Merge branch 'master' of https://github.com/rg3/youtube-dl

.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 *2019.01.30.1*. 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 Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.01*. 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 Issues with outdated version will be rejected.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 **2019.01.30.1**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.01**
 
 ### 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
@@ -36,7 +36,7 @@ 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 2019.01.30.1
+[debug] youtube-dl version 2019.03.01
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

.travis.yml

@@ -9,7 +9,6 @@ python:
   - "3.6"
   - "pypy"
   - "pypy3"
-sudo: false
 env:
   - YTDL_TEST_SET=core
   - YTDL_TEST_SET=download

ChangeLog

@@ -1,3 +1,72 @@
+version 2019.03.01
+
+Core
++ [downloader/external] Add support for rate limit and retries for wget
+* [downloader/external] Fix infinite retries for curl (#19303)
+
+Extractors
+* [npo] Fix extraction (#20084)
+* [francetv:site] Extend video id regex (#20029, #20071)
++ [periscope] Extract width and height (#20015)
+* [servus] Fix extraction (#19297)
+* [bbccouk] Make subtitles non fatal (#19651)
+* [metacafe] Fix family filter bypass (#19287)
+
+
+version 2019.02.18
+
+Extractors
+* [tvp:website] Fix and improve extraction
++ [tvp] Detect unavailable videos
+* [tvp] Fix description extraction and make thumbnail optional
++ [linuxacademy] Add support for linuxacademy.com (#12207)
+* [bilibili] Update keys (#19233)
+* [udemy] Extend URL regular expressions (#14330, #15883)
+* [udemy] Update User-Agent and detect captcha (#14713, #15839, #18126)
+* [noovo] Fix extraction (#19230)
+* [rai] Relax URL regular expression (#19232)
++ [vshare] Pass Referer to download request (#19205, #19221)
++ [openload] Add support for oload.live (#19222)
+* [imgur] Use video id as title fallback (#18590)
++ [twitch] Add new source format detection approach (#19193)
+* [tvplayhome] Fix video id extraction (#19190)
+* [tvplayhome] Fix episode metadata extraction (#19190)
+* [rutube:embed] Fix extraction (#19163)
++ [rutube:embed] Add support private videos (#19163)
++ [soundcloud] Extract more metadata
++ [trunews] Add support for trunews.com (#19153)
++ [linkedin:learning] Extract chapter_number and chapter_id (#19162)
+
+
+version 2019.02.08
+
+Core
+* [utils] Improve JSON-LD regular expression (#18058)
+* [YoutubeDL] Fallback to ie_key of matching extractor while making
+  download archive id when no explicit ie_key is provided (#19022)
+
+Extractors
++ [malltv] Add support for mall.tv (#18058, #17856)
++ [spankbang:playlist] Add support for playlists (#19145)
+* [spankbang] Extend URL regular expression
+* [trutv] Fix extraction (#17336)
+* [toutv] Fix authentication (#16398, #18700)
+* [pornhub] Fix tags and categories extraction (#13720, #19135)
+* [pornhd] Fix formats extraction
++ [pornhd] Extract like count (#19123, #19125)
+* [radiocanada] Switch to the new media requests (#19115)
++ [teachable] Add support for courses.workitdaily.com (#18871)
+- [vporn] Remove extractor (#16276)
++ [soundcloud:pagedplaylist] Add ie and title to entries (#19022, #19086)
++ [drtuber] Extract duration (#19078)
+* [soundcloud] Fix paged playlists extraction, add support for albums and update client id
+* [soundcloud] Update client id
+* [drtv] Improve preference (#19079)
++ [openload] Add support for openload.pw and oload.pw (#18930)
++ [openload] Add support for oload.info (#19073)
+* [crackle] Authorize media detail request (#16931)
+
+
 version 2019.01.30.1
 
 Core

docs/supportedsites.md

@@ -458,6 +458,7 @@
  - **LineTV**
  - **linkedin:learning**
  - **linkedin:learning:course**
+ - **LinuxAcademy**
  - **LiTV**
  - **LiveLeak**
  - **LiveLeakEmbed**
@@ -476,6 +477,7 @@
  - **mailru:music**: Музыка@Mail.Ru
  - **mailru:music:search**: Музыка@Mail.Ru
  - **MakerTV**
+ - **MallTV**
  - **mangomolo:live**
  - **mangomolo:video**
  - **ManyVids**
@@ -827,6 +829,7 @@
  - **southpark.nl**
  - **southparkstudios.dk**
  - **SpankBang**
+ - **SpankBangPlaylist**
  - **Spankwire**
  - **Spiegel**
  - **Spiegel:Article**: Articles on spiegel.de
@@ -913,6 +916,7 @@
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
+ - **TruNews**
  - **TruTV**
  - **Tube8**
  - **TubiTv**
@@ -1057,7 +1061,6 @@
  - **Voot**
  - **VoxMedia**
  - **VoxMediaVolume**
- - **Vporn**
  - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **Vrak**
  - **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be

test/test_InfoExtractor.py

@@ -61,6 +61,7 @@ class TestInfoExtractor(unittest.TestCase):
             <meta content='Foo' property=og:foobar>
             <meta name="og:test1" content='foo > < bar'/>
             <meta name="og:test2" content="foo >//< bar"/>
+            <meta property=og-test3 content='Ill-formatted opengraph'/>
             '''
         self.assertEqual(ie._og_search_title(html), 'Foo')
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
@@ -69,6 +70,7 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
         self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
         self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
+        self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph')
         self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
         self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
         self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)

test/test_YoutubeDLCookieJar.py

@@ -29,6 +29,16 @@ class TestYoutubeDLCookieJar(unittest.TestCase):
             tf.close()
             os.remove(tf.name)
 
+    def test_strip_httponly_prefix(self):
+        cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt')
+        cookiejar.load(ignore_discard=True, ignore_expires=True)
+
+        def assert_cookie_has_value(key):
+            self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE')
+
+        assert_cookie_has_value('HTTPONLY_COOKIE')
+        assert_cookie_has_value('JS_ACCESSIBLE_COOKIE')
+
 
 if __name__ == '__main__':
     unittest.main()

test/testdata/cookies/httponly_cookies.txt

@@ -0,0 +1,6 @@
+# Netscape HTTP Cookie File
+# http://curl.haxx.se/rfc/cookie_spec.html
+# This is a generated file!  Do not edit.
+
+#HttpOnly_www.foobar.foobar	FALSE	/	TRUE	2147483647	HTTPONLY_COOKIE	HTTPONLY_COOKIE_VALUE
+www.foobar.foobar	FALSE	/	TRUE	2147483647	JS_ACCESSIBLE_COOKIE	JS_ACCESSIBLE_COOKIE_VALUE

youtube_dl/YoutubeDL.py

@@ -82,6 +82,7 @@ from .utils import (
     sanitize_url,
     sanitized_Request,
     std_headers,
+    str_or_none,
     subtitles_filename,
     UnavailableVideoError,
     url_basename,
@@ -2060,15 +2061,24 @@ class YoutubeDL(object):
                         self.report_warning('Unable to remove downloaded original file')
 
     def _make_archive_id(self, info_dict):
+        video_id = info_dict.get('id')
+        if not video_id:
+            return
         # Future-proof against any change in case
         # and backwards compatibility with prior versions
-        extractor = info_dict.get('extractor_key')
+        extractor = info_dict.get('extractor_key') or info_dict.get('ie_key')  # key in a playlist
         if extractor is None:
-            if 'id' in info_dict:
+            url = str_or_none(info_dict.get('url'))
-                extractor = info_dict.get('ie_key')  # key in a playlist
+            if not url:
-        if extractor is None:
+                return
-            return None  # Incomplete video information
+            # Try to find matching extractor for the URL and take its ie_key
-        return extractor.lower() + ' ' + info_dict['id']
+            for ie in self._ies:
+                if ie.suitable(url):
+                    extractor = ie.ie_key()
+                    break
+            else:
+                return
+        return extractor.lower() + ' ' + video_id
 
     def in_download_archive(self, info_dict):
         fn = self.params.get('download_archive')
@@ -2076,7 +2086,7 @@ class YoutubeDL(object):
             return False
 
         vid_id = self._make_archive_id(info_dict)
-        if vid_id is None:
+        if not vid_id:
             return False  # Incomplete video information
 
         try:

youtube_dl/downloader/external.py

@@ -121,7 +121,11 @@ class CurlFD(ExternalFD):
         cmd += self._valueless_option('--silent', 'noprogress')
         cmd += self._valueless_option('--verbose', 'verbose')
         cmd += self._option('--limit-rate', 'ratelimit')
-        cmd += self._option('--retry', 'retries')
+        retry = self._option('--retry', 'retries')
+        if len(retry) == 2:
+            if retry[1] in ('inf', 'infinite'):
+                retry[1] = '2147483647'
+            cmd += retry
         cmd += self._option('--max-filesize', 'max_filesize')
         cmd += self._option('--interface', 'source_address')
         cmd += self._option('--proxy', 'proxy')
@@ -160,6 +164,12 @@ class WgetFD(ExternalFD):
         cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
+        cmd += self._option('--limit-rate', 'ratelimit')
+        retry = self._option('--tries', 'retries')
+        if len(retry) == 2:
+            if retry[1] in ('inf', 'infinite'):
+                retry[1] = '0'
+            cmd += retry
         cmd += self._option('--bind-address', 'source_address')
         cmd += self._option('--proxy', 'proxy')
         cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')

youtube_dl/extractor/bbc.py

@@ -1,8 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import itertools
+import re
+import xml
 
 from .common import InfoExtractor
 from ..utils import (
@@ -17,6 +18,7 @@ from ..utils import (
     parse_iso8601,
     try_get,
     unescapeHTML,
+    url_or_none,
     urlencode_postdata,
     urljoin,
 )
@@ -310,7 +312,13 @@ class BBCCoUkIE(InfoExtractor):
     def _get_subtitles(self, media, programme_id):
         subtitles = {}
         for connection in self._extract_connections(media):
-            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+            cc_url = url_or_none(connection.get('href'))
+            if not cc_url:
+                continue
+            captions = self._download_xml(
+                cc_url, programme_id, 'Downloading captions', fatal=False)
+            if not isinstance(captions, xml.etree.ElementTree.Element):
+                continue
             lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
             subtitles[lang] = [
                 {

youtube_dl/extractor/bilibili.py

@@ -93,8 +93,8 @@ class BiliBiliIE(InfoExtractor):
         }]
     }]
 
-    _APP_KEY = '84956560bc028eb7'
+    _APP_KEY = 'iVGUTjsxvpLeuDCf'
-    _BILIBILI_KEY = '94aba54af9065f71de72f5508f1cd42e'
+    _BILIBILI_KEY = 'aHRmhWMLkdeMuILqORnYZocwMBpMEOdt'
 
     def _report_error(self, result):
         if 'message' in result:

youtube_dl/extractor/common.py

@@ -1058,7 +1058,7 @@ class InfoExtractor(object):
     @staticmethod
     def _og_regexes(prop):
         content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
-        property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
+        property_re = (r'(?:name|property)=(?:\'og[:-]%(prop)s\'|"og[:-]%(prop)s"|\s*og[:-]%(prop)s\b)'
                        % {'prop': re.escape(prop)})
         template = r'<meta[^>]+?%s[^>]+?%s'
         return [

youtube_dl/extractor/crunchyroll.py

@@ -56,22 +56,11 @@ class CrunchyrollBaseIE(InfoExtractor):
         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')
 
         def is_logged(webpage):
-            return '<title>Redirecting' in webpage
+            return 'href="/logout"' in webpage
 
