release 2017.04.15

In order not to break sorting when new formats appear

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.03.26*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.03.26**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.04.15*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.04.15**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2017.03.26
+[debug] youtube-dl version 2017.04.15
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

AUTHORS

@@ -210,3 +210,4 @@ Lars Vierbergen
 Juanjo Benages
 Xiao Di Guan
 Thomas Winant
+Daniel Twardowski

ChangeLog

@@ -1,3 +1,100 @@
+version 2017.04.15
+
+Extractors
+* [youku] Fix fileid extraction (#12741, #12743)
+
+
+version 2017.04.14
+
+Core
++ [downloader/hls] Add basic support for EXT-X-BYTERANGE tag (#10955)
++ [adobepass] Improve Comcast and Verison login code (#10803)
++ [adobepass] Add support for Verizon (#10803)
+
+Extractors
++ [aenetworks] Add support for specials (#12723)
++ [hbo] Extract HLS formats
++ [go90] Add support for go90.com (#10127)
++ [tv2hu] Add support for tv2.hu (#10509)
++ [generic] Exclude URLs with xml ext from valid video URLs (#10768, #11654)
+* [youtube] Improve HLS formats extraction
+* [afreecatv] Fix extraction for videos with different key layout (#12718)
+- [youtube] Remove explicit preference for audio-only and video-only formats in
+  order not to break sorting when new formats appear
+* [canalplus] Bypass geo restriction
+
+
+version 2017.04.11
+
+Extractors
+* [afreecatv] Fix extraction (#12706)
++ [generic] Add support for <object> YouTube embeds (#12637)
+* [bbccouk] Treat bitrate as audio+video bitrate in media selector
++ [bbccouk] Skip unrecognized formats in media selector (#12701)
++ [bbccouk] Add support for https protocol in media selector (#12701)
+* [curiositystream] Fix extraction (#12638)
+* [adn] Update subtitle decryption key
+* [chaturbate] Fix extraction (#12665, #12688, #12690)
+
+
+version 2017.04.09
+
+Extractors
++ [medici] Add support for medici.tv (#3406)
++ [rbmaradio] Add support for redbullradio.com URLs (#12687)
++ [npo:live] Add support for default URL (#12555)
+* [mixcloud:playlist] Fix title, description and view count extraction (#12582)
++ [thesun] Add suport for thesun.co.uk (#11298, #12674)
++ [ceskateleveize:porady] Add support for porady (#7411, #12645)
+* [ceskateleveize] Improve extraction and remove URL replacement hacks
++ [kaltura] Add support for iframe embeds (#12679)
+* [airmozilla] Fix extraction (#12670)
+* [wshh] Extract html5 entries and delegate to generic extractor (12676)
++ [raiplay] Extract subtitles
++ [xfileshare] Add support for vidlo.us (#12660)
++ [xfileshare] Add support for vidbom.com (#12661)
++ [aenetworks] Add more video URL regular expressions (#12657)
++ [odnoklassniki] Fix format sorting for 1080p quality
++ [rtl2] Add support for you.rtl2.de (#10257)
++ [vshare] Add support for vshare.io (#12278)
+
+
+version 2017.04.03
+
+Core
++ [extractor/common] Add censorship check for TransTelekom ISP
+* [extractor/common] Move censorship checks to a separate method
+
+Extractors
++ [discoveryvr] Add support for discoveryvr.com (#12578)
++ [tv5mondeplus] Add support for tv5mondeplus.com (#11386)
++ [periscope] Add support for pscp.tv URLs (#12618, #12625)
+
+
+version 2017.04.02
+
+Core
+* [YoutubeDL] Return early when extraction of url_transparent fails
+
+Extractors
+* [rai] Fix and improve extraction (#11790)
++ [vrv] Add support for series pages
+* [limelight] Improve extraction for audio only formats
+* [funimation] Fix extraction (#10696, #11773)
++ [xfileshare] Add support for vidabc.com (#12589)
++ [xfileshare] Improve extraction and extract hls formats
++ [crunchyroll] Pass geo verifcation proxy
++ [cwtv] Extract ISM formats
++ [tvplay] Bypass geo restriction
++ [vrv] Add support for vrv.co
++ [packtpub] Add support for packtpub.com (#12610)
++ [generic] Pass base_url to _parse_jwplayer_data
++ [adn] Add support for animedigitalnetwork.fr (#4866)
++ [allocine] Extract more metadata
+* [allocine] Fix extraction (#12592)
+* [openload] Fix extraction
+
+
 version 2017.03.26
 
 Core

README.md

@@ -181,10 +181,10 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
     -R, --retries RETRIES            Number of retries (default is 10), or
                                      "infinite".
     --fragment-retries RETRIES       Number of retries for a fragment (default
-                                     is 10), or "infinite" (DASH and hlsnative
-                                     only)
-    --skip-unavailable-fragments     Skip unavailable fragments (DASH and
-                                     hlsnative only)
+                                     is 10), or "infinite" (DASH, hlsnative and
+                                     ISM)
+    --skip-unavailable-fragments     Skip unavailable fragments (DASH, hlsnative
+                                     and ISM)
     --abort-on-unavailable-fragment  Abort downloading when some fragment is not
                                      available
     --buffer-size SIZE               Size of download buffer (e.g. 1024 or 16K)

docs/supportedsites.md

@@ -28,6 +28,7 @@
  - **acast**
  - **acast:channel**
  - **AddAnime**
+ - **ADN**: Anime Digital Network
  - **AdobeTV**
  - **AdobeTVChannel**
  - **AdobeTVShow**
@@ -126,7 +127,7 @@
  - **CamWithHer**
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
- - **Canvas**
+ - **Canvas**: canvas.be and een.be
  - **CarambaTV**
  - **CarambaTVPage**
  - **CartoonNetwork**
@@ -144,6 +145,7 @@
  - **CCTV**: 央视网
  - **CDA**
  - **CeskaTelevize**
+ - **CeskaTelevizePorady**
  - **channel9**: Channel 9
  - **CharlieRose**
  - **Chaturbate**
@@ -212,6 +214,7 @@
  - **DiscoveryGo**
  - **DiscoveryGoPlaylist**
  - **DiscoveryNetworksDe**
+ - **DiscoveryVR**
  - **Disney**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
@@ -305,6 +308,7 @@
  - **Globo**
  - **GloboArticle**
  - **Go**
+ - **Go90**
  - **GodTube**
  - **GodTV**
  - **Golem**
@@ -429,6 +433,7 @@
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
  - **Medialaan**
+ - **Medici**
  - **Meipai**: 美拍
  - **MelonVOD**
  - **META**
@@ -572,6 +577,8 @@
  - **orf:iptv**: iptv.ORF.at
  - **orf:oe1**: Radio Österreich 1
  - **orf:tvthek**: ORF TVthek
+ - **PacktPub**
+ - **PacktPubCourse**
  - **PandaTV**: 熊猫TV
  - **pandora.tv**: 판도라TV
  - **parliamentlive.tv**: UK parliament videos
@@ -629,7 +636,7 @@
  - **radiofrance**
  - **RadioJavan**
  - **Rai**
- - **RaiTV**
+ - **RaiPlay**
  - **RBMARadio**
  - **RDS**: RDS.ca
  - **RedBullTV**
@@ -654,7 +661,9 @@
  - **rte**: Raidió Teilifís Éireann TV
  - **rte:radio**: Raidió Teilifís Éireann radio
  - **rtl.nl**: rtl.nl and rtlxl.nl
- - **RTL2**
+ - **rtl2**
+ - **rtl2:you**
+ - **rtl2:you:series**
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
@@ -776,6 +785,7 @@
  - **TheScene**
  - **TheSixtyOne**
  - **TheStar**
+ - **TheSun**
  - **TheWeatherChannel**
  - **ThisAmericanLife**
  - **ThisAV**
@@ -809,9 +819,11 @@
  - **Tutv**
  - **tv.dfb.de**
  - **TV2**
+ - **tv2.hu**
  - **TV2Article**
  - **TV3**
  - **TV4**: tv4.se and tv4play.se
+ - **TV5MondePlus**: TV5MONDE+
  - **TVA**
  - **TVANouvelles**
  - **TVANouvellesArticle**
@@ -888,7 +900,7 @@
  - **vidme:user**
  - **vidme:user:likes**
  - **Vidzi**
- - **vier**
+ - **vier**: vier.be and vijf.be
  - **vier:videos**
  - **ViewLift**
  - **ViewLiftEmbed**
@@ -925,7 +937,10 @@
  - **Vporn**
  - **vpro**: npo.nl and ntr.nl
  - **Vrak**
- - **VRT**
+ - **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be
+ - **vrv**
+ - **vrv:series**
+ - **VShare**
  - **vube**: Vube.com
  - **VuClip**
  - **VVVVID**
@@ -953,7 +968,7 @@
  - **WSJ**: Wall Street Journal
  - **XBef**
  - **XboxClips**
- - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE
+ - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo
  - **XHamster**
  - **XHamsterEmbed**
  - **xiami:album**: 虾米音乐 - 专辑

test/test_download.py

@@ -151,7 +151,7 @@ def generator(test_case, tname):
             try_num = 1
             while True:
                 try:
-                    # We're not using .download here sine that is just a shim
+                    # We're not using .download here since that is just a shim
                     # for outside error handling, and returns the exit code
                     # instead of the result dict.
                     res_dict = ydl.extract_info(
@@ -199,7 +199,16 @@ def generator(test_case, tname):
                 self.assertEqual(
                     test_case['playlist_duration_sum'], got_duration)
 
-            for tc in test_cases:
+            # Generalize both playlists and single videos to unified format for
+            # simplicity
+            if 'entries' not in res_dict:
+                res_dict['entries'] = [res_dict]
+
+            for tc_num, tc in enumerate(test_cases):
+                tc_res_dict = res_dict['entries'][tc_num]
+                # First, check test cases' data against extracted data alone
+                expect_info_dict(self, tc_res_dict, tc.get('info_dict', {}))
+                # Now, check downloaded file consistency
                 tc_filename = get_tc_filename(tc)
                 if not test_case.get('params', {}).get('skip_download', False):
                     self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
@@ -217,13 +226,14 @@ def generator(test_case, tname):
                     if 'md5' in tc:
                         md5_for_file = _file_md5(tc_filename)
                         self.assertEqual(md5_for_file, tc['md5'])
+                # Finally, check test cases' data again but this time against
+                # extracted data from info JSON file written during processing
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
                 self.assertTrue(
                     os.path.exists(info_json_fn),
                     'Missing info file %s' % info_json_fn)
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
-
                 expect_info_dict(self, info_dict, tc.get('info_dict', {}))
         finally:
             try_rm_tcs_files()

test/test_subtitles.py

@@ -21,7 +21,7 @@ from youtube_dl.extractor import (
     NPOIE,
     ComedyCentralIE,
     NRKTVIE,
-    RaiTVIE,
+    RaiPlayIE,
     VikiIE,
     ThePlatformIE,
     ThePlatformFeedIE,
@@ -258,9 +258,9 @@ class TestNRKSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
 
 
-class TestRaiSubtitles(BaseTestSubtitles):
-    url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
-    IE = RaiTVIE
+class TestRaiPlaySubtitles(BaseTestSubtitles):
+    url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
+    IE = RaiPlayIE
 
     def test_allsubtitles(self):
         self.DL.params['writesubtitles'] = True

youtube_dl/YoutubeDL.py

@@ -837,6 +837,12 @@ class YoutubeDL(object):
                 ie_result['url'], ie_key=ie_result.get('ie_key'),
                 extra_info=extra_info, download=False, process=False)
 
+            # extract_info may return None when ignoreerrors is enabled and
+            # extraction failed with an error, don't crash and return early
+            # in this case
+            if not info:
+                return info
+
             force_properties = dict(
                 (k, v) for k, v in ie_result.items() if v is not None)
             for f in ('_type', 'url', 'ie_key'):
@@ -849,7 +855,7 @@ class YoutubeDL(object):
 
             return self.process_ie_result(
                 new_result, download=download, extra_info=extra_info)
-        elif result_type == 'playlist' or result_type == 'multi_video':
+        elif result_type in ('playlist', 'multi_video'):
             # We process each entry in the playlist
             playlist = ie_result.get('title') or ie_result.get('id')
             self.to_screen('[download] Downloading playlist: %s' % playlist)

youtube_dl/compat.py

@@ -2692,7 +2692,7 @@ else:
                 userhome = pwent.pw_dir
             userhome = userhome.rstrip('/')
             return (userhome + path[i:]) or '/'
-    elif compat_os_name == 'nt' or compat_os_name == 'ce':
+    elif compat_os_name in ('nt', 'ce'):
         def compat_expanduser(path):
             """Expand ~ and ~user constructs.
 

youtube_dl/downloader/hls.py

@@ -34,7 +34,7 @@ class HlsFD(FragmentFD):
     def can_download(manifest, info_dict):
         UNSUPPORTED_FEATURES = (
             r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
-            r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
+            # r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [2]
 
             # Live streams heuristic does not always work (e.g. geo restricted to Germany
             # http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
@@ -52,7 +52,9 @@ class HlsFD(FragmentFD):
             # 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
         )
         check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
-        check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest)
+        is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
+        check_results.append(can_decrypt_frag or not is_aes128_enc)
+        check_results.append(not (is_aes128_enc and r'#EXT-X-BYTERANGE' in manifest))
         check_results.append(not info_dict.get('is_live'))
         return all(check_results)
 
@@ -100,6 +102,7 @@ class HlsFD(FragmentFD):
         i = 0
         media_sequence = 0
         decrypt_info = {'METHOD': 'NONE'}
+        byte_range = {}
         frags_filenames = []
         for line in s.splitlines():
             line = line.strip()
@@ -114,11 +117,14 @@ class HlsFD(FragmentFD):
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
                     count = 0
+                    headers = info_dict.get('http_headers', {})
+                    if byte_range:
+                        headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'])
                     while count <= fragment_retries:
                         try:
                             success = ctx['dl'].download(frag_filename, {
                                 'url': frag_url,
-                                'http_headers': info_dict.get('http_headers'),
+                                'http_headers': headers,
                             })
                             if not success:
                                 return False
@@ -167,6 +173,13 @@ class HlsFD(FragmentFD):
                         decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
                 elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
                     media_sequence = int(line[22:])
+                elif line.startswith('#EXT-X-BYTERANGE'):
+                    splitted_byte_range = line[17:].split('@')
+                    sub_range_start = int(splitted_byte_range[1]) if len(splitted_byte_range) == 2 else byte_range['end']
+                    byte_range = {
+                        'start': sub_range_start,
+                        'end': sub_range_start + int(splitted_byte_range[0]),
+                    }
 
         self._finish_frag_download(ctx)
 

youtube_dl/downloader/rtmp.py

@@ -169,7 +169,7 @@ class RtmpFD(FileDownloader):
             self.report_error('[rtmpdump] Could not connect to RTMP server.')
             return False
 
