release 2018.06.19

[ci skip]

.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 *2018.06.02*. 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 Issues with outdated version will be rejected.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 **2018.06.02**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.06.19*. 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 Issues with outdated version will be rejected.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 **2018.06.19**
 
 ### 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 2018.06.02
+[debug] youtube-dl version 2018.06.19
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

ChangeLog

@@ -1,3 +1,80 @@
+version 2018.06.19
+
+Core
++ [extractor/common] Introduce expected_status in _download_* methods
+  for convenient accept of HTTP requests failed with non 2xx status codes
++ [compat] Introduce compat_integer_types
+
+Extractors
+* [peertube] Improve generic support (#16733)
++ [6play] Use geo verification headers
+* [rtbf] Fix extraction for python 3.2
+* [vgtv] Improve HLS formats extraction
++ [vgtv] Add support for www.aftonbladet.se/tv URLs
+* [bbccouk] Use expected_status
+* [markiza] Expect 500 HTTP status code
+* [tvnow] Try all clear manifest URLs (#15361)
+
+
+version 2018.06.18
+
+Core
+* [downloader/rtmp] Fix downloading in verbose mode (#16736)
+
+Extractors
++ [markiza] Add support for markiza.sk (#16750)
+* [wat] Try all supported adaptive URLs
++ [6play] Add support for rtlplay.be and extract hd usp formats
++ [rtbf] Add support for audio and live streams (#9638, #11923)
++ [rtbf] Extract HLS, DASH and all HTTP formats
++ [rtbf] Extract subtitles
++ [rtbf] Fixup specific HTTP URLs (#16101)
++ [expressen] Add support for expressen.se
+* [vidzi] Fix extraction (#16678)
+* [pbs] Improve extraction (#16623, #16684)
+* [bilibili] Restrict cid regular expression (#16638, #16734)
+
+
+version 2018.06.14
+
+Core
+* [downloader/http] Fix retry on error when streaming to stdout (#16699)
+
+Extractors
++ [discoverynetworks] Add support for disco-api videos (#16724)
++ [dailymotion] Add support for password protected videos (#9789)
++ [abc:iview] Add support for livestreams (#12354)
+* [abc:iview] Fix extraction (#16704)
++ [crackle] Add support for sonycrackle.com (#16698)
++ [tvnet] Add support for tvnet.gov.vn (#15462)
+* [nrk] Update API hosts and try all previously known ones (#16690)
+* [wimp] Fix Youtube embeds extraction
+
+
+version 2018.06.11
+
+Extractors
+* [npo] Extend URL regular expression and add support for npostart.nl (#16682)
++ [inc] Add support for another embed schema (#16666)
+* [tv4] Fix format extraction (#16650)
++ [nexx] Add support for free cdn (#16538)
++ [pbs] Add another cove id pattern (#15373)
++ [rbmaradio] Add support for 192k format (#16631)
+
+
+version 2018.06.04
+
+Extractors
++ [camtube] Add support for camtube.co
++ [twitter:card] Extract guest token (#16609)
++ [chaturbate] Use geo verification headers
++ [bbc] Add support for bbcthree (#16612)
+* [youtube] Move metadata extraction after video availability check
++ [youtube] Extract track and artist
++ [safari] Add support for new URL schema (#16614)
+* [adn] Fix extraction
+
+
 version 2018.06.02
 
 Core

devscripts/gh-pages/update-copyright.py

@@ -13,7 +13,7 @@ year = str(datetime.datetime.now().year)
 for fn in glob.glob('*.html*'):
     with io.open(fn, encoding='utf-8') as f:
         content = f.read()
-    newc = re.sub(r'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', 'Copyright © 2006-' + year, content)
+    newc = re.sub(r'(?P<copyright>Copyright © 2011-)(?P<year>[0-9]{4})', 'Copyright © 2011-' + year, content)
     if content != newc:
         tmpFn = fn + '.part'
         with io.open(tmpFn, 'wt', encoding='utf-8') as outf:

