.in', 'r', encoding='utf-8') as tmplf:
     template = tmplf.read()
 
-md5sum = hashlib.md5(data).hexdigest()
-sha1sum = hashlib.sha1(data).hexdigest()
 sha256sum = hashlib.sha256(data).hexdigest()
 template = template.replace('@PROGRAM_VERSION@', version)
 template = template.replace('@PROGRAM_URL@', URL)
-template = template.replace('@PROGRAM_MD5SUM@', md5sum)
-template = template.replace('@PROGRAM_SHA1SUM@', sha1sum)
 template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
 template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0])
 template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1])

devscripts/install_srelay.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-
-mkdir -p tmp && cd tmp
-wget -N http://downloads.sourceforge.net/project/socks-relay/socks-relay/srelay-0.4.8/srelay-0.4.8b6.tar.gz
-tar zxvf srelay-0.4.8b6.tar.gz
-cd srelay-0.4.8b6
-./configure
-make

docs/supportedsites.md

@@ -224,6 +224,7 @@
  - **Firstpost**
  - **FiveTV**
  - **Flickr**
+ - **Flipagram**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
  - **FootyRoom**
  - **Formula1**
@@ -553,6 +554,7 @@
  - **RICE**
  - **RingTV**
  - **RockstarGames**
+ - **RoosterTeeth**
  - **RottenTomatoes**
  - **Roxwel**
  - **RTBF**
@@ -566,6 +568,7 @@
  - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
  - **RTVNH**
+ - **Rudo**
  - **RUHD**
  - **RulePorn**
  - **rutube**: Rutube videos
@@ -792,6 +795,7 @@
  - **vine:user**
  - **vk**: VK
  - **vk:uservideos**: VK - User's Videos
+ - **vk:wallpost**
  - **vlive**
  - **Vodlocker**
  - **VoiceRepublic**

test/test_compat.py

@@ -88,6 +88,7 @@ class TestCompat(unittest.TestCase):
     def test_compat_shlex_split(self):
         self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
         self.assertEqual(compat_shlex_split('-option "one\ntwo" \n -flag'), ['-option', 'one\ntwo', '-flag'])
+        self.assertEqual(compat_shlex_split('-val 中文'), ['-val', '中文'])
 
     def test_compat_etree_fromstring(self):
         xml = '''

test/test_utils.py

@@ -81,6 +81,7 @@ from youtube_dl.utils import (
     cli_option,
     cli_valueless_option,
     cli_bool_option,
+    parse_codecs,
 )
 from youtube_dl.compat import (
     compat_chr,
@@ -608,6 +609,29 @@ class TestUtil(unittest.TestCase):
             limit_length('foo bar baz asd', 12).startswith('foo bar'))
         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 
+    def test_parse_codecs(self):
+        self.assertEqual(parse_codecs(''), {})
+        self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
+            'vcodec': 'avc1.77.30',
+            'acodec': 'mp4a.40.2',
+        })
+        self.assertEqual(parse_codecs('mp4a.40.2'), {
+            'vcodec': 'none',
+            'acodec': 'mp4a.40.2',
+        })
+        self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
+            'vcodec': 'avc1.42001e',
+            'acodec': 'mp4a.40.5',
+        })
+        self.assertEqual(parse_codecs('avc3.640028'), {
+            'vcodec': 'avc3.640028',
+            'acodec': 'none',
+        })
+        self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
+            'vcodec': 'h264',
+            'acodec': 'aac',
+        })
+
     def test_escape_rfc3986(self):
         reserved = "!*'();:@&=+$,/?#[]"
         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'

youtube_dl/compat.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import binascii
@@ -2594,15 +2595,19 @@ except ImportError:  # Python < 3.3
             return "'" + s.replace("'", "'\"'\"'") + "'"
 
 
-if sys.version_info >= (2, 7, 3):
+try:
+    args = shlex.split('中文')
+    assert (isinstance(args, list) and
+            isinstance(args[0], compat_str) and
+            args[0] == '中文')
     compat_shlex_split = shlex.split
-else:
+except (AssertionError, UnicodeEncodeError):
     # Working around shlex issue with unicode strings on some python 2
     # versions (see http://bugs.python.org/issue1548891)
     def compat_shlex_split(s, comments=False, posix=True):
         if isinstance(s, compat_str):
             s = s.encode('utf-8')
-        return shlex.split(s, comments, posix)
+        return list(map(lambda s: s.decode('utf-8'), shlex.split(s, comments, posix)))
 
 
 def compat_ord(c):

youtube_dl/extractor/animeondemand.py

@@ -22,6 +22,7 @@ class AnimeOnDemandIE(InfoExtractor):
     _APPLY_HTML5_URL = 'https://www.anime-on-demand.de/html5apply'
     _NETRC_MACHINE = 'animeondemand'
     _TESTS = [{
+        # jap, OmU
         'url': 'https://www.anime-on-demand.de/anime/161',
         'info_dict': {
             'id': '161',
@@ -30,17 +31,21 @@ class AnimeOnDemandIE(InfoExtractor):
         },
         'playlist_mincount': 4,
     }, {
-        # Film wording is used instead of Episode
+        # Film wording is used instead of Episode, ger/jap, Dub/OmU
         'url': 'https://www.anime-on-demand.de/anime/39',
         'only_matching': True,
     }, {
-        # Episodes without titles
+        # Episodes without titles, jap, OmU
         'url': 'https://www.anime-on-demand.de/anime/162',
         'only_matching': True,
     }, {
         # ger/jap, Dub/OmU, account required
         'url': 'https://www.anime-on-demand.de/anime/169',
         'only_matching': True,
+    }, {
+        # Full length film, non-series, ger/jap, Dub/OmU, account required
+        'url': 'https://www.anime-on-demand.de/anime/185',
+        'only_matching': True,
     }]
 
     def _login(self):
@@ -110,35 +115,12 @@ class AnimeOnDemandIE(InfoExtractor):
 
         entries = []
 
-        for num, episode_html in enumerate(re.findall(
-                r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage), 1):
-            episodebox_title = self._search_regex(
-                (r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1',
-                 r'class="episodebox-title"[^>]+>(?P<title>.+?)<'),
-                episode_html, 'episodebox title', default=None, group='title')
-            if not episodebox_title:
-                continue
-
-            episode_number = int(self._search_regex(
-                r'(?:Episode|Film)\s*(\d+)',
-                episodebox_title, 'episode number', default=num))
-            episode_title = self._search_regex(
-                r'(?:Episode|Film)\s*\d+\s*-\s*(.+)',
-                episodebox_title, 'episode title', default=None)
-
-            video_id = 'episode-%d' % episode_number
-
-            common_info = {
-                'id': video_id,
-                'series': anime_title,
-                'episode': episode_title,
-                'episode_number': episode_number,
-            }
-
+        def extract_info(html, video_id, num=None):
+            title, description = [None] * 2
             formats = []
 
             for input_ in re.findall(
-                    r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', episode_html):
+                    r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', html):
                 attributes = extract_attributes(input_)
                 playlist_urls = []
                 for playlist_key in ('data-playlist', 'data-otherplaylist'):
@@ -161,7 +143,7 @@ class AnimeOnDemandIE(InfoExtractor):
                         format_id_list.append(lang)
                     if kind:
                         format_id_list.append(kind)
-                    if not format_id_list:
+                    if not format_id_list and num is not None:
                         format_id_list.append(compat_str(num))
                     format_id = '-'.join(format_id_list)
                     format_note = ', '.join(filter(None, (kind, lang_note)))
@@ -215,28 +197,74 @@ class AnimeOnDemandIE(InfoExtractor):
                             })
                         formats.extend(file_formats)
 
-            if formats:
-                self._sort_formats(formats)
+            return {
+                'title': title,
+                'description': description,
+                'formats': formats,
+            }
+
+        def extract_entries(html, video_id, common_info, num=None):
+            info = extract_info(html, video_id, num)
+
+            if info['formats']:
+                self._sort_formats(info['formats'])
                 f = common_info.copy()
-                f.update({
-                    'title': title,
-                    'description': description,
-                    'formats': formats,
-                })
+                f.update(info)
                 entries.append(f)
 
-            # Extract teaser only when full episode is not available
-            if not formats:
+            # Extract teaser/trailer only when full episode is not available
+            if not info['formats']:
                 m = re.search(
-                    r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
-                    episode_html)
+                    r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>(?P<kind>Teaser|Trailer)<',
+                    html)
                 if m:
                     f = common_info.copy()
                     f.update({
-                        'id': '%s-teaser' % f['id'],
+                        'id': '%s-%s' % (f['id'], m.group('kind').lower()),
                         'title': m.group('title'),
                         'url': compat_urlparse.urljoin(url, m.group('href')),
                     })
                     entries.append(f)
 
+        def extract_episodes(html):
+            for num, episode_html in enumerate(re.findall(
+                    r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', html), 1):
+                episodebox_title = self._search_regex(
+                    (r'class="episodebox-title"[^>]+title=(["\'])(?P<title>.+?)\1',
+                     r'class="episodebox-title"[^>]+>(?P<title>.+?)<'),
+                    episode_html, 'episodebox title', default=None, group='title')
+                if not episodebox_title:
+                    continue
+
+                episode_number = int(self._search_regex(
+                    r'(?:Episode|Film)\s*(\d+)',
+                    episodebox_title, 'episode number', default=num))
+                episode_title = self._search_regex(
+                    r'(?:Episode|Film)\s*\d+\s*-\s*(.+)',
+                    episodebox_title, 'episode title', default=None)
+
+                video_id = 'episode-%d' % episode_number
+
+                common_info = {
+                    'id': video_id,
+                    'series': anime_title,
+                    'episode': episode_title,
+                    'episode_number': episode_number,
+                }
+
+                extract_entries(episode_html, video_id, common_info)
+
+        def extract_film(html, video_id):
+            common_info = {
+                'id': anime_id,
+                'title': anime_title,
+                'description': anime_description,
+            }
+            extract_entries(html, video_id, common_info)
+
+        extract_episodes(webpage)
+
+        if not entries:
+            extract_film(webpage, anime_id)
+
         return self.playlist_result(entries, anime_id, anime_title, anime_description)

youtube_dl/extractor/ard.py

@@ -13,6 +13,7 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     xpath_text,
+    update_url_query,
 )
 from ..compat import compat_etree_fromstring
 
@@ -34,6 +35,7 @@ class ARDMediathekIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
+        'skip': 'HTTP Error 404: Not Found',
     }, {
         'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
         'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
@@ -44,6 +46,7 @@ class ARDMediathekIE(InfoExtractor):
             'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
             'duration': 5252,
         },
+        'skip': 'HTTP Error 404: Not Found',
     }, {
         # audio
         'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
@@ -55,6 +58,7 @@ class ARDMediathekIE(InfoExtractor):
             'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
             'duration': 3240,
         },
+        'skip': 'HTTP Error 404: Not Found',
     }, {
         'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
         'only_matching': True,
@@ -113,11 +117,14 @@ class ARDMediathekIE(InfoExtractor):
                         continue
                     if ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
-                            stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
-                            video_id, preference=-1, f4m_id='hds', fatal=False))
+                            update_url_query(stream_url, {
+                                'hdcore': '3.1.1',
+                                'plugin': 'aasp-3.1.1.69.124'
+                            }),
+                            video_id, f4m_id='hds', fatal=False))
                     elif ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
-                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls', fatal=False))
+                            stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
                     else:
                         if server and server.startswith('rtmp'):
                             f = {
@@ -231,7 +238,8 @@ class ARDIE(InfoExtractor):
             'title': 'Die Story im Ersten: Mission unter falscher Flagge',
             'upload_date': '20140804',
             'thumbnail': 're:^https?://.*\.jpg$',
-        }
+        },
+        'skip': 'HTTP Error 404: Not Found',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/bbc.py

@@ -44,6 +44,8 @@ class BBCCoUkIE(InfoExtractor):
 
     _MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
     _EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
+    # Unified Streaming Platform
+    _USP_RE = r'/([^/]+)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
 