-        while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
+        while retval in (RD_INCOMPLETE, RD_FAILED) and not test and not live:
             prevsize = os.path.getsize(encodeFilename(tmpfilename))
             self.to_screen('[rtmpdump] %s bytes' % prevsize)
             time.sleep(5.0)  # This seems to be needed

youtube_dl/extractor/adn.py

@@ -0,0 +1,136 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+import json
+import os
+
+from .common import InfoExtractor
+from ..aes import aes_cbc_decrypt
+from ..compat import compat_ord
+from ..utils import (
+    bytes_to_intlist,
+    ExtractorError,
+    float_or_none,
+    intlist_to_bytes,
+    srt_subtitles_timecode,
+    strip_or_none,
+)
+
+
+class ADNIE(InfoExtractor):
+    IE_DESC = 'Anime Digital Network'
+    _VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
+        'md5': 'e497370d847fd79d9d4c74be55575c7a',
+        'info_dict': {
+            'id': '7778',
+            'ext': 'mp4',
+            'title': 'Blue Exorcist - Kyôto Saga - Épisode 1',
+            'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
+        }
+    }
+
+    def _get_subtitles(self, sub_path, video_id):
+        if not sub_path:
+            return None
+
+        enc_subtitles = self._download_webpage(
+            'http://animedigitalnetwork.fr/' + sub_path,
+            video_id, fatal=False)
+        if not enc_subtitles:
+            return None
+
+        # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
+        dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
+            bytes_to_intlist(base64.b64decode(enc_subtitles[24:])),
+            bytes_to_intlist(b'\nd\xaf\xd2J\xd0\xfc\xe1\xfc\xdf\xb61\xe8\xe1\xf0\xcc'),
+            bytes_to_intlist(base64.b64decode(enc_subtitles[:24]))
+        ))
+        subtitles_json = self._parse_json(
+            dec_subtitles[:-compat_ord(dec_subtitles[-1])],
+            None, fatal=False)
+        if not subtitles_json:
+            return None
+
+        subtitles = {}
+        for sub_lang, sub in subtitles_json.items():
+            srt = ''
+            for num, current in enumerate(sub):
+                start, end, text = (
+                    float_or_none(current.get('startTime')),
+                    float_or_none(current.get('endTime')),
+                    current.get('text'))
+                if start is None or end is None or text is None:
+                    continue
+                srt += os.linesep.join(
+                    (
+                        '%d' % num,
+                        '%s --> %s' % (
+                            srt_subtitles_timecode(start),
+                            srt_subtitles_timecode(end)),
+                        text,
+                        os.linesep,
+                    ))
+
+            if sub_lang == 'vostf':
+                sub_lang = 'fr'
+            subtitles.setdefault(sub_lang, []).extend([{
+                'ext': 'json',
+                'data': json.dumps(sub),
+            }, {
+                'ext': 'srt',
+                'data': srt,
+            }])
+        return subtitles
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        player_config = self._parse_json(self._search_regex(
+            r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id)
+
+        video_info = {}
+        video_info_str = self._search_regex(
+            r'videoInfo\s*=\s*({.+});', webpage,
+            'video info', fatal=False)
+        if video_info_str:
+            video_info = self._parse_json(
+                video_info_str, video_id, fatal=False) or {}
+
+        options = player_config.get('options') or {}
+        metas = options.get('metas') or {}
+        title = metas.get('title') or video_info['title']
+        links = player_config.get('links') or {}
+
+        formats = []
+        for format_id, qualities in links.items():
+            for load_balancer_url in qualities.values():
+                load_balancer_data = self._download_json(
+                    load_balancer_url, video_id, fatal=False) or {}
+                m3u8_url = load_balancer_data.get('location')
+                if not m3u8_url:
+                    continue
+                m3u8_formats = self._extract_m3u8_formats(
+                    m3u8_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id=format_id, fatal=False)
+                if format_id == 'vf':
+                    for f in m3u8_formats:
+                        f['language'] = 'fr'
+                formats.extend(m3u8_formats)
+        error = options.get('error')
+        if not formats and error:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
+            'thumbnail': video_info.get('image'),
+            'formats': formats,
+            'subtitles': self.extract_subtitles(player_config.get('subtitles'), video_id),
+            'episode': metas.get('subtitle') or video_info.get('videoTitle'),
+            'series': video_info.get('playlistTitle'),
+        }

youtube_dl/extractor/adobepass.py

@@ -41,6 +41,11 @@ MSO_INFO = {
         'username_field': 'IDToken1',
         'password_field': 'IDToken2',
     },
+    'Verizon': {
+        'name': 'Verizon FiOS',
+        'username_field': 'IDToken1',
+        'password_field': 'IDToken2',
+    },
     'thr030': {
         'name': '3 Rivers Communications'
     },
@@ -1384,40 +1389,72 @@ class AdobePassIE(InfoExtractor):
                     # Comcast page flow varies by video site and whether you
                     # are on Comcast's network.
                     provider_redirect_page, urlh = provider_redirect_page_res
-                    # Check for Comcast auto login
                     if 'automatically signing you in' in provider_redirect_page:
                         oauth_redirect_url = self._html_search_regex(
                             r'window\.location\s*=\s*[\'"]([^\'"]+)',
                             provider_redirect_page, 'oauth redirect')
-                        # Just need to process the request. No useful data comes back
                         self._download_webpage(
                             oauth_redirect_url, video_id, 'Confirming auto login')
                     else:
                         if '<form name="signin"' in provider_redirect_page:
-                            # already have the form, just fill it
                             provider_login_page_res = provider_redirect_page_res
                         elif 'http-equiv="refresh"' in provider_redirect_page:
-                            # redirects to the login page
                             oauth_redirect_url = self._html_search_regex(
                                 r'content="0;\s*url=([^\'"]+)',
                                 provider_redirect_page, 'meta refresh redirect')
                             provider_login_page_res = self._download_webpage_handle(
-                                oauth_redirect_url,
-                                video_id, 'Downloading Provider Login Page')
+                                oauth_redirect_url, video_id,
+                                'Downloading Provider Login Page')
                         else:
                             provider_login_page_res = post_form(
-                                provider_redirect_page_res, 'Downloading Provider Login Page')
+                                provider_redirect_page_res,
+                                'Downloading Provider Login Page')
 
-                        mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', {
-                            mso_info.get('username_field', 'username'): username,
-                            mso_info.get('password_field', 'password'): password,
-                        })
+                        mvpd_confirm_page_res = post_form(
+                            provider_login_page_res, 'Logging in', {
+                                mso_info['username_field']: username,
+                                mso_info['password_field']: password,
+                            })
                         mvpd_confirm_page, urlh = mvpd_confirm_page_res
                         if '<button class="submit" value="Resume">Resume</button>' in mvpd_confirm_page:
                             post_form(mvpd_confirm_page_res, 'Confirming Login')
-
+                elif mso_id == 'Verizon':
+                    # In general, if you're connecting from a Verizon-assigned IP,
+                    # you will not actually pass your credentials.
+                    provider_redirect_page, urlh = provider_redirect_page_res
+                    if 'Please wait ...' in provider_redirect_page:
+                        saml_redirect_url = self._html_search_regex(
+                            r'self\.parent\.location=(["\'])(?P<url>.+?)\1',
+                            provider_redirect_page,
+                            'SAML Redirect URL', group='url')
+                        saml_login_page = self._download_webpage(
+                            saml_redirect_url, video_id,
+                            'Downloading SAML Login Page')
+                    else:
+                        saml_login_page_res = post_form(
+                            provider_redirect_page_res, 'Logging in', {
+                                mso_info['username_field']: username,
+                                mso_info['password_field']: password,
+                            })
+                        saml_login_page, urlh = saml_login_page_res
+                        if 'Please try again.' in saml_login_page:
+                            raise ExtractorError(
+                                'We\'re sorry, but either the User ID or Password entered is not correct.')
+                    saml_login_url = self._search_regex(
+                        r'xmlHttp\.open\("POST"\s*,\s*(["\'])(?P<url>.+?)\1',
+                        saml_login_page, 'SAML Login URL', group='url')
+                    saml_response_json = self._download_json(
+                        saml_login_url, video_id, 'Downloading SAML Response',
+                        headers={'Content-Type': 'text/xml'})
+                    self._download_webpage(
+                        saml_response_json['targetValue'], video_id,
+                        'Confirming Login', data=urlencode_postdata({
+                            'SAMLResponse': saml_response_json['SAMLResponse'],
+                            'RelayState': saml_response_json['RelayState']
+                        }), headers={
+                            'Content-Type': 'application/x-www-form-urlencoded'
+                        })
                 else:
-                    # Normal, non-Comcast flow
                     provider_login_page_res = post_form(
                         provider_redirect_page_res, 'Downloading Provider Login Page')
                     mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', {

youtube_dl/extractor/aenetworks.py

@@ -23,7 +23,19 @@ class AENetworksBaseIE(ThePlatformIE):
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'
     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime|lifetimemovieclub)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?P<domain>
+                            (?:history|aetv|mylifetime|lifetimemovieclub)\.com|
+                            fyi\.tv
+                        )/
+                        (?:
+                            shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
+                            movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
+                            specials/(?P<special_display_id>[^/]+)/full-special
+                        )
+                    '''
     _TESTS = [{
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
         'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
@@ -65,6 +77,9 @@ class AENetworksIE(AENetworksBaseIE):
     }, {
         'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
         'only_matching': True
+    }, {
+        'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
+        'only_matching': True
     }]
     _DOMAIN_TO_REQUESTOR_ID = {
         'history.com': 'HISTORY',
@@ -75,8 +90,8 @@ class AENetworksIE(AENetworksBaseIE):
     }
 
     def _real_extract(self, url):
-        domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
-        display_id = show_path or movie_display_id
+        domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups()
+        display_id = show_path or movie_display_id or special_display_id
         webpage = self._download_webpage(url, display_id)
         if show_path:
             url_parts = show_path.split('/')
@@ -107,7 +122,10 @@ class AENetworksIE(AENetworksBaseIE):
         }
         video_id = self._html_search_meta('aetn:VideoID', webpage)
         media_url = self._search_regex(
-            r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
+            [r"media_url\s*=\s*'(?P<url>[^']+)'",
+             r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
+             r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
+            webpage, 'video url', group='url')
         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
             r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
         info = self._parse_theplatform_metadata(theplatform_metadata)

youtube_dl/extractor/afreecatv.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_xpath
 from ..utils import (
+    determine_ext,
     ExtractorError,
     int_or_none,
     xpath_text,
@@ -72,13 +73,70 @@ class AfreecaTVIE(InfoExtractor):
         'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
         'info_dict': {
             'id': '18650793',
-            'ext': 'flv',
+            'ext': 'mp4',
+            'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': '윈아디',
             'uploader_id': 'badkids',
-            'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
+            'duration': 107,
         },
         'params': {
-            'skip_download': True,  # requires rtmpdump
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
+        'info_dict': {
+            'id': '10481652',
+            'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
+            'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
+            'uploader': 'dailyapril',
+            'uploader_id': 'dailyapril',
+            'duration': 6492,
+        },
+        'playlist_count': 2,
+        'playlist': [{
+            'md5': 'd8b7c174568da61d774ef0203159bf97',
+            'info_dict': {
+                'id': '20160502_c4c62b9d_174361386_1',
+                'ext': 'mp4',
+                'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
+                'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
+                'uploader': 'dailyapril',
+                'uploader_id': 'dailyapril',
+                'upload_date': '20160502',
+                'duration': 3601,
+            },
+        }, {
+            'md5': '58f2ce7f6044e34439ab2d50612ab02b',
+            'info_dict': {
+                'id': '20160502_39e739bb_174361386_2',
+                'ext': 'mp4',
+                'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
+                'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
+                'uploader': 'dailyapril',
+                'uploader_id': 'dailyapril',
+                'upload_date': '20160502',
+                'duration': 2891,
+            },
+        }],
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # non standard key
+        'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
+        'info_dict': {
+            'id': '20170411_BE689A0E_190960999_1_2_h',
+            'ext': 'mp4',
+            'title': '혼자사는여자집',
+            'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
+            'uploader': '♥이슬이',
+            'uploader_id': 'dasl8121',
+            'upload_date': '20170411',
+            'duration': 213,
+        },
+        'params': {
+            'skip_download': True,
         },
     }, {
         'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
@@ -94,7 +152,7 @@ class AfreecaTVIE(InfoExtractor):
         m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
         if m:
             video_key['upload_date'] = m.group('upload_date')
-            video_key['part'] = m.group('part')
+            video_key['part'] = int(m.group('part'))
         return video_key
 
     def _real_extract(self, url):
@@ -109,23 +167,65 @@ class AfreecaTVIE(InfoExtractor):
             raise ExtractorError('Specified AfreecaTV video does not exist',
                                  expected=True)
 
-        video_url_raw = video_element.text
-
-        app, playpath = video_url_raw.split('mp4:')
+        video_url = video_element.text.strip()
 
         title = xpath_text(video_xml, './track/title', 'title', fatal=True)
+
         uploader = xpath_text(video_xml, './track/nickname', 'uploader')
         uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
-        duration = int_or_none(xpath_text(video_xml, './track/duration',
-                                          'duration'))
+        duration = int_or_none(xpath_text(
+            video_xml, './track/duration', 'duration'))
         thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
 
-        return {
+        common_entry = {
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'thumbnail': thumbnail,
+        }
+
+        info = common_entry.copy()
+        info.update({
+            'id': video_id,
+            'title': title,
+            'duration': duration,
+        })
+
+        if not video_url:
+            entries = []
+            file_elements = video_element.findall(compat_xpath('./file'))
+            one = len(file_elements) == 1
+            for file_num, file_element in enumerate(file_elements, start=1):
+                file_url = file_element.text
+                if not file_url:
+                    continue
+                key = file_element.get('key', '')
+                upload_date = self._search_regex(
+                    r'^(\d{8})_', key, 'upload date', default=None)
+                file_duration = int_or_none(file_element.get('duration'))
+                format_id = key if key else '%s_%s' % (video_id, file_num)
+                formats = self._extract_m3u8_formats(
+                    file_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls',
+                    note='Downloading part %d m3u8 information' % file_num)
+                title = title if one else '%s (part %d)' % (title, file_num)
+                file_info = common_entry.copy()
+                file_info.update({
+                    'id': format_id,
+                    'title': title,
+                    'upload_date': upload_date,
+                    'duration': file_duration,
+                    'formats': formats,
+                })
+                entries.append(file_info)
+            entries_info = info.copy()
+            entries_info.update({
+                '_type': 'multi_video',
+                'entries': entries,
+            })
+            return entries_info
+
+        info = {
             'id': video_id,
-            'url': app,
-            'ext': 'flv',
-            'play_path': 'mp4:' + playpath,
-            'rtmp_live': True,  # downloading won't end without this
             'title': title,
             'uploader': uploader,
             'uploader_id': uploader_id,
@@ -133,6 +233,21 @@ class AfreecaTVIE(InfoExtractor):
             'thumbnail': thumbnail,
         }
 
+        if determine_ext(video_url) == 'm3u8':
+            info['formats'] = self._extract_m3u8_formats(
+                video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls')
+        else:
+            app, playpath = video_url.split('mp4:')
+            info.update({
+                'url': app,
+                'ext': 'flv',
+                'play_path': 'mp4:' + playpath,
+                'rtmp_live': True,  # downloading won't end without this
+            })
+
+        return info
+
 
 class AfreecaTVGlobalIE(AfreecaTVIE):
     IE_NAME = 'afreecatv:global'

youtube_dl/extractor/airmozilla.py

@@ -15,12 +15,12 @@ class AirMozillaIE(InfoExtractor):
     _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
     _TEST = {
         'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
-        'md5': '2e3e7486ba5d180e829d453875b9b8bf',
+        'md5': '8d02f53ee39cf006009180e21df1f3ba',
         'info_dict': {
             'id': '6x4q2w',
             'ext': 'mp4',
             'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
-            'thumbnail': r're:https?://vid\.ly/(?P<id>[0-9a-z-]+)/poster',
+            'thumbnail': r're:https?://.*/poster\.jpg',
             'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
             'timestamp': 1422487800,
             'upload_date': '20150128',
@@ -34,21 +34,13 @@ class AirMozillaIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
+        video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')
 
         embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
-        jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
-        metadata = self._parse_json(jwconfig, video_id)
-
-        formats = [{
-            'url': source['file'],
-            'ext': source['type'],
-            'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
-            'format': source['label'],
-            'height': int(source['label'].rstrip('p')),
-        } for source in metadata['playlist'][0]['sources']]
-        self._sort_formats(formats)
+        jwconfig = self._parse_json(self._search_regex(
+            r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
 
+        info_dict = self._parse_jwplayer_data(jwconfig, video_id)
         view_count = int_or_none(self._html_search_regex(
             r'Views since archived: ([0-9]+)',
             webpage, 'view count', fatal=False))
@@ -58,17 +50,17 @@ class AirMozillaIE(InfoExtractor):
             r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
             webpage, 'duration', fatal=False))
 
-        return {
+        info_dict.update({
             'id': video_id,
             'title': self._og_search_title(webpage),
-            'formats': formats,
             'url': self._og_search_url(webpage),
             'display_id': display_id,
-            'thumbnail': metadata['playlist'][0].get('image'),
             'description': self._og_search_description(webpage),
             'timestamp': timestamp,
             'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
             'duration': duration,
             'view_count': view_count,
             'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
-        }
+        })
+
+        return info_dict

youtube_dl/extractor/allocine.py

@@ -2,9 +2,13 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
-    remove_end,
+    int_or_none,
     qualities,
+    remove_end,
+    try_get,
+    unified_timestamp,
     url_basename,
 )
 
