release 2015.11.21

Looks like some courses are available without pluralsight account

AUTHORS

@@ -144,3 +144,5 @@ Lee Jenkins
 Anssi Hannula
 Lukáš Lalinský
 Qijiang Fan
+Rémy Léone
+Marco Ferragina

README.md

@@ -329,8 +329,8 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Subtitle Options:
     --write-sub                      Write subtitle file
-    --write-auto-sub                 Write automatic subtitle file (YouTube
-                                     only)
+    --write-auto-sub                 Write automatically generated subtitle file
+                                     (YouTube only)
     --all-subs                       Download all the available subtitles of the
                                      video
     --list-subs                      List all available subtitles for the video

docs/supportedsites.md

@@ -67,7 +67,8 @@
  - **Bpb**: Bundeszentrale für politische Bildung
  - **BR**: Bayerischer Rundfunk Mediathek
  - **Break**
- - **Brightcove**
+ - **brightcove:legacy**
+ - **brightcove:new**
  - **bt:article**: Bergens Tidende Articles
  - **bt:vestlendingen**: Bergens Tidende - Vestlendingen
  - **BuzzFeed**
@@ -123,10 +124,12 @@
  - **DctpTv**
  - **DeezerPlaylist**
  - **defense.gouv.fr**
+ - **democracynow**
  - **DHM**: Filmarchiv - Deutsches Historisches Museum
  - **Discovery**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
+ - **DPlay**
  - **dramafever**
  - **dramafever:series**
  - **DRBonanza**
@@ -195,10 +198,10 @@
  - **Giga**
  - **Glide**: Glide mobile video messages (glide.me)
  - **Globo**
+ - **GloboArticle**
  - **GodTube**
  - **GoldenMoustache**
  - **Golem**
- - **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com
  - **Goshgay**
  - **Groupon**
  - **Hark**
@@ -365,6 +368,7 @@
  - **nowness:playlist**
  - **nowness:series**
  - **NowTV**
+ - **NowTVList**
  - **nowvideo**: NowVideo
  - **npo**: npo.nl and ntr.nl
  - **npo.nl:live**
@@ -424,7 +428,6 @@
  - **qqmusic:playlist**: QQ音乐 - 歌单
  - **qqmusic:singer**: QQ音乐 - 歌手
  - **qqmusic:toplist**: QQ音乐 - 排行榜
- - **Quickscope**: Quick Scope
  - **QuickVid**
  - **R7**
  - **radio.de**
@@ -491,6 +494,7 @@
  - **soompi:show**
  - **soundcloud**
  - **soundcloud:playlist**
+ - **soundcloud:search**: Soundcloud search
  - **soundcloud:set**
  - **soundcloud:user**
  - **soundgasm**
@@ -617,7 +621,6 @@
  - **video.mit.edu**
  - **VideoDetective**
  - **videofy.me**
- - **videolectures.net**
  - **VideoMega**
  - **VideoPremium**
  - **VideoTt**: video.tt - Your True Tube
@@ -627,6 +630,7 @@
  - **vier**
  - **vier:videos**
  - **Viewster**
+ - **Viidea**
  - **viki**
  - **viki:channel**
  - **vimeo**
@@ -669,6 +673,7 @@
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
+ - **XFileShare**: XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me
  - **XHamster**
  - **XHamsterEmbed**
  - **XMinus**
@@ -703,6 +708,7 @@
  - **youtube:show**: YouTube.com (multi-season) shows
  - **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
  - **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
+ - **youtube:user:playlists**: YouTube.com user playlists
  - **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
  - **Zapiks**
  - **ZDF**

test/test_jsinterp.py

@@ -19,6 +19,9 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function x3(){return 42;}')
         self.assertEqual(jsi.call_function('x3'), 42)
 
+        jsi = JSInterpreter('var x5 = function(){return 42;}')
+        self.assertEqual(jsi.call_function('x5'), 42)
+
     def test_calc(self):
         jsi = JSInterpreter('function x4(a){return 2*a+1;}')
         self.assertEqual(jsi.call_function('x4', 3), 7)

test/test_subtitles.py

@@ -28,6 +28,7 @@ from youtube_dl.extractor import (
     ThePlatformFeedIE,
     RTVEALaCartaIE,
     FunnyOrDieIE,
+    DemocracynowIE,
 )
 
 
@@ -346,5 +347,25 @@ class TestFunnyOrDieSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
 
 
+class TestDemocracynowSubtitles(BaseTestSubtitles):
+    url = 'http://www.democracynow.org/shows/2015/7/3'
+    IE = DemocracynowIE
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+
+    def test_subtitles_in_page(self):
+        self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -210,8 +210,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unescapeHTML('%20;'), '%20;')
         self.assertEqual(unescapeHTML('/'), '/')
         self.assertEqual(unescapeHTML('/'), '/')
-        self.assertEqual(
-            unescapeHTML('é'), 'é')
+        self.assertEqual(unescapeHTML('é'), 'é')
+        self.assertEqual(unescapeHTML('�'), '�')
 
     def test_daterange(self):
         _20century = DateRange("19000101", "20000101")

youtube_dl/YoutubeDL.py

@@ -156,7 +156,7 @@ class YoutubeDL(object):
     writethumbnail:    Write the thumbnail image to a file
     write_all_thumbnails:  Write all thumbnail formats to files
     writesubtitles:    Write the video subtitles to a file
-    writeautomaticsub: Write the automatic subtitles to a file
+    writeautomaticsub: Write the automatically generated subtitles to a file
     allsubtitles:      Downloads all the subtitles of the video
                        (requires writesubtitles or writeautomaticsub)
     listsubtitles:     Lists all available subtitles for the video
@@ -572,7 +572,7 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            outtmpl = sanitize_path(self.params.get('outtmpl', DEFAULT_OUTTMPL))
+            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
             tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             # Temporary fix for #4787
@@ -580,7 +580,7 @@ class YoutubeDL(object):
             # to workaround encoding issues with subprocess on python2 @ Windows
             if sys.version_info < (3, 0) and sys.platform == 'win32':
                 filename = encodeFilename(filename, True).decode(preferredencoding())
-            return filename
+            return sanitize_path(filename)
         except ValueError as err:
             self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
@@ -833,6 +833,7 @@ class YoutubeDL(object):
                                                       extra_info=extra)
                 playlist_results.append(entry_result)
             ie_result['entries'] = playlist_results
+            self.to_screen('[download] Finished downloading playlist: %s' % playlist)
             return ie_result
         elif result_type == 'compat_list':
             self.report_warning(
@@ -937,7 +938,7 @@ class YoutubeDL(object):
                     filter_parts.append(string)
 
         def _remove_unused_ops(tokens):
-            # Remove operators that we don't use and join them with the sourrounding strings
+            # Remove operators that we don't use and join them with the surrounding strings
             # for example: 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
             ALLOWED_OPS = ('/', '+', ',', '(', ')')
             last_string, last_start, last_end, last_line = None, None, None, None

youtube_dl/__init__.py

@@ -377,7 +377,7 @@ def _real_main(argv=None):
     with YoutubeDL(ydl_opts) as ydl:
         # Update version
         if opts.update_self:
-            update_self(ydl.to_screen, opts.verbose)
+            update_self(ydl.to_screen, opts.verbose, ydl._opener)
 
         # Remove cache dir
         if opts.rm_cachedir:

youtube_dl/downloader/common.py

@@ -42,7 +42,7 @@ class FileDownloader(object):
     min_filesize:       Skip files smaller than this size
     max_filesize:       Skip files larger than this size
     xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
-                        (experimenatal)
+                        (experimental)
     external_downloader_args:  A list of additional command-line arguments for the
                         external downloader.
 

youtube_dl/downloader/rtmp.py

@@ -117,7 +117,7 @@ class RtmpFD(FileDownloader):
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when
-        # the connection was interrumpted and resuming appears to be
+        # the connection was interrupted and resuming appears to be
         # possible. This is part of rtmpdump's normal usage, AFAIK.
         basic_args = [
             'rtmpdump', '--verbose', '-r', url,

youtube_dl/extractor/__init__.py

@@ -60,7 +60,10 @@ from .bloomberg import BloombergIE
 from .bpb import BpbIE
 from .br import BRIE
 from .breakcom import BreakIE
-from .brightcove import BrightcoveIE
+from .brightcove import (
+    BrightcoveLegacyIE,
+    BrightcoveNewIE,
+)
 from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
@@ -124,10 +127,12 @@ from .dbtv import DBTVIE
 from .dcn import DCNIE
 from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
+from .democracynow import DemocracynowIE
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .dotsub import DotsubIE
 from .douyutv import DouyuTVIE
+from .dplay import DPlayIE
 from .dramafever import (
     DramaFeverIE,
     DramaFeverSeriesIE,
@@ -211,13 +216,15 @@ from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
 from .giga import GigaIE
 from .glide import GlideIE
-from .globo import GloboIE
+from .globo import (
+    GloboIE,
+    GloboArticleIE,
+)
 from .godtube import GodTubeIE
 from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
-from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
 from .groupon import GrouponIE
 from .hark import HarkIE
@@ -414,7 +421,10 @@ from .nowness import (
     NownessPlaylistIE,
     NownessSeriesIE,
 )
-from .nowtv import NowTVIE
+from .nowtv import (
+    NowTVIE,
+    NowTVListIE,
+)
 from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,
@@ -452,10 +462,7 @@ from .orf import (
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
-from .periscope import (
-    PeriscopeIE,
-    QuickscopeIE,
-)
+from .periscope import PeriscopeIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
@@ -569,7 +576,8 @@ from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
-    SoundcloudPlaylistIE
+    SoundcloudPlaylistIE,
+    SoundcloudSearchIE
 )
 from .soundgasm import (
     SoundgasmIE,
@@ -720,7 +728,6 @@ from .vh1 import VH1IE
 from .vice import ViceIE
 from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
-from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE
 from .videopremium import VideoPremiumIE
@@ -730,6 +737,7 @@ from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
 from .viewster import ViewsterIE
+from .viidea import ViideaIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -782,6 +790,7 @@ from .wrzuta import WrzutaIE
 from .wsj import WSJIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
+from .xfileshare import XFileShareIE
 from .xhamster import (
     XHamsterIE,
     XHamsterEmbedIE,
@@ -825,6 +834,7 @@ from .youtube import (
     YoutubeTruncatedIDIE,
     YoutubeTruncatedURLIE,
     YoutubeUserIE,
+    YoutubeUserPlaylistsIE,
     YoutubeWatchLaterIE,
 )
 from .zapiks import ZapiksIE

youtube_dl/extractor/aljazeera.py

@@ -15,7 +15,7 @@ class AlJazeeraIE(InfoExtractor):
             'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
             'uploader': 'Al Jazeera English',
         },
-        'add_ie': ['Brightcove'],
+        'add_ie': ['BrightcoveLegacy'],
         'skip': 'Not accessible from Travis CI server',
     }
 
@@ -32,5 +32,5 @@ class AlJazeeraIE(InfoExtractor):
                 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
                 '&%40videoPlayer={0}'.format(brightcove_id)
             ),
-            'ie_key': 'Brightcove',
+            'ie_key': 'BrightcoveLegacy',
         }

youtube_dl/extractor/bbc.py

@@ -27,7 +27,7 @@ class BBCCoUkIE(InfoExtractor):
     _MEDIASELECTOR_URLS = [
         # Provides HQ HLS streams with even better quality that pc mediaset but fails
         # with geolocation in some cases when it's even not geo restricted at all (e.g.
-        # http://www.bbc.co.uk/programmes/b06bp7lf)
+        # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
         'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
         'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
     ]
@@ -334,7 +334,7 @@ class BBCCoUkIE(InfoExtractor):
                 return self._download_media_selector_url(
                     mediaselector_url % programme_id, programme_id)
             except BBCCoUkIE.MediaSelectionError as e:
-                if e.id in ('notukerror', 'geolocation'):
+                if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
                     last_exception = e
                     continue
                 self._raise_extractor_error(e)
@@ -345,7 +345,7 @@ class BBCCoUkIE(InfoExtractor):
             media_selection = self._download_xml(
                 url, programme_id, 'Downloading media selection XML')
         except ExtractorError as ee:
-            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
                 media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
             else:
                 raise

youtube_dl/extractor/beeg.py

@@ -33,6 +33,8 @@ class BeegIE(InfoExtractor):
 
         formats = []
         for format_id, video_url in video.items():
+            if not video_url:
+                continue
             height = self._search_regex(
                 r'^(\d+)[pP]$', format_id, 'height', default=None)
             if not height:

youtube_dl/extractor/bloomberg.py

@@ -6,9 +6,9 @@ from .common import InfoExtractor
 
 
 class BloombergIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://www\.bloomberg\.com/news/[^/]+/[^/]+/(?P<id>[^/?#]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
         # The md5 checksum changes
         'info_dict': {
@@ -17,7 +17,10 @@ class BloombergIE(InfoExtractor):
             'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
             'description': 'md5:a8ba0302912d03d246979735c17d2761',
         },
-    }
+    }, {
+        'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         name = self._match_id(url)

youtube_dl/extractor/brightcove.py

@@ -20,12 +20,17 @@ from ..utils import (
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
+    float_or_none,
+    js_to_json,
+    int_or_none,
+    parse_iso8601,
     unescapeHTML,
     unsmuggle_url,
 )
 
 
-class BrightcoveIE(InfoExtractor):
+class BrightcoveLegacyIE(InfoExtractor):
+    IE_NAME = 'brightcove:legacy'
     _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
     _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
 
