release 2017.11.26

[skip ci]

.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 *2017.10.29*. 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 Issues with outdated version will be rejected.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 **2017.10.29**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.11.26*. 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 Issues with outdated version will be rejected.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 **2017.11.26**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [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 2017.10.29
+[debug] youtube-dl version 2017.11.26
 [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: {}

ChangeLog

@@ -1,3 +1,72 @@
+version 2017.11.26
+
+Core
+* [extractor/common] Use final URL when dumping request (#14769)
+
+Extractors
+* [fczenit] Fix extraction
+- [firstpost] Remove extractor
+* [freespeech] Fix extraction
+* [nexx] Extract more formats
++ [openload] Add support for openload.link (#14763)
+* [empflix] Relax URL regular expression
+* [empflix] Fix extractrion
+* [tnaflix] Don't modify download URLs (#14811)
+- [gamersyde] Remove extractor
+* [francetv:generationwhat] Fix extraction
++ [massengeschmacktv] Add support for Massengeschmack TV
+* [fox9] Fix extraction
+* [faz] Fix extraction and add support for Perform Group embeds (#14714)
++ [performgroup] Add support for performgroup.com
++ [jwplatform] Add support for iframes (#14828)
+* [culturebox] Fix extraction (#14827)
+* [youku] Fix extraction; update ccode (#14815)
+* [livestream] Make SMIL extraction non fatal (#14792)
++ [drtuber] Add support for mobile URLs (#14772)
++ [spankbang] Add support for mobile URLs (#14771)
+* [instagram] Fix description, timestamp and counters extraction (#14755)
+
+
+version 2017.11.15
+
+Core
+* [common] Skip Apple FairPlay m3u8 manifests (#14741)
+* [YoutubeDL] Fix playlist range optimization for --playlist-items (#14740)
+
+Extractors
+* [vshare] Capture and output error message
+* [vshare] Fix extraction (#14473)
+* [crunchyroll] Extract old RTMP formats
+* [tva] Fix extraction (#14736)
+* [gamespot] Lower preference of HTTP formats (#14652)
+* [instagram:user] Fix extraction (#14699)
+* [ccma] Fix typo (#14730)
+- Remove sensitive data from logging in messages
+* [instagram:user] Fix extraction (#14699)
++ [gamespot] Add support for article URLs (#14652)
+* [gamespot] Skip Brightcove Once HTTP formats (#14652)
+* [cartoonnetwork] Update tokenizer_src (#14666)
++ [wsj] Recognize another URL pattern (#14704)
+* [pandatv] Update API URL and sign format URLs (#14693)
+* [crunchyroll] Use old login method (#11572)
+
+
+version 2017.11.06
+
+Core
++ [extractor/common] Add protocol for f4m formats
+* [f4m] Prefer baseURL for relative URLs (#14660)
+* [extractor/common] Respect URL query in _extract_wowza_formats (14645)
+
+Extractors
++ [hotstar:playlist] Add support for playlists (#12465)
+* [hotstar] Bypass geo restriction (#14672)
+- [22tracks] Remove extractor (#11024, #14628)
++ [skysport] Sdd support ooyala videos protected with embed_token (#14641)
+* [gamespot] Extract formats referenced with new data fields (#14652)
+* [spankbang] Detect unavailable videos (#14644)
+
+
 version 2017.10.29
 
 Core

Makefile

@@ -110,7 +110,6 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		--exclude '*~' \
 		--exclude '__pycache__' \
 		--exclude '.git' \
-		--exclude 'testdata' \
 		--exclude 'docs/_build' \
 		-- \
 		bin devscripts test youtube_dl docs \

docs/supportedsites.md

@@ -3,8 +3,6 @@
  - **1up.com**
  - **20min**
  - **220.ro**
- - **22tracks:genre**
- - **22tracks:track**
  - **24video**
  - **3qsdn**: 3Q SDN
  - **3sat**
@@ -268,10 +266,8 @@
  - **fc2**
  - **fc2:embed**
  - **Fczenit**
- - **fernsehkritik.tv**
  - **filmon**
  - **filmon:channel**
- - **Firstpost**
  - **FiveTV**
  - **Flickr**
  - **Flipagram**
@@ -285,7 +281,7 @@
  - **foxnews:article**
  - **foxnews:insider**
  - **FoxSports**
- - **france2.fr:generation-quoi**
+ - **france2.fr:generation-what**
  - **FranceCulture**
  - **FranceInter**
  - **FranceTV**
@@ -303,7 +299,6 @@
  - **GameInformer**
  - **GameOne**
  - **gameone:playlist**
- - **Gamersyde**
  - **GameSpot**
  - **GameStar**
  - **Gaskrank**
@@ -342,6 +337,7 @@
  - **HornBunny**
  - **HotNewHipHop**
  - **HotStar**
+ - **hotstar:playlist**
  - **Howcast**
  - **HowStuffWorks**
  - **HRTi**
@@ -442,6 +438,7 @@
  - **mangomolo:live**
  - **mangomolo:video**
  - **ManyVids**
+ - **massengeschmack.tv**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -609,6 +606,7 @@
  - **pcmag**
  - **PearVideo**
  - **People**
+ - **PerformGroup**
  - **periscope**: Periscope
  - **periscope:user**: Periscope user videos
  - **PhilharmonieDeParis**: Philharmonie de Paris

test/test_InfoExtractor.py

@@ -574,6 +574,32 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 self.ie._sort_formats(formats)
                 expect_value(self, formats, expected_formats, None)
 
+    def test_parse_f4m_formats(self):
+        _TEST_CASES = [
+            (
+                # https://github.com/rg3/youtube-dl/issues/14660
+                'custom_base_url',
+                'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
+                [{
+                    'manifest_url': 'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
+                    'ext': 'flv',
+                    'format_id': '2148',
+                    'protocol': 'f4m',
+                    'tbr': 2148,
+                    'width': 1280,
+                    'height': 720,
+                }]
+            ),
+        ]
+
+        for f4m_file, f4m_url, expected_formats in _TEST_CASES:
+            with io.open('./test/testdata/f4m/%s.f4m' % f4m_file,
+                         mode='r', encoding='utf-8') as f:
+                formats = self.ie._parse_f4m_formats(
+                    compat_etree_fromstring(f.read().encode('utf-8')),
+                    f4m_url, None)
+                self.ie._sort_formats(formats)
+                expect_value(self, formats, expected_formats, None)
 
 if __name__ == '__main__':
     unittest.main()

test/test_YoutubeDL.py

@@ -466,11 +466,11 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL({'simulate': True})
         self.assertEqual(ydl._default_format_spec({}), 'bestvideo+bestaudio/best')
 
-        ydl = YDL({'is_live': True})
-        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
 
-        ydl = YDL({'simulate': True, 'is_live': True})
-        self.assertEqual(ydl._default_format_spec({}), 'bestvideo+bestaudio/best')
+        ydl = YDL({'simulate': True})
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo+bestaudio/best')
 
         ydl = YDL({'outtmpl': '-'})
         self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')

test/testdata/f4m/custom_base_url.f4m

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest xmlns="http://ns.adobe.com/f4m/1.0">
+    <streamType>recorded</streamType>
+    <baseURL>http://vod.livestream.com/events/0000000000673980/</baseURL>
+    <duration>269.293</duration>
+    <bootstrapInfo profile="named" id="bootstrap_1">AAAAm2Fic3QAAAAAAAAAAQAAAAPoAAAAAAAEG+0AAAAAAAAAAAAAAAAAAQAAABlhc3J0AAAAAAAAAAABAAAAAQAAAC4BAAAAVmFmcnQAAAAAAAAD6AAAAAAEAAAAAQAAAAAAAAAAAAAXcAAAAC0AAAAAAAQHQAAAE5UAAAAuAAAAAAAEGtUAAAEYAAAAAAAAAAAAAAAAAAAAAAA=</bootstrapInfo>
+    <media url="b90f532f-b0f6-4f4e-8289-706d490b2fd8_2292" bootstrapInfoId="bootstrap_1" bitrate="2148" width="1280" height="720" videoCodec="avc1.4d401f" audioCodec="mp4a.40.2">
+        <metadata>AgAKb25NZXRhRGF0YQgAAAAIAAhkdXJhdGlvbgBAcNSwIMSbpgAFd2lkdGgAQJQAAAAAAAAABmhlaWdodABAhoAAAAAAAAAJZnJhbWVyYXRlAEA4/7DoLwW3AA12aWRlb2RhdGFyYXRlAECe1DLgjcobAAx2aWRlb2NvZGVjaWQAQBwAAAAAAAAADWF1ZGlvZGF0YXJhdGUAQGSimlvaPKQADGF1ZGlvY29kZWNpZABAJAAAAAAAAAAACQ==</metadata>
+    </media>
+</manifest>

youtube_dl/YoutubeDL.py

@@ -948,7 +948,8 @@ class YoutubeDL(object):
                 report_download(n_entries)
             else:  # iterable
                 if playlistitems:
-                    entries = make_playlistitems_entries(list(ie_entries))
+                    entries = make_playlistitems_entries(list(itertools.islice(
+                        ie_entries, 0, max(playlistitems))))
                 else:
                     entries = list(itertools.islice(
                         ie_entries, playliststart, playlistend))

youtube_dl/downloader/f4m.py

@@ -243,8 +243,17 @@ def remove_encrypted_media(media):
                        media))
 
 
-def _add_ns(prop):
-    return '{http://ns.adobe.com/f4m/1.0}%s' % prop
+def _add_ns(prop, ver=1):
+    return '{http://ns.adobe.com/f4m/%d.0}%s' % (ver, prop)
+
+
+def get_base_url(manifest):
+    base_url = xpath_text(
+        manifest, [_add_ns('baseURL'), _add_ns('baseURL', 2)],
+        'base URL', default=None)
+    if base_url:
+        base_url = base_url.strip()
+    return base_url
 
 
 class F4mFD(FragmentFD):
@@ -330,13 +339,13 @@ class F4mFD(FragmentFD):
             rate, media = list(filter(
                 lambda f: int(f[0]) == requested_bitrate, formats))[0]
 
