release 2016.09.08

Add missing r prefix for _VALID_URLs

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.03*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.09.03**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.08*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.09.08**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.09.03
+[debug] youtube-dl version 2016.09.08
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

AUTHORS

@@ -183,3 +183,5 @@ Petr Zvoníček
 Pratyush Singh
 Aleksander Nitecki
 Sebastian Blunt
+Matěj Cepl
+Xie Yanbo

ChangeLog

@@ -1,3 +1,55 @@
+version 2016.09.08
+
+Extractors
++ [jwplatform] Extract height from format label
++ [yahoo] Extract Brightcove Legacy Studio embeds (#9345)
+* [videomore] Fix extraction (#10592)
+* [foxgay] Fix extraction (#10480)
++ [rmcdecouverte] Add extractor for rmcdecouverte.bfmtv.com (#9709)
+* [gamestar] Fix metadata extraction (#10479)
+* [puls4] Fix extraction (#10583)
++ [cctv] Add extractor for CCTV and CNTV (#8153)
++ [lci] Add extractor for lci.fr (#10573)
++ [wat] Extract DASH formats
++ [viafree] Improve video id detection (#10569)
++ [trutv] Add extractor for trutv.com (#10519)
++ [nick] Add support for nickelodeon.nl (#10559)
++ [abcotvs:clips] Add support for clips.abcotvs.com
++ [abcotvs] Add support for ABC Owned Television Stations sites (#9551)
++ [miaopai] Add extractor for miaopai.com (#10556)
+* [gamestar] Fix metadata extraction (#10479)
++ [bilibili] Add support for episodes (#10190)
++ [tvnoe] Add extractor for tvnoe.cz (#10524)
+
+
+version 2016.09.04.1
+
+Core
+* In DASH downloader if the first segment fails, abort the whole download
+  process to prevent throttling (#10497)
++ Add support for --skip-unavailable-fragments and --fragment retries in
+  hlsnative downloader (#10165, #10448).
++ Add support for --skip-unavailable-fragments in DASH downloader
++ Introduce --skip-unavailable-fragments option for fragment based downloaders
+  that allows to skip fragments unavailable due to a HTTP error
+* Fix extraction of video/audio entries with src attribute in
+  _parse_html5_media_entries (#10540)
+
+Extractors
+* [theplatform] Relax URL regular expression (#10546)
+* [youtube:playlist] Extend URL regular expression
+* [rottentomatoes] Delegate extraction to internetvideoarchive extractor
+* [internetvideoarchive] Extract all formats
+* [pornvoisines] Fix extraction (#10469)
+* [rottentomatoes] Fix extraction (#10467)
+* [espn] Extend URL regular expression (#10549)
+* [vimple] Extend URL regular expression (#10547)
+* [youtube:watchlater] Fix extraction (#10544)
+* [youjizz] Fix extraction (#10437)
++ [foxnews] Add support for FoxNews Insider (#10445)
++ [fc2] Recognize Flash player URLs (#10512)
+
+
 version 2016.09.03
 
 Core
@@ -5,7 +57,6 @@ Core
   _extract_m3u8_formats (#10522)
 * Handle semicolon in mimetype2ext
 
-
 Extractors
 + [youtube] Add support for rental videos' previews (#10532)
 * [youtube:playlist] Fallback to video extraction for video/playlist URLs when

README.md

@@ -89,6 +89,8 @@ which means you can modify it, redistribute it or use it however you like.
     --mark-watched                   Mark videos watched (YouTube only)
     --no-mark-watched                Do not mark videos watched (YouTube only)
     --no-color                       Do not emit color codes in output
+    --abort-on-unavailable-fragment  Abort downloading when some fragment is not
+                                     available
 
 ## Network Options:
     --proxy URL                      Use the specified HTTP/HTTPS/SOCKS proxy.
@@ -173,7 +175,10 @@ which means you can modify it, redistribute it or use it however you like.
     -R, --retries RETRIES            Number of retries (default is 10), or
                                      "infinite".
     --fragment-retries RETRIES       Number of retries for a fragment (default
-                                     is 10), or "infinite" (DASH only)
+                                     is 10), or "infinite" (DASH and hlsnative
+                                     only)
+    --skip-unavailable-fragments     Skip unavailable fragments (DASH and
+                                     hlsnative only)
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)
                                      (default is 1024)
     --no-resize-buffer               Do not automatically adjust the buffer
@@ -846,6 +851,16 @@ will download the complete `PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re` playlist and cre
 
     youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
 
+### Should I add `--hls-prefer-native` into my config?
+
+When youtube-dl detects an HLS video, it can download it either with the built-in downloader or ffmpeg. Since many HLS streams are slightly invalid and ffmpeg/youtube-dl each handle some invalid cases better than the other, there is an option to switch the downloader if needed.
+
+When youtube-dl knows that one particular downloader works better for a given website, that downloader will be picked. Otherwise, youtube-dl will pick the best downloader for general compatibility, which at the moment happens to be ffmpeg. This choice may change in future versions of youtube-dl, with improvements of the built-in downloader and/or ffmpeg.
+
+In particular, the generic extractor (used when your website is not in the [list of supported sites by youtube-dl](http://rg3.github.io/youtube-dl/supportedsites.html) cannot mandate one specific downloader.
+
+If you put either `--hls-prefer-native` or `--hls-prefer-ffmpeg` into your configuration, a different subset of videos will fail to download correctly. Instead, it is much better to [file an issue](https://yt-dl.org/bug) or a pull request which details why the native or the ffmpeg HLS downloader is a better choice for your use case.
+
 ### Can you add support for this anime video site, or site which shows current movies for free?
 
 As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.

docs/supportedsites.md

@@ -19,9 +19,10 @@
  - **9now.com.au**
  - **abc.net.au**
  - **abc.net.au:iview**
- - **Abc7News**
  - **abcnews**
  - **abcnews:video**
+ - **abcotvs**: ABC Owned Television Stations
+ - **abcotvs:clips**
  - **AcademicEarth:Course**
  - **acast**
  - **acast:channel**
@@ -128,6 +129,7 @@
  - **CBSNews**: CBS News
  - **CBSNewsLiveVideo**: CBS News Live Videos
  - **CBSSports**
+ - **CCTV**
  - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
@@ -232,6 +234,7 @@
  - **FacebookPluginsVideo**
  - **faz.net**
  - **fc2**
+ - **fc2:embed**
  - **Fczenit**
  - **features.aol.com**
  - **fernsehkritik.tv**
@@ -245,6 +248,7 @@
  - **FOX**
  - **Foxgay**
  - **FoxNews**: Fox News and Fox Business Video
+ - **foxnews:insider**
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
@@ -350,6 +354,7 @@
  - **kuwo:song**: 酷我音乐
  - **la7.it**
  - **Laola1Tv**
+ - **LCI**
  - **Lcp**
  - **LcpPlay**
  - **Le**: 乐视网
@@ -388,6 +393,7 @@
  - **Metacritic**
  - **Mgoon**
  - **MGTV**: 芒果TV
+ - **MiaoPai**
  - **Minhateca**
  - **MinistryGrid**
  - **Minoto**
@@ -574,6 +580,7 @@
  - **revision3:embed**
  - **RICE**
  - **RingTV**
+ - **RMCDecouverte**
  - **RockstarGames**
  - **RoosterTeeth**
  - **RottenTomatoes**
@@ -719,6 +726,7 @@
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
  - **trollvids**
+ - **TruTV**
  - **Tube8**
  - **TubiTv**
  - **tudou**
@@ -740,6 +748,7 @@
  - **TVCArticle**
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvland.com**
+ - **TVNoe**
  - **tvp**: Telewizja Polska
  - **tvp:embed**: Telewizja Polska
  - **tvp:series**

youtube_dl/__init__.py

@@ -318,6 +318,7 @@ def _real_main(argv=None):
         'nooverwrites': opts.nooverwrites,
         'retries': opts.retries,
         'fragment_retries': opts.fragment_retries,
+        'skip_unavailable_fragments': opts.skip_unavailable_fragments,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,

youtube_dl/downloader/dash.py

@@ -38,8 +38,10 @@ class DashSegmentsFD(FragmentFD):
         segments_filenames = []
 
         fragment_retries = self.params.get('fragment_retries', 0)
+        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
-        def append_url_to_file(target_url, tmp_filename, segment_name):
+        def process_segment(segment, tmp_filename, fatal):
+            target_url, segment_name = segment
             target_filename = '%s-%s' % (tmp_filename, segment_name)
             count = 0
             while count <= fragment_retries:
@@ -52,26 +54,35 @@ class DashSegmentsFD(FragmentFD):
                     down.close()
                     segments_filenames.append(target_sanitized)
                     break
-                except (compat_urllib_error.HTTPError, ) as err:
+                except compat_urllib_error.HTTPError as err:
                     # YouTube may often return 404 HTTP error for a fragment causing the
                     # whole download to fail. However if the same fragment is immediately
                     # retried with the same request data this usually succeeds (1-2 attemps
                     # is usually enough) thus allowing to download the whole file successfully.
-                    # So, we will retry all fragments that fail with 404 HTTP error for now.
-                    if err.code != 404:
-                        raise
-                    # Retry fragment
+                    # To be future-proof we will retry all fragments that fail with any
+                    # HTTP error.
                     count += 1
                     if count <= fragment_retries:
-                        self.report_retry_fragment(segment_name, count, fragment_retries)
+                        self.report_retry_fragment(err, segment_name, count, fragment_retries)
             if count > fragment_retries:
+                if not fatal:
+                    self.report_skip_fragment(segment_name)
+                    return True
                 self.report_error('giving up after %s fragment retries' % fragment_retries)
                 return False
+            return True
 
-        if initialization_url:
-            append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
-        for i, segment_url in enumerate(segment_urls):
-            append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
+        segments_to_download = [(initialization_url, 'Init')] if initialization_url else []
+        segments_to_download.extend([
+            (segment_url, 'Seg%d' % i)
+            for i, segment_url in enumerate(segment_urls)])
+
+        for i, segment in enumerate(segments_to_download):
+            # In DASH, the first segment contains necessary headers to
+            # generate a valid MP4 file, so always abort for the first segment
+            fatal = i == 0 or not skip_unavailable_fragments
+            if not process_segment(segment, ctx['tmpfilename'], fatal):
+                return False
 
         self._finish_frag_download(ctx)
 

youtube_dl/downloader/fragment.py

@@ -6,6 +6,7 @@ import time
 from .common import FileDownloader
 from .http import HttpFD
 from ..utils import (
+    error_to_compat_str,
     encodeFilename,
     sanitize_open,
 )
@@ -22,13 +23,19 @@ class FragmentFD(FileDownloader):
 