         # Already logged in
         if is_logged(login_page):
@@ -110,7 +99,6 @@ class CrunchyrollBaseIE(InfoExtractor):
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
         raise ExtractorError('Unable to log in')
-        '''
 
     def _real_initialize(self):
         self._login()

youtube_dl/extractor/drtuber.py

@@ -4,7 +4,9 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     NO_DEFAULT,
+    parse_duration,
     str_to_int,
 )
 
@@ -65,6 +67,9 @@ class DrTuberIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
+        duration = int_or_none(video_data.get('duration')) or parse_duration(
+            video_data.get('duration_format'))
+
         title = self._html_search_regex(
             (r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
              r'<title>([^<]+)\s*@\s+DrTuber',
@@ -103,4 +108,5 @@ class DrTuberIE(InfoExtractor):
             'comment_count': comment_count,
             'categories': categories,
             'age_limit': self._rta_search(webpage),
+            'duration': duration,
         }

youtube_dl/extractor/drtv.py

@@ -171,10 +171,13 @@ class DRTVIE(InfoExtractor):
                         continue
                     target = link.get('Target')
                     format_id = target or ''
-                    preference = None
+                    if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
-                    if asset_target in ('SpokenSubtitles', 'SignLanguage'):
                         preference = -1
                         format_id += '-%s' % asset_target
+                    elif asset_target == 'Default':
+                        preference = 1
+                    else:
+                        preference = None
                     if target == 'HDS':
                         f4m_formats = self._extract_f4m_formats(
                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',

youtube_dl/extractor/espn.py

@@ -29,7 +29,8 @@ class ESPNIE(OnceIE):
                                     (?:
                                         .*?\?.*?\bid=|
                                         /_/id/
-                                    )
+                                    )|
+                                    [^/]+/video/
                                 )
                             )|
                             (?:www\.)espnfc\.(?:com|us)/(?:video/)?[^/]+/\d+/video/
@@ -94,6 +95,9 @@ class ESPNIE(OnceIE):
     }, {
         'url': 'http://www.espnfc.com/english-premier-league/23/video/3324163/premier-league-in-90-seconds-golden-tweets',
         'only_matching': True,
+    }, {
+        'url': 'http://www.espn.com/espnw/video/26066627/arkansas-gibson-completes-hr-cycle-four-innings',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -593,6 +593,7 @@ from .linkedin import (
     LinkedInLearningIE,
     LinkedInLearningCourseIE,
 )
+from .linuxacademy import LinuxAcademyIE
 from .litv import LiTVIE
 from .liveleak import (
     LiveLeakIE,
@@ -619,6 +620,7 @@ from .mailru import (
     MailRuMusicSearchIE,
 )
 from .makertv import MakerTVIE
+from .malltv import MallTVIE
 from .mangomolo import (
     MangomoloVideoIE,
     MangomoloLiveIE,
@@ -1058,7 +1060,10 @@ from .southpark import (
     SouthParkEsIE,
     SouthParkNlIE
 )
-from .spankbang import SpankBangIE
+from .spankbang import (
+    SpankBangIE,
+    SpankBangPlaylistIE,
+)
 from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
@@ -1167,6 +1172,7 @@ from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trunews import TruNewsIE
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
@@ -1212,7 +1218,7 @@ from .tvnow import (
 from .tvp import (
     TVPEmbedIE,
     TVPIE,
-    TVPSeriesIE,
+    TVPWebsiteIE,
 )
 from .tvplay import (
     TVPlayIE,
@@ -1362,7 +1368,6 @@ from .voxmedia import (
     VoxMediaVolumeIE,
     VoxMediaIE,
 )
-from .vporn import VpornIE
 from .vrt import VRTIE
 from .vrak import VrakIE
 from .vrv import (

youtube_dl/extractor/francetv.py

@@ -271,7 +271,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
 
         catalogue = None
         video_id = self._search_regex(
-            r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1',
+            r'(?:data-main-video\s*=|videoId\s*:)\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'video id', default=None, group='id')
 
         if not video_id:

youtube_dl/extractor/imgur.py

@@ -27,6 +27,10 @@ class ImgurIE(InfoExtractor):
     }, {
         'url': 'https://i.imgur.com/crGpqCV.mp4',
         'only_matching': True,
+    }, {
+        # no title
+        'url': 'https://i.imgur.com/jxBXAMC.gifv',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -87,7 +91,7 @@ class ImgurIE(InfoExtractor):
         return {
             'id': video_id,
             'formats': formats,
-            'title': self._og_search_title(webpage),
+            'title': self._og_search_title(webpage, default=video_id),
         }
 
 

youtube_dl/extractor/libsyn.py

@@ -1,12 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
+    get_element_by_class,
     parse_duration,
+    strip_or_none,
     unified_strdate,
 )
 
@@ -21,7 +23,9 @@ class LibsynIE(InfoExtractor):
             'id': '6385796',
             'ext': 'mp3',
             'title': "Champion Minded - Developing a Growth Mindset",
-            'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
+            # description fetched using another request:
+            # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
+            # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
             'upload_date': '20180320',
             'thumbnail': 're:^https?://.*',
         },
@@ -38,22 +42,36 @@ class LibsynIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
+        url, video_id = re.match(self._VALID_URL, url).groups()
-        video_id = m.group('id')
-        url = m.group('mainurl')
         webpage = self._download_webpage(url, video_id)
 
-        podcast_title = self._search_regex(
+        data = self._parse_json(self._search_regex(
-            r'<h3>([^<]+)</h3>', webpage, 'podcast title', default=None)
+            r'var\s+playlistItem\s*=\s*({.+?});',
-        if podcast_title:
+            webpage, 'JSON data block'), video_id)
-            podcast_title = podcast_title.strip()
+
-        episode_title = self._search_regex(
+        episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
-            r'(?:<div class="episode-title">|<h4>)([^<]+)</', webpage, 'episode title')
+        if not episode_title:
-        if episode_title:
+            self._search_regex(
-            episode_title = episode_title.strip()
+                [r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
+                webpage, 'episode title')
+        episode_title = episode_title.strip()
+
+        podcast_title = strip_or_none(clean_html(self._search_regex(
+            r'<h3>([^<]+)</h3>', webpage, 'podcast title',
+            default=None) or get_element_by_class('podcast-title', webpage)))
 
         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
 
+        formats = []
+        for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
+            f_url = data.get(k)
+            if not f_url:
+                continue
+            formats.append({
+                'url': f_url,
+                'format_id': format_id,
+            })
+
         description = self._html_search_regex(
             r'<p\s+id="info_text_body">(.+?)</p>', webpage,
             'description', default=None)
@@ -61,27 +79,15 @@ class LibsynIE(InfoExtractor):
             # Strip non-breaking and normal spaces
             description = description.replace('\u00A0', ' ').strip()
         release_date = unified_strdate(self._search_regex(
-            r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
+            r'<div class="release_date">Released: ([^<]+)<',
-
+            webpage, 'release date', default=None) or data.get('release_date'))
-        data_json = self._search_regex(r'var\s+playlistItem\s*=\s*(\{.*?\});\n', webpage, 'JSON data block')
-        data = json.loads(data_json)
-
-        formats = [{
-            'url': data['media_url'],
-            'format_id': 'main',
-        }, {
-            'url': data['media_url_libsyn'],
-            'format_id': 'libsyn',
-        }]
-        thumbnail = data.get('thumbnail_url')
-        duration = parse_duration(data.get('duration'))
 
         return {
             'id': video_id,
             'title': title,
             'description': description,
-            'thumbnail': thumbnail,
+            'thumbnail': data.get('thumbnail_url'),
             'upload_date': release_date,
-            'duration': duration,
+            'duration': parse_duration(data.get('duration')),
             'formats': formats,
         }

youtube_dl/extractor/linkedin.py

@@ -34,12 +34,15 @@ class LinkedInLearningBaseIE(InfoExtractor):
                 'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value,
             }, query=query)['elements'][0]
 
-    def _get_video_id(self, urn, course_slug, video_slug):
+    def _get_urn_id(self, video_data):
+        urn = video_data.get('urn')
         if urn:
             mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn)
             if mobj:
                 return mobj.group(1)
-        return '%s/%s' % (course_slug, video_slug)
+
+    def _get_video_id(self, video_data, course_slug, video_slug):
+        return self._get_urn_id(video_data) or '%s/%s' % (course_slug, video_slug)
 
     def _real_initialize(self):
         email, password = self._get_login_info()
@@ -123,7 +126,7 @@ class LinkedInLearningIE(LinkedInLearningBaseIE):
         self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr'))
 
         return {
-            'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug),
+            'id': self._get_video_id(video_data, course_slug, video_slug),
             'title': title,
             'formats': formats,
             'thumbnail': video_data.get('defaultThumbnail'),
@@ -154,18 +157,21 @@ class LinkedInLearningCourseIE(LinkedInLearningBaseIE):
         course_data = self._call_api(course_slug, 'chapters,description,title')
 
         entries = []
-        for chapter in course_data.get('chapters', []):
+        for chapter_number, chapter in enumerate(course_data.get('chapters', []), 1):
             chapter_title = chapter.get('title')
+            chapter_id = self._get_urn_id(chapter)
             for video in chapter.get('videos', []):
                 video_slug = video.get('slug')
                 if not video_slug:
                     continue
                 entries.append({
                     '_type': 'url_transparent',
-                    'id': self._get_video_id(video.get('urn'), course_slug, video_slug),
+                    'id': self._get_video_id(video, course_slug, video_slug),
                     'title': video.get('title'),
                     'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug),
                     'chapter': chapter_title,
+                    'chapter_number': chapter_number,
+                    'chapter_id': chapter_id,
                     'ie_key': LinkedInLearningIE.ie_key(),
                 })
 