     _NAMESPACES = (
         _MEDIASELECTION_NS,
@@ -55,12 +57,11 @@ class BBCCoUkIE(InfoExtractor):
             'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
             'info_dict': {
                 'id': 'b039d07m',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
                 'description': 'The Canadian poet and songwriter reflects on his musical career.',
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             }
         },
@@ -92,7 +93,7 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
-            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+            'skip': 'this episode is not currently available',
         },
         {
             'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
@@ -107,7 +108,7 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
-            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+            'skip': 'this episode is not currently available',
         }, {
             'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
             'info_dict': {
@@ -127,13 +128,12 @@ class BBCCoUkIE(InfoExtractor):
             'note': 'Audio',
             'info_dict': {
                 'id': 'p022h44j',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
                 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
                 'duration': 227,
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             }
         }, {
@@ -141,13 +141,12 @@ class BBCCoUkIE(InfoExtractor):
             'note': 'Video',
             'info_dict': {
                 'id': 'p025c103',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
                 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
                 'duration': 226,
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             }
         }, {
@@ -163,7 +162,7 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
-            'skip': 'geolocation',
+            'skip': 'this episode is not currently available',
         }, {
             'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
             'info_dict': {
@@ -177,7 +176,7 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
-            'skip': 'geolocation',
+            'skip': 'this episode is not currently available',
         }, {
             # iptv-all mediaset fails with geolocation however there is no geo restriction
             # for this programme at all
@@ -192,18 +191,17 @@ class BBCCoUkIE(InfoExtractor):
                 # rtmp download
                 'skip_download': True,
             },
-            'skip': 'Now it\'s really geo-restricted',
+            'skip': 'this episode is not currently available on BBC iPlayer Radio',
         }, {
             # compact player (https://github.com/rg3/youtube-dl/issues/8147)
             'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
             'info_dict': {
                 'id': 'p028bfkj',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
                 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         }, {
@@ -248,9 +246,15 @@ class BBCCoUkIE(InfoExtractor):
             elif transfer_format == 'dash':
                 pass
             elif transfer_format == 'hls':
-                formats.extend(self._extract_m3u8_formats(
+                is_unified_streaming = re.search(self._USP_RE, href)
+                if is_unified_streaming:
+                    href = re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href)
+                m3u8_formats = self._extract_m3u8_formats(
                     href, programme_id, ext='mp4', entry_protocol='m3u8_native',
-                    m3u8_id=supplier, fatal=False))
+                    m3u8_id=supplier, fatal=False)
+                if is_unified_streaming:
+                    self._check_formats(m3u8_formats, programme_id)
+                formats.extend(m3u8_formats)
             # Direct link
             else:
                 formats.append({
@@ -305,13 +309,14 @@ class BBCCoUkIE(InfoExtractor):
         for connection in self._extract_connections(media):
             conn_formats = self._extract_connection(connection, programme_id)
             for format in conn_formats:
-                format.update({
-                    'width': width,
-                    'height': height,
-                    'vbr': vbr,
-                    'vcodec': vcodec,
-                    'filesize': file_size,
-                })
+                if format.get('protocol') != 'm3u8_native':
+                    format.update({
+                        'width': width,
+                        'height': height,
+                        'vbr': vbr,
+                        'vcodec': vcodec,
+                        'filesize': file_size,
+                    })
                 if service:
                     format['format_id'] = '%s_%s' % (service, format['format_id'])
             formats.extend(conn_formats)

youtube_dl/extractor/biobiochiletv.py

@@ -2,11 +2,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import remove_end
+from ..utils import (
+    ExtractorError,
+    remove_end,
+)
+from .rudo import RudoIE
 
 
 class BioBioChileTVIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.biobiochile\.cl/notas/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
+    _VALID_URL = r'https?://(?:tv|www)\.biobiochile\.cl/(?:notas|noticias)/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
 
     _TESTS = [{
         'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',
@@ -18,6 +22,7 @@ class BioBioChileTVIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'Fernando Atria',
         },
+        'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
     }, {
         # different uploader layout
         'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',
@@ -32,6 +37,16 @@ class BioBioChileTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
+    }, {
+        'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml',
+        'info_dict': {
+            'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos',
+            'ext': 'mp4',
+            'uploader': '(none)',
+            'upload_date': '20160708',
+            'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos',
+        },
     }, {
         'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
         'only_matching': True,
@@ -45,42 +60,22 @@ class BioBioChileTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        rudo_url = RudoIE._extract_url(webpage)
+        if not rudo_url:
+            raise ExtractorError('No videos found')
+
         title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')
 
-        file_url = self._search_regex(
-            r'loadFWPlayerVideo\([^,]+,\s*(["\'])(?P<url>.+?)\1',
-            webpage, 'file url', group='url')
-
-        base_url = self._search_regex(
-            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*fileURL', webpage,
-            'base url', default='http://unlimited2-cl.digitalproserver.com/bbtv/',
-            group='url')
-
-        formats = self._extract_m3u8_formats(
-            '%s%s/playlist.m3u8' % (base_url, file_url), video_id, 'mp4',
-            entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
-        f = {
-            'url': '%s%s' % (base_url, file_url),
-            'format_id': 'http',
-            'protocol': 'http',
-            'preference': 1,
-        }
-        if formats:
-            f_copy = formats[-1].copy()
-            f_copy.update(f)
-            f = f_copy
-        formats.append(f)
-        self._sort_formats(formats)
-
         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._html_search_regex(
-            r'<a[^>]+href=["\']https?://busca\.biobiochile\.cl/author[^>]+>(.+?)</a>',
+            r'<a[^>]+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
             webpage, 'uploader', fatal=False)
 
         return {
+            '_type': 'url_transparent',
+            'url': rudo_url,
             'id': video_id,
             'title': title,
             'thumbnail': thumbnail,
             'uploader': uploader,
-            'formats': formats,
         }

youtube_dl/extractor/brightcove.py

@@ -26,6 +26,7 @@ from ..utils import (
     unescapeHTML,
     unsmuggle_url,
     update_url_query,
+    clean_html,
 )
 
 
@@ -620,7 +621,7 @@ class BrightcoveNewIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'description': json_data.get('description'),
+            'description': clean_html(json_data.get('description')),
             'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
             'duration': float_or_none(json_data.get('duration'), 1000),
             'timestamp': parse_iso8601(json_data.get('published_at')),

youtube_dl/extractor/common.py

@@ -44,6 +44,7 @@ from ..utils import (
     sanitized_Request,
     unescapeHTML,
     unified_strdate,
+    unified_timestamp,
     url_basename,
     xpath_element,
     xpath_text,
@@ -54,6 +55,8 @@ from ..utils import (
     update_Request,
     update_url_query,
     parse_m3u8_attributes,
+    extract_attributes,
+    parse_codecs,
 )
 
 
@@ -161,6 +164,7 @@ class InfoExtractor(object):
                         * "height" (optional, int)
                         * "resolution" (optional, string "{width}x{height"},
                                         deprecated)
+                        * "filesize" (optional, int)
     thumbnail:      Full URL to a video thumbnail image.
     description:    Full video description.
     uploader:       Full name of the video uploader.
@@ -803,15 +807,17 @@ class InfoExtractor(object):
         return self._html_search_meta('twitter:player', html,
                                       'twitter card player')
 
-    def _search_json_ld(self, html, video_id, **kwargs):
+    def _search_json_ld(self, html, video_id, expected_type=None, **kwargs):
         json_ld = self._search_regex(
             r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
             html, 'JSON-LD', group='json_ld', **kwargs)
         if not json_ld:
             return {}
-        return self._json_ld(json_ld, video_id, fatal=kwargs.get('fatal', True))
+        return self._json_ld(
+            json_ld, video_id, fatal=kwargs.get('fatal', True),
+            expected_type=expected_type)
 
-    def _json_ld(self, json_ld, video_id, fatal=True):
+    def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None):
         if isinstance(json_ld, compat_str):
             json_ld = self._parse_json(json_ld, video_id, fatal=fatal)
         if not json_ld:
@@ -819,6 +825,8 @@ class InfoExtractor(object):
         info = {}
         if json_ld.get('@context') == 'http://schema.org':
             item_type = json_ld.get('@type')
+            if expected_type is not None and expected_type != item_type:
+                return info
             if item_type == 'TVEpisode':
                 info.update({
                     'episode': unescapeHTML(json_ld.get('name')),
@@ -837,6 +845,19 @@ class InfoExtractor(object):
                     'title': unescapeHTML(json_ld.get('headline')),
                     'description': unescapeHTML(json_ld.get('articleBody')),
                 })
+            elif item_type == 'VideoObject':
+                info.update({
+                    'url': json_ld.get('contentUrl'),
+                    'title': unescapeHTML(json_ld.get('name')),
+                    'description': unescapeHTML(json_ld.get('description')),
+                    'thumbnail': json_ld.get('thumbnailUrl'),
+                    'duration': parse_duration(json_ld.get('duration')),
+                    'timestamp': unified_timestamp(json_ld.get('uploadDate')),
+                    'filesize': float_or_none(json_ld.get('contentSize')),
+                    'tbr': int_or_none(json_ld.get('bitrate')),
+                    'width': int_or_none(json_ld.get('width')),
+                    'height': int_or_none(json_ld.get('height')),
+                })
         return dict((k, v) for k, v in info.items() if v is not None)
 
     @staticmethod
@@ -1186,6 +1207,7 @@ class InfoExtractor(object):
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
+                    'fps': float_or_none(last_info.get('FRAME-RATE')),
                     'protocol': entry_protocol,
                     'preference': preference,
                 }
@@ -1194,24 +1216,17 @@ class InfoExtractor(object):
                     width_str, height_str = resolution.split('x')
                     f['width'] = int(width_str)
                     f['height'] = int(height_str)
-                codecs = last_info.get('CODECS')
-                if codecs:
-                    vcodec, acodec = [None] * 2
-                    va_codecs = codecs.split(',')
-                    if len(va_codecs) == 1:
-                        # Audio only entries usually come with single codec and
-                        # no resolution. For more robustness we also check it to
-                        # be mp4 audio.
-                        if not resolution and va_codecs[0].startswith('mp4a'):
-                            vcodec, acodec = 'none', va_codecs[0]
-                        else:
-                            vcodec = va_codecs[0]
-                    else:
-                        vcodec, acodec = va_codecs[:2]
+                # Unified Streaming Platform
+                mobj = re.search(
+                    r'audio.*?(?:%3D|=)(\d+)(?:-video.*?(?:%3D|=)(\d+))?', f['url'])
+                if mobj:
+                    abr, vbr = mobj.groups()
+                    abr, vbr = float_or_none(abr, 1000), float_or_none(vbr, 1000)
                     f.update({
-                        'acodec': acodec,
-                        'vcodec': vcodec,
+                        'vbr': vbr,
+                        'abr': abr,
                     })
+                f.update(parse_codecs(last_info.get('CODECS')))
                 if last_media is not None:
                     f['m3u8_media'] = last_media
                     last_media = None
@@ -1616,6 +1631,62 @@ class InfoExtractor(object):
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
         return formats
 
+    def _parse_html5_media_entries(self, base_url, webpage):
+        def absolute_url(video_url):
+            return compat_urlparse.urljoin(base_url, video_url)
+
+        def parse_content_type(content_type):
+            if not content_type:
+                return {}
+            ctr = re.search(r'(?P<mimetype>[^/]+/[^;]+)(?:;\s*codecs="?(?P<codecs>[^"]+))?', content_type)
+            if ctr:
+                mimetype, codecs = ctr.groups()
+                f = parse_codecs(codecs)
+                f['ext'] = mimetype2ext(mimetype)
+                return f
+            return {}
+
+        entries = []
+        for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage):
+            media_info = {
+                'formats': [],
+                'subtitles': {},
+            }
+            media_attributes = extract_attributes(media_tag)
+            src = media_attributes.get('src')
+            if src:
+                media_info['formats'].append({
+                    'url': absolute_url(src),
+                    'vcodec': 'none' if media_type == 'audio' else None,
+                })
+            media_info['thumbnail'] = media_attributes.get('poster')
+            if media_content:
+                for source_tag in re.findall(r'<source[^>]+>', media_content):
+                    source_attributes = extract_attributes(source_tag)
+                    src = source_attributes.get('src')
+                    if not src:
+                        continue
+                    f = parse_content_type(source_attributes.get('type'))
+                    f.update({
+                        'url': absolute_url(src),
+                        'vcodec': 'none' if media_type == 'audio' else None,
+                    })
+                    media_info['formats'].append(f)
+                for track_tag in re.findall(r'<track[^>]+>', media_content):
+                    track_attributes = extract_attributes(track_tag)
+                    kind = track_attributes.get('kind')
+                    if not kind or kind == 'subtitles':
+                        src = track_attributes.get('src')
+                        if not src:
+                            continue
+                        lang = track_attributes.get('srclang') or track_attributes.get('lang') or track_attributes.get('label')
+                        media_info['subtitles'].setdefault(lang, []).append({
+                            'url': absolute_url(src),
+                        })
+            if media_info['formats']:
+                entries.append(media_info)
+        return entries
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()

youtube_dl/extractor/dbtv.py

@@ -4,78 +4,47 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    float_or_none,
-    int_or_none,
-    clean_html,
-)
 