     Available options:
 
-    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH only)
+    fragment_retries:   Number of times to retry a fragment for HTTP error (DASH
+                        and hlsnative only)
+    skip_unavailable_fragments:
+                        Skip unavailable fragments (DASH and hlsnative only)
     """
 
-    def report_retry_fragment(self, fragment_name, count, retries):
+    def report_retry_fragment(self, err, fragment_name, count, retries):
         self.to_screen(
-            '[download] Got server HTTP error. Retrying fragment %s (attempt %d of %s)...'
-            % (fragment_name, count, self.format_retries(retries)))
+            '[download] Got server HTTP error: %s. Retrying fragment %s (attempt %d of %s)...'
+            % (error_to_compat_str(err), fragment_name, count, self.format_retries(retries)))
+
+    def report_skip_fragment(self, fragment_name):
+        self.to_screen('[download] Skipping fragment %s...' % fragment_name)
 
     def _prepare_and_start_frag_download(self, ctx):
         self._prepare_frag_download(ctx)

youtube_dl/downloader/hls.py

@@ -13,6 +13,7 @@ from .fragment import FragmentFD
 from .external import FFmpegFD
 
 from ..compat import (
+    compat_urllib_error,
     compat_urlparse,
     compat_struct_pack,
 )
@@ -83,6 +84,10 @@ class HlsFD(FragmentFD):
 
         self._prepare_and_start_frag_download(ctx)
 
+        fragment_retries = self.params.get('fragment_retries', 0)
+        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
+        test = self.params.get('test', False)
+
         extra_query = None
         extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
         if extra_param_to_segment_url:
@@ -99,15 +104,37 @@ class HlsFD(FragmentFD):
                         line
                         if re.match(r'^https?://', line)
                         else compat_urlparse.urljoin(man_url, line))
-                    frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+                    frag_name = 'Frag%d' % i
+                    frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
-                    success = ctx['dl'].download(frag_filename, {'url': frag_url})
-                    if not success:
+                    count = 0
+                    while count <= fragment_retries:
+                        try:
+                            success = ctx['dl'].download(frag_filename, {'url': frag_url})
+                            if not success:
+                                return False
+                            down, frag_sanitized = sanitize_open(frag_filename, 'rb')
+                            frag_content = down.read()
+                            down.close()
+                            break
+                        except compat_urllib_error.HTTPError as err:
+                            # Unavailable (possibly temporary) fragments may be served.
+                            # First we try to retry then either skip or abort.
+                            # See https://github.com/rg3/youtube-dl/issues/10165,
+                            # https://github.com/rg3/youtube-dl/issues/10448).
+                            count += 1
+                            if count <= fragment_retries:
+                                self.report_retry_fragment(err, frag_name, count, fragment_retries)
+                    if count > fragment_retries:
+                        if skip_unavailable_fragments:
+                            i += 1
+                            media_sequence += 1
+                            self.report_skip_fragment(frag_name)
+                            continue
+                        self.report_error(
+                            'giving up after %s fragment retries' % fragment_retries)
                         return False
-                    down, frag_sanitized = sanitize_open(frag_filename, 'rb')
-                    frag_content = down.read()
-                    down.close()
                     if decrypt_info['METHOD'] == 'AES-128':
                         iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
                         frag_content = AES.new(
@@ -115,7 +142,7 @@ class HlsFD(FragmentFD):
                     ctx['dest_stream'].write(frag_content)
                     frags_filenames.append(frag_sanitized)
                     # We only download the first fragment during the test
-                    if self.params.get('test', False):
+                    if test:
                         break
                     i += 1
                     media_sequence += 1

youtube_dl/extractor/abcnews.py

@@ -12,7 +12,7 @@ from ..compat import compat_urlparse
 
 class AbcNewsVideoIE(AMPIE):
     IE_NAME = 'abcnews:video'
-    _VALID_URL = 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
+    _VALID_URL = r'https?://abcnews\.go\.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
@@ -49,7 +49,7 @@ class AbcNewsVideoIE(AMPIE):
 
 class AbcNewsIE(InfoExtractor):
     IE_NAME = 'abcnews'
-    _VALID_URL = 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
+    _VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',

youtube_dl/extractor/abcotvs.py

@@ -1,13 +1,19 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
-class Abc7NewsIE(InfoExtractor):
-    _VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
+class ABCOTVSIE(InfoExtractor):
+    IE_NAME = 'abcotvs'
+    IE_DESC = 'ABC Owned Television Stations'
+    _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
@@ -15,7 +21,7 @@ class Abc7NewsIE(InfoExtractor):
                 'id': '472581',
                 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
                 'ext': 'mp4',
-                'title': 'East Bay museum celebrates history of synthesized music',
+                'title': 'East Bay museum celebrates vintage synthesizers',
                 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'timestamp': 1421123075,
@@ -41,7 +47,7 @@ class Abc7NewsIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         m3u8 = self._html_search_meta(
-            'contentURL', webpage, 'm3u8 url', fatal=True)
+            'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
 
         formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
         self._sort_formats(formats)
@@ -66,3 +72,41 @@ class Abc7NewsIE(InfoExtractor):
             'uploader': uploader,
             'formats': formats,
         }
+
+
+class ABCOTVSClipsIE(InfoExtractor):
+    IE_NAME = 'abcotvs:clips'
+    _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://clips.abcotvs.com/kabc/video/214814',
+        'info_dict': {
+            'id': '214814',
+            'ext': 'mp4',
+            'title': 'SpaceX launch pad explosion destroys rocket, satellite',
+            'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
+            'upload_date': '20160901',
+            'timestamp': 1472756695,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
+        title = video_data['title']
+        formats = self._extract_m3u8_formats(
+            video_data['videoURL'].split('?')[0], video_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnailURL'),
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': int_or_none(video_data.get('pubDate')),
+            'formats': formats,
+        }

youtube_dl/extractor/ard.py

@@ -238,7 +238,7 @@ class ARDMediathekIE(InfoExtractor):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
     _TEST = {
         'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
         'md5': 'd216c3a86493f9322545e045ddc3eb35',

youtube_dl/extractor/bilibili.py

@@ -10,11 +10,12 @@ from ..utils import (
     int_or_none,
     float_or_none,
     unified_timestamp,
+    urlencode_postdata,
 )
 
 
 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
@@ -77,6 +78,17 @@ class BiliBiliIE(InfoExtractor):
             'skip_download': True,
         },
         'expected_warnings': ['upload time'],
+    }, {
+        'url': 'http://bangumi.bilibili.com/anime/v/40068',
+        'md5': '08d539a0884f3deb7b698fb13ba69696',
+        'info_dict': {
+            'id': '40068',
+            'ext': 'mp4',
+            'duration': 1402.357,
+            'title': '混沌武士 : 第7集 四面楚歌 A Risky Racket',
+            'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
+            'thumbnail': 're:^http?://.+\.jpg',
+        },
     }]
 
     _APP_KEY = '6f90a59ac58a4123'
@@ -84,13 +96,19 @@ class BiliBiliIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
 
-        cid = compat_parse_qs(self._search_regex(
-            [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
-             r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
-            webpage, 'player parameters'))['cid'][0]
+        if 'anime/v' not in url:
+            cid = compat_parse_qs(self._search_regex(
+                [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
+                 r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
+                webpage, 'player parameters'))['cid'][0]
+        else:
+            js = self._download_json(
+                'http://bangumi.bilibili.com/web_api/get_source', video_id,
+                data=urlencode_postdata({'episode_id': video_id}),
+                headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'})
+            cid = js['result']['cid']
 
         payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
         sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
@@ -125,6 +143,7 @@ class BiliBiliIE(InfoExtractor):
         description = self._html_search_meta('description', webpage)
         timestamp = unified_timestamp(self._html_search_regex(
             r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
+        thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
 
         # TODO 'view_count' requires deobfuscating Javascript
         info = {
@@ -132,7 +151,7 @@ class BiliBiliIE(InfoExtractor):
             'title': title,
             'description': description,
             'timestamp': timestamp,
-            'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
+            'thumbnail': thumbnail,
             'duration': float_or_none(video_info.get('timelength'), scale=1000),
         }
 

youtube_dl/extractor/cartoonnetwork.py

@@ -30,7 +30,7 @@ class CartoonNetworkIE(TurnerBaseIE):
         return self._extract_cvp_info(
             'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
                 'secure': {
-                    'media_src': 'http://apple-secure.cdn.turner.com/toon/big',
+                    'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
                     'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
                 },
             })

youtube_dl/extractor/cctv.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class CCTVIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:.+?\.)?
+        (?:
+            cctv\.(?:com|cn)|
+            cntv\.cn
+        )/
+        (?:
+            video/[^/]+/(?P<id>[0-9a-f]{32})|
+            \d{4}/\d{2}/\d{2}/(?P<display_id>VID[0-9A-Za-z]+)
+        )'''
+    _TESTS = [{
+        'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
+        'md5': '819c7b49fc3927d529fb4cd555621823',
+        'info_dict': {
+            'id': '454368eb19ad44a1925bf1eb96140a61',
+            'ext': 'mp4',
+            'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1',
+        }
+    }, {
+        'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(
+                r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})',
+                webpage, 'video_id')
+        api_data = self._download_json(
+            'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id)
+        m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url'])
+
+        return {
+            'id': video_id,
+            'title': api_data['title'],
+            'formats': self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False),
+            'duration': float_or_none(api_data.get('video', {}).get('totalLength')),
+        }

youtube_dl/extractor/common.py

@@ -1163,13 +1163,6 @@ class InfoExtractor(object):
                               m3u8_id=None, note=None, errnote=None,
                               fatal=True, live=False):
 
-        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
-
-        format_url = lambda u: (
-            u
-            if re.match(r'^https?://', u)
-            else compat_urlparse.urljoin(m3u8_url, u))
-
         res = self._download_webpage_handle(
             m3u8_url, video_id,
             note=note or 'Downloading m3u8 information',
@@ -1180,6 +1173,13 @@ class InfoExtractor(object):
         m3u8_doc, urlh = res
         m3u8_url = urlh.geturl()
 