youtube_dl/extractor/linuxacademy.py

@@ -0,0 +1,174 @@
+from __future__ import unicode_literals
+
+import json
+import random
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_b64decode,
+    compat_HTTPError,
+    compat_str,
+)
+from ..utils import (
+    ExtractorError,
+    orderedSet,
+    unescapeHTML,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class LinuxAcademyIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?linuxacademy\.com/cp/
+                        (?:
+                            courses/lesson/course/(?P<chapter_id>\d+)/lesson/(?P<lesson_id>\d+)|
+                            modules/view/id/(?P<course_id>\d+)
+                        )
+                    '''
+    _TESTS = [{
+        'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2/module/154',
+        'info_dict': {
+            'id': '1498-2',
+            'ext': 'mp4',
+            'title': "Introduction to the Practitioner's Brief",
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'Requires Linux Academy account credentials',
+    }, {
+        'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2',
+        'only_matching': True,
+    }, {
+        'url': 'https://linuxacademy.com/cp/modules/view/id/154',
+        'info_dict': {
+            'id': '154',
+            'title': 'AWS Certified Cloud Practitioner',
+            'description': 'md5:039db7e60e4aac9cf43630e0a75fa834',
+        },
+        'playlist_count': 41,
+        'skip': 'Requires Linux Academy account credentials',
+    }]
+
+    _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize'
+    _ORIGIN_URL = 'https://linuxacademy.com'
+    _CLIENT_ID = 'KaWxNn1C2Gc7n83W9OFeXltd8Utb5vvx'
+    _NETRC_MACHINE = 'linuxacademy'
+
+    def _real_initialize(self):
+        self._login()
+
+    def _login(self):
+        username, password = self._get_login_info()
+        if username is None:
+            return
+
+        def random_string():
+            return ''.join([
+                random.choice('0123456789ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz-._~')
+                for _ in range(32)])
+
+        webpage, urlh = self._download_webpage_handle(
+            self._AUTHORIZE_URL, None, 'Downloading authorize page', query={
+                'client_id': self._CLIENT_ID,
+                'response_type': 'token id_token',
+                'redirect_uri': self._ORIGIN_URL,
+                'scope': 'openid email user_impersonation profile',
+                'audience': self._ORIGIN_URL,
+                'state': random_string(),
+                'nonce': random_string(),
+            })
+
+        login_data = self._parse_json(
+            self._search_regex(
+                r'atob\(\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
+                'login info', group='value'), None,
+            transform_source=lambda x: compat_b64decode(x).decode('utf-8')
+        )['extraParams']
+
+        login_data.update({
+            'client_id': self._CLIENT_ID,
+            'redirect_uri': self._ORIGIN_URL,
+            'tenant': 'lacausers',
+            'connection': 'Username-Password-Authentication',
+            'username': username,
+            'password': password,
+            'sso': 'true',
+        })
+
+        login_state_url = compat_str(urlh.geturl())
+
+        try:
+            login_page = self._download_webpage(
+                'https://login.linuxacademy.com/usernamepassword/login', None,
+                'Downloading login page', data=json.dumps(login_data).encode(),
+                headers={
+                    'Content-Type': 'application/json',
+                    'Origin': 'https://login.linuxacademy.com',
+                    'Referer': login_state_url,
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                error = self._parse_json(e.cause.read(), None)
+                message = error.get('description') or error['code']
+                raise ExtractorError(
+                    '%s said: %s' % (self.IE_NAME, message), expected=True)
+            raise
+
+        callback_page, urlh = self._download_webpage_handle(
+            'https://login.linuxacademy.com/login/callback', None,
+            'Downloading callback page',
+            data=urlencode_postdata(self._hidden_inputs(login_page)),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Origin': 'https://login.linuxacademy.com',
+                'Referer': login_state_url,
+            })
+
+        access_token = self._search_regex(
+            r'access_token=([^=&]+)', compat_str(urlh.geturl()),
+            'access token')
+
+        self._download_webpage(
+            'https://linuxacademy.com/cp/login/tokenValidateLogin/token/%s'
+            % access_token, None, 'Downloading token validation page')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        chapter_id, lecture_id, course_id = mobj.group('chapter_id', 'lesson_id', 'course_id')
+        item_id = course_id if course_id else '%s-%s' % (chapter_id, lecture_id)
+
+        webpage = self._download_webpage(url, item_id)
+
+        # course path
+        if course_id:
+            entries = [
+                self.url_result(
+                    urljoin(url, lesson_url), ie=LinuxAcademyIE.ie_key())
+                for lesson_url in orderedSet(re.findall(
+                    r'<a[^>]+\bhref=["\'](/cp/courses/lesson/course/\d+/lesson/\d+/module/\d+)',
+                    webpage))]
+            title = unescapeHTML(self._html_search_regex(
+                (r'class=["\']course-title["\'][^>]*>(?P<value>[^<]+)',
+                 r'var\s+title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'),
+                webpage, 'title', default=None, group='value'))
+            description = unescapeHTML(self._html_search_regex(
+                r'var\s+description\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'description', default=None, group='value'))
+            return self.playlist_result(entries, course_id, title, description)
+
+        # single video path
+        info = self._extract_jwplayer_data(
+            webpage, item_id, require_title=False, m3u8_id='hls',)
+        title = self._search_regex(
+            (r'>Lecture\s*:\s*(?P<value>[^<]+)',
+             r'lessonName\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'title', group='value')
+        info.update({
+            'id': item_id,
+            'title': title,
+        })
+        return info

youtube_dl/extractor/malltv.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import merge_dicts
+
+
+class MallTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+        'md5': '1c4a37f080e1f3023103a7b43458e518',
+        'info_dict': {
+            'id': 't0zzt0',
+            'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+            'ext': 'mp4',
+            'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
+            'description': 'md5:25fc0ec42a72ba602b602c683fa29deb',
+            'duration': 216,
+            'timestamp': 1538870400,
+            'upload_date': '20181007',
+            'view_count': int,
+        }
+    }, {
+        'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, display_id, headers=self.geo_verification_headers())
+
+        SOURCE_RE = r'(<source[^>]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P<id>[\da-z]+)/index)\b'
+        video_id = self._search_regex(
+            SOURCE_RE, webpage, 'video id', group='id')
+
+        media = self._parse_html5_media_entries(
+            url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id,
+            m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0]
+
+        info = self._search_json_ld(webpage, video_id, default={})
+
+        return merge_dicts(media, info, {
+            'id': video_id,
+            'display_id': display_id,
+            'title': self._og_search_title(webpage, default=None) or display_id,
+            'description': self._og_search_description(webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+        })

youtube_dl/extractor/metacafe.py

@@ -1,12 +1,13 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
+    compat_urllib_parse,
     compat_urllib_parse_unquote,
-    compat_urllib_parse_urlencode,
 )
 from ..utils import (
     determine_ext,
@@ -144,7 +145,7 @@ class MetacafeIE(InfoExtractor):
 
         headers = {
             # Disable family filter
-            'Cookie': 'user=%s; ' % compat_urllib_parse_urlencode({'ffilter': False})
+            'Cookie': 'user=%s; ' % compat_urllib_parse.quote(json.dumps({'ffilter': False}))
         }
 
         # AnyClip videos require the flashversion cookie so that we get the link

youtube_dl/extractor/noovo.py

@@ -57,7 +57,8 @@ class NoovoIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        bc_url = BrightcoveNewIE._extract_url(self, webpage)
+        brightcove_id = self._search_regex(
+            r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
 
         data = self._parse_json(
             self._search_regex(
@@ -89,7 +90,10 @@ class NoovoIE(InfoExtractor):
         return {
             '_type': 'url_transparent',
             'ie_key': BrightcoveNewIE.ie_key(),
-            'url': smuggle_url(bc_url, {'geo_countries': ['CA']}),
+            'url': smuggle_url(
+                self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+                {'geo_countries': ['CA']}),
+            'id': brightcove_id,
             'title': title,
             'description': description,
             'series': series,

youtube_dl/extractor/npo.py

@@ -12,11 +12,16 @@ from ..utils import (
     ExtractorError,
     fix_xml_ampersands,
     int_or_none,
+    merge_dicts,
     orderedSet,
     parse_duration,
     qualities,
+    str_or_none,
     strip_jsonp,
     unified_strdate,
+    unified_timestamp,
+    url_or_none,
+    urlencode_postdata,
 )
 
 
@@ -176,9 +181,118 @@ class NPOIE(NPOBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        return self._get_info(video_id)
+        try:
+            return self._get_info(url, video_id)
+        except ExtractorError:
+            return self._get_old_info(video_id)
 
-    def _get_info(self, video_id):
+    def _get_info(self, url, video_id):
+        token = self._download_json(
+            'https://www.npostart.nl/api/token', video_id,
+            'Downloading token', headers={
+                'Referer': url,
+                'X-Requested-With': 'XMLHttpRequest',
+            })['token']
+
+        player = self._download_json(
+            'https://www.npostart.nl/player/%s' % video_id, video_id,
+            'Downloading player JSON', data=urlencode_postdata({
+                'autoplay': 0,
+                'share': 1,
+                'pageUrl': url,
+                'hasAdConsent': 0,
+                '_token': token,
+            }))
+
+        player_token = player['token']
+
+        format_urls = set()
+        formats = []
+        for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
+            streams = self._download_json(
+                'https://start-player.npo.nl/video/%s/streams' % video_id,
+                video_id, 'Downloading %s profile JSON' % profile, fatal=False,
+                query={
+                    'profile': profile,
+                    'quality': 'npo',
+                    'tokenId': player_token,
+                    'streamType': 'broadcast',
+                })
+            if not streams:
+                continue
+            stream = streams.get('stream')
+            if not isinstance(stream, dict):
+                continue
+            stream_url = url_or_none(stream.get('src'))
+            if not stream_url or stream_url in format_urls:
+                continue
+            format_urls.add(stream_url)
+            if stream.get('protection') is not None:
+                continue
+            stream_type = stream.get('type')
+            stream_ext = determine_ext(stream_url)
+            if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    stream_url, video_id, mpd_id='dash', fatal=False))
+            elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, video_id, ext='mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+            elif '.ism/Manifest' in stream_url:
+                formats.extend(self._extract_ism_formats(
+                    stream_url, video_id, ism_id='mss', fatal=False))
+            else:
+                formats.append({
+                    'url': stream_url,
+                })
+
+        self._sort_formats(formats)
+
+        info = {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+        }
+
+        embed_url = url_or_none(player.get('embedUrl'))
+        if embed_url:
+            webpage = self._download_webpage(
+                embed_url, video_id, 'Downloading embed page', fatal=False)
+            if webpage:
+                video = self._parse_json(
+                    self._search_regex(
+                        r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
+                        default='{}'), video_id)
+                if video:
+                    title = video.get('episodeTitle')
+                    subtitles = {}
+                    subtitles_list = video.get('subtitles')
+                    if isinstance(subtitles_list, list):
+                        for cc in subtitles_list:
+                            cc_url = url_or_none(cc.get('src'))
+                            if not cc_url:
+                                continue
+                            lang = str_or_none(cc.get('language')) or 'nl'
+                            subtitles.setdefault(lang, []).append({
+                                'url': cc_url,
+                            })
+                    return merge_dicts({
+                        'title': title,
+                        'description': video.get('description'),
+                        'thumbnail': url_or_none(
+                            video.get('still_image_url') or video.get('orig_image_url')),
+                        'duration': int_or_none(video.get('duration')),
+                        'timestamp': unified_timestamp(video.get('broadcastDate')),
+                        'creator': video.get('channel'),
+                        'series': video.get('title'),
+                        'episode': title,
+                        'episode_number': int_or_none(video.get('episodeNumber')),
+                        'subtitles': subtitles,
+                    }, info)
+
+        return info
+
+    def _get_old_info(self, video_id):
         metadata = self._download_json(
             'http://e.omroep.nl/metadata/%s' % video_id,
             video_id,
@@ -280,7 +394,7 @@ class NPOIE(NPOBaseIE):
             # JSON
             else:
                 video_url = stream_info.get('url')
-            if not video_url or video_url in urls:
+            if not video_url or 'vodnotavailable.' in video_url or video_url in urls:
                 continue
             urls.add(video_url)
             if determine_ext(video_url) == 'm3u8':

youtube_dl/extractor/openload.py

@@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor):
                             (?:www\.)?
                             (?:
                                 openload\.(?:co|io|link|pw)|
-                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw)
+                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live)
                             )
                         )/
                         (?:f|embed)/
@@ -346,6 +346,9 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.pw/f/WyKgK8s94N0',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.live/f/-Z58UZ-GR4M',
+        '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/periscope.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     parse_iso8601,
     unescapeHTML,
 )
@@ -75,6 +76,14 @@ class PeriscopeIE(PeriscopeBaseIE):
             'url': broadcast[image],
         } for image in ('image_url', 'image_url_small') if broadcast.get(image)]
 