 
 class DBTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
+    _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:[^/]+/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
     _TESTS = [{
         'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
-        'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
+        'md5': '2e24f67936517b143a234b4cadf792ec',
         'info_dict': {
-            'id': '33100',
+            'id': '3649835190001',
             'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
             'ext': 'mp4',
             'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
             'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
-            'thumbnail': 're:https?://.*\.jpg$',
-            'timestamp': 1404039863.438,
+            'thumbnail': 're:https?://.*\.jpg',
+            'timestamp': 1404039863,
             'upload_date': '20140629',
             'duration': 69.544,
-            'view_count': int,
-            'categories': list,
-        }
+            'uploader_id': '1027729757001',
+        },
+        'add_ie': ['BrightcoveNew']
     }, {
         'url': 'http://dbtv.no/3649835190001',
         'only_matching': True,
     }, {
         'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
         'only_matching': True,
+    }, {
+        'url': 'http://dbtv.no/vice/5000634109001',
+        'only_matching': True,
+    }, {
+        'url': 'http://dbtv.no/filmtrailer/3359293614001',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id') or video_id
-
-        data = self._download_json(
-            'http://api.dbtv.no/discovery/%s' % video_id, display_id)
-
-        video = data['playlist'][0]
-
-        formats = [{
-            'url': f['URL'],
-            'vcodec': f.get('container'),
-            'width': int_or_none(f.get('width')),
-            'height': int_or_none(f.get('height')),
-            'vbr': float_or_none(f.get('rate'), 1000),
-            'filesize': int_or_none(f.get('size')),
-        } for f in video['renditions'] if 'URL' in f]
-
-        if not formats:
-            for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]:
-                if url_key in video:
-                    formats.append({
-                        'url': video[url_key],
-                        'format_id': format_id,
-                    })
-
-        self._sort_formats(formats)
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
 
         return {
-            'id': compat_str(video['id']),
+            '_type': 'url_transparent',
+            'url': 'http://players.brightcove.net/1027729757001/default_default/index.html?videoId=%s' % video_id,
+            'id': video_id,
             'display_id': display_id,
-            'title': video['title'],
-            'description': clean_html(video['desc']),
-            'thumbnail': video.get('splash') or video.get('thumb'),
-            'timestamp': float_or_none(video.get('publishedAt'), 1000),
-            'duration': float_or_none(video.get('length'), 1000),
-            'view_count': int_or_none(video.get('views')),
-            'categories': video.get('tags'),
-            'formats': formats,
+            'ie_key': 'BrightcoveNew',
         }

youtube_dl/extractor/ellentv.py

@@ -6,12 +6,13 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    NO_DEFAULT,
 )
 
 
 class EllenTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
         'md5': '4294cf98bc165f218aaa0b89e0fd8042',
         'info_dict': {
@@ -22,24 +23,47 @@ class EllenTVIE(InfoExtractor):
             'timestamp': 1428035648,
             'upload_date': '20150403',
             'uploader_id': 'batchUser',
-        }
-    }
+        },
+    }, {
+        # not available via http://widgets.ellentube.com/
+        'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
+        'info_dict': {
+            'id': '1_szkgu2m2',
+            'ext': 'flv',
+            'title': "Ellen's Amazingly Talented Audience",
+            'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
+            'timestamp': 1255140900,
+            'upload_date': '20091010',
+            'uploader_id': 'ellenkaltura@gmail.com',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(
-            'http://widgets.ellentube.com/videos/%s' % video_id,
-            video_id)
+        URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
 
-        partner_id = self._search_regex(
-            r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
+        for num, url_ in enumerate(URLS, 1):
+            webpage = self._download_webpage(
+                url_, video_id, fatal=num == len(URLS))
 
-        kaltura_id = self._search_regex(
-            [r'id="kaltura_player_([^"]+)"',
-             r"_wb_entry_id\s*:\s*'([^']+)",
-             r'data-kaltura-entry-id="([^"]+)'],
-            webpage, 'kaltura id')
+            default = NO_DEFAULT if num == len(URLS) else None
+
+            partner_id = self._search_regex(
+                r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
+                default=default)
+
+            kaltura_id = self._search_regex(
+                [r'id="kaltura_player_([^"]+)"',
+                 r"_wb_entry_id\s*:\s*'([^']+)",
+                 r'data-kaltura-entry-id="([^"]+)'],
+                webpage, 'kaltura id', default=default)
+
+            if partner_id and kaltura_id:
+                break
 
         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
 

youtube_dl/extractor/extractors.py

@@ -256,6 +256,7 @@ from .fivemin import FiveMinIE
 from .fivetv import FiveTVIE
 from .fktv import FKTVIE
 from .flickr import FlickrIE
+from .flipagram import FlipagramIE
 from .folketinget import FolketingetIE
 from .footyroom import FootyRoomIE
 from .formula1 import Formula1IE
@@ -679,6 +680,7 @@ from .rice import RICEIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rockstargames import RockstarGamesIE
+from .roosterteeth import RoosterTeethIE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtbf import RTBFIE
@@ -689,6 +691,7 @@ from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
 from .rtvnh import RTVNHIE
+from .rudo import RudoIE
 from .ruhd import RUHDIE
 from .ruleporn import RulePornIE
 from .rutube import (
@@ -986,6 +989,7 @@ from .viki import (
 from .vk import (
     VKIE,
     VKUserVideosIE,
+    VKWallPostIE,
 )
 from .vlive import VLiveIE
 from .vodlocker import VodlockerIE

youtube_dl/extractor/facebook.py

@@ -219,12 +219,25 @@ class FacebookIE(InfoExtractor):
 
         BEFORE = '{swf.addParam(param[0], param[1]);});'
         AFTER = '.forEach(function(variable) {swf.addVariable(variable[0], variable[1]);});'
-        m = re.search(re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER), webpage)
-        if m:
-            swf_params = m.group(1).replace('\\\\', '\\').replace('\\"', '"')
+        PATTERN = re.escape(BEFORE) + '(?:\n|\\\\n)(.*?)' + re.escape(AFTER)
+
+        for m in re.findall(PATTERN, webpage):
+            swf_params = m.replace('\\\\', '\\').replace('\\"', '"')
             data = dict(json.loads(swf_params))
             params_raw = compat_urllib_parse_unquote(data['params'])
-            video_data = json.loads(params_raw)['video_data']
+            video_data_candidate = json.loads(params_raw)['video_data']
+            for _, f in video_data_candidate.items():
+                if not f:
+                    continue
+                if isinstance(f, dict):
+                    f = [f]
+                if not isinstance(f, list):
+                    continue
+                if f[0].get('video_id') == video_id:
+                    video_data = video_data_candidate
+                    break
+            if video_data:
+                break
 
         def video_data_list2dict(video_data):
             ret = {}

youtube_dl/extractor/flipagram.py

@@ -0,0 +1,115 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    try_get,
+    unified_timestamp,
+)
+
+
+class FlipagramIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://flipagram.com/f/nyvTSJMKId',
+        'md5': '888dcf08b7ea671381f00fab74692755',
+        'info_dict': {
+            'id': 'nyvTSJMKId',
+            'ext': 'mp4',
+            'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
+            'description': 'md5:d55e32edc55261cae96a41fa85ff630e',
+            'duration': 35.571,
+            'timestamp': 1461244995,
+            'upload_date': '20160421',
+            'uploader': 'kitty juria',
+            'uploader_id': 'sjuria101',
+            'creator': 'kitty juria',
+            'view_count': int,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'comments': list,
+            'formats': 'mincount:2',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        video_data = self._parse_json(
+            self._search_regex(
+                r'window\.reactH2O\s*=\s*({.+});', webpage, 'video data'),
+            video_id)
+
+        flipagram = video_data['flipagram']
+        video = flipagram['video']
+
+        json_ld = self._search_json_ld(webpage, video_id, default=False)
+        title = json_ld.get('title') or flipagram['captionText']
+        description = json_ld.get('description') or flipagram.get('captionText')
+
+        formats = [{
+            'url': video['url'],
+            'width': int_or_none(video.get('width')),
+            'height': int_or_none(video.get('height')),
+            'filesize': int_or_none(video_data.get('size')),
+        }]
+
+        preview_url = try_get(
+            flipagram, lambda x: x['music']['track']['previewUrl'], compat_str)
+        if preview_url:
+            formats.append({
+                'url': preview_url,
+                'ext': 'm4a',
+                'vcodec': 'none',
+            })
+
+        self._sort_formats(formats)
+
+        counts = flipagram.get('counts', {})
+        user = flipagram.get('user', {})
+        video_data = flipagram.get('video', {})
+
+        thumbnails = [{
+            'url': self._proto_relative_url(cover['url']),
+            'width': int_or_none(cover.get('width')),
+            'height': int_or_none(cover.get('height')),
+            'filesize': int_or_none(cover.get('size')),
+        } for cover in flipagram.get('covers', []) if cover.get('url')]
+
+        # Note that this only retrieves comments that are initally loaded.
+        # For videos with large amounts of comments, most won't be retrieved.
+        comments = []
+        for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []):
+            text = comment.get('comment')
+            if not text or not isinstance(text, list):
+                continue
+            comments.append({
+                'author': comment.get('user', {}).get('name'),
+                'author_id': comment.get('user', {}).get('username'),
+                'id': comment.get('id'),
+                'text': text[0],
+                'timestamp': unified_timestamp(comment.get('created')),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': float_or_none(flipagram.get('duration'), 1000),
+            'thumbnails': thumbnails,
+            'timestamp': unified_timestamp(flipagram.get('iso8601Created')),
+            'uploader': user.get('name'),
+            'uploader_id': user.get('username'),
+            'creator': user.get('name'),
+            'view_count': int_or_none(counts.get('plays')),
+            'like_count': int_or_none(counts.get('likes')),
+            'repost_count': int_or_none(counts.get('reflips')),
+            'comment_count': int_or_none(counts.get('comments')),
+            'comments': comments,
+            'formats': formats,
+        }

youtube_dl/extractor/generic.py

@@ -1313,6 +1313,38 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Kaltura'],
         },
+        {
+            # Non-standard Vimeo embed
+            'url': 'https://openclassrooms.com/courses/understanding-the-web',
+            'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
+            'info_dict': {
+                'id': '148867247',
+                'ext': 'mp4',
+                'title': 'Understanding the web - Teaser',
+                'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
+                'upload_date': '20151214',
+                'uploader': 'OpenClassrooms',
+                'uploader_id': 'openclassrooms',
+            },
+            'add_ie': ['Vimeo'],
+        },
+        # {
+        #     # TODO: find another test
+        #     # http://schema.org/VideoObject
+        #     'url': 'https://flipagram.com/f/nyvTSJMKId',
+        #     'md5': '888dcf08b7ea671381f00fab74692755',
+        #     'info_dict': {
+        #         'id': 'nyvTSJMKId',
+        #         'ext': 'mp4',
+        #         'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
+        #         'description': '#love for cats.',
+        #         'timestamp': 1461244995,
+        #         'upload_date': '20160421',
+        #     },
+        #     'params': {
+        #         'force_generic_extractor': True,
+        #     },
+        # }
     ]
 
     def report_following_redirect(self, new_url):
@@ -2157,6 +2189,19 @@ class GenericIE(InfoExtractor):
         if embed_url:
             return self.url_result(embed_url)
 
+        # Looking for http://schema.org/VideoObject
+        json_ld = self._search_json_ld(
+            webpage, video_id, default=None, expected_type='VideoObject')
+        if json_ld and json_ld.get('url'):
+            info_dict.update({
+                'title': video_title or info_dict['title'],
+                'description': video_description,
+                'thumbnail': video_thumbnail,
+                'age_limit': age_limit
+            })
+            info_dict.update(json_ld)
+            return info_dict
+
         def check_video(vurl):
             if YoutubeIE.suitable(vurl):
                 return True

youtube_dl/extractor/leeco.py

@@ -23,6 +23,7 @@ from ..utils import (
     str_or_none,
     url_basename,
     urshift,
+    update_url_query,
 )
 
 
@@ -89,6 +90,10 @@ class LeIE(InfoExtractor):
         _loc3_ = self.ror(_loc3_, _loc2_ % 17)
         return _loc3_
 
+    # reversed from http://jstatic.letvcdn.com/sdk/player.js
+    def get_mms_key(self, time):
+        return self.ror(time, 8) ^ 185025305
+
     # see M3U8Encryption class in KLetvPlayer.swf
     @staticmethod
     def decrypt_m3u8(encrypted_data):
@@ -109,23 +114,7 @@ class LeIE(InfoExtractor):
 
         return bytes(_loc7_)
 
-    def _real_extract(self, url):
-        media_id = self._match_id(url)
-        page = self._download_webpage(url, media_id)
-        params = {
-            'id': media_id,
-            'platid': 1,
-            'splatid': 101,
-            'format': 1,
-            'tkey': self.calc_time_key(int(time.time())),
-            'domain': 'www.le.com'
-        }
-
-        play_json = self._download_json(
-            'http://api.le.com/mms/out/video/playJson',
-            media_id, 'Downloading playJson data', query=params,
-            headers=self.geo_verification_headers())
-
+    def _check_errors(self, play_json):
         # Check for errors
         playstatus = play_json['playstatus']
         if playstatus['status'] == 0:
@@ -136,43 +125,99 @@ class LeIE(InfoExtractor):
                 msg = 'Generic error. flag = %d' % flag
             raise ExtractorError(msg, expected=True)
 