-        base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
+        # Prefer baseURL for relative URLs as per 11.2 of F4M 3.0 spec.
+        man_base_url = get_base_url(doc) or man_url
+
+        base_url = compat_urlparse.urljoin(man_base_url, media.attrib['url'])
         bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
-        # From Adobe F4M 3.0 spec:
-        # The <baseURL> element SHALL be the base URL for all relative
-        # (HTTP-based) URLs in the manifest. If <baseURL> is not present, said
-        # URLs should be relative to the location of the containing document.
-        boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, man_url)
+        boot_info, bootstrap_url = self._parse_bootstrap_node(
+            bootstrap_node, man_base_url)
         live = boot_info['live']
         metadata_node = media.find(_add_ns('metadata'))
         if metadata_node is not None:

youtube_dl/extractor/animeondemand.py

@@ -78,7 +78,7 @@ class AnimeOnDemandIE(InfoExtractor):
             post_url = urljoin(self._LOGIN_URL, post_url)
 
         response = self._download_webpage(
-            post_url, None, 'Logging in as %s' % username,
+            post_url, None, 'Logging in',
             data=urlencode_postdata(login_form), headers={
                 'Referer': self._LOGIN_URL,
             })

youtube_dl/extractor/atresplayer.py

@@ -87,7 +87,7 @@ class AtresPlayerIE(InfoExtractor):
             self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         response = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+            request, None, 'Logging in')
 
         error = self._html_search_regex(
             r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>',

youtube_dl/extractor/bambuser.py

@@ -59,7 +59,7 @@ class BambuserIE(InfoExtractor):
             self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Referer', self._LOGIN_URL)
         response = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+            request, None, 'Logging in')
 
         login_error = self._html_search_regex(
             r'(?s)<div class="messages error">(.+?)</div>',

youtube_dl/extractor/cartoonnetwork.py

@@ -31,7 +31,7 @@ class CartoonNetworkIE(TurnerBaseIE):
             'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
                 'secure': {
                     'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
-                    'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
+                    'tokenizer_src': 'https://token.vgtf.net/token/token_mobile',
                 },
             }, {
                 'url': url,

youtube_dl/extractor/ccma.py

@@ -93,7 +93,7 @@ class CCMAIE(InfoExtractor):
             'description': clean_html(informacio.get('descripcio')),
             'duration': duration,
             'timestamp': timestamp,
-            'thumnails': thumbnails,
+            'thumbnails': thumbnails,
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/common.py

@@ -29,7 +29,10 @@ from ..compat import (
     compat_urlparse,
     compat_xml_parse_error,
 )
-from ..downloader.f4m import remove_encrypted_media
+from ..downloader.f4m import (
+    get_base_url,
+    remove_encrypted_media,
+)
 from ..utils import (
     NO_DEFAULT,
     age_restricted,
@@ -589,19 +592,11 @@ class InfoExtractor(object):
         if not encoding:
             encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
         if self._downloader.params.get('dump_intermediate_pages', False):
-            try:
-                url = url_or_request.get_full_url()
-            except AttributeError:
-                url = url_or_request
-            self.to_screen('Dumping request to ' + url)
+            self.to_screen('Dumping request to ' + urlh.geturl())
             dump = base64.b64encode(webpage_bytes).decode('ascii')
             self._downloader.to_screen(dump)
         if self._downloader.params.get('write_pages', False):
-            try:
-                url = url_or_request.get_full_url()
-            except AttributeError:
-                url = url_or_request
-            basen = '%s_%s' % (video_id, url)
+            basen = '%s_%s' % (video_id, urlh.geturl())
             if len(basen) > 240:
                 h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
                 basen = basen[:240 - len(h)] + h
@@ -1239,11 +1234,8 @@ class InfoExtractor(object):
         media_nodes = remove_encrypted_media(media_nodes)
         if not media_nodes:
             return formats
-        base_url = xpath_text(
-            manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'],
-            'base URL', default=None)
-        if base_url:
-            base_url = base_url.strip()
+
+        manifest_base_url = get_base_url(manifest)
 
         bootstrap_info = xpath_element(
             manifest, ['{http://ns.adobe.com/f4m/1.0}bootstrapInfo', '{http://ns.adobe.com/f4m/2.0}bootstrapInfo'],
@@ -1275,7 +1267,7 @@ class InfoExtractor(object):
                     continue
                 manifest_url = (
                     media_url if media_url.startswith('http://') or media_url.startswith('https://')
-                    else ((base_url or '/'.join(manifest_url.split('/')[:-1])) + '/' + media_url))
+                    else ((manifest_base_url or '/'.join(manifest_url.split('/')[:-1])) + '/' + media_url))
                 # If media_url is itself a f4m manifest do the recursive extraction
                 # since bitrates in parent manifest (this one) and media_url manifest
                 # may differ leading to inability to resolve the format by requested
@@ -1310,6 +1302,7 @@ class InfoExtractor(object):
                 'url': manifest_url,
                 'manifest_url': manifest_url,
                 'ext': 'flv' if bootstrap_info is not None else None,
+                'protocol': 'f4m',
                 'tbr': tbr,
                 'width': width,
                 'height': height,
@@ -1355,6 +1348,9 @@ class InfoExtractor(object):
         if '#EXT-X-FAXS-CM:' in m3u8_doc:  # Adobe Flash Access
             return []
 
+        if re.search(r'#EXT-X-SESSION-KEY:.*?URI="skd://', m3u8_doc):  # Apple FairPlay
+            return []
+
         formats = []
 
         format_url = lambda u: (
@@ -2233,27 +2229,35 @@ class InfoExtractor(object):
         return formats
 
     def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
+        query = compat_urlparse.urlparse(url).query
         url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)
         url_base = self._search_regex(
             r'(?:(?:https?|rtmp|rtsp):)?(//[^?]+)', url, 'format url')
         http_base_url = '%s:%s' % ('http', url_base)
         formats = []
+
+        def manifest_url(manifest):
+            m_url = '%s/%s' % (http_base_url, manifest)
+            if query:
+                m_url += '?%s' % query
+            return m_url
+
         if 'm3u8' not in skip_protocols:
             formats.extend(self._extract_m3u8_formats(
-                http_base_url + '/playlist.m3u8', video_id, 'mp4',
+                manifest_url('playlist.m3u8'), video_id, 'mp4',
                 m3u8_entry_protocol, m3u8_id='hls', fatal=False))
         if 'f4m' not in skip_protocols:
             formats.extend(self._extract_f4m_formats(
-                http_base_url + '/manifest.f4m',
+                manifest_url('manifest.f4m'),
                 video_id, f4m_id='hds', fatal=False))
         if 'dash' not in skip_protocols:
             formats.extend(self._extract_mpd_formats(
-                http_base_url + '/manifest.mpd',
+                manifest_url('manifest.mpd'),
                 video_id, mpd_id='dash', fatal=False))
         if re.search(r'(?:/smil:|\.smil)', url_base):
             if 'smil' not in skip_protocols:
                 rtmp_formats = self._extract_smil_formats(
-                    http_base_url + '/jwplayer.smil',
+                    manifest_url('jwplayer.smil'),
                     video_id, fatal=False)
                 for rtmp_format in rtmp_formats:
                     rtsp_format = rtmp_format.copy()

youtube_dl/extractor/crunchyroll.py

@@ -38,11 +38,32 @@ class CrunchyrollBaseIE(InfoExtractor):
     _LOGIN_FORM = 'login_form'
     _NETRC_MACHINE = 'crunchyroll'
 
+    def _call_rpc_api(self, method, video_id, note=None, data=None):
+        data = data or {}
+        data['req'] = 'RpcApi' + method
+        data = compat_urllib_parse_urlencode(data).encode('utf-8')
+        return self._download_xml(
+            'http://www.crunchyroll.com/xml/',
+            video_id, note, fatal=False, data=data, headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+            })
+
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
             return
 
+        self._download_webpage(
+            'https://www.crunchyroll.com/?a=formhandler',
+            None, 'Logging in', 'Wrong login info',
+            data=urlencode_postdata({
+                'formname': 'RpcApiUser_Login',
+                'next_url': 'https://www.crunchyroll.com/acct/membership',
+                'name': username,
+                'password': password,
+            }))
+
+        '''
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
@@ -86,6 +107,7 @@ class CrunchyrollBaseIE(InfoExtractor):
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
         raise ExtractorError('Unable to log in')
+        '''
 
     def _real_initialize(self):
         self._login()
@@ -365,15 +387,19 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
     def _get_subtitles(self, video_id, webpage):
         subtitles = {}
         for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
-            sub_page = self._download_webpage(
-                'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
-                video_id, note='Downloading subtitles for ' + sub_name)
-            id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
-            iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
-            data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
-            if not id or not iv or not data:
+            sub_doc = self._call_rpc_api(
+                'Subtitle_GetXml', video_id,
+                'Downloading subtitles for ' + sub_name, data={
+                    'subtitle_script_id': sub_id,
+                })
+            if not sub_doc:
                 continue
-            subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
+            sid = sub_doc.get('id')
+            iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
+            data = xpath_text(sub_doc, 'data', 'subtitle data')
+            if not sid or not iv or not data:
+                continue
+            subtitle = self._decrypt_subtitles(data, iv, sid).decode('utf-8')
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
@@ -444,65 +470,79 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         for fmt in available_fmts:
             stream_quality, stream_format = self._FORMAT_IDS[fmt]
             video_format = fmt + 'p'
-            streamdata_req = sanitized_Request(
-                'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
-                % (video_id, stream_format, stream_quality),
-                compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8'))
-            streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            streamdata = self._download_xml(
-                streamdata_req, video_id,
-                note='Downloading media info for %s' % video_format)
-            stream_info = streamdata.find('./{default}preload/stream_info')
-            video_encode_id = xpath_text(stream_info, './video_encode_id')
-            if video_encode_id in video_encode_ids:
-                continue
-            video_encode_ids.append(video_encode_id)
+            stream_infos = []
+            streamdata = self._call_rpc_api(
+                'VideoPlayer_GetStandardConfig', video_id,
+                'Downloading media info for %s' % video_format, data={
+                    'media_id': video_id,
+                    'video_format': stream_format,
+                    'video_quality': stream_quality,
+                    'current_page': url,
+                })
+            if streamdata:
+                stream_info = streamdata.find('./{default}preload/stream_info')
+                if stream_info:
+                    stream_infos.append(stream_info)
+            stream_info = self._call_rpc_api(
+                'VideoEncode_GetStreamInfo', video_id,
+                'Downloading stream info for %s' % video_format, data={
+                    'media_id': video_id,
+                    'video_format': stream_format,
+                    'video_encode_quality': stream_quality,
+                })
+            if stream_info:
+                stream_infos.append(stream_info)
+            for stream_info in stream_infos:
+                video_encode_id = xpath_text(stream_info, './video_encode_id')
+                if video_encode_id in video_encode_ids:
+                    continue
+                video_encode_ids.append(video_encode_id)
 