+        formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
+
+        format_url = lambda u: (
+            u
+            if re.match(r'^https?://', u)
+            else compat_urlparse.urljoin(m3u8_url, u))
+
         # We should try extracting formats only from master playlists [1], i.e.
         # playlists that describe available qualities. On the other hand media
         # playlists [2] should be returned as is since they contain just the media
@@ -1749,7 +1749,7 @@ class InfoExtractor(object):
             media_attributes = extract_attributes(media_tag)
             src = media_attributes.get('src')
             if src:
-                _, formats = _media_formats(src)
+                _, formats = _media_formats(src, media_type)
                 media_info['formats'].extend(formats)
             media_info['thumbnail'] = media_attributes.get('poster')
             if media_content:

youtube_dl/extractor/dailymotion.py

@@ -394,7 +394,7 @@ class DailymotionUserIE(DailymotionPlaylistIE):
 
 
 class DailymotionCloudIE(DailymotionBaseInfoExtractor):
-    _VALID_URL_PREFIX = r'http://api\.dmcloud\.net/(?:player/)?embed/'
+    _VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/'
     _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX
     _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX
 

youtube_dl/extractor/espn.py

@@ -5,7 +5,7 @@ from ..utils import remove_end
 
 
 class ESPNIE(InfoExtractor):
-    _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://espn.go.com/video/clip?id=10365079',
         'md5': '60e5d097a523e767d06479335d1bdc58',
@@ -47,6 +47,9 @@ class ESPNIE(InfoExtractor):
     }, {
         'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
         'only_matching': True,
+    }, {
+        'url': 'http://www.espn.com/video/clip?id=10365079',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -5,11 +5,14 @@ from .abc import (
     ABCIE,
     ABCIViewIE,
 )
-from .abc7news import Abc7NewsIE
 from .abcnews import (
     AbcNewsIE,
     AbcNewsVideoIE,
 )
+from .abcotvs import (
+    ABCOTVSIE,
+    ABCOTVSClipsIE,
+)
 from .academicearth import AcademicEarthCourseIE
 from .acast import (
     ACastIE,
@@ -143,6 +146,7 @@ from .cbsnews import (
 )
 from .cbssports import CBSSportsIE
 from .ccc import CCCIE
+from .cctv import CCTVIE
 from .cda import CDAIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
@@ -269,7 +273,10 @@ from .facebook import (
     FacebookPluginsVideoIE,
 )
 from .faz import FazIE
-from .fc2 import FC2IE
+from .fc2 import (
+    FC2IE,
+    FC2EmbedIE,
+)
 from .fczenit import FczenitIE
 from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
@@ -284,7 +291,10 @@ from .formula1 import Formula1IE
 from .fourtube import FourTubeIE
 from .fox import FOXIE
 from .foxgay import FoxgayIE
-from .foxnews import FoxNewsIE
+from .foxnews import (
+    FoxNewsIE,
+    FoxNewsInsiderIE,
+)
 from .foxsports import FoxSportsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
@@ -415,6 +425,7 @@ from .kuwo import (
 )
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
+from .lci import LCIIE
 from .lcp import (
     LcpPlayIE,
     LcpIE,
@@ -465,6 +476,7 @@ from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
 from .mgtv import MGTVIE
+from .miaopai import MiaoPaiIE
 from .microsoftvirtualacademy import (
     MicrosoftVirtualAcademyIE,
     MicrosoftVirtualAcademyCourseIE,
@@ -712,6 +724,7 @@ from .revision3 import (
 )
 from .rice import RICEIE
 from .ringtv import RingTVIE
+from .rmcdecouverte import RMCDecouverteIE
 from .ro220 import Ro220IE
 from .rockstargames import RockstarGamesIE
 from .roosterteeth import RoosterTeethIE
@@ -881,6 +894,7 @@ from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
 from .trollvids import TrollvidsIE
+from .trutv import TruTVIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
 from .tudou import (
@@ -910,6 +924,7 @@ from .tvc import (
 )
 from .tvigle import TvigleIE
 from .tvland import TVLandIE
+from .tvnoe import TVNoeIE
 from .tvp import (
     TVPEmbedIE,
     TVPIE,

youtube_dl/extractor/fc2.py

@@ -1,10 +1,12 @@
-#! -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import hashlib
+import re
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_parse_qs,
     compat_urllib_request,
     compat_urlparse,
 )
@@ -16,7 +18,7 @@ from ..utils import (
 
 
 class FC2IE(InfoExtractor):
-    _VALID_URL = r'^https?://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
+    _VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
     IE_NAME = 'fc2'
     _NETRC_MACHINE = 'fc2'
     _TESTS = [{
@@ -75,12 +77,17 @@ class FC2IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         self._login()
-        webpage = self._download_webpage(url, video_id)
-        self._downloader.cookiejar.clear_session_cookies()  # must clear
-        self._login()
+        webpage = None
+        if not url.startswith('fc2:'):
+            webpage = self._download_webpage(url, video_id)
+            self._downloader.cookiejar.clear_session_cookies()  # must clear
+            self._login()
 
-        title = self._og_search_title(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
+        title = 'FC2 video %s' % video_id
+        thumbnail = None
+        if webpage is not None:
+            title = self._og_search_title(webpage)
+            thumbnail = self._og_search_thumbnail(webpage)
         refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url
 
         mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
@@ -113,3 +120,41 @@ class FC2IE(InfoExtractor):
             'ext': 'flv',
             'thumbnail': thumbnail,
         }
+
+
+class FC2EmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.fc2\.com/flv2\.swf\?(?P<query>.+)'
+    IE_NAME = 'fc2:embed'
+
+    _TEST = {
+        'url': 'http://video.fc2.com/flv2.swf?t=201404182936758512407645&i=20130316kwishtfitaknmcgd76kjd864hso93htfjcnaogz629mcgfs6rbfk0hsycma7shkf85937cbchfygd74&i=201403223kCqB3Ez&d=2625&sj=11&lang=ja&rel=1&from=11&cmt=1&tk=TlRBM09EQTNNekU9&tl=プリズン･ブレイク%20S1-01%20マイケル%20【吹替】',
+        'md5': 'b8aae5334cb691bdb1193a88a6ab5d5a',
+        'info_dict': {
+            'id': '201403223kCqB3Ez',
+            'ext': 'flv',
+            'title': 'プリズン･ブレイク S1-01 マイケル 【吹替】',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        query = compat_parse_qs(mobj.group('query'))
+
+        video_id = query['i'][-1]
+        title = query.get('tl', ['FC2 video %s' % video_id])[0]
+
+        sj = query.get('sj', [None])[0]
+        thumbnail = None
+        if sj:
+            # See thumbnailImagePath() in ServerConst.as of flv2.swf
+            thumbnail = 'http://video%s-thumbnail.fc2.com/up/pic/%s.jpg' % (
+                sj, '/'.join((video_id[:6], video_id[6:8], video_id[-2], video_id[-1], video_id)))
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': FC2IE.ie_key(),
+            'url': 'fc2:%s' % video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/foxgay.py

@@ -1,18 +1,24 @@
 from __future__ import unicode_literals
 
+import itertools
+
 from .common import InfoExtractor
+from ..utils import (
+    get_element_by_id,
+    remove_end,
+)
 
 
 class FoxgayIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
     _TEST = {
         'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
-        'md5': '80d72beab5d04e1655a56ad37afe6841',
+        'md5': '344558ccfea74d33b7adbce22e577f54',
         'info_dict': {
             'id': '2582',
             'ext': 'mp4',
-            'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a',
-            'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf',
+            'title': 'Fuck Turkish-style',
+            'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
             'age_limit': 18,
             'thumbnail': 're:https?://.*\.jpg$',
         },
@@ -22,27 +28,35 @@ class FoxgayIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(
-            r'<title>(?P<title>.*?)</title>',
-            webpage, 'title', fatal=False)
-        description = self._html_search_regex(
-            r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>',
-            webpage, 'description', fatal=False)
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' - Foxgay.com')
+        description = get_element_by_id('inf_tit', webpage)
 
+        # The default user-agent with foxgay cookies leads to pages without videos
+        self._downloader.cookiejar.clear('.foxgay.com')
         # Find the URL for the iFrame which contains the actual video.
+        iframe_url = self._html_search_regex(
+            r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', webpage,
+            'video frame', group='url')
         iframe = self._download_webpage(
-            self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'),
-            video_id)
-        video_url = self._html_search_regex(
-            r"v_path = '(?P<vid>http://.*?)'", iframe, 'url')
-        thumb_url = self._html_search_regex(
-            r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False)
+            iframe_url, video_id, headers={'User-Agent': 'curl/7.50.1'},
+            note='Downloading video frame')
+        video_data = self._parse_json(self._search_regex(
+            r'video_data\s*=\s*([^;]+);', iframe, 'video data'), video_id)
+
+        formats = [{
+            'url': source,
+            'height': resolution,
+        } for source, resolution in zip(
+            video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
-            'url': video_url,
+            'formats': formats,
             'description': description,
-            'thumbnail': thumb_url,
+            'thumbnail': video_data.get('act_vid', {}).get('thumb'),
             'age_limit': 18,
         }

youtube_dl/extractor/foxnews.py

@@ -3,11 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .amp import AMPIE
+from .common import InfoExtractor
 
 
 class FoxNewsIE(AMPIE):
     IE_DESC = 'Fox News and Fox Business Video'
-    _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
+    _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
@@ -49,6 +50,11 @@ class FoxNewsIE(AMPIE):
             'url': 'http://video.foxbusiness.com/v/4442309889001',
             'only_matching': True,
         },
+        {
+            # From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
+            'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):
@@ -58,3 +64,43 @@ class FoxNewsIE(AMPIE):
             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
         info['id'] = video_id
         return info
+
+
+class FoxNewsInsiderIE(InfoExtractor):
+    _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
+    IE_NAME = 'foxnews:insider'
+
+    _TEST = {
+        'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
+        'md5': 'a10c755e582d28120c62749b4feb4c0c',
+        'info_dict': {
+            'id': '5099377331001',
+            'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
+            'ext': 'mp4',
+            'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
+            'description': 'Is campus censorship getting out of control?',
+            'timestamp': 1472168725,
+            'upload_date': '20160825',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'add_ie': [FoxNewsIE.ie_key()],
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': FoxNewsIE.ie_key(),
+            'url': embed_url,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/gamestar.py

@@ -1,14 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    parse_duration,
-    str_to_int,
-    unified_strdate,
+    remove_end,
 )
 
 
@@ -21,8 +17,9 @@ class GameStarIE(InfoExtractor):
             'id': '76110',
             'ext': 'mp4',
             'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
-            'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den vollständigen Trailer an.',
-            'thumbnail': 'http://images.gamestar.de/images/idgwpgsgp/bdb/2494525/600x.jpg',
+            'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1406542020,
             'upload_date': '20140728',
             'duration': 17
         }
@@ -32,41 +29,27 @@ class GameStarIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        og_title = self._og_search_title(webpage)
-        title = re.sub(r'\s*- Video (bei|-) GameStar\.de$', '', og_title)
-
         url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id
 