@@ -22,6 +26,10 @@ class AllocineIE(InfoExtractor):
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
             'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
             'thumbnail': r're:http://.*\.jpg',
+            'duration': 39,
+            'timestamp': 1404273600,
+            'upload_date': '20140702',
+            'view_count': int,
         },
     }, {
         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
@@ -33,6 +41,10 @@ class AllocineIE(InfoExtractor):
             'title': 'Planes 2 Bande-annonce VF',
             'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
             'thumbnail': r're:http://.*\.jpg',
+            'duration': 69,
+            'timestamp': 1385659800,
+            'upload_date': '20131128',
+            'view_count': int,
         },
     }, {
         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
@@ -44,6 +56,10 @@ class AllocineIE(InfoExtractor):
             'title': 'Dragons 2 - Bande annonce finale VF',
             'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
             'thumbnail': r're:http://.*\.jpg',
+            'duration': 144,
+            'timestamp': 1397589900,
+            'upload_date': '20140415',
+            'view_count': int,
         },
     }, {
         'url': 'http://www.allocine.fr/video/video-19550147/',
@@ -69,34 +85,37 @@ class AllocineIE(InfoExtractor):
             r'data-model="([^"]+)"', webpage, 'data model', default=None)
         if model:
             model_data = self._parse_json(model, display_id)
-
-            for video_url in model_data['sources'].values():
+            video = model_data['videos'][0]
+            title = video['title']
+            for video_url in video['sources'].values():
                 video_id, format_id = url_basename(video_url).split('_')[:2]
                 formats.append({
                     'format_id': format_id,
                     'quality': quality(format_id),
                     'url': video_url,
                 })
-
-            title = model_data['title']
+            duration = int_or_none(video.get('duration'))
+            view_count = int_or_none(video.get('view_count'))
+            timestamp = unified_timestamp(try_get(
+                video, lambda x: x['added_at']['date'], compat_str))
         else:
             video_id = display_id
             media_data = self._download_json(
                 'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
+            title = remove_end(
+                self._html_search_regex(
+                    r'(?s)<title>(.+?)</title>', webpage, 'title').strip(),
+                ' - AlloCiné')
             for key, value in media_data['video'].items():
                 if not key.endswith('Path'):
                     continue
-
                 format_id = key[:-len('Path')]
                 formats.append({
                     'format_id': format_id,
                     'quality': quality(format_id),
                     'url': value,
                 })
-
-            title = remove_end(self._html_search_regex(
-                r'(?s)<title>(.+?)</title>', webpage, 'title'
-            ).strip(), ' - AlloCiné')
+            duration, view_count, timestamp = [None] * 3
 
         self._sort_formats(formats)
 
@@ -104,7 +123,10 @@ class AllocineIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'formats': formats,
             'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'formats': formats,
         }

youtube_dl/extractor/bbc.py

@@ -361,7 +361,7 @@ class BBCCoUkIE(InfoExtractor):
                             fmt.update({
                                 'width': width,
                                 'height': height,
-                                'vbr': bitrate,
+                                'tbr': bitrate,
                                 'vcodec': encoding,
                             })
                         else:
@@ -370,7 +370,7 @@ class BBCCoUkIE(InfoExtractor):
                                 'acodec': encoding,
                                 'vcodec': 'none',
                             })
-                        if protocol == 'http':
+                        if protocol in ('http', 'https'):
                             # Direct link
                             fmt.update({
                                 'url': href,
@@ -389,6 +389,8 @@ class BBCCoUkIE(InfoExtractor):
                                 'rtmp_live': False,
                                 'ext': 'flv',
                             })
+                        else:
+                            continue
                         formats.append(fmt)
             elif kind == 'captions':
                 subtitles = self.extract_subtitles(media, programme_id)
@@ -407,7 +409,7 @@ class BBCCoUkIE(InfoExtractor):
                 description = smp_config['summary']
                 for item in smp_config['items']:
                     kind = item['kind']
-                    if kind != 'programme' and kind != 'radioProgramme':
+                    if kind not in ('programme', 'radioProgramme'):
                         continue
                     programme_id = item.get('vpid')
                     duration = int_or_none(item.get('duration'))
@@ -448,7 +450,7 @@ class BBCCoUkIE(InfoExtractor):
 
         for item in self._extract_items(playlist):
             kind = item.get('kind')
-            if kind != 'programme' and kind != 'radioProgramme':
+            if kind not in ('programme', 'radioProgramme'):
                 continue
             title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
             description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)

youtube_dl/extractor/canalplus.py

@@ -45,6 +45,9 @@ class CanalplusIE(InfoExtractor):
         'itele': 'itele',
     }
 
+    # Only works for direct mp4 URLs
+    _GEO_COUNTRIES = ['FR']
+
     _TESTS = [{
         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
         'info_dict': {
@@ -56,6 +59,7 @@ class CanalplusIE(InfoExtractor):
             'upload_date': '20160702',
         },
     }, {
+        # geo restricted, bypassed
         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
         'info_dict': {
             'id': '1108190',
@@ -65,19 +69,20 @@ class CanalplusIE(InfoExtractor):
             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
             'upload_date': '20140724',
         },
-        'skip': 'Only works from France',
+        'expected_warnings': ['HTTP Error 403: Forbidden'],
     }, {
-        'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html',
-        'md5': '4b47b12b4ee43002626b97fad8fb1de5',
+        # geo restricted, bypassed
+        'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html?vid=1443684',
+        'md5': 'bb6f9f343296ab7ebd88c97b660ecf8d',
         'info_dict': {
-            'id': '1420213',
+            'id': '1443684',
             'display_id': 'pid6318-videos-integrales',
             'ext': 'mp4',
-            'title': 'TPMP ! Même le matin - Les 35H de Baba - 14/10/2016',
-            'description': 'md5:f96736c1b0ffaa96fd5b9e60ad871799',
-            'upload_date': '20161014',
+            'title': 'Guess my iep ! - TPMP - 07/04/2017',
+            'description': 'md5:6f005933f6e06760a9236d9b3b5f17fa',
+            'upload_date': '20170407',
         },
-        'skip': 'Only works from France',
+        'expected_warnings': ['HTTP Error 403: Forbidden'],
     }, {
         'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
         'info_dict': {
@@ -134,15 +139,15 @@ class CanalplusIE(InfoExtractor):
 
         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 
-        fmt_url = next(iter(media.get('VIDEOS')))
-        if '/geo' in fmt_url.lower():
-            response = self._request_webpage(
-                HEADRequest(fmt_url), video_id,
-                'Checking if the video is georestricted')
-            if '/blocage' in response.geturl():
-                raise ExtractorError(
-                    'The video is not available in your country',
-                    expected=True)
+        # _, fmt_url = next(iter(media['VIDEOS'].items()))
+        # if '/geo' in fmt_url.lower():
+        #     response = self._request_webpage(
+        #         HEADRequest(fmt_url), video_id,
+        #         'Checking if the video is georestricted')
+        #     if '/blocage' in response.geturl():
+        #         raise ExtractorError(
+        #             'The video is not available in your country',
+        #             expected=True)
 
         formats = []
         for format_id, format_url in media['VIDEOS'].items():

youtube_dl/extractor/canvas.py

@@ -7,6 +7,7 @@ from ..utils import float_or_none
 
 
 class CanvasIE(InfoExtractor):
+    IE_DESC = 'canvas.be and een.be'
     _VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',

youtube_dl/extractor/ceskatelevize.py

@@ -12,13 +12,14 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     sanitized_Request,
+    unescapeHTML,
     urlencode_postdata,
     USER_AGENTS,
 )
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
         'info_dict': {
@@ -62,40 +63,12 @@ class CeskaTelevizeIE(InfoExtractor):
         },
         'skip': 'Georestricted to Czech Republic',
     }, {
-        # video with 18+ caution trailer
-        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
-        'info_dict': {
-            'id': '215562210900007-bogotart',
-            'title': 'Queer: Bogotart',
-            'description': 'Alternativní průvodce současným queer světem',
-        },
-        'playlist': [{
-            'info_dict': {
-                'id': '61924494876844842',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Varování 18+)',
-                'duration': 10.2,
-            },
-        }, {
-            'info_dict': {
-                'id': '61924494877068022',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Queer)',
-                'thumbnail': r're:^https?://.*\.jpg',
-                'duration': 1558.3,
-            },
-        }],
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
+        'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
-
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
@@ -103,13 +76,28 @@ class CeskaTelevizeIE(InfoExtractor):
         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
-        typ = self._html_search_regex(
-            r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
-        episode_id = self._html_search_regex(
-            r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
+        type_ = None
+        episode_id = None
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'getPlaylistUrl\(\[({.+?})\]', webpage, 'playlist',
+                default='{}'), playlist_id)
+        if playlist:
+            type_ = playlist.get('type')
+            episode_id = playlist.get('id')
+
+        if not type_:
+            type_ = self._html_search_regex(
+                r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],',
+                webpage, 'type')
+        if not episode_id:
+            episode_id = self._html_search_regex(
+                r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],',
+                webpage, 'episode_id')
 
         data = {
-            'playlist[0][type]': typ,
+            'playlist[0][type]': type_,
             'playlist[0][id]': episode_id,
             'requestUrl': compat_urllib_parse_urlparse(url).path,
             'requestSource': 'iVysilani',
@@ -245,3 +233,47 @@ class CeskaTelevizeIE(InfoExtractor):
                     yield line
 
         return '\r\n'.join(_fix_subtitle(subtitles))
+
+
+class CeskaTelevizePoradyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
+    _TESTS = [{
+        # video with 18+ caution trailer
+        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
+        'info_dict': {
+            'id': '215562210900007-bogotart',
+            'title': 'Queer: Bogotart',
+            'description': 'Alternativní průvodce současným queer světem',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '61924494876844842',
+                'ext': 'mp4',
+                'title': 'Queer: Bogotart (Varování 18+)',
+                'duration': 10.2,
+            },
+        }, {
+            'info_dict': {
+                'id': '61924494877068022',
+                'ext': 'mp4',
+                'title': 'Queer: Bogotart (Queer)',
+                'thumbnail': r're:^https?://.*\.jpg',
+                'duration': 1558.3,
+            },
+        }],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        data_url = unescapeHTML(self._search_regex(
+            r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'iframe player url', group='url'))
+
+        return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())

youtube_dl/extractor/chaturbate.py

@@ -33,10 +33,17 @@ class ChaturbateIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer(
-            r'hlsSource(?P<id>.+?)\s*=\s*(?P<q>["\'])(?P<url>http.+?)(?P=q)', webpage)]
+        m3u8_urls = []
 
-        if not m3u8_formats:
+        for m in re.finditer(
+                r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage):
+            m3u8_fast_url, m3u8_no_fast_url = m.group('url'), m.group(
+                'url').replace('_fast', '')
+            for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url):
+                if m3u8_url not in m3u8_urls:
+                    m3u8_urls.append(m3u8_url)
+
+        if not m3u8_urls:
             error = self._search_regex(
                 [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
                  r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
@@ -50,7 +57,8 @@ class ChaturbateIE(InfoExtractor):
             raise ExtractorError('Unable to find stream URL')
 
         formats = []
-        for m3u8_id, m3u8_url in m3u8_formats:
+        for m3u8_url in m3u8_urls:
+            m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow'
             formats.extend(self._extract_m3u8_formats(
                 m3u8_url, video_id, ext='mp4',
                 # ffmpeg skips segments for fast m3u8

youtube_dl/extractor/common.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import base64
@@ -547,6 +548,34 @@ class InfoExtractor(object):
 
         return encoding
 
+    def __check_blocked(self, content):
+        first_block = content[:512]
+        if ('<title>Access to this site is blocked</title>' in content and
+                'Websense' in first_block):
+            msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
+            blocked_iframe = self._html_search_regex(
+                r'<iframe src="([^"]+)"', content,
+                'Websense information URL', default=None)
+            if blocked_iframe:
+                msg += ' Visit %s for more details' % blocked_iframe
+            raise ExtractorError(msg, expected=True)
+        if '<title>The URL you requested has been blocked</title>' in first_block:
+            msg = (
+                'Access to this webpage has been blocked by Indian censorship. '
+                'Use a VPN or proxy server (with --proxy) to route around it.')
+            block_msg = self._html_search_regex(
+                r'</h1><p>(.*?)</p>',
+                content, 'block message', default=None)
+            if block_msg:
+                msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
+            raise ExtractorError(msg, expected=True)
+        if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content and
+                'blocklist.rkn.gov.ru' in content):
+            raise ExtractorError(
+                'Access to this webpage has been blocked by decision of the Russian government. '
+                'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
+                expected=True)
+
     def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
@@ -588,25 +617,7 @@ class InfoExtractor(object):
         except LookupError:
             content = webpage_bytes.decode('utf-8', 'replace')
 
-        if ('<title>Access to this site is blocked</title>' in content and
-                'Websense' in content[:512]):
-            msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
-            blocked_iframe = self._html_search_regex(
-                r'<iframe src="([^"]+)"', content,
-                'Websense information URL', default=None)
-            if blocked_iframe:
-                msg += ' Visit %s for more details' % blocked_iframe
-            raise ExtractorError(msg, expected=True)
-        if '<title>The URL you requested has been blocked</title>' in content[:512]:
-            msg = (
-                'Access to this webpage has been blocked by Indian censorship. '
-                'Use a VPN or proxy server (with --proxy) to route around it.')
-            block_msg = self._html_search_regex(
-                r'</h1><p>(.*?)</p>',
-                content, 'block message', default=None)
-            if block_msg:
-                msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
-            raise ExtractorError(msg, expected=True)
+        self.__check_blocked(content)
 
         return content
 
@@ -1768,7 +1779,7 @@ class InfoExtractor(object):
                     if content_type == 'text':
                         # TODO implement WebVTT downloading
                         pass
-                    elif content_type == 'video' or content_type == 'audio':
+                    elif content_type in ('video', 'audio'):
                         base_url = ''
                         for element in (representation, adaptation_set, period, mpd_doc):
                             base_url_e = element.find(_add_ns('BaseURL'))

youtube_dl/extractor/crunchyroll.py

@@ -390,7 +390,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         else:
             webpage_url = 'http://www.' + mobj.group('url')
 
-        webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
+        webpage = self._download_webpage(
+            self._add_skip_wall(webpage_url), video_id,
+            headers=self.geo_verification_headers())
         note_m = self._html_search_regex(
             r'<div class="showmedia-trailer-notice">(.+?)</div>',
             webpage, 'trailer-notice', default='')
@@ -565,7 +567,9 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
     def _real_extract(self, url):
         show_id = self._match_id(url)
 
-        webpage = self._download_webpage(self._add_skip_wall(url), show_id)
+        webpage = self._download_webpage(
+            self._add_skip_wall(url), show_id,
+            headers=self.geo_verification_headers())
         title = self._html_search_regex(
             r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
             webpage, 'title')

youtube_dl/extractor/curiositystream.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -49,6 +51,48 @@ class CuriosityStreamBaseIE(InfoExtractor):
         limelight_media_id = media['limelight_media_id']
         title = media['title']
 
+        formats = []
+        for encoding in media.get('encodings', []):
+            m3u8_url = encoding.get('master_playlist_url')
+            if m3u8_url:
+                formats.extend(self._extract_m3u8_formats(
+                    m3u8_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            encoding_url = encoding.get('url')
+            file_url = encoding.get('file_url')
+            if not encoding_url and not file_url:
+                continue
+            f = {
+                'width': int_or_none(encoding.get('width')),
+                'height': int_or_none(encoding.get('height')),
+                'vbr': int_or_none(encoding.get('video_bitrate')),
+                'abr': int_or_none(encoding.get('audio_bitrate')),
+                'filesize': int_or_none(encoding.get('size_in_bytes')),
+                'vcodec': encoding.get('video_codec'),
+                'acodec': encoding.get('audio_codec'),
+                'container': encoding.get('container_type'),
+            }
+            for f_url in (encoding_url, file_url):
+                if not f_url:
+                    continue
+                fmt = f.copy()
+                rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
+                if rtmp:
+                    fmt.update({
+                        'url': rtmp.group('url'),
+                        'play_path': rtmp.group('playpath'),
+                        'app': rtmp.group('app'),
+                        'ext': 'flv',
+                        'format_id': 'rtmp',
+                    })
+                else:
+                    fmt.update({
+                        'url': f_url,
+                        'format_id': 'http',
+                    })
+                formats.append(fmt)
+        self._sort_formats(formats)
+
         subtitles = {}
         for closed_caption in media.get('closed_captions', []):
             sub_url = closed_caption.get('file')
@@ -60,16 +104,14 @@ class CuriosityStreamBaseIE(InfoExtractor):
             })
 
         return {
-            '_type': 'url_transparent',
             'id': video_id,
-            'url': 'limelight:media:' + limelight_media_id,
+            'formats': formats,
             'title': title,
             'description': media.get('description'),
             'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
             'duration': int_or_none(media.get('duration')),
             'tags': media.get('tags'),
             'subtitles': subtitles,
-            'ie_key': 'LimelightMedia',
         }
 
 
@@ -78,14 +120,12 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
     _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
     _TEST = {
         'url': 'https://app.curiositystream.com/video/2',
-        'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
+        'md5': '262bb2f257ff301115f1973540de8983',
         'info_dict': {
             'id': '2',
             'ext': 'mp4',
             'title': 'How Did You Develop The Internet?',
             'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
-            'timestamp': 1448388615,
-            'upload_date': '20151124',
         }
     }
 
@@ -105,7 +145,7 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
             'title': 'Curious Minds: The Internet',
             'description': 'How is the internet shaping our lives in the 21st Century?',
         },
-        'playlist_mincount': 17,
+        'playlist_mincount': 12,
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/cwtv.py