+        width = int_or_none(broadcast.get('width'))
+        height = int_or_none(broadcast.get('height'))
+
+        def add_width_and_height(f):
+            for key, val in (('width', width), ('height', height)):
+                if not f.get(key):
+                    f[key] = val
+
         video_urls = set()
         formats = []
         for format_id in ('replay', 'rtmp', 'hls', 'https_hls', 'lhls', 'lhlsweb'):
@@ -83,16 +92,21 @@ class PeriscopeIE(PeriscopeBaseIE):
                 continue
             video_urls.add(video_url)
             if format_id != 'rtmp':
-                formats.extend(self._extract_m3u8_formats(
+                m3u8_formats = self._extract_m3u8_formats(
                     video_url, token, 'mp4',
                     entry_protocol='m3u8_native'
                     if state in ('ended', 'timed_out') else 'm3u8',
-                    m3u8_id=format_id, fatal=False))
+                    m3u8_id=format_id, fatal=False)
+                if len(m3u8_formats) == 1:
+                    add_width_and_height(m3u8_formats[0])
+                formats.extend(m3u8_formats)
                 continue
-            formats.append({
+            rtmp_format = {
                 'url': video_url,
                 'ext': 'flv' if format_id == 'rtmp' else 'mp4',
-            })
+            }
+            add_width_and_height(rtmp_format)
+            formats.append(rtmp_format)
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/pornhd.py

@@ -4,9 +4,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
     int_or_none,
     js_to_json,
+    urljoin,
 )
 
 
@@ -14,7 +16,7 @@ class PornHdIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
     _TESTS = [{
         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
-        'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
+        'md5': '87f1540746c1d32ec7a2305c12b96b25',
         'info_dict': {
             'id': '9864',
             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
@@ -23,6 +25,7 @@ class PornHdIE(InfoExtractor):
             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
             'thumbnail': r're:^https?://.*\.jpg',
             'view_count': int,
+            'like_count': int,
             'age_limit': 18,
         }
     }, {
@@ -37,6 +40,7 @@ class PornHdIE(InfoExtractor):
             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
             'thumbnail': r're:^https?://.*\.jpg',
             'view_count': int,
+            'like_count': int,
             'age_limit': 18,
         },
         'skip': 'Not available anymore',
@@ -65,12 +69,14 @@ class PornHdIE(InfoExtractor):
 
         formats = []
         for format_id, video_url in sources.items():
+            video_url = urljoin(url, video_url)
             if not video_url:
                 continue
             height = int_or_none(self._search_regex(
                 r'^(\d+)[pP]', format_id, 'height', default=None))
             formats.append({
                 'url': video_url,
+                'ext': determine_ext(video_url, 'mp4'),
                 'format_id': format_id,
                 'height': height,
             })
@@ -85,6 +91,11 @@ class PornHdIE(InfoExtractor):
             r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
             'thumbnail', fatal=False, group='url')
 
+        like_count = int_or_none(self._search_regex(
+            (r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
+             r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
+            webpage, 'like count', fatal=False))
+
         return {
             'id': video_id,
             'display_id': display_id,
@@ -92,6 +103,7 @@ class PornHdIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,
+            'like_count': like_count,
             'formats': formats,
             'age_limit': 18,
         }

youtube_dl/extractor/pornhub.py

@@ -16,7 +16,6 @@ from .openload import PhantomJSwrapper
 from ..utils import (
     ExtractorError,
     int_or_none,
-    js_to_json,
     orderedSet,
     remove_quotes,
     str_to_int,
@@ -303,14 +302,12 @@ class PornHubIE(PornHubBaseIE):
         comment_count = self._extract_count(
             r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
 
-        page_params = self._parse_json(self._search_regex(
+        def extract_list(meta_key):
-            r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
+            div = self._search_regex(
-            webpage, 'page parameters', group='data', default='{}'),
+                r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
-            video_id, transform_source=js_to_json, fatal=False)
+                % meta_key, webpage, meta_key, default=None)
-        tags = categories = None
+            if div:
-        if page_params:
+                return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
-            tags = page_params.get('tags', '').split(',')
-            categories = page_params.get('categories', '').split(',')
 
         return {
             'id': video_id,
@@ -325,8 +322,8 @@ class PornHubIE(PornHubBaseIE):
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
-            'tags': tags,
+            'tags': extract_list('tags'),
-            'categories': categories,
+            'categories': extract_list('categories'),
             'subtitles': subtitles,
         }
 

youtube_dl/extractor/radiocanada.py

@@ -4,16 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
-    xpath_text,
-    find_xpath_attr,
     determine_ext,
+    ExtractorError,
     int_or_none,
     unified_strdate,
-    xpath_element,
-    ExtractorError,
-    determine_protocol,
-    unsmuggle_url,
 )
 
 
@@ -61,107 +57,67 @@ class RadioCanadaIE(InfoExtractor):
             'only_matching': True,
         }
     ]
+    _GEO_COUNTRIES = ['CA']
+    _access_token = None
+    _claims = None
 
-    def _real_extract(self, url):
+    def _call_api(self, path, video_id=None, app_code=None, query=None):
-        url, smuggled_data = unsmuggle_url(url, {})
+        if not query:
-        app_code, video_id = re.match(self._VALID_URL, url).groups()
+            query = {}
-
+        query.update({
-        metadata = self._download_xml(
+            'client_key': '773aea60-0e80-41bb-9c7f-e6d7c3ad17fb',
-            'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
+            'output': 'json',
-            video_id, note='Downloading metadata XML', query={
+        })
+        if video_id:
+            query.update({
                 'appCode': app_code,
                 'idMedia': video_id,
             })
+        if self._access_token:
+            query['access_token'] = self._access_token
+        try:
+            return self._download_json(
+                'https://services.radio-canada.ca/media/' + path, video_id, query=query)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422):
+                data = self._parse_json(e.cause.read().decode(), None)
+                error = data.get('error_description') or data['errorMessage']['text']
+                raise ExtractorError(error, expected=True)
+            raise
+
+    def _extract_info(self, app_code, video_id):
+        metas = self._call_api('meta/v1/index.ashx', video_id, app_code)['Metas']
 
         def get_meta(name):
-            el = find_xpath_attr(metadata, './/Meta', 'name', name)
+            for meta in metas:
-            return el.text if el is not None else None
+                if meta.get('name') == name:
+                    text = meta.get('text')
+                    if text:
+                        return text
 
         # protectionType does not necessarily mean the video is DRM protected (see
         # https://github.com/rg3/youtube-dl/pull/18609).
         if get_meta('protectionType'):
             self.report_warning('This video is probably DRM protected.')
 
-        device_types = ['ipad']
+        query = {
-        if not smuggled_data:
+            'connectionType': 'hd',
-            device_types.append('flash')
+            'deviceType': 'ipad',
-            device_types.append('android')
+            'multibitrate': 'true',
-
+        }
-        formats = []
+        if self._claims:
-        error = None
+            query['claims'] = self._claims
-        # TODO: extract f4m formats
+        v_data = self._call_api('validation/v2/', video_id, app_code, query)
-        # f4m formats can be extracted using flashhd device_type but they produce unplayable file
+        v_url = v_data.get('url')
-        for device_type in device_types:
+        if not v_url:
-            validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx'
+            error = v_data['message']
-            query = {
+            if error == "Le contenu sélectionné n'est pas disponible dans votre pays":
-                'appCode': app_code,
+                raise self.raise_geo_restricted(error, self._GEO_COUNTRIES)
-                'idMedia': video_id,
+            if error == 'Le contenu sélectionné est disponible seulement en premium':
-                'connectionType': 'broadband',
+                self.raise_login_required(error)
-                'multibitrate': 'true',
-                'deviceType': device_type,
-            }
-            if smuggled_data:
-                validation_url = 'https://services.radio-canada.ca/media/validation/v2/'
-                query.update(smuggled_data)
-            else:
-                query.update({
-                    # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
-                    'paysJ391wsHjbOJwvCs26toz': 'CA',
-                    'bypasslock': 'NZt5K62gRqfc',
-                })
-            v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False)
-            v_url = xpath_text(v_data, 'url')
-            if not v_url:
-                continue
-            if v_url == 'null':
-                error = xpath_text(v_data, 'message')
-                continue
-            ext = determine_ext(v_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    v_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    v_url, video_id, f4m_id='hds', fatal=False))
-            else:
-                ext = determine_ext(v_url)
-                bitrates = xpath_element(v_data, 'bitrates')
-                for url_e in bitrates.findall('url'):
-                    tbr = int_or_none(url_e.get('bitrate'))
-                    if not tbr:
-                        continue
-                    f_url = re.sub(r'\d+\.%s' % ext, '%d.%s' % (tbr, ext), v_url)
-                    protocol = determine_protocol({'url': f_url})
-                    f = {
-                        'format_id': '%s-%d' % (protocol, tbr),
-                        'url': f_url,
-                        'ext': 'flv' if protocol == 'rtmp' else ext,
-                        'protocol': protocol,
-                        'width': int_or_none(url_e.get('width')),
-                        'height': int_or_none(url_e.get('height')),
-                        'tbr': tbr,
-                    }
-                    mobj = re.match(r'(?P<url>rtmp://[^/]+/[^/]+)/(?P<playpath>[^?]+)(?P<auth>\?.+)', f_url)
-                    if mobj:
-                        f.update({
-                            'url': mobj.group('url') + mobj.group('auth'),
-                            'play_path': mobj.group('playpath'),
-                        })
-                    formats.append(f)
-                    if protocol == 'rtsp':
-                        base_url = self._search_regex(
-                            r'rtsp://([^?]+)', f_url, 'base url', default=None)
-                        if base_url:
-                            base_url = 'http://' + base_url
-                            formats.extend(self._extract_m3u8_formats(
-                                base_url + '/playlist.m3u8', video_id, 'mp4',
-                                'm3u8_native', m3u8_id='hls', fatal=False))
-                            formats.extend(self._extract_f4m_formats(
-                                base_url + '/manifest.f4m', video_id,
-                                f4m_id='hds', fatal=False))
-        if not formats and error:
             raise ExtractorError(
                 '%s said: %s' % (self.IE_NAME, error), expected=True)
+        formats = self._extract_m3u8_formats(v_url, video_id, 'mp4')
         self._sort_formats(formats)
 
         subtitles = {}
@@ -186,11 +142,14 @@ class RadioCanadaIE(InfoExtractor):
             'formats': formats,
         }
 
+    def _real_extract(self, url):
+        return self._extract_info(*re.match(self._VALID_URL, url).groups())
+
 
 class RadioCanadaAudioVideoIE(InfoExtractor):
     'radiocanada:audiovideo'
-    _VALID_URL = r'https?://ici\.radio-canada\.ca/audio-video/media-(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://ici\.radio-canada\.ca/([^/]+/)*media-(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam',
         'info_dict': {
             'id': '7527184',
@@ -203,7 +162,10 @@ class RadioCanadaAudioVideoIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'https://ici.radio-canada.ca/info/videos/media-7527184/barack-obama-au-vietnam',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         return self.url_result('radiocanada:medianet:%s' % self._match_id(url))

youtube_dl/extractor/rai.py

@@ -288,7 +288,7 @@ class RaiPlayPlaylistIE(InfoExtractor):
 
 
 class RaiIE(RaiBaseIE):
-    _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
+    _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
     _TESTS = [{
         # var uniquename = "ContentItem-..."
         # data-id="ContentItem-..."
@@ -375,6 +375,9 @@ class RaiIE(RaiBaseIE):
         # Direct MMS URL
         'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html',
+        'only_matching': True,
     }]
 
     def _extract_from_content_id(self, content_id, url):

youtube_dl/extractor/rutube.py

@@ -21,7 +21,17 @@ from ..utils import (
 
 
 class RutubeBaseIE(InfoExtractor):
-    def _extract_video(self, video, video_id=None, require_title=True):
+    def _download_api_info(self, video_id, query=None):
+        if not query:
+            query = {}
+        query['format'] = 'json'
+        return self._download_json(
+            'http://rutube.ru/api/video/%s/' % video_id,
+            video_id, 'Downloading video JSON',
+            'Unable to download video JSON', query=query)
+
+    @staticmethod
+    def _extract_info(video, video_id=None, require_title=True):
         title = video['title'] if require_title else video.get('title')
 
         age_limit = video.get('is_adult')
@@ -32,7 +42,7 @@ class RutubeBaseIE(InfoExtractor):
         category = try_get(video, lambda x: x['category']['name'])
 
         return {
-            'id': video.get('id') or video_id,
+            'id': video.get('id') or video_id if video_id else video['id'],
             'title': title,
             'description': video.get('description'),
             'thumbnail': video.get('thumbnail_url'),
@@ -47,6 +57,42 @@ class RutubeBaseIE(InfoExtractor):
             'is_live': bool_or_none(video.get('is_livestream')),
         }
 