@@ -346,3 +351,172 @@ class BrightcoveIE(InfoExtractor):
         if 'url' not in info and not info.get('formats'):
             raise ExtractorError('Unable to extract video url for %s' % info['id'])
         return info
+
+
+class BrightcoveNewIE(InfoExtractor):
+    IE_NAME = 'brightcove:new'
+    _VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+)'
+    _TESTS = [{
+        'url': 'http://players.brightcove.net/929656772001/e41d32dc-ec74-459e-a845-6c69f7b724ea_default/index.html?videoId=4463358922001',
+        'md5': 'c8100925723840d4b0d243f7025703be',
+        'info_dict': {
+            'id': '4463358922001',
+            'ext': 'mp4',
+            'title': 'Meet the man behind Popcorn Time',
+            'description': 'md5:eac376a4fe366edc70279bfb681aea16',
+            'duration': 165.768,
+            'timestamp': 1441391203,
+            'upload_date': '20150904',
+            'uploader_id': '929656772001',
+            'formats': 'mincount:22',
+        },
+    }, {
+        # with rtmp streams
+        'url': 'http://players.brightcove.net/4036320279001/5d112ed9-283f-485f-a7f9-33f42e8bc042_default/index.html?videoId=4279049078001',
+        'info_dict': {
+            'id': '4279049078001',
+            'ext': 'mp4',
+            'title': 'Titansgrave: Chapter 0',
+            'description': 'Titansgrave: Chapter 0',
+            'duration': 1242.058,
+            'timestamp': 1433556729,
+            'upload_date': '20150606',
+            'uploader_id': '4036320279001',
+            'formats': 'mincount:41',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        # Reference:
+        # 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe
+        # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript)
+        # 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html
+
+        entries = []
+
+        # Look for iframe embeds [1]
+        for _, url in re.findall(
+                r'<iframe[^>]+src=(["\'])((?:https?:)//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
+            entries.append(url)
+
+        # Look for embed_in_page embeds [2]
+        for video_id, account_id, player_id, embed in re.findall(
+                # According to examples from [3] it's unclear whether video id
+                # may be optional and what to do when it is
+                r'''(?sx)
+                    <video[^>]+
+                        data-video-id=["\'](\d+)["\'][^>]*>.*?
+                    </video>.*?
+                    <script[^>]+
+                        src=["\'](?:https?:)?//players\.brightcove\.net/
+                        (\d+)/([\da-f-]+)_([^/]+)/index\.min\.js
+                ''', webpage):
+            entries.append(
+                'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
+                % (account_id, player_id, embed, video_id))
+
+        return entries
+
+    def _real_extract(self, url):
+        account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
+
+        webpage = self._download_webpage(
+            'http://players.brightcove.net/%s/%s_%s/index.min.js'
+            % (account_id, player_id, embed), video_id)
+
+        policy_key = None
+
+        catalog = self._search_regex(
+            r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
+        if catalog:
+            catalog = self._parse_json(
+                js_to_json(catalog), video_id, fatal=False)
+            if catalog:
+                policy_key = catalog.get('policyKey')
+
+        if not policy_key:
+            policy_key = self._search_regex(
+                r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
+                webpage, 'policy key', group='pk')
+
+        req = compat_urllib_request.Request(
+            'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s'
+            % (account_id, video_id),
+            headers={'Accept': 'application/json;pk=%s' % policy_key})
+        json_data = self._download_json(req, video_id)
+
+        title = json_data['name']
+
+        formats = []
+        for source in json_data.get('sources', []):
+            source_type = source.get('type')
+            src = source.get('src')
+            if source_type == 'application/x-mpegURL':
+                if not src:
+                    continue
+                m3u8_formats = self._extract_m3u8_formats(
+                    src, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+            else:
+                streaming_src = source.get('streaming_src')
+                stream_name, app_name = source.get('stream_name'), source.get('app_name')
+                if not src and not streaming_src and (not stream_name or not app_name):
+                    continue
+                tbr = float_or_none(source.get('avg_bitrate'), 1000)
+                height = int_or_none(source.get('height'))
+                f = {
+                    'tbr': tbr,
+                    'width': int_or_none(source.get('width')),
+                    'height': height,
+                    'filesize': int_or_none(source.get('size')),
+                    'container': source.get('container'),
+                    'vcodec': source.get('codec'),
+                    'ext': source.get('container').lower(),
+                }
+
+                def build_format_id(kind):
+                    format_id = kind
+                    if tbr:
+                        format_id += '-%dk' % int(tbr)
+                    if height:
+                        format_id += '-%dp' % height
+                    return format_id
+
+                if src or streaming_src:
+                    f.update({
+                        'url': src or streaming_src,
+                        'format_id': build_format_id('http' if src else 'http-streaming'),
+                        'preference': 2 if src else 1,
+                    })
+                else:
+                    f.update({
+                        'url': app_name,
+                        'play_path': stream_name,
+                        'format_id': build_format_id('rtmp'),
+                    })
+                formats.append(f)
+        self._sort_formats(formats)
+
+        description = json_data.get('description')
+        thumbnail = json_data.get('thumbnail')
+        timestamp = parse_iso8601(json_data.get('published_at'))
+        duration = float_or_none(json_data.get('duration'), 1000)
+        tags = json_data.get('tags', [])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader_id': account_id,
+            'formats': formats,
+            'tags': tags,
+        }

youtube_dl/extractor/cbs.py

@@ -1,6 +1,8 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_request
+from ..utils import smuggle_url
 
 
 class CBSIE(InfoExtractor):
@@ -46,13 +48,19 @@ class CBSIE(InfoExtractor):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        request = compat_urllib_request.Request(url)
+        # Android UA is served with higher quality (720p) streams (see
+        # https://github.com/rg3/youtube-dl/issues/7490)
+        request.add_header('User-Agent', 'Mozilla/5.0 (Linux; Android 4.4; Nexus 5)')
+        webpage = self._download_webpage(request, display_id)
         real_id = self._search_regex(
             [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
             webpage, 'real video ID')
         return {
             '_type': 'url_transparent',
             'ie_key': 'ThePlatform',
-            'url': 'theplatform:%s' % real_id,
+            'url': smuggle_url(
+                'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true&manifest=m3u' % real_id,
+                {'force_smil_url': True}),
             'display_id': display_id,
         }

youtube_dl/extractor/cbsnews.py

@@ -67,9 +67,12 @@ class CBSNewsIE(InfoExtractor):
                 'format_id': format_id,
             }
             if uri.startswith('rtmp'):
+                play_path = re.sub(
+                    r'{slistFilePath}', '',
+                    uri.split('<break>')[-1].split('{break}')[-1])
                 fmt.update({
                     'app': 'ondemand?auth=cbs',
-                    'play_path': 'mp4:' + uri.split('<break>')[-1],
+                    'play_path': 'mp4:' + play_path,
                     'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
                     'page_url': 'http://www.cbsnews.com',
                     'ext': 'flv',

youtube_dl/extractor/cmt.py

@@ -4,7 +4,7 @@ from .mtv import MTVIE
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://www\.cmt\.com/videos/.+?/(?P<videoid>[^/]+)\.jhtml'
+    _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
     _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
     _TESTS = [{
@@ -16,4 +16,7 @@ class CMTIE(MTVIE):
             'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
             'description': 'Blame It All On My Roots',
         },
+    }, {
+        'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
+        'only_matching': True,
     }]

youtube_dl/extractor/common.py

@@ -891,6 +891,11 @@ class InfoExtractor(object):
         if not media_nodes:
             manifest_version = '2.0'
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
+        base_url = xpath_text(
+            manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'],
+            'base URL', default=None)
+        if base_url:
+            base_url = base_url.strip()
         for i, media_el in enumerate(media_nodes):
             if manifest_version == '2.0':
                 media_url = media_el.attrib.get('href') or media_el.attrib.get('url')
@@ -898,7 +903,7 @@ class InfoExtractor(object):
                     continue
                 manifest_url = (
                     media_url if media_url.startswith('http://') or media_url.startswith('https://')
-                    else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url))
+                    else ((base_url or '/'.join(manifest_url.split('/')[:-1])) + '/' + media_url))
                 # If media_url is itself a f4m manifest do the recursive extraction
                 # since bitrates in parent manifest (this one) and media_url manifest
                 # may differ leading to inability to resolve the format by requested

youtube_dl/extractor/crunchyroll.py

@@ -21,6 +21,7 @@ from ..utils import (
     bytes_to_intlist,
     intlist_to_bytes,
     int_or_none,
+    lowercase_escape,
     remove_end,
     unified_strdate,
     urlencode_postdata,
@@ -104,7 +105,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             'id': '589804',
             'ext': 'flv',
             'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
-            'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
+            'description': 'md5:2fbc01f90b87e8e9137296f37b461c12',
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'Danny Choo Network',
             'upload_date': '20120213',
@@ -287,11 +288,15 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         if 'To view this, please log in to verify you are 18 or older.' in webpage:
             self.raise_login_required()
 
-        video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
+        video_title = self._html_search_regex(
+            r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>',
+            webpage, 'video_title')
         video_title = re.sub(r' {2,}', ' ', video_title)
-        video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
-        if not video_description:
-            video_description = None
+        video_description = self._html_search_regex(
+            r'<script[^>]*>\s*.+?\[media_id=%s\].+?"description"\s*:\s*"([^"]+)' % video_id,
+            webpage, 'description', default=None)
+        if video_description:
+            video_description = lowercase_escape(video_description.replace(r'\r\n', '\n'))
         video_upload_date = self._html_search_regex(
             [r'<div>Availability for free users:(.+?)</div>', r'<div>[^<>]+<span>\s*(.+?\d{4})\s*</span></div>'],
             webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)

youtube_dl/extractor/democracynow.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import os.path
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    url_basename,
+    remove_start,
+)
+
+
+class DemocracynowIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
+    IE_NAME = 'democracynow'
+    _TESTS = [{
+        'url': 'http://www.democracynow.org/shows/2015/7/3',
+        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
+        'info_dict': {
+            'id': '2015-0703-001',
+            'ext': 'mp4',
+            'title': 'July 03, 2015 - Democracy Now!',
+            'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
+        },
+    }, {
+        'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
+        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
+        'info_dict': {
+            'id': '2015-0703-001',
+            'ext': 'mp4',
+            'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
+            'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        description = self._og_search_description(webpage)
+
+        json_data = self._parse_json(self._search_regex(
+            r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
+            display_id)
+        video_id = None
+        formats = []
+
+        default_lang = 'en'
+
+        subtitles = {}
+
+        def add_subtitle_item(lang, info_dict):
+            if lang not in subtitles:
+                subtitles[lang] = []
+            subtitles[lang].append(info_dict)
+
+        # chapter_file are not subtitles
+        if 'caption_file' in json_data:
+            add_subtitle_item(default_lang, {
+                'url': compat_urlparse.urljoin(url, json_data['caption_file']),
+            })
+
+        for subtitle_item in json_data.get('captions', []):
+            lang = subtitle_item.get('language', '').lower() or default_lang
+            add_subtitle_item(lang, {
+                'url': compat_urlparse.urljoin(url, subtitle_item['url']),
+            })
+
+        for key in ('file', 'audio', 'video'):
+            media_url = json_data.get(key, '')
+            if not media_url:
+                continue
+            media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
+            video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
+            formats.append({
+                'url': media_url,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id or display_id,
+            'title': json_data['title'],
+            'description': description,
+            'subtitles': subtitles,
+            'formats': formats,
+        }

youtube_dl/extractor/dplay.py

@@ -0,0 +1,51 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import time
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class DPlayIE(InfoExtractor):
+    _VALID_URL = r'http://www\.dplay\.se/[^/]+/(?P<id>[^/?#]+)'
+
+    _TEST = {
+        'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
+        'info_dict': {
+            'id': '3172',
+            'ext': 'mp4',
+            'display_id': 'season-1-svensken-lar-sig-njuta-av-livet',
+            'title': 'Svensken lär sig njuta av livet',
+            'duration': 2650,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            r'data-video-id="(\d+)"', webpage, 'video id')
+
+        info = self._download_json(
+            'http://www.dplay.se/api/v2/ajax/videos?video_id=' + video_id,
+            video_id)['data'][0]
+
+        self._set_cookie(
+            'secure.dplay.se', 'dsc-geo',
+            '{"countryCode":"NL","expiry":%d}' % ((time.time() + 20 * 60) * 1000))
+        # TODO: consider adding support for 'stream_type=hds', it seems to
+        # require setting some cookies
+        manifest_url = self._download_json(
+            'https://secure.dplay.se/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % video_id,
+            video_id, 'Getting manifest url for hls stream')['hls']
+        formats = self._extract_m3u8_formats(
+            manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': info['title'],
+            'formats': formats,
+            'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
+        }

youtube_dl/extractor/dumpert.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import base64
+import re
 
 from .common import InfoExtractor
 from ..compat import compat_urllib_request
@@ -9,7 +10,7 @@ from ..utils import qualities
 
 
 class DumpertIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
+    _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
     _TESTS = [{
         'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
@@ -26,9 +27,11 @@ class DumpertIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        protocol = mobj.group('protocol')
 
-        url = 'https://www.dumpert.nl/mediabase/' + video_id
+        url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'nsfw=1; cpc=10')
         webpage = self._download_webpage(req, video_id)

youtube_dl/extractor/extremetube.py

@@ -3,23 +3,20 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_urllib_request,
-)
+from ..compat import compat_urllib_request
 from ..utils import (
-    qualities,
+    int_or_none,
     str_to_int,
 )
 
 
 class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
         'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
         'info_dict': {
-            'id': '652431',
+            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
@@ -29,12 +26,16 @@ class ExtremeTubeIE(InfoExtractor):
     }, {
         'url': 'http://www.extremetube.com/gay/video/abcde-1234',
         'only_matching': True,
+    }, {
+        'url': 'http://www.extremetube.com/video/latina-slut-fucked-by-fat-black-dick',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.extremetube.com/video/652431',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
@@ -49,20 +50,36 @@ class ExtremeTubeIE(InfoExtractor):
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 
-        flash_vars = compat_parse_qs(self._search_regex(
-            r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
+        flash_vars = self._parse_json(
+            self._search_regex(
+                r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
+            video_id)
 
         formats = []
-        quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
-        for k, vals in flash_vars.items():
-            m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
-            if m is not None:
-                formats.append({
-                    'format_id': m.group('quality'),
-                    'quality': quality(m.group('quality')),
-                    'url': vals[0],
+        for quality_key, video_url in flash_vars.items():
+            height = int_or_none(self._search_regex(
+                r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
+            if not height:
+                continue
+            f = {
+                'url': video_url,
+            }
+            mobj = re.search(
+                r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
+            if mobj:
+                height = int(mobj.group('height'))
+                bitrate = int(mobj.group('bitrate'))
+                f.update({
+                    'format_id': '%dp-%dk' % (height, bitrate),
+                    'height': height,
+                    'tbr': bitrate,
                 })
-
+            else:
+                f.update({
+                    'format_id': '%dp' % height,
+                    'height': height,
+                })
+            formats.append(f)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/funnyordie.py

@@ -45,11 +45,20 @@ class FunnyOrDieIE(InfoExtractor):
 
         links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
 
-        bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
-        bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
-        bitrates.sort()
+        m3u8_url = self._search_regex(
+            r'<source[^>]+src=(["\'])(?P<url>.+?/master\.m3u8)\1',
+            webpage, 'm3u8 url', default=None, group='url')
 
         formats = []
+
+        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)
+
+        bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)]
+        bitrates.sort()
+
         for bitrate in bitrates:
             for link in links:
                 formats.append({

youtube_dl/extractor/generic.py

@@ -30,7 +30,10 @@ from ..utils import (
     url_basename,
     xpath_text,
 )
-from .brightcove import BrightcoveIE
+from .brightcove import (
+    BrightcoveLegacyIE,
+    BrightcoveNewIE,
+)
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
@@ -275,7 +278,7 @@ class GenericIE(InfoExtractor):
         # it also tests brightcove videos that need to set the 'Referer' in the
         # http requests
         {
-            'add_ie': ['Brightcove'],
+            'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
             'info_dict': {
                 'id': '2765128793001',
@@ -299,7 +302,7 @@ class GenericIE(InfoExtractor):
                 'uploader': 'thestar.com',
                 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
             },
-            'add_ie': ['Brightcove'],
+            'add_ie': ['BrightcoveLegacy'],
         },
         {
             'url': 'http://www.championat.com/video/football/v/87/87499.html',
@@ -314,7 +317,7 @@ class GenericIE(InfoExtractor):
         },
         {
             # https://github.com/rg3/youtube-dl/issues/3541
-            'add_ie': ['Brightcove'],
+            'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
             'info_dict': {
                 'id': '3866516442001',
@@ -820,6 +823,19 @@ class GenericIE(InfoExtractor):
                 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
             },
         },
+        # Kaltura embed protected with referrer
+        {
+            'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
+            'info_dict': {
+                'id': '1_g4fbemnq',
+                'ext': 'mp4',
+                'title': 'Violetta - Achter De Schermen - Ruggero',
+                'description': 'Achter de schermen met Ruggero',
+                'timestamp': 1435133761,
+                'upload_date': '20150624',
+                'uploader_id': 'echojecka',
+            },
+        },
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@@ -1031,6 +1047,31 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'cinemasnob',
             },
+        },
+        # BrightcoveInPageEmbed embed
+        {
+            'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
+            'info_dict': {
+                'id': '4238694884001',
+                'ext': 'flv',
+                'title': 'Tabletop: Dread, Last Thoughts',
+                'description': 'Tabletop: Dread, Last Thoughts',
+                'duration': 51690,
+            },
+        },
+        # JWPlayer with M3U8
+        {
+            'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
+            'info_dict': {
+                'id': 'playlist',
+                'ext': 'mp4',
+                'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
+                'uploader': 'ren.tv',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            }
         }
     ]
 