-        description = self._og_search_description(webpage).strip()
-
-        thumbnail = self._proto_relative_url(
-            self._og_search_thumbnail(webpage), scheme='http:')
-
-        upload_date = unified_strdate(self._html_search_regex(
-            r'<span style="float:left;font-size:11px;">Datum: ([0-9]+\.[0-9]+\.[0-9]+)&nbsp;&nbsp;',
-            webpage, 'upload_date', fatal=False))
-
-        duration = parse_duration(self._html_search_regex(
-            r'&nbsp;&nbsp;Länge: ([0-9]+:[0-9]+)</span>', webpage, 'duration',
-            fatal=False))
-
-        view_count = str_to_int(self._html_search_regex(
-            r'&nbsp;&nbsp;Zuschauer: ([0-9\.]+)&nbsp;&nbsp;', webpage,
-            'view_count', fatal=False))
+        # TODO: there are multiple ld+json objects in the webpage,
+        # while _search_json_ld finds only the first one
+        json_ld = self._parse_json(self._search_regex(
+            r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
+            webpage, 'JSON-LD', group='json_ld'), video_id)
+        info_dict = self._json_ld(json_ld, video_id)
+        info_dict['title'] = remove_end(info_dict['title'], ' - GameStar')
 
+        view_count = json_ld.get('interactionCount')
         comment_count = int_or_none(self._html_search_regex(
-            r'>Kommentieren \(([0-9]+)\)</a>', webpage, 'comment_count',
+            r'([0-9]+) Kommentare</span>', webpage, 'comment_count',
             fatal=False))
 
-        return {
+        info_dict.update({
             'id': video_id,
-            'title': title,
             'url': url,
             'ext': 'mp4',
-            'thumbnail': thumbnail,
-            'description': description,
-            'upload_date': upload_date,
-            'duration': duration,
             'view_count': view_count,
             'comment_count': comment_count
-        }
+        })
+
+        return info_dict

youtube_dl/extractor/globo.py

@@ -19,7 +19,7 @@ from ..utils import (
 
 
 class GloboIE(InfoExtractor):
-    _VALID_URL = '(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
+    _VALID_URL = r'(?:globo:|https?://.+?\.globo\.com/(?:[^/]+/)*(?:v/(?:[^/]+/)?|videos/))(?P<id>\d{7,})'
 
     _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
     _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s'
@@ -396,7 +396,7 @@ class GloboIE(InfoExtractor):
 
 
 class GloboArticleIE(InfoExtractor):
-    _VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
+    _VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
 
     _VIDEOID_REGEXES = [
         r'\bdata-video-id=["\'](\d{7,})',

youtube_dl/extractor/internetvideoarchive.py

@@ -48,13 +48,23 @@ class InternetVideoArchiveIE(InfoExtractor):
             # There are multiple videos in the playlist whlie only the first one
             # matches the video played in browsers
             video_info = configuration['playlist'][0]
+            title = video_info['title']
 
             formats = []
             for source in video_info['sources']:
                 file_url = source['file']
                 if determine_ext(file_url) == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        file_url, video_id, ext='mp4', m3u8_id='hls'))
+                    m3u8_formats = self._extract_m3u8_formats(
+                        file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+                    if m3u8_formats:
+                        formats.extend(m3u8_formats)
+                        file_url = m3u8_formats[0]['url']
+                        formats.extend(self._extract_f4m_formats(
+                            file_url.replace('.m3u8', '.f4m'),
+                            video_id, f4m_id='hds', fatal=False))
+                        formats.extend(self._extract_mpd_formats(
+                            file_url.replace('.m3u8', '.mpd'),
+                            video_id, mpd_id='dash', fatal=False))
                 else:
                     a_format = {
                         'url': file_url,
@@ -70,7 +80,6 @@ class InternetVideoArchiveIE(InfoExtractor):
 
             self._sort_formats(formats)
 
-            title = video_info['title']
             description = video_info.get('description')
             thumbnail = video_info.get('image')
         else:

youtube_dl/extractor/jwplatform.py

@@ -63,10 +63,17 @@ class JWPlatformBaseIE(InfoExtractor):
                         'ext': ext,
                     })
                 else:
+                    height = int_or_none(source.get('height'))
+                    if height is None:
+                        # Often no height is provided but there is a label in
+                        # format like 1080p.
+                        height = int_or_none(self._search_regex(
+                            r'^(\d{3,})[pP]$', source.get('label') or '',
+                            'height', default=None))
                     a_format = {
                         'url': source_url,
                         'width': int_or_none(source.get('width')),
-                        'height': int_or_none(source.get('height')),
+                        'height': height,
                         'ext': ext,
                     }
                     if source_url.startswith('rtmp'):

youtube_dl/extractor/karaoketv.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class KaraoketvIE(InfoExtractor):
-    _VALID_URL = r'http://www.karaoketv.co.il/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://www\.karaoketv\.co\.il/[^/]+/(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.karaoketv.co.il/%D7%A9%D7%99%D7%A8%D7%99_%D7%A7%D7%A8%D7%99%D7%95%D7%A7%D7%99/58356/%D7%90%D7%99%D7%96%D7%95%D7%9F',
         'info_dict': {

youtube_dl/extractor/lci.py

@@ -0,0 +1,24 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class LCIIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lci\.fr/[^/]+/[\w-]+-(?P<id>\d+)\.html'
+    _TEST = {
+        'url': 'http://www.lci.fr/international/etats-unis-a-j-62-hillary-clinton-reste-sans-voix-2001679.html',
+        'md5': '2fdb2538b884d4d695f9bd2bde137e6c',
+        'info_dict': {
+            'id': '13244802',
+            'ext': 'mp4',
+            'title': 'Hillary Clinton et sa quinte de toux, en plein meeting',
+            'description': 'md5:a4363e3a960860132f8124b62f4a01c9',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        wat_id = self._search_regex(r'data-watid=[\'"](\d+)', webpage, 'wat id')
+        return self.url_result('wat:' + wat_id, 'Wat', wat_id)

youtube_dl/extractor/miaopai.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class MiaoPaiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?miaopai\.com/show/(?P<id>[-A-Za-z0-9~_]+)'
+    _TEST = {
+        'url': 'http://www.miaopai.com/show/n~0hO7sfV1nBEw4Y29-Hqg__.htm',
+        'md5': '095ed3f1cd96b821add957bdc29f845b',
+        'info_dict': {
+            'id': 'n~0hO7sfV1nBEw4Y29-Hqg__',
+            'ext': 'mp4',
+            'title': '西游记音乐会的秒拍视频',
+            'thumbnail': 're:^https?://.*/n~0hO7sfV1nBEw4Y29-Hqg___m.jpg',
+        }
+    }
+
+    _USER_AGENT_IPAD = 'Mozilla/5.0 (iPad; CPU OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, video_id, headers={'User-Agent': self._USER_AGENT_IPAD})
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<div[^>]+class=(?P<q1>[\'"]).*\bvideo_img\b.*(?P=q1)[^>]+data-url=(?P<q2>[\'"])(?P<url>[^\'"]+)(?P=q2)',
+            webpage, 'thumbnail', fatal=False, group='url')
+        videos = self._parse_html5_media_entries(url, webpage, video_id)
+        info = videos[0]
+
+        info.update({
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+        })
+        return info

youtube_dl/extractor/moevideo.py

@@ -35,7 +35,8 @@ class MoeVideoIE(InfoExtractor):
                 'height': 360,
                 'duration': 179,
                 'filesize': 17822500,
-            }
+            },
+            'skip': 'Video has been removed',
         },
         {
             'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',

youtube_dl/extractor/nick.py

@@ -69,13 +69,16 @@ class NickIE(MTVServicesInfoExtractor):
 
 class NickDeIE(MTVServicesInfoExtractor):
     IE_NAME = 'nick.de'
-    _VALID_URL = r'https?://(?:www\.)?nick\.de/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:nick\.de|nickelodeon\.nl)/(?:playlist|shows)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.nick.de/playlist/3773-top-videos/videos/episode/17306-zu-wasser-und-zu-land-rauchende-erdnusse',
         'only_matching': True,
     }, {
         'url': 'http://www.nick.de/shows/342-icarly',
         'only_matching': True,
+    }, {
+        'url': 'http://www.nickelodeon.nl/shows/474-spongebob/videos/17403-een-kijkje-in-de-keuken-met-sandy-van-binnenuit',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/onet.py

@@ -90,7 +90,7 @@ class OnetBaseIE(InfoExtractor):
 
 
 class OnetIE(OnetBaseIE):
-    _VALID_URL = 'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
+    _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
     IE_NAME = 'onet.tv'
 
     _TEST = {

youtube_dl/extractor/pornovoisines.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import random
 
 from .common import InfoExtractor
 from ..utils import (
@@ -13,61 +12,69 @@ from ..utils import (
 
 
 class PornoVoisinesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
-
-    _VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
-        '/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
-
-    _SERVER_NUMBERS = (1, 2)
+    _VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P<id>\d+)/(?P<display_id>[^/.]+)'
 
     _TEST = {
-        'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
-        'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
+        'url': 'http://www.pornovoisines.com/videos/show/919/recherche-appartement.html',
+        'md5': '6f8aca6a058592ab49fe701c8ba8317b',
         'info_dict': {
-            'id': '1285',
+            'id': '919',
             'display_id': 'recherche-appartement',
             'ext': 'mp4',
             'title': 'Recherche appartement',
-            'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
+            'description': 'md5:fe10cb92ae2dd3ed94bb4080d11ff493',
             'thumbnail': 're:^https?://.*\.jpg$',
             'upload_date': '20140925',
             'duration': 120,
             'view_count': int,
             'average_rating': float,
-            'categories': ['Débutantes', 'Scénario', 'Sodomie'],
+            'categories': ['Débutante', 'Débutantes', 'Scénario', 'Sodomie'],
             'age_limit': 18,
+            'subtitles': {
+                'fr': [{
+                    'ext': 'vtt',
+                }]
+            },
         }
     }
 
-    @classmethod
-    def build_video_url(cls, num):
-        return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num)
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         display_id = mobj.group('display_id')
 
+        settings_url = self._download_json(
+            'http://www.pornovoisines.com/api/video/%s/getsettingsurl/' % video_id,
+            video_id, note='Getting settings URL')['video_settings_url']
+        settings = self._download_json(settings_url, video_id)['data']
+
+        formats = []
+        for kind, data in settings['variants'].items():
+            if kind == 'HLS':
+                formats.extend(self._extract_m3u8_formats(
+                    data, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
+            elif kind == 'MP4':
+                for item in data:
+                    formats.append({
+                        'url': item['url'],
+                        'height': item.get('height'),
+                        'bitrate': item.get('bitrate'),
+                    })
+        self._sort_formats(formats)
+
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self.build_video_url(video_id)
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
 