docs/supportedsites.md

@@ -129,6 +129,7 @@
  - **Camdemy**
  - **CamdemyFolder**
  - **CamModels**
+ - **CamTube**
  - **CamWithHer**
  - **canalc2.tv**
  - **Canalplus**: mycanal.fr and piwiplus.fr
@@ -265,6 +266,7 @@
  - **Europa**
  - **EveryonesMixtape**
  - **ExpoTV**
+ - **Expressen**
  - **ExtremeTube**
  - **EyedoTV**
  - **facebook**
@@ -454,6 +456,8 @@
  - **mangomolo:live**
  - **mangomolo:video**
  - **ManyVids**
+ - **Markiza**
+ - **MarkizaPage**
  - **massengeschmack.tv**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
@@ -892,6 +896,7 @@
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvland.com**
  - **TVN24**
+ - **TVNet**
  - **TVNoe**
  - **TVNow**
  - **TVNowList**

youtube_dl/compat.py

@@ -2787,6 +2787,12 @@ except NameError:  # Python 3
     compat_numeric_types = (int, float, complex)
 
 
+try:
+    compat_integer_types = (int, long)
+except NameError:  # Python 3
+    compat_integer_types = (int, )
+
+
 if sys.version_info < (2, 7):
     def compat_socket_create_connection(address, timeout, source_address=None):
         host, port = address
@@ -2974,6 +2980,7 @@ __all__ = [
     'compat_http_client',
     'compat_http_server',
     'compat_input',
+    'compat_integer_types',
     'compat_itertools_count',
     'compat_kwargs',
     'compat_numeric_types',

youtube_dl/downloader/http.py

@@ -217,10 +217,11 @@ class HttpFD(FileDownloader):
             before = start  # start measuring
 
             def retry(e):
-                if ctx.tmpfilename != '-':
+                to_stdout = ctx.tmpfilename == '-'
+                if not to_stdout:
                     ctx.stream.close()
                 ctx.stream = None
-                ctx.resume_len = os.path.getsize(encodeFilename(ctx.tmpfilename))
+                ctx.resume_len = byte_counter if to_stdout else os.path.getsize(encodeFilename(ctx.tmpfilename))
                 raise RetryDownload(e)
 
             while True:

youtube_dl/downloader/rtmp.py

@@ -24,13 +24,12 @@ class RtmpFD(FileDownloader):
     def real_download(self, filename, info_dict):
         def run_rtmpdump(args):
             start = time.time()
+            resume_percent = None
+            resume_downloaded_data_len = None
             proc = subprocess.Popen(args, stderr=subprocess.PIPE)
             cursor_in_new_line = True
-
-            def dl():
-                resume_percent = None
-                resume_downloaded_data_len = None
-                proc_stderr_closed = False
+            proc_stderr_closed = False
+            try:
                 while not proc_stderr_closed:
                     # read line from stderr
                     line = ''
@@ -90,12 +89,8 @@ class RtmpFD(FileDownloader):
                                 self.to_screen('')
                             cursor_in_new_line = True
                             self.to_screen('[rtmpdump] ' + line)
-
-            try:
-                dl()
             finally:
                 proc.wait()
-
             if not cursor_in_new_line:
                 self.to_screen('')
             return proc.returncode

youtube_dl/extractor/abc.py

@@ -105,22 +105,22 @@ class ABCIE(InfoExtractor):
 
 class ABCIViewIE(InfoExtractor):
     IE_NAME = 'abc.net.au:iview'
-    _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
     _GEO_COUNTRIES = ['AU']
 
     # ABC iview programs are normally available for 14 days only.
     _TESTS = [{
-        'url': 'https://iview.abc.net.au/programs/ben-and-hollys-little-kingdom/ZY9247A021S00',
+        'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00',
         'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
         'info_dict': {
-            'id': 'ZY9247A021S00',
+            'id': 'ZX9371A050S00',
             'ext': 'mp4',
-            'title': "Gaston's Visit",
+            'title': "Gaston's Birthday",
             'series': "Ben And Holly's Little Kingdom",
-            'description': 'md5:18db170ad71cf161e006a4c688e33155',
-            'upload_date': '20180318',
+            'description': 'md5:f9de914d02f226968f598ac76f105bcf',
+            'upload_date': '20180604',
             'uploader_id': 'abc4kids',
-            'timestamp': 1521400959,
+            'timestamp': 1528140219,
         },
         'params': {
             'skip_download': True,
@@ -129,17 +129,16 @@ class ABCIViewIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        video_params = self._parse_json(self._search_regex(
-            r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
-        title = video_params.get('title') or video_params['seriesTitle']
-        stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
+        video_params = self._download_json(
+            'https://iview.abc.net.au/api/programs/' + video_id, video_id)
+        title = unescapeHTML(video_params.get('title') or video_params['seriesTitle'])
+        stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
 