@@ -1290,14 +1331,14 @@ class GenericIE(InfoExtractor):
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
 
-        # Look for BrightCove:
-        bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
+        # Look for Brightcove Legacy Studio embeds
+        bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
         if bc_urls:
             self.to_screen('Brightcove video detected.')
             entries = [{
                 '_type': 'url',
                 'url': smuggle_url(bc_url, {'Referer': url}),
-                'ie_key': 'Brightcove'
+                'ie_key': 'BrightcoveLegacy'
             } for bc_url in bc_urls]
 
             return {
@@ -1307,6 +1348,11 @@ class GenericIE(InfoExtractor):
                 'entries': entries,
             }
 
+        # Look for Brightcove New Studio embeds
+        bc_urls = BrightcoveNewIE._extract_urls(webpage)
+        if bc_urls:
+            return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
+
         # Look for embedded rtl.nl player
         matches = re.findall(
             r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
@@ -1672,10 +1718,12 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'Zapiks')
 
         # Look for Kaltura embeds
-        mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
-                re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
+        mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
+                re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
         if mobj is not None:
-            return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
+            return self.url_result(smuggle_url(
+                'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
+                {'source_url': url}), 'Kaltura')
 
         # Look for Eagle.Platform embeds
         mobj = re.search(
@@ -1720,7 +1768,7 @@ class GenericIE(InfoExtractor):
 
         # Look for UDN embeds
         mobj = re.search(
-            r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
+            r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
         if mobj is not None:
             return self.url_result(
                 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
@@ -1840,6 +1888,7 @@ class GenericIE(InfoExtractor):
 
         entries = []
         for video_url in found:
+            video_url = video_url.replace('\\/', '/')
             video_url = compat_urlparse.urljoin(url, video_url)
             video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
 
@@ -1851,25 +1900,24 @@ class GenericIE(InfoExtractor):
             # here's a fun little line of code for you:
             video_id = os.path.splitext(video_id)[0]
 
+            entry_info_dict = {
+                'id': video_id,
+                'uploader': video_uploader,
+                'title': video_title,
+                'age_limit': age_limit,
+            }
+
             ext = determine_ext(video_url)
             if ext == 'smil':
-                entries.append({
-                    'id': video_id,
-                    'formats': self._extract_smil_formats(video_url, video_id),
-                    'uploader': video_uploader,
-                    'title': video_title,
-                    'age_limit': age_limit,
-                })
+                entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
             elif ext == 'xspf':
                 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
+            elif ext == 'm3u8':
+                entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
             else:
-                entries.append({
-                    'id': video_id,
-                    'url': video_url,
-                    'uploader': video_uploader,
-                    'title': video_title,
-                    'age_limit': age_limit,
-                })
+                entry_info_dict['url'] = video_url
+
+            entries.append(entry_info_dict)
 
         if len(entries) == 1:
             return entries[0]

youtube_dl/extractor/globo.py

@@ -14,79 +14,58 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    str_or_none,
 )
 
 
 class GloboIE(InfoExtractor):
-    _VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)'
+    _VALID_URL = '(?: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'
 
-    _VIDEOID_REGEXES = [
-        r'\bdata-video-id="(\d+)"',
-        r'\bdata-player-videosids="(\d+)"',
-        r'<div[^>]+\bid="(\d+)"',
-    ]
-
     _RESIGN_EXPIRATION = 86400
 
-    _TESTS = [
-        {
-            'url': 'http://globotv.globo.com/sportv/futebol-nacional/v/os-gols-de-atletico-mg-3-x-2-santos-pela-24a-rodada-do-brasileirao/3654973/',
-            'md5': '03ebf41cb7ade43581608b7d9b71fab0',
-            'info_dict': {
-                'id': '3654973',
-                'ext': 'mp4',
-                'title': 'Os gols de Atlético-MG 3 x 2 Santos pela 24ª rodada do Brasileirão',
-                'duration': 251.585,
-                'uploader': 'SporTV',
-                'uploader_id': 698,
-                'like_count': int,
-            }
+    _TESTS = [{
+        'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/',
+        'md5': 'b3ccc801f75cd04a914d51dadb83a78d',
+        'info_dict': {
+            'id': '3607726',
+            'ext': 'mp4',
+            'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa',
+            'duration': 103.204,
+            'uploader': 'Globo.com',
+            'uploader_id': '265',
         },
-        {
-            'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/',
-            'md5': 'b3ccc801f75cd04a914d51dadb83a78d',
-            'info_dict': {
-                'id': '3607726',
-                'ext': 'mp4',
-                'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa',
-                'duration': 103.204,
-                'uploader': 'Globo.com',
-                'uploader_id': 265,
-                'like_count': int,
-            }
+    }, {
+        'url': 'http://globoplay.globo.com/v/4581987/',
+        'md5': 'f36a1ecd6a50da1577eee6dd17f67eff',
+        'info_dict': {
+            'id': '4581987',
+            'ext': 'mp4',
+            'title': 'Acidentes de trânsito estão entre as maiores causas de queda de energia em SP',
+            'duration': 137.973,
+            'uploader': 'Rede Globo',
+            'uploader_id': '196',
         },
-        {
-            'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
-            'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
-            'info_dict': {
-                'id': '3652183',
-                'ext': 'mp4',
-                'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
-                'duration': 110.711,
-                'uploader': 'Rede Globo',
-                'uploader_id': 196,
-                'like_count': int,
-            }
-        },
-        {
-            'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
-            'md5': 'c1defca721ce25b2354e927d3e4b3dec',
-            'info_dict': {
-                'id': '3928201',
-                'ext': 'mp4',
-                'title': 'Ator e diretor argentino, Ricado Darín fala sobre utopias e suas perdas',
-                'duration': 1472.906,
-                'uploader': 'Canal Brasil',
-                'uploader_id': 705,
-                'like_count': int,
-            }
-        },
-    ]
+    }, {
+        'url': 'http://canalbrasil.globo.com/programas/sangue-latino/videos/3928201.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://globosatplay.globo.com/globonews/v/4472924/',
+        'only_matching': True,
+    }, {
+        'url': 'http://globotv.globo.com/t/programa/v/clipe-sexo-e-as-negas-adeus/3836166/',
+        'only_matching': True,
+    }, {
+        'url': 'http://globotv.globo.com/canal-brasil/sangue-latino/t/todos-os-videos/v/ator-e-diretor-argentino-ricado-darin-fala-sobre-utopias-e-suas-perdas/3928201/',
+        'only_matching': True,
+    }, {
+        'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html',
+        'only_matching': True,
+    }]
 
-    class MD5():
+    class MD5:
         HEX_FORMAT_LOWERCASE = 0
         HEX_FORMAT_UPPERCASE = 1
         BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = ''
@@ -353,9 +332,6 @@ class GloboIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
-        video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
-
         video = self._download_json(
             self._API_URL_TEMPLATE % video_id, video_id)['videos'][0]
 
@@ -364,7 +340,7 @@ class GloboIE(InfoExtractor):
         formats = []
         for resource in video['resources']:
             resource_id = resource.get('_id')
-            if not resource_id:
+            if not resource_id or resource_id.endswith('manifest'):
                 continue
 
             security = self._download_json(
@@ -393,20 +369,23 @@ class GloboIE(InfoExtractor):
             resource_url = resource['url']
             signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
             if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(signed_url, resource_id, 'mp4'))
+                m3u8_formats = self._extract_m3u8_formats(
+                    signed_url, resource_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
             else:
                 formats.append({
                     'url': signed_url,
-                    'format_id': resource_id,
-                    'height': resource.get('height'),
+                    'format_id': 'http-%s' % resource_id,
+                    'height': int_or_none(resource.get('height')),
                 })
 
         self._sort_formats(formats)
 
         duration = float_or_none(video.get('duration'), 1000)
-        like_count = int_or_none(video.get('likes'))
         uploader = video.get('channel')
-        uploader_id = video.get('channel_id')
+        uploader_id = str_or_none(video.get('channel_id'))
 
         return {
             'id': video_id,
@@ -414,6 +393,46 @@ class GloboIE(InfoExtractor):
             'duration': duration,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'like_count': like_count,
             'formats': formats
         }
+
+
+class GloboArticleIE(InfoExtractor):
+    _VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)\.html'
+
+    _VIDEOID_REGEXES = [
+        r'\bdata-video-id=["\'](\d{7,})',
+        r'\bdata-player-videosids=["\'](\d{7,})',
+        r'\bvideosIDs\s*:\s*["\'](\d{7,})',
+        r'\bdata-id=["\'](\d{7,})',
+        r'<div[^>]+\bid=["\'](\d{7,})',
+    ]
+
+    _TESTS = [{
+        'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
+        'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
+        'info_dict': {
+            'id': '3652183',
+            'ext': 'mp4',
+            'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
+            'duration': 110.711,
+            'uploader': 'Rede Globo',
+            'uploader_id': '196',
+        }
+    }, {
+        'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://gshow.globo.com/programas/tv-xuxa/O-Programa/noticia/2014/01/xuxa-e-junno-namoram-muuuito-em-luau-de-zeze-di-camargo-e-luciano.html',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if GloboIE.suitable(url) else super(GloboArticleIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
+        return self.url_result('globo:%s' % video_id, 'Globo')

youtube_dl/extractor/googleplus.py

@@ -61,7 +61,7 @@ class GooglePlusIE(InfoExtractor):
             'width': int(width),
             'height': int(height),
         } for width, height, video_url in re.findall(
-            r'\d+,(\d+),(\d+),"(https?://redirector\.googlevideo\.com.*?)"', webpage)]
+            r'\d+,(\d+),(\d+),"(https?://[^.]+\.googleusercontent.com.*?)"', webpage)]
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/instagram.py

@@ -10,8 +10,8 @@ from ..utils import (
 
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+)'
+    _TESTS = [{
         'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
         'md5': '0d2da106a9d2631273e192b372806516',
         'info_dict': {
@@ -21,7 +21,10 @@ class InstagramIE(InfoExtractor):
             'title': 'Video by naomipq',
             'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
         }
-    }
+    }, {
+        'url': 'https://instagram.com/p/-Cmh1cukG2/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/kaltura.py

@@ -2,12 +2,18 @@
 from __future__ import unicode_literals
 
 import re
+import base64
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse
+from ..compat import (
+    compat_urllib_parse,
+    compat_urlparse,
+)
 from ..utils import (
+    clean_html,
     ExtractorError,
     int_or_none,
+    unsmuggle_url,
 )
 
 
@@ -16,7 +22,7 @@ class KalturaIE(InfoExtractor):
                 (?:
                     kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)|
                     https?://
-                        (:?(?:www|cdnapisec)\.)?kaltura\.com/
+                        (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/
                         (?:
                             (?:
                                 # flash player
@@ -121,31 +127,47 @@ class KalturaIE(InfoExtractor):
             video_id, actions, note='Downloading video info JSON')
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+
         mobj = re.match(self._VALID_URL, url)
         partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5')
         entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5')
 
         info, source_data = self._get_video_info(entry_id, partner_id)
 
-        formats = [{
-            'format_id': '%(fileExt)s-%(bitrate)s' % f,
-            'ext': f['fileExt'],
-            'tbr': f['bitrate'],
-            'fps': f.get('frameRate'),
-            'filesize_approx': int_or_none(f.get('size'), invscale=1024),
-            'container': f.get('containerFormat'),
-            'vcodec': f.get('videoCodecId'),
-            'height': f.get('height'),
-            'width': f.get('width'),
-            'url': '%s/flavorId/%s' % (info['dataUrl'], f['id']),
-        } for f in source_data['flavorAssets']]
+        source_url = smuggled_data.get('source_url')
+        if source_url:
+            referrer = base64.b64encode(
+                '://'.join(compat_urlparse.urlparse(source_url)[:2])
+                .encode('utf-8')).decode('utf-8')
+        else:
+            referrer = None
+
+        formats = []
+        for f in source_data['flavorAssets']:
+            video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id'])
+            if referrer:
+                video_url += '?referrer=%s' % referrer
+            formats.append({
+                'format_id': '%(fileExt)s-%(bitrate)s' % f,
+                'ext': f.get('fileExt'),
+                'tbr': int_or_none(f['bitrate']),
+                'fps': int_or_none(f.get('frameRate')),
+                'filesize_approx': int_or_none(f.get('size'), invscale=1024),
+                'container': f.get('containerFormat'),
+                'vcodec': f.get('videoCodecId'),
+                'height': int_or_none(f.get('height')),
+                'width': int_or_none(f.get('width')),
+                'url': video_url,
+            })
+        self._check_formats(formats, entry_id)
         self._sort_formats(formats)
 
         return {
             'id': entry_id,
             'title': info['name'],
             'formats': formats,
-            'description': info.get('description'),
+            'description': clean_html(info.get('description')),
             'thumbnail': info.get('thumbnailUrl'),
             'duration': info.get('duration'),
             'timestamp': info.get('createdAt'),

youtube_dl/extractor/lynda.py

@@ -25,7 +25,7 @@ class LyndaBaseIE(InfoExtractor):
         self._login()
 
     def _login(self):
-        (username, password) = self._get_login_info()
+        username, password = self._get_login_info()
         if username is None:
             return
 
@@ -82,6 +82,15 @@ class LyndaBaseIE(InfoExtractor):
                         expected=True)
             raise ExtractorError('Unable to log in')
 
+    def _logout(self):
+        username, _ = self._get_login_info()
+        if username is None:
+            return
+
+        self._download_webpage(
+            'http://www.lynda.com/ajax/logout.aspx', None,
+            'Logging out', 'Unable to log out', fatal=False)
+
 
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
@@ -108,51 +117,47 @@ class LyndaIE(LyndaBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        page = self._download_webpage(
+        video = self._download_json(
             'http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
             video_id, 'Downloading video JSON')
-        video_json = json.loads(page)
 
-        if 'Status' in video_json:
+        if 'Status' in video:
             raise ExtractorError(
-                'lynda returned error: %s' % video_json['Message'], expected=True)
+                'lynda returned error: %s' % video['Message'], expected=True)
 
-        if video_json['HasAccess'] is False:
+        if video.get('HasAccess') is False:
             self.raise_login_required('Video %s is only available for members' % video_id)
 
-        video_id = compat_str(video_json['ID'])
-        duration = video_json['DurationInSeconds']
-        title = video_json['Title']
+        video_id = compat_str(video.get('ID') or video_id)
+        duration = int_or_none(video.get('DurationInSeconds'))
+        title = video['Title']
 
         formats = []
 