-            video_file = xpath_text(stream_info, './file')
-            if not video_file:
-                continue
-            if video_file.startswith('http'):
-                formats.extend(self._extract_m3u8_formats(
-                    video_file, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
-                continue
-
-            video_url = xpath_text(stream_info, './host')
-            if not video_url:
-                continue
-            metadata = stream_info.find('./metadata')
-            format_info = {
-                'format': video_format,
-                'format_id': video_format,
-                'height': int_or_none(xpath_text(metadata, './height')),
-                'width': int_or_none(xpath_text(metadata, './width')),
-            }
-
-            if '.fplive.net/' in video_url:
-                video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
-                parsed_video_url = compat_urlparse.urlparse(video_url)
-                direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
-                    netloc='v.lvlt.crcdn.net',
-                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
-                if self._is_valid_url(direct_video_url, video_id, video_format):
-                    format_info.update({
-                        'url': direct_video_url,
-                    })
-                    formats.append(format_info)
+                video_file = xpath_text(stream_info, './file')
+                if not video_file:
+                    continue
+                if video_file.startswith('http'):
+                    formats.extend(self._extract_m3u8_formats(
+                        video_file, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
                     continue
 
-            format_info.update({
-                'url': video_url,
-                'play_path': video_file,
-                'ext': 'flv',
-            })
-            formats.append(format_info)
-        self._sort_formats(formats)
+                video_url = xpath_text(stream_info, './host')
+                if not video_url:
+                    continue
+                metadata = stream_info.find('./metadata')
+                format_info = {
+                    'format': video_format,
+                    'height': int_or_none(xpath_text(metadata, './height')),
+                    'width': int_or_none(xpath_text(metadata, './width')),
+                }
 
-        metadata = self._download_xml(
-            'http://www.crunchyroll.com/xml', video_id,
-            note='Downloading media info', query={
-                'req': 'RpcApiVideoPlayer_GetMediaMetadata',
+                if '.fplive.net/' in video_url:
+                    video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
+                    parsed_video_url = compat_urlparse.urlparse(video_url)
+                    direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
+                        netloc='v.lvlt.crcdn.net',
+                        path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
+                    if self._is_valid_url(direct_video_url, video_id, video_format):
+                        format_info.update({
+                            'format_id': 'http-' + video_format,
+                            'url': direct_video_url,
+                        })
+                        formats.append(format_info)
+                        continue
+
+                format_info.update({
+                    'format_id': 'rtmp-' + video_format,
+                    'url': video_url,
+                    'play_path': video_file,
+                    'ext': 'flv',
+                })
+                formats.append(format_info)
+        self._sort_formats(formats, ('height', 'width', 'tbr', 'fps'))
+
+        metadata = self._call_rpc_api(
+            'VideoPlayer_GetMediaMetadata', video_id,
+            note='Downloading media info', data={
                 'media_id': video_id,
             })
 

youtube_dl/extractor/dramafever.py

@@ -54,7 +54,7 @@ class DramaFeverBaseIE(AMPIE):
         request = sanitized_Request(
             self._LOGIN_URL, urlencode_postdata(login_form))
         response = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+            request, None, 'Logging in')
 
         if all(logout_pattern not in response
                for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):

youtube_dl/extractor/drtuber.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class DrTuberIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
     _TESTS = [{
         'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
         'md5': '93e680cf2536ad0dfb7e74d94a89facd',
@@ -28,6 +28,9 @@ class DrTuberIE(InfoExtractor):
     }, {
         'url': 'http://www.drtuber.com/embed/489939',
         'only_matching': True,
+    }, {
+        'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
+        'only_matching': True,
     }]
 
     @staticmethod

youtube_dl/extractor/extractors.py

@@ -344,11 +344,9 @@ from .filmon import (
     FilmOnIE,
     FilmOnChannelIE,
 )
-from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
 from .fivetv import FiveTVIE
-from .fktv import FKTVIE
 from .flickr import FlickrIE
 from .flipagram import FlipagramIE
 from .folketinget import FolketingetIE
@@ -375,7 +373,7 @@ from .francetv import (
     FranceTVIE,
     FranceTVEmbedIE,
     FranceTVInfoIE,
-    GenerationQuoiIE,
+    GenerationWhatIE,
     CultureboxIE,
 )
 from .freesound import FreesoundIE
@@ -391,7 +389,6 @@ from .gameone import (
     GameOneIE,
     GameOnePlaylistIE,
 )
-from .gamersyde import GamersydeIE
 from .gamespot import GameSpotIE
 from .gamestar import GameStarIE
 from .gaskrank import GaskrankIE
@@ -432,7 +429,10 @@ from .hitbox import HitboxIE, HitboxLiveIE
 from .hitrecord import HitRecordIE
 from .hornbunny import HornBunnyIE
 from .hotnewhiphop import HotNewHipHopIE
-from .hotstar import HotStarIE
+from .hotstar import (
+    HotStarIE,
+    HotStarPlaylistIE,
+)
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE
 from .hrti import (
@@ -569,6 +569,7 @@ from .mangomolo import (
     MangomoloLiveIE,
 )
 from .manyvids import ManyVidsIE
+from .massengeschmacktv import MassengeschmackTVIE
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .mediaset import MediasetIE
@@ -786,6 +787,7 @@ from .patreon import PatreonIE
 from .pbs import PBSIE
 from .pearvideo import PearVideoIE
 from .people import PeopleIE
+from .performgroup import PerformGroupIE
 from .periscope import (
     PeriscopeIE,
     PeriscopeUserIE,
@@ -1110,10 +1112,6 @@ from .tvplayer import TVPlayerIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
-from .twentytwotracks import (
-    TwentyTwoTracksIE,
-    TwentyTwoTracksGenreIE
-)
 from .twitch import (
     TwitchVideoIE,
     TwitchChapterIE,

youtube_dl/extractor/faz.py

@@ -1,7 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_etree_fromstring
 from ..utils import (
     xpath_element,
     xpath_text,
@@ -43,10 +46,15 @@ class FazIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
         description = self._og_search_description(webpage)
-        config_xml_url = self._search_regex(
-            r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url')
-        config = self._download_xml(
-            config_xml_url, video_id, 'Downloading config xml')
+        media = self._html_search_regex(
+            r"data-videojs-media='([^']+)",
+            webpage, 'media')
+        if media == 'extern':
+            perform_url = self._search_regex(
+                r"<iframe[^>]+?src='((?:http:)?//player\.performgroup\.com/eplayer/eplayer\.html#/?[0-9a-f]{26}\.[0-9a-z]{26})",
+                webpage, 'perform url')
+            return self.url_result(perform_url)
+        config = compat_etree_fromstring(media)
 
         encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
         formats = []
@@ -55,12 +63,24 @@ class FazIE(InfoExtractor):
             if encoding is not None:
                 encoding_url = xpath_text(encoding, 'FILENAME')
                 if encoding_url:
-                    formats.append({
+                    tbr = xpath_text(encoding, 'AVERAGEBITRATE', 1000)
+                    if tbr:
+                        tbr = int_or_none(tbr.replace(',', '.'))
+                    f = {
                         'url': encoding_url,
                         'format_id': code.lower(),
                         'quality': pref,
-                        'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')),
-                    })
+                        'tbr': tbr,
+                        'vcodec': xpath_text(encoding, 'CODEC'),
+                    }
+                    mobj = re.search(r'(\d+)x(\d+)_(\d+)\.mp4', encoding_url)
+                    if mobj:
+                        f.update({
+                            'width': int(mobj.group(1)),
+                            'height': int(mobj.group(2)),
+                            'tbr': tbr or int(mobj.group(3)),
+                        })
+                    formats.append(f)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/fczenit.py

@@ -2,7 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..utils import (
+    int_or_none,
+    float_or_none,
+)
 
 
 class FczenitIE(InfoExtractor):
@@ -14,6 +17,8 @@ class FczenitIE(InfoExtractor):
             'id': '41044',
             'ext': 'mp4',
             'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»',
+            'timestamp': 1462283735,
+            'upload_date': '20160503',
         },
     }
 
@@ -21,28 +26,31 @@ class FczenitIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        video_title = self._html_search_regex(
-            r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title')
+        msi_id = self._search_regex(
+            r"(?s)config\s*=\s*{.+?video_id\s*:\s*'([^']+)'", webpage, 'msi id')
 
-        video_items = self._parse_json(self._search_regex(
-            r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'),
-            video_id)
-
-        def merge_dicts(*dicts):
-            ret = {}
-            for a_dict in dicts:
-                ret.update(a_dict)
-            return ret
+        msi_data = self._download_json(
+            'http://player.fc-zenit.ru/msi/video', msi_id, query={
+                'video': msi_id,
+            })['data']
+        title = msi_data['name']
 
         formats = [{
-            'url': compat_urlparse.urljoin(url, video_url),
-            'tbr': int(tbr),
-        } for tbr, video_url in merge_dicts(*video_items).items()]
+            'format_id': q.get('label'),
+            'url': q['url'],
+            'height': int_or_none(q.get('label')),
+        } for q in msi_data['qualities'] if q.get('url')]
 
         self._sort_formats(formats)
 
+        tags = [tag['label'] for tag in msi_data.get('tags', []) if tag.get('label')]
+
         return {
             'id': video_id,
-            'title': video_title,
+            'title': title,
+            'thumbnail': msi_data.get('preview'),
             'formats': formats,
+            'duration': float_or_none(msi_data.get('duration')),
+            'timestamp': int_or_none(msi_data.get('date')),
+            'tags': tags,
         }

youtube_dl/extractor/firstpost.py

@@ -1,50 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class FirstpostIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
-
-    _TEST = {
-        'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
-        'md5': 'ee9114957692f01fb1263ed87039112a',
-        'info_dict': {
-            'id': '1025403',
-            'ext': 'mp4',
-            'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
-            'description': 'md5:feef3041cb09724e0bdc02843348f5f4',
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        page = self._download_webpage(url, video_id)
-
-        title = self._html_search_meta('twitter:title', page, 'title', fatal=True)
-        description = self._html_search_meta('twitter:description', page, 'title')
-
-        data = self._download_xml(
-            'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
-            'Downloading video XML')
-
-        item = data.find('./playlist/item')
-        thumbnail = item.find('./image').text
-
-        formats = [
-            {
-                'url': details.find('./file').text,
-                'format_id': details.find('./label').text.strip(),
-                'width': int(details.find('./width').text.strip()),
-                'height': int(details.find('./height').text.strip()),
-            } for details in item.findall('./source/file_details') if details.find('./file').text
-        ]
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'formats': formats,
-        }