-        title = self._html_search_regex(
-            r'<h1>(.+?)</h1>', webpage, 'title', flags=re.DOTALL)
-        description = self._html_search_regex(
-            r'<article id="descriptif">(.+?)</article>',
-            webpage, 'description', fatal=False, flags=re.DOTALL)
-
-        thumbnail = self._search_regex(
-            r'<div id="mediaspace%s">\s*<img src="/?([^"]+)"' % video_id,
-            webpage, 'thumbnail', fatal=False)
-        if thumbnail:
-            thumbnail = 'http://www.pornovoisines.com/%s' % thumbnail
+        # The webpage has a bug - there's no space between "thumb" and src=
+        thumbnail = self._html_search_regex(
+            r'<img[^>]+class=([\'"])thumb\1[^>]*src=([\'"])(?P<url>[^"]+)\2',
+            webpage, 'thumbnail', fatal=False, group='url')
 
         upload_date = unified_strdate(self._search_regex(
-            r'Publié le ([\d-]+)', webpage, 'upload date', fatal=False))
-        duration = int_or_none(self._search_regex(
-            'Durée (\d+)', webpage, 'duration', fatal=False))
+            r'Le\s*<b>([\d/]+)', webpage, 'upload date', fatal=False))
+        duration = settings.get('main', {}).get('duration')
         view_count = int_or_none(self._search_regex(
             r'(\d+) vues', webpage, 'view count', fatal=False))
         average_rating = self._search_regex(
@@ -75,15 +82,19 @@ class PornoVoisinesIE(InfoExtractor):
         if average_rating:
             average_rating = float_or_none(average_rating.replace(',', '.'))
 
-        categories = self._html_search_meta(
-            'keywords', webpage, 'categories', fatal=False)
+        categories = self._html_search_regex(
+            r'(?s)Catégories\s*:\s*<b>(.+?)</b>', webpage, 'categories', fatal=False)
         if categories:
             categories = [category.strip() for category in categories.split(',')]
 
+        subtitles = {'fr': [{
+            'url': subtitle,
+        } for subtitle in settings.get('main', {}).get('vtt_tracks', {}).values()]}
+
         return {
             'id': video_id,
             'display_id': display_id,
-            'url': video_url,
+            'formats': formats,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
@@ -93,4 +104,5 @@ class PornoVoisinesIE(InfoExtractor):
             'average_rating': average_rating,
             'categories': categories,
             'age_limit': 18,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/prosiebensat1.py

@@ -15,7 +15,111 @@ from ..utils import (
 )
 
 
-class ProSiebenSat1IE(InfoExtractor):
+class ProSiebenSat1BaseIE(InfoExtractor):
+    def _extract_video_info(self, url, clip_id):
+        client_location = url
+
+        video = self._download_json(
+            'http://vas.sim-technik.de/vas/live/v2/videos',
+            clip_id, 'Downloading videos JSON', query={
+                'access_token': self._TOKEN,
+                'client_location': client_location,
+                'client_name': self._CLIENT_NAME,
+                'ids': clip_id,
+            })[0]
+
+        if video.get('is_protected') is True:
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
+        duration = float_or_none(video.get('duration'))
+        source_ids = [compat_str(source['id']) for source in video['sources']]
+
+        client_id = self._SALT[:2] + sha1(''.join([clip_id, self._SALT, self._TOKEN, client_location, self._SALT, self._CLIENT_NAME]).encode('utf-8')).hexdigest()
+
+        sources = self._download_json(
+            'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
+            clip_id, 'Downloading sources JSON', query={
+                'access_token': self._TOKEN,
+                'client_id': client_id,
+                'client_location': client_location,
+                'client_name': self._CLIENT_NAME,
+            })
+        server_id = sources['server_id']
+
+        def fix_bitrate(bitrate):
+            bitrate = int_or_none(bitrate)
+            if not bitrate:
+                return None
+            return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
+
+        formats = []
+        for source_id in source_ids:
+            client_id = self._SALT[:2] + sha1(''.join([self._SALT, clip_id, self._TOKEN, server_id, client_location, source_id, self._SALT, self._CLIENT_NAME]).encode('utf-8')).hexdigest()
+            urls = self._download_json(
+                'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
+                clip_id, 'Downloading urls JSON', fatal=False, query={
+                    'access_token': self._TOKEN,
+                    'client_id': client_id,
+                    'client_location': client_location,
+                    'client_name': self._CLIENT_NAME,
+                    'server_id': server_id,
+                    'source_ids': source_id,
+                })
+            if not urls:
+                continue
+            if urls.get('status_code') != 0:
+                raise ExtractorError('This video is unavailable', expected=True)
+            urls_sources = urls['sources']
+            if isinstance(urls_sources, dict):
+                urls_sources = urls_sources.values()
+            for source in urls_sources:
+                source_url = source.get('url')
+                if not source_url:
+                    continue
+                protocol = source.get('protocol')
+                mimetype = source.get('mimetype')
+                if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        source_url, clip_id, f4m_id='hds', fatal=False))
+                elif mimetype == 'application/x-mpegURL':
+                    formats.extend(self._extract_m3u8_formats(
+                        source_url, clip_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+                else:
+                    tbr = fix_bitrate(source['bitrate'])
+                    if protocol in ('rtmp', 'rtmpe'):
+                        mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
+                        if not mobj:
+                            continue
+                        path = mobj.group('path')
+                        mp4colon_index = path.rfind('mp4:')
+                        app = path[:mp4colon_index]
+                        play_path = path[mp4colon_index:]
+                        formats.append({
+                            'url': '%s/%s' % (mobj.group('url'), app),
+                            'app': app,
+                            'play_path': play_path,
+                            'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
+                            'page_url': 'http://www.prosieben.de',
+                            'tbr': tbr,
+                            'ext': 'flv',
+                            'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
+                        })
+                    else:
+                        formats.append({
+                            'url': source_url,
+                            'tbr': tbr,
+                            'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
+                        })
+        self._sort_formats(formats)
+
+        return {
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class ProSiebenSat1IE(ProSiebenSat1BaseIE):
     IE_NAME = 'prosiebensat1'
     IE_DESC = 'ProSiebenSat.1 Digital'
     _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany|7tv)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
@@ -188,6 +292,9 @@ class ProSiebenSat1IE(InfoExtractor):
         },
     ]
 
+    _TOKEN = 'prosieben'
+    _SALT = '01!8d8F_)r9]4s[qeuXfP%'
+    _CLIENT_NAME = 'kolibri-2.0.19-splec4'
     _CLIPID_REGEXES = [
         r'"clip_id"\s*:\s+"(\d+)"',
         r'clipid: "(\d+)"',
@@ -234,123 +341,22 @@ class ProSiebenSat1IE(InfoExtractor):
     def _extract_clip(self, url, webpage):
         clip_id = self._html_search_regex(
             self._CLIPID_REGEXES, webpage, 'clip id')
-
-        access_token = 'prosieben'
-        client_name = 'kolibri-2.0.19-splec4'
-        client_location = url
-
-        video = self._download_json(
-            'http://vas.sim-technik.de/vas/live/v2/videos',
-            clip_id, 'Downloading videos JSON', query={
-                'access_token': access_token,
-                'client_location': client_location,
-                'client_name': client_name,
-                'ids': clip_id,
-            })[0]
-
-        if video.get('is_protected') is True:
-            raise ExtractorError('This video is DRM protected.', expected=True)
-
-        duration = float_or_none(video.get('duration'))
-        source_ids = [compat_str(source['id']) for source in video['sources']]
-
-        g = '01!8d8F_)r9]4s[qeuXfP%'
-        client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name]).encode('utf-8')).hexdigest()
-
-        sources = self._download_json(
-            'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
-            clip_id, 'Downloading sources JSON', query={
-                'access_token': access_token,
-                'client_id': client_id,
-                'client_location': client_location,
-                'client_name': client_name,
-            })
-        server_id = sources['server_id']
-
         title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
-
-        def fix_bitrate(bitrate):
-            bitrate = int_or_none(bitrate)
-            if not bitrate:
-                return None
-            return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
-
-        formats = []
-        for source_id in source_ids:
-            client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id, client_location, source_id, g, client_name]).encode('utf-8')).hexdigest()
-            urls = self._download_json(
-                'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
-                clip_id, 'Downloading urls JSON', fatal=False, query={
-                    'access_token': access_token,
-                    'client_id': client_id,
-                    'client_location': client_location,
-                    'client_name': client_name,
-                    'server_id': server_id,
-                    'source_ids': source_id,
-                })
-            if not urls:
-                continue
-            if urls.get('status_code') != 0:
-                raise ExtractorError('This video is unavailable', expected=True)
-            urls_sources = urls['sources']
-            if isinstance(urls_sources, dict):
-                urls_sources = urls_sources.values()
-            for source in urls_sources:
-                source_url = source.get('url')
-                if not source_url:
-                    continue
-                protocol = source.get('protocol')
-                mimetype = source.get('mimetype')
-                if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
-                    formats.extend(self._extract_f4m_formats(
-                        source_url, clip_id, f4m_id='hds', fatal=False))
-                elif mimetype == 'application/x-mpegURL':
-                    formats.extend(self._extract_m3u8_formats(
-                        source_url, clip_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls', fatal=False))
-                else:
-                    tbr = fix_bitrate(source['bitrate'])
-                    if protocol in ('rtmp', 'rtmpe'):
-                        mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
-                        if not mobj:
-                            continue
-                        path = mobj.group('path')
-                        mp4colon_index = path.rfind('mp4:')
-                        app = path[:mp4colon_index]
-                        play_path = path[mp4colon_index:]
-                        formats.append({
-                            'url': '%s/%s' % (mobj.group('url'), app),
-                            'app': app,
-                            'play_path': play_path,
-                            'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
-                            'page_url': 'http://www.prosieben.de',
-                            'tbr': tbr,
-                            'ext': 'flv',
-                            'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
-                        })
-                    else:
-                        formats.append({
-                            'url': source_url,
-                            'tbr': tbr,
-                            'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
-                        })
-        self._sort_formats(formats)
-
+        info = self._extract_video_info(url, clip_id)
         description = self._html_search_regex(
             self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
         thumbnail = self._og_search_thumbnail(webpage)
         upload_date = unified_strdate(self._html_search_regex(
             self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))
 
-        return {
+        info.update({
             'id': clip_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
             'upload_date': upload_date,
-            'duration': duration,
-            'formats': formats,
-        }
+        })
+        return info
 
     def _extract_playlist(self, url, webpage):
         playlist_id = self._html_search_regex(

youtube_dl/extractor/puls4.py

@@ -1,88 +1,51 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+from .prosiebensat1 import ProSiebenSat1BaseIE
 from ..utils import (
-    ExtractorError,
     unified_strdate,
-    int_or_none,
+    parse_duration,
+    compat_str,
 )
 