-        fmts = video_json.get('Formats')
+        fmts = video.get('Formats')
         if fmts:
-            formats.extend([
-                {
-                    'url': fmt['Url'],
-                    'ext': fmt['Extension'],
-                    'width': fmt['Width'],
-                    'height': fmt['Height'],
-                    'filesize': fmt['FileSize'],
-                    'format_id': str(fmt['Resolution'])
-                } for fmt in fmts])
+            formats.extend([{
+                'url': f['Url'],
+                'ext': f.get('Extension'),
+                'width': int_or_none(f.get('Width')),
+                'height': int_or_none(f.get('Height')),
+                'filesize': int_or_none(f.get('FileSize')),
+                'format_id': compat_str(f.get('Resolution')) if f.get('Resolution') else None,
+            } for f in fmts if f.get('Url')])
 
-        prioritized_streams = video_json.get('PrioritizedStreams')
+        prioritized_streams = video.get('PrioritizedStreams')
         if prioritized_streams:
             for prioritized_stream_id, prioritized_stream in prioritized_streams.items():
-                formats.extend([
-                    {
-                        'url': video_url,
-                        'width': int_or_none(format_id),
-                        'format_id': '%s-%s' % (prioritized_stream_id, format_id),
-                    } for format_id, video_url in prioritized_stream.items()
-                ])
+                formats.extend([{
+                    'url': video_url,
+                    'width': int_or_none(format_id),
+                    'format_id': '%s-%s' % (prioritized_stream_id, format_id),
+                } for format_id, video_url in prioritized_stream.items()])
 
         self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
-        subtitles = self.extract_subtitles(video_id, page)
+        subtitles = self.extract_subtitles(video_id)
 
         return {
             'id': video_id,
@@ -183,7 +188,7 @@ class LyndaIE(LyndaBaseIE):
         if srt:
             return srt
 
-    def _get_subtitles(self, video_id, webpage):
+    def _get_subtitles(self, video_id):
         url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
         subs = self._download_json(url, None, False)
         if subs:
@@ -205,12 +210,13 @@ class LyndaCourseIE(LyndaBaseIE):
         course_path = mobj.group('coursepath')
         course_id = mobj.group('courseid')
 
-        page = self._download_webpage(
+        course = self._download_json(
             'http://www.lynda.com/ajax/player?courseId=%s&type=course' % course_id,
             course_id, 'Downloading course JSON')
-        course_json = json.loads(page)
 
-        if 'Status' in course_json and course_json['Status'] == 'NotFound':
+        self._logout()
+
+        if course.get('Status') == 'NotFound':
             raise ExtractorError(
                 'Course %s does not exist' % course_id, expected=True)
 
@@ -220,12 +226,13 @@ class LyndaCourseIE(LyndaBaseIE):
         # Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
         # by single video API anymore
 
-        for chapter in course_json['Chapters']:
-            for video in chapter['Videos']:
-                if video['HasAccess'] is False:
+        for chapter in course['Chapters']:
+            for video in chapter.get('Videos', []):
+                if video.get('HasAccess') is False:
                     unaccessible_videos += 1
                     continue
-                videos.append(video['ID'])
+                if video.get('ID'):
+                    videos.append(video['ID'])
 
         if unaccessible_videos > 0:
             self._downloader.report_warning(
@@ -238,6 +245,6 @@ class LyndaCourseIE(LyndaBaseIE):
                 'Lynda')
             for video_id in videos]
 
-        course_title = course_json['Title']
+        course_title = course.get('Title')
 
         return self.playlist_result(entries, course_id, course_title)

youtube_dl/extractor/miomio.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import random
 
 from .common import InfoExtractor
+from ..compat import compat_urllib_request
 from ..utils import (
     xpath_text,
     int_or_none,
@@ -51,6 +52,8 @@ class MioMioIE(InfoExtractor):
         mioplayer_path = self._search_regex(
             r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
 
+        http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
+
         xml_config = self._search_regex(
             r'flashvars="type=(?:sina|video)&(.+?)&',
             webpage, 'xml config')
@@ -60,14 +63,12 @@ class MioMioIE(InfoExtractor):
             'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
             video_id)
 
-        # the following xml contains the actual configuration information on the video file(s)
-        vid_config = self._download_xml(
+        vid_config_request = compat_urllib_request.Request(
             'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
-            video_id)
+            headers=http_headers)
 
-        http_headers = {
-            'Referer': 'http://www.miomio.tv%s' % mioplayer_path,
-        }
+        # the following xml contains the actual configuration information on the video file(s)
+        vid_config = self._download_xml(vid_config_request, video_id)
 
         if not int_or_none(xpath_text(vid_config, 'timelength')):
             raise ExtractorError('Unable to load videos!', expected=True)

youtube_dl/extractor/mit.py

@@ -86,7 +86,7 @@ class MITIE(TechTVMITIE):
         webpage = self._download_webpage(url, page_title)
         embed_url = self._search_regex(
             r'<iframe .*?src="(.+?)"', webpage, 'embed url')
-        return self.url_result(embed_url, ie='TechTVMIT')
+        return self.url_result(embed_url)
 
 
 class OCWMITIE(InfoExtractor):

youtube_dl/extractor/movieclips.py

@@ -1,80 +1,42 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..compat import (
-    compat_str,
-)
-from ..utils import (
-    ExtractorError,
-    clean_html,
+    compat_urllib_request,
 )
 
 
 class MovieClipsIE(InfoExtractor):
-    _VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?'
+    _VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/(?P<id>[^/?#]+)'
     _TEST = {
-        'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/',
+        'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597?autoPlay=true&playlistId=5',
         'info_dict': {
-            'id': 'Wy7ZU',
-            'display_id': 'my-week-with-marilyn-movie-do-you-love-me',
+            'id': 'pKIGmG83AqD9',
+            'display_id': 'warcraft-trailer-1-561180739597',
             'ext': 'mp4',
-            'title': 'My Week with Marilyn - Do You Love Me?',
-            'description': 'md5:e86795bd332fe3cff461e7c8dc542acb',
+            'title': 'Warcraft Trailer 1',
+            'description': 'Watch Trailer 1 from Warcraft (2016). Legendary’s WARCRAFT is a 3D epic adventure of world-colliding conflict based.',
             'thumbnail': 're:^https?://.*\.jpg$',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        }
+        'add_ie': ['ThePlatform'],
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
-        show_id = display_id or video_id
+        display_id = self._match_id(url)
 
-        config = self._download_xml(
-            'http://config.movieclips.com/player/config/%s' % video_id,
-            show_id, 'Downloading player config')
-
-        if config.find('./country-region').text == 'false':
-            raise ExtractorError(
-                '%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True)
-
-        properties = config.find('./video/properties')
-        smil_file = properties.attrib['smil_file']
-
-        smil = self._download_xml(smil_file, show_id, 'Downloading SMIL')
-        base_url = smil.find('./head/meta').attrib['base']
-
-        formats = []
-        for video in smil.findall('./body/switch/video'):
-            vbr = int(video.attrib['system-bitrate']) / 1000
-            src = video.attrib['src']
-            formats.append({
-                'url': base_url,
-                'play_path': src,
-                'ext': src.split(':')[0],
-                'vbr': vbr,
-                'format_id': '%dk' % vbr,
-            })
-
-        self._sort_formats(formats)
-
-        title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title'])
-        description = clean_html(compat_str(properties.attrib['clip_description']))
-        thumbnail = properties.attrib['image']
-        categories = properties.attrib['clip_categories'].split(',')
+        req = compat_urllib_request.Request(url)
+        # it doesn't work if it thinks the browser it's too old
+        req.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/43.0 (Chrome)')
+        webpage = self._download_webpage(req, display_id)
+        theplatform_link = self._html_search_regex(r'src="(http://player.theplatform.com/p/.*?)"', webpage, 'theplatform link')
+        title = self._html_search_regex(r'<title[^>]*>([^>]+)-\s*\d+\s*|\s*Movieclips.com</title>', webpage, 'title')
+        description = self._html_search_meta('description', webpage)
 
         return {
-            'id': video_id,
-            'display_id': display_id,
+            '_type': 'url_transparent',
+            'url': theplatform_link,
             'title': title,
+            'display_id': display_id,
             'description': description,
-            'thumbnail': thumbnail,
-            'categories': categories,
-            'formats': formats,
         }

youtube_dl/extractor/ndr.py

@@ -23,7 +23,7 @@ class NDRBaseIE(InfoExtractor):
 class NDRIE(NDRBaseIE):
     IE_NAME = 'ndr'
     IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
-    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
+    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
     _TESTS = [{
         # httpVideo, same content id
         'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
@@ -78,6 +78,9 @@ class NDRIE(NDRBaseIE):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.ndr.de/Fettes-Brot-Ferris-MC-und-Thees-Uhlmann-live-on-stage,festivalsommer116.html',
+        'only_matching': True,
     }]
 
     def _extract_embed(self, webpage, display_id):
@@ -102,7 +105,7 @@ class NDRIE(NDRBaseIE):
 class NJoyIE(NDRBaseIE):
     IE_NAME = 'njoy'
     IE_DESC = 'N-JOY'
-    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
+    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
     _TESTS = [{
         # httpVideo, same content id
         'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
@@ -235,7 +238,7 @@ class NDREmbedBaseIE(InfoExtractor):
 
 class NDREmbedIE(NDREmbedBaseIE):
     IE_NAME = 'ndr:embed'
-    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
+    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
     _TESTS = [{
         'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
         'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
@@ -329,7 +332,7 @@ class NDREmbedIE(NDREmbedBaseIE):
 
 class NJoyEmbedIE(NDREmbedBaseIE):
     IE_NAME = 'njoy:embed'
-    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
+    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
     _TESTS = [{
         # httpVideo
         'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',

youtube_dl/extractor/neteasemusic.py

@@ -40,7 +40,7 @@ class NetEaseMusicBaseIE(InfoExtractor):
             if not details:
                 continue
             formats.append({
-                'url': 'http://m1.music.126.net/%s/%s.%s' %
+                'url': 'http://m5.music.126.net/%s/%s.%s' %
                        (cls._encrypt(details['dfsId']), details['dfsId'],
                         details['extension']),
                 'ext': details.get('extension'),

youtube_dl/extractor/novamov.py

@@ -4,10 +4,14 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_urllib_request,
     compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
+    NO_DEFAULT,
+    encode_dict,
+    urlencode_postdata,
 )
 
 
@@ -38,19 +42,40 @@ class NovaMovIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
-        page = self._download_webpage(
-            'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
+        url = 'http://%s/video/%s' % (self._HOST, video_id)
 
-        if re.search(self._FILE_DELETED_REGEX, page) is not None:
+        webpage = self._download_webpage(
+            url, video_id, 'Downloading video page')
+
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
-        filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
+        def extract_filekey(default=NO_DEFAULT):
+            return self._search_regex(
+                self._FILEKEY_REGEX, webpage, 'filekey', default=default)
 
-        title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
-        description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
+        filekey = extract_filekey(default=None)
+
+        if not filekey:
+            fields = self._hidden_inputs(webpage)
+            post_url = self._search_regex(
+                r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
+                'post url', default=url, group='url')
+            if not post_url.startswith('http'):
+                post_url = compat_urlparse.urljoin(url, post_url)
+            request = compat_urllib_request.Request(
+                post_url, urlencode_postdata(encode_dict(fields)))
+            request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+            request.add_header('Referer', post_url)
+            webpage = self._download_webpage(
+                request, video_id, 'Downloading continue to the video page')
+
+        filekey = extract_filekey()
+
+        title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
+        description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
 
         api_response = self._download_webpage(
             'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,

youtube_dl/extractor/nowness.py

@@ -1,7 +1,7 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-from .brightcove import BrightcoveIE
+from .brightcove import BrightcoveLegacyIE
 from .common import InfoExtractor
 from ..utils import ExtractorError
 from ..compat import (
@@ -22,10 +22,10 @@ class NownessBaseIE(InfoExtractor):
                             'http://www.nowness.com/iframe?id=%s' % video_id, video_id,
                             note='Downloading player JavaScript',
                             errnote='Unable to download player JavaScript')
-                        bc_url = BrightcoveIE._extract_brightcove_url(player_code)
+                        bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code)
                         if bc_url is None:
                             raise ExtractorError('Could not find player definition')
-                        return self.url_result(bc_url, 'Brightcove')
+                        return self.url_result(bc_url, 'BrightcoveLegacy')
                     elif source == 'vimeo':
                         return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
                     elif source == 'youtube':

youtube_dl/extractor/nowtv.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
@@ -13,8 +15,63 @@ from ..utils import (
 )
 
 
-class NowTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<id>.+?)/(?:player|preview)'
+class NowTVBaseIE(InfoExtractor):
+    _VIDEO_FIELDS = (
+        'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort',
+        'broadcastStartDate', 'seoUrl', 'duration', 'files',
+        'format.defaultImage169Format', 'format.defaultImage169Logo')
+
+    def _extract_video(self, info, display_id=None):
+        video_id = compat_str(info['id'])
+
+        files = info['files']
+        if not files:
+            if info.get('geoblocked', False):
+                raise ExtractorError(
+                    'Video %s is not available from your location due to geo restriction' % video_id,
+                    expected=True)
+            if not info.get('free', True):
+                raise ExtractorError(
+                    'Video %s is not available for free' % video_id, expected=True)
+
+        formats = []
+        for item in files['items']:
+            if determine_ext(item['path']) != 'f4v':
+                continue
+            app, play_path = remove_start(item['path'], '/').split('/', 1)
+            formats.append({
+                'url': 'rtmpe://fms.rtl.de',
+                'app': app,
+                'play_path': 'mp4:%s' % play_path,
+                'ext': 'flv',
+                'page_url': 'http://rtlnow.rtl.de',
+                'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf',
+                'tbr': int_or_none(item.get('bitrate')),
+            })
+        self._sort_formats(formats)
+
+        title = info['title']
+        description = info.get('articleLong') or info.get('articleShort')
+        timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ')
+        duration = parse_duration(info.get('duration'))
+
+        f = info.get('format', {})
+        thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo')
+
+        return {
+            'id': video_id,
+            'display_id': display_id or info.get('seoUrl'),
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class NowTVIE(NowTVBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:list/[^/]+/)?(?P<id>[^/]+)/(?:player|preview)'
 
     _TESTS = [{
         # rtl
@@ -23,7 +80,7 @@ class NowTVIE(InfoExtractor):
             'id': '203519',
             'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
             'ext': 'flv',
-            'title': 'Die neuen Bauern und eine Hochzeit',
+            'title': 'Inka Bause stellt die neuen Bauern vor',
             'description': 'md5:e234e1ed6d63cf06be5c070442612e7e',
             'thumbnail': 're:^https?://.*\.jpg$',
             'timestamp': 1432580700,
@@ -136,58 +193,65 @@ class NowTVIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-        display_id_split = display_id.split('/')
-        if len(display_id) > 2:
-            display_id = '/'.join((display_id_split[0], display_id_split[-1]))
+        mobj = re.match(self._VALID_URL, url)
+        display_id = '%s/%s' % (mobj.group('show_id'), mobj.group('id'))
 
         info = self._download_json(
-            'https://api.nowtv.de/v3/movies/%s?fields=id,title,free,geoblocked,articleLong,articleShort,broadcastStartDate,seoUrl,duration,format,files' % display_id,
-            display_id)
+            'https://api.nowtv.de/v3/movies/%s?fields=%s'
+            % (display_id, ','.join(self._VIDEO_FIELDS)), display_id)
 