youtube_dl/extractor/fktv.py

@@ -1,51 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    determine_ext,
-    js_to_json,
-)
-
-
-class FKTVIE(InfoExtractor):
-    IE_NAME = 'fernsehkritik.tv'
-    _VALID_URL = r'https?://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
-
-    _TEST = {
-        'url': 'http://fernsehkritik.tv/folge-1',
-        'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79',
-        'info_dict': {
-            'id': '1',
-            'ext': 'mp4',
-            'title': 'Folge 1 vom 10. April 2007',
-            'thumbnail': r're:^https?://.*\.jpg$',
-        },
-    }
-
-    def _real_extract(self, url):
-        episode = self._match_id(url)
-
-        webpage = self._download_webpage(
-            'http://fernsehkritik.tv/folge-%s/play' % episode, episode)
-        title = clean_html(self._html_search_regex(
-            '<h3>([^<]+)</h3>', webpage, 'title'))
-        thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
-        sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
-
-        formats = []
-        for source in sources:
-            furl = source.get('src')
-            if furl:
-                formats.append({
-                    'url': furl,
-                    'format_id': determine_ext(furl),
-                })
-        self._sort_formats(formats)
-
-        return {
-            'id': episode,
-            'title': title,
-            'formats': formats,
-            'thumbnail': thumbnail,
-        }

youtube_dl/extractor/fox9.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 from .anvato import AnvatoIE
-from ..utils import js_to_json
 
 
 class FOX9IE(AnvatoIE):
@@ -34,9 +33,9 @@ class FOX9IE(AnvatoIE):
 
         video_id = self._parse_json(
             self._search_regex(
-                r'AnvatoPlaylist\s*\(\s*(\[.+?\])\s*\)\s*;',
+                r"this\.videosJson\s*=\s*'(\[.+?\])';",
                 webpage, 'anvato playlist'),
-            video_id, transform_source=js_to_json)[0]['video']
+            video_id)[0]['video']
 
         return self._get_anvato_videos(
             'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',

youtube_dl/extractor/francetv.py

@@ -3,7 +3,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..compat import compat_urlparse
@@ -308,31 +307,32 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
         return self._extract_video(video_id, catalogue)
 
 
-class GenerationQuoiIE(InfoExtractor):
-    IE_NAME = 'france2.fr:generation-quoi'
-    _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
+class GenerationWhatIE(InfoExtractor):
+    IE_NAME = 'france2.fr:generation-what'
+    _VALID_URL = r'https?://generation-what\.francetv\.fr/[^/]+/video/(?P<id>[^/?#]+)'
 
-    _TEST = {
-        'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
+    _TESTS = [{
+        'url': 'http://generation-what.francetv.fr/portrait/video/present-arms',
         'info_dict': {
-            'id': 'k7FJX8VBcvvLmX4wA5Q',
+            'id': 'wtvKYUG45iw',
             'ext': 'mp4',
-            'title': 'Génération Quoi - Garde à Vous',
-            'uploader': 'Génération Quoi',
+            'title': 'Generation What - Garde à vous - FRA',
+            'uploader': 'Generation What',
+            'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w',
+            'upload_date': '20160411',
         },
-        'params': {
-            # It uses Dailymotion
-            'skip_download': True,
-        },
-    }
+    }, {
+        'url': 'http://generation-what.francetv.fr/europe/video/present-arms',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
-        info_json = self._download_webpage(info_url, display_id)
-        info = json.loads(info_json)
-        return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
-                               ie='Dailymotion')
+        webpage = self._download_webpage(url, display_id)
+        youtube_id = self._search_regex(
+            r"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';",
+            webpage, 'youtube id')
+        return self.url_result(youtube_id, 'Youtube', youtube_id)
 
 
 class CultureboxIE(FranceTVBaseInfoExtractor):
@@ -363,6 +363,6 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
             raise ExtractorError('Video %s is not available' % name, expected=True)
 
         video_id, catalogue = self._search_regex(
-            r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
+            r'"https?://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
 
         return self._extract_video(video_id, catalogue)

youtube_dl/extractor/freespeech.py

@@ -1,37 +1,34 @@
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
 
 
 class FreespeechIE(InfoExtractor):
     IE_NAME = 'freespeech.org'
-    _VALID_URL = r'https?://(?:www\.)?freespeech\.org/video/(?P<title>.+)'
+    _VALID_URL = r'https?://(?:www\.)?freespeech\.org/stories/(?P<id>.+)'
     _TEST = {
         'add_ie': ['Youtube'],
-        'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',
+        'url': 'http://www.freespeech.org/stories/fcc-announces-net-neutrality-rollback-whats-stake/',
         'info_dict': {
-            'id': 'poKsVCZ64uU',
-            'ext': 'webm',
-            'title': 'Obama, Romney Campaign in Colorado Ahead of Debate',
-            'description': 'Obama, Romney Campaign in Colorado Ahead of Debate',
-            'uploader': 'freespeechtv',
+            'id': 'waRk6IPqyWM',
+            'ext': 'mp4',
+            'title': 'What\'s At Stake - Net Neutrality Special',
+            'description': 'Presented by MNN and FSTV',
+            'upload_date': '20170728',
             'uploader_id': 'freespeechtv',
-            'upload_date': '20121002',
+            'uploader': 'freespeechtv',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        title = mobj.group('title')
-        webpage = self._download_webpage(url, title)
-        info_json = self._search_regex(r'jQuery\.extend\(Drupal\.settings, ({.*?})\);', webpage, 'info')
-        info = json.loads(info_json)
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        youtube_url = self._search_regex(
+            r'data-video-url="([^"]+)"',
+            webpage, 'youtube url')
 
         return {
             '_type': 'url',
-            'url': info['jw_player']['basic_video_node_player']['file'],
+            'url': youtube_url,
             'ie_key': 'Youtube',
         }

youtube_dl/extractor/funimation.py

@@ -57,7 +57,7 @@ class FunimationIE(InfoExtractor):
         try:
             data = self._download_json(
                 'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
-                None, 'Logging in as %s' % username, data=urlencode_postdata({
+                None, 'Logging in', data=urlencode_postdata({
                     'username': username,
                     'password': password,
                 }))

youtube_dl/extractor/gamersyde.py

@@ -1,70 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    js_to_json,
-    parse_duration,
-    remove_start,
-)
-
-
-class GamersydeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?gamersyde\.com/hqstream_(?P<display_id>[\da-z_]+)-(?P<id>\d+)_[a-z]{2}\.html'
-    _TEST = {
-        'url': 'http://www.gamersyde.com/hqstream_bloodborne_birth_of_a_hero-34371_en.html',
-        'md5': 'f38d400d32f19724570040d5ce3a505f',
-        'info_dict': {
-            'id': '34371',
-            'ext': 'mp4',
-            'duration': 372,
-            'title': 'Bloodborne - Birth of a hero',
-            'thumbnail': r're:^https?://.*\.jpg$',
-        }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
-
-        webpage = self._download_webpage(url, display_id)
-
-        playlist = self._parse_json(
-            self._search_regex(
-                r'(?s)playlist: \[({.+?})\]\s*}\);', webpage, 'files'),
-            display_id, transform_source=js_to_json)
-
-        formats = []
-        for source in playlist['sources']:
-            video_url = source.get('file')
-            if not video_url:
-                continue
-            format_id = source.get('label')
-            f = {
-                'url': video_url,
-                'format_id': format_id,
-            }
-            m = re.search(r'^(?P<height>\d+)[pP](?P<fps>\d+)fps', format_id)
-            if m:
-                f.update({
-                    'height': int(m.group('height')),
-                    'fps': int(m.group('fps')),
-                })
-            formats.append(f)
-        self._sort_formats(formats)
-
-        title = remove_start(playlist['title'], '%s - ' % video_id)
-        thumbnail = playlist.get('image')
-        duration = parse_duration(self._search_regex(
-            r'Length:</label>([^<]+)<', webpage, 'duration', fatal=False))
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'formats': formats,
-        }

youtube_dl/extractor/gamespot.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class GameSpotIE(OnceIE):
-    _VALID_URL = r'https?://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
+    _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
@@ -35,6 +35,12 @@ class GameSpotIE(OnceIE):
         'params': {
             'skip_download': True,  # m3u8 downloads
         },
+    }, {
+        'url': 'https://www.gamespot.com/videos/embed/6439218/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -52,7 +58,7 @@ class GameSpotIE(OnceIE):
             manifest_url = f4m_url
             formats.extend(self._extract_f4m_formats(
                 f4m_url + '?hdcore=3.7.0', page_id, f4m_id='hds', fatal=False))
-        m3u8_url = streams.get('m3u8_stream')
+        m3u8_url = dict_get(streams, ('m3u8_stream', 'adaptive_stream'))
         if m3u8_url:
             manifest_url = m3u8_url
             m3u8_formats = self._extract_m3u8_formats(
@@ -60,7 +66,7 @@ class GameSpotIE(OnceIE):
                 m3u8_id='hls', fatal=False)
             formats.extend(m3u8_formats)
         progressive_url = dict_get(
-            streams, ('progressive_hd', 'progressive_high', 'progressive_low'))
+            streams, ('progressive_hd', 'progressive_high', 'progressive_low', 'other_lr'))
         if progressive_url and manifest_url:
             qualities_basename = self._search_regex(
                 r'/([^/]+)\.csmil/',
@@ -105,7 +111,8 @@ class GameSpotIE(OnceIE):
             onceux_url = self._parse_json(unescapeHTML(onceux_json), page_id).get('metadataUri')
             if onceux_url:
                 formats.extend(self._extract_once_formats(re.sub(
-                    r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url)))
+                    r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url),
+                    http_formats_preference=-1))
 
         if not formats:
             for quality in ['sd', 'hd']:

youtube_dl/extractor/generic.py

@@ -102,6 +102,7 @@ from .joj import JojIE
 from .megaphone import MegaphoneIE
 from .vzaar import VzaarIE
 from .channel9 import Channel9IE
+from .vshare import VShareIE
 
 
 class GenericIE(InfoExtractor):
@@ -1098,9 +1099,9 @@ class GenericIE(InfoExtractor):
         },
         # jwplayer rtmp
         {
-            'url': 'http://www.suffolk.edu/sjc/',
+            'url': 'http://www.suffolk.edu/sjc/live.php',
             'info_dict': {
-                'id': 'sjclive',
+                'id': 'live',
                 'ext': 'flv',
                 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
                 'uploader': 'www.suffolk.edu',
@@ -1108,7 +1109,7 @@ class GenericIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
-            'skip': 'does not contain a video anymore',
+            'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
         },
         # Complex jwplayer
         {
@@ -1135,6 +1136,19 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             }
         },
+        {
+            # JWPlatform iframe
+            'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
+            'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
+            'info_dict': {
+                'id': 'O0c5JcKT',
+                'ext': 'mp4',
+                'upload_date': '20171122',
+                'timestamp': 1511366290,
+                'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
+            },
+            'add_ie': [JWPlatformIE.ie_key()],
+        },
         {
             # Video.js embed, multiple formats
             'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
@@ -1921,6 +1935,16 @@ class GenericIE(InfoExtractor):
                 'title': 'Rescue Kit 14 Free Edition - Getting started',
             },
             'playlist_count': 4,
+        },
+        {
+            # vshare embed
+            'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
+            'md5': '17b39f55b5497ae8b59f5fbce8e35886',
+            'info_dict': {
+                'id': '0f64ce6',
+                'title': 'vl14062007715967',
+                'ext': 'mp4',
+            }
         }
         # {
         #     # TODO: find another test
@@ -2879,6 +2903,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
 