-        playurl = play_json['playurl']
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        page = self._download_webpage(url, media_id)
 
-        formats = ['350', '1000', '1300', '720p', '1080p']
-        dispatch = playurl['dispatch']
+        play_json_h5 = self._download_json(
+            'http://api.le.com/mms/out/video/playJsonH5',
+            media_id, 'Downloading html5 playJson data', query={
+                'id': media_id,
+                'platid': 3,
+                'splatid': 304,
+                'format': 1,
+                'tkey': self.get_mms_key(int(time.time())),
+                'domain': 'www.le.com',
+                'tss': 'no',
+            },
+            headers=self.geo_verification_headers())
+        self._check_errors(play_json_h5)
 
-        urls = []
-        for format_id in formats:
-            if format_id in dispatch:
-                media_url = playurl['domain'][0] + dispatch[format_id][0]
-                media_url += '&' + compat_urllib_parse_urlencode({
-                    'm3v': 1,
+        play_json_flash = self._download_json(
+            'http://api.le.com/mms/out/video/playJson',
+            media_id, 'Downloading flash playJson data', query={
+                'id': media_id,
+                'platid': 1,
+                'splatid': 101,
+                'format': 1,
+                'tkey': self.calc_time_key(int(time.time())),
+                'domain': 'www.le.com',
+            },
+            headers=self.geo_verification_headers())
+        self._check_errors(play_json_flash)
+
+        def get_h5_urls(media_url, format_id):
+            location = self._download_json(
+                media_url, media_id,
+                'Download JSON metadata for format %s' % format_id, query={
                     'format': 1,
                     'expect': 3,
-                    'rateid': format_id,
-                })
+                    'tss': 'no',
+                })['location']
 
-                nodes_data = self._download_json(
-                    media_url, media_id,
-                    'Download JSON metadata for format %s' % format_id)
+            return {
+                'http': update_url_query(location, {'tss': 'no'}),
+                'hls': update_url_query(location, {'tss': 'ios'}),
+            }
 
-                req = self._request_webpage(
-                    nodes_data['nodelist'][0]['location'], media_id,
-                    note='Downloading m3u8 information for format %s' % format_id)
+        def get_flash_urls(media_url, format_id):
+            media_url += '&' + compat_urllib_parse_urlencode({
+                'm3v': 1,
+                'format': 1,
+                'expect': 3,
+                'rateid': format_id,
+            })
 
-                m3u8_data = self.decrypt_m3u8(req.read())
+            nodes_data = self._download_json(
+                media_url, media_id,
+                'Download JSON metadata for format %s' % format_id)
 
-                url_info_dict = {
-                    'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
-                    'ext': determine_ext(dispatch[format_id][1]),
-                    'format_id': format_id,
-                    'protocol': 'm3u8',
-                }
+            req = self._request_webpage(
+                nodes_data['nodelist'][0]['location'], media_id,
+                note='Downloading m3u8 information for format %s' % format_id)
 
-                if format_id[-1:] == 'p':
-                    url_info_dict['height'] = int_or_none(format_id[:-1])
+            m3u8_data = self.decrypt_m3u8(req.read())
 
-                urls.append(url_info_dict)
+            return {
+                'hls': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
+            }
+
+        extracted_formats = []
+        formats = []
+        for play_json, get_urls in ((play_json_h5, get_h5_urls), (play_json_flash, get_flash_urls)):
+            playurl = play_json['playurl']
+            play_domain = playurl['domain'][0]
+
+            for format_id, format_data in playurl.get('dispatch', []).items():
+                if format_id in extracted_formats:
+                    continue
+                extracted_formats.append(format_id)
+
+                media_url = play_domain + format_data[0]
+                for protocol, format_url in get_urls(media_url, format_id).items():
+                    f = {
+                        'url': format_url,
+                        'ext': determine_ext(format_data[1]),
+                        'format_id': '%s-%s' % (protocol, format_id),
+                        'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
+                        'quality': int_or_none(format_id),
+                    }
+
+                    if format_id[-1:] == 'p':
+                        f['height'] = int_or_none(format_id[:-1])
+
+                    formats.append(f)
+        self._sort_formats(formats, ('height', 'quality', 'format_id'))
 
         publish_time = parse_iso8601(self._html_search_regex(
             r'发布时间&nbsp;([^<>]+) ', page, 'publish time', default=None),
@@ -181,7 +226,7 @@ class LeIE(InfoExtractor):
 
         return {
             'id': media_id,
-            'formats': urls,
+            'formats': formats,
             'title': playurl['title'],
             'thumbnail': playurl['pic'],
             'description': description,

youtube_dl/extractor/lynda.py

@@ -100,7 +100,7 @@ class LyndaIE(LyndaBaseIE):
 
     _TESTS = [{
         'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
-        'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
+        # md5 is unstable
         'info_dict': {
             'id': '114408',
             'ext': 'mp4',

youtube_dl/extractor/mgtv.py

@@ -26,7 +26,8 @@ class MGTVIE(InfoExtractor):
         video_id = self._match_id(url)
         api_data = self._download_json(
             'http://v.api.mgtv.com/player/video', video_id,
-            query={'video_id': video_id})['data']
+            query={'video_id': video_id},
+            headers=self.geo_verification_headers())['data']
         info = api_data['info']
 
         formats = []

youtube_dl/extractor/miomio.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import random
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     xpath_text,
     int_or_none,
@@ -18,13 +19,16 @@ class MioMioIE(InfoExtractor):
     _TESTS = [{
         # "type=video" in flashvars
         'url': 'http://www.miomio.tv/watch/cc88912/',
-        'md5': '317a5f7f6b544ce8419b784ca8edae65',
         'info_dict': {
             'id': '88912',
             'ext': 'flv',
             'title': '【SKY】字幕 铠武昭和VS平成 假面骑士大战FEAT战队 魔星字幕组 字幕',
             'duration': 5923,
         },
+        'params': {
+            # The server provides broken file
+            'skip_download': True,
+        }
     }, {
         'url': 'http://www.miomio.tv/watch/cc184024/',
         'info_dict': {
@@ -32,7 +36,7 @@ class MioMioIE(InfoExtractor):
             'title': '《动漫同人插画绘制》',
         },
         'playlist_mincount': 86,
-        'skip': 'This video takes time too long for retrieving the URL',
+        'skip': 'Unable to load videos',
     }, {
         'url': 'http://www.miomio.tv/watch/cc173113/',
         'info_dict': {
@@ -40,20 +44,23 @@ class MioMioIE(InfoExtractor):
             'title': 'The New Macbook 2015 上手试玩与简评'
         },
         'playlist_mincount': 2,
+        'skip': 'Unable to load videos',
+    }, {
+        # new 'h5' player
+        'url': 'http://www.miomio.tv/watch/cc273295/',
+        'md5': '',
+        'info_dict': {
+            'id': '273295',
+            'ext': 'mp4',
+            'title': 'アウト×デラックス 20160526',
+        },
+        'params': {
+            # intermittent HTTP 500
+            'skip_download': True,
+        },
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        title = self._html_search_meta(
-            'description', webpage, 'title', fatal=True)
-
-        mioplayer_path = self._search_regex(
-            r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
-
-        http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
-
+    def _extract_mioplayer(self, webpage, video_id, title, http_headers):
         xml_config = self._search_regex(
             r'flashvars="type=(?:sina|video)&(.+?)&',
             webpage, 'xml config')
@@ -92,10 +99,34 @@ class MioMioIE(InfoExtractor):
                 'http_headers': http_headers,
             })
 
+        return entries
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_meta(
+            'description', webpage, 'title', fatal=True)
+
+        mioplayer_path = self._search_regex(
+            r'src="(/mioplayer(?:_h5)?/[^"]+)"', webpage, 'ref_path')
+
+        if '_h5' in mioplayer_path:
+            player_url = compat_urlparse.urljoin(url, mioplayer_path)
+            player_webpage = self._download_webpage(
+                player_url, video_id,
+                note='Downloading player webpage', headers={'Referer': url})
+            entries = self._parse_html5_media_entries(player_url, player_webpage)
+            http_headers = {'Referer': player_url}
+        else:
+            http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
+            entries = self._extract_mioplayer(webpage, video_id, title, http_headers)
+
         if len(entries) == 1:
             segment = entries[0]
             segment['id'] = video_id
             segment['title'] = title
+            segment['http_headers'] = http_headers
             return segment
 
         return {

youtube_dl/extractor/mitele.py

@@ -12,12 +12,69 @@ from ..utils import (
     get_element_by_attribute,
     int_or_none,
     remove_start,
+    extract_attributes,
+    determine_ext,
 )
 
 
-class MiTeleIE(InfoExtractor):
+class MiTeleBaseIE(InfoExtractor):
+    def _get_player_info(self, url, webpage):
+        player_data = extract_attributes(self._search_regex(
+            r'(?s)(<ms-video-player.+?</ms-video-player>)',
+            webpage, 'ms video player'))
+        video_id = player_data['data-media-id']
+        config_url = compat_urlparse.urljoin(url, player_data['data-config'])
+        config = self._download_json(
+            config_url, video_id, 'Downloading config JSON')
+        mmc_url = config['services']['mmc']
+
+        duration = None
+        formats = []
+        for m_url in (mmc_url, mmc_url.replace('/flash.json', '/html5.json')):
+            mmc = self._download_json(
+                m_url, video_id, 'Downloading mmc JSON')
+            if not duration:
+                duration = int_or_none(mmc.get('duration'))
+            for location in mmc['locations']:
+                gat = self._proto_relative_url(location.get('gat'), 'http:')
+                bas = location.get('bas')
+                loc = location.get('loc')
+                ogn = location.get('ogn')
+                if None in (gat, bas, loc, ogn):
+                    continue
+                token_data = {
+                    'bas': bas,
+                    'icd': loc,
+                    'ogn': ogn,
+                    'sta': '0',
+                }
+                media = self._download_json(
+                    '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)),
+                    video_id, 'Downloading %s JSON' % location['loc'])
+                file_ = media.get('file')
+                if not file_:
+                    continue
+                ext = determine_ext(file_)
+                if ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
+                        video_id, f4m_id='hds', fatal=False))
+                elif ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        file_, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'thumbnail': player_data.get('data-poster') or config.get('poster', {}).get('imageUrl'),
+            'duration': duration,
+        }
+
+
+class MiTeleIE(MiTeleBaseIE):
     IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
+    _VALID_URL = r'https?://www\.mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
 
     _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
@@ -25,7 +82,7 @@ class MiTeleIE(InfoExtractor):
         'info_dict': {
             'id': '0NF1jJnxS1Wu3pHrmvFyw2',
             'display_id': 'programa-144',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Tor, la web invisible',
             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
             'series': 'Diario de',
@@ -40,7 +97,7 @@ class MiTeleIE(InfoExtractor):
         'info_dict': {
             'id': 'eLZSwoEd1S3pVyUm8lc6F',
             'display_id': 'programa-226',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
             'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
             'series': 'Cuarto Milenio',
@@ -59,40 +116,7 @@ class MiTeleIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
 
-        config_url = self._search_regex(
-            r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
-        config_url = compat_urlparse.urljoin(url, config_url)
-
-        config = self._download_json(
-            config_url, display_id, 'Downloading config JSON')
-
-        mmc = self._download_json(
-            config['services']['mmc'], display_id, 'Downloading mmc JSON')
-
-        formats = []
-        for location in mmc['locations']:
-            gat = self._proto_relative_url(location.get('gat'), 'http:')
-            bas = location.get('bas')
-            loc = location.get('loc')
-            ogn = location.get('ogn')
-            if None in (gat, bas, loc, ogn):
-                continue
-            token_data = {
-                'bas': bas,
-                'icd': loc,
-                'ogn': ogn,
-                'sta': '0',
-            }
-            media = self._download_json(
-                '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)),
-                display_id, 'Downloading %s JSON' % location['loc'])
-            file_ = media.get('file')
-            if not file_:
-                continue
-            formats.extend(self._extract_f4m_formats(
-                file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
-                display_id, f4m_id=loc))
-        self._sort_formats(formats)
+        info = self._get_player_info(url, webpage)
 
         title = self._search_regex(
             r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
@@ -112,21 +136,12 @@ class MiTeleIE(InfoExtractor):
                 title = remove_start(self._search_regex(
                     r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
 