-        house_number = video_params.get('episodeHouseNumber')
-        path = '/auth/hls/sign?ts={0}&hn={1}&d=android-mobile'.format(
+        house_number = video_params.get('episodeHouseNumber') or video_id
+        path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
             int(time.time()), house_number)
         sig = hmac.new(
-            'android.content.res.Resources'.encode('utf-8'),
+            b'android.content.res.Resources',
             path.encode('utf-8'), hashlib.sha256).hexdigest()
         token = self._download_webpage(
             'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
@@ -169,18 +168,26 @@ class ABCIViewIE(InfoExtractor):
                 'ext': 'vtt',
             }]
 
+        is_live = video_params.get('livestream') == '1'
+        if is_live:
+            title = self._live_title(title)
+
         return {
             'id': video_id,
-            'title': unescapeHTML(title),
-            'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
-            'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
+            'title': title,
+            'description': video_params.get('description'),
+            'thumbnail': video_params.get('thumbnail'),
             'duration': int_or_none(video_params.get('eventDuration')),
             'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
             'series': unescapeHTML(video_params.get('seriesTitle')),
             'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
-            'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage, default=None)),
-            'episode': self._html_search_meta('episode_title', webpage, default=None),
+            'season_number': int_or_none(self._search_regex(
+                r'\bSeries\s+(\d+)\b', title, 'season number', default=None)),
+            'episode_number': int_or_none(self._search_regex(
+                r'\bEp\s+(\d+)\b', title, 'episode number', default=None)),
+            'episode_id': house_number,
             'uploader_id': video_params.get('channel'),
             'formats': formats,
             'subtitles': subtitles,
+            'is_live': is_live,
         }

youtube_dl/extractor/adn.py

@@ -1,8 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
+import binascii
 import json
 import os
+import random
 
 from .common import InfoExtractor
 from ..aes import aes_cbc_decrypt
@@ -12,9 +15,12 @@ from ..compat import (
 )
 from ..utils import (
     bytes_to_intlist,
+    bytes_to_long,
     ExtractorError,
     float_or_none,
     intlist_to_bytes,
+    long_to_bytes,
+    pkcs1pad,
     srt_subtitles_timecode,
     strip_or_none,
     urljoin,
@@ -35,6 +41,7 @@ class ADNIE(InfoExtractor):
         }
     }
     _BASE_URL = 'http://animedigitalnetwork.fr'
+    _RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)
 
     def _get_subtitles(self, sub_path, video_id):
         if not sub_path:
@@ -42,16 +49,14 @@ class ADNIE(InfoExtractor):
 
         enc_subtitles = self._download_webpage(
             urljoin(self._BASE_URL, sub_path),
-            video_id, fatal=False, headers={
-                'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0',
-            })
+            video_id, fatal=False)
         if not enc_subtitles:
             return None
 
         # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
-            bytes_to_intlist(b'\xc8\x6e\x06\xbc\xbe\xc6\x49\xf5\x88\x0d\xc8\x47\xc4\x27\x0c\x60'),
+            bytes_to_intlist(binascii.unhexlify(self._K + '9032ad7083106400')),
             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
         ))
         subtitles_json = self._parse_json(
@@ -112,11 +117,24 @@ class ADNIE(InfoExtractor):
         error = None
         if not links:
             links_url = player_config.get('linksurl') or options['videoUrl']
-            links_data = self._download_json(urljoin(
-                self._BASE_URL, links_url), video_id)
+            token = options['token']
+            self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
+            message = bytes_to_intlist(json.dumps({
+                'k': self._K,
+                'e': 60,
+                't': token,
+            }))
+            padded_message = intlist_to_bytes(pkcs1pad(message, 128))
+            n, e = self._RSA_KEY
+            encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
+            authorization = base64.b64encode(encrypted_message).decode()
+            links_data = self._download_json(
+                urljoin(self._BASE_URL, links_url), video_id, headers={
+                    'Authorization': 'Bearer ' + authorization,
+                })
             links = links_data.get('links') or {}
             metas = metas or links_data.get('meta') or {}
-            sub_path = sub_path or links_data.get('subtitles')
+            sub_path = (sub_path or links_data.get('subtitles')) + '&token=' + token
             error = links_data.get('error')
         title = metas.get('title') or video_info['title']
 