+        vshare_urls = VShareIE._extract_urls(webpage)
+        if vshare_urls:
+            return self.playlist_from_matches(
+                vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
+
         def merge_dicts(dict1, dict2):
             merged = {}
             for k, v in dict1.items():

youtube_dl/extractor/hotstar.py

@@ -1,22 +1,47 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
-    ExtractorError,
     determine_ext,
+    ExtractorError,
     int_or_none,
 )
 
 
-class HotStarIE(InfoExtractor):
+class HotStarBaseIE(InfoExtractor):
+    _GEO_COUNTRIES = ['IN']
+
+    def _download_json(self, *args, **kwargs):
+        response = super(HotStarBaseIE, self)._download_json(*args, **kwargs)
+        if response['resultCode'] != 'OK':
+            if kwargs.get('fatal'):
+                raise ExtractorError(
+                    response['errorDescription'], expected=True)
+            return None
+        return response['resultObj']
+
+    def _download_content_info(self, content_id):
+        return self._download_json(
+            'https://account.hotstar.com/AVS/besc', content_id, query={
+                'action': 'GetAggregatedContentDetails',
+                'appVersion': '5.0.40',
+                'channel': 'PCTV',
+                'contentId': content_id,
+            })['contentInfo'][0]
+
+
+class HotStarIE(HotStarBaseIE):
     _VALID_URL = r'https?://(?:www\.)?hotstar\.com/(?:.+?[/-])?(?P<id>\d{10})'
     _TESTS = [{
         'url': 'http://www.hotstar.com/on-air-with-aib--english-1000076273',
         'info_dict': {
             'id': '1000076273',
             'ext': 'mp4',
-            'title': 'On Air With AIB - English',
+            'title': 'On Air With AIB',
             'description': 'md5:c957d8868e9bc793ccb813691cc4c434',
             'timestamp': 1447227000,
             'upload_date': '20151111',
@@ -34,23 +59,11 @@ class HotStarIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True, query=None):
-        json_data = super(HotStarIE, self)._download_json(
-            url_or_request, video_id, note, fatal=fatal, query=query)
-        if json_data['resultCode'] != 'OK':
-            if fatal:
-                raise ExtractorError(json_data['errorDescription'])
-            return None
-        return json_data['resultObj']
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(
-            'http://account.hotstar.com/AVS/besc', video_id, query={
-                'action': 'GetAggregatedContentDetails',
-                'channel': 'PCTV',
-                'contentId': video_id,
-            })['contentInfo'][0]
+
+        video_data = self._download_content_info(video_id)
+
         title = video_data['episodeTitle']
 
         if video_data.get('encrypted') == 'Y':
@@ -99,3 +112,51 @@ class HotStarIE(InfoExtractor):
             'episode_number': int_or_none(video_data.get('episodeNumber')),
             'series': video_data.get('contentTitle'),
         }
+
+
+class HotStarPlaylistIE(HotStarBaseIE):
+    IE_NAME = 'hotstar:playlist'
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com/tv/[^/]+/(?P<content_id>\d+))/(?P<type>[^/]+)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.hotstar.com/tv/pratidaan/14982/episodes/14812/9993',
+        'info_dict': {
+            'id': '14812',
+        },
+        'playlist_mincount': 75,
+    }, {
+        'url': 'http://www.hotstar.com/tv/pratidaan/14982/popular-clips/9998/9998',
+        'only_matching': True,
+    }]
+    _ITEM_TYPES = {
+        'episodes': 'EPISODE',
+        'popular-clips': 'CLIPS',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        base_url = mobj.group('url')
+        content_id = mobj.group('content_id')
+        playlist_type = mobj.group('type')
+
+        content_info = self._download_content_info(content_id)
+        playlist_id = compat_str(content_info['categoryId'])
+
+        collection = self._download_json(
+            'https://search.hotstar.com/AVS/besc', playlist_id, query={
+                'action': 'SearchContents',
+                'appVersion': '5.0.40',
+                'channel': 'PCTV',
+                'moreFilters': 'series:%s;' % playlist_id,
+                'query': '*',
+                'searchOrder': 'last_broadcast_date desc,year desc,title asc',
+                'type': self._ITEM_TYPES.get(playlist_type, 'EPISODE'),
+            })
+
+        entries = [
+            self.url_result(
+                '%s/_/%s' % (base_url, video['contentId']),
+                ie=HotStarIE.ie_key(), video_id=video['contentId'])
+            for video in collection['response']['docs']
+            if video.get('contentId')]
+
+        return self.playlist_result(entries, playlist_id)

youtube_dl/extractor/instagram.py

@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
@@ -7,7 +8,6 @@ from ..compat import compat_str
 from ..utils import (
     get_element_by_attribute,
     int_or_none,
-    limit_length,
     lowercase_escape,
     try_get,
 )
@@ -130,13 +130,21 @@ class InstagramIE(InfoExtractor):
                 video_url = media.get('video_url')
                 height = int_or_none(media.get('dimensions', {}).get('height'))
                 width = int_or_none(media.get('dimensions', {}).get('width'))
-                description = media.get('caption')
+                description = try_get(
+                    media, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'],
+                    compat_str) or media.get('caption')
                 thumbnail = media.get('display_src')
-                timestamp = int_or_none(media.get('date'))
+                timestamp = int_or_none(media.get('taken_at_timestamp') or media.get('date'))
                 uploader = media.get('owner', {}).get('full_name')
                 uploader_id = media.get('owner', {}).get('username')
-                like_count = int_or_none(media.get('likes', {}).get('count'))
-                comment_count = int_or_none(media.get('comments', {}).get('count'))
+
+                def get_count(key, kind):
+                    return int_or_none(try_get(
+                        media, (lambda x: x['edge_media_%s' % key]['count'],
+                                lambda x: x['%ss' % kind]['count'])))
+                like_count = get_count('preview_like', 'like')
+                comment_count = get_count('to_comment', 'comment')
+
                 comments = [{
                     'author': comment.get('user', {}).get('username'),
                     'author_id': comment.get('user', {}).get('id'),
@@ -212,7 +220,7 @@ class InstagramIE(InfoExtractor):
 
 
 class InstagramUserIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?instagram\.com/(?P<id>[^/]{2,})/?(?:$|[?#])'
     IE_DESC = 'Instagram user profile'
     IE_NAME = 'instagram:user'
     _TEST = {
@@ -221,82 +229,79 @@ class InstagramUserIE(InfoExtractor):
             'id': 'porsche',
             'title': 'porsche',
         },
-        'playlist_mincount': 2,
-        'playlist': [{
-            'info_dict': {
-                'id': '614605558512799803_462752227',
-                'ext': 'mp4',
-                'title': '#Porsche Intelligent Performance.',
-                'thumbnail': r're:^https?://.*\.jpg',
-                'uploader': 'Porsche',
-                'uploader_id': 'porsche',
-                'timestamp': 1387486713,
-                'upload_date': '20131219',
-            },
-        }],
+        'playlist_count': 5,
         'params': {
             'extract_flat': True,
             'skip_download': True,
+            'playlistend': 5,
         }
     }
 
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        uploader_id = mobj.group('username')
+    def _entries(self, uploader_id):
+        query = {
+            '__a': 1,
+        }
 
-        entries = []
-        page_count = 0
-        media_url = 'http://instagram.com/%s/media' % uploader_id
-        while True:
+        def get_count(kind):
+            return int_or_none(try_get(
+                node, lambda x: x['%ss' % kind]['count']))
+
+        for page_num in itertools.count(1):
             page = self._download_json(
-                media_url, uploader_id,
-                note='Downloading page %d ' % (page_count + 1),
-            )
-            page_count += 1
+                'https://instagram.com/%s/' % uploader_id, uploader_id,
+                note='Downloading page %d' % page_num,
+                fatal=False, query=query)
+            if not page:
+                break
 
-            for it in page['items']:
-                if it.get('type') != 'video':
+            nodes = try_get(page, lambda x: x['user']['media']['nodes'], list)
+            if not nodes:
+                break
+
+            max_id = None
+
+            for node in nodes:
+                node_id = node.get('id')
+                if node_id:
+                    max_id = node_id
+
+                if node.get('__typename') != 'GraphVideo' and node.get('is_video') is not True:
+                    continue
+                video_id = node.get('code')
+                if not video_id:
                     continue
-                like_count = int_or_none(it.get('likes', {}).get('count'))
-                user = it.get('user', {})
 
-                formats = [{
-                    'format_id': k,
-                    'height': v.get('height'),
-                    'width': v.get('width'),
-                    'url': v['url'],
-                } for k, v in it['videos'].items()]
-                self._sort_formats(formats)
+                info = self.url_result(
+                    'https://instagram.com/p/%s/' % video_id,
+                    ie=InstagramIE.ie_key(), video_id=video_id)
 
-                thumbnails_el = it.get('images', {})
-                thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
+                description = try_get(
+                    node, [lambda x: x['caption'], lambda x: x['text']['id']],
+                    compat_str)
+                thumbnail = node.get('thumbnail_src') or node.get('display_src')
+                timestamp = int_or_none(node.get('date'))
 
-                # In some cases caption is null, which corresponds to None
-                # in python. As a result, it.get('caption', {}) gives None
-                title = (it.get('caption') or {}).get('text', it['id'])
+                comment_count = get_count('comment')
+                like_count = get_count('like')
+                view_count = int_or_none(node.get('video_views'))
 
-                entries.append({
-                    'id': it['id'],
-                    'title': limit_length(title, 80),
-                    'formats': formats,
+                info.update({
+                    'description': description,
                     'thumbnail': thumbnail,
-                    'webpage_url': it.get('link'),
-                    'uploader': user.get('full_name'),
-                    'uploader_id': user.get('username'),
+                    'timestamp': timestamp,
+                    'comment_count': comment_count,
                     'like_count': like_count,
-                    'timestamp': int_or_none(it.get('created_time')),
+                    'view_count': view_count,
                 })
 
-            if not page['items']:
-                break
-            max_id = page['items'][-1]['id'].split('_')[0]
-            media_url = (
-                'http://instagram.com/%s/media?max_id=%s' % (
-                    uploader_id, max_id))
+                yield info
 