-        video_id = self._search_regex(
-            r'data-media-id\s*=\s*"([^"]+)"', webpage,
-            'data media id', default=None) or display_id
-        thumbnail = config.get('poster', {}).get('imageUrl')
-        duration = int_or_none(mmc.get('duration'))
-
-        return {
-            'id': video_id,
+        info.update({
             'display_id': display_id,
             'title': title,
             'description': get_element_by_attribute('class', 'text', webpage),
             'series': series,
             'season': season,
             'episode': episode,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'formats': formats,
-        }
+        })
+        return info

youtube_dl/extractor/nick.py

@@ -8,7 +8,7 @@ from ..utils import update_url_query
 
 class NickIE(MTVServicesInfoExtractor):
     IE_NAME = 'nick.com'
-    _VALID_URL = r'https?://(?:www\.)?nick\.com/videos/clip/(?P<id>[^/?#.]+)'
+    _VALID_URL = r'https?://(?:www\.)?nick(?:jr)?\.com/(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
     _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'
     _TESTS = [{
         'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html',
@@ -52,6 +52,9 @@ class NickIE(MTVServicesInfoExtractor):
                 }
             },
         ],
+    }, {
+        'url': 'http://www.nickjr.com/paw-patrol/videos/pups-save-a-goldrush-s3-ep302-full-episode/',
+        'only_matching': True,
     }]
 
     def _get_feed_query(self, uri):

youtube_dl/extractor/playvid.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 class PlayvidIE(InfoExtractor):
     _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
         'md5': 'ffa2f6b2119af359f544388d8c01eb6c',
         'info_dict': {
@@ -24,8 +24,19 @@ class PlayvidIE(InfoExtractor):
             'title': 'md5:9256d01c6317e3f703848b5906880dc8',
             'duration': 82,
             'age_limit': 18,
-        }
-    }
+        },
+        'skip': 'Video removed due to ToS',
+    }, {
+        'url': 'http://www.playvid.com/watch/hwb0GpNkzgH',
+        'md5': '39d49df503ad7b8f23a4432cbf046477',
+        'info_dict': {
+            'id': 'hwb0GpNkzgH',
+            'ext': 'mp4',
+            'title': 'Ellen Euro Cutie Blond Takes a Sexy Survey Get Facial in The Park',
+            'age_limit': 18,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/polskieradio.py

@@ -33,6 +33,7 @@ class PolskieRadioIE(InfoExtractor):
                 'timestamp': 1456594200,
                 'upload_date': '20160227',
                 'duration': 2364,
+                'thumbnail': 're:^https?://static\.prsa\.pl/images/.*\.jpg$'
             },
         }],
     }, {
@@ -68,6 +69,8 @@ class PolskieRadioIE(InfoExtractor):
             r'(?s)<span[^>]+id="datetime2"[^>]*>(.+?)</span>',
             webpage, 'timestamp', fatal=False))
 
+        thumbnail_url = self._og_search_thumbnail(webpage)
+
         entries = []
 
         media_urls = set()
@@ -87,6 +90,7 @@ class PolskieRadioIE(InfoExtractor):
                 'duration': int_or_none(media.get('length')),
                 'vcodec': 'none' if media.get('provider') == 'audio' else None,
                 'timestamp': timestamp,
+                'thumbnail': thumbnail_url
             })
 
         title = self._og_search_title(webpage).strip()

youtube_dl/extractor/radiocanada.py

@@ -12,6 +12,7 @@ from ..utils import (
     unified_strdate,
     xpath_element,
     ExtractorError,
+    determine_protocol,
 )
 
 
@@ -22,13 +23,13 @@ class RadioCanadaIE(InfoExtractor):
         'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
         'info_dict': {
             'id': '7184272',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Le parcours du tireur capté sur vidéo',
             'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
             'upload_date': '20141023',
         },
         'params': {
-            # rtmp download
+            # m3u8 download
             'skip_download': True,
         },
     }
@@ -36,11 +37,14 @@ class RadioCanadaIE(InfoExtractor):
     def _real_extract(self, url):
         app_code, video_id = re.match(self._VALID_URL, url).groups()
 
+        device_types = ['ipad', 'android']
+        if app_code != 'toutv':
+            device_types.append('flash')
+
         formats = []
-        # TODO: extract m3u8 and f4m formats
-        # m3u8 formats can be extracted using ipad device_type return 403 error code when ffmpeg try to download segements
+        # TODO: extract f4m formats
         # f4m formats can be extracted using flashhd device_type but they produce unplayable file
-        for device_type in ('flash',):
+        for device_type in device_types:
             v_data = self._download_xml(
                 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx',
                 video_id, note='Downloading %s XML' % device_type, query={
@@ -52,7 +56,7 @@ class RadioCanadaIE(InfoExtractor):
                     # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
                     'paysJ391wsHjbOJwvCs26toz': 'CA',
                     'bypasslock': 'NZt5K62gRqfc',
-                })
+                }, fatal=False)
             v_url = xpath_text(v_data, 'url')
             if not v_url:
                 continue
@@ -64,7 +68,8 @@ class RadioCanadaIE(InfoExtractor):
                 formats.extend(self._extract_m3u8_formats(
                     v_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
             elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(v_url, video_id, f4m_id='hds', fatal=False))
+                formats.extend(self._extract_f4m_formats(
+                    v_url, video_id, f4m_id='hds', fatal=False))
             else:
                 ext = determine_ext(v_url)
                 bitrates = xpath_element(v_data, 'bitrates')
@@ -72,15 +77,28 @@ class RadioCanadaIE(InfoExtractor):
                     tbr = int_or_none(url_e.get('bitrate'))
                     if not tbr:
                         continue
+                    f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
+                    protocol = determine_protocol({'url': f_url})
                     formats.append({
-                        'format_id': 'rtmp-%d' % tbr,
-                        'url': re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url),
-                        'ext': 'flv',
-                        'protocol': 'rtmp',
+                        'format_id': '%s-%d' % (protocol, tbr),
+                        'url': f_url,
+                        'ext': 'flv' if protocol == 'rtmp' else ext,
+                        'protocol': protocol,
                         'width': int_or_none(url_e.get('width')),
                         'height': int_or_none(url_e.get('height')),
                         'tbr': tbr,
                     })
+                    if protocol == 'rtsp':
+                        base_url = self._search_regex(
+                            r'rtsp://([^?]+)', f_url, 'base url', default=None)
+                        if base_url:
+                            base_url = 'http://' + base_url
+                            formats.extend(self._extract_m3u8_formats(
+                                base_url + '/playlist.m3u8', video_id, 'mp4',
+                                'm3u8_native', m3u8_id='hls', fatal=False))
+                            formats.extend(self._extract_f4m_formats(
+                                base_url + '/manifest.f4m', video_id,
+                                f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
         metadata = self._download_xml(
@@ -115,13 +133,13 @@ class RadioCanadaAudioVideoIE(InfoExtractor):
         'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam',
         'info_dict': {
             'id': '7527184',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Barack Obama au Vietnam',
             'description': 'Les États-Unis lèvent l\'embargo sur la vente d\'armes qui datait de la guerre du Vietnam',
             'upload_date': '20160523',
         },
         'params': {
-            # rtmp download
+            # m3u8 download
             'skip_download': True,
         },
     }

youtube_dl/extractor/roosterteeth.py

@@ -0,0 +1,148 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    strip_or_none,
+    unescapeHTML,
+    urlencode_postdata,
+)
+
+
+class RoosterTeethIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
+    _LOGIN_URL = 'https://roosterteeth.com/login'
+    _NETRC_MACHINE = 'roosterteeth'
+    _TESTS = [{
+        'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
+        'md5': 'e2bd7764732d785ef797700a2489f212',
+        'info_dict': {
+            'id': '26576',
+            'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
+            'ext': 'mp4',
+            'title': 'Million Dollars, But...: Million Dollars, But... The Game Announcement',
+            'description': 'md5:0cc3b21986d54ed815f5faeccd9a9ca5',
+            'thumbnail': 're:^https?://.*\.png$',
+            'series': 'Million Dollars, But...',
+            'episode': 'Million Dollars, But... The Game Announcement',
+            'comment_count': int,
+        },
+    }, {
+        'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
+        'only_matching': True,
+    }, {
+        'url': 'http://funhaus.roosterteeth.com/episode/funhaus-shorts-2016-austin-sucks-funhaus-shorts',
+        'only_matching': True,
+    }, {
+        'url': 'http://screwattack.roosterteeth.com/episode/death-battle-season-3-mewtwo-vs-shadow',
+        'only_matching': True,
+    }, {
+        'url': 'http://theknow.roosterteeth.com/episode/the-know-game-news-season-1-boring-steam-sales-are-better',
+        'only_matching': True,
+    }, {
+        # only available for FIRST members
+        'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
+        'only_matching': True,
+    }]
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None,
+            note='Downloading login page',
+            errnote='Unable to download login page')
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'username': username,
+            'password': password,
+        })
+
+        login_request = self._download_webpage(
+            self._LOGIN_URL, None,
+            note='Logging in as %s' % username,
+            data=urlencode_postdata(login_form),
+            headers={
+                'Referer': self._LOGIN_URL,
+            })
+
+        if not any(re.search(p, login_request) for p in (
+                r'href=["\']https?://(?:www\.)?roosterteeth\.com/logout"',
+                r'>Sign Out<')):
+            error = self._html_search_regex(
+                r'(?s)<div[^>]+class=(["\']).*?\balert-danger\b.*?\1[^>]*>(?:\s*<button[^>]*>.*?</button>)?(?P<error>.+?)</div>',
+                login_request, 'alert', default=None, group='error')
+            if error:
+                raise ExtractorError('Unable to login: %s' % error, expected=True)
+            raise ExtractorError('Unable to log in')
+
+    def _real_initialize(self):
+        self._login()
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        episode = strip_or_none(unescapeHTML(self._search_regex(
+            (r'videoTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'<title>(?P<title>[^<]+)</title>'), webpage, 'title',
+            default=None, group='title')))
+
+        title = strip_or_none(self._og_search_title(
+            webpage, default=None)) or episode
+
+        m3u8_url = self._search_regex(
+            r'file\s*:\s*(["\'])(?P<url>http.+?\.m3u8.*?)\1',
+            webpage, 'm3u8 url', default=None, group='url')
+
+        if not m3u8_url:
+            if re.search(r'<div[^>]+class=["\']non-sponsor', webpage):
+                self.raise_login_required(
+                    '%s is only available for FIRST members' % display_id)
+
+            if re.search(r'<div[^>]+class=["\']golive-gate', webpage):
+                self.raise_login_required('%s is not available yet' % display_id)
+
+            raise ExtractorError('Unable to extract m3u8 URL')
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, display_id, ext='mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        description = strip_or_none(self._og_search_description(webpage))
+        thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage))
+
+        series = self._search_regex(
+            (r'<h2>More ([^<]+)</h2>', r'<a[^>]+>See All ([^<]+) Videos<'),
+            webpage, 'series', fatal=False)
+
+        comment_count = int_or_none(self._search_regex(
+            r'>Comments \((\d+)\)<', webpage,
+            'comment count', fatal=False))
+
+        video_id = self._search_regex(
+            (r'containerId\s*=\s*["\']episode-(\d+)\1',
+             r'<div[^<]+id=["\']episode-(\d+)'), webpage,
+            'video id', default=display_id)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'series': series,
+            'episode': episode,
+            'comment_count': comment_count,
+            'formats': formats,
+        }

youtube_dl/extractor/rudo.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    js_to_json,
+    get_element_by_class,
+    unified_strdate,
+)
+
+
+class RudoIE(JWPlatformBaseIE):
+    _VALID_URL = r'https?://rudo\.video/vod/(?P<id>[0-9a-zA-Z]+)'
+
+    _TEST = {
+        'url': 'http://rudo.video/vod/oTzw0MGnyG',
+        'md5': '2a03a5b32dd90a04c83b6d391cf7b415',
+        'info_dict': {
+            'id': 'oTzw0MGnyG',
+            'ext': 'mp4',
+            'title': 'Comentario Tomás Mosciatti',
+            'upload_date': '20160617',
+        },
+    }
+
+    @classmethod
+    def _extract_url(self, webpage):
+        mobj = re.search(
+            '<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id, encoding='iso-8859-1')
+
+        jwplayer_data = self._parse_json(self._search_regex(
+            r'(?s)playerInstance\.setup\(({.+?})\)', webpage, 'jwplayer data'), video_id,
+            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')
+
+        info_dict.update({
+            'title': self._og_search_title(webpage),
+            'upload_date': unified_strdate(get_element_by_class('date', webpage)),
+        })
+
+        return info_dict

youtube_dl/extractor/shahid.py

@@ -2,11 +2,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlencode
 from ..utils import (
     ExtractorError,
     int_or_none,
     parse_iso8601,
+    str_or_none,
 )
 
 
@@ -33,45 +33,27 @@ class ShahidIE(InfoExtractor):
         'only_matching': True
     }]
 
-    def _handle_error(self, response):
-        if not isinstance(response, dict):
-            return
-        error = response.get('error')
+    def _call_api(self, path, video_id, note):
+        data = self._download_json(
+            'http://api.shahid.net/api/v1_1/' + path, video_id, note, query={
+                'apiKey': 'sh@hid0nlin3',
+                'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
+            }).get('data', {})
+
+        error = data.get('error')
         if error:
             raise ExtractorError(
                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
                 expected=True)
 