@@ -82,6 +82,11 @@ class CWTVIE(InfoExtractor):
                             'url': quality_url,
                             'tbr': tbr,
                         })
+        video_metadata = video_data['assetFields']
+        ism_url = video_metadata.get('smoothStreamingUrl')
+        if ism_url:
+            formats.extend(self._extract_ism_formats(
+                ism_url, video_id, ism_id='mss', fatal=False))
         self._sort_formats(formats)
 
         thumbnails = [{
@@ -90,8 +95,6 @@ class CWTVIE(InfoExtractor):
             'height': image.get('height'),
         } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
 
-        video_metadata = video_data['assetFields']
-
         subtitles = {
             'en': [{
                 'url': video_metadata['UnicornCcUrl'],

youtube_dl/extractor/discoveryvr.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class DiscoveryVRIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?discoveryvr\.com/watch/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.discoveryvr.com/watch/discovery-vr-an-introduction',
+        'md5': '32b1929798c464a54356378b7912eca4',
+        'info_dict': {
+            'id': 'discovery-vr-an-introduction',
+            'ext': 'mp4',
+            'title': 'Discovery VR - An Introduction',
+            'description': 'md5:80d418a10efb8899d9403e61d8790f06',
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        bootstrap_data = self._search_regex(
+            r'root\.DVR\.bootstrapData\s+=\s+"({.+?})";',
+            webpage, 'bootstrap data')
+        bootstrap_data = self._parse_json(
+            bootstrap_data.encode('utf-8').decode('unicode_escape'),
+            display_id)
+        videos = self._parse_json(bootstrap_data['videos'], display_id)['allVideos']
+        video_data = next(video for video in videos if video.get('slug') == display_id)
+
+        series = video_data.get('showTitle')
+        title = episode = video_data.get('title') or series
+        if series and series != title:
+            title = '%s - %s' % (series, title)
+
+        formats = []
+        for f, format_id in (('cdnUriM3U8', 'mobi'), ('webVideoUrlSd', 'sd'), ('webVideoUrlHd', 'hd')):
+            f_url = video_data.get(f)
+            if not f_url:
+                continue
+            formats.append({
+                'format_id': format_id,
+                'url': f_url,
+            })
+
+        return {
+            'id': display_id,
+            'display_id': display_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnail': video_data.get('thumbnail'),
+            'duration': parse_duration(video_data.get('runTime')),
+            'formats': formats,
+            'episode': episode,
+            'series': series,
+        }

youtube_dl/extractor/extractors.py

@@ -19,6 +19,7 @@ from .acast import (
     ACastChannelIE,
 )
 from .addanime import AddAnimeIE
+from .adn import ADNIE
 from .adobetv import (
     AdobeTVIE,
     AdobeTVShowIE,
@@ -164,7 +165,10 @@ from .ccc import CCCIE
 from .ccma import CCMAIE
 from .cctv import CCTVIE
 from .cda import CDAIE
-from .ceskatelevize import CeskaTelevizeIE
+from .ceskatelevize import (
+    CeskaTelevizeIE,
+    CeskaTelevizePoradyIE,
+)
 from .channel9 import Channel9IE
 from .charlierose import CharlieRoseIE
 from .chaturbate import ChaturbateIE
@@ -272,6 +276,7 @@ from .discoverygo import (
     DiscoveryGoPlaylistIE,
 )
 from .discoverynetworks import DiscoveryNetworksDeIE
+from .discoveryvr import DiscoveryVRIE
 from .disney import DisneyIE
 from .dispeak import DigitallySpeakingIE
 from .dropbox import DropboxIE
@@ -379,6 +384,7 @@ from .globo import (
     GloboArticleIE,
 )
 from .go import GoIE
+from .go90 import Go90IE
 from .godtube import GodTubeIE
 from .godtv import GodTVIE
 from .golem import GolemIE
@@ -536,6 +542,7 @@ from .mangomolo import (
 )
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
+from .medici import MediciIE
 from .meipai import MeipaiIE
 from .melonvod import MelonVODIE
 from .meta import METAIE
@@ -728,6 +735,10 @@ from .orf import (
     ORFFM4IE,
     ORFIPTVIE,
 )
+from .packtpub import (
+    PacktPubIE,
+    PacktPubCourseIE,
+)
 from .pandatv import PandaTVIE
 from .pandoratv import PandoraTVIE
 from .parliamentliveuk import ParliamentLiveUKIE
@@ -797,7 +808,7 @@ from .radiojavan import RadioJavanIE
 from .radiobremen import RadioBremenIE
 from .radiofrance import RadioFranceIE
 from .rai import (
-    RaiTVIE,
+    RaiPlayIE,
     RaiIE,
 )
 from .rbmaradio import RBMARadioIE
@@ -828,7 +839,11 @@ from .rozhlas import RozhlasIE
 from .rtbf import RTBFIE
 from .rte import RteIE, RteRadioIE
 from .rtlnl import RtlNlIE
-from .rtl2 import RTL2IE
+from .rtl2 import (
+    RTL2IE,
+    RTL2YouIE,
+    RTL2YouSeriesIE,
+)
 from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
@@ -970,6 +985,7 @@ from .theplatform import (
 from .thescene import TheSceneIE
 from .thesixtyone import TheSixtyOneIE
 from .thestar import TheStarIE
+from .thesun import TheSunIE
 from .theweatherchannel import TheWeatherChannelIE
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisav import ThisAVIE
@@ -1016,8 +1032,10 @@ from .tv2 import (
     TV2IE,
     TV2ArticleIE,
 )
+from .tv2hu import TV2HuIE
 from .tv3 import TV3IE
 from .tv4 import TV4IE
+from .tv5mondeplus import TV5MondePlusIE
 from .tva import TVAIE
 from .tvanouvelles import (
     TVANouvellesIE,
@@ -1177,6 +1195,11 @@ from .voxmedia import VoxMediaIE
 from .vporn import VpornIE
 from .vrt import VRTIE
 from .vrak import VrakIE
+from .vrv import (
+    VRVIE,
+    VRVSeriesIE,
+)
+from .vshare import VShareIE
 from .medialaan import MedialaanIE
 from .vube import VubeIE
 from .vuclip import VuClipIE

youtube_dl/extractor/funimation.py

@@ -7,9 +7,9 @@ from ..compat import (
     compat_urllib_parse_unquote_plus,
 )
 from ..utils import (
-    clean_html,
     determine_ext,
     int_or_none,
+    js_to_json,
     sanitized_Request,
     ExtractorError,
     urlencode_postdata
@@ -17,34 +17,26 @@ from ..utils import (
 
 
 class FunimationIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
 
     _NETRC_MACHINE = 'funimation'
 
     _TESTS = [{
-        'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
+        'url': 'https://www.funimation.com/shows/hacksign/role-play/',
         'info_dict': {
-            'id': '658',
-            'display_id': 'breeze',
-            'ext': 'mp4',
-            'title': 'Air - 1 - Breeze',
-            'description': 'md5:1769f43cd5fc130ace8fd87232207892',
-            'thumbnail': r're:https?://.*\.jpg',
-        },
-        'skip': 'Access without user interaction is forbidden by CloudFlare, and video removed',
-    }, {
-        'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play',
-        'info_dict': {
-            'id': '31128',
+            'id': '91144',
             'display_id': 'role-play',
             'ext': 'mp4',
-            'title': '.hack//SIGN - 1 - Role Play',
+            'title': '.hack//SIGN - Role Play',
             'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
             'thumbnail': r're:https?://.*\.jpg',
         },
-        'skip': 'Access without user interaction is forbidden by CloudFlare',
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
-        'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview',
+        'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
         'info_dict': {
             'id': '9635',
             'display_id': 'broadcast-dub-preview',
@@ -54,25 +46,13 @@ class FunimationIE(InfoExtractor):
             'thumbnail': r're:https?://.*\.(?:jpg|png)',
         },
         'skip': 'Access without user interaction is forbidden by CloudFlare',
+    }, {
+        'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
+        'only_matching': True,
     }]
 
     _LOGIN_URL = 'http://www.funimation.com/login'
 
-    def _download_webpage(self, *args, **kwargs):
-        try:
-            return super(FunimationIE, self)._download_webpage(*args, **kwargs)
-        except ExtractorError as ee:
-            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
-                response = ee.cause.read()
-                if b'>Please complete the security check to access<' in response:
-                    raise ExtractorError(
-                        'Access to funimation.com is blocked by CloudFlare. '
-                        'Please browse to http://www.funimation.com/, solve '
-                        'the reCAPTCHA, export browser cookies to a text file,'
-                        ' and then try again with --cookies YOUR_COOKIE_FILE.',
-                        expected=True)
-            raise
-
     def _extract_cloudflare_session_ua(self, url):
         ci_session_cookie = self._get_cookies(url).get('ci_session')
         if ci_session_cookie:
@@ -114,119 +94,74 @@ class FunimationIE(InfoExtractor):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        def _search_kane(name):
+            return self._search_regex(
+                r"KANE_customdimensions\.%s\s*=\s*'([^']+)';" % name,
+                webpage, name, default=None)
+
+        title_data = self._parse_json(self._search_regex(
+            r'TITLE_DATA\s*=\s*({[^}]+})',
+            webpage, 'title data', default=''),
+            display_id, js_to_json, fatal=False) or {}
+
+        video_id = title_data.get('id') or self._search_regex([
+            r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
+            r'<iframe[^>]+src="/player/(\d+)"',
+        ], webpage, 'video_id', default=None)
+        if not video_id:
+            player_url = self._html_search_meta([
+                'al:web:url',
+                'og:video:url',
+                'og:video:secure_url',
+            ], webpage, fatal=True)
+            video_id = self._search_regex(r'/player/(\d+)', player_url, 'video id')
+
+        title = episode = title_data.get('title') or _search_kane('videoTitle') or self._og_search_title(webpage)
+        series = _search_kane('showName')
+        if series:
+            title = '%s - %s' % (series, title)
+        description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
+
+        try:
+            sources = self._download_json(
+                'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
+                video_id)['items']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                error = self._parse_json(e.cause.read(), video_id)['errors'][0]
+                raise ExtractorError('%s said: %s' % (
+                    self.IE_NAME, error.get('detail') or error.get('title')), expected=True)
+            raise
 
-        errors = []
         formats = []
-
-        ERRORS_MAP = {
-            'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn',
-            'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut',
-            'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut',
-            'ERROR_VIDEO_EXPIRED': 'videoExpired',
-            'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable',
-            'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription',
-            'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription',
-            'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding',
-            'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN',
-            'ERROR_STREAM_NOT_FOUND': 'streamNotFound',
-        }
-
-        USER_AGENTS = (
-            # PC UA is served with m3u8 that provides some bonus lower quality formats
-            ('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'),
-            # Mobile UA allows to extract direct links and also does not fail when
-            # PC UA fails with hulu error (e.g.
-            # http://www.funimation.com/shows/hacksign/videos/official/role-play)
-            ('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'),
-        )
-
-        user_agent = self._extract_cloudflare_session_ua(url)
-        if user_agent:
-            USER_AGENTS = ((None, user_agent),)
-
-        for kind, user_agent in USER_AGENTS:
-            request = sanitized_Request(url)
-            request.add_header('User-Agent', user_agent)
-            webpage = self._download_webpage(
-                request, display_id,
-                'Downloading %s webpage' % kind if kind else 'Downloading webpage')
-
-            playlist = self._parse_json(
-                self._search_regex(
-                    r'var\s+playersData\s*=\s*(\[.+?\]);\n',
-                    webpage, 'players data'),
-                display_id)[0]['playlist']
-
-            items = next(item['items'] for item in playlist if item.get('items'))
-            item = next(item for item in items if item.get('itemAK') == display_id)
-
-            error_messages = {}
-            video_error_messages = self._search_regex(
-                r'var\s+videoErrorMessages\s*=\s*({.+?});\n',
-                webpage, 'error messages', default=None)
-            if video_error_messages:
-                error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False)
-                if error_messages_json:
-                    for _, error in error_messages_json.items():
-                        type_ = error.get('type')
-                        description = error.get('description')
-                        content = error.get('content')
-                        if type_ == 'text' and description and content:
-                            error_message = ERRORS_MAP.get(description)
-                            if error_message:
-                                error_messages[error_message] = content
-
-            for video in item.get('videoSet', []):
-                auth_token = video.get('authToken')
-                if not auth_token:
-                    continue
-                funimation_id = video.get('FUNImationID') or video.get('videoId')
-                preference = 1 if video.get('languageMode') == 'dub' else 0
-                if not auth_token.startswith('?'):
-                    auth_token = '?%s' % auth_token
-                for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)):
-                    format_url = video.get('%sUrl' % quality)
-                    if not format_url:
-                        continue
-                    if not format_url.startswith(('http', '//')):
-                        errors.append(format_url)
-                        continue
-                    if determine_ext(format_url) == 'm3u8':
-                        formats.extend(self._extract_m3u8_formats(
-                            format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
-                            preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False))
-                    else:
-                        tbr = int_or_none(self._search_regex(
-                            r'-(\d+)[Kk]', format_url, 'tbr', default=None))
-                        formats.append({
-                            'url': format_url + auth_token,
-                            'format_id': '%s-http-%dp' % (funimation_id, height),
-                            'height': height,
-                            'tbr': tbr,
-                            'preference': preference,
-                        })
-
-        if not formats and errors:
-            raise ExtractorError(
-                '%s returned error: %s'
-                % (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))),
-                expected=True)
-
+        for source in sources:
+            source_url = source.get('src')
+            if not source_url:
+                continue
+            source_type = source.get('videoType') or determine_ext(source_url)
+            if source_type == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    source_url, video_id, 'mp4',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'format_id': source_type,
+                    'url': source_url,
+                })
         self._sort_formats(formats)
 
-        title = item['title']
-        artist = item.get('artist')
-        if artist:
-            title = '%s - %s' % (artist, title)
-        description = self._og_search_description(webpage) or item.get('description')
-        thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl')
-        video_id = item.get('itemId') or display_id
-
         return {
             'id': video_id,
             'display_id': display_id,
             'title': title,
             'description': description,
-            'thumbnail': thumbnail,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'series': series,
+            'season_number': int_or_none(title_data.get('seasonNum') or _search_kane('season')),
+            'episode_number': int_or_none(title_data.get('episodeNum')),
+            'episode': episode,
+            'season_id': title_data.get('seriesId'),
             'formats': formats,
         }

youtube_dl/extractor/generic.py

@@ -730,6 +730,21 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             }
         },
+        # YouTube <object> embed
+        {
+            'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
+            'md5': '516718101ec834f74318df76259fb3cc',
+            'info_dict': {
+                'id': 'msN87y-iEx0',
+                'ext': 'webm',
+                'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
+                'upload_date': '20080526',
+                'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
+                'uploader': 'Christopher Sykes',
+                'uploader_id': 'ChristopherJSykes',
+            },
+            'add_ie': ['Youtube'],
+        },
         # Camtasia studio
         {
             'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
@@ -1080,6 +1095,21 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Kaltura'],
         },
+        {
+            # Kaltura iframe embed
+            'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
+            'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
+            'info_dict': {
+                'id': '0_f2cfbpwy',
+                'ext': 'mp4',
+                'title': 'I. M. Pei: A Centennial Celebration',
+                'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
+                'upload_date': '20170403',
+                'uploader_id': 'batchUser',
+                'timestamp': 1491232186,
+            },
+            'add_ie': ['Kaltura'],
+        },
         # Eagle.Platform embed (generic URL)
         {
             'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@@ -1923,6 +1953,7 @@ class GenericIE(InfoExtractor):
                 data-video-url=|
                 <embed[^>]+?src=|
                 embedSWF\(?:\s*|
+                <object[^>]+data=|
                 new\s+SWFObject\(
             )
             (["\'])
@@ -2568,7 +2599,7 @@ class GenericIE(InfoExtractor):
             webpage, video_id, transform_source=js_to_json)
         if jwplayer_data:
             info = self._parse_jwplayer_data(
-                jwplayer_data, video_id, require_title=False)
+                jwplayer_data, video_id, require_title=False, base_url=url)
             if not info.get('title'):
                 info['title'] = video_title
             return info
@@ -2580,7 +2611,7 @@ class GenericIE(InfoExtractor):
                 return True
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
-            return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
+            return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
 
         def filter_video(urls):
             return list(filter(check_video, urls))