-        return {
-            '_type': 'playlist',
-            'entries': entries,
-            'id': uploader_id,
-            'title': uploader_id,
-        }
+            if not max_id:
+                break
+
+            query['max_id'] = max_id
+
+    def _real_extract(self, url):
+        uploader_id = self._match_id(url)
+        return self.playlist_result(
+            self._entries(uploader_id), uploader_id, uploader_id)

youtube_dl/extractor/jwplatform.py

@@ -24,7 +24,7 @@ class JWPlatformIE(InfoExtractor):
     @staticmethod
     def _extract_url(webpage):
         mobj = re.search(
-            r'<script[^>]+?src=["\'](?P<url>(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})',
+            r'<(?:script|iframe)[^>]+?src=["\'](?P<url>(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})',
             webpage)
         if mobj:
             return mobj.group('url')

youtube_dl/extractor/livestream.py

@@ -114,7 +114,7 @@ class LivestreamIE(InfoExtractor):
 
         smil_url = video_data.get('smil_url')
         if smil_url:
-            formats.extend(self._extract_smil_formats(smil_url, video_id))
+            formats.extend(self._extract_smil_formats(smil_url, video_id, fatal=False))
 
         m3u8_url = video_data.get('m3u8_url')
         if m3u8_url:

youtube_dl/extractor/massengeschmacktv.py

@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    mimetype2ext,
+    parse_filesize,
+)
+
+
+class MassengeschmackTVIE(InfoExtractor):
+    IE_NAME = 'massengeschmack.tv'
+    _VALID_URL = r'https?://(?:www\.)?massengeschmack\.tv/play/(?P<id>[^?&#]+)'
+
+    _TEST = {
+        'url': 'https://massengeschmack.tv/play/fktv202',
+        'md5': 'a9e054db9c2b5a08f0a0527cc201e8d3',
+        'info_dict': {
+            'id': 'fktv202',
+            'ext': 'mp4',
+            'title': 'Fernsehkritik-TV - Folge 202',
+        },
+    }
+
+    def _real_extract(self, url):
+        episode = self._match_id(url)
+
+        webpage = self._download_webpage(url, episode)
+        title = clean_html(self._html_search_regex(
+            '<h3>([^<]+)</h3>', webpage, 'title'))
+        thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
+        sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
+
+        formats = []
+        for source in sources:
+            furl = source.get('src')
+            if not furl:
+                continue
+            furl = self._proto_relative_url(furl)
+            ext = determine_ext(furl) or mimetype2ext(source.get('type'))
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    furl, episode, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'url': furl,
+                    'format_id': determine_ext(furl),
+                })
+
+        for (durl, format_id, width, height, filesize) in re.findall(r'''(?x)
+                                   <a[^>]+?href="(?P<url>(?:https:)?//[^"]+)".*?
+                                   <strong>(?P<format_id>.+?)</strong>.*?
+                                   <small>(?:(?P<width>\d+)x(?P<height>\d+))?\s+?\((?P<filesize>[\d,]+\s*[GM]iB)\)</small>
+                                ''', webpage):
+            formats.append({
+                'url': durl,
+                'format_id': format_id,
+                'width': int_or_none(width),
+                'height': int_or_none(height),
+                'filesize': parse_filesize(filesize),
+                'vcodec': 'none' if format_id.startswith('Audio') else None,
+            })
+
+        self._sort_formats(formats, ('width', 'height', 'filesize', 'tbr'))
+
+        return {
+            'id': episode,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/nexx.py

@@ -28,7 +28,7 @@ class NexxIE(InfoExtractor):
     _TESTS = [{
         # movie
         'url': 'https://api.nexx.cloud/v3/748/videos/byid/128907',
-        'md5': '16746bfc28c42049492385c989b26c4a',
+        'md5': '828cea195be04e66057b846288295ba1',
         'info_dict': {
             'id': '128907',
             'ext': 'mp4',
@@ -42,9 +42,6 @@ class NexxIE(InfoExtractor):
             'timestamp': 1384264416,
             'upload_date': '20131112',
         },
-        'params': {
-            'format': 'bestvideo',
-        },
     }, {
         # episode
         'url': 'https://api.nexx.cloud/v3/741/videos/byid/247858',
@@ -62,7 +59,6 @@ class NexxIE(InfoExtractor):
             'season_number': 2,
         },
         'params': {
-            'format': 'bestvideo',
             'skip_download': True,
         },
     }, {
@@ -193,35 +189,67 @@ class NexxIE(InfoExtractor):
         stream_data = video['streamdata']
         language = general.get('language_raw') or ''
 
-        # TODO: reverse more cdns and formats
+        # TODO: reverse more cdns
 
         cdn = stream_data['cdnType']
         assert cdn == 'azure'
 
         azure_locator = stream_data['azureLocator']
 
-        AZURE_URL = 'http://nx-p%02d.akamaized.net/'
+        AZURE_URL = 'http://nx%s%02d.akamaized.net/'
 
-        for secure in ('s', ''):
-            cdn_shield = stream_data.get('cdnShieldHTTP%s' % secure.upper())
-            if cdn_shield:
-                azure_base = 'http%s://%s' % (secure, cdn_shield)
-                break
-        else:
-            azure_base = AZURE_URL % int(stream_data['azureAccount'].replace('nexxplayplus', ''))
+        def get_cdn_shield_base(shield_type='', prefix='-p'):
+            for secure in ('', 's'):
+                cdn_shield = stream_data.get('cdnShield%sHTTP%s' % (shield_type, secure.upper()))
+                if cdn_shield:
+                    return 'http%s://%s' % (secure, cdn_shield)
+            else:
+                return AZURE_URL % (prefix, int(stream_data['azureAccount'].replace('nexxplayplus', '')))
 
+        azure_stream_base = get_cdn_shield_base()
         is_ml = ',' in language
-        azure_m3u8_url = '%s%s/%s_src%s.ism/Manifest(format=m3u8-aapl)' % (
-            azure_base, azure_locator, video_id, ('_manifest' if is_ml else ''))
+        azure_manifest_url = '%s%s/%s_src%s.ism/Manifest' % (
+            azure_stream_base, azure_locator, video_id, ('_manifest' if is_ml else '')) + '%s'
 
         protection_token = try_get(
             video, lambda x: x['protectiondata']['token'], compat_str)
         if protection_token:
-            azure_m3u8_url += '?hdnts=%s' % protection_token
+            azure_manifest_url += '?hdnts=%s' % protection_token
 
         formats = self._extract_m3u8_formats(
-            azure_m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
-            m3u8_id='%s-hls' % cdn)
+            azure_manifest_url % '(format=m3u8-aapl)',
+            video_id, 'mp4', 'm3u8_native',
+            m3u8_id='%s-hls' % cdn, fatal=False)
+        formats.extend(self._extract_mpd_formats(
+            azure_manifest_url % '(format=mpd-time-csf)',
+            video_id, mpd_id='%s-dash' % cdn, fatal=False))
+        formats.extend(self._extract_ism_formats(
+            azure_manifest_url % '', video_id, ism_id='%s-mss' % cdn, fatal=False))
+
+        azure_progressive_base = get_cdn_shield_base('Prog', '-d')
+        azure_file_distribution = stream_data.get('azureFileDistribution')
+        if azure_file_distribution:
+            fds = azure_file_distribution.split(',')
+            if fds:
+                for fd in fds:
+                    ss = fd.split(':')
+                    if len(ss) == 2:
+                        tbr = int_or_none(ss[0])
+                        if tbr:
+                            f = {
+                                'url': '%s%s/%s_src_%s_%d.mp4' % (
+                                    azure_progressive_base, azure_locator, video_id, ss[1], tbr),
+                                'format_id': '%s-http-%d' % (cdn, tbr),
+                                'tbr': tbr,
+                            }
+                            width_height = ss[1].split('x')
+                            if len(width_height) == 2:
+                                f.update({
+                                    'width': int_or_none(width_height[0]),
+                                    'height': int_or_none(width_height[1]),
+                                })
+                            formats.append(f)
+
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/noco.py

@@ -70,7 +70,7 @@ class NocoIE(InfoExtractor):
             return
 
         login = self._download_json(
-            self._LOGIN_URL, None, 'Logging in as %s' % username,
+            self._LOGIN_URL, None, 'Logging in',
             data=urlencode_postdata({
                 'a': 'login',
                 'cookie': '1',

youtube_dl/extractor/once.py

@@ -11,7 +11,7 @@ class OnceIE(InfoExtractor):
     ADAPTIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/master/playlist/%s/%s/%s/content.m3u8'
     PROGRESSIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/media/progressive/%s/%s/%s/%s/content.mp4'
 
-    def _extract_once_formats(self, url):
+    def _extract_once_formats(self, url, http_formats_preference=None):
         domain_id, application_id, media_item_id = re.match(
             OnceIE._VALID_URL, url).groups()
         formats = self._extract_m3u8_formats(
@@ -35,6 +35,7 @@ class OnceIE(InfoExtractor):
                     'format_id': adaptive_format['format_id'].replace(
                         'hls', 'http'),
                     'protocol': 'http',
+                    'preference': http_formats_preference,
                 })
                 progressive_formats.append(progressive_format)
         self._check_formats(progressive_formats, media_item_id)

youtube_dl/extractor/openload.py

@@ -140,7 +140,7 @@ class PhantomJSwrapper(object):
         for name in self._TMP_FILE_NAMES:
             try:
                 os.remove(self._TMP_FILES[name].name)
-            except:
+            except (IOError, OSError):
                 pass
 
     def _save_cookies(self, url):
@@ -242,7 +242,7 @@ class PhantomJSwrapper(object):
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -286,6 +286,9 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
         'only_matching': True,
+    }, {
+        'url': 'http://www.openload.link/f/KnG-kKZdcfY',
+        'only_matching': True,
     }]
 
     _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'

youtube_dl/extractor/orf.py

@@ -49,13 +49,13 @@ class ORFTVthekIE(InfoExtractor):
         'params': {
             'skip_download': True,  # rtsp downloads
         },
-        '_skip': 'Blocked outside of Austria / Germany',
+        'skip': 'Blocked outside of Austria / Germany',
     }, {
         'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
-        'skip_download': True,
+        'only_matching': True,
     }, {
         'url': 'http://tvthek.orf.at/profile/Universum/35429',
-        'skip_download': True,
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/pandatv.py

@@ -33,7 +33,7 @@ class PandaTVIE(InfoExtractor):
         video_id = self._match_id(url)
 
         config = self._download_json(
-            'https://www.panda.tv/api_room?roomid=%s' % video_id, video_id)
+            'https://www.panda.tv/api_room_v2?roomid=%s' % video_id, video_id)
 
         error_code = config.get('errno', 0)
         if error_code is not 0:
@@ -66,6 +66,11 @@ class PandaTVIE(InfoExtractor):
             plflag1 = '4'
         live_panda = 'live_panda' if plflag0 < 1 else ''
 