youtube_dl/extractor/bbc.py

@@ -12,6 +12,7 @@ from ..utils import (
     float_or_none,
     get_element_by_class,
     int_or_none,
+    js_to_json,
     parse_duration,
     parse_iso8601,
     try_get,
@@ -20,7 +21,6 @@ from ..utils import (
     urljoin,
 )
 from ..compat import (
-    compat_etree_fromstring,
     compat_HTTPError,
     compat_urlparse,
 )
@@ -333,14 +333,9 @@ class BBCCoUkIE(InfoExtractor):
         self._raise_extractor_error(last_exception)
 
     def _download_media_selector_url(self, url, programme_id=None):
-        try:
-            media_selection = self._download_xml(
-                url, programme_id, 'Downloading media selection XML')
-        except ExtractorError as ee:
-            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
-                media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
-            else:
-                raise
+        media_selection = self._download_xml(
+            url, programme_id, 'Downloading media selection XML',
+            expected_status=(403, 404))
         return self._process_media_selector(media_selection, programme_id)
 
     def _process_media_selector(self, media_selection, programme_id):
@@ -772,6 +767,17 @@ class BBCIE(BBCCoUkIE):
         # single video article embedded with data-media-vpid
         'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
         'only_matching': True,
+    }, {
+        'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
+        'info_dict': {
+            'id': 'p06556y7',
+            'ext': 'mp4',
+            'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
+            'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
+        },
+        'params': {
+            'skip_download': True,
+        }
     }]
 
     @classmethod
@@ -994,6 +1000,36 @@ class BBCIE(BBCCoUkIE):
                     'subtitles': subtitles,
                 }
 
+        bbc3_config = self._parse_json(
+            self._search_regex(
+                r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,
+                'bbcthree config', default='{}'),
+            playlist_id, transform_source=js_to_json, fatal=False)
+        if bbc3_config:
+            bbc3_playlist = try_get(
+                bbc3_config, lambda x: x['payload']['content']['bbcMedia']['playlist'],
+                dict)
+            if bbc3_playlist:
+                playlist_title = bbc3_playlist.get('title') or playlist_title
+                thumbnail = bbc3_playlist.get('holdingImageURL')
+                entries = []
+                for bbc3_item in bbc3_playlist['items']:
+                    programme_id = bbc3_item.get('versionID')
+                    if not programme_id:
+                        continue
+                    formats, subtitles = self._download_media_selector(programme_id)
+                    self._sort_formats(formats)
+                    entries.append({
+                        'id': programme_id,
+                        'title': playlist_title,
+                        'thumbnail': thumbnail,
+                        'timestamp': timestamp,
+                        'formats': formats,
+                        'subtitles': subtitles,
+                    })
+                return self.playlist_result(
+                    entries, playlist_id, playlist_title, playlist_description)
+
         def extract_all(pattern):
             return list(filter(None, map(
                 lambda s: self._parse_json(s, playlist_id, fatal=False),

youtube_dl/extractor/bilibili.py

@@ -114,7 +114,7 @@ class BiliBiliIE(InfoExtractor):
 
         if 'anime/' not in url:
             cid = self._search_regex(
-                r'cid(?:["\']:|=)(\d+)', webpage, 'cid',
+                r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid',
                 default=None
             ) or compat_parse_qs(self._search_regex(
                 [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',