youtube_dl/extractor/go90.py

@@ -0,0 +1,92 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class Go90IE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?go90\.com/videos/(?P<id>[0-9a-zA-Z]+)'
+    _TEST = {
+        'url': 'https://www.go90.com/videos/84BUqjLpf9D',
+        'md5': 'efa7670dbbbf21a7b07b360652b24a32',
+        'info_dict': {
+            'id': '84BUqjLpf9D',
+            'ext': 'mp4',
+            'title': 'Inside The Utah Coalition Against Pornography Convention',
+            'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.',
+            'timestamp': 1491868800,
+            'upload_date': '20170411',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            'https://www.go90.com/api/view/items/' + video_id,
+            video_id, headers={
+                'Content-Type': 'application/json; charset=utf-8',
+            }, data=b'{"client":"web","device_type":"pc"}')
+        title = video_data['title']
+        main_video_asset = video_data['main_video_asset']
+
+        thumbnails = []
+        formats = []
+        for asset in video_data.get('assets'):
+            if asset.get('id') == main_video_asset:
+                for source in asset.get('sources', []):
+                    source_location = source.get('location')
+                    if not source_location:
+                        continue
+                    source_type = source.get('type')
+                    if source_type == 'hls':
+                        m3u8_formats = self._extract_m3u8_formats(
+                            source_location, video_id, 'mp4',
+                            'm3u8_native', m3u8_id='hls', fatal=False)
+                        for f in m3u8_formats:
+                            mobj = re.search(r'/hls-(\d+)-(\d+)K', f['url'])
+                            if mobj:
+                                height, tbr = mobj.groups()
+                                height = int_or_none(height)
+                                f.update({
+                                    'height': f.get('height') or height,
+                                    'width': f.get('width') or int_or_none(height / 9.0 * 16.0 if height else None),
+                                    'tbr': f.get('tbr') or int_or_none(tbr),
+                                })
+                        formats.extend(m3u8_formats)
+                    elif source_type == 'dash':
+                        formats.extend(self._extract_mpd_formats(
+                            source_location, video_id, mpd_id='dash', fatal=False))
+                    else:
+                        formats.append({
+                            'format_id': source.get('name'),
+                            'url': source_location,
+                            'width': int_or_none(source.get('width')),
+                            'height': int_or_none(source.get('height')),
+                            'tbr': int_or_none(source.get('bitrate')),
+                        })
+            elif asset.get('type') == 'image':
+                asset_location = asset.get('location')
+                if not asset_location:
+                    continue
+                thumbnails.append({
+                    'url': asset_location,
+                    'width': int_or_none(asset.get('width')),
+                    'height': int_or_none(asset.get('height')),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': video_data.get('short_description'),
+            'like_count': int_or_none(video_data.get('like_count')),
+            'timestamp': parse_iso8601(video_data.get('released_at')),
+        }

youtube_dl/extractor/hbo.py

@@ -92,12 +92,14 @@ class HBOBaseIE(InfoExtractor):
                         video_url.replace('.tar', '/base_index_w8.m3u8'),
                         video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
                 elif source.tag == 'hls':
-                    # #EXT-X-BYTERANGE is not supported by native hls downloader
-                    # and ffmpeg (#10955)
-                    # formats.extend(self._extract_m3u8_formats(
-                    #     video_url.replace('.tar', '/base_index.m3u8'),
-                    #     video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
-                    continue
+                    m3u8_formats = self._extract_m3u8_formats(
+                        video_url.replace('.tar', '/base_index.m3u8'),
+                        video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
+                    for f in m3u8_formats:
+                        if f.get('vcodec') == 'none' and not f.get('tbr'):
+                            f['tbr'] = int_or_none(self._search_regex(
+                                r'-(\d+)k/', f['url'], 'tbr', default=None))
+                    formats.extend(m3u8_formats)
                 elif source.tag == 'dash':
                     formats.extend(self._extract_mpd_formats(
                         video_url.replace('.tar', '/manifest.mpd'),
@@ -110,7 +112,7 @@ class HBOBaseIE(InfoExtractor):
                         'width': format_info.get('width'),
                         'height': format_info.get('height'),
                     })
-        self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
+        self._sort_formats(formats)
 
         thumbnails = []
         card_sizes = xpath_element(video_data, 'titleCardSizes')

youtube_dl/extractor/kaltura.py

@@ -91,6 +91,7 @@ class KalturaIE(InfoExtractor):
                     }],
                 },
             },
+            'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
             'params': {
                 'skip_download': True,
             },
@@ -107,27 +108,37 @@ class KalturaIE(InfoExtractor):
 
     @staticmethod
     def _extract_url(webpage):
+        # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
         mobj = (
             re.search(
                 r"""(?xs)
                     kWidget\.(?:thumb)?[Ee]mbed\(
                     \{.*?
-                        (?P<q1>['\"])wid(?P=q1)\s*:\s*
-                        (?P<q2>['\"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
-                        (?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*
-                        (?P<q4>['\"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
+                        (?P<q1>['"])wid(?P=q1)\s*:\s*
+                        (?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
+                        (?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
+                        (?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
                 """, webpage) or
             re.search(
                 r'''(?xs)
-                    (?P<q1>["\'])
+                    (?P<q1>["'])
                         (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
                     (?P=q1).*?
                     (?:
                         entry_?[Ii]d|
-                        (?P<q2>["\'])entry_?[Ii]d(?P=q2)
+                        (?P<q2>["'])entry_?[Ii]d(?P=q2)
                     )\s*:\s*
-                    (?P<q3>["\'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
-                ''', webpage))
+                    (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
+                ''', webpage) or
+            re.search(
+                r'''(?xs)
+                    <iframe[^>]+src=(?P<q1>["'])
+                      (?:https?:)?//(?:www\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
+                      (?:(?!(?P=q1)).)*
+                      [?&]entry_id=(?P<id>(?:(?!(?P=q1))[^&])+)
+                    (?P=q1)
+                ''', webpage)
+        )
         if mobj:
             embed_info = mobj.groupdict()
             url = 'kaltura:%(partner_id)s:%(id)s' % embed_info

youtube_dl/extractor/limelight.py

@@ -62,13 +62,21 @@ class LimelightBaseIE(InfoExtractor):
                 fmt = {
                     'url': stream_url,
                     'abr': float_or_none(stream.get('audioBitRate')),
-                    'vbr': float_or_none(stream.get('videoBitRate')),
                     'fps': float_or_none(stream.get('videoFrameRate')),
-                    'width': int_or_none(stream.get('videoWidthInPixels')),
-                    'height': int_or_none(stream.get('videoHeightInPixels')),
                     'ext': ext,
                 }
-                rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp4:.+)$', stream_url)
+                width = int_or_none(stream.get('videoWidthInPixels'))
+                height = int_or_none(stream.get('videoHeightInPixels'))
+                vbr = float_or_none(stream.get('videoBitRate'))
+                if width or height or vbr:
+                    fmt.update({
+                        'width': width,
+                        'height': height,
+                        'vbr': vbr,
+                    })
+                else:
+                    fmt['vcodec'] = 'none'
+                rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', stream_url)
                 if rtmp:
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):

youtube_dl/extractor/medici.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate,
+    update_url_query,
+    urlencode_postdata,
+)
+
+
+class MediciIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?medici\.tv/#!/(?P<id>[^?#&]+)'
+    _TEST = {
+        'url': 'http://www.medici.tv/#!/daniel-harding-frans-helmerson-verbier-festival-music-camp',
+        'md5': '004c21bb0a57248085b6ff3fec72719d',
+        'info_dict': {
+            'id': '3059',
+            'ext': 'flv',
+            'title': 'Daniel Harding conducts the Verbier Festival Music Camp \u2013 With Frans Helmerson',
+            'description': 'md5:322a1e952bafb725174fd8c1a8212f58',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'upload_date': '20170408',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        # Sets csrftoken cookie
+        self._download_webpage(url, video_id)
+
+        MEDICI_URL = 'http://www.medici.tv/'
+
+        data = self._download_json(
+            MEDICI_URL, video_id,
+            data=urlencode_postdata({
+                'json': 'true',
+                'page': '/%s' % video_id,
+                'timezone_offset': -420,
+            }), headers={
+                'X-CSRFToken': self._get_cookies(url)['csrftoken'].value,
+                'X-Requested-With': 'XMLHttpRequest',
+                'Referer': MEDICI_URL,
+                'Content-Type': 'application/x-www-form-urlencoded',
+            })
+
+        video = data['video']['videos']['video1']
+
+        title = video.get('nom') or data['title']
+
+        video_id = video.get('id') or video_id
+        formats = self._extract_f4m_formats(
+            update_url_query(video['url_akamai'], {
+                'hdcore': '3.1.0',
+                'plugin=aasp': '3.1.0.43.124',
+            }), video_id, f4m_id='hds')
+
+        description = data.get('meta_description')
+        thumbnail = video.get('url_thumbnail') or data.get('main_image')
+        upload_date = unified_strdate(data['video'].get('date'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'formats': formats,
+        }

youtube_dl/extractor/mixcloud.py

@@ -97,7 +97,7 @@ class MixcloudIE(InfoExtractor):
         view_count = str_to_int(self._search_regex(
             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
              r'/listeners/?">([0-9,.]+)</a>',
-             r'm-tooltip=["\']([\d,.]+) plays'],
+             r'(?:m|data)-tooltip=["\']([\d,.]+) plays'],
             webpage, 'play count', default=None))
 
         return {
@@ -138,12 +138,12 @@ class MixcloudPlaylistBaseIE(InfoExtractor):
 
     def _get_user_description(self, page_content):
         return self._html_search_regex(
-            r'<div[^>]+class="description-text"[^>]*>(.+?)</div>',
+            r'<div[^>]+class="profile-bio"[^>]*>(.+?)</div>',
             page_content, 'user description', fatal=False)
 
 
 class MixcloudUserIE(MixcloudPlaylistBaseIE):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
+    _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
     IE_NAME = 'mixcloud:user'
 
     _TESTS = [{
@@ -151,7 +151,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
         'info_dict': {
             'id': 'dholbach_uploads',
             'title': 'Daniel Holbach (uploads)',
-            'description': 'md5:327af72d1efeb404a8216c27240d1370',
+            'description': 'md5:def36060ac8747b3aabca54924897e47',
         },
         'playlist_mincount': 11,
     }, {
@@ -159,7 +159,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
         'info_dict': {
             'id': 'dholbach_uploads',
             'title': 'Daniel Holbach (uploads)',
-            'description': 'md5:327af72d1efeb404a8216c27240d1370',
+            'description': 'md5:def36060ac8747b3aabca54924897e47',
         },
         'playlist_mincount': 11,
     }, {
@@ -167,7 +167,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
         'info_dict': {
             'id': 'dholbach_favorites',
             'title': 'Daniel Holbach (favorites)',
-            'description': 'md5:327af72d1efeb404a8216c27240d1370',
+            'description': 'md5:def36060ac8747b3aabca54924897e47',
         },
         'params': {
             'playlist_items': '1-100',
@@ -178,7 +178,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
         'info_dict': {
             'id': 'dholbach_listens',
             'title': 'Daniel Holbach (listens)',
-            'description': 'md5:327af72d1efeb404a8216c27240d1370',
+            'description': 'md5:def36060ac8747b3aabca54924897e47',
         },
         'params': {
             'playlist_items': '1-100',
@@ -216,7 +216,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
 
 
 class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
+    _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
     IE_NAME = 'mixcloud:playlist'
 
     _TESTS = [{
@@ -229,12 +229,7 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
         'playlist_mincount': 16,
     }, {
         'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
-        'info_dict': {
-            'id': 'maxvibes_jazzcat-on-ness-radio',
-            'title': 'Jazzcat on Ness Radio',
-            'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
-        },
-        'playlist_mincount': 23
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -243,15 +238,16 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
         playlist_id = mobj.group('playlist')
         video_id = '%s_%s' % (user_id, playlist_id)
 
-        profile = self._download_webpage(
+        webpage = self._download_webpage(
             url, user_id,
             note='Downloading playlist page',
             errnote='Unable to download playlist page')
 
-        description = self._get_user_description(profile)
-        playlist_title = self._html_search_regex(
-            r'<span[^>]+class="[^"]*list-playlist-title[^"]*"[^>]*>(.*?)</span>',
-            profile, 'playlist title')
+        title = self._html_search_regex(
+            r'<a[^>]+class="parent active"[^>]*><b>\d+</b><span[^>]*>([^<]+)',
+            webpage, 'playlist title',
+            default=None) or self._og_search_title(webpage, fatal=False)
+        description = self._get_user_description(webpage)
 
         entries = OnDemandPagedList(
             functools.partial(
@@ -259,11 +255,11 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
                 '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
             self._PAGE_SIZE)
 
-        return self.playlist_result(entries, video_id, playlist_title, description)
+        return self.playlist_result(entries, video_id, title, description)
 
 
 class MixcloudStreamIE(MixcloudPlaylistBaseIE):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
+    _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
     IE_NAME = 'mixcloud:stream'
 
     _TEST = {

youtube_dl/extractor/npo.py

@@ -313,9 +313,9 @@ class NPOIE(NPOBaseIE):
 
 class NPOLiveIE(NPOBaseIE):
     IE_NAME = 'npo.nl:live'
-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?npo\.nl/live(?:/(?P<id>[^/?#&]+))?'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.npo.nl/live/npo-1',
         'info_dict': {
             'id': 'LI_NL1_4188102',
@@ -327,10 +327,13 @@ class NPOLiveIE(NPOBaseIE):
         'params': {
             'skip_download': True,
         }
-    }
+    }, {
+        'url': 'http://www.npo.nl/live',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        display_id = self._match_id(url) or 'npo-1'
 
         webpage = self._download_webpage(url, display_id)
 

youtube_dl/extractor/odnoklassniki.py

@@ -176,7 +176,7 @@ class OdnoklassnikiIE(InfoExtractor):
             })
             return info
 
-        quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
+        quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd', 'full'))
 
         formats = [{
             'url': f['url'],

youtube_dl/extractor/openload.py

@@ -75,51 +75,38 @@ class OpenloadIE(InfoExtractor):
             '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
             webpage, 'openload ID')
 
-        video_url_chars = []
-
-        first_char = ord(ol_id[0])
-        key = first_char - 55
-        maxKey = max(2, key)
-        key = min(maxKey, len(ol_id) - 38)
-        t = ol_id[key:key + 36]
-
-        hashMap = {}
-        v = ol_id.replace(t, '')
-        h = 0
-
-        while h < len(t):
-            f = t[h:h + 3]
-            i = int(f, 8)
-            hashMap[h / 3] = i
-            h += 3
-
-        h = 0
-        H = 0
-        while h < len(v):
-            B = ''
-            C = ''
-            if len(v) >= h + 2:
-                B = v[h:h + 2]
-            if len(v) >= h + 3:
-                C = v[h:h + 3]
-            i = int(B, 16)
-            h += 2
-            if H % 3 == 0:
-                i = int(C, 8)
-                h += 1
-            elif H % 2 == 0 and H != 0 and ord(v[H - 1]) < 60:
-                i = int(C, 10)
-                h += 1
-            index = H % 7
-
-            A = hashMap[index]
-            i ^= 213
-            i ^= A
-            video_url_chars.append(compat_chr(i))
-            H += 1
+        decoded = ''
+        a = ol_id[0:24]
+        b = []
+        for i in range(0, len(a), 8):
+            b.append(int(a[i:i + 8] or '0', 16))
+        ol_id = ol_id[24:]
+        j = 0
+        k = 0
+        while j < len(ol_id):
+            c = 128
+            d = 0
+            e = 0
+            f = 0
+            _more = True
+            while _more:
+                if j + 1 >= len(ol_id):
+                    c = 143
+                f = int(ol_id[j:j + 2] or '0', 16)
+                j += 2
+                d += (f & 127) << e
+                e += 7
+                _more = f >= c
+            g = d ^ b[k % 3]
+            for i in range(4):
+                char_dec = (g >> 8 * i) & (c + 127)
+                char = compat_chr(char_dec)
+                if char != '#':
+                    decoded += char
+            k += 1
 
         video_url = 'https://openload.co/stream/%s?mime=true'
-        video_url = video_url % (''.join(video_url_chars))
+        video_url = video_url % decoded
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,