-        video_id = compat_str(info['id'])
+        return self._extract_video(info, display_id)
 
-        files = info['files']
-        if not files:
-            if info.get('geoblocked', False):
-                raise ExtractorError(
-                    'Video %s is not available from your location due to geo restriction' % video_id,
-                    expected=True)
-            if not info.get('free', True):
-                raise ExtractorError(
-                    'Video %s is not available for free' % video_id, expected=True)
 
-        formats = []
-        for item in files['items']:
-            if determine_ext(item['path']) != 'f4v':
-                continue
-            app, play_path = remove_start(item['path'], '/').split('/', 1)
-            formats.append({
-                'url': 'rtmpe://fms.rtl.de',
-                'app': app,
-                'play_path': 'mp4:%s' % play_path,
-                'ext': 'flv',
-                'page_url': 'http://rtlnow.rtl.de',
-                'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf',
-                'tbr': int_or_none(item.get('bitrate')),
-            })
-        self._sort_formats(formats)
+class NowTVListIE(NowTVBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/list/(?P<id>[^?/#&]+)$'
 
-        title = info['title']
-        description = info.get('articleLong') or info.get('articleShort')
-        timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ')
-        duration = parse_duration(info.get('duration'))
+    _SHOW_FIELDS = ('title', )
+    _SEASON_FIELDS = ('id', 'headline', 'seoheadline', )
 
-        f = info.get('format', {})
-        thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo')
+    _TESTS = [{
+        'url': 'http://www.nowtv.at/rtl/stern-tv/list/aktuell',
+        'info_dict': {
+            'id': '17006',
+            'title': 'stern TV - Aktuell',
+        },
+        'playlist_count': 1,
+    }, {
+        'url': 'http://www.nowtv.at/rtl/das-supertalent/list/free-staffel-8',
+        'info_dict': {
+            'id': '20716',
+            'title': 'Das Supertalent - FREE Staffel 8',
+        },
+        'playlist_count': 14,
+    }]
 
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'duration': duration,
-            'formats': formats,
-        }
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        show_id = mobj.group('show_id')
+        season_id = mobj.group('id')
+
+        fields = []
+        fields.extend(self._SHOW_FIELDS)
+        fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS)
+        fields.extend(
+            'formatTabs.formatTabPages.container.movies.%s' % field
+            for field in self._VIDEO_FIELDS)
+
+        list_info = self._download_json(
+            'https://api.nowtv.de/v3/formats/seo?fields=%s&name=%s.php'
+            % (','.join(fields), show_id),
+            season_id)
+
+        season = next(
+            season for season in list_info['formatTabs']['items']
+            if season.get('seoheadline') == season_id)
+
+        title = '%s - %s' % (list_info['title'], season['headline'])
+
+        entries = []
+        for container in season['formatTabPages']['items']:
+            for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []:
+                entries.append(self._extract_video(info))
+
+        return self.playlist_result(
+            entries, compat_str(season.get('id') or season_id), title)

youtube_dl/extractor/nowvideo.py

@@ -7,9 +7,9 @@ class NowVideoIE(NovaMovIE):
     IE_NAME = 'nowvideo'
     IE_DESC = 'NowVideo'
 
-    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|ec|sx|eu|at|ag|co|li)'}
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'}
 
-    _HOST = 'www.nowvideo.ch'
+    _HOST = 'www.nowvideo.to'
 
     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
     _FILEKEY_REGEX = r'var fkzd="([^"]+)";'

youtube_dl/extractor/pbs.py

@@ -8,6 +8,7 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,
+    strip_jsonp,
     unified_strdate,
     US_RATINGS,
 )
@@ -21,7 +22,7 @@ class PBSIE(InfoExtractor):
            # Article with embedded player (or direct video)
            (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
-           video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
+           (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
     '''
 
@@ -153,6 +154,26 @@ class PBSIE(InfoExtractor):
             'params': {
                 'skip_download': True,  # requires ffmpeg
             },
+        },
+        {
+            # Frontline video embedded via flp2012.js
+            'url': 'http://www.pbs.org/wgbh/pages/frontline/the-atomic-artists',
+            'info_dict': {
+                'id': '2070868960',
+                'display_id': 'the-atomic-artists',
+                'ext': 'mp4',
+                'title': 'FRONTLINE - The Atomic Artists',
+                'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+                'duration': 723,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
+        },
+        {
+            'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
+            'only_matching': True,
         }
     ]
     _ERRORS = {
@@ -191,9 +212,30 @@ class PBSIE(InfoExtractor):
             if media_id:
                 return media_id, presumptive_id, upload_date
 
-            url = self._search_regex(
-                r'(?s)<iframe[^>]+?(?:[a-z-]+?=["\'].*?["\'][^>]+?)*?\bsrc=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
-                webpage, 'player URL')
+            # Fronline video embedded via flp
+            video_id = self._search_regex(
+                r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None)
+            if video_id:
+                # pkg_id calculation is reverse engineered from
+                # http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
+                prg_id = self._search_regex(
+                    r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:]
+                if 'q' in prg_id:
+                    prg_id = prg_id.split('q')[1]
+                prg_id = int(prg_id, 16)
+                getdir = self._download_json(
+                    'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
+                    presumptive_id, 'Downloading getdir JSON',
+                    transform_source=strip_jsonp)
+                return getdir['mid'], presumptive_id, upload_date
+
+            for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
+                url = self._search_regex(
+                    r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe,
+                    'player URL', default=None, group='url')
+                if url:
+                    break
+
             mobj = re.match(self._VALID_URL, url)
 
         player_id = mobj.group('player_id')
@@ -221,7 +263,7 @@ class PBSIE(InfoExtractor):
             return self.playlist_result(entries, display_id)
 
         info = self._download_json(
-            'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
+            'http://player.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
             display_id)
 
         formats = []

youtube_dl/extractor/periscope.py

@@ -2,17 +2,14 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
 from ..utils import parse_iso8601
 
 
 class PeriscopeIE(InfoExtractor):
     IE_DESC = 'Periscope'
-    _VALID_URL = r'https?://(?:www\.)?periscope\.tv/w/(?P<id>[^/?#]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?periscope\.tv/[^/]+/(?P<id>[^/?#]+)'
+    # Alive example URLs can be found here http://onperiscope.com/
+    _TESTS = [{
         'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==',
         'md5': '65b57957972e503fcbbaeed8f4fa04ca',
         'info_dict': {
@@ -25,11 +22,18 @@ class PeriscopeIE(InfoExtractor):
             'uploader_id': '1465763',
         },
         'skip': 'Expires in 24 hours',
-    }
+    }, {
+        'url': 'https://www.periscope.tv/w/1ZkKzPbMVggJv',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.periscope.tv/bastaakanoggano/1OdKrlkZZjOJX',
+        'only_matching': True,
+    }]
 
-    def _call_api(self, method, token):
+    def _call_api(self, method, value):
+        attribute = 'token' if len(value) > 13 else 'broadcast_id'
         return self._download_json(
-            'https://api.periscope.tv/api/v2/%s?token=%s' % (method, token), token)
+            'https://api.periscope.tv/api/v2/%s?%s=%s' % (method, attribute, value), value)
 
     def _real_extract(self, url):
         token = self._match_id(url)
@@ -76,24 +80,3 @@ class PeriscopeIE(InfoExtractor):
             'thumbnails': thumbnails,
             'formats': formats,
         }
-
-
-class QuickscopeIE(InfoExtractor):
-    IE_DESC = 'Quick Scope'
-    _VALID_URL = r'https?://watchonperiscope\.com/broadcast/(?P<id>\d+)'
-    _TEST = {
-        'url': 'https://watchonperiscope.com/broadcast/56180087',
-        'only_matching': True,
-    }
-
-    def _real_extract(self, url):
-        broadcast_id = self._match_id(url)
-        request = compat_urllib_request.Request(
-            'https://watchonperiscope.com/api/accessChannel', compat_urllib_parse.urlencode({
-                'broadcast_id': broadcast_id,
-                'entry_ticket': '',
-                'from_push': 'false',
-                'uses_sessions': 'true',
-            }).encode('utf-8'))
-        return self.url_result(
-            self._download_json(request, broadcast_id)['share_url'], 'Periscope')

youtube_dl/extractor/pluralsight.py

@@ -1,7 +1,8 @@
 from __future__ import unicode_literals
 
-import re
 import json
+import random
+import collections
 
 from .common import InfoExtractor
 from ..compat import (
@@ -17,13 +18,18 @@ from ..utils import (
 )
 
 
-class PluralsightIE(InfoExtractor):
+class PluralsightBaseIE(InfoExtractor):
+    _API_BASE = 'http://app.pluralsight.com'
+
+
+class PluralsightIE(PluralsightBaseIE):
     IE_NAME = 'pluralsight'
-    _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/training/player\?author=(?P<author>[^&]+)&name=(?P<name>[^&]+)(?:&mode=live)?&clip=(?P<clip>\d+)&course=(?P<course>[^&]+)'
-    _LOGIN_URL = 'https://www.pluralsight.com/id/'
+    _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/training/player\?'
+    _LOGIN_URL = 'https://app.pluralsight.com/id/'
+
     _NETRC_MACHINE = 'pluralsight'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.pluralsight.com/training/player?author=mike-mckeown&name=hosting-sql-server-windows-azure-iaas-m7-mgmt&mode=live&clip=3&course=hosting-sql-server-windows-azure-iaas',
         'md5': '4d458cf5cf4c593788672419a8dd4cf8',
         'info_dict': {
@@ -33,7 +39,14 @@ class PluralsightIE(InfoExtractor):
             'duration': 338,
         },
         'skip': 'Requires pluralsight account credentials',
-    }
+    }, {
+        'url': 'https://app.pluralsight.com/training/player?course=angularjs-get-started&author=scott-allen&name=angularjs-get-started-m1-introduction&clip=0&mode=live',
+        'only_matching': True,
+    }, {
+        # available without pluralsight account
+        'url': 'http://app.pluralsight.com/training/player?author=scott-allen&name=angularjs-get-started-m1-introduction&mode=live&clip=0&course=angularjs-get-started',
+        'only_matching': True,
+    }]
 
     def _real_initialize(self):
         self._login()
@@ -41,7 +54,7 @@ class PluralsightIE(InfoExtractor):
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
-            self.raise_login_required('Pluralsight account is required')
+            return
 
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
@@ -73,12 +86,19 @@ class PluralsightIE(InfoExtractor):
         if error:
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
+        if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
+            raise ExtractorError('Unable to log in')
+
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        author = mobj.group('author')
-        name = mobj.group('name')
-        clip_id = mobj.group('clip')
-        course = mobj.group('course')
+        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+
+        author = qs.get('author', [None])[0]
+        name = qs.get('name', [None])[0]
+        clip_id = qs.get('clip', [None])[0]
+        course = qs.get('course', [None])[0]
+
+        if any(not f for f in (author, name, clip_id, course,)):
+            raise ExtractorError('Invalid URL', expected=True)
 
         display_id = '%s-%s' % (name, clip_id)
 
@@ -112,13 +132,33 @@ class PluralsightIE(InfoExtractor):
             'high': {'width': 1024, 'height': 768},
         }
 
+        AllowedQuality = collections.namedtuple('AllowedQuality', ['ext', 'qualities'])
+
         ALLOWED_QUALITIES = (
-            ('webm', ('high',)),
-            ('mp4', ('low', 'medium', 'high',)),
+            AllowedQuality('webm', ('high',)),
+            AllowedQuality('mp4', ('low', 'medium', 'high',)),
         )
 
+        # In order to minimize the number of calls to ViewClip API and reduce
+        # the probability of being throttled or banned by Pluralsight we will request
+        # only single format until formats listing was explicitly requested.
+        if self._downloader.params.get('listformats', False):
+            allowed_qualities = ALLOWED_QUALITIES
+        else:
+            def guess_allowed_qualities():
+                req_format = self._downloader.params.get('format') or 'best'
+                req_format_split = req_format.split('-')
+                if len(req_format_split) > 1:
+                    req_ext, req_quality = req_format_split
+                    for allowed_quality in ALLOWED_QUALITIES:
+                        if req_ext == allowed_quality.ext and req_quality in allowed_quality.qualities:
+                            return (AllowedQuality(req_ext, (req_quality, )), )
+                req_ext = 'webm' if self._downloader.params.get('prefer_free_formats') else 'mp4'
+                return (AllowedQuality(req_ext, ('high', )), )
+            allowed_qualities = guess_allowed_qualities()
+
         formats = []
-        for ext, qualities in ALLOWED_QUALITIES:
+        for ext, qualities in allowed_qualities:
             for quality in qualities:
                 f = QUALITIES[quality].copy()
                 clip_post = {
@@ -132,12 +172,23 @@ class PluralsightIE(InfoExtractor):
                     'q': '%dx%d' % (f['width'], f['height']),
                 }
                 request = compat_urllib_request.Request(
-                    'http://www.pluralsight.com/training/Player/ViewClip',
+                    '%s/training/Player/ViewClip' % self._API_BASE,
                     json.dumps(clip_post).encode('utf-8'))
                 request.add_header('Content-Type', 'application/json;charset=utf-8')
                 format_id = '%s-%s' % (ext, quality)
                 clip_url = self._download_webpage(
                     request, display_id, 'Downloading %s URL' % format_id, fatal=False)
+
+                # Pluralsight tracks multiple sequential calls to ViewClip API and start
+                # to return 429 HTTP errors after some time (see
+                # https://github.com/rg3/youtube-dl/pull/6989). Moreover it may even lead
+                # to account ban (see https://github.com/rg3/youtube-dl/issues/6842).
+                # To somewhat reduce the probability of these consequences
+                # we will sleep random amount of time before each call to ViewClip.
+                self._sleep(
+                    random.randint(2, 5), display_id,
+                    '%(video_id)s: Waiting for %(timeout)s seconds to avoid throttling')
+
                 if not clip_url:
                     continue
                 f.update({
@@ -163,10 +214,10 @@ class PluralsightIE(InfoExtractor):
         }
 
 
-class PluralsightCourseIE(InfoExtractor):
+class PluralsightCourseIE(PluralsightBaseIE):
     IE_NAME = 'pluralsight:course'
-    _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/courses/(?P<id>[^/]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?:www|app)\.)?pluralsight\.com/(?:library/)?courses/(?P<id>[^/]+)'
+    _TESTS = [{
         # Free course from Pluralsight Starter Subscription for Microsoft TechNet
         # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz
         'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas',
@@ -176,7 +227,14 @@ class PluralsightCourseIE(InfoExtractor):
             'description': 'md5:61b37e60f21c4b2f91dc621a977d0986',
         },
         'playlist_count': 31,
-    }
+    }, {
+        # available without pluralsight account
+        'url': 'https://www.pluralsight.com/courses/angularjs-get-started',
+        'only_matching': True,
+    }, {
+        'url': 'https://app.pluralsight.com/library/courses/understanding-microsoft-azure-amazon-aws/table-of-contents',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         course_id = self._match_id(url)
@@ -184,14 +242,14 @@ class PluralsightCourseIE(InfoExtractor):
         # TODO: PSM cookie
 
         course = self._download_json(
-            'http://www.pluralsight.com/data/course/%s' % course_id,
+            '%s/data/course/%s' % (self._API_BASE, course_id),
             course_id, 'Downloading course JSON')
 
         title = course['title']
         description = course.get('description') or course.get('shortDescription')
 
         course_data = self._download_json(
-            'http://www.pluralsight.com/data/course/content/%s' % course_id,
+            '%s/data/course/content/%s' % (self._API_BASE, course_id),
             course_id, 'Downloading course data JSON')
 
         entries = []
@@ -201,7 +259,7 @@ class PluralsightCourseIE(InfoExtractor):
                 if not player_parameters:
                     continue
                 entries.append(self.url_result(
-                    'http://www.pluralsight.com/training/player?%s' % player_parameters,
+                    '%s/training/player?%s' % (self._API_BASE, player_parameters),
                     'Pluralsight'))
 
         return self.playlist_result(entries, course_id, title, description)

youtube_dl/extractor/prosiebensat1.py

@@ -20,7 +20,7 @@ from ..utils import (
 class ProSiebenSat1IE(InfoExtractor):
     IE_NAME = 'prosiebensat1'
     IE_DESC = 'ProSiebenSat.1 Digital'
-    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at|ch)|ran\.de|fem\.com)/(?P<id>.+)'
 