+    def _download_and_extract_info(self, video_id, query=None):
+        return self._extract_info(
+            self._download_api_info(video_id, query=query), video_id)
+
+    def _download_api_options(self, video_id, query=None):
+        if not query:
+            query = {}
+        query['format'] = 'json'
+        return self._download_json(
+            'http://rutube.ru/api/play/options/%s/' % video_id,
+            video_id, 'Downloading options JSON',
+            'Unable to download options JSON',
+            headers=self.geo_verification_headers(), query=query)
+
+    def _extract_formats(self, options, video_id):
+        formats = []
+        for format_id, format_url in options['video_balancer'].items():
+            ext = determine_ext(format_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    format_url, video_id, f4m_id=format_id, fatal=False))
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                })
+        self._sort_formats(formats)
+        return formats
+
+    def _download_and_extract_formats(self, video_id, query=None):
+        return self._extract_formats(
+            self._download_api_options(video_id, query=query), video_id)
+
 
 class RutubeIE(RutubeBaseIE):
     IE_NAME = 'rutube'
@@ -55,13 +101,13 @@ class RutubeIE(RutubeBaseIE):
 
     _TESTS = [{
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
-        'md5': '79938ade01294ef7e27574890d0d3769',
+        'md5': '1d24f180fac7a02f3900712e5a5764d6',
         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
-            'duration': 80,
+            'duration': 81,
             'uploader': 'NTDRussian',
             'uploader_id': '29790',
             'timestamp': 1381943602,
@@ -94,39 +140,12 @@ class RutubeIE(RutubeBaseIE):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
+        info = self._download_and_extract_info(video_id)
-        video = self._download_json(
+        info['formats'] = self._download_and_extract_formats(video_id)
-            'http://rutube.ru/api/video/%s/?format=json' % video_id,
-            video_id, 'Downloading video JSON')
-
-        info = self._extract_video(video, video_id)
-
-        options = self._download_json(
-            'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
-            video_id, 'Downloading options JSON',
-            headers=self.geo_verification_headers())
-
-        formats = []
-        for format_id, format_url in options['video_balancer'].items():
-            ext = determine_ext(format_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    format_url, video_id, f4m_id=format_id, fatal=False))
-            else:
-                formats.append({
-                    'url': format_url,
-                    'format_id': format_id,
-                })
-        self._sort_formats(formats)
-
-        info['formats'] = formats
         return info
 
 
-class RutubeEmbedIE(InfoExtractor):
+class RutubeEmbedIE(RutubeBaseIE):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'
     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
@@ -135,7 +154,7 @@ class RutubeEmbedIE(InfoExtractor):
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
-            'ext': 'flv',
+            'ext': 'mp4',
             'timestamp': 1387830582,
             'upload_date': '20131223',
             'uploader_id': '297833',
@@ -149,16 +168,26 @@ class RutubeEmbedIE(InfoExtractor):
     }, {
         'url': 'http://rutube.ru/play/embed/8083783',
         'only_matching': True,
+    }, {
+        # private video
+        'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         embed_id = self._match_id(url)
-        webpage = self._download_webpage(url, embed_id)
+        # Query may contain private videos token and should be passed to API
-
+        # requests (see #19163)
-        canonical_url = self._html_search_regex(
+        query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
-            r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
+        options = self._download_api_options(embed_id, query)
-            'Canonical URL')
+        video_id = options['effective_video']
-        return self.url_result(canonical_url, RutubeIE.ie_key())
+        formats = self._extract_formats(options, video_id)
+        info = self._download_and_extract_info(video_id, query)
+        info.update({
+            'extractor_key': 'Rutube',
+            'formats': formats,
+        })
+        return info
 
 
 class RutubePlaylistBaseIE(RutubeBaseIE):
@@ -181,7 +210,7 @@ class RutubePlaylistBaseIE(RutubeBaseIE):
                 video_url = url_or_none(result.get('video_url'))
                 if not video_url:
                     continue
-                entry = self._extract_video(result, require_title=False)
+                entry = self._extract_info(result, require_title=False)
                 entry.update({
                     '_type': 'url',
                     'url': video_url,

youtube_dl/extractor/servus.py

@@ -1,31 +1,44 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 
 
 class ServusIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:at|de)/p/[^/]+/(?P<id>AA-\w+|\d+-\d+)'
+    _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)'
     _TESTS = [{
         'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
-        'md5': '046dee641cda1c4cabe13baef3be2c1c',
+        'md5': '3e1dd16775aa8d5cbef23628cfffc1f4',
         'info_dict': {
             'id': 'AA-1T6VBU5PW1W12',
             'ext': 'mp4',
-            'title': 'Die Grünen aus Volkssicht',
+            'title': 'Die Grünen aus Sicht des Volkes',
-            'description': 'md5:052b5da1cb2cd7d562ef1f19be5a5cba',
+            'description': 'md5:1247204d85783afe3682644398ff2ec4',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg',
         }
     }, {
         'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id = self._match_id(url).upper()
         webpage = self._download_webpage(url, video_id)
 
-        title = self._og_search_title(webpage)
+        title = self._search_regex(
+            (r'videoLabel\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'<h\d+[^>]+\bclass=["\']heading--(?:one|two)["\'][^>]*>(?P<title>[^<]+)'),
+            webpage, 'title', default=None,
+            group='title') or self._og_search_title(webpage)
+        title = re.sub(r'\s*-\s*Servus TV\s*$', '', title)
         description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
 

youtube_dl/extractor/sixplay.py

@@ -61,7 +61,8 @@ class SixPlayIE(InfoExtractor):
         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
         formats = []
         subtitles = {}
-        for asset in clip_data['assets']:
+        assets = clip_data.get('assets') or []
+        for asset in assets:
             asset_url = asset.get('full_physical_path')
             protocol = asset.get('protocol')
             if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls:

youtube_dl/extractor/soundcloud.py

@@ -16,8 +16,10 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
-    unified_strdate,
+    try_get,
+    unified_timestamp,
     update_url_query,
+    url_or_none,
 )
 
 
@@ -34,7 +36,7 @@ class SoundcloudIE(InfoExtractor):
                     (?:(?:(?:www\.|m\.)?soundcloud\.com/
                             (?!stations/track)
                             (?P<uploader>[\w\d-]+)/
-                            (?!(?:tracks|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
+                            (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
@@ -50,12 +52,17 @@ class SoundcloudIE(InfoExtractor):
             'info_dict': {
                 'id': '62986583',
                 'ext': 'mp3',
-                'upload_date': '20121011',
+                'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
                 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d',
                 'uploader': 'E.T. ExTerrestrial Music',
-                'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
+                'timestamp': 1349920598,
+                'upload_date': '20121011',
                 'duration': 143,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             }
         },
         # not streamable song
@@ -67,9 +74,14 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Goldrushed',
                 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
                 'uploader': 'The Royal Concept',
+                'timestamp': 1337635207,
                 'upload_date': '20120521',
-                'duration': 227,
+                'duration': 30,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
             'params': {
                 # rtmp
@@ -84,11 +96,16 @@ class SoundcloudIE(InfoExtractor):
                 'id': '123998367',
                 'ext': 'mp3',
                 'title': 'Youtube - Dl Test Video \'\' Ä↭',
-                'uploader': 'jaimeMF',
                 'description': 'test chars:  \"\'/\\ä↭',
+                'uploader': 'jaimeMF',
+                'timestamp': 1386604920,
                 'upload_date': '20131209',
                 'duration': 9,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # private link (alt format)
@@ -99,11 +116,16 @@ class SoundcloudIE(InfoExtractor):
                 'id': '123998367',
                 'ext': 'mp3',
                 'title': 'Youtube - Dl Test Video \'\' Ä↭',
-                'uploader': 'jaimeMF',
                 'description': 'test chars:  \"\'/\\ä↭',
+                'uploader': 'jaimeMF',
+                'timestamp': 1386604920,
                 'upload_date': '20131209',
                 'duration': 9,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # downloadable song
@@ -116,9 +138,14 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Bus Brakes',
                 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66',
                 'uploader': 'oddsamples',
+                'timestamp': 1389232924,
                 'upload_date': '20140109',
                 'duration': 17,
                 'license': 'cc-by-sa',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # private link, downloadable format
@@ -131,9 +158,14 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
                 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
                 'uploader': 'Ori Uplift Music',
+                'timestamp': 1504206263,
                 'upload_date': '20170831',
                 'duration': 7449,
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
         },
         # no album art, use avatar pic for thumbnail
@@ -146,10 +178,15 @@ class SoundcloudIE(InfoExtractor):
                 'title': 'Sideways (Prod. Mad Real)',
                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
                 'uploader': 'garyvee',
+                'timestamp': 1488152409,
                 'upload_date': '20170226',
                 'duration': 207,
                 'thumbnail': r're:https?://.*\.jpg',
                 'license': 'all-rights-reserved',
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'repost_count': int,
             },
             'params': {
                 'skip_download': True,
@@ -157,7 +194,7 @@ class SoundcloudIE(InfoExtractor):
         },
     ]
 
-    _CLIENT_ID = 'LvWovRaJZlWCHql0bISuum8Bd2KX79mb'
+    _CLIENT_ID = 'NmW1FlPaiL94ueEu7oziOWjYEzZzQDcK'
 
     @staticmethod
     def _extract_urls(webpage):
@@ -175,22 +212,33 @@ class SoundcloudIE(InfoExtractor):
 
     def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None):
         track_id = compat_str(info['id'])
+        title = info['title']
         name = full_title or track_id
         if quiet:
             self.report_extraction(name)
         thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url')
         if isinstance(thumbnail, compat_str):
             thumbnail = thumbnail.replace('-large', '-t500x500')
+        username = try_get(info, lambda x: x['user']['username'], compat_str)
+
+        def extract_count(key):
+            return int_or_none(info.get('%s_count' % key))
+
         result = {
             'id': track_id,
-            'uploader': info.get('user', {}).get('username'),
+            'uploader': username,
-            'upload_date': unified_strdate(info.get('created_at')),
+            'timestamp': unified_timestamp(info.get('created_at')),
-            'title': info['title'],
+            'title': title,
             'description': info.get('description'),
             'thumbnail': thumbnail,
             'duration': int_or_none(info.get('duration'), 1000),
             'webpage_url': info.get('permalink_url'),
             'license': info.get('license'),
+            'view_count': extract_count('playback'),
+            'like_count': extract_count('favoritings'),
+            'comment_count': extract_count('comment'),
+            'repost_count': extract_count('reposts'),
+            'genre': info.get('genre'),
         }
         formats = []
         query = {'client_id': self._CLIENT_ID}
@@ -368,7 +416,6 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
 
 
 class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
-    _API_BASE = 'https://api.soundcloud.com'
     _API_V2_BASE = 'https://api-v2.soundcloud.com'
 
     def _extract_playlist(self, base_url, playlist_id, playlist_title):
@@ -389,21 +436,30 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
                 next_href, playlist_id, 'Downloading track page %s' % (i + 1))
 
             collection = response['collection']
-            if not collection:
-                break
 