youtube_dl/extractor/packtpub.py

@@ -0,0 +1,138 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    remove_end,
+    strip_or_none,
+    unified_timestamp,
+    urljoin,
+)
+
+
+class PacktPubBaseIE(InfoExtractor):
+    _PACKT_BASE = 'https://www.packtpub.com'
+    _MAPT_REST = '%s/mapt-rest' % _PACKT_BASE
+
+
+class PacktPubIE(PacktPubBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
+        'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
+        'info_dict': {
+            'id': '20530',
+            'ext': 'mp4',
+            'title': 'Project Intro',
+            'thumbnail': r're:(?i)^https?://.*\.jpg',
+            'timestamp': 1490918400,
+            'upload_date': '20170331',
+        },
+    }
+
+    def _handle_error(self, response):
+        if response.get('status') != 'success':
+            raise ExtractorError(
+                '% said: %s' % (self.IE_NAME, response['message']),
+                expected=True)
+
+    def _download_json(self, *args, **kwargs):
+        response = super(PacktPubIE, self)._download_json(*args, **kwargs)
+        self._handle_error(response)
+        return response
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        course_id, chapter_id, video_id = mobj.group(
+            'course_id', 'chapter_id', 'id')
+
+        video = self._download_json(
+            '%s/users/me/products/%s/chapters/%s/sections/%s'
+            % (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
+            'Downloading JSON video')['data']
+
+        content = video.get('content')
+        if not content:
+            raise ExtractorError('This video is locked', expected=True)
+
+        video_url = content['file']
+
+        metadata = self._download_json(
+            '%s/products/%s/chapters/%s/sections/%s/metadata'
+            % (self._MAPT_REST, course_id, chapter_id, video_id),
+            video_id)['data']
+
+        title = metadata['pageTitle']
+        course_title = metadata.get('title')
+        if course_title:
+            title = remove_end(title, ' - %s' % course_title)
+        timestamp = unified_timestamp(metadata.get('publicationDate'))
+        thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+        }
+
+
+class PacktPubCourseIE(PacktPubBaseIE):
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))'
+    _TEST = {
+        'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
+        'info_dict': {
+            'id': '9781787122215',
+            'title': 'Learn Nodejs by building 12 projects [Video]',
+        },
+        'playlist_count': 90,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PacktPubIE.suitable(url) else super(
+            PacktPubCourseIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        url, course_id = mobj.group('url', 'id')
+
+        course = self._download_json(
+            '%s/products/%s/metadata' % (self._MAPT_REST, course_id),
+            course_id)['data']
+
+        entries = []
+        for chapter_num, chapter in enumerate(course['tableOfContents'], 1):
+            if chapter.get('type') != 'chapter':
+                continue
+            children = chapter.get('children')
+            if not isinstance(children, list):
+                continue
+            chapter_info = {
+                'chapter': chapter.get('title'),
+                'chapter_number': chapter_num,
+                'chapter_id': chapter.get('id'),
+            }
+            for section in children:
+                if section.get('type') != 'section':
+                    continue
+                section_url = section.get('seoUrl')
+                if not isinstance(section_url, compat_str):
+                    continue
+                entry = {
+                    '_type': 'url_transparent',
+                    'url': urljoin(url + '/', section_url),
+                    'title': strip_or_none(section.get('title')),
+                    'description': clean_html(section.get('summary')),
+                    'ie_key': PacktPubIE.ie_key(),
+                }
+                entry.update(chapter_info)
+                entries.append(entry)
+
+        return self.playlist_result(entries, course_id, course.get('title'))

youtube_dl/extractor/periscope.py

@@ -20,7 +20,7 @@ class PeriscopeBaseIE(InfoExtractor):
 class PeriscopeIE(PeriscopeBaseIE):
     IE_DESC = 'Periscope'
     IE_NAME = 'periscope'
-    _VALID_URL = r'https?://(?:www\.)?periscope\.tv/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:periscope|pscp)\.tv/[^/]+/(?P<id>[^/?#]+)'
     # Alive example URLs can be found here http://onperiscope.com/
     _TESTS = [{
         'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==',
@@ -41,6 +41,9 @@ class PeriscopeIE(PeriscopeBaseIE):
     }, {
         'url': 'https://www.periscope.tv/bastaakanoggano/1OdKrlkZZjOJX',
         'only_matching': True,
+    }, {
+        'url': 'https://www.periscope.tv/w/1ZkKzPbMVggJv',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -103,7 +106,7 @@ class PeriscopeIE(PeriscopeBaseIE):
 
 
 class PeriscopeUserIE(PeriscopeBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?periscope\.tv/(?P<id>[^/]+)/?$'
+    _VALID_URL = r'https?://(?:www\.)?(?:periscope|pscp)\.tv/(?P<id>[^/]+)/?$'
     IE_DESC = 'Periscope user videos'
     IE_NAME = 'periscope:user'
 

youtube_dl/extractor/rai.py

@@ -1,23 +1,40 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_urlparse,
+    compat_str,
+)
 from ..utils import (
-    determine_ext,
     ExtractorError,
+    determine_ext,
     find_xpath_attr,
     fix_xml_ampersands,
+    GeoRestrictedError,
     int_or_none,
     parse_duration,
+    strip_or_none,
+    try_get,
     unified_strdate,
+    unified_timestamp,
     update_url_query,
+    urljoin,
     xpath_text,
 )
 
 
 class RaiBaseIE(InfoExtractor):
-    def _extract_relinker_formats(self, relinker_url, video_id):
+    _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
+    _GEO_COUNTRIES = ['IT']
+    _GEO_BYPASS = False
+
+    def _extract_relinker_info(self, relinker_url, video_id):
         formats = []
+        geoprotection = None
+        is_live = None
+        duration = None
 
         for platform in ('mon', 'flash', 'native'):
             relinker = self._download_xml(
@@ -27,9 +44,27 @@ class RaiBaseIE(InfoExtractor):
                 query={'output': 45, 'pl': platform},
                 headers=self.geo_verification_headers())
 
-            media_url = find_xpath_attr(relinker, './url', 'type', 'content').text
+            if not geoprotection:
+                geoprotection = xpath_text(
+                    relinker, './geoprotection', default=None) == 'Y'
+
+            if not is_live:
+                is_live = xpath_text(
+                    relinker, './is_live', default=None) == 'Y'
+            if not duration:
+                duration = parse_duration(xpath_text(
+                    relinker, './duration', default=None))
+
+            url_elem = find_xpath_attr(relinker, './url', 'type', 'content')
+            if url_elem is None:
+                continue
+
+            media_url = url_elem.text
+
+            # This does not imply geo restriction (e.g.
+            # http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
             if media_url == 'http://download.rai.it/video_no_available.mp4':
-                self.raise_geo_restricted()
+                continue
 
             ext = determine_ext(media_url)
             if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
@@ -53,215 +88,333 @@ class RaiBaseIE(InfoExtractor):
                     'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
                 })
 
-        return formats
+        if not formats and geoprotection is True:
+            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
 
-    def _extract_from_content_id(self, content_id, base_url):
+        return dict((k, v) for k, v in {
+            'is_live': is_live,
+            'duration': duration,
+            'formats': formats,
+        }.items() if v is not None)
+
+    @staticmethod
+    def _extract_subtitles(url, subtitle_url):
+        subtitles = {}
+        if subtitle_url and isinstance(subtitle_url, compat_str):
+            subtitle_url = urljoin(url, subtitle_url)
+            STL_EXT = '.stl'
+            SRT_EXT = '.srt'
+            subtitles['it'] = [{
+                'ext': 'stl',
+                'url': subtitle_url,
+            }]
+            if subtitle_url.endswith(STL_EXT):
+                srt_url = subtitle_url[:-len(STL_EXT)] + SRT_EXT
+                subtitles['it'].append({
+                    'ext': 'srt',
+                    'url': srt_url,
+                })
+        return subtitles
+
+
+class RaiPlayIE(RaiBaseIE):
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s)\.html)' % RaiBaseIE._UUID_RE
+    _TESTS = [{
+        'url': 'http://www.raiplay.it/video/2016/10/La-Casa-Bianca-e06118bb-59a9-4636-b914-498e4cfd2c66.html?source=twitter',
+        'md5': '340aa3b7afb54bfd14a8c11786450d76',
+        'info_dict': {
+            'id': 'e06118bb-59a9-4636-b914-498e4cfd2c66',
+            'ext': 'mp4',
+            'title': 'La Casa Bianca',
+            'alt_title': 'S2016 - Puntata del 23/10/2016',
+            'description': 'md5:a09d45890850458077d1f68bb036e0a5',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Rai 3',
+            'creator': 'Rai 3',
+            'duration': 3278,
+            'timestamp': 1477764300,
+            'upload_date': '20161029',
+            'series': 'La Casa Bianca',
+            'season': '2016',
+        },
+    }, {
+        'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
+        'md5': '8970abf8caf8aef4696e7b1f2adfc696',
+        'info_dict': {
+            'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
+            'ext': 'mp4',
+            'title': 'Report del 07/04/2014',
+            'alt_title': 'S2013/14 - Puntata del 07/04/2014',
+            'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'Rai 5',
+            'creator': 'Rai 5',
+            'duration': 6160,
+            'series': 'Report',
+            'season_number': 5,
+            'season': '2013/14',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        url, video_id = mobj.group('url', 'id')
+
+        media = self._download_json(
+            '%s?json' % url, video_id, 'Downloading video JSON')
+
+        title = media['name']
+
+        video = media['video']
+
+        relinker_info = self._extract_relinker_info(video['contentUrl'], video_id)
+        self._sort_formats(relinker_info['formats'])
+
+        thumbnails = []
+        if 'images' in media:
+            for _, value in media.get('images').items():
+                if value:
+                    thumbnails.append({
+                        'url': value.replace('[RESOLUTION]', '600x400')
+                    })
+
+        timestamp = unified_timestamp(try_get(
+            media, lambda x: x['availabilities'][0]['start'], compat_str))
+
+        subtitles = self._extract_subtitles(url, video.get('subtitles'))
+
+        info = {
+            'id': video_id,
+            'title': title,
+            'alt_title': media.get('subtitle'),
+            'description': media.get('description'),
+            'uploader': media.get('channel'),
+            'creator': media.get('editor'),
+            'duration': parse_duration(video.get('duration')),
+            'timestamp': timestamp,
+            'thumbnails': thumbnails,
+            'series': try_get(
+                media, lambda x: x['isPartOf']['name'], compat_str),
+            'season_number': int_or_none(try_get(
+                media, lambda x: x['isPartOf']['numeroStagioni'])),
+            'season': media.get('stagione') or None,
+            'subtitles': subtitles,
+        }
+
+        info.update(relinker_info)
+
+        return info
+
+
+class RaiIE(RaiBaseIE):
+    _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
+    _TESTS = [{
+        # var uniquename = "ContentItem-..."
+        # data-id="ContentItem-..."
+        'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
+        'info_dict': {
+            'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
+            'ext': 'mp4',
+            'title': 'TG PRIMO TEMPO',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 1758,
+            'upload_date': '20140612',
+        }
+    }, {
+        # with ContentItem in many metas
+        'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
+        'info_dict': {
+            'id': '1632c009-c843-4836-bb65-80c33084a64b',
+            'ext': 'mp4',
+            'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
+            'description': 'I film in uscita questa settimana.',
+            'thumbnail': r're:^https?://.*\.png$',
+            'duration': 833,
+            'upload_date': '20161103',
+        }
+    }, {
+        # with ContentItem in og:url
+        'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
+        'md5': '11959b4e44fa74de47011b5799490adf',
+        'info_dict': {
+            'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
+            'ext': 'mp4',
+            'title': 'TG1 ore 20:00 del 03/11/2016',
+            'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 2214,
+            'upload_date': '20161103',
+        }
+    }, {
+        # drawMediaRaiTV(...)
+        'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
+        'md5': '2dd727e61114e1ee9c47f0da6914e178',
+        'info_dict': {
+            'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
+            'ext': 'mp4',
+            'title': 'Il pacco',
+            'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'upload_date': '20141221',
+        },
+    }, {
+        # initEdizione('ContentItem-...'
+        'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
+        'info_dict': {
+            'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
+            'ext': 'mp4',
+            'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
+            'duration': 2274,
+            'upload_date': '20170401',
+        },
+        'skip': 'Changes daily',
+    }, {
+        # HDS live stream with only relinker URL
+        'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
+        'info_dict': {
+            'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
+            'ext': 'flv',
+            'title': 'EuroNews',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # HLS live stream with ContentItem in og:url
+        'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
+        'info_dict': {
+            'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
+            'ext': 'mp4',
+            'title': 'La diretta di Rainews24',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _extract_from_content_id(self, content_id, url):
         media = self._download_json(
             'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id,
             content_id, 'Downloading video JSON')
 
+        title = media['name'].strip()
+
+        media_type = media['type']
+        if 'Audio' in media_type:
+            relinker_info = {
+                'formats': {
+                    'format_id': media.get('formatoAudio'),
+                    'url': media['audioUrl'],
+                    'ext': media.get('formatoAudio'),
+                }
+            }
+        elif 'Video' in media_type:
+            relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)
+        else:
+            raise ExtractorError('not a media file')
+
+        self._sort_formats(relinker_info['formats'])
+
         thumbnails = []
         for image_type in ('image', 'image_medium', 'image_300'):
             thumbnail_url = media.get(image_type)
             if thumbnail_url:
                 thumbnails.append({
-                    'url': compat_urlparse.urljoin(base_url, thumbnail_url),
+                    'url': compat_urlparse.urljoin(url, thumbnail_url),
                 })
 
-        formats = []
-        media_type = media['type']
-        if 'Audio' in media_type:
-            formats.append({
-                'format_id': media.get('formatoAudio'),
-                'url': media['audioUrl'],
-                'ext': media.get('formatoAudio'),
-            })
-        elif 'Video' in media_type:
-            formats.extend(self._extract_relinker_formats(media['mediaUri'], content_id))
-            self._sort_formats(formats)
-        else:
-            raise ExtractorError('not a media file')
+        subtitles = self._extract_subtitles(url, media.get('subtitlesUrl'))
 
-        subtitles = {}
-        captions = media.get('subtitlesUrl')
-        if captions:
-            STL_EXT = '.stl'
-            SRT_EXT = '.srt'
-            if captions.endswith(STL_EXT):
-                captions = captions[:-len(STL_EXT)] + SRT_EXT
-            subtitles['it'] = [{
-                'ext': 'srt',
-                'url': captions,
-            }]
-
-        return {
+        info = {
             'id': content_id,
-            'title': media['name'],
-            'description': media.get('desc'),
+            'title': title,
+            'description': strip_or_none(media.get('desc')),
             'thumbnails': thumbnails,
             'uploader': media.get('author'),
             'upload_date': unified_strdate(media.get('date')),
             'duration': parse_duration(media.get('length')),
-            'formats': formats,
             'subtitles': subtitles,
         }
 
+        info.update(relinker_info)
 
-class RaiTVIE(RaiBaseIE):
-    _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+(?:media|ondemand)/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
-    _TESTS = [
-        {
-            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
-            'md5': '8970abf8caf8aef4696e7b1f2adfc696',
-            'info_dict': {
-                'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
-                'ext': 'mp4',
-                'title': 'Report del 07/04/2014',
-                'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
-                'upload_date': '20140407',
-                'duration': 6160,
-                'thumbnail': r're:^https?://.*\.jpg$',
-            }
-        },
-        {
-            # no m3u8 stream
-            'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
-            # HDS download, MD5 is unstable
-            'info_dict': {
-                'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
-                'ext': 'flv',
-                'title': 'TG PRIMO TEMPO',
-                'upload_date': '20140612',
-                'duration': 1758,
-                'thumbnail': r're:^https?://.*\.jpg$',
-            },
-            'skip': 'Geo-restricted to Italy',
-        },
-        {
-            'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
-            'md5': '35cf7c229f22eeef43e48b5cf923bef0',
-            'info_dict': {
-                'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
-                'ext': 'mp4',
-                'title': 'State of the Net, Antonella La Carpia: regole virali',
-                'description': 'md5:b0ba04a324126903e3da7763272ae63c',
-                'upload_date': '20140613',
-            },
-            'skip': 'Error 404',
-        },
-        {
-            'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
-            'info_dict': {
-                'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
-                'ext': 'mp4',
-                'title': 'Alluvione in Sardegna e dissesto idrogeologico',
-                'description': 'Edizione delle ore 20:30 ',
-            },
-            'skip': 'invalid urls',
-        },
-        {
-            'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
-            'md5': 'e57493e1cb8bc7c564663f363b171847',
-            'info_dict': {
-                'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
-                'ext': 'mp4',
-                'title': 'Il Candidato - Primo episodio: "Le Primarie"',
-                'description': 'md5:364b604f7db50594678f483353164fb8',
-                'upload_date': '20140923',
-                'duration': 386,
-                'thumbnail': r're:^https?://.*\.jpg$',
-            }
-        },
-    ]
+        return info
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        return self._extract_from_content_id(video_id, url)
-
-
-class RaiIE(RaiBaseIE):
-    _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
-    _TESTS = [
-        {
-            'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
-            'md5': '2dd727e61114e1ee9c47f0da6914e178',
-            'info_dict': {
-                'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
-                'ext': 'mp4',
-                'title': 'Il pacco',
-                'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
-                'upload_date': '20141221',
-            },
-        },
-        {
-            # Direct relinker URL
-            'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
-            # HDS live stream, MD5 is unstable
-            'info_dict': {
-                'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
-                'ext': 'flv',
-                'title': 'EuroNews',
-            },
-            'skip': 'Geo-restricted to Italy',
-        },
-        {
-            # Embedded content item ID
-            'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
-            'md5': '84c1135ce960e8822ae63cec34441d63',
-            'info_dict': {
-                'id': '0960e765-62c8-474a-ac4b-7eb3e2be39c8',
-                'ext': 'mp4',
-                'title': 'TG1 ore 20:00 del 02/07/2016',
-                'upload_date': '20160702',
-            },
-        },
-        {
-            'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
-            # HDS live stream, MD5 is unstable
-            'info_dict': {
-                'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
-                'ext': 'flv',
-                'title': 'La diretta di Rainews24',
-            },
-        },
-    ]
-
-    @classmethod
-    def suitable(cls, url):
-        return False if RaiTVIE.suitable(url) else super(RaiIE, cls).suitable(url)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        iframe_url = self._search_regex(
-            [r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
-             r'drawMediaRaiTV\(["\'](.+?)["\']'],
-            webpage, 'iframe', default=None)
-        if iframe_url:
-            if not iframe_url.startswith('http'):
-                iframe_url = compat_urlparse.urljoin(url, iframe_url)
-            return self.url_result(iframe_url)
+        content_item_id = None
 