+        plflag_auth = self._parse_json(video_info['plflag_list'], video_id)
+        sign = plflag_auth['auth']['sign']
+        ts = plflag_auth['auth']['time']
+        rid = plflag_auth['auth']['rid']
+
         quality_key = qualities(['OD', 'HD', 'SD'])
         suffix = ['_small', '_mid', '']
         formats = []
@@ -77,8 +82,8 @@ class PandaTVIE(InfoExtractor):
                 continue
             for pref, (ext, pl) in enumerate((('m3u8', '-hls'), ('flv', ''))):
                 formats.append({
-                    'url': 'https://pl%s%s.live.panda.tv/live_panda/%s%s%s.%s'
-                    % (pl, plflag1, room_key, live_panda, suffix[quality], ext),
+                    'url': 'https://pl%s%s.live.panda.tv/live_panda/%s%s%s.%s?sign=%s&ts=%s&rid=%s'
+                    % (pl, plflag1, room_key, live_panda, suffix[quality], ext, sign, ts, rid),
                     'format_id': '%s-%s' % (k, ext),
                     'quality': quality,
                     'source_preference': pref,

youtube_dl/extractor/patreon.py

@@ -67,7 +67,7 @@ class PatreonIE(InfoExtractor):
             'https://www.patreon.com/processLogin',
             compat_urllib_parse_urlencode(login_form).encode('utf-8')
         )
-        login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
+        login_page = self._download_webpage(request, None, note='Logging in')
 
         if re.search(r'onLoginFailed', login_page):
             raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)

youtube_dl/extractor/performgroup.py

@@ -0,0 +1,83 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class PerformGroupIE(InfoExtractor):
+    _VALID_URL = r'https?://player\.performgroup\.com/eplayer(?:/eplayer\.html|\.js)#/?(?P<id>[0-9a-f]{26})\.(?P<auth_token>[0-9a-z]{26})'
+    _TESTS = [{
+        # http://www.faz.net/aktuell/sport/fussball/wm-2018-playoffs-schweiz-besiegt-nordirland-1-0-15286104.html
+        'url': 'http://player.performgroup.com/eplayer/eplayer.html#d478c41c5d192f56b9aa859de8.1w4crrej5w14e1ed4s1ce4ykab',
+        'md5': '259cb03d142e2e52471e8837ecacb29f',
+        'info_dict': {
+            'id': 'xgrwobuzumes1lwjxtcdpwgxd',
+            'ext': 'mp4',
+            'title': 'Liga MX: Keine Einsicht nach Horrorfoul',
+            'description': 'md5:7cd3b459c82725b021e046ab10bf1c5b',
+            'timestamp': 1511533477,
+            'upload_date': '20171124',
+        }
+    }]
+
+    def _call_api(self, service, auth_token, content_id, referer_url):
+        return self._download_json(
+            'http://ep3.performfeeds.com/ep%s/%s/%s/' % (service, auth_token, content_id),
+            content_id, headers={
+                'Referer': referer_url,
+                'Origin': 'http://player.performgroup.com',
+            }, query={
+                '_fmt': 'json',
+            })
+
+    def _real_extract(self, url):
+        player_id, auth_token = re.search(self._VALID_URL, url).groups()
+        bootstrap = self._call_api('bootstrap', auth_token, player_id, url)
+        video = bootstrap['config']['dataSource']['sourceItems'][0]['videos'][0]
+        video_id = video['uuid']
+        vod = self._call_api('vod', auth_token, video_id, url)
+        media = vod['videos']['video'][0]['media']
+
+        formats = []
+        hls_url = media.get('hls', {}).get('url')
+        if hls_url:
+            formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+
+        hds_url = media.get('hds', {}).get('url')
+        if hds_url:
+            formats.extend(self._extract_f4m_formats(hds_url + '?hdcore', video_id, f4m_id='hds', fatal=False))
+
+        for c in media.get('content', []):
+            c_url = c.get('url')
+            if not c_url:
+                continue
+            tbr = int_or_none(c.get('bitrate'), 1000)
+            format_id = 'http'
+            if tbr:
+                format_id += '-%d' % tbr
+            formats.append({
+                'format_id': format_id,
+                'url': c_url,
+                'tbr': tbr,
+                'width': int_or_none(c.get('width')),
+                'height': int_or_none(c.get('height')),
+                'filesize': int_or_none(c.get('fileSize')),
+                'vcodec': c.get('type'),
+                'fps': int_or_none(c.get('videoFrameRate')),
+                'vbr': int_or_none(c.get('videoRate'), 1000),
+                'abr': int_or_none(c.get('audioRate'), 1000),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video['title'],
+            'description': video.get('description'),
+            'thumbnail': video.get('poster'),
+            'duration': int_or_none(video.get('duration')),
+            'timestamp': int_or_none(video.get('publishedTime'), 1000),
+            'formats': formats,
+        }

youtube_dl/extractor/pluralsight.py

@@ -116,7 +116,7 @@ class PluralsightIE(PluralsightBaseIE):
             post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
 
         response = self._download_webpage(
-            post_url, None, 'Logging in as %s' % username,
+            post_url, None, 'Logging in',
             data=urlencode_postdata(login_form),
             headers={'Content-Type': 'application/x-www-form-urlencoded'})
 

youtube_dl/extractor/roosterteeth.py

@@ -68,7 +68,7 @@ class RoosterTeethIE(InfoExtractor):
 
         login_request = self._download_webpage(
             self._LOGIN_URL, None,
-            note='Logging in as %s' % username,
+            note='Logging in',
             data=urlencode_postdata(login_form),
             headers={
                 'Referer': self._LOGIN_URL,

youtube_dl/extractor/rozhlas.py

@@ -21,7 +21,7 @@ class RozhlasIE(InfoExtractor):
         }
     }, {
         'url': 'http://prehravac.rozhlas.cz/audio/3421320/embed',
-        'skip_download': True,
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/safari.py

@@ -61,7 +61,7 @@ class SafariBaseIE(InfoExtractor):
         request = sanitized_Request(
             self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
         login_page = self._download_webpage(
-            request, None, 'Logging in as %s' % username)
+            request, None, 'Logging in')
 
         if not is_logged(login_page):
             raise ExtractorError(

youtube_dl/extractor/skysports.py

@@ -2,7 +2,12 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import strip_or_none
+from ..utils import (
+    extract_attributes,
+    smuggle_url,
+    strip_or_none,
+    urljoin,
+)
 
 
 class SkySportsIE(InfoExtractor):
@@ -22,12 +27,22 @@ class SkySportsIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+        video_data = extract_attributes(self._search_regex(
+            r'(<div.+?class="sdc-article-video__media-ooyala"[^>]+>)', webpage, 'video data'))
+
+        video_url = 'ooyala:%s' % video_data['data-video-id']
+        if video_data.get('data-token-required') == 'true':
+            token_fetch_options = self._parse_json(video_data.get('data-token-fetch-options', '{}'), video_id, fatal=False) or {}
+            token_fetch_url = token_fetch_options.get('url')
+            if token_fetch_url:
+                embed_token = self._download_webpage(urljoin(url, token_fetch_url), video_id, fatal=False)
+                if embed_token:
+                    video_url = smuggle_url(video_url, {'embed_token': embed_token.strip('"')})
 
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'url': 'ooyala:%s' % self._search_regex(
-                r'data-video-id="([^"]+)"', webpage, 'ooyala id'),
+            'url': video_url,
             'title': self._og_search_title(webpage),
             'description': strip_or_none(self._og_search_description(webpage)),
             'ie_key': 'Ooyala',

youtube_dl/extractor/spankbang.py

@@ -3,10 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class SpankBangIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
+    _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
     _TESTS = [{
         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',
@@ -14,7 +15,7 @@ class SpankBangIE(InfoExtractor):
             'id': '3vvn',
             'ext': 'mp4',
             'title': 'fantasy solo',
-            'description': 'Watch fantasy solo free HD porn video - 05 minutes - dillion harper masturbates on a bed free adult movies.',
+            'description': 'Watch fantasy solo free HD porn video - 05 minutes -  Babe,Masturbation,Solo,Toy  - dillion harper masturbates on a bed free adult movies sexy clips.',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'silly2587',
             'age_limit': 18,
@@ -27,12 +28,20 @@ class SpankBangIE(InfoExtractor):
         # no uploader
         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
         'only_matching': True,
+    }, {
+        # mobile page
+        'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
+            raise ExtractorError(
+                'Video %s is not available' % video_id, expected=True)
+
         stream_key = self._html_search_regex(
             r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
             webpage, 'stream key')

youtube_dl/extractor/tnaflix.py

@@ -21,6 +21,8 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
         r'flashvars\.config\s*=\s*escape\("([^"]+)"',
         r'<input[^>]+name="config\d?" value="([^"]+)"',
     ]
+    _HOST = 'tna'
+    _VKEY_SUFFIX = ''
     _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
     _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
     _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
@@ -72,7 +74,13 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id') if 'display_id' in mobj.groupdict() else video_id
+        for display_id_key in ('display_id', 'display_id_2'):
+            if display_id_key in mobj.groupdict():
+                display_id = mobj.group(display_id_key)
+                if display_id:
+                    break
+        else:
+            display_id = video_id
 
         webpage = self._download_webpage(url, display_id)
 
@@ -81,8 +89,8 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
 
         if not cfg_url:
             inputs = self._hidden_inputs(webpage)
-            cfg_url = ('https://cdn-fck.tnaflix.com/tnaflix/%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
-                       % (inputs['vkey'], inputs['nkey'], video_id))
+            cfg_url = ('https://cdn-fck.%sflix.com/%sflix/%s%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
+                       % (self._HOST, self._HOST, inputs['vkey'], self._VKEY_SUFFIX, inputs['nkey'], video_id))
 
         cfg_xml = self._download_xml(
             cfg_url, display_id, 'Downloading metadata',
@@ -91,7 +99,8 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
         formats = []
 
         def extract_video_url(vl):
-            return re.sub(r'speed=\d+', 'speed=', unescapeHTML(vl.text))
+            # Any URL modification now results in HTTP Error 403: Forbidden
+            return unescapeHTML(vl.text)
 
         video_link = cfg_xml.find('./videoLink')
         if video_link is not None:
@@ -192,18 +201,21 @@ class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
             webpage)]
 