     _TESTS = [
         {

youtube_dl/extractor/rtbf.py

@@ -9,8 +9,8 @@ from ..utils import (
 
 
 class RTBFIE(InfoExtractor):
-    _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?rtbf\.be/(?:video/[^?]+\?.*\bid=|ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=)(?P<id>\d+)'
+    _TESTS = [{
         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
         'md5': '799f334ddf2c0a582ba80c44655be570',
         'info_dict': {
@@ -19,7 +19,14 @@ class RTBFIE(InfoExtractor):
             'title': 'Les Diables au coeur (épisode 2)',
             'duration': 3099,
         }
-    }
+    }, {
+        # geo restricted
+        'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858',
+        'only_matching': True,
+    }]
 
     _QUALITIES = [
         ('mobile', 'mobile'),

youtube_dl/extractor/rtve.py

@@ -6,7 +6,7 @@ import re
 import time
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_request, compat_urlparse
+from ..compat import compat_urllib_request
 from ..utils import (
     ExtractorError,
     float_or_none,
@@ -107,15 +107,9 @@ class RTVEALaCartaIE(InfoExtractor):
         png = self._download_webpage(png_request, video_id, 'Downloading url information')
         video_url = _decrypt_url(png)
         if not video_url.endswith('.f4m'):
-            auth_url = video_url.replace(
+            video_url = video_url.replace(
                 'resources/', 'auth/resources/'
             ).replace('.net.rtve', '.multimedia.cdn.rtve')
-            video_path = self._download_webpage(
-                auth_url, video_id, 'Getting video url')
-            # Use mvod1.akcdn instead of flash.akamaihd.multimedia.cdn to get
-            # the right Content-Length header and the mp4 format
-            video_url = compat_urlparse.urljoin(
-                'http://mvod1.akcdn.rtve.es/', video_path)
 
         subtitles = None
         if info.get('sbtFile') is not None:

youtube_dl/extractor/rutube.py

@@ -9,7 +9,7 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
-    ExtractorError,
+    determine_ext,
     unified_strdate,
 )
 
@@ -51,10 +51,26 @@ class RutubeIE(InfoExtractor):
             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
             video_id, 'Downloading options JSON')
 
-        m3u8_url = options['video_balancer'].get('m3u8')
-        if m3u8_url is None:
-            raise ExtractorError('Couldn\'t find m3u8 manifest url')
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+        formats = []
+        for format_id, format_url in options['video_balancer'].items():
+            ext = determine_ext(format_url)
+            print(ext)
+            if ext == 'm3u8':
+                m3u8_formats = self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
+                if m3u8_formats:
+                    formats.extend(m3u8_formats)
+            elif ext == 'f4m':
+                f4m_formats = self._extract_f4m_formats(
+                    format_url, video_id, f4m_id=format_id, fatal=False)
+                if f4m_formats:
+                    formats.extend(f4m_formats)
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                })
+        self._sort_formats(formats)
 
         return {
             'id': video['id'],
@@ -74,9 +90,9 @@ class RutubeIE(InfoExtractor):
 class RutubeEmbedIE(InfoExtractor):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'
-    _VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)'
+    _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
@@ -90,7 +106,10 @@ class RutubeEmbedIE(InfoExtractor):
         'params': {
             'skip_download': 'Requires ffmpeg',
         },
-    }
+    }, {
+        'url': 'http://rutube.ru/play/embed/8083783',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         embed_id = self._match_id(url)

youtube_dl/extractor/ruutu.py

@@ -57,16 +57,21 @@ class RuutuIE(InfoExtractor):
                     extract_formats(child)
                 elif child.tag.endswith('File'):
                     video_url = child.text
-                    if not video_url or video_url in processed_urls or 'NOT_USED' in video_url:
+                    if (not video_url or video_url in processed_urls or
+                            any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
                         return
                     processed_urls.append(video_url)
                     ext = determine_ext(video_url)
                     if ext == 'm3u8':
-                        formats.extend(self._extract_m3u8_formats(
-                            video_url, video_id, 'mp4', m3u8_id='hls'))
+                        m3u8_formats = self._extract_m3u8_formats(
+                            video_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+                        if m3u8_formats:
+                            formats.extend(m3u8_formats)
                     elif ext == 'f4m':
-                        formats.extend(self._extract_f4m_formats(
-                            video_url, video_id, f4m_id='hds'))
+                        f4m_formats = self._extract_f4m_formats(
+                            video_url, video_id, f4m_id='hds', fatal=False)
+                        if f4m_formats:
+                            formats.extend(f4m_formats)
                     else:
                         proto = compat_urllib_parse_urlparse(video_url).scheme
                         if not child.tag.startswith('HTTP') and proto != 'rtmp':

youtube_dl/extractor/safari.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .brightcove import BrightcoveIE
+from .brightcove import BrightcoveLegacyIE
 
 from ..compat import (
     compat_urllib_parse,
@@ -112,11 +112,11 @@ class SafariIE(SafariBaseIE):
             '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
             part)
 
-        bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+        bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
         if not bc_url:
             raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
 
-        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
+        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy')
 
 
 class SafariCourseIE(SafariBaseIE):

youtube_dl/extractor/soundcloud.py

@@ -4,13 +4,17 @@ from __future__ import unicode_literals
 import re
 import itertools
 
-from .common import InfoExtractor
+from .common import (
+    InfoExtractor,
+    SearchInfoExtractor
+)
 from ..compat import (
     compat_str,
     compat_urlparse,
     compat_urllib_parse,
 )
 from ..utils import (
+    encode_dict,
     ExtractorError,
     int_or_none,
     unified_strdate,
@@ -469,3 +473,60 @@ class SoundcloudPlaylistIE(SoundcloudIE):
             'description': data.get('description'),
             'entries': entries,
         }
+
+
+class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
+    IE_NAME = 'soundcloud:search'
+    IE_DESC = 'Soundcloud search'
+    _MAX_RESULTS = float('inf')
+    _TESTS = [{
+        'url': 'scsearch15:post-avant jazzcore',
+        'info_dict': {
+            'title': 'post-avant jazzcore',
+        },
+        'playlist_count': 15,
+    }]
+
+    _SEARCH_KEY = 'scsearch'
+    _MAX_RESULTS_PER_PAGE = 200
+    _DEFAULT_RESULTS_PER_PAGE = 50
+    _API_V2_BASE = 'https://api-v2.soundcloud.com'
+
+    def _get_collection(self, endpoint, collection_id, **query):
+        limit = min(
+            query.get('limit', self._DEFAULT_RESULTS_PER_PAGE),
+            self._MAX_RESULTS_PER_PAGE)
+        query['limit'] = limit
+        query['client_id'] = self._CLIENT_ID
+        query['linked_partitioning'] = '1'
+        query['offset'] = 0
+        data = compat_urllib_parse.urlencode(encode_dict(query))
+        next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data)
+
+        collected_results = 0
+
+        for i in itertools.count(1):
+            response = self._download_json(
+                next_url, collection_id, 'Downloading page {0}'.format(i),
+                'Unable to download API page')
+
+            collection = response.get('collection', [])
+            if not collection:
+                break
+
+            collection = list(filter(bool, collection))
+            collected_results += len(collection)
+
+            for item in collection:
+                yield self.url_result(item['uri'], SoundcloudIE.ie_key())
+
+            if not collection or collected_results >= limit:
+                break
+
+            next_url = response.get('next_href')
+            if not next_url:
+                break
+
+    def _get_n_results(self, query, n):
+        tracks = self._get_collection('/search/tracks', query, limit=n, q=query)
+        return self.playlist_result(tracks, playlist_title=query)

youtube_dl/extractor/space.py

@@ -3,14 +3,14 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .brightcove import BrightcoveIE
+from .brightcove import BrightcoveLegacyIE
 from ..utils import RegexNotFoundError, ExtractorError
 
 
 class SpaceIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
     _TEST = {
-        'add_ie': ['Brightcove'],
+        'add_ie': ['BrightcoveLegacy'],
         'url': 'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
         'info_dict': {
             'id': '2780937028001',
@@ -31,8 +31,8 @@ class SpaceIE(InfoExtractor):
             brightcove_url = self._og_search_video_url(webpage)
         except RegexNotFoundError:
             # Other videos works fine with the info from the object
-            brightcove_url = BrightcoveIE._extract_brightcove_url(webpage)
+            brightcove_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
         if brightcove_url is None:
             raise ExtractorError(
                 'The webpage does not contain a video', expected=True)
-        return self.url_result(brightcove_url, BrightcoveIE.ie_key())
+        return self.url_result(brightcove_url, BrightcoveLegacyIE.ie_key())

youtube_dl/extractor/theplatform.py

@@ -139,6 +139,11 @@ class ThePlatformIE(ThePlatformBaseIE):
             'upload_date': '20150701',
             'categories': ['Today/Shows/Orange Room', 'Today/Sections/Money', 'Today/Topics/Tech', "Today/Topics/Editor's picks"],
         },
+    }, {
+        # From http://www.nbc.com/the-blacklist/video/sir-crispin-crandall/2928790?onid=137781#vc137781=1
+        # geo-restricted (US), HLS encrypted with AES-128
+        'url': 'http://player.theplatform.com/p/NnzsPC/onsite_universal/select/media/guid/2410887629/2928790?fwsitesection=nbc_the_blacklist_video_library&autoPlay=true&carouselID=137781',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -182,8 +187,12 @@ class ThePlatformIE(ThePlatformBaseIE):
             # Seems there's no pattern for the interested script filename, so
             # I try one by one
             for script in reversed(scripts):
-                feed_script = self._download_webpage(script, video_id, 'Downloading feed script')
-                feed_id = self._search_regex(r'defaultFeedId\s*:\s*"([^"]+)"', feed_script, 'default feed id', default=None)
+                feed_script = self._download_webpage(
+                    self._proto_relative_url(script, 'http:'),
+                    video_id, 'Downloading feed script')
+                feed_id = self._search_regex(
+                    r'defaultFeedId\s*:\s*"([^"]+)"', feed_script,
+                    'default feed id', default=None)
                 if feed_id is not None:
                     break
             if feed_id is None:
@@ -193,6 +202,15 @@ class ThePlatformIE(ThePlatformBaseIE):
 
         if smuggled_data.get('force_smil_url', False):
             smil_url = url
+        # Explicitly specified SMIL (see https://github.com/rg3/youtube-dl/issues/7385)
+        elif '/guid/' in url:
+            webpage = self._download_webpage(url, video_id)
+            smil_url = self._search_regex(
+                r'<link[^>]+href=(["\'])(?P<url>.+?)\1[^>]+type=["\']application/smil\+xml',
+                webpage, 'smil url', group='url')
+            path = self._search_regex(
+                r'link\.theplatform\.com/s/((?:[^/?#&]+/)+[^/?#&]+)', smil_url, 'path')
+            smil_url += '?' if '?' not in smil_url else '&' + 'formats=m3u,mpeg4&format=SMIL'
         elif mobj.group('config'):
             config_url = url + '&form=json'
             config_url = config_url.replace('swf/', 'config/')

youtube_dl/extractor/tlc.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .brightcove import BrightcoveIE
+from .brightcove import BrightcoveLegacyIE
 from .discovery import DiscoveryIE
 from ..compat import compat_urlparse
 
@@ -66,6 +66,6 @@ class TlcDeIE(InfoExtractor):
 
         return {
             '_type': 'url',
-            'url': BrightcoveIE._extract_brightcove_url(iframe),
-            'ie': BrightcoveIE.ie_key(),
+            'url': BrightcoveLegacyIE._extract_brightcove_url(iframe),
+            'ie': BrightcoveLegacyIE.ie_key(),
         }

youtube_dl/extractor/twitter.py

@@ -9,6 +9,8 @@ from ..utils import (
     float_or_none,
     xpath_text,
     remove_end,
+    int_or_none,
+    ExtractorError,
 )
 
 
@@ -18,7 +20,7 @@ class TwitterCardIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
-            'md5': '7d2f6b4d2eb841a7ccc893d479bfceb4',
+            'md5': '4fa26a35f9d1bf4b646590ba8e84be19',
             'info_dict': {
                 'id': '560070183650213889',
                 'ext': 'mp4',
@@ -50,6 +52,20 @@ class TwitterCardIE(InfoExtractor):
                 'uploader': 'OMG! Ubuntu!',
                 'uploader_id': 'omgubuntu',
             },
+            'add_ie': ['Youtube'],
+        },
+        {
+            'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568',
+            'md5': 'ab2745d0b0ce53319a534fccaa986439',
+            'info_dict': {
+                'id': 'iBb2x00UVlv',
+                'ext': 'mp4',
+                'upload_date': '20151113',
+                'uploader_id': '1189339351084113920',
+                'uploader': '@ArsenalTerje',
+                'title': 'Vine by @ArsenalTerje',
+            },
+            'add_ie': ['Vine'],
         }
     ]
 
@@ -69,11 +85,11 @@ class TwitterCardIE(InfoExtractor):
             request.add_header('User-Agent', user_agent)
             webpage = self._download_webpage(request, video_id)
 
-            youtube_url = self._html_search_regex(
-                r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
-                webpage, 'youtube iframe', default=None)
-            if youtube_url:
-                return self.url_result(youtube_url, 'Youtube')
+            iframe_url = self._html_search_regex(
+                r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
+                webpage, 'video iframe', default=None)
+            if iframe_url:
+                return self.url_result(iframe_url)
 
             config = self._parse_json(self._html_search_regex(
                 r'data-player-config="([^"]+)"', webpage, 'data player config'),
@@ -120,9 +136,9 @@ class TwitterIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
     _TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'https://twitter.com/freethenipple/status/643211948184596480',
-        'md5': '31cd83a116fc41f99ae3d909d4caf6a0',
+        'md5': 'db6612ec5d03355953c3ca9250c97e5e',
         'info_dict': {
             'id': '643211948184596480',
             'ext': 'mp4',
@@ -133,7 +149,30 @@ class TwitterIE(InfoExtractor):
             'uploader': 'FREE THE NIPPLE',
             'uploader_id': 'freethenipple',
         },
-    }
+    }, {
+        'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
+        'md5': 'f36dcd5fb92bf7057f155e7d927eeb42',
+        'info_dict': {
+            'id': '657991469417025536',
+            'ext': 'mp4',
+            'title': 'Gifs - tu vai cai tu vai cai tu nao eh capaz disso tu vai cai',
+            'description': 'Gifs on Twitter: "tu vai cai tu vai cai tu nao eh capaz disso tu vai cai https://t.co/tM46VHFlO5"',
+            'thumbnail': 're:^https?://.*\.png',
+            'uploader': 'Gifs',
+            'uploader_id': 'giphz',
+        },
+    }, {
+        'url': 'https://twitter.com/starwars/status/665052190608723968',
+        'md5': '39b7199856dee6cd4432e72c74bc69d4',
+        'info_dict': {
+            'id': '665052190608723968',
+            'ext': 'mp4',
+            'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.',
+            'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."',
+            'uploader_id': 'starwars',
+            'uploader': 'Star Wars',
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -144,23 +183,46 @@ class TwitterIE(InfoExtractor):
 
         username = remove_end(self._og_search_title(webpage), ' on Twitter')
 