 
-class Puls4IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?puls4\.com/video/[^/]+/play/(?P<id>[0-9]+)'
+class Puls4IE(ProSiebenSat1BaseIE):
+    _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)'
     _TESTS = [{
-        'url': 'http://www.puls4.com/video/pro-und-contra/play/2716816',
-        'md5': '49f6a6629747eeec43cef6a46b5df81d',
+        'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
+        'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
         'info_dict': {
-            'id': '2716816',
-            'ext': 'mp4',
-            'title': 'Pro und Contra vom 23.02.2015',
-            'description': 'md5:293e44634d9477a67122489994675db6',
-            'duration': 2989,
-            'upload_date': '20150224',
+            'id': '118118',
+            'ext': 'flv',
+            'title': 'Tobias Homberger von myclubs im #2min2miotalk',
+            'description': 'md5:f9def7c5e8745d6026d8885487d91955',
+            'upload_date': '20160830',
             'uploader': 'PULS_4',
         },
-        'skip': 'Only works from Germany',
-    }, {
-        'url': 'http://www.puls4.com/video/kult-spielfilme/play/1298106',
-        'md5': '6a48316c8903ece8dab9b9a7bf7a59ec',
-        'info_dict': {
-            'id': '1298106',
-            'ext': 'mp4',
-            'title': 'Lucky Fritz',
-        },
-        'skip': 'Only works from Germany',
     }]
+    _TOKEN = 'puls4'
+    _SALT = '01!kaNgaiNgah1Ie4AeSha'
+    _CLIENT_NAME = ''
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        error_message = self._html_search_regex(
-            r'<div[^>]+class="message-error"[^>]*>(.+?)</div>',
-            webpage, 'error message', default=None)
-        if error_message:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
-
-        real_url = self._html_search_regex(
-            r'\"fsk-button\".+?href=\"([^"]+)',
-            webpage, 'fsk_button', default=None)
-        if real_url:
-            webpage = self._download_webpage(real_url, video_id)
-
-        player = self._search_regex(
-            r'p4_video_player(?:_iframe)?\("video_\d+_container"\s*,(.+?)\);\s*\}',
-            webpage, 'player')
-
-        player_json = self._parse_json(
-            '[%s]' % player, video_id,
-            transform_source=lambda s: s.replace('undefined,', ''))
-
-        formats = None
-        result = None
-
-        for v in player_json:
-            if isinstance(v, list) and not formats:
-                formats = [{
-                    'url': f['url'],
-                    'format': 'hd' if f.get('hd') else 'sd',
-                    'width': int_or_none(f.get('size_x')),
-                    'height': int_or_none(f.get('size_y')),
-                    'tbr': int_or_none(f.get('bitrate')),
-                } for f in v]
-                self._sort_formats(formats)
-            elif isinstance(v, dict) and not result:
-                result = {
-                    'id': video_id,
-                    'title': v['videopartname'].strip(),
-                    'description': v.get('videotitle'),
-                    'duration': int_or_none(v.get('videoduration') or v.get('episodeduration')),
-                    'upload_date': unified_strdate(v.get('clipreleasetime')),
-                    'uploader': v.get('channel'),
-                }
-
-        result['formats'] = formats
-
-        return result
+        path = self._match_id(url)
+        content_path = self._download_json(
+            'http://www.puls4.com/api/json-fe/page/' + path, path)['content'][0]['url']
+        media = self._download_json(
+            'http://www.puls4.com' + content_path,
+            content_path)['mediaCurrent']
+        player_content = media['playerContent']
+        info = self._extract_video_info(url, player_content['id'])
+        info.update({
+            'id': compat_str(media['objectId']),
+            'title': player_content['title'],
+            'description': media.get('description'),
+            'thumbnail': media.get('previewLink'),
+            'upload_date': unified_strdate(media.get('date')),
+            'duration': parse_duration(player_content.get('duration')),
+            'episode': player_content.get('episodePartName'),
+            'show': media.get('channel'),
+            'season_id': player_content.get('seasonId'),
+            'uploader': player_content.get('sourceCompany'),
+        })
+        return info

youtube_dl/extractor/rmcdecouverte.py

@@ -0,0 +1,39 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveLegacyIE
+from ..compat import (
+    compat_parse_qs,
+    compat_urlparse,
+)
+
+
+class RMCDecouverteIE(InfoExtractor):
+    _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/mediaplayer-replay.*?\bid=(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://rmcdecouverte.bfmtv.com/mediaplayer-replay/?id=1430&title=LES%20HEROS%20DU%2088e%20ETAGE',
+        'info_dict': {
+            'id': '5111223049001',
+            'ext': 'mp4',
+            'title': ': LES HEROS DU 88e ETAGE',
+            'description': 'Découvrez comment la bravoure de deux hommes dans la Tour Nord du World Trade Center a sauvé  la vie d\'innombrables personnes le 11 septembre 2001.',
+            'uploader_id': '1969646226001',
+            'upload_date': '20160904',
+            'timestamp': 1472951103,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+        'skip': 'Only works from France',
+    }
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1969646226001/default_default/index.html?videoId=%s'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
+        brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
+        return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

youtube_dl/extractor/rottentomatoes.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from .internetvideoarchive import InternetVideoArchiveIE
 
 
@@ -11,21 +10,23 @@ class RottenTomatoesIE(InfoExtractor):
     _TEST = {
         'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
         'info_dict': {
-            'id': '613340',
+            'id': '11028566',
             'ext': 'mp4',
             'title': 'Toy Story 3',
+            'description': 'From the creators of the beloved TOY STORY films, comes a story that will reunite the gang in a whole new way.',
+            'thumbnail': 're:^https?://.*\.jpg$',
         },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        og_video = self._og_search_video_url(webpage)
-        query = compat_urlparse.urlparse(og_video).query
+        iva_id = self._search_regex(r'publishedid=(\d+)', webpage, 'internet video archive id')
 
         return {
             '_type': 'url_transparent',
-            'url': InternetVideoArchiveIE._build_xml_url(query),
+            'url': 'http://video.internetvideoarchive.net/player/6/configuration.ashx?domain=www.videodetective.com&customerid=69249&playerid=641&publishedid=' + iva_id,
             'ie_key': InternetVideoArchiveIE.ie_key(),
+            'id': video_id,
             'title': self._og_search_title(webpage),
         }

youtube_dl/extractor/rutube.py

@@ -88,7 +88,7 @@ class RutubeIE(InfoExtractor):
 class RutubeEmbedIE(InfoExtractor):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'
-    _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 
     _TESTS = [{
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',

youtube_dl/extractor/spiegel.py

@@ -103,7 +103,7 @@ class SpiegelIE(InfoExtractor):
 
 
 class SpiegelArticleIE(InfoExtractor):
-    _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
     IE_NAME = 'Spiegel:Article'
     IE_DESC = 'Articles on spiegel.de'
     _TESTS = [{

youtube_dl/extractor/tbs.py

@@ -53,7 +53,7 @@ class TBSIE(TurnerBaseIE):
                     'media_src': 'http://ht.cdn.turner.com/%s/big' % site,
                 },
                 'secure': {
-                    'media_src': 'http://apple-secure.cdn.turner.com/%s/big' % site,
+                    'media_src': 'http://androidhls-secure.cdn.turner.com/%s/big' % site,
                     'tokenizer_src': 'http://www.%s.com/video/processors/services/token_ipadAdobe.do' % domain,
                 },
             })

youtube_dl/extractor/theplatform.py

@@ -96,7 +96,7 @@ class ThePlatformBaseIE(OnceIE):
 class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
     _VALID_URL = r'''(?x)
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
-           (?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
+           (?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)?|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
          |theplatform:)(?P<id>[^/\?&]+)'''
 
     _TESTS = [{
@@ -116,6 +116,7 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
             # rtmp download
             'skip_download': True,
         },
+        'skip': '404 Not Found',
     }, {
         # from http://www.cnet.com/videos/tesla-model-s-a-second-step-towards-a-cleaner-motoring-future/
         'url': 'http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRT',

youtube_dl/extractor/tlc.py

@@ -1,10 +1,14 @@
 # encoding: utf-8
 from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from .brightcove import BrightcoveLegacyIE
-from ..compat import compat_parse_qs
+from ..compat import (
+    compat_parse_qs,
+    compat_urlparse,
+)
 
 
 class TlcDeIE(InfoExtractor):
@@ -35,5 +39,5 @@ class TlcDeIE(InfoExtractor):
             title = mobj.group('title')
             webpage = self._download_webpage(url, title)
             brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
-            brightcove_id = compat_parse_qs(brightcove_legacy_url)['@videoPlayer'][0]
+            brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
         return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)

youtube_dl/extractor/trutv.py

@@ -0,0 +1,35 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .turner import TurnerBaseIE
+
+
+class TruTVIE(TurnerBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?trutv\.com(?:(?P<path>/shows/[^/]+/videos/[^/?#]+?)\.html|/full-episodes/[^/]+/(?P<id>\d+))'
+    _TEST = {
+        'url': 'http://www.trutv.com/shows/10-things/videos/you-wont-believe-these-sports-bets.html',
+        'md5': '2cdc844f317579fed1a7251b087ff417',
+        'info_dict': {
+            'id': '/shows/10-things/videos/you-wont-believe-these-sports-bets',
+            'ext': 'mp4',
+            'title': 'You Won\'t Believe These Sports Bets',
+            'description': 'Jamie Lee sits down with a bookie to discuss the bizarre world of illegal sports betting.',
+            'upload_date': '20130305',
+        }
+    }
+
+    def _real_extract(self, url):
+        path, video_id = re.match(self._VALID_URL, url).groups()
+        if path:
+            data_src = 'http://www.trutv.com/video/cvp/v2/xml/content.xml?id=%s.xml' % path
+        else:
+            data_src = 'http://www.trutv.com/tveverywhere/services/cvpXML.do?titleId=' + video_id
+        return self._extract_cvp_info(
+            data_src, path, {
+                'secure': {
+                    'media_src': 'http://androidhls-secure.cdn.turner.com/trutv/big',
+                    'tokenizer_src': 'http://www.trutv.com/tveverywhere/processors/services/token_ipadAdobe.do',
+                },
+            })

youtube_dl/extractor/turner.py

@@ -12,7 +12,7 @@ from ..utils import (
     parse_duration,
     xpath_attr,
     update_url_query,
-    compat_urlparse,
+    ExtractorError,
 )
 