 
-class TNAFlixIE(TNAFlixNetworkBaseIE):
+class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE):
+    _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
+    _UPLOADER_REGEX = r'<span>by\s*<a[^>]+\bhref=["\']/profile/[^>]+>([^<]+)<'
+    _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
+
+
+class TNAFlixIE(TNAEMPFlixBaseIE):
     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 
     _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
-    _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
-    _UPLOADER_REGEX = r'<i>\s*Verified Member\s*</i>\s*<h\d+>(.+?)<'
-    _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 
     _TESTS = [{
         # anonymous uploader, no categories
         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
-        'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+        'md5': '7e569419fe6d69543d01e6be22f5f7c4',
         'info_dict': {
             'id': '553878',
             'display_id': 'Carmella-Decesare-striptease',
@@ -228,7 +240,7 @@ class TNAFlixIE(TNAFlixNetworkBaseIE):
             'duration': 164,
             'age_limit': 18,
             'uploader': 'bobwhite39',
-            'categories': ['Amateur Porn', 'Squirting Videos', 'Teen Girls 18+'],
+            'categories': list,
         }
     }, {
         'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
@@ -236,14 +248,15 @@ class TNAFlixIE(TNAFlixNetworkBaseIE):
     }]
 
 
-class EMPFlixIE(TNAFlixNetworkBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
+class EMPFlixIE(TNAEMPFlixBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?empflix\.com/(?:videos/(?P<display_id>.+?)-|[^/]+/(?P<display_id_2>[^/]+)/video)(?P<id>[0-9]+)'
 
-    _UPLOADER_REGEX = r'<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)</li>'
+    _HOST = 'emp'
+    _VKEY_SUFFIX = '-1'
 
     _TESTS = [{
         'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
-        'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+        'md5': 'bc30d48b91a7179448a0bda465114676',
         'info_dict': {
             'id': '33051',
             'display_id': 'Amateur-Finger-Fuck',
@@ -259,6 +272,9 @@ class EMPFlixIE(TNAFlixNetworkBaseIE):
     }, {
         'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051',
+        'only_matching': True,
     }]
 
 

youtube_dl/extractor/tva.py

@@ -32,6 +32,8 @@ class TVAIE(InfoExtractor):
         video_data = self._download_json(
             'https://videos.tva.ca/proxy/item/_' + video_id, video_id, headers={
                 'Accept': 'application/json',
+            }, query={
+                'appId': '5955fc5f23eec60006c951f1',
             })
 
         def get_attribute(key):

youtube_dl/extractor/twentytwotracks.py

@@ -1,86 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import int_or_none
-
-# 22Tracks regularly replace the audio tracks that can be streamed on their
-# site. The tracks usually expire after 1 months, so we can't add tests.
-
-
-class TwentyTwoTracksIE(InfoExtractor):
-    _VALID_URL = r'https?://22tracks\.com/(?P<city>[a-z]+)/(?P<genre>[\da-z]+)/(?P<id>\d+)'
-    IE_NAME = '22tracks:track'
-
-    _API_BASE = 'http://22tracks.com/api'
-
-    def _extract_info(self, city, genre_name, track_id=None):
-        item_id = track_id if track_id else genre_name
-
-        cities = self._download_json(
-            '%s/cities' % self._API_BASE, item_id,
-            'Downloading cities info',
-            'Unable to download cities info')
-        city_id = [x['id'] for x in cities if x['slug'] == city][0]
-
-        genres = self._download_json(
-            '%s/genres/%s' % (self._API_BASE, city_id), item_id,
-            'Downloading %s genres info' % city,
-            'Unable to download %s genres info' % city)
-        genre = [x for x in genres if x['slug'] == genre_name][0]
-        genre_id = genre['id']
-
-        tracks = self._download_json(
-            '%s/tracks/%s' % (self._API_BASE, genre_id), item_id,
-            'Downloading %s genre tracks info' % genre_name,
-            'Unable to download track info')
-
-        return [x for x in tracks if x['id'] == item_id][0] if track_id else [genre['title'], tracks]
-
-    def _get_track_url(self, filename, track_id):
-        token = self._download_json(
-            'http://22tracks.com/token.php?desktop=true&u=/128/%s' % filename,
-            track_id, 'Downloading token', 'Unable to download token')
-        return 'http://audio.22tracks.com%s?st=%s&e=%d' % (token['filename'], token['st'], token['e'])
-
-    def _extract_track_info(self, track_info, track_id):
-        download_url = self._get_track_url(track_info['filename'], track_id)
-        title = '%s - %s' % (track_info['artist'].strip(), track_info['title'].strip())
-        return {
-            'id': track_id,
-            'url': download_url,
-            'ext': 'mp3',
-            'title': title,
-            'duration': int_or_none(track_info.get('duration')),
-            'timestamp': int_or_none(track_info.get('published_at') or track_info.get('created'))
-        }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        city = mobj.group('city')
-        genre = mobj.group('genre')
-        track_id = mobj.group('id')
-
-        track_info = self._extract_info(city, genre, track_id)
-        return self._extract_track_info(track_info, track_id)
-
-
-class TwentyTwoTracksGenreIE(TwentyTwoTracksIE):
-    _VALID_URL = r'https?://22tracks\.com/(?P<city>[a-z]+)/(?P<genre>[\da-z]+)/?$'
-    IE_NAME = '22tracks:genre'
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        city = mobj.group('city')
-        genre = mobj.group('genre')
-
-        genre_title, tracks = self._extract_info(city, genre)
-
-        entries = [
-            self._extract_track_info(track_info, track_info['id'])
-            for track_info in tracks]
-
-        return self.playlist_result(entries, genre, genre_title)

youtube_dl/extractor/twitch.py

@@ -101,7 +101,7 @@ class TwitchBaseIE(InfoExtractor):
             fail(clean_html(login_page))
 
         redirect_page, handle = login_step(
-            login_page, handle, 'Logging in as %s' % username, {
+            login_page, handle, 'Logging in', {
                 'username': username,
                 'password': password,
             })

youtube_dl/extractor/udemy.py

@@ -164,7 +164,7 @@ class UdemyIE(InfoExtractor):
         })
 
         response = self._download_webpage(
-            self._LOGIN_URL, None, 'Logging in as %s' % username,
+            self._LOGIN_URL, None, 'Logging in',
             data=urlencode_postdata(login_form),
             headers={
                 'Referer': self._ORIGIN_URL,

youtube_dl/extractor/vidzi.py

@@ -28,10 +28,10 @@ class VidziIE(InfoExtractor):
         },
     }, {
         'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
-        'skip_download': True,
+        'only_matching': True,
     }, {
         'url': 'http://vidzi.cc/cghql9yq6emu.html',
-        'skip_download': True,
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/viki.py

@@ -99,7 +99,7 @@ class VikiBaseIE(InfoExtractor):
 
         login = self._call_api(
             'sessions.json', None,
-            'Logging in as %s' % username, post_data=login_form)
+            'Logging in', post_data=login_form)
 
         self._token = login.get('token')
         if not self._token:

youtube_dl/extractor/vk.py

@@ -67,7 +67,7 @@ class VKBaseIE(InfoExtractor):
 
         login_page = self._download_webpage(
             'https://login.vk.com/?act=login', None,
-            note='Logging in as %s' % username,
+            note='Logging in',
             data=urlencode_postdata(login_form))
 
         if re.search(r'onLoginFailed', login_page):

youtube_dl/extractor/vshare.py

@@ -1,14 +1,21 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import compat_chr
+from ..utils import (
+    decode_packed_codes,
+    ExtractorError,
+)
 
 
 class VShareIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?vshare\.io/[dv]/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://vshare.io/d/0f64ce6',
-        'md5': '16d7b8fef58846db47419199ff1ab3e7',
+        'md5': '17b39f55b5497ae8b59f5fbce8e35886',
         'info_dict': {
             'id': '0f64ce6',
             'title': 'vl14062007715967',
@@ -19,20 +26,49 @@ class VShareIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?vshare\.io/v/[^/?#&]+)',
+            webpage)
+
+    def _extract_packed(self, webpage):
+        packed = self._search_regex(
+            r'(eval\(function.+)', webpage, 'packed code')
+        unpacked = decode_packed_codes(packed)
+        digits = self._search_regex(r'\[((?:\d+,?)+)\]', unpacked, 'digits')
+        digits = [int(digit) for digit in digits.split(',')]
+        key_digit = self._search_regex(
+            r'fromCharCode\(.+?(\d+)\)}', unpacked, 'key digit')
+        chars = [compat_chr(d - int(key_digit)) for d in digits]
+        return ''.join(chars)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            'https://vshare.io/d/%s' % video_id, video_id)
+            'https://vshare.io/v/%s/width-650/height-430/1' % 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')
+            r'<title>([^<]+)</title>', webpage, 'title')
+        title = title.split(' - ')[0]
 
-        return {
+        error = self._html_search_regex(
+            r'(?s)<div[^>]+\bclass=["\']xxx-error[^>]+>(.+?)</div', webpage,
+            'error', default=None)
+        if error:
+            raise ExtractorError(error, expected=True)
+
+        info = self._parse_html5_media_entries(
+            url, '<video>%s</video>' % self._extract_packed(webpage),
+            video_id)[0]
+
+        self._sort_formats(info['formats'])
+
+        info.update({
             'id': video_id,
             'title': title,
-            'url': video_url,
-        }
+        })
+
+        return info

youtube_dl/extractor/wsj.py

@@ -13,7 +13,7 @@ class WSJIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                         (?:
                             https?://video-api\.wsj\.com/api-video/player/iframe\.html\?.*?\bguid=|
-                            https?://(?:www\.)?(?:wsj|barrons)\.com/video/[^/]+/|
+                            https?://(?:www\.)?(?:wsj|barrons)\.com/video/(?:[^/]+/)+|
                             wsj:
                         )
                         (?P<id>[a-fA-F0-9-]{36})
@@ -38,6 +38,9 @@ class WSJIE(InfoExtractor):
     }, {
         'url': 'http://www.barrons.com/video/capitalism-deserves-more-respect-from-millennials/F301217E-6F46-43AE-B8D2-B7180D642EE9.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.wsj.com/video/series/a-brief-history-of/the-modern-cell-carrier-how-we-got-here/980E2187-401D-48A1-B82B-1486CEE06CB9',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/youku.py

@@ -154,7 +154,7 @@ class YoukuIE(InfoExtractor):
         # request basic data
         basic_data_params = {
             'vid': video_id,
-            'ccode': '0402' if 'tudou.com' in url else '0401',
+            'ccode': '0502',
             'client_ip': '192.168.1.1',
             'utid': cna,
             'client_ts': time.time() / 1000,
@@ -240,7 +240,7 @@ class YoukuShowIE(InfoExtractor):
     }, {
         # Ongoing playlist. The initial page is the last one
         'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
-        'only_matchine': True,
+        'only_matching': True,
     }]
 
     def _extract_entries(self, playlist_data_url, show_id, note, query):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.10.29'
+__version__ = '2017.11.26'