-    def _download_json(self, url, video_id, note='Downloading JSON metadata'):
-        response = super(ShahidIE, self)._download_json(url, video_id, note)['data']
-        self._handle_error(response)
-        return response
+        return data
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-
-        api_vars = {
-            'id': video_id,
-            'type': 'player',
-            'url': 'http://api.shahid.net/api/v1_1',
-            'playerType': 'episode',
-        }
-
-        flashvars = self._search_regex(
-            r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None)
-        if flashvars:
-            for key in api_vars.keys():
-                value = self._search_regex(
-                    r'\b%s\s*:\s*(?P<q>["\'])(?P<value>.+?)(?P=q)' % key,
-                    flashvars, 'type', default=None, group='value')
-                if value:
-                    api_vars[key] = value
-
-        player = self._download_json(
-            'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html'
-            % (video_id, api_vars['type']), video_id, 'Downloading player JSON')
+        player = self._call_api(
+            'Content/Episode/%s' % video_id,
+            video_id, 'Downloading player JSON')
 
         if player.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
@@ -79,22 +61,11 @@ class ShahidIE(InfoExtractor):
         formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
         self._sort_formats(formats)
 
-        video = self._download_json(
-            '%s/%s/%s?%s' % (
-                api_vars['url'], api_vars['playerType'], api_vars['id'],
-                compat_urllib_parse_urlencode({
-                    'apiKey': 'sh@hid0nlin3',
-                    'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-                })),
-            video_id, 'Downloading video JSON')
-
-        video = video[api_vars['playerType']]
+        video = self._call_api(
+            'episode/%s' % video_id, video_id,
+            'Downloading video JSON')['episode']
 
         title = video['title']
-        description = video.get('description')
-        thumbnail = video.get('thumbnailUrl')
-        duration = int_or_none(video.get('duration'))
-        timestamp = parse_iso8601(video.get('referenceDate'))
         categories = [
             category['name']
             for category in video.get('genres', []) if 'name' in category]
@@ -102,10 +73,16 @@ class ShahidIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
+            'description': video.get('description'),
+            'thumbnail': video.get('thumbnailUrl'),
+            'duration': int_or_none(video.get('duration')),
+            'timestamp': parse_iso8601(video.get('referenceDate')),
             'categories': categories,
+            'series': video.get('showTitle') or video.get('showName'),
+            'season': video.get('seasonTitle'),
+            'season_number': int_or_none(video.get('seasonNumber')),
+            'season_id': str_or_none(video.get('seasonId')),
+            'episode_number': int_or_none(video.get('number')),
+            'episode_id': video_id,
             'formats': formats,
         }

youtube_dl/extractor/srmediathek.py

@@ -11,7 +11,7 @@ from ..utils import (
 class SRMediathekIE(ARDMediathekIE):
     IE_NAME = 'sr:mediathek'
     IE_DESC = 'Saarländischer Rundfunk'
-    _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
 
     _TESTS = [{
         'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
@@ -35,7 +35,9 @@ class SRMediathekIE(ARDMediathekIE):
             # m3u8 download
             'skip_download': True,
         },
-        'expected_warnings': ['Unable to download f4m manifest']
+    }, {
+        'url': 'http://sr-mediathek.de/index.php?seite=7&id=7480',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/telecinco.py

@@ -1,50 +1,41 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_unquote,
-    compat_urllib_parse_urlencode,
-    compat_urlparse,
-)
-from ..utils import (
-    get_element_by_attribute,
-    parse_duration,
-    strip_jsonp,
-)
+from .mitele import MiTeleBaseIE
 
 
-class TelecincoIE(InfoExtractor):
+class TelecincoIE(MiTeleBaseIE):
     IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
     _VALID_URL = r'https?://www\.(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
 
     _TESTS = [{
         'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
-        'md5': '5cbef3ad5ef17bf0d21570332d140729',
+        'md5': '8d7b2d5f699ee2709d992a63d5cd1712',
         'info_dict': {
-            'id': 'MDSVID20141015_0058',
+            'id': 'JEA5ijCnF6p5W08A1rNKn7',
             'ext': 'mp4',
-            'title': 'Con Martín Berasategui, hacer un bacalao al ...',
+            'title': 'Bacalao con kokotxas al pil-pil',
+            'description': 'md5:1382dacd32dd4592d478cbdca458e5bb',
             'duration': 662,
         },
     }, {
         'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
-        'md5': '0a5b9f3cc8b074f50a0578f823a12694',
+        'md5': '284393e5387b3b947b77c613ef04749a',
         'info_dict': {
-            'id': 'MDSVID20150916_0128',
+            'id': 'jn24Od1zGLG4XUZcnUnZB6',
             'ext': 'mp4',
-            'title': '¿Quién es este ex futbolista con el que hablan ...',
+            'title': '¿Quién es este ex futbolista con el que hablan Leo Messi y Luis Suárez?',
+            'description': 'md5:a62ecb5f1934fc787107d7b9a2262805',
             'duration': 79,
         },
     }, {
         'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
-        'md5': 'ad1bfaaba922dd4a295724b05b68f86a',
+        'md5': '749afab6ea5a136a8806855166ae46a2',
         'info_dict': {
-            'id': 'MDSVID20150513_0220',
+            'id': 'aywerkD2Sv1vGNqq9b85Q2',
             'ext': 'mp4',
             'title': '#DOYLACARA. Con la trata no hay trato',
+            'description': 'md5:2771356ff7bfad9179c5f5cd954f1477',
             'duration': 50,
         },
     }, {
@@ -56,40 +47,16 @@ class TelecincoIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        episode = self._match_id(url)
-        webpage = self._download_webpage(url, episode)
-        embed_data_json = self._search_regex(
-            r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
-        ).replace('\'', '"')
-        embed_data = json.loads(embed_data_json)
-
-        domain = embed_data['mediaUrl']
-        if not domain.startswith('http'):
-            # only happens in telecinco.es videos
-            domain = 'http://' + domain
-        info_url = compat_urlparse.urljoin(
-            domain,
-            compat_urllib_parse_unquote(embed_data['flashvars']['host'])
-        )
-        info_el = self._download_xml(info_url, episode).find('./video/info')
-
-        video_link = info_el.find('videoUrl/link').text
-        token_query = compat_urllib_parse_urlencode({'id': video_link})
-        token_info = self._download_json(
-            embed_data['flashvars']['ov_tk'] + '?' + token_query,
-            episode,
-            transform_source=strip_jsonp
-        )
-        formats = self._extract_m3u8_formats(
-            token_info['tokenizedUrl'], episode, ext='mp4', entry_protocol='m3u8_native')
-        self._sort_formats(formats)
-
-        return {
-            'id': embed_data['videoId'],
-            'display_id': episode,
-            'title': info_el.find('title').text,
-            'formats': formats,
-            'description': get_element_by_attribute('class', 'text', webpage),
-            'thumbnail': info_el.find('thumb').text,
-            'duration': parse_duration(info_el.find('duration').text),
-        }
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        title = self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage, 'title')
+        info = self._get_player_info(url, webpage)
+        info.update({
+            'display_id': display_id,
+            'title': title,
+            'description': self._html_search_meta(
+                ['og:description', 'twitter:description'],
+                webpage, 'title', fatal=False),
+        })
+        return info

youtube_dl/extractor/tmz.py

@@ -5,31 +5,27 @@ from .common import InfoExtractor
 
 
 class TMZIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/]+)/?'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/?#]+)'
+    _TESTS = [{
         'url': 'http://www.tmz.com/videos/0_okj015ty/',
-        'md5': '791204e3bf790b1426cb2db0706184c0',
+        'md5': '4d22a51ef205b6c06395d8394f72d560',
         'info_dict': {
             'id': '0_okj015ty',
-            'url': 'http://tmz.vo.llnwd.net/o28/2014-03/13/0_okj015ty_0_rt8ro3si_2.mp4',
             'ext': 'mp4',
             'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!',
             'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie???  Or is she just showing off her amazing boobs?',
-            'thumbnail': r're:http://cdnbakmi\.kaltura\.com/.*thumbnail.*',
+            'timestamp': 1394747163,
+            'uploader_id': 'batchUser',
+            'upload_date': '20140313',
         }
-    }
+    }, {
+        'url': 'http://www.tmz.com/videos/0-cegprt2p/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        return {
-            'id': video_id,
-            'url': self._html_search_meta('VideoURL', webpage, fatal=True),
-            'title': self._og_search_title(webpage),
-            'description': self._og_search_description(webpage),
-            'thumbnail': self._html_search_meta('ThumbURL', webpage),
-        }
+        video_id = self._match_id(url).replace('-', '_')
+        return self.url_result('kaltura:591531:%s' % video_id, 'Kaltura', video_id)
 
 
 class TMZArticleIE(InfoExtractor):

youtube_dl/extractor/toutv.py

@@ -1,74 +1,41 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    unified_strdate,
-)
+from ..utils import int_or_none
 
 
 class TouTvIE(InfoExtractor):
     IE_NAME = 'tou.tv'
-    _VALID_URL = r'https?://www\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/(?P<episode>S[0-9]+E[0-9]+)))'
+    _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+/S[0-9]+E[0-9]+)'
 
     _TEST = {
-        'url': 'http://www.tou.tv/30-vies/S04E41',
+        'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
         'info_dict': {
-            'id': '30-vies_S04E41',
+            'id': '122017',
             'ext': 'mp4',
-            'title': '30 vies Saison 4 / Épisode 41',
-            'description': 'md5:da363002db82ccbe4dafeb9cab039b09',
-            'age_limit': 8,
-            'uploader': 'Groupe des Nouveaux Médias',
-            'duration': 1296,
-            'upload_date': '20131118',
-            'thumbnail': 'http://static.tou.tv/medias/images/2013-11-18_19_00_00_30VIES_0341_01_L.jpeg',
+            'title': 'Saison 2015 Épisode 17',
+            'description': 'La photo de famille 2',
+            'upload_date': '20100717',
         },
         'params': {
-            'skip_download': True,  # Requires rtmpdump
+            # m3u8 download
+            'skip_download': True,
         },
-        'skip': 'Only available in Canada'
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-
-        mediaId = self._search_regex(
-            r'"idMedia":\s*"([^"]+)"', webpage, 'media ID')
-
-        streams_url = 'http://release.theplatform.com/content.select?pid=' + mediaId
-        streams_doc = self._download_xml(
-            streams_url, video_id, note='Downloading stream list')
-
-        video_url = next(n.text
-                         for n in streams_doc.findall('.//choice/url')
-                         if '//ad.doubleclick' not in n.text)
-        if video_url.endswith('/Unavailable.flv'):
-            raise ExtractorError(
-                'Access to this video is blocked from outside of Canada',
-                expected=True)
-
-        duration_str = self._html_search_meta(
-            'video:duration', webpage, 'duration')
-        duration = int(duration_str) if duration_str else None
-        upload_date_str = self._html_search_meta(
-            'video:release_date', webpage, 'upload date')
-        upload_date = unified_strdate(upload_date_str) if upload_date_str else None
+        path = self._match_id(url)
+        metadata = self._download_json('http://ici.tou.tv/presentation/%s' % path, path)
+        video_id = metadata['IdMedia']
+        details = metadata['Details']
+        title = details['OriginalTitle']
 
         return {
+            '_type': 'url_transparent',
+            'url': 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id),
             'id': video_id,
-            'title': self._og_search_title(webpage),
-            'url': video_url,
-            'description': self._og_search_description(webpage),
-            'uploader': self._dc_search_uploader(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'age_limit': self._media_rating_search(webpage),
-            'duration': duration,
-            'upload_date': upload_date,
-            'ext': 'mp4',
+            'title': title,
+            'thumbnail': details.get('ImageUrl'),
+            'duration': int_or_none(details.get('LengthInSeconds')),
         }

youtube_dl/extractor/tvplay.py

@@ -8,43 +8,36 @@ from ..compat import compat_str
 from ..utils import (
     parse_iso8601,
     qualities,
+    determine_ext,
+    update_url_query,
+    int_or_none,
 )
 