 
@@ -24,6 +24,7 @@ class TurnerBaseIE(InfoExtractor):
         video_data = self._download_xml(data_src, video_id)
         video_id = video_data.attrib['id']
         title = xpath_text(video_data, 'headline', fatal=True)
+        content_id = xpath_text(video_data, 'contentId') or video_id
         # rtmp_src = xpath_text(video_data, 'akamai/src')
         # if rtmp_src:
         #     splited_rtmp_src = rtmp_src.split(',')
@@ -54,7 +55,7 @@ class TurnerBaseIE(InfoExtractor):
                 # auth = self._download_webpage(
                 #     protected_path_data['tokenizer_src'], query={
                 #         'path': protected_path,
-                #         'videoId': video_id,
+                #         'videoId': content_id,
                 #         'aifp': aifp,
                 #     })
                 # token = xpath_text(auth, 'token')
@@ -72,8 +73,11 @@ class TurnerBaseIE(InfoExtractor):
                     auth = self._download_xml(
                         secure_path_data['tokenizer_src'], video_id, query={
                             'path': secure_path,
-                            'videoId': video_id,
+                            'videoId': content_id,
                         })
+                    error_msg = xpath_text(auth, 'error/msg')
+                    if error_msg:
+                        raise ExtractorError(error_msg, expected=True)
                     token = xpath_text(auth, 'token')
                     if not token:
                         continue
@@ -93,19 +97,9 @@ class TurnerBaseIE(InfoExtractor):
                 formats.extend(self._extract_smil_formats(
                     video_url, video_id, fatal=False))
             elif ext == 'm3u8':
-                m3u8_formats = self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', m3u8_id=format_id or 'hls',
-                    fatal=False)
-                if m3u8_formats:
-                    # Sometimes final URLs inside m3u8 are unsigned, let's fix this
-                    # ourselves
-                    qs = compat_urlparse.urlparse(video_url).query
-                    if qs:
-                        query = compat_urlparse.parse_qs(qs)
-                        for m3u8_format in m3u8_formats:
-                            m3u8_format['url'] = update_url_query(m3u8_format['url'], query)
-                            m3u8_format['extra_param_to_segment_url'] = qs
-                    formats.extend(m3u8_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4',
+                    m3u8_id=format_id or 'hls', fatal=False))
             elif ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
                     update_url_query(video_url, {'hdcore': '3.7.0'}),

youtube_dl/extractor/tvnoe.py

@@ -0,0 +1,49 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+    js_to_json,
+)
+
+
+class TVNoeIE(JWPlatformBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.tvnoe.cz/video/10362',
+        'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
+        'info_dict': {
+            'id': '10362',
+            'ext': 'mp4',
+            'series': 'Noční univerzita',
+            'title': 'prof. Tomáš Halík, Th.D. - Návrat náboženství a střet civilizací',
+            'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        iframe_url = self._search_regex(
+            r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')
+
+        ifs_page = self._download_webpage(iframe_url, video_id)
+        jwplayer_data = self._parse_json(
+            self._find_jwplayer_data(ifs_page),
+            video_id, transform_source=js_to_json)
+        info_dict = self._parse_jwplayer_data(
+            jwplayer_data, video_id, require_title=False, base_url=iframe_url)
+
+        info_dict.update({
+            'id': video_id,
+            'title': clean_html(get_element_by_class(
+                'field-name-field-podnazev', webpage)),
+            'description': clean_html(get_element_by_class(
+                'field-name-body', webpage)),
+            'series': clean_html(get_element_by_class('title', webpage))
+        })
+
+        return info_dict

youtube_dl/extractor/tvplay.py

@@ -348,6 +348,25 @@ class ViafreeIE(InfoExtractor):
             'skip_download': True,
         },
         'add_ie': [TVPlayIE.ie_key()],
+    }, {
+        # with relatedClips
+        'url': 'http://www.viafree.se/program/reality/sommaren-med-youtube-stjarnorna/sasong-1/avsnitt-1',
+        'info_dict': {
+            'id': '758770',
+            'ext': 'mp4',
+            'title': 'Sommaren med YouTube-stjärnorna S01E01',
+            'description': 'md5:2bc69dce2c4bb48391e858539bbb0e3f',
+            'series': 'Sommaren med YouTube-stjärnorna',
+            'season': 'Säsong 1',
+            'season_number': 1,
+            'duration': 1326,
+            'timestamp': 1470905572,
+            'upload_date': '20160811',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [TVPlayIE.ie_key()],
     }, {
         'url': 'http://www.viafree.no/programmer/underholdning/det-beste-vorspielet/sesong-2/episode-1',
         'only_matching': True,
@@ -365,8 +384,17 @@ class ViafreeIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        video_id = self._search_regex(
-            r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](?P<id>\d{6,})',
-            webpage, 'video id')
+        video_id = None
+
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
+        if thumbnail:
+            video_id = self._search_regex(
+                r'https?://[^/]+/imagecache/(?:[^/]+/)+seasons/\d+/(\d{6,})/',
+                thumbnail, 'video id', default=None)
+
+        if not video_id:
+            video_id = self._search_regex(
+                r'currentVideo["\']\s*:\s*.+?["\']id["\']\s*:\s*["\'](\d{6,})',
+                webpage, 'video id')
 
         return self.url_result('mtg:%s' % video_id, TVPlayIE.ie_key())

youtube_dl/extractor/twitter.py

@@ -342,7 +342,7 @@ class TwitterIE(InfoExtractor):
 
 class TwitterAmplifyIE(TwitterBaseIE):
     IE_NAME = 'twitter:amplify'
-    _VALID_URL = 'https?://amp\.twimg\.com/v/(?P<id>[0-9a-f\-]{36})'
+    _VALID_URL = r'https?://amp\.twimg\.com/v/(?P<id>[0-9a-f\-]{36})'
 
     _TEST = {
         'url': 'https://amp.twimg.com/v/0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951',

youtube_dl/extractor/videomore.py

@@ -6,8 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    parse_age_limit,
-    parse_iso8601,
+    xpath_element,
     xpath_text,
 )
 
@@ -17,38 +16,32 @@ class VideomoreIE(InfoExtractor):
     _VALID_URL = r'videomore:(?P<sid>\d+)$|https?://videomore\.ru/(?:(?:embed|[^/]+/[^/]+)/|[^/]+\?.*\btrack_id=)(?P<id>\d+)(?:[/?#&]|\.(?:xml|json)|$)'
     _TESTS = [{
         'url': 'http://videomore.ru/kino_v_detalayah/5_sezon/367617',
-        'md5': '70875fbf57a1cd004709920381587185',
+        'md5': '44455a346edc0d509ac5b5a5b531dc35',
         'info_dict': {
             'id': '367617',
             'ext': 'flv',
-            'title': 'В гостях Алексей Чумаков и Юлия Ковальчук',
-            'description': 'В гостях – лучшие романтические комедии года, «Выживший» Иньярриту и «Стив Джобс» Дэнни Бойла.',
+            'title': 'Кино в деталях 5 сезон В гостях Алексей Чумаков и Юлия Ковальчук',
             'series': 'Кино в деталях',
             'episode': 'В гостях Алексей Чумаков и Юлия Ковальчук',
-            'episode_number': None,
-            'season': 'Сезон 2015',
-            'season_number': 5,
             'thumbnail': 're:^https?://.*\.jpg',
             'duration': 2910,
-            'age_limit': 16,
             'view_count': int,
+            'comment_count': int,
+            'age_limit': 16,
         },
     }, {
         'url': 'http://videomore.ru/embed/259974',
         'info_dict': {
             'id': '259974',
             'ext': 'flv',
-            'title': '80 серия',
-            'description': '«Медведей» ждет решающий матч. Макеев выясняет отношения со Стрельцовым. Парни узнают подробности прошлого Макеева.',
+            'title': 'Молодежка 2 сезон 40 серия',
             'series': 'Молодежка',
-            'episode': '80 серия',
-            'episode_number': 40,
-            'season': '2 сезон',
-            'season_number': 2,
+            'episode': '40 серия',
             'thumbnail': 're:^https?://.*\.jpg',
             'duration': 2809,
-            'age_limit': 16,
             'view_count': int,
+            'comment_count': int,
+            'age_limit': 16,
         },
         'params': {
             'skip_download': True,
@@ -58,13 +51,8 @@ class VideomoreIE(InfoExtractor):
         'info_dict': {
             'id': '341073',
             'ext': 'flv',
-            'title': 'Команда проиграла из-за Бакина?',
-            'description': 'Молодежка 3 сезон скоро',
-            'series': 'Молодежка',
+            'title': 'Промо Команда проиграла из-за Бакина?',
             'episode': 'Команда проиграла из-за Бакина?',
-            'episode_number': None,
-            'season': 'Промо',
-            'season_number': 99,
             'thumbnail': 're:^https?://.*\.jpg',
             'duration': 29,
             'age_limit': 16,
@@ -109,43 +97,33 @@ class VideomoreIE(InfoExtractor):
             'http://videomore.ru/video/tracks/%s.xml' % video_id,
             video_id, 'Downloading video XML')
 
-        video_url = xpath_text(video, './/video_url', 'video url', fatal=True)
+        item = xpath_element(video, './/playlist/item', fatal=True)
+
+        title = xpath_text(
+            item, ('./title', './episode_name'), 'title', fatal=True)
+
+        video_url = xpath_text(item, './video_url', 'video url', fatal=True)
         formats = self._extract_f4m_formats(video_url, video_id, f4m_id='hds')
         self._sort_formats(formats)
 
-        data = self._download_json(
-            'http://videomore.ru/video/tracks/%s.json' % video_id,
-            video_id, 'Downloading video JSON')
+        thumbnail = xpath_text(item, './thumbnail_url')
+        duration = int_or_none(xpath_text(item, './duration'))
+        view_count = int_or_none(xpath_text(item, './views'))
+        comment_count = int_or_none(xpath_text(item, './count_comments'))
+        age_limit = int_or_none(xpath_text(item, './min_age'))
 