-        content_item_id = self._search_regex(
-            r'initEdizione\((?P<q1>[\'"])ContentItem-(?P<content_id>[^\'"]+)(?P=q1)',
-            webpage, 'content item ID', group='content_id', default=None)
+        content_item_url = self._html_search_meta(
+            ('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
+             'twitter:player', 'jsonlink'), webpage, default=None)
+        if content_item_url:
+            content_item_id = self._search_regex(
+                r'ContentItem-(%s)' % self._UUID_RE, content_item_url,
+                'content item id', default=None)
+
+        if not content_item_id:
+            content_item_id = self._search_regex(
+                r'''(?x)
+                    (?:
+                        (?:initEdizione|drawMediaRaiTV)\(|
+                        <(?:[^>]+\bdata-id|var\s+uniquename)=
+                    )
+                    (["\'])
+                    (?:(?!\1).)*\bContentItem-(?P<id>%s)
+                ''' % self._UUID_RE,
+                webpage, 'content item id', default=None, group='id')
+
+        content_item_ids = set()
         if content_item_id:
-            return self._extract_from_content_id(content_item_id, url)
+            content_item_ids.add(content_item_id)
+        if video_id not in content_item_ids:
+            content_item_ids.add(video_id)
 
-        relinker_url = compat_urlparse.urljoin(url, self._search_regex(
-            r'(?:var\s+videoURL|mediaInfo\.mediaUri)\s*=\s*(?P<q1>[\'"])(?P<url>(https?:)?//mediapolis\.rai\.it/relinker/relinkerServlet\.htm\?cont=\d+)(?P=q1)',
-            webpage, 'relinker URL', group='url'))
-        formats = self._extract_relinker_formats(relinker_url, video_id)
-        self._sort_formats(formats)
+        for content_item_id in content_item_ids:
+            try:
+                return self._extract_from_content_id(content_item_id, url)
+            except GeoRestrictedError:
+                raise
+            except ExtractorError:
+                pass
+
+        relinker_url = self._search_regex(
+            r'''(?x)
+                (?:
+                    var\s+videoURL|
+                    mediaInfo\.mediaUri
+                )\s*=\s*
+                ([\'"])
+                (?P<url>
+                    (?:https?:)?
+                    //mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
+                    (?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
+            ''',
+            webpage, 'relinker URL', group='url')
+
+        relinker_info = self._extract_relinker_info(
+            urljoin(url, relinker_url), video_id)
+        self._sort_formats(relinker_info['formats'])
 
         title = self._search_regex(
             r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1',
-            webpage, 'title', group='title', default=None) or self._og_search_title(webpage)
+            webpage, 'title', group='title',
+            default=None) or self._og_search_title(webpage)
 
-        return {
+        info = {
             'id': video_id,
             'title': title,
-            'formats': formats,
         }
+
+        info.update(relinker_info)
+
+        return info

youtube_dl/extractor/rbmaradio.py

@@ -13,15 +13,15 @@ from ..utils import (
 
 
 class RBMARadioIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:rbmaradio|redbullradio)\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
     _TEST = {
         'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011',
         'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
         'info_dict': {
             'id': 'ford-lopatin-live-at-primavera-sound-2011',
             'ext': 'mp3',
-            'title': 'Main Stage - Ford & Lopatin',
-            'description': 'md5:4f340fb48426423530af5a9d87bd7b91',
+            'title': 'Main Stage - Ford & Lopatin at Primavera Sound',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
             'thumbnail': r're:^https?://.*\.jpg',
             'duration': 2452,
             'timestamp': 1307103164,

youtube_dl/extractor/rtl2.py

@@ -1,13 +1,26 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..aes import aes_cbc_decrypt
+from ..compat import (
+    compat_ord,
+    compat_str,
+)
+from ..utils import (
+    bytes_to_intlist,
+    ExtractorError,
+    intlist_to_bytes,
+    int_or_none,
+    strip_or_none,
+)
 
 
 class RTL2IE(InfoExtractor):
+    IE_NAME = 'rtl2'
     _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
     _TESTS = [{
         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
@@ -98,3 +111,98 @@ class RTL2IE(InfoExtractor):
             'duration': int_or_none(video_info.get('duration')),
             'formats': formats,
         }
+
+
+class RTL2YouBaseIE(InfoExtractor):
+    _BACKWERK_BASE_URL = 'https://p-you-backwerk.rtl2apps.de/'
+
+
+class RTL2YouIE(RTL2YouBaseIE):
+    IE_NAME = 'rtl2:you'
+    _VALID_URL = r'http?://you\.rtl2\.de/(?:video/\d+/|youplayer/index\.html\?.*?\bvid=)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://you.rtl2.de/video/3002/15740/MJUNIK%20%E2%80%93%20Home%20of%20YOU/307-hirn-wo-bist-du',
+        'info_dict': {
+            'id': '15740',
+            'ext': 'mp4',
+            'title': 'MJUNIK – Home of YOU - #307 Hirn, wo bist du?!',
+            'description': 'md5:ddaa95c61b372b12b66e115b2772fe01',
+            'age_limit': 12,
+        },
+    }, {
+        'url': 'http://you.rtl2.de/youplayer/index.html?vid=15712',
+        'only_matching': True,
+    }]
+    _AES_KEY = b'\xe9W\xe4.<*\xb8\x1a\xd2\xb6\x92\xf3C\xd3\xefL\x1b\x03*\xbbbH\xc0\x03\xffo\xc2\xf2(\xaa\xaa!'
+    _GEO_COUNTRIES = ['DE']
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        stream_data = self._download_json(
+            self._BACKWERK_BASE_URL + 'stream/video/' + video_id, video_id)
+
+        data, iv = base64.b64decode(stream_data['streamUrl']).decode().split(':')
+        stream_url = intlist_to_bytes(aes_cbc_decrypt(
+            bytes_to_intlist(base64.b64decode(data)),
+            bytes_to_intlist(self._AES_KEY),
+            bytes_to_intlist(base64.b64decode(iv))
+        ))
+        if b'rtl2_you_video_not_found' in stream_url:
+            raise ExtractorError('video not found', expected=True)
+
+        formats = self._extract_m3u8_formats(
+            stream_url[:-compat_ord(stream_url[-1])].decode(),
+            video_id, 'mp4', 'm3u8_native')
+        self._sort_formats(formats)
+
+        video_data = self._download_json(
+            self._BACKWERK_BASE_URL + 'video/' + video_id, video_id)
+
+        series = video_data.get('formatTitle')
+        title = episode = video_data.get('title') or series
+        if series and series != title:
+            title = '%s - %s' % (series, title)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': strip_or_none(video_data.get('description')),
+            'thumbnail': video_data.get('image'),
+            'duration': int_or_none(stream_data.get('duration') or video_data.get('duration'), 1000),
+            'series': series,
+            'episode': episode,
+            'age_limit': int_or_none(video_data.get('minimumAge')),
+        }
+
+
+class RTL2YouSeriesIE(RTL2YouBaseIE):
+    IE_NAME = 'rtl2:you:series'
+    _VALID_URL = r'http?://you\.rtl2\.de/videos/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://you.rtl2.de/videos/115/dragon-ball',
+        'info_dict': {
+            'id': '115',
+        },
+        'playlist_mincount': 5,
+    }
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        stream_data = self._download_json(
+            self._BACKWERK_BASE_URL + 'videos',
+            series_id, query={
+                'formatId': series_id,
+                'limit': 1000000000,
+            })
+
+        entries = []
+        for video in stream_data.get('videos', []):
+            video_id = compat_str(video['videoId'])
+            if not video_id:
+                continue
+            entries.append(self.url_result(
+                'http://you.rtl2.de/video/%s/%s' % (series_id, video_id),
+                'RTL2You', video_id))
+        return self.playlist_result(entries, series_id)

youtube_dl/extractor/rudo.py

@@ -26,7 +26,7 @@ class RudoIE(InfoExtractor):
     }
 
     @classmethod
-    def _extract_url(self, webpage):
+    def _extract_url(cls, webpage):
         mobj = re.search(
             r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
             webpage)

youtube_dl/extractor/thesun.py

@@ -0,0 +1,32 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .ooyala import OoyalaIE
+
+
+class TheSunIE(InfoExtractor):
+    _VALID_URL = r'https://(?:www\.)?thesun\.co\.uk/[^/]+/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.thesun.co.uk/tvandshowbiz/2261604/orlando-bloom-and-katy-perry-post-adorable-instagram-video-together-celebrating-thanksgiving-after-split-rumours/',
+        'info_dict': {
+            'id': '2261604',
+            'title': 'md5:cba22f48bad9218b64d5bbe0e16afddf',
+        },
+        'playlist_count': 2,
+    }
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, article_id)
+
+        entries = []
+        for ooyala_id in re.findall(
+                r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)',
+                webpage):
+            entries.append(OoyalaIE._build_url_result(ooyala_id))
+
+        return self.playlist_result(
+            entries, article_id, self._og_search_title(webpage, fatal=False))

youtube_dl/extractor/tv2hu.py

@@ -0,0 +1,62 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class TV2HuIE(InfoExtractor):
+    IE_NAME = 'tv2.hu'
+    _VALID_URL = r'https?://(?:www\.)?tv2\.hu/(?:[^/]+/)+(?P<id>\d+)_[^/?#]+?\.html'
+    _TESTS = [{
+        'url': 'http://tv2.hu/ezek_megorultek/217679_ezek-megorultek---1.-adas-1.-resz.html',
+        'md5': '585e58e2e090f34603804bb2c48e98d8',
+        'info_dict': {
+            'id': '217679',
+            'ext': 'mp4',
+            'title': 'Ezek megőrültek! - 1. adás 1. rész',
+            'upload_date': '20160826',
+            'thumbnail': r're:^https?://.*\.jpg$'
+        }
+    }, {
+        'url': 'http://tv2.hu/ezek_megorultek/teljes_adasok/217677_ezek-megorultek---1.-adas-2.-resz.html',
+        'only_matching': True
+    }, {
+        'url': 'http://tv2.hu/musoraink/aktiv/aktiv_teljes_adas/217963_aktiv-teljes-adas---2016.08.30..html',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        json_url = self._search_regex(
+            r'jsonUrl\s*=\s*"([^"]+)"', webpage, 'json url')
+        json_data = self._download_json(json_url, video_id)
+
+        formats = []
+        for b in ('bitrates', 'backupBitrates'):
+            bitrates = json_data.get(b, {})
+            m3u8_url = bitrates.get('hls')
+            if m3u8_url:
+                formats.extend(self._extract_wowza_formats(
+                    m3u8_url, video_id, skip_protocols=['rtmp', 'rtsp']))
+
+            for mp4_url in bitrates.get('mp4', []):
+                height = int_or_none(self._search_regex(
+                    r'\.(\d+)p\.mp4', mp4_url, 'height', default=None))
+                formats.append({
+                    'format_id': 'http' + ('-%d' % height if height else ''),
+                    'url': mp4_url,
+                    'height': height,
+                    'width': int_or_none(height / 9.0 * 16.0 if height else None),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage).strip(),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'upload_date': self._search_regex(
+                r'/vod/(\d{8})/', json_url, 'upload_date', default=None),
+            'formats': formats,
+        }

youtube_dl/extractor/tv5mondeplus.py

@@ -0,0 +1,79 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    determine_ext,
+    extract_attributes,
+    get_element_by_class,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)
+
+
+class TV5MondePlusIE(InfoExtractor):
+    IE_DESC = 'TV5MONDE+'
+    _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
+        'md5': '12130fc199f020673138a83466542ec6',
+        'info_dict': {
+            'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
+            'ext': 'mp4',
+            'title': 'Tdah, mon amour - Enfants',
+            'description': 'md5:230e3aca23115afcf8006d1bece6df74',
+            'upload_date': '20170401',
+            'timestamp': 1491022860,
+        }
+    }
+    _GEO_BYPASS = False
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
+            self.raise_geo_restricted(countries=['FR'])
+
+        series = get_element_by_class('video-detail__title', webpage)
+        title = episode = get_element_by_class(
+            'video-detail__subtitle', webpage) or series
+        if series and series != title:
+            title = '%s - %s' % (series, title)
+        vpl_data = extract_attributes(self._search_regex(
+            r'(<[^>]+class="video_player_loader"[^>]+>)',
+            webpage, 'video player loader'))
+
+        video_files = self._parse_json(
+            vpl_data['data-broadcast'], display_id).get('files', [])
+        formats = []
+        for video_file in video_files:
+            v_url = video_file.get('url')
+            if not v_url:
+                continue
+            video_format = video_file.get('format') or determine_ext(v_url)
+            if video_format == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    v_url, display_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'url': v_url,
+                    'format_id': video_format,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': display_id,
+            'display_id': display_id,
+            'title': title,
+            'description': clean_html(get_element_by_class('video-detail__description', webpage)),
+            'thumbnail': vpl_data.get('data-image'),
+            'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
+            'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)),
+            'formats': formats,
+            'episode': episode,
+            'series': series,
+        }

youtube_dl/extractor/tvplay.py

@@ -225,7 +225,11 @@ class TVPlayIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
+        geo_country = self._search_regex(
+            r'https?://[^/]+\.([a-z]{2})', url,
+            'geo country', default=None)
+        if geo_country:
+            self._initialize_geo_bypass([geo_country.upper()])
         video = self._download_json(
             'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')
 

youtube_dl/extractor/vier.py

@@ -9,6 +9,7 @@ from .common import InfoExtractor
 
 class VierIE(InfoExtractor):
     IE_NAME = 'vier'
+    IE_DESC = 'vier.be and vijf.be'
     _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
     _TESTS = [{
         'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',

youtube_dl/extractor/viewlift.py

@@ -68,7 +68,7 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
             type_ = source.get('type')
             ext = determine_ext(file_)
             format_id = source.get('label') or ext
-            if all(v == 'm3u8' or v == 'hls' for v in (type_, ext)):
+            if all(v in ('m3u8', 'hls') for v in (type_, ext)):
                 formats.extend(self._extract_m3u8_formats(
                     file_, video_id, 'mp4', m3u8_id='hls'))
             else:

youtube_dl/extractor/vlive.py

@@ -70,9 +70,9 @@ class VLiveIE(InfoExtractor):
         status, long_video_id, key = params[2], params[5], params[6]
         status = remove_start(status, 'PRODUCT_')
 