 
 class TVPlayIE(InfoExtractor):
     IE_DESC = 'TV3Play and related services'
     _VALID_URL = r'''(?x)https?://(?:www\.)?
-        (?:tvplay\.lv/parraides|
-           tv3play\.lt/programos|
-           play\.tv3\.lt/programos|
-           tv3play\.ee/sisu|
-           tv3play\.se/program|
-           tv6play\.se/program|
-           tv8play\.se/program|
-           tv10play\.se/program|
-           tv3play\.no/programmer|
-           viasat4play\.no/programmer|
-           tv6play\.no/programmer|
-           tv3play\.dk/programmer|
+        (?:tvplay(?:\.skaties)?\.lv/parraides|
+           (?:tv3play|play\.tv3)\.lt/programos|
+           tv3play(?:\.tv3)?\.ee/sisu|
+           tv(?:3|6|8|10)play\.se/program|
+           (?:(?:tv3play|viasat4play|tv6play)\.no|tv3play\.dk)/programmer|
            play\.novatv\.bg/programi
         )/[^/]+/(?P<id>\d+)
         '''
     _TESTS = [
         {
             'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
+            'md5': 'a1612fe0849455423ad8718fe049be21',
             'info_dict': {
                 'id': '418113',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Kādi ir īri? - Viņas melo labāk',
                 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
                 'duration': 25,
                 'timestamp': 1406097056,
                 'upload_date': '20140723',
             },
-            'params': {
-                # rtmp download
-                'skip_download': True,
-            },
         },
         {
             'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
@@ -82,7 +75,7 @@ class TVPlayIE(InfoExtractor):
             'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
             'info_dict': {
                 'id': '395385',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Husräddarna S02E07',
                 'description': 'md5:f210c6c89f42d4fc39faa551be813777',
                 'duration': 2574,
@@ -90,7 +83,6 @@ class TVPlayIE(InfoExtractor):
                 'upload_date': '20140520',
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -98,7 +90,7 @@ class TVPlayIE(InfoExtractor):
             'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
             'info_dict': {
                 'id': '266636',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Den sista dokusåpan S01E08',
                 'description': 'md5:295be39c872520221b933830f660b110',
                 'duration': 1492,
@@ -107,7 +99,6 @@ class TVPlayIE(InfoExtractor):
                 'age_limit': 18,
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -115,7 +106,7 @@ class TVPlayIE(InfoExtractor):
             'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
             'info_dict': {
                 'id': '282756',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Antikjakten S01E10',
                 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
                 'duration': 2646,
@@ -123,7 +114,6 @@ class TVPlayIE(InfoExtractor):
                 'upload_date': '20120925',
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -131,7 +121,7 @@ class TVPlayIE(InfoExtractor):
             'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
             'info_dict': {
                 'id': '230898',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Anna Anka søker assistent - Ep. 8',
                 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
                 'duration': 2656,
@@ -139,7 +129,6 @@ class TVPlayIE(InfoExtractor):
                 'upload_date': '20100628',
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -147,7 +136,7 @@ class TVPlayIE(InfoExtractor):
             'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
             'info_dict': {
                 'id': '21873',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Budbringerne program 10',
                 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
                 'duration': 1297,
@@ -155,7 +144,6 @@ class TVPlayIE(InfoExtractor):
                 'upload_date': '20090929',
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -163,7 +151,7 @@ class TVPlayIE(InfoExtractor):
             'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
             'info_dict': {
                 'id': '361883',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
                 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
                 'duration': 2594,
@@ -171,7 +159,6 @@ class TVPlayIE(InfoExtractor):
                 'upload_date': '20140224',
             },
             'params': {
-                # rtmp download
                 'skip_download': True,
             },
         },
@@ -191,6 +178,14 @@ class TVPlayIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
@@ -199,7 +194,9 @@ class TVPlayIE(InfoExtractor):
         video = self._download_json(
             'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON')
 
-        if video['is_geo_blocked']:
+        title = video['title']
+
+        if video.get('is_geo_blocked'):
             self.report_warning(
                 'This content might not be available in your country due to copyright reasons')
 
@@ -208,42 +205,50 @@ class TVPlayIE(InfoExtractor):
 
         quality = qualities(['hls', 'medium', 'high'])
         formats = []
-        for format_id, video_url in streams['streams'].items():
+        for format_id, video_url in streams.get('streams', {}).items():
             if not video_url or not isinstance(video_url, compat_str):
                 continue
-            fmt = {
-                'format_id': format_id,
-                'preference': quality(format_id),
-            }
-            if video_url.startswith('rtmp'):
-                m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
-                if not m:
-                    continue
-                fmt.update({
-                    'ext': 'flv',
-                    'url': m.group('url'),
-                    'app': m.group('app'),
-                    'play_path': m.group('playpath'),
-                })
-            elif video_url.endswith('.f4m'):
+            ext = determine_ext(video_url)
+            if ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
-                    video_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id))
-                continue
+                    update_url_query(video_url, {
+                        'hdcore': '3.5.0',
+                        'plugin': 'aasp-3.5.0.151.81'
+                    }), video_id, f4m_id='hds', fatal=False))
+            elif ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
             else:
-                fmt.update({
-                    'url': video_url,
-                })
-            formats.append(fmt)
-
+                fmt = {
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'ext': ext,
+                }
+                if video_url.startswith('rtmp'):
+                    m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
+                    if not m:
+                        continue
+                    fmt.update({
+                        'ext': 'flv',
+                        'url': m.group('url'),
+                        'app': m.group('app'),
+                        'play_path': m.group('playpath'),
+                    })
+                else:
+                    fmt.update({
+                        'url': video_url,
+                    })
+                formats.append(fmt)
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': video['title'],
-            'description': video['description'],
-            'duration': video['duration'],
-            'timestamp': parse_iso8601(video['created_at']),
-            'view_count': video['views']['total'],
-            'age_limit': video.get('age_limit', 0),
+            'title': title,
+            'description': video.get('description'),
+            'duration': int_or_none(video.get('duration')),
+            'timestamp': parse_iso8601(video.get('created_at')),
+            'view_count': int_or_none(video.get('views', {}).get('total')),
+            'age_limit': int_or_none(video.get('age_limit', 0)),
             'formats': formats,
         }

youtube_dl/extractor/tweakers.py

@@ -1,25 +1,62 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    determine_ext,
+    mimetype2ext,
+)
 
 
 class TweakersIE(InfoExtractor):
     _VALID_URL = r'https?://tweakers\.net/video/(?P<id>\d+)'
     _TEST = {
         'url': 'https://tweakers.net/video/9926/new-nintendo-3ds-xl-op-alle-fronten-beter.html',
-        'md5': '3147e4ddad366f97476a93863e4557c8',
+        'md5': 'fe73e417c093a788e0160c4025f88b15',
         'info_dict': {
             'id': '9926',
             'ext': 'mp4',
             'title': 'New Nintendo 3DS XL - Op alle fronten beter',
-            'description': 'md5:f97324cc71e86e11c853f0763820e3ba',
+            'description': 'md5:3789b21fed9c0219e9bcaacd43fab280',
             'thumbnail': 're:^https?://.*\.jpe?g$',
             'duration': 386,
+            'uploader_id': 's7JeEm',
         }
     }
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        entries = self._extract_xspf_playlist(
-            'https://tweakers.net/video/s1playlist/%s/playlist.xspf' % playlist_id, playlist_id)
-        return self.playlist_result(entries, playlist_id)
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            'https://tweakers.net/video/s1playlist/%s/1920/1080/playlist.json' % video_id,
+            video_id)['items'][0]
+
+        title = video_data['title']
+
+        formats = []
+        for location in video_data.get('locations', {}).get('progressive', []):
+            format_id = location.get('label')
+            width = int_or_none(location.get('width'))
+            height = int_or_none(location.get('height'))
+            for source in location.get('sources', []):
+                source_url = source.get('src')
+                if not source_url:
+                    continue
+                ext = mimetype2ext(source.get('type')) or determine_ext(source_url)
+                formats.append({
+                    'format_id': format_id,
+                    'url': source_url,
+                    'width': width,
+                    'height': height,
+                    'ext': ext,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('poster'),
+            'duration': int_or_none(video_data.get('duration')),
+            'uploader_id': video_data.get('account'),
+            'formats': formats,
+        }

youtube_dl/extractor/vidzi.py

@@ -9,8 +9,8 @@ from ..utils import (
 
 
 class VidziIE(JWPlatformBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P<id>\w+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [{
         'url': 'http://vidzi.tv/cghql9yq6emu.html',
         'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
         'info_dict': {
@@ -22,12 +22,16 @@ class VidziIE(JWPlatformBaseIE):
             # m3u8 download
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
+        'skip_download': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'http://vidzi.tv/%s' % video_id, video_id)
         title = self._html_search_regex(
             r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
 

youtube_dl/extractor/vimeo.py

@@ -364,6 +364,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
         if mobj:
             return mobj.group(1)
+        # Look more for non-standard embedded Vimeo player
+        mobj = re.search(
+            r'<video[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)(?P=q1)', webpage)
+        if mobj:
+            return mobj.group('url')
 
     def _verify_player_video_password(self, url, video_id):
         password = self._downloader.params.get('videopassword')

youtube_dl/extractor/vk.py

@@ -6,11 +6,18 @@ import json
 import sys
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
+    clean_html,
     ExtractorError,
+    get_element_by_class,
     int_or_none,
     orderedSet,
+    parse_duration,
+    remove_start,
     str_to_int,
     unescapeHTML,
     unified_strdate,
@@ -20,7 +27,55 @@ from .vimeo import VimeoIE
 from .pladform import PladformIE
 
 
-class VKIE(InfoExtractor):
+class VKBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'vk'
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_page, url_handle = self._download_webpage_handle(
+            'https://vk.com', None, 'Downloading login page')
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'email': username.encode('cp1251'),
+            'pass': password.encode('cp1251'),
+        })
+
+        # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
+        # and expects the first one to be set rather than second (see
+        # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
+        # As of RFC6265 the newer one cookie should be set into cookie store
+        # what actually happens.
+        # We will workaround this VK issue by resetting the remixlhk cookie to
+        # the first one manually.
+        cookies = url_handle.headers.get('Set-Cookie')
+        if cookies:
+            if sys.version_info[0] >= 3:
+                cookies = cookies.encode('iso-8859-1')
+            cookies = cookies.decode('utf-8')
+            remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
+            if remixlhk:
+                value, domain = remixlhk.groups()
+                self._set_cookie(domain, 'remixlhk', value)
+
+        login_page = self._download_webpage(
+            'https://login.vk.com/?act=login', None,
+            note='Logging in as %s' % username,
+            data=urlencode_postdata(login_form))
+
+        if re.search(r'onLoginFailed', login_page):
+            raise ExtractorError(
+                'Unable to login, incorrect username and/or password', expected=True)
+
+    def _real_initialize(self):
+        self._login()
+
+
+class VKIE(VKBaseIE):
     IE_NAME = 'vk'
     IE_DESC = 'VK'
     _VALID_URL = r'''(?x)
@@ -38,8 +93,6 @@ class VKIE(InfoExtractor):
                             (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>[\da-f]+))?
                         )
                     '''
-    _NETRC_MACHINE = 'vk'
-
     _TESTS = [
         {
             'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
@@ -189,49 +242,6 @@ class VKIE(InfoExtractor):
         }
     ]
 
-    def _login(self):
-        (username, password) = self._get_login_info()
-        if username is None:
-            return
-
-        login_page, url_handle = self._download_webpage_handle(
-            'https://vk.com', None, 'Downloading login page')
-
-        login_form = self._hidden_inputs(login_page)
-
-        login_form.update({
-            'email': username.encode('cp1251'),
-            'pass': password.encode('cp1251'),
-        })
-
-        # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
-        # and expects the first one to be set rather than second (see
-        # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
-        # As of RFC6265 the newer one cookie should be set into cookie store
-        # what actually happens.
-        # We will workaround this VK issue by resetting the remixlhk cookie to
-        # the first one manually.
-        cookies = url_handle.headers.get('Set-Cookie')
-        if sys.version_info[0] >= 3:
-            cookies = cookies.encode('iso-8859-1')
-        cookies = cookies.decode('utf-8')
-        remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
-        if remixlhk:
-            value, domain = remixlhk.groups()
-            self._set_cookie(domain, 'remixlhk', value)
-
-        login_page = self._download_webpage(
-            'https://login.vk.com/?act=login', None,
-            note='Logging in as %s' % username,
-            data=urlencode_postdata(login_form))
-
-        if re.search(r'onLoginFailed', login_page):
-            raise ExtractorError(
-                'Unable to login, incorrect username and/or password', expected=True)
-
-    def _real_initialize(self):
-        self._login()
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
@@ -355,7 +365,7 @@ class VKIE(InfoExtractor):
         }
 