-            def resolve_permalink_url(candidates):
+            if not isinstance(collection, list):
+                collection = []
+
+            # Empty collection may be returned, in this case we proceed
+            # straight to next_href
+
+            def resolve_entry(candidates):
                 for cand in candidates:
-                    if isinstance(cand, dict):
+                    if not isinstance(cand, dict):
-                        permalink_url = cand.get('permalink_url')
+                        continue
-                        entry_id = self._extract_id(cand)
+                    permalink_url = url_or_none(cand.get('permalink_url'))
-                        if permalink_url and permalink_url.startswith('http'):
+                    if not permalink_url:
-                            return permalink_url, entry_id
+                        continue
+                    return self.url_result(
+                        permalink_url,
+                        ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None,
+                        video_id=self._extract_id(cand),
+                        video_title=cand.get('title'))
 
             for e in collection:
-                permalink_url, entry_id = resolve_permalink_url((e, e.get('track'), e.get('playlist')))
+                entry = resolve_entry((e, e.get('track'), e.get('playlist')))
-                if permalink_url:
+                if entry:
-                    entries.append(self.url_result(permalink_url, video_id=entry_id))
+                    entries.append(entry)
 
             next_href = response.get('next_href')
             if not next_href:
@@ -429,46 +485,53 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
                             (?:(?:www|m)\.)?soundcloud\.com/
                             (?P<user>[^/]+)
                             (?:/
-                                (?P<rsrc>tracks|sets|reposts|likes|spotlight)
+                                (?P<rsrc>tracks|albums|sets|reposts|likes|spotlight)
                             )?
                             /?(?:[?#].*)?$
                     '''
     IE_NAME = 'soundcloud:user'
     _TESTS = [{
-        'url': 'https://soundcloud.com/the-akashic-chronicler',
+        'url': 'https://soundcloud.com/soft-cell-official',
         'info_dict': {
-            'id': '114582580',
+            'id': '207965082',
-            'title': 'The Akashic Chronicler (All)',
+            'title': 'Soft Cell (All)',
         },
-        'playlist_mincount': 74,
+        'playlist_mincount': 28,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/tracks',
+        'url': 'https://soundcloud.com/soft-cell-official/tracks',
         'info_dict': {
-            'id': '114582580',
+            'id': '207965082',
-            'title': 'The Akashic Chronicler (Tracks)',
+            'title': 'Soft Cell (Tracks)',
         },
-        'playlist_mincount': 37,
+        'playlist_mincount': 27,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/sets',
+        'url': 'https://soundcloud.com/soft-cell-official/albums',
         'info_dict': {
-            'id': '114582580',
+            'id': '207965082',
-            'title': 'The Akashic Chronicler (Playlists)',
+            'title': 'Soft Cell (Albums)',
+        },
+        'playlist_mincount': 1,
+    }, {
+        'url': 'https://soundcloud.com/jcv246/sets',
+        'info_dict': {
+            'id': '12982173',
+            'title': 'Jordi / cv (Playlists)',
         },
         'playlist_mincount': 2,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/reposts',
+        'url': 'https://soundcloud.com/jcv246/reposts',
         'info_dict': {
-            'id': '114582580',
+            'id': '12982173',
-            'title': 'The Akashic Chronicler (Reposts)',
+            'title': 'Jordi / cv (Reposts)',
         },
-        'playlist_mincount': 7,
+        'playlist_mincount': 6,
     }, {
-        'url': 'https://soundcloud.com/the-akashic-chronicler/likes',
+        'url': 'https://soundcloud.com/clalberg/likes',
         'info_dict': {
-            'id': '114582580',
+            'id': '11817582',
-            'title': 'The Akashic Chronicler (Likes)',
+            'title': 'clalberg (Likes)',
         },
-        'playlist_mincount': 321,
+        'playlist_mincount': 5,
     }, {
         'url': 'https://soundcloud.com/grynpyret/spotlight',
         'info_dict': {
@@ -479,10 +542,11 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
     }]
 
     _BASE_URL_MAP = {
-        'all': '%s/profile/soundcloud:users:%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_BASE,
+        'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
-        'reposts': '%s/profile/soundcloud:users:%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
+        'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
         'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
     }
@@ -490,6 +554,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
     _TITLE_MAP = {
         'all': 'All',
         'tracks': 'Tracks',
+        'albums': 'Albums',
         'sets': 'Playlists',
         'reposts': 'Reposts',
         'likes': 'Likes',

youtube_dl/extractor/spankbang.py

@@ -5,14 +5,17 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    orderedSet,
     parse_duration,
     parse_resolution,
     str_to_int,
+    url_or_none,
+    urlencode_postdata,
 )
 
 
 class SpankBangIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
+    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/(?:video|play|embed)\b'
     _TESTS = [{
         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',
@@ -41,29 +44,71 @@ class SpankBangIE(InfoExtractor):
         # 4k
         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
         'only_matching': True,
+    }, {
+        'url': 'https://m.spankbang.com/3vvn/play/fantasy+solo/480p/',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.spankbang.com/3vvn/play',
+        'only_matching': True,
+    }, {
+        'url': 'https://spankbang.com/2y3td/embed/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id, headers={
+        webpage = self._download_webpage(
-            'Cookie': 'country=US'
+            url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
-        })
+            video_id, headers={'Cookie': 'country=US'})
 
         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
             raise ExtractorError(
                 'Video %s is not available' % video_id, expected=True)
 
         formats = []
-        for mobj in re.finditer(
+
-                r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
+        def extract_format(format_id, format_url):
-                webpage):
+            f_url = url_or_none(format_url)
-            format_id, format_url = mobj.group('id', 'url')
+            if not f_url:
+                return
             f = parse_resolution(format_id)
             f.update({
-                'url': format_url,
+                'url': f_url,
                 'format_id': format_id,
             })
             formats.append(f)
+
+        STREAM_URL_PREFIX = 'stream_url_'
+
+        for mobj in re.finditer(
+                r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
+                % STREAM_URL_PREFIX, webpage):
+            extract_format(mobj.group('id', 'url'))
+
+        if not formats:
+            stream_key = self._search_regex(
+                r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'stream key', group='value')
+
+            sb_csrf_session = self._get_cookies(
+                'https://spankbang.com')['sb_csrf_session'].value
+
+            stream = self._download_json(
+                'https://spankbang.com/api/videos/stream', video_id,
+                'Downloading stream JSON', data=urlencode_postdata({
+                    'id': stream_key,
+                    'data': 0,
+                    'sb_csrf_session': sb_csrf_session,
+                }), headers={
+                    'Referer': url,
+                    'X-CSRFToken': sb_csrf_session,
+                })
+
+            for format_id, format_url in stream.items():
+                if format_id.startswith(STREAM_URL_PREFIX):
+                    extract_format(
+                        format_id[len(STREAM_URL_PREFIX):], format_url)
+
         self._sort_formats(formats)
 
         title = self._html_search_regex(
@@ -94,3 +139,33 @@ class SpankBangIE(InfoExtractor):
             'formats': formats,
             'age_limit': age_limit,
         }
+
+
+class SpankBangPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+'
+    _TEST = {
+        'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
+        'info_dict': {
+            'id': 'ug0k',
+            'title': 'Big Ass Titties',
+        },
+        'playlist_mincount': 50,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
+
+        entries = [self.url_result(
+            'https://spankbang.com/%s/video' % video_id,
+            ie=SpankBangIE.ie_key(), video_id=video_id)
+            for video_id in orderedSet(re.findall(
+                r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))]
+
+        title = self._html_search_regex(
+            r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title',
+            fatal=False)
+
+        return self.playlist_result(entries, playlist_id, title)

youtube_dl/extractor/teachable.py

@@ -27,6 +27,7 @@ class TeachableBaseIE(InfoExtractor):
         'market.saleshacker.com': 'saleshacker',
         'learnability.org': 'learnability',
         'edurila.com': 'edurila',
+        'courses.workitdaily.com': 'workitdaily',
     }
 
     _VALID_URL_SUB_TUPLE = (_URL_PREFIX, '|'.join(re.escape(site) for site in _SITES.keys()))

youtube_dl/extractor/toutv.py

@@ -3,22 +3,19 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .radiocanada import RadioCanadaIE
 from ..utils import (
-    int_or_none,
-    js_to_json,
-    urlencode_postdata,
     extract_attributes,
-    smuggle_url,
+    int_or_none,
+    merge_dicts,
+    urlencode_postdata,
 )
 
 
-class TouTvIE(InfoExtractor):
+class TouTvIE(RadioCanadaIE):
     _NETRC_MACHINE = 'toutv'
     IE_NAME = 'tou.tv'
     _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)'
-    _access_token = None
-    _claims = None
 
     _TESTS = [{
         'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
@@ -46,18 +43,14 @@ class TouTvIE(InfoExtractor):
         email, password = self._get_login_info()
         if email is None:
             return
-        state = 'http://ici.tou.tv/'
-        webpage = self._download_webpage(state, None, 'Downloading homepage')
-        toutvlogin = self._parse_json(self._search_regex(
-            r'(?s)toutvlogin\s*=\s*({.+?});', webpage, 'toutvlogin'), None, js_to_json)
-        authorize_url = toutvlogin['host'] + '/auth/oauth/v2/authorize'
         login_webpage = self._download_webpage(
-            authorize_url, None, 'Downloading login page', query={
+            'https://services.radio-canada.ca/auth/oauth/v2/authorize',
-                'client_id': toutvlogin['clientId'],
+            None, 'Downloading login page', query={
-                'redirect_uri': 'https://ici.tou.tv/login/loginCallback',
+                'client_id': '4dd36440-09d5-4468-8923-b6d91174ad36',
+                'redirect_uri': 'https://ici.tou.tv/logincallback',
                 'response_type': 'token',
-                'scope': 'media-drmt openid profile email id.write media-validation.read.privileged',
+                'scope': 'id.write media-validation.read',
-                'state': state,
+                'state': '/',
             })
 
         def extract_form_url_and_data(wp, default_form_url, form_spec_re=''):
@@ -86,12 +79,7 @@ class TouTvIE(InfoExtractor):
         self._access_token = self._search_regex(
             r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
             urlh.geturl(), 'access token')
-        self._claims = self._download_json(
+        self._claims = self._call_api('validation/v2/getClaims')['claims']
-            'https://services.radio-canada.ca/media/validation/v2/getClaims',
-            None, 'Extracting Claims', query={
-                'token': self._access_token,
-                'access_token': self._access_token,
-            })['claims']
 
     def _real_extract(self, url):
         path = self._match_id(url)
@@ -102,19 +90,10 @@ class TouTvIE(InfoExtractor):
             self.report_warning('This video is probably DRM protected.', path)
         video_id = metadata['IdMedia']
         details = metadata['Details']
-        title = details['OriginalTitle']
-        video_url = 'radiocanada:%s:%s' % (metadata.get('AppCode', 'toutv'), video_id)
-        if self._access_token and self._claims:
-            video_url = smuggle_url(video_url, {
-                'access_token': self._access_token,
-                'claims': self._claims,
-            })
 