-        if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
+        if status in ('LIVE_ON_AIR', 'BIG_EVENT_ON_AIR'):
             return self._live(video_id, webpage)
-        elif status == 'VOD_ON_AIR' or status == 'BIG_EVENT_INTRO':
+        elif status in ('VOD_ON_AIR', 'BIG_EVENT_INTRO'):
             if long_video_id and key:
                 return self._replay(video_id, webpage, long_video_id, key)
             else:

youtube_dl/extractor/vrt.py

@@ -10,6 +10,7 @@ from ..utils import (
 
 
 class VRTIE(InfoExtractor):
+    IE_DESC = 'deredactie.be, sporza.be, cobra.be and cobra.canvas.be'
     _VALID_URL = r'https?://(?:deredactie|sporza|cobra(?:\.canvas)?)\.be/cm/(?:[^/]+/)+(?P<id>[^/]+)/*'
     _TESTS = [
         # deredactie.be

youtube_dl/extractor/vrv.py

@@ -0,0 +1,191 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+import json
+import hashlib
+import hmac
+import random
+import string
+import time
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_urlencode,
+    compat_urlparse,
+)
+from ..utils import (
+    float_or_none,
+    int_or_none,
+)
+
+
+class VRVBaseIE(InfoExtractor):
+    _API_DOMAIN = None
+    _API_PARAMS = {}
+    _CMS_SIGNING = {}
+
+    def _call_api(self, path, video_id, note, data=None):
+        base_url = self._API_DOMAIN + '/core/' + path
+        encoded_query = compat_urllib_parse_urlencode({
+            'oauth_consumer_key': self._API_PARAMS['oAuthKey'],
+            'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]),
+            'oauth_signature_method': 'HMAC-SHA1',
+            'oauth_timestamp': int(time.time()),
+            'oauth_version': '1.0',
+        })
+        headers = self.geo_verification_headers()
+        if data:
+            data = json.dumps(data).encode()
+            headers['Content-Type'] = 'application/json'
+        method = 'POST' if data else 'GET'
+        base_string = '&'.join([method, compat_urlparse.quote(base_url, ''), compat_urlparse.quote(encoded_query, '')])
+        oauth_signature = base64.b64encode(hmac.new(
+            (self._API_PARAMS['oAuthSecret'] + '&').encode('ascii'),
+            base_string.encode(), hashlib.sha1).digest()).decode()
+        encoded_query += '&oauth_signature=' + compat_urlparse.quote(oauth_signature, '')
+        return self._download_json(
+            '?'.join([base_url, encoded_query]), video_id,
+            note='Downloading %s JSON metadata' % note, headers=headers, data=data)
+
+    def _call_cms(self, path, video_id, note):
+        if not self._CMS_SIGNING:
+            self._CMS_SIGNING = self._call_api('index', video_id, 'CMS Signing')['cms_signing']
+        return self._download_json(
+            self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING,
+            note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers())
+
+    def _set_api_params(self, webpage, video_id):
+        if not self._API_PARAMS:
+            self._API_PARAMS = self._parse_json(self._search_regex(
+                r'window\.__APP_CONFIG__\s*=\s*({.+?})</script>',
+                webpage, 'api config'), video_id)['cxApiParams']
+            self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co')
+
+    def _get_cms_resource(self, resource_key, video_id):
+        return self._call_api(
+            'cms_resource', video_id, 'resource path', data={
+                'resource_key': resource_key,
+            })['__links__']['cms_resource']['href']
+
+
+class VRVIE(VRVBaseIE):
+    IE_NAME = 'vrv'
+    _VALID_URL = r'https?://(?:www\.)?vrv\.co/watch/(?P<id>[A-Z0-9]+)'
+    _TEST = {
+        'url': 'https://vrv.co/watch/GR9PNZ396/Hidden-America-with-Jonah-Ray:BOSTON-WHERE-THE-PAST-IS-THE-PRESENT',
+        'info_dict': {
+            'id': 'GR9PNZ396',
+            'ext': 'mp4',
+            'title': 'BOSTON: WHERE THE PAST IS THE PRESENT',
+            'description': 'md5:4ec8844ac262ca2df9e67c0983c6b83f',
+            'uploader_id': 'seeso',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, video_id,
+            headers=self.geo_verification_headers())
+        media_resource = self._parse_json(self._search_regex(
+            r'window\.__INITIAL_STATE__\s*=\s*({.+?})</script>',
+            webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {}
+
+        video_data = media_resource.get('json')
+        if not video_data:
+            self._set_api_params(webpage, video_id)
+            episode_path = self._get_cms_resource(
+                'cms:/episodes/' + video_id, video_id)
+            video_data = self._call_cms(episode_path, video_id, 'video')
+        title = video_data['title']
+
+        streams_json = media_resource.get('streams', {}).get('json', {})
+        if not streams_json:
+            self._set_api_params(webpage, video_id)
+            streams_path = video_data['__links__']['streams']['href']
+            streams_json = self._call_cms(streams_path, video_id, 'streams')
+
+        audio_locale = streams_json.get('audio_locale')
+        formats = []
+        for stream_id, stream in streams_json.get('streams', {}).get('adaptive_hls', {}).items():
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            stream_id = stream_id or audio_locale
+            m3u8_formats = self._extract_m3u8_formats(
+                stream_url, video_id, 'mp4', m3u8_id=stream_id,
+                note='Downloading %s m3u8 information' % stream_id,
+                fatal=False)
+            if audio_locale:
+                for f in m3u8_formats:
+                    f['language'] = audio_locale
+            formats.extend(m3u8_formats)
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for thumbnail in video_data.get('images', {}).get('thumbnails', []):
+            thumbnail_url = thumbnail.get('source')
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int_or_none(thumbnail.get('width')),
+                'height': int_or_none(thumbnail.get('height')),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': video_data.get('description'),
+            'duration': float_or_none(video_data.get('duration_ms'), 1000),
+            'uploader_id': video_data.get('channel_id'),
+            'series': video_data.get('series_title'),
+            'season': video_data.get('season_title'),
+            'season_number': int_or_none(video_data.get('season_number')),
+            'season_id': video_data.get('season_id'),
+            'episode': title,
+            'episode_number': int_or_none(video_data.get('episode_number')),
+            'episode_id': video_data.get('production_episode_id'),
+        }
+
+
+class VRVSeriesIE(VRVBaseIE):
+    IE_NAME = 'vrv:series'
+    _VALID_URL = r'https?://(?:www\.)?vrv\.co/series/(?P<id>[A-Z0-9]+)'
+    _TEST = {
+        'url': 'https://vrv.co/series/G68VXG3G6/The-Perfect-Insider',
+        'info_dict': {
+            'id': 'G68VXG3G6',
+        },
+        'playlist_mincount': 11,
+    }
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        webpage = self._download_webpage(
+            url, series_id,
+            headers=self.geo_verification_headers())
+
+        self._set_api_params(webpage, series_id)
+        seasons_path = self._get_cms_resource(
+            'cms:/seasons?series_id=' + series_id, series_id)
+        seasons_data = self._call_cms(seasons_path, series_id, 'seasons')
+
+        entries = []
+        for season in seasons_data.get('items', []):
+            episodes_path = season['__links__']['season/episodes']['href']
+            episodes = self._call_cms(episodes_path, series_id, 'episodes')
+            for episode in episodes.get('items', []):
+                episode_id = episode['id']
+                entries.append(self.url_result(
+                    'https://vrv.co/watch/' + episode_id,
+                    'VRV', episode_id, episode.get('title')))
+
+        return self.playlist_result(entries, series_id)

youtube_dl/extractor/vshare.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class VShareIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?vshare\.io/[dv]/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://vshare.io/d/0f64ce6',
+        'md5': '16d7b8fef58846db47419199ff1ab3e7',
+        'info_dict': {
+            'id': '0f64ce6',
+            'title': 'vl14062007715967',
+            'ext': 'mp4',
+        }
+    }, {
+        'url': 'https://vshare.io/v/0f64ce6/width-650/height-430/1',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'https://vshare.io/d/%s' % video_id, video_id)
+
+        title = self._html_search_regex(
+            r'(?s)<div id="root-container">(.+?)<br/>', webpage, 'title')
+        video_url = self._search_regex(
+            r'<a[^>]+href=(["\'])(?P<url>(?:https?:)?//.+?)\1[^>]*>[Cc]lick\s+here',
+            webpage, 'video url', group='url')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+        }

youtube_dl/extractor/worldstarhiphop.py

@@ -1,12 +1,10 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class WorldStarHipHopIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?v=(?P<id>.*)'
+    _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?.*?\bv=(?P<id>[^&]+)'
     _TESTS = [{
         'url': 'http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO',
         'md5': '9d04de741161603bf7071bbf4e883186',
@@ -17,48 +15,26 @@ class WorldStarHipHopIE(InfoExtractor):
         }
     }, {
         'url': 'http://m.worldstarhiphop.com/android/video.php?v=wshh6a7q1ny0G34ZwuIO',
-        'md5': 'dc1c76c83ecc4190bb1eb143899b87d3',
-        'info_dict': {
-            'id': 'wshh6a7q1ny0G34ZwuIO',
-            'ext': 'mp4',
-            'title': 'KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!'
-        }
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        m_vevo_id = re.search(r'videoId=(.*?)&amp?', webpage)
-        if m_vevo_id is not None:
-            return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
 
-        video_url = self._search_regex(
-            [r'so\.addVariable\("file","(.*?)"\)',
-             r'<div class="artlist">\s*<a[^>]+href="([^"]+)">'],
-            webpage, 'video URL')
+        if not entries:
+            return self.url_result(url, 'Generic')
 
-        if 'youtube' in video_url:
-            return self.url_result(video_url, ie='Youtube')
-
-        video_title = self._html_search_regex(
+        title = self._html_search_regex(
             [r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
              r'<span[^>]+class="tc-sp-pinned-title">(.*)</span>'],
             webpage, 'title')
 
-        # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
-        thumbnail = self._html_search_regex(
-            r'rel="image_src" href="(.*)" />', webpage, 'thumbnail',
-            default=None)
-        if not thumbnail:
-            _title = r'candytitles.*>(.*)</span>'
-            mobj = re.search(_title, webpage)
-            if mobj is not None:
-                video_title = mobj.group(1)
-
-        return {
+        info = entries[0]
+        info.update({
             'id': video_id,
-            'url': video_url,
-            'title': video_title,
-            'thumbnail': thumbnail,
-        }
+            'title': title,
+        })
+        return info

youtube_dl/extractor/xfileshare.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     decode_packed_codes,
+    determine_ext,
     ExtractorError,
     int_or_none,
     NO_DEFAULT,
@@ -26,6 +27,9 @@ class XFileShareIE(InfoExtractor):
         ('vidto.me', 'Vidto'),
         ('streamin.to', 'Streamin.To'),
         ('xvidstage.com', 'XVIDSTAGE'),
+        ('vidabc.com', 'Vid ABC'),
+        ('vidbom.com', 'VidBom'),
+        ('vidlo.us', 'vidlo'),
     )
 
     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
@@ -95,6 +99,16 @@ class XFileShareIE(InfoExtractor):
         # removed by administrator
         'url': 'http://xvidstage.com/amfy7atlkx25',
         'only_matching': True,
+    }, {
+        'url': 'http://vidabc.com/i8ybqscrphfv',
+        'info_dict': {
+            'id': 'i8ybqscrphfv',
+            'ext': 'mp4',
+            'title': 're:Beauty and the Beast 2017',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):
@@ -133,31 +147,45 @@ class XFileShareIE(InfoExtractor):
             webpage, 'title', default=None) or self._og_search_title(
             webpage, default=None) or video_id).strip()
 
-        def extract_video_url(default=NO_DEFAULT):
-            return self._search_regex(
-                (r'file\s*:\s*(["\'])(?P<url>http.+?)\1,',
-                 r'file_link\s*=\s*(["\'])(?P<url>http.+?)\1',
-                 r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http.+?)\2\)',
-                 r'<embed[^>]+src=(["\'])(?P<url>http.+?)\1'),
-                webpage, 'file url', default=default, group='url')
+        def extract_formats(default=NO_DEFAULT):
+            urls = []
+            for regex in (
+                    r'file\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
+                    r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
+                    r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
+                    r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
+                for mobj in re.finditer(regex, webpage):
+                    video_url = mobj.group('url')
+                    if video_url not in urls:
+                        urls.append(video_url)
+            formats = []
+            for video_url in urls:
+                if determine_ext(video_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls',
+                        fatal=False))
+                else:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': 'sd',
+                    })
+            if not formats and default is not NO_DEFAULT:
+                return default
+            self._sort_formats(formats)
+            return formats
 
-        video_url = extract_video_url(default=None)
+        formats = extract_formats(default=None)
 
-        if not video_url:
+        if not formats:
             webpage = decode_packed_codes(self._search_regex(
                 r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
                 webpage, 'packed code'))
-            video_url = extract_video_url()
+            formats = extract_formats()
 
         thumbnail = self._search_regex(
             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 
-        formats = [{
-            'format_id': 'sd',
-            'url': video_url,
-            'quality': 1,
-        }]
-
         return {
             'id': video_id,
             'title': title,

youtube_dl/extractor/youku.py

@@ -10,12 +10,14 @@ import time
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_urlencode,
     compat_ord,
+    compat_str,
+    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     ExtractorError,
     get_element_by_attribute,
+    try_get,
 )
 
 
@@ -105,7 +107,9 @@ class YoukuIE(InfoExtractor):
             if stream.get('channel_type') == 'tail':
                 continue
             format = stream.get('stream_type')
-            fileid = stream['stream_fileid']
+            fileid = try_get(
+                stream, lambda x: x['segs'][0]['fileid'],
+                compat_str) or stream['stream_fileid']
             fileid_dict[format] = fileid
 
         def get_fileid(format, n):

youtube_dl/extractor/youtube.py

@@ -317,60 +317,60 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
 
         # DASH mp4 video
-        '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},  # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
-        '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
-        '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
-        '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
-        '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
+        '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'},  # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
+        '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
+        '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
+        '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
+        '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
 
         # Dash mp4 audio
-        '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
-        '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
-        '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
-        '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
-        '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
-        '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'preference': -50, 'container': 'm4a_dash'},
-        '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'preference': -50, 'container': 'm4a_dash'},
+        '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
+        '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
+        '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
+        '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
+        '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
+        '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
+        '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
 
         # Dash webm
-        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
-        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
-        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
-        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
-        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
-        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
-        '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
-        '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
+        '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+        '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+        '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+        '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+        '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+        '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
+        '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
+        '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
         # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
-        '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
-        '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
-        '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
-        '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
-        '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
+        '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
+        '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
+        '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
+        '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
+        '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
 
         # Dash webm audio
-        '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
-        '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
+        '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
+        '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
 
         # Dash webm audio with opus inside
-        '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
-        '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
-        '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
+        '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
+        '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
+        '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
 
         # RTMP (unnamed)
         '_rtmp': {'protocol': 'rtmp'},
@@ -1253,21 +1253,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         video_id = mobj.group(2)
         return video_id
 
-    def _extract_from_m3u8(self, manifest_url, video_id):
-        url_map = {}
-
-        def _get_urls(_manifest):
-            lines = _manifest.split('\n')
-            urls = filter(lambda l: l and not l.startswith('#'),
-                          lines)
-            return urls
-        manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
-        formats_urls = _get_urls(manifest)
-        for format_url in formats_urls:
-            itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
-            url_map[itag] = format_url
-        return url_map
-
     def _extract_annotations(self, video_id):
         url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
         return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
@@ -1573,19 +1558,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if self._downloader.params.get('writeannotations', False):
             video_annotations = self._extract_annotations(video_id)
 
-        def _map_to_format_list(urlmap):
-            formats = []
-            for itag, video_real_url in urlmap.items():
-                dct = {
-                    'format_id': itag,
-                    'url': video_real_url,
-                    'player_url': player_url,
-                }
-                if itag in self._formats:
-                    dct.update(self._formats[itag])
-                formats.append(dct)
-            return formats
-
         if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
             self.report_rtmp_download()
             formats = [{
@@ -1718,11 +1690,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 formats.append(dct)
         elif video_info.get('hlsvp'):
             manifest_url = video_info['hlsvp'][0]
-            url_map = self._extract_from_m3u8(manifest_url, video_id)
-            formats = _map_to_format_list(url_map)
-            # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
-            for a_format in formats:
+            formats = []
+            m3u8_formats = self._extract_m3u8_formats(
+                manifest_url, video_id, 'mp4', fatal=False)
+            for a_format in m3u8_formats:
+                itag = self._search_regex(
+                    r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
+                if itag:
+                    a_format['format_id'] = itag
+                    if itag in self._formats:
+                        dct = self._formats[itag].copy()
+                        dct.update(a_format)
+                        a_format = dct
+                a_format['player_url'] = player_url
+                # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
                 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
+                formats.append(a_format)
         else:
             unavailable_message = self._html_search_regex(
                 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',

youtube_dl/options.py

@@ -459,11 +459,11 @@ def parseOpts(overrideArguments=None):
     downloader.add_option(
         '--fragment-retries',
         dest='fragment_retries', metavar='RETRIES', default=10,
-        help='Number of retries for a fragment (default is %default), or "infinite" (DASH and hlsnative only)')
+        help='Number of retries for a fragment (default is %default), or "infinite" (DASH, hlsnative and ISM)')
     downloader.add_option(
         '--skip-unavailable-fragments',
         action='store_true', dest='skip_unavailable_fragments', default=True,
-        help='Skip unavailable fragments (DASH and hlsnative only)')
+        help='Skip unavailable fragments (DASH, hlsnative and ISM)')
     downloader.add_option(
         '--abort-on-unavailable-fragment',
         action='store_false', dest='skip_unavailable_fragments',

youtube_dl/postprocessor/ffmpeg.py

@@ -552,7 +552,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
             sub_filenames.append(old_file)
             new_file = subtitles_filename(filename, lang, new_ext)
 
-            if ext == 'dfxp' or ext == 'ttml' or ext == 'tt':
+            if ext in ('dfxp', 'ttml', 'tt'):
                 self._downloader.report_warning(
                     'You have requested to convert dfxp (TTML) subtitles into another format, '
                     'which results in style information loss')

youtube_dl/postprocessor/metadatafromtitle.py

@@ -26,7 +26,7 @@ class MetadataFromTitlePP(PostProcessor):
             regex += r'(?P<' + match.group(1) + '>.+)'
             lastpos = match.end()
         if lastpos < len(fmt):
-            regex += re.escape(fmt[lastpos:len(fmt)])
+            regex += re.escape(fmt[lastpos:])
         return regex
 
     def run(self, info):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.03.26'
+__version__ = '2017.04.15'