-        title = self._og_search_description(webpage).strip('').replace('\n', ' ')
+        title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”')
 
         # strip  'https -_t.co_BJYgOjSeGA' junk from filenames
-        mobj = re.match(r'“(.*)\s+(https?://[^ ]+)”', title)
-        title, short_url = mobj.groups()
+        title = re.sub(r'\s+(https?://[^ ]+)', '', title)
 
-        card_id = self._search_regex(
-            r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url')
-        card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
-
-        return {
-            '_type': 'url_transparent',
-            'ie_key': 'TwitterCard',
+        info = {
             'uploader_id': user_id,
             'uploader': username,
-            'url': card_url,
             'webpage_url': url,
-            'description': '%s on Twitter: "%s %s"' % (username, title, short_url),
+            'description': '%s on Twitter: "%s"' % (username, description),
             'title': username + ' - ' + title,
         }
+
+        card_id = self._search_regex(
+            r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url', default=None)
+        if card_id:
+            card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
+            info.update({
+                '_type': 'url_transparent',
+                'ie_key': 'TwitterCard',
+                'url': card_url,
+            })
+            return info
+
+        mobj = re.search(r'''(?x)
+            <video[^>]+class="animated-gif"[^>]+
+                (?:data-height="(?P<height>\d+)")?[^>]+
+                (?:data-width="(?P<width>\d+)")?[^>]+
+                (?:poster="(?P<poster>[^"]+)")?[^>]*>\s*
+                <source[^>]+video-src="(?P<url>[^"]+)"
+        ''', webpage)
+
+        if mobj:
+            info.update({
+                'id': twid,
+                'url': mobj.group('url'),
+                'height': int_or_none(mobj.group('height')),
+                'width': int_or_none(mobj.group('width')),
+                'thumbnail': mobj.group('poster'),
+            })
+            return info
+
+        raise ExtractorError('There\'s not video in this tweet.')

youtube_dl/extractor/udn.py

@@ -12,7 +12,8 @@ from ..compat import compat_urlparse
 
 class UDNEmbedIE(InfoExtractor):
     IE_DESC = '聯合影音'
-    _VALID_URL = r'https?://video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)'
+    _PROTOCOL_RELATIVE_VALID_URL = r'//video\.udn\.com/(?:embed|play)/news/(?P<id>\d+)'
+    _VALID_URL = r'https?:' + _PROTOCOL_RELATIVE_VALID_URL
     _TESTS = [{
         'url': 'http://video.udn.com/embed/news/300040',
         'md5': 'de06b4c90b042c128395a88f0384817e',

youtube_dl/extractor/videolecturesnet.py

@@ -1,82 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_urlparse,
-)
-from ..utils import (
-    ExtractorError,
-    parse_duration,
-)
-
-
-class VideoLecturesNetIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P<id>[^/#?]+)/*(?:[#?].*)?$'
-    IE_NAME = 'videolectures.net'
-
-    _TESTS = [{
-        'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
-        'info_dict': {
-            'id': 'promogram_igor_mekjavic_eng',
-            'ext': 'mp4',
-            'title': 'Automatics, robotics and biocybernetics',
-            'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
-            'upload_date': '20130627',
-            'duration': 565,
-            'thumbnail': 're:http://.*\.jpg',
-        },
-    }, {
-        # video with invalid direct format links (HTTP 403)
-        'url': 'http://videolectures.net/russir2010_filippova_nlp/',
-        'info_dict': {
-            'id': 'russir2010_filippova_nlp',
-            'ext': 'flv',
-            'title': 'NLP at Google',
-            'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
-            'duration': 5352,
-            'thumbnail': 're:http://.*\.jpg',
-        },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://videolectures.net/deeplearning2015_montreal/',
-        'info_dict': {
-            'id': 'deeplearning2015_montreal',
-            'title': 'Deep Learning Summer School, Montreal 2015',
-            'description': 'md5:90121a40cc6926df1bf04dcd8563ed3b',
-        },
-        'playlist_count': 30,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id
-
-        try:
-            smil = self._download_smil(smil_url, video_id)
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
-                # Probably a playlist
-                webpage = self._download_webpage(url, video_id)
-                entries = [
-                    self.url_result(compat_urlparse.urljoin(url, video_url), 'VideoLecturesNet')
-                    for _, video_url in re.findall(r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', webpage)]
-                playlist_title = self._html_search_meta('title', webpage, 'title', fatal=True)
-                playlist_description = self._html_search_meta('description', webpage, 'description')
-                return self.playlist_result(entries, video_id, playlist_title, playlist_description)
-
-        info = self._parse_smil(smil, smil_url, video_id)
-
-        info['id'] = video_id
-
-        switch = smil.find('.//switch')
-        if switch is not None:
-            info['duration'] = parse_duration(switch.attrib.get('dur'))
-
-        return info

youtube_dl/extractor/vidzi.py

@@ -20,8 +20,14 @@ class VidziIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        video_url = self._html_search_regex(
-            r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, 'video url')
+        video_host = self._html_search_regex(
+            r'id=\'vplayer\'><img src="http://(.*?)/i', webpage,
+            'video host')
+        video_hash = self._html_search_regex(
+            r'\|([a-z0-9]+)\|hls\|type', webpage, 'video_hash')
+        ext = self._html_search_regex(
+            r'\|tracks\|([a-z0-9]+)\|', webpage, 'video ext')
+        video_url = 'http://' + video_host + '/' + video_hash + '/v.' + ext
         title = self._html_search_regex(
             r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
 

youtube_dl/extractor/viidea.py

@@ -0,0 +1,188 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urlparse,
+    compat_str,
+)
+from ..utils import (
+    parse_duration,
+    js_to_json,
+    parse_iso8601,
+)
+
+
+class ViideaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)http://(?:www\.)?(?:
+            videolectures\.net|
+            flexilearn\.viidea\.net|
+            presentations\.ocwconsortium\.org|
+            video\.travel-zoom\.si|
+            video\.pomp-forum\.si|
+            tv\.nil\.si|
+            video\.hekovnik.com|
+            video\.szko\.si|
+            kpk\.viidea\.com|
+            inside\.viidea\.net|
+            video\.kiberpipa\.org|
+            bvvideo\.si|
+            kongres\.viidea\.net|
+            edemokracija\.viidea\.com
+        )(?:/lecture)?/(?P<id>[^/]+)(?:/video/(?P<part>\d+))?/*(?:[#?].*)?$'''
+
+    _TESTS = [{
+        'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/',
+        'info_dict': {
+            'id': '20171',
+            'display_id': 'promogram_igor_mekjavic_eng',
+            'ext': 'mp4',
+            'title': 'Automatics, robotics and biocybernetics',
+            'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
+            'thumbnail': 're:http://.*\.jpg',
+            'timestamp': 1372349289,
+            'upload_date': '20130627',
+            'duration': 565,
+        },
+    }, {
+        # video with invalid direct format links (HTTP 403)
+        'url': 'http://videolectures.net/russir2010_filippova_nlp/',
+        'info_dict': {
+            'id': '14891',
+            'display_id': 'russir2010_filippova_nlp',
+            'ext': 'flv',
+            'title': 'NLP at Google',
+            'description': 'md5:fc7a6d9bf0302d7cc0e53f7ca23747b3',
+            'thumbnail': 're:http://.*\.jpg',
+            'timestamp': 1284375600,
+            'upload_date': '20100913',
+            'duration': 5352,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        # event playlist
+        'url': 'http://videolectures.net/deeplearning2015_montreal/',
+        'info_dict': {
+            'id': '23181',
+            'title': 'Deep Learning Summer School, Montreal 2015',
+            'description': 'md5:0533a85e4bd918df52a01f0e1ebe87b7',
+            'thumbnail': 're:http://.*\.jpg',
+            'timestamp': 1438560000,
+        },
+        'playlist_count': 30,
+    }, {
+        # multi part lecture
+        'url': 'http://videolectures.net/mlss09uk_bishop_ibi/',
+        'info_dict': {
+            'id': '9737',
+            'display_id': 'mlss09uk_bishop_ibi',
+            'title': 'Introduction To Bayesian Inference',
+            'thumbnail': 're:http://.*\.jpg',
+            'timestamp': 1251622800,
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '9737_part1',
+                'display_id': 'mlss09uk_bishop_ibi_part1',
+                'ext': 'wmv',
+                'title': 'Introduction To Bayesian Inference (Part 1)',
+                'thumbnail': 're:http://.*\.jpg',
+                'duration': 4622,
+                'timestamp': 1251622800,
+                'upload_date': '20090830',
+            },
+        }, {
+            'info_dict': {
+                'id': '9737_part2',
+                'display_id': 'mlss09uk_bishop_ibi_part2',
+                'ext': 'wmv',
+                'title': 'Introduction To Bayesian Inference (Part 2)',
+                'thumbnail': 're:http://.*\.jpg',
+                'duration': 5641,
+                'timestamp': 1251622800,
+                'upload_date': '20090830',
+            },
+        }],
+        'playlist_count': 2,
+    }]
+
+    def _real_extract(self, url):
+        lecture_slug, explicit_part_id = re.match(self._VALID_URL, url).groups()
+
+        webpage = self._download_webpage(url, lecture_slug)
+
+        cfg = self._parse_json(self._search_regex(
+            [r'cfg\s*:\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*:\s*\(?\s*function',
+             r'cfg\s*:\s*({[^}]+})'],
+            webpage, 'cfg'), lecture_slug, js_to_json)
+
+        lecture_id = compat_str(cfg['obj_id'])
+
+        base_url = self._proto_relative_url(cfg['livepipe'], 'http:')
+
+        lecture_data = self._download_json(
+            '%s/site/api/lecture/%s?format=json' % (base_url, lecture_id),
+            lecture_id)['lecture'][0]
+
+        lecture_info = {
+            'id': lecture_id,
+            'display_id': lecture_slug,
+            'title': lecture_data['title'],
+            'timestamp': parse_iso8601(lecture_data.get('time')),
+            'description': lecture_data.get('description_wiki'),
+            'thumbnail': lecture_data.get('thumb'),
+        }
+
+        playlist_entries = []
+        lecture_type = lecture_data.get('type')
+        parts = [compat_str(video) for video in cfg.get('videos', [])]
+        if parts:
+            multipart = len(parts) > 1
+
+            def extract_part(part_id):
+                smil_url = '%s/%s/video/%s/smil.xml' % (base_url, lecture_slug, part_id)
+                smil = self._download_smil(smil_url, lecture_id)
+                info = self._parse_smil(smil, smil_url, lecture_id)
+                info['id'] = lecture_id if not multipart else '%s_part%s' % (lecture_id, part_id)
+                info['display_id'] = lecture_slug if not multipart else '%s_part%s' % (lecture_slug, part_id)
+                if multipart:
+                    info['title'] += ' (Part %s)' % part_id
+                switch = smil.find('.//switch')
+                if switch is not None:
+                    info['duration'] = parse_duration(switch.attrib.get('dur'))
+                item_info = lecture_info.copy()
+                item_info.update(info)
+                return item_info
+
+            if explicit_part_id or not multipart:
+                result = extract_part(explicit_part_id or parts[0])
+            else:
+                result = {
+                    '_type': 'multi_video',
+                    'entries': [extract_part(part) for part in parts],
+                }
+                result.update(lecture_info)
+
+            # Immediately return explicitly requested part or non event item
+            if explicit_part_id or lecture_type != 'evt':
+                return result
+
+            playlist_entries.append(result)
+
+        # It's probably a playlist
+        if not parts or lecture_type == 'evt':
+            playlist_webpage = self._download_webpage(
+                '%s/site/ajax/drilldown/?id=%s' % (base_url, lecture_id), lecture_id)
+            entries = [
+                self.url_result(compat_urlparse.urljoin(url, video_url), 'Viidea')
+                for _, video_url in re.findall(
+                    r'<a[^>]+href=(["\'])(.+?)\1[^>]+id=["\']lec=\d+', playlist_webpage)]
+            playlist_entries.extend(entries)
+
+        playlist = self.playlist_result(playlist_entries, lecture_id)
+        playlist.update(lecture_info)
+        return playlist

youtube_dl/extractor/vimeo.py

@@ -8,11 +8,11 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_HTTPError,
-    compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
 )
 from ..utils import (
+    encode_dict,
     ExtractorError,
     InAdvancePagedList,
     int_or_none,
@@ -40,17 +40,17 @@ class VimeoBaseInfoExtractor(InfoExtractor):
         self.report_login()
         webpage = self._download_webpage(self._LOGIN_URL, None, False)
         token, vuid = self._extract_xsrft_and_vuid(webpage)
-        data = urlencode_postdata({
+        data = urlencode_postdata(encode_dict({
             'action': 'login',
             'email': username,
             'password': password,
             'service': 'vimeo',
             'token': token,
-        })
+        }))
         login_request = compat_urllib_request.Request(self._LOGIN_URL, data)
         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        login_request.add_header('Cookie', 'vuid=%s' % vuid)
         login_request.add_header('Referer', self._LOGIN_URL)
+        self._set_vimeo_cookie('vuid', vuid)
         self._download_webpage(login_request, None, False, 'Wrong login info')
 
     def _extract_xsrft_and_vuid(self, webpage):
@@ -62,6 +62,9 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             webpage, 'vuid', group='vuid')
         return xsrft, vuid
 
+    def _set_vimeo_cookie(self, name, value):
+        self._set_cookie('vimeo.com', name, value)
+
 
 class VimeoIE(VimeoBaseInfoExtractor):
     """Information extractor for vimeo.com."""
@@ -186,6 +189,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'note': 'Video not completely processed, "failed" seed status',
             'only_matching': True,
         },
+        {
+            'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
+            'only_matching': True,
+        },
     ]
 
     @staticmethod
@@ -208,17 +215,17 @@ class VimeoIE(VimeoBaseInfoExtractor):
         if password is None:
             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
         token, vuid = self._extract_xsrft_and_vuid(webpage)
-        data = urlencode_postdata({
+        data = urlencode_postdata(encode_dict({
             'password': password,
             'token': token,
-        })
+        }))
         if url.startswith('http://'):
             # vimeo only supports https now, but the user can give an http url
             url = url.replace('http://', 'https://')
         password_request = compat_urllib_request.Request(url + '/password', data)
         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid)
         password_request.add_header('Referer', url)
+        self._set_vimeo_cookie('vuid', vuid)
         return self._download_webpage(
             password_request, video_id,
             'Verifying the password', 'Wrong password')
@@ -227,7 +234,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         password = self._downloader.params.get('videopassword', None)
         if password is None:
             raise ExtractorError('This video is protected by a password, use the --video-password option')
-        data = compat_urllib_parse.urlencode({'password': password})
+        data = urlencode_postdata(encode_dict({'password': password}))
         pass_url = url + '/check-password'
         password_request = compat_urllib_request.Request(pass_url, data)
         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
@@ -384,47 +391,29 @@ class VimeoIE(VimeoBaseInfoExtractor):
             like_count = None
             comment_count = None
 