-        return {
+        return merge_dicts({
-            '_type': 'url_transparent',
-            'url': video_url,
             'id': video_id,
-            'title': title,
+            'title': details.get('OriginalTitle'),
             'thumbnail': details.get('ImageUrl'),
             'duration': int_or_none(details.get('LengthInSeconds')),
-        }
+        }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))

youtube_dl/extractor/trunews.py

@@ -0,0 +1,75 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    dict_get,
+    float_or_none,
+    int_or_none,
+    unified_timestamp,
+    update_url_query,
+    url_or_none,
+)
+
+
+class TruNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
+        'md5': 'a19c024c3906ff954fac9b96ce66bb08',
+        'info_dict': {
+            'id': '5c5a21e65d3c196e1c0020cc',
+            'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
+            'ext': 'mp4',
+            'title': "Will Democrats Stage a Circus During President Trump's State of the Union Speech?",
+            'description': 'md5:c583b72147cc92cf21f56a31aff7a670',
+            'duration': 3685,
+            'timestamp': 1549411440,
+            'upload_date': '20190206',
+        },
+        'add_ie': ['Zype'],
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        video = self._download_json(
+            'https://api.zype.com/videos', display_id, query={
+                'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H',
+                'per_page': 1,
+                'active': 'true',
+                'friendly_title': display_id,
+            })['response'][0]
+
+        zype_id = video['_id']
+
+        thumbnails = []
+        thumbnails_list = video.get('thumbnails')
+        if isinstance(thumbnails_list, list):
+            for thumbnail in thumbnails_list:
+                if not isinstance(thumbnail, dict):
+                    continue
+                thumbnail_url = url_or_none(thumbnail.get('url'))
+                if not thumbnail_url:
+                    continue
+                thumbnails.append({
+                    'url': thumbnail_url,
+                    'width': int_or_none(thumbnail.get('width')),
+                    'height': int_or_none(thumbnail.get('height')),
+                })
+
+        return {
+            '_type': 'url_transparent',
+            'url': update_url_query(
+                'https://player.zype.com/embed/%s.js' % zype_id,
+                {'api_key': 'X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'}),
+            'ie_key': 'Zype',
+            'id': zype_id,
+            'display_id': display_id,
+            'title': video.get('title'),
+            'description': dict_get(video, ('description', 'ott_description', 'short_description')),
+            'duration': int_or_none(video.get('duration')),
+            'timestamp': unified_timestamp(video.get('published_at')),
+            'average_rating': float_or_none(video.get('rating')),
+            'view_count': int_or_none(video.get('request_count')),
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/trutv.py

@@ -4,44 +4,72 @@ from __future__ import unicode_literals
 import re
 
 from .turner import TurnerBaseIE
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class TruTVIE(TurnerBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?trutv\.com(?:(?P<path>/shows/[^/]+/videos/[^/?#]+?)\.html|/full-episodes/[^/]+/(?P<id>\d+))'
+    _VALID_URL = r'https?://(?:www\.)?trutv\.com/(?:shows|full-episodes)/(?P<series_slug>[0-9A-Za-z-]+)/(?:videos/(?P<clip_slug>[0-9A-Za-z-]+)|(?P<id>\d+))'
     _TEST = {
-        'url': 'http://www.trutv.com/shows/10-things/videos/you-wont-believe-these-sports-bets.html',
+        'url': 'https://www.trutv.com/shows/the-carbonaro-effect/videos/sunlight-activated-flower.html',
-        'md5': '2cdc844f317579fed1a7251b087ff417',
         'info_dict': {
-            'id': '/shows/10-things/videos/you-wont-believe-these-sports-bets',
+            'id': 'f16c03beec1e84cd7d1a51f11d8fcc29124cc7f1',
             'ext': 'mp4',
-            'title': 'You Won\'t Believe These Sports Bets',
+            'title': 'Sunlight-Activated Flower',
-            'description': 'Jamie Lee sits down with a bookie to discuss the bizarre world of illegal sports betting.',
+            'description': "A customer is stunned when he sees Michael's sunlight-activated flower.",
-            'upload_date': '20130305',
+        },
-        }
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
-        path, video_id = re.match(self._VALID_URL, url).groups()
+        series_slug, clip_slug, video_id = re.match(self._VALID_URL, url).groups()
-        auth_required = False
+
-        if path:
+        if video_id:
-            data_src = 'http://www.trutv.com/video/cvp/v2/xml/content.xml?id=%s.xml' % path
+            path = 'episode'
+            display_id = video_id
         else:
-            webpage = self._download_webpage(url, video_id)
+            path = 'series/clip'
-            video_id = self._search_regex(
+            display_id = clip_slug
-                r"TTV\.TVE\.episodeId\s*=\s*'([^']+)';",
+
-                webpage, 'video id', default=video_id)
+        data = self._download_json(
-            auth_required = self._search_regex(
+            'https://api.trutv.com/v2/web/%s/%s/%s' % (path, series_slug, display_id),
-                r'TTV\.TVE\.authRequired\s*=\s*(true|false);',
+            display_id)
-                webpage, 'auth required', default='false') == 'true'
+        video_data = data['episode'] if video_id else data['info']
-            data_src = 'http://www.trutv.com/tveverywhere/services/cvpXML.do?titleId=' + video_id
+        media_id = video_data['mediaId']
-        return self._extract_cvp_info(
+        title = video_data['title'].strip()
-            data_src, path, {
+
-                'secure': {
+        info = self._extract_ngtv_info(
-                    'media_src': 'http://androidhls-secure.cdn.turner.com/trutv/big',
+            media_id, {}, {
-                    'tokenizer_src': 'http://www.trutv.com/tveverywhere/processors/services/token_ipadAdobe.do',
-                },
-            }, {
                 'url': url,
                 'site_name': 'truTV',
-                'auth_required': auth_required,
+                'auth_required': video_data.get('isAuthRequired'),
             })
+
+        thumbnails = []
+        for image in video_data.get('images', []):
+            image_url = image.get('srcUrl')
+            if not image_url:
+                continue
+            thumbnails.append({
+                'url': image_url,
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
+            })
+
+        info.update({
+            'id': media_id,
+            'display_id': display_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnails': thumbnails,
+            'timestamp': parse_iso8601(video_data.get('publicationDate')),
+            'series': video_data.get('showTitle'),
+            'season_number': int_or_none(video_data.get('seasonNum')),
+            'episode_number': int_or_none(video_data.get('episodeNum')),
+        })
+        return info

youtube_dl/extractor/tvp.py

@@ -1,14 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     clean_html,
-    get_element_by_attribute,
+    determine_ext,
     ExtractorError,
+    get_element_by_attribute,
+    orderedSet,
 )
 
 
@@ -19,12 +21,12 @@ class TVPIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536',
-        'md5': '8aa518c15e5cc32dfe8db400dc921fbb',
+        'md5': 'a21eb0aa862f25414430f15fdfb9e76c',
         'info_dict': {
             'id': '194536',
             'ext': 'mp4',
-            'title': 'Czas honoru, I seria – odc. 13',
+            'title': 'Czas honoru, odc. 13 – Władek',
-            'description': 'md5:381afa5bca72655fe94b05cfe82bf53d',
+            'description': 'md5:437f48b93558370b031740546b696e24',
         },
     }, {
         'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
@@ -45,6 +47,7 @@ class TVPIE(InfoExtractor):
             'title': 'Wiadomości, 28.09.2017, 19:30',
             'description': 'Wydanie główne codziennego serwisu informacyjnego.'
         },
+        'skip': 'HTTP Error 404: Not Found',
     }, {
         'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
         'only_matching': True,
@@ -75,8 +78,10 @@ class TVPIE(InfoExtractor):
         return {
             '_type': 'url_transparent',
             'url': 'tvp:' + video_id,
-            'description': self._og_search_description(webpage, default=None),
+            'description': self._og_search_description(
-            'thumbnail': self._og_search_thumbnail(webpage),
+                webpage, default=None) or self._html_search_meta(
+                'description', webpage, default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'ie_key': 'TVPEmbed',
         }
 
@@ -87,6 +92,15 @@ class TVPEmbedIE(InfoExtractor):
     _VALID_URL = r'(?:tvp:|https?://[^/]+\.tvp\.(?:pl|info)/sess/tvplayer\.php\?.*?object_id=)(?P<id>\d+)'
 
     _TESTS = [{
+        'url': 'tvp:194536',
+        'md5': 'a21eb0aa862f25414430f15fdfb9e76c',
+        'info_dict': {
+            'id': '194536',
+            'ext': 'mp4',
+            'title': 'Czas honoru, odc. 13 – Władek',
+        },
+    }, {
+        # not available
         'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268',
         'md5': '8c9cd59d16edabf39331f93bf8a766c7',
         'info_dict': {
@@ -94,6 +108,7 @@ class TVPEmbedIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Panorama, 07.12.2015, 15:40',
         },
+        'skip': 'Transmisja została zakończona lub materiał niedostępny',
     }, {
         'url': 'tvp:22670268',
         'only_matching': True,
@@ -105,10 +120,13 @@ class TVPEmbedIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://www.tvp.pl/sess/tvplayer.php?object_id=%s' % video_id, video_id)
 
-        error_massage = get_element_by_attribute('class', 'msg error', webpage)
+        error = self._html_search_regex(
-        if error_massage:
+            r'(?s)<p[^>]+\bclass=["\']notAvailable__text["\'][^>]*>(.+?)</p>',
+            webpage, 'error', default=None) or clean_html(
+            get_element_by_attribute('class', 'msg error', webpage))
+        if error:
             raise ExtractorError('%s said: %s' % (
-                self.IE_NAME, clean_html(error_massage)), expected=True)
+                self.IE_NAME, clean_html(error)), expected=True)
 
         title = self._search_regex(
             r'name\s*:\s*([\'"])Title\1\s*,\s*value\s*:\s*\1(?P<title>.+?)\1',
@@ -180,48 +198,55 @@ class TVPEmbedIE(InfoExtractor):
         }
 
 
-class TVPSeriesIE(InfoExtractor):
+class TVPWebsiteIE(InfoExtractor):
     IE_NAME = 'tvp:series'
-    _VALID_URL = r'https?://vod\.tvp\.pl/(?:[^/]+/){2}(?P<id>[^/]+)/?$'
+    _VALID_URL = r'https?://vod\.tvp\.pl/website/(?P<display_id>[^,]+),(?P<id>\d+)'
 
     _TESTS = [{
-        'url': 'http://vod.tvp.pl/filmy-fabularne/filmy-za-darmo/ogniem-i-mieczem',
+        # series
+        'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312/video',
         'info_dict': {
-            'title': 'Ogniem i mieczem',
+            'id': '38678312',
-            'id': '4278026',
         },
-        'playlist_count': 4,
+        'playlist_count': 115,
     }, {
-        'url': 'http://vod.tvp.pl/audycje/podroze/boso-przez-swiat',
+        # film
+        'url': 'https://vod.tvp.pl/website/gloria,35139666',
         'info_dict': {
-            'title': 'Boso przez świat',
+            'id': '36637049',
-            'id': '9329207',
+            'ext': 'mp4',
+            'title': 'Gloria, Gloria',
         },
-        'playlist_count': 86,
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['TVPEmbed'],
+    }, {
+        'url': 'https://vod.tvp.pl/website/lzy-cennet,38678312',
+        'only_matching': True,
     }]
 