 
-class VKUserVideosIE(InfoExtractor):
+class VKUserVideosIE(VKBaseIE):
     IE_NAME = 'vk:uservideos'
     IE_DESC = "VK - User's Videos"
     _VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/videos(?P<id>-?[0-9]+)(?!\?.*\bz=video)(?:[/?#&]|$)'
@@ -396,3 +406,121 @@ class VKUserVideosIE(InfoExtractor):
             webpage, 'title', default=page_id))
 
         return self.playlist_result(entries, page_id, title)
+
+
+class VKWallPostIE(VKBaseIE):
+    IE_NAME = 'vk:wallpost'
+    _VALID_URL = r'https?://(?:(?:(?:(?:m|new)\.)?vk\.com/(?:[^?]+\?.*\bw=)?wall(?P<id>-?\d+_\d+)))'
+    _TESTS = [{
+        # public page URL, audio playlist
+        'url': 'https://vk.com/bs.official?w=wall-23538238_35',
+        'info_dict': {
+            'id': '23538238_35',
+            'title': 'Black Shadow - Wall post 23538238_35',
+            'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
+        },
+        'playlist': [{
+            'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
+            'info_dict': {
+                'id': '135220665_111806521',
+                'ext': 'mp3',
+                'title': 'Black Shadow - Слепое Верование',
+                'duration': 370,
+                'uploader': 'Black Shadow',
+                'artist': 'Black Shadow',
+                'track': 'Слепое Верование',
+            },
+        }, {
+            'md5': '4cc7e804579122b17ea95af7834c9233',
+            'info_dict': {
+                'id': '135220665_111802303',
+                'ext': 'mp3',
+                'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
+                'duration': 423,
+                'uploader': 'Black Shadow',
+                'artist': 'Black Shadow',
+                'track': 'Война - Негасимое Бездны Пламя!',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        }],
+        'skip': 'Requires vk account credentials',
+    }, {
+        # single YouTube embed, no leading -
+        'url': 'https://vk.com/wall85155021_6319',
+        'info_dict': {
+            'id': '85155021_6319',
+            'title': 'Sergey Gorbunov - Wall post 85155021_6319',
+        },
+        'playlist_count': 1,
+        'skip': 'Requires vk account credentials',
+    }, {
+        # wall page URL
+        'url': 'https://vk.com/wall-23538238_35',
+        'only_matching': True,
+    }, {
+        # mobile wall page URL
+        'url': 'https://m.vk.com/wall-23538238_35',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        post_id = self._match_id(url)
+
+        wall_url = 'https://vk.com/wall%s' % post_id
+
+        post_id = remove_start(post_id, '-')
+
+        webpage = self._download_webpage(wall_url, post_id)
+
+        error = self._html_search_regex(
+            r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
+            webpage, 'error', default=None)
+        if error:
+            raise ExtractorError('VK said: %s' % error, expected=True)
+
+        description = clean_html(get_element_by_class('wall_post_text', webpage))
+        uploader = clean_html(get_element_by_class(
+            'fw_post_author', webpage)) or self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        entries = []
+
+        for audio in re.finditer(r'''(?sx)
+                            <input[^>]+
+                                id=(?P<q1>["\'])audio_info(?P<id>\d+_\d+).*?(?P=q1)[^>]+
+                                value=(?P<q2>["\'])(?P<url>http.+?)(?P=q2)
+                                .+?
+                            </table>''', webpage):
+            audio_html = audio.group(0)
+            audio_id = audio.group('id')
+            duration = parse_duration(get_element_by_class('duration', audio_html))
+            track = self._html_search_regex(
+                r'<span[^>]+id=["\']title%s[^>]*>([^<]+)' % audio_id,
+                audio_html, 'title', default=None)
+            artist = self._html_search_regex(
+                r'>([^<]+)</a></b>\s*&ndash', audio_html,
+                'artist', default=None)
+            entries.append({
+                'id': audio_id,
+                'url': audio.group('url'),
+                'title': '%s - %s' % (artist, track) if artist and track else audio_id,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'uploader': uploader,
+                'artist': artist,
+                'track': track,
+            })
+
+        for video in re.finditer(
+                r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
+            entries.append(self.url_result(
+                compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
+
+        title = 'Wall post %s' % post_id
+
+        return self.playlist_result(
+            orderedSet(entries), post_id,
+            '%s - %s' % (uploader, title) if uploader else title,
+            description)

youtube_dl/extractor/vuclip.py

@@ -9,7 +9,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     parse_duration,
-    qualities,
+    remove_end,
 )
 
 
@@ -22,7 +22,7 @@ class VuClipIE(InfoExtractor):
             'id': '922692425',
             'ext': '3gp',
             'title': 'The Toy Soldiers - Hollywood Movie Trailer',
-            'duration': 180,
+            'duration': 177,
         }
     }
 
@@ -46,34 +46,21 @@ class VuClipIE(InfoExtractor):
                 '%s said: %s' % (self.IE_NAME, error_msg), expected=True)
 
         # These clowns alternate between two page types
-        links_code = self._search_regex(
-            r'''(?xs)
-                (?:
-                    <img\s+src="[^"]*/play.gif".*?>|
-                    <!--\ player\ end\ -->\s*</div><!--\ thumb\ end-->
-                )
-                (.*?)
-                (?:
-                    <a\s+href="fblike|<div\s+class="social">
-                )
-            ''', webpage, 'links')
-        title = self._html_search_regex(
-            r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip()
+        video_url = self._search_regex(
+            r'<a[^>]+href="([^"]+)"[^>]*><img[^>]+src="[^"]*/play\.gif',
+            webpage, 'video URL', default=None)
+        if video_url:
+            formats = [{
+                'url': video_url,
+            }]
+        else:
+            formats = self._parse_html5_media_entries(url, webpage)[0]['formats']
 
-        quality_order = qualities(['Reg', 'Hi'])
-        formats = []
-        for url, q in re.findall(
-                r'<a\s+href="(?P<url>[^"]+)".*?>(?:<button[^>]*>)?(?P<q>[^<]+)(?:</button>)?</a>', links_code):
-            format_id = compat_urllib_parse_urlparse(url).scheme + '-' + q
-            formats.append({
-                'format_id': format_id,
-                'url': url,
-                'quality': quality_order(q),
-            })
-        self._sort_formats(formats)
+        title = remove_end(self._html_search_regex(
+            r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip(), ' - Video')
 
-        duration = parse_duration(self._search_regex(
-            r'\(([0-9:]+)\)</span>', webpage, 'duration', fatal=False))
+        duration = parse_duration(self._html_search_regex(
+            r'[(>]([0-9]+:[0-9]+)(?:<span|\))', webpage, 'duration', fatal=False))
 
         return {
             'id': video_id,

youtube_dl/extractor/wat.py

@@ -9,7 +9,6 @@ from ..utils import (
     ExtractorError,
     unified_strdate,
     HEADRequest,
-    float_or_none,
 )
 
 
@@ -95,16 +94,7 @@ class WatIE(InfoExtractor):
             m3u8_url.replace('ios.', 'web.').replace('.m3u8', '.f4m'),
             video_id, f4m_id='hds', fatal=False))
         for m3u8_format in m3u8_formats:
-            mobj = re.search(
-                r'audio.*?%3D(\d+)(?:-video.*?%3D(\d+))?', m3u8_format['url'])
-            if not mobj:
-                continue
-            abr, vbr = mobj.groups()
-            abr, vbr = float_or_none(abr, 1000), float_or_none(vbr, 1000)
-            m3u8_format.update({
-                'vbr': vbr,
-                'abr': abr,
-            })
+            vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr')
             if not vbr or not abr:
                 continue
             f = m3u8_format.copy()

youtube_dl/extractor/youtube.py

@@ -137,7 +137,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         # Two-Factor
         # TODO add SMS and phone call support - these require making a request and then prompting the user
 
-        if re.search(r'(?i)<form[^>]* id="challenge"', login_results) is not None:
+        if re.search(r'(?i)<form[^>]+id="challenge"', login_results) is not None:
             tfa_code = self._get_tfa_info('2-step verification code')
 
             if not tfa_code:
@@ -165,17 +165,17 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             if tfa_results is False:
                 return False
 
-            if re.search(r'(?i)<form[^>]* id="challenge"', tfa_results) is not None:
+            if re.search(r'(?i)<form[^>]+id="challenge"', tfa_results) is not None:
                 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
                 return False
-            if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
+            if re.search(r'(?i)<form[^>]+id="gaia_loginform"', tfa_results) is not None:
                 self._downloader.report_warning('unable to log in - did the page structure change?')
                 return False
             if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
                 self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
                 return False
 
-        if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
+        if re.search(r'(?i)<form[^>]+id="gaia_loginform"', login_results) is not None:
             self._downloader.report_warning('unable to log in: bad username or password')
             return False
         return True
@@ -858,6 +858,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         {
             'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
             'only_matching': True,
+        },
+        {
+            # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
+            'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
+            'only_matching': True,
         }
     ]
 
@@ -1978,10 +1983,13 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
         return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
                 else super(YoutubeChannelIE, cls).suitable(url))
 
+    def _build_template_url(self, url, channel_id):
+        return self._TEMPLATE_URL % channel_id
+
     def _real_extract(self, url):
         channel_id = self._match_id(url)
 
-        url = self._TEMPLATE_URL % channel_id
+        url = self._build_template_url(url, channel_id)
 
         # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
         # Workaround by extracting as a playlist if managed to obtain channel playlist URL
@@ -2038,8 +2046,8 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
 
 class YoutubeUserIE(YoutubeChannelIE):
     IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
-    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/|c/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
-    _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos'
+    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
+    _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
     IE_NAME = 'youtube:user'
 
     _TESTS = [{
@@ -2049,12 +2057,24 @@ class YoutubeUserIE(YoutubeChannelIE):
             'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
             'title': 'Uploads from The Linux Foundation',
         }
+    }, {
+        # Only available via https://www.youtube.com/c/12minuteathlete/videos
+        # but not https://www.youtube.com/user/12minuteathlete/videos
+        'url': 'https://www.youtube.com/c/12minuteathlete/videos',
+        'playlist_mincount': 249,
+        'info_dict': {
+            'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
+            'title': 'Uploads from 12 Minute Athlete',
+        }
     }, {
         'url': 'ytuser:phihag',
         'only_matching': True,
     }, {
         'url': 'https://www.youtube.com/c/gametrailers',
         'only_matching': True,
+    }, {
+        'url': 'https://www.youtube.com/gametrailers',
+        'only_matching': True,
     }, {
         # This channel is not available.
         'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
@@ -2071,6 +2091,10 @@ class YoutubeUserIE(YoutubeChannelIE):
         else:
             return super(YoutubeUserIE, cls).suitable(url)
 
+    def _build_template_url(self, url, channel_id):
+        mobj = re.match(self._VALID_URL, url)
+        return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
+
 
 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
     IE_DESC = 'YouTube.com live streams'

youtube_dl/options.py

@@ -26,7 +26,11 @@ def parseOpts(overrideArguments=None):
         except IOError:
             return default  # silently skip if file is not present
         try:
-            res = compat_shlex_split(optionf.read(), comments=True)
+            # FIXME: https://github.com/rg3/youtube-dl/commit/dfe5fa49aed02cf36ba9f743b11b0903554b5e56
+            contents = optionf.read()
+            if sys.version_info < (3,):
+                contents = contents.decode(preferredencoding())
+            res = compat_shlex_split(contents, comments=True)
         finally:
             optionf.close()
         return res
@@ -812,11 +816,11 @@ def parseOpts(overrideArguments=None):
             system_conf = []
             user_conf = []
         else:
-            system_conf = compat_conf(_readOptions('/etc/youtube-dl.conf'))
+            system_conf = _readOptions('/etc/youtube-dl.conf')
             if '--ignore-config' in system_conf:
                 user_conf = []
             else:
-                user_conf = compat_conf(_readUserConf())
+                user_conf = _readUserConf()
         argv = system_conf + user_conf + command_line_conf
 
         opts, args = parser.parse_args(argv)

youtube_dl/postprocessor/ffmpeg.py

@@ -363,8 +363,10 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
         input_files = [filename] + sub_filenames
 
         opts = [
-            '-map', '0',
-            '-c', 'copy',
+            '-map', '0:v',
+            '-c:v', 'copy',
+            '-map', '0:a',
+            '-c:a', 'copy',
             # Don't copy the existing subtitles, we may be running the
             # postprocessor a second time
             '-map', '-0:s',

youtube_dl/utils.py

@@ -2126,6 +2126,42 @@ def mimetype2ext(mt):
     }.get(res, res)
 
 
+def parse_codecs(codecs_str):
+    # http://tools.ietf.org/html/rfc6381
+    if not codecs_str:
+        return {}
+    splited_codecs = list(filter(None, map(
+        lambda str: str.strip(), codecs_str.strip().strip(',').split(','))))
+    vcodec, acodec = None, None
+    for full_codec in splited_codecs:
+        codec = full_codec.split('.')[0]
+        if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v'):
+            if not vcodec:
+                vcodec = full_codec
+        elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac'):
+            if not acodec:
+                acodec = full_codec
+        else:
+            write_string('WARNING: Unknown codec %s' % full_codec, sys.stderr)
+    if not vcodec and not acodec:
+        if len(splited_codecs) == 2:
+            return {
+                'vcodec': vcodec,
+                'acodec': acodec,
+            }
+        elif len(splited_codecs) == 1:
+            return {
+                'vcodec': 'none',
+                'acodec': vcodec,
+            }
+    else:
+        return {
+            'vcodec': vcodec or 'none',
+            'acodec': acodec or 'none',
+        }
+    return {}
+
+
 def urlhandle_detect_ext(url_handle):
     getheader = url_handle.headers.get
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.07.07'
+__version__ = '2016.07.13'