-        title = data.get('title') or data['project_title']
-        description = data.get('description') or data.get('description_raw')
-        timestamp = parse_iso8601(data.get('published_at'))
-        duration = int_or_none(data.get('duration'))
-        view_count = int_or_none(data.get('views'))
-        age_limit = parse_age_limit(data.get('min_age'))
-        thumbnails = [{
-            'url': thumbnail,
-        } for thumbnail in data.get('big_thumbnail_urls', [])]
-
-        series = data.get('project_title')
-        episode = data.get('title')
-        episode_number = int_or_none(data.get('episode_of_season') or None)
-        season = data.get('season_title')
-        season_number = int_or_none(data.get('season_pos') or None)
+        series = xpath_text(item, './project_name')
+        episode = xpath_text(item, './episode_name')
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
             'series': series,
             'episode': episode,
-            'episode_number': episode_number,
-            'season': season,
-            'season_number': season_number,
-            'thumbnails': thumbnails,
-            'timestamp': timestamp,
+            'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,
+            'comment_count': comment_count,
             'age_limit': age_limit,
             'formats': formats,
         }

youtube_dl/extractor/vimple.py

@@ -28,23 +28,24 @@ class SprutoBaseIE(InfoExtractor):
 
 class VimpleIE(SprutoBaseIE):
     IE_DESC = 'Vimple - one-click video hosting'
-    _VALID_URL = r'https?://(?:player\.vimple\.ru/iframe|vimple\.ru)/(?P<id>[\da-f-]{32,36})'
-    _TESTS = [
-        {
-            'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
-            'md5': '2e750a330ed211d3fd41821c6ad9a279',
-            'info_dict': {
-                'id': 'c0f6b168-7dcd-4000-a97e-be70068039cf',
-                'ext': 'mp4',
-                'title': 'Sunset',
-                'duration': 20,
-                'thumbnail': 're:https?://.*?\.jpg',
-            },
-        }, {
-            'url': 'http://player.vimple.ru/iframe/52e1beec-1314-4a83-aeac-c61562eadbf9',
-            'only_matching': True,
-        }
-    ]
+    _VALID_URL = r'https?://(?:player\.vimple\.(?:ru|co)/iframe|vimple\.(?:ru|co))/(?P<id>[\da-f-]{32,36})'
+    _TESTS = [{
+        'url': 'http://vimple.ru/c0f6b1687dcd4000a97ebe70068039cf',
+        'md5': '2e750a330ed211d3fd41821c6ad9a279',
+        'info_dict': {
+            'id': 'c0f6b168-7dcd-4000-a97e-be70068039cf',
+            'ext': 'mp4',
+            'title': 'Sunset',
+            'duration': 20,
+            'thumbnail': 're:https?://.*?\.jpg',
+        },
+    }, {
+        'url': 'http://player.vimple.ru/iframe/52e1beec-1314-4a83-aeac-c61562eadbf9',
+        'only_matching': True,
+    }, {
+        'url': 'http://vimple.co/04506a053f124483b8fb05ed73899f19',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/wat.py

@@ -86,38 +86,50 @@ class WatIE(InfoExtractor):
 
         def extract_url(path_template, url_type):
             req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id)
-            head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type)
-            red_url = head.geturl()
-            if req_url == red_url:
-                raise ExtractorError(
-                    '%s said: Sorry, this video is not available from your country.' % self.IE_NAME,
-                    expected=True)
-            return red_url
+            head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type, fatal=False)
+            if head:
+                red_url = head.geturl()
+                if req_url != red_url:
+                    return red_url
+            return None
+
+        def remove_bitrate_limit(manifest_url):
+            return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url)
 
         formats = []
         try:
-            http_url = extract_url('android5/%s.mp4', 'http')
-            m3u8_url = extract_url('ipad/%s.m3u8', 'm3u8')
-            m3u8_formats = self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
-            formats.extend(m3u8_formats)
-            formats.extend(self._extract_f4m_formats(
-                m3u8_url.replace('ios.', 'web.').replace('.m3u8', '.f4m'),
-                video_id, f4m_id='hds', fatal=False))
-            for m3u8_format in m3u8_formats:
-                vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr')
-                if not vbr or not abr:
-                    continue
-                format_id = m3u8_format['format_id'].replace('hls', 'http')
-                fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url)
-                if self._is_valid_url(fmt_url, video_id, format_id):
-                    f = m3u8_format.copy()
-                    f.update({
-                        'url': fmt_url,
-                        'format_id': format_id,
-                        'protocol': 'http',
-                    })
-                    formats.append(f)
+            manifest_urls = self._download_json(
+                'http://www.wat.tv/get/webhtml/' + video_id, video_id)
+            m3u8_url = manifest_urls.get('hls')
+            if m3u8_url:
+                m3u8_url = remove_bitrate_limit(m3u8_url)
+                m3u8_formats = self._extract_m3u8_formats(
+                    m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+                    formats.extend(self._extract_f4m_formats(
+                        m3u8_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
+                        video_id, f4m_id='hds', fatal=False))
+                    http_url = extract_url('android5/%s.mp4', 'http')
+                    if http_url:
+                        for m3u8_format in m3u8_formats:
+                            vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr')
+                            if not vbr or not abr:
+                                continue
+                            format_id = m3u8_format['format_id'].replace('hls', 'http')
+                            fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url)
+                            if self._is_valid_url(fmt_url, video_id, format_id):
+                                f = m3u8_format.copy()
+                                f.update({
+                                    'url': fmt_url,
+                                    'format_id': format_id,
+                                    'protocol': 'http',
+                                })
+                                formats.append(f)
+            mpd_url = manifest_urls.get('mpd')
+            if mpd_url:
+                formats.extend(self._extract_mpd_formats(remove_bitrate_limit(
+                    mpd_url), video_id, mpd_id='dash', fatal=False))
             self._sort_formats(formats)
         except ExtractorError:
             abr = 64

youtube_dl/extractor/yahoo.py

@@ -19,7 +19,10 @@ from ..utils import (
     determine_ext,
 )
 
-from .brightcove import BrightcoveNewIE
+from .brightcove import (
+    BrightcoveLegacyIE,
+    BrightcoveNewIE,
+)
 from .nbc import NBCSportsVPlayerIE
 
 
@@ -223,6 +226,11 @@ class YahooIE(InfoExtractor):
         if nbc_sports_url:
             return self.url_result(nbc_sports_url, NBCSportsVPlayerIE.ie_key())
 
+        # Look for Brightcove Legacy Studio embeds
+        bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
+        if bc_url:
+            return self.url_result(bc_url, BrightcoveLegacyIE.ie_key())
+
         # Look for Brightcove New Studio embeds
         bc_url = BrightcoveNewIE._extract_url(webpage)
         if bc_url:

youtube_dl/extractor/youjizz.py

@@ -1,21 +1,16 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class YouJizzIE(InfoExtractor):
     _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/(?:[^/#?]+)?-(?P<id>[0-9]+)\.html(?:$|[?#])'
     _TESTS = [{
         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
-        'md5': '07e15fa469ba384c7693fd246905547c',
+        'md5': '78fc1901148284c69af12640e01c6310',
         'info_dict': {
             'id': '2189178',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Zeichentrick 1',
             'age_limit': 18,
         }
@@ -27,38 +22,18 @@ class YouJizzIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+        # YouJizz's HTML5 player has invalid HTML
+        webpage = webpage.replace('"controls', '" controls')
         age_limit = self._rta_search(webpage)
         video_title = self._html_search_regex(
             r'<title>\s*(.*)\s*</title>', webpage, 'title')
 
-        embed_page_url = self._search_regex(
-            r'(https?://www.youjizz.com/videos/embed/[0-9]+)',
-            webpage, 'embed page')
-        webpage = self._download_webpage(
-            embed_page_url, video_id, note='downloading embed page')
+        info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
 
-        # Get the video URL
-        m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage)
-        if m_playlist is not None:
-            playlist_url = m_playlist.group('playlist')
-            playlist_page = self._download_webpage(playlist_url, video_id,
-                                                   'Downloading playlist page')
-            m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
-            if len(m_levels) == 0:
-                raise ExtractorError('Unable to extract video url')
-            videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
-            (_, video_url) = sorted(videos)[0]
-            video_url = video_url.replace('%252F', '%2F')
-        else:
-            video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
-                                           webpage, 'video URL')
-
-        return {
+        info_dict.update({
             'id': video_id,
-            'url': video_url,
             'title': video_title,
-            'ext': 'flv',
-            'format': 'flv',
-            'player_url': embed_page_url,
             'age_limit': age_limit,
-        }
+        })
+
+        return info_dict

youtube_dl/extractor/youtube.py

@@ -264,7 +264,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                          )
                      )?                                                       # all until now is optional -> you can pass the naked ID
                      ([0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID
-                     (?!.*?&list=)                                            # combined list/video URLs are handled by the playlist IE
+                     (?!.*?\blist=)                                            # combined list/video URLs are handled by the playlist IE
                      (?(1).+)?                                                # if we found the ID, everything can follow
                      $"""
     _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
@@ -1778,11 +1778,14 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
     _VALID_URL = r"""(?x)(?:
                         (?:https?://)?
                         (?:\w+\.)?
-                        youtube\.com/
                         (?:
-                           (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
-                           \? (?:.*?[&;])*? (?:p|a|list)=
-                        |  p/
+                            youtube\.com/
+                            (?:
+                               (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
+                               \? (?:.*?[&;])*? (?:p|a|list)=
+                            |  p/
+                            )|
+                            youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
                         )
                         (
                             (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
@@ -1887,6 +1890,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             'skip_download': True,
         },
         'add_ie': [YoutubeIE.ie_key()],
+    }, {
+        'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
+        'only_matching': True,
     }]
 
     def _real_initialize(self):
@@ -2376,7 +2382,7 @@ class YoutubeWatchLaterIE(YoutubePlaylistIE):
     }]
 
     def _real_extract(self, url):
-        video = self._check_download_just_video(url, 'WL')
+        _, video = self._check_download_just_video(url, 'WL')
         if video:
             return video
         _, playlist = self._extract_playlist('WL')
@@ -2411,7 +2417,7 @@ class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
 
 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
     IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
-    _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
+    _VALID_URL = r'https?://www\.youtube\.com/feed/history|:ythistory'
     _FEED_NAME = 'history'
     _PLAYLIST_TITLE = 'Youtube History'
 

youtube_dl/options.py

@@ -423,7 +423,15 @@ def parseOpts(overrideArguments=None):
     downloader.add_option(
         '--fragment-retries',
         dest='fragment_retries', metavar='RETRIES', default=10,
-        help='Number of retries for a fragment (default is %default), or "infinite" (DASH only)')
+        help='Number of retries for a fragment (default is %default), or "infinite" (DASH and hlsnative only)')
+    downloader.add_option(
+        '--skip-unavailable-fragments',
+        action='store_true', dest='skip_unavailable_fragments', default=True,
+        help='Skip unavailable fragments (DASH and hlsnative only)')
+    general.add_option(
+        '--abort-on-unavailable-fragment',
+        action='store_false', dest='skip_unavailable_fragments',
+        help='Abort downloading when some fragment is not available')
     downloader.add_option(
         '--buffer-size',
         dest='buffersize', metavar='SIZE', default='1024',

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.09.03'
+__version__ = '2016.09.08'