+    def _entries(self, display_id, playlist_id):
+        url = 'https://vod.tvp.pl/website/%s,%s/video' % (display_id, playlist_id)
+        for page_num in itertools.count(1):
+            page = self._download_webpage(
+                url, display_id, 'Downloading page %d' % page_num,
+                query={'page': page_num})
+
+            video_ids = orderedSet(re.findall(
+                r'<a[^>]+\bhref=["\']/video/%s,[^,]+,(\d+)' % display_id,
+                page))
+
+            if not video_ids:
+                break
+
+            for video_id in video_ids:
+                yield self.url_result(
+                    'tvp:%s' % video_id, ie=TVPEmbedIE.ie_key(),
+                    video_id=video_id)
+
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
-        webpage = self._download_webpage(url, display_id, tries=5)
+        display_id, playlist_id = mobj.group('display_id', 'id')
-
+        return self.playlist_result(
-        title = self._html_search_regex(
+            self._entries(display_id, playlist_id), playlist_id)
-            r'(?s) id=[\'"]path[\'"]>(?:.*? / ){2}(.*?)</span>', webpage, 'series')
-        playlist_id = self._search_regex(r'nodeId:\s*(\d+)', webpage, 'playlist id')
-        playlist = self._download_webpage(
-            'http://vod.tvp.pl/vod/seriesAjax?type=series&nodeId=%s&recommend'
-            'edId=0&sort=&page=0&pageSize=10000' % playlist_id, display_id, tries=5,
-            note='Downloading playlist')
-
-        videos_paths = re.findall(
-            '(?s)class="shortTitle">.*?href="(/[^"]+)', playlist)
-        entries = [
-            self.url_result('http://vod.tvp.pl%s' % v_path, ie=TVPIE.ie_key())
-            for v_path in videos_paths]
-
-        return {
-            '_type': 'playlist',
-            'id': playlist_id,
-            'display_id': display_id,
-            'title': title,
-            'entries': entries,
-        }

youtube_dl/extractor/tvplay.py

@@ -493,10 +493,9 @@ class TVPlayHomeIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._search_regex(
-            r'data-asset-id\s*=\s*["\'](\d{5,7})\b', webpage, 'video id',
+            r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
-            default=None)
 
-        if video_id:
+        if len(video_id) < 8:
             return self.url_result(
                 'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
 
@@ -537,8 +536,9 @@ class TVPlayHomeIE(InfoExtractor):
             r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
             default=None))
         episode = self._search_regex(
-            r'(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'episode',
+            (r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
-            default=None, group='value')
+             r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
+            'episode', default=None, group='value')
         episode_number = int_or_none(self._search_regex(
             r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
             default=None))

youtube_dl/extractor/twitch.py

@@ -136,7 +136,12 @@ class TwitchBaseIE(InfoExtractor):
             source = next(f for f in formats if f['format_id'] == 'Source')
             source['preference'] = 10
         except StopIteration:
-            pass  # No Source stream present
+            for f in formats:
+                if '/chunked/' in f['url']:
+                    f.update({
+                        'source_preference': 10,
+                        'format_note': 'Source',
+                    })
         self._sort_formats(formats)
 
 

youtube_dl/extractor/udemy.py

@@ -29,7 +29,7 @@ class UdemyIE(InfoExtractor):
     IE_NAME = 'udemy'
     _VALID_URL = r'''(?x)
                     https?://
-                        www\.udemy\.com/
+                        (?:[^/]+\.)?udemy\.com/
                         (?:
                             [^#]+\#/lecture/|
                             lecture/view/?\?lectureId=|
@@ -64,6 +64,9 @@ class UdemyIE(InfoExtractor):
         # only outputs rendition
         'url': 'https://www.udemy.com/how-you-can-help-your-local-community-5-amazing-examples/learn/v4/t/lecture/3225750?start=0',
         'only_matching': True,
+    }, {
+        'url': 'https://wipro.udemy.com/java-tutorial/#/lecture/172757',
+        'only_matching': True,
     }]
 
     def _extract_course_info(self, webpage, video_id):
@@ -123,10 +126,22 @@ class UdemyIE(InfoExtractor):
 
     def _download_webpage_handle(self, *args, **kwargs):
         headers = kwargs.get('headers', {}).copy()
-        headers['User-Agent'] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4'
+        headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
         kwargs['headers'] = headers
-        return super(UdemyIE, self)._download_webpage_handle(
+        ret = super(UdemyIE, self)._download_webpage_handle(
             *args, **compat_kwargs(kwargs))
+        if not ret:
+            return ret
+        webpage, _ = ret
+        if any(p in webpage for p in (
+                '>Please verify you are a human',
+                'Access to this page has been denied because we believe you are using automation tools to browse the website',
+                '"_pxCaptcha"')):
+            raise ExtractorError(
+                'Udemy asks you to solve a CAPTCHA. Login with browser, '
+                'solve CAPTCHA, then export cookies and pass cookie file to '
+                'youtube-dl with --cookies.', expected=True)
+        return ret
 
     def _download_json(self, url_or_request, *args, **kwargs):
         headers = {
@@ -403,8 +418,14 @@ class UdemyIE(InfoExtractor):
 
 class UdemyCourseIE(UdemyIE):
     IE_NAME = 'udemy:course'
-    _VALID_URL = r'https?://(?:www\.)?udemy\.com/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?udemy\.com/(?P<id>[^/?#&]+)'
-    _TESTS = []
+    _TESTS = [{
+        'url': 'https://www.udemy.com/java-tutorial/',
+        'only_matching': True,
+    }, {
+        'url': 'https://wipro.udemy.com/java-tutorial/',
+        'only_matching': True,
+    }]
 
     @classmethod
     def suitable(cls, url):

youtube_dl/extractor/vimeo.py

@@ -502,7 +502,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         orig_url = url
-        if mobj.group('pro') or mobj.group('player'):
+        if mobj.group('pro'):
+            # some videos require portfolio_id to be present in player url
+            # https://github.com/rg3/youtube-dl/issues/20070
+            url = self._extract_url(url, self._download_webpage(url, video_id))
+        elif mobj.group('player'):
             url = 'https://player.vimeo.com/video/' + video_id
         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
             url = 'https://vimeo.com/' + video_id

youtube_dl/extractor/vporn.py

@@ -1,123 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    parse_duration,
-    str_to_int,
-    urljoin,
-)
-
-
-class VpornIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
-    _TESTS = [
-        {
-            'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
-            'md5': 'facf37c1b86546fa0208058546842c55',
-            'info_dict': {
-                'id': '497944',
-                'display_id': 'violet-on-her-th-birthday',
-                'ext': 'mp4',
-                'title': 'Violet on her 19th birthday',
-                'description': 'Violet dances in front of the camera which is sure to get you horny.',
-                'thumbnail': r're:^https?://.*\.jpg$',
-                'uploader': 'kileyGrope',
-                'categories': ['Masturbation', 'Teen'],
-                'duration': 393,
-                'age_limit': 18,
-                'view_count': int,
-            },
-            'skip': 'video removed',
-        },
-        {
-            'url': 'http://www.vporn.com/female/hana-shower/523564/',
-            'md5': 'ced35a4656198a1664cf2cda1575a25f',
-            'info_dict': {
-                'id': '523564',
-                'display_id': 'hana-shower',
-                'ext': 'mp4',
-                'title': 'Hana Shower',
-                'description': 'Hana showers at the bathroom.',
-                'thumbnail': r're:^https?://.*\.jpg$',
-                'uploader': 'Hmmmmm',
-                'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'],
-                'duration': 588,
-                'age_limit': 18,
-                'view_count': int,
-            }
-        },
-    ]
-
-    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)
-
-        errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!'
-        if errmsg in webpage:
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
-
-        title = self._html_search_regex(
-            r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
-        description = self._html_search_regex(
-            r'class="(?:descr|description_txt)">(.*?)</div>',
-            webpage, 'description', fatal=False)
-        thumbnail = urljoin('http://www.vporn.com', self._html_search_regex(
-            r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description',
-            default=None))
-
-        uploader = self._html_search_regex(
-            r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>',
-            webpage, 'uploader', fatal=False)
-
-        categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage)
-
-        duration = parse_duration(self._search_regex(
-            r'Runtime:\s*</span>\s*(\d+ min \d+ sec)',
-            webpage, 'duration', fatal=False))
-
-        view_count = str_to_int(self._search_regex(
-            r'class="views">([\d,\.]+) [Vv]iews<',
-            webpage, 'view count', fatal=False))
-        comment_count = str_to_int(self._html_search_regex(
-            r"'Comments \(([\d,\.]+)\)'",
-            webpage, 'comment count', default=None))
-
-        formats = []
-
-        for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage):
-            video_url = video[1]
-            fmt = {
-                'url': video_url,
-                'format_id': video[0],
-            }
-            m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)_(?P<vbr>\d+)k\.mp4$', video_url)
-            if m:
-                fmt.update({
-                    'width': int(m.group('width')),
-                    'height': int(m.group('height')),
-                    'vbr': int(m.group('vbr')),
-                })
-            formats.append(fmt)
-
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'categories': categories,
-            'duration': duration,
-            'view_count': view_count,
-            'comment_count': comment_count,
-            'age_limit': 18,
-            'formats': formats,
-        }

youtube_dl/extractor/vshare.py

@@ -48,7 +48,7 @@ class VShareIE(InfoExtractor):
 
         webpage = self._download_webpage(
             'https://vshare.io/v/%s/width-650/height-430/1' % video_id,
-            video_id)
+            video_id, headers={'Referer': url})
 
         title = self._html_search_regex(
             r'<title>([^<]+)</title>', webpage, 'title')

youtube_dl/extractor/youtube.py

@@ -352,6 +352,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?yourepeat\.com/|
                             tube\.majestyc\.net/|
                             (?:www\.)?invidio\.us/|
+                            (?:www\.)?invidious\.snopyta\.org/|
+                            (?:www\.)?invidious\.kabi\.tk/|
+                            (?:www\.)?vid\.wxzm\.sx/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:

youtube_dl/utils.py

@@ -184,7 +184,7 @@ DATE_FORMATS_MONTH_FIRST.extend([
 ])
 
 PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)"
-JSON_LD_RE = r'(?is)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>'
+JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>'
 
 
 def preferredencoding():
@@ -1141,6 +1141,8 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
 
 
 class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
+    _HTTPONLY_PREFIX = '#HttpOnly_'
+
     def save(self, filename=None, ignore_discard=False, ignore_expires=False):
         # Store session cookies with `expires` set to 0 instead of an empty
         # string
@@ -1150,7 +1152,21 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
         compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires)
 
     def load(self, filename=None, ignore_discard=False, ignore_expires=False):
-        compat_cookiejar.MozillaCookieJar.load(self, filename, ignore_discard, ignore_expires)
+        """Load cookies from a file."""
+        if filename is None:
+            if self.filename is not None:
+                filename = self.filename
+            else:
+                raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
+
+        cf = io.StringIO()
+        with open(filename) as f:
+            for line in f:
+                if line.startswith(self._HTTPONLY_PREFIX):
+                    line = line[len(self._HTTPONLY_PREFIX):]
+                cf.write(compat_str(line))
+        cf.seek(0)
+        self._really_load(cf, filename, ignore_discard, ignore_expires)
         # Session cookies are denoted by either `expires` field set to
         # an empty string or 0. MozillaCookieJar only recognizes the former
         # (see [1]). So we need force the latter to be recognized as session

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2019.01.30.1'
+__version__ = '2019.03.01'