-        # Vimeo specific: extract request signature and timestamp
-        sig = config['request']['signature']
-        timestamp = config['request']['timestamp']
-
-        # Vimeo specific: extract video codec and quality information
-        # First consider quality, then codecs, then take everything
-        codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
-        files = {'hd': [], 'sd': [], 'other': []}
-        config_files = config["video"].get("files") or config["request"].get("files")
-        for codec_name, codec_extension in codecs:
-            for quality in config_files.get(codec_name, []):
-                format_id = '-'.join((codec_name, quality)).lower()
-                key = quality if quality in files else 'other'
-                video_url = None
-                if isinstance(config_files[codec_name], dict):
-                    file_info = config_files[codec_name][quality]
-                    video_url = file_info.get('url')
-                else:
-                    file_info = {}
-                if video_url is None:
-                    video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
-                        % (video_id, sig, timestamp, quality, codec_name.upper())
-
-                files[key].append({
-                    'ext': codec_extension,
-                    'url': video_url,
-                    'format_id': format_id,
-                    'width': int_or_none(file_info.get('width')),
-                    'height': int_or_none(file_info.get('height')),
-                    'tbr': int_or_none(file_info.get('bitrate')),
-                })
         formats = []
-        m3u8_url = config_files.get('hls', {}).get('all')
+        config_files = config['video'].get('files') or config['request'].get('files', {})
+        for f in config_files.get('progressive', []):
+            video_url = f.get('url')
+            if not video_url:
+                continue
+            formats.append({
+                'url': video_url,
+                'format_id': 'http-%s' % f.get('quality'),
+                'width': int_or_none(f.get('width')),
+                'height': int_or_none(f.get('height')),
+                'fps': int_or_none(f.get('fps')),
+                'tbr': int_or_none(f.get('bitrate')),
+            })
+        m3u8_url = config_files.get('hls', {}).get('url')
         if m3u8_url:
             m3u8_formats = self._extract_m3u8_formats(
                 m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False)
             if m3u8_formats:
                 formats.extend(m3u8_formats)
-        for key in ('other', 'sd', 'hd'):
-            formats += files[key]
-        self._sort_formats(formats)
+        # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
+        # at the same time without actual units specified. This lead to wrong sorting.
+        self._sort_formats(formats, field_preference=('height', 'width', 'fps', 'format_id'))
 
         subtitles = {}
         text_tracks = config['request'].get('text_tracks')
@@ -488,21 +477,20 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
         token, vuid = self._extract_xsrft_and_vuid(webpage)
         fields['token'] = token
         fields['password'] = password
-        post = urlencode_postdata(fields)
+        post = urlencode_postdata(encode_dict(fields))
         password_path = self._search_regex(
             r'action="([^"]+)"', login_form, 'password URL')
         password_url = compat_urlparse.urljoin(page_url, password_path)
         password_request = compat_urllib_request.Request(password_url, post)
         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
-        password_request.add_header('Cookie', 'vuid=%s' % vuid)
-        self._set_cookie('vimeo.com', 'xsrft', token)
+        self._set_vimeo_cookie('vuid', vuid)
+        self._set_vimeo_cookie('xsrft', token)
 
         return self._download_webpage(
             password_request, list_id,
             'Verifying the password', 'Wrong password')
 
-    def _extract_videos(self, list_id, base_url):
-        video_ids = []
+    def _title_and_entries(self, list_id, base_url):
         for pagenum in itertools.count(1):
             page_url = self._page_url(base_url, pagenum)
             webpage = self._download_webpage(
@@ -511,18 +499,18 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
 
             if pagenum == 1:
                 webpage = self._login_list_password(page_url, list_id, webpage)
+                yield self._extract_list_title(webpage)
+
+            for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
+                yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 
-            video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
                 break
 
-        entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
-                   for video_id in video_ids]
-        return {'_type': 'playlist',
-                'id': list_id,
-                'title': self._extract_list_title(webpage),
-                'entries': entries,
-                }
+    def _extract_videos(self, list_id, base_url):
+        title_and_entries = self._title_and_entries(list_id, base_url)
+        list_title = next(title_and_entries)
+        return self.playlist_result(title_and_entries, list_id, list_title)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -583,7 +571,7 @@ class VimeoAlbumIE(VimeoChannelIE):
 
 class VimeoGroupsIE(VimeoAlbumIE):
     IE_NAME = 'vimeo:group'
-    _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)'
+    _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
     _TESTS = [{
         'url': 'https://vimeo.com/groups/rolexawards',
         'info_dict': {

youtube_dl/extractor/vk.py

@@ -281,9 +281,13 @@ class VKIE(InfoExtractor):
             mobj.group(1) + ' ' + mobj.group(2)
             upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
 
-        view_count = str_to_int(self._search_regex(
-            r'"mv_views_count_number"[^>]*>([\d,.]+) views<',
-            info_page, 'view count', fatal=False))
+        view_count = None
+        views = self._html_search_regex(
+            r'"mv_views_count_number"[^>]*>(.+?\bviews?)<',
+            info_page, 'view count', fatal=False)
+        if views:
+            view_count = str_to_int(self._search_regex(
+                r'([\d,.]+)', views, 'view count', fatal=False))
 
         formats = [{
             'format_id': k,

youtube_dl/extractor/wsj.py

@@ -84,6 +84,5 @@ class WSJIE(InfoExtractor):
             'duration': duration,
             'upload_date': upload_date,
             'title': title,
-            'formats': formats,
             'categories': categories,
         }

youtube_dl/extractor/xfileshare.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -15,11 +15,11 @@ from ..utils import (
 )
 
 
-class GorillaVidIE(InfoExtractor):
-    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net and filehoot.com'
+class XFileShareIE(InfoExtractor):
+    IE_DESC = 'XFileShare based sites: GorillaVid.in, daclips.in, movpod.in, fastvideo.in, realvid.net, filehoot.com and vidto.me'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
-            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com))/
+            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net|filehoot\.com|vidto\.me))/
         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
     '''
 
@@ -76,6 +76,13 @@ class GorillaVidIE(InfoExtractor):
             'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
             'thumbnail': 're:http://.*\.jpg',
         }
+    }, {
+        'url': 'http://vidto.me/ku5glz52nqe1.html',
+        'info_dict': {
+            'id': 'ku5glz52nqe1',
+            'ext': 'mp4',
+            'title': 'test'
+        }
     }]
 
     def _real_extract(self, url):
@@ -104,13 +111,18 @@ class GorillaVidIE(InfoExtractor):
 
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
-        title = self._search_regex(
-            [r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'>Watch (.+) '],
-            webpage, 'title', default=None) or self._og_search_title(webpage)
+        title = (self._search_regex(
+            [r'style="z-index: [0-9]+;">([^<]+)</span>',
+             r'<td nowrap>([^<]+)</td>',
+             r'>Watch (.+) ',
+             r'<h2 class="video-page-head">([^<]+)</h2>'],
+            webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
         video_url = self._search_regex(
-            r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
+            [r'file\s*:\s*["\'](http[^"\']+)["\'],',
+             r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
+            webpage, 'file url')
         thumbnail = self._search_regex(
-            r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
+            r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 
         formats = [{
             'format_id': 'sd',

youtube_dl/extractor/youtube.py

@@ -224,6 +224,17 @@ class YoutubePlaylistBaseInfoExtractor(InfoExtractor):
         return zip(ids_in_page, titles_in_page)
 
 
+class YoutubePlaylistsBaseInfoExtractor(InfoExtractor):
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        entries = [
+            self.url_result(compat_urlparse.urljoin(url, playlist), 'YoutubePlaylist')
+            for playlist in re.findall(r'href="(/playlist\?list=.+?)"', webpage)]
+        title = self._og_search_title(webpage, fatal=False)
+        return self.playlist_result(entries, playlist_id, title)
+
+
 class YoutubeIE(YoutubeBaseInfoExtractor):
     IE_DESC = 'YouTube.com'
     _VALID_URL = r"""(?x)^
@@ -703,7 +714,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _extract_signature_function(self, video_id, player_url, example_sig):
         id_m = re.match(
-            r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?)?\.(?P<ext>[a-z]+)$',
+            r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
             player_url)
         if not id_m:
             raise ExtractorError('Cannot identify player %r' % player_url)
@@ -1107,6 +1118,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     if not video_info:
                         video_info = get_video_info
                     if 'token' in get_video_info:
+                        # Different get_video_info requests may report different results, e.g.
+                        # some may report video unavailability, but some may serve it without
+                        # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
+                        # the original webpage as well as el=info and el=embedded get_video_info
+                        # requests report video unavailability due to geo restriction while
+                        # el=detailpage succeeds and returns valid data). This is probably
+                        # due to YouTube measures against IP ranges of hosting providers.
+                        # Working around by preferring the first succeeded video_info containing
+                        # the token if no such video_info yet was found.
+                        if 'token' not in video_info:
+                            video_info = get_video_info
                         break
         if 'token' not in video_info:
             if 'reason' in video_info:
@@ -1332,7 +1354,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                                 player_desc = 'flash player %s' % player_version
                             else:
                                 player_version = self._search_regex(
-                                    r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
+                                    [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
                                     player_url,
                                     'html5 player', fatal=False)
                                 player_desc = 'html5 player %s' % player_version
@@ -1604,7 +1626,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtract
                 self.report_warning('Youtube gives an alert message: ' + match)
 
         playlist_title = self._html_search_regex(
-            r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
+            r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
             page, 'title')
 
         return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title)
@@ -1731,6 +1753,21 @@ class YoutubeUserIE(YoutubeChannelIE):
             return super(YoutubeUserIE, cls).suitable(url)
 
 
+class YoutubeUserPlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
+    IE_DESC = 'YouTube.com user playlists'
+    _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/user/(?P<id>[^/]+)/playlists'
+    IE_NAME = 'youtube:user:playlists'
+
+    _TEST = {
+        'url': 'http://www.youtube.com/user/ThirstForScience/playlists',
+        'playlist_mincount': 4,
+        'info_dict': {
+            'id': 'ThirstForScience',
+            'title': 'Thirst for Science',
+        },
+    }
+
+
 class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
     IE_DESC = 'YouTube.com searches'
     # there doesn't appear to be a real limit, for example if you search for
@@ -1826,7 +1863,7 @@ class YoutubeSearchURLIE(InfoExtractor):
         }
 
 
-class YoutubeShowIE(InfoExtractor):
+class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
     IE_DESC = 'YouTube.com (multi-season) shows'
     _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)'
     IE_NAME = 'youtube:show'
@@ -1840,26 +1877,9 @@ class YoutubeShowIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
-        webpage = self._download_webpage(
-            'https://www.youtube.com/show/%s/playlists' % playlist_id, playlist_id, 'Downloading show webpage')
-        # There's one playlist for each season of the show
-        m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage))
-        self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons)))
-        entries = [
-            self.url_result(
-                'https://www.youtube.com' + season.group(1), 'YoutubePlaylist')
-            for season in m_seasons
-        ]
-        title = self._og_search_title(webpage, fatal=False)
-
-        return {
-            '_type': 'playlist',
-            'id': playlist_id,
-            'title': title,
-            'entries': entries,
-        }
+        playlist_id = self._match_id(url)
+        return super(YoutubeShowIE, self)._real_extract(
+            'https://www.youtube.com/show/%s/playlists' % playlist_id)
 
 
 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):

youtube_dl/jsinterp.py

@@ -232,10 +232,10 @@ class JSInterpreter(object):
     def extract_function(self, funcname):
         func_m = re.search(
             r'''(?x)
-                (?:function\s+%s|[{;]%s\s*=\s*function)\s*
+                (?:function\s+%s|[{;]%s\s*=\s*function|var\s+%s\s*=\s*function)\s*
                 \((?P<args>[^)]*)\)\s*
                 \{(?P<code>[^}]+)\}''' % (
-                re.escape(funcname), re.escape(funcname)),
+                re.escape(funcname), re.escape(funcname), re.escape(funcname)),
             self.code)
         if func_m is None:
             raise ExtractorError('Could not find JS function %r' % funcname)

youtube_dl/options.py

@@ -363,7 +363,7 @@ def parseOpts(overrideArguments=None):
     subtitles.add_option(
         '--write-auto-sub', '--write-automatic-sub',
         action='store_true', dest='writeautomaticsub', default=False,
-        help='Write automatic subtitle file (YouTube only)')
+        help='Write automatically generated subtitle file (YouTube only)')
     subtitles.add_option(
         '--all-subs',
         action='store_true', dest='allsubtitles', default=False,

youtube_dl/postprocessor/ffmpeg.py

@@ -272,7 +272,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
             return [], information
 
         try:
-            self._downloader.to_screen('[' + self.basename + '] Destination: ' + new_path)
+            self._downloader.to_screen('[ffmpeg] Destination: ' + new_path)
             self.run_ffmpeg(path, new_path, acodec, more_opts)
         except AudioConversionError as e:
             raise PostProcessingError(

youtube_dl/update.py

@@ -9,11 +9,8 @@ import subprocess
 import sys
 from zipimport import zipimporter
 
-from .compat import (
-    compat_str,
-    compat_urllib_request,
-)
-from .utils import make_HTTPS_handler
+from .compat import compat_str
+
 from .version import __version__
 
 
@@ -47,7 +44,7 @@ def rsa_verify(message, signature, key):
     return True
 
 
-def update_self(to_screen, verbose):
+def update_self(to_screen, verbose, opener):
     """Update the program file with the latest version from the repository"""
 
     UPDATE_URL = "https://rg3.github.io/youtube-dl/update/"
@@ -59,9 +56,6 @@ def update_self(to_screen, verbose):
         to_screen('It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.')
         return
 
-    https_handler = make_HTTPS_handler({})
-    opener = compat_urllib_request.build_opener(https_handler)
-
     # Check if there is a new version
     try:
         newversion = opener.open(VERSION_URL).read().decode('utf-8').strip()

youtube_dl/utils.py

@@ -396,10 +396,14 @@ def _htmlentity_transform(entity):
             numstr = '0%s' % numstr
         else:
             base = 10
-        return compat_chr(int(numstr, base))
+        # See https://github.com/rg3/youtube-dl/issues/7518
+        try:
+            return compat_chr(int(numstr, base))
+        except ValueError:
+            pass
 
     # Unknown entity in name, return its literal representation
-    return ('&%s;' % entity)
+    return '&%s;' % entity
 
 
 def unescapeHTML(s):
@@ -1664,7 +1668,9 @@ def urlencode_postdata(*args, **kargs):
 
 
 def encode_dict(d, encoding='utf-8'):
-    return dict((k.encode(encoding), v.encode(encoding)) for k, v in d.items())
+    def encode(v):
+        return v.encode(encoding) if isinstance(v, compat_basestring) else v
+    return dict((encode(k), encode(v)) for k, v in d.items())
 
 
 US_RATINGS = {

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2015.11.02'
+__version__ = '2015.11.21'