youtube_dl/extractor/camtube.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_timestamp,
+)
+
+
+class CamTubeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|api)\.)?camtube\.co/recordings?/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://camtube.co/recording/minafay-030618-1136-chaturbate-female',
+        'info_dict': {
+            'id': '42ad3956-dd5b-445a-8313-803ea6079fac',
+            'display_id': 'minafay-030618-1136-chaturbate-female',
+            'ext': 'mp4',
+            'title': 'minafay-030618-1136-chaturbate-female',
+            'duration': 1274,
+            'timestamp': 1528018608,
+            'upload_date': '20180603',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    _API_BASE = 'https://api.camtube.co'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        token = self._download_json(
+            '%s/rpc/session/new' % self._API_BASE, display_id,
+            'Downloading session token')['token']
+
+        self._set_cookie('api.camtube.co', 'session', token)
+
+        video = self._download_json(
+            '%s/recordings/%s' % (self._API_BASE, display_id), display_id,
+            headers={'Referer': url})
+
+        video_id = video['uuid']
+        timestamp = unified_timestamp(video.get('createdAt'))
+        duration = int_or_none(video.get('duration'))
+        view_count = int_or_none(video.get('viewCount'))
+        like_count = int_or_none(video.get('likeCount'))
+        creator = video.get('stageName')
+
+        formats = [{
+            'url': '%s/recordings/%s/manifest.m3u8'
+                   % (self._API_BASE, video_id),
+            'format_id': 'hls',
+            'ext': 'mp4',
+            'protocol': 'm3u8_native',
+        }]
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': display_id,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'creator': creator,
+            'formats': formats,
+        }

youtube_dl/extractor/chaturbate.py

@@ -31,7 +31,8 @@ class ChaturbateIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            url, video_id, headers=self.geo_verification_headers())
 
         m3u8_urls = []
 

youtube_dl/extractor/common.py

@@ -19,6 +19,7 @@ from ..compat import (
     compat_cookies,
     compat_etree_fromstring,
     compat_getpass,
+    compat_integer_types,
     compat_http_client,
     compat_os_name,
     compat_str,
@@ -548,8 +549,26 @@ class InfoExtractor(object):
     def IE_NAME(self):
         return compat_str(type(self).__name__[:-2])
 
-    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
-        """ Returns the response handle """
+    @staticmethod
+    def __can_accept_status_code(err, expected_status):
+        assert isinstance(err, compat_urllib_error.HTTPError)
+        if expected_status is None:
+            return False
+        if isinstance(expected_status, compat_integer_types):
+            return err.code == expected_status
+        elif isinstance(expected_status, (list, tuple)):
+            return err.code in expected_status
+        elif callable(expected_status):
+            return expected_status(err.code) is True
+        else:
+            assert False
+
+    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}, expected_status=None):
+        """
+        Return the response handle.
+
+        See _download_webpage docstring for arguments specification.
+        """
         if note is None:
             self.report_download_webpage(video_id)
         elif note is not False:
@@ -578,6 +597,10 @@ class InfoExtractor(object):
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            if isinstance(err, compat_urllib_error.HTTPError):
+                if self.__can_accept_status_code(err, expected_status):
+                    return err.fp
+
             if errnote is False:
                 return False
             if errnote is None:
@@ -590,13 +613,17 @@ class InfoExtractor(object):
                 self._downloader.report_warning(errmsg)
                 return False
 
-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}):
-        """ Returns a tuple (page content as string, URL handle) """
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None):
+        """
+        Return a tuple (page content as string, URL handle).
+
+        See _download_webpage docstring for arguments specification.
+        """
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 
-        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query)
+        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query, expected_status=expected_status)
         if urlh is False:
             assert not fatal
             return False
@@ -685,13 +712,52 @@ class InfoExtractor(object):
 
         return content
 
-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers={}, query={}):
-        """ Returns the data of the page as a string """
+    def _download_webpage(
+            self, url_or_request, video_id, note=None, errnote=None,
+            fatal=True, tries=1, timeout=5, encoding=None, data=None,
+            headers={}, query={}, expected_status=None):
+        """
+        Return the data of the page as a string.
+
+        Arguments:
+        url_or_request -- plain text URL as a string or
+            a compat_urllib_request.Requestobject
+        video_id -- Video/playlist/item identifier (string)
+
+        Keyword arguments:
+        note -- note printed before downloading (string)
+        errnote -- note printed in case of an error (string)
+        fatal -- flag denoting whether error should be considered fatal,
+            i.e. whether it should cause ExtractionError to be raised,
+            otherwise a warning will be reported and extraction continued
+        tries -- number of tries
+        timeout -- sleep interval between tries
+        encoding -- encoding for a page content decoding, guessed automatically
+            when not explicitly specified
+        data -- POST data (bytes)
+        headers -- HTTP headers (dict)
+        query -- URL query (dict)
+        expected_status -- allows to accept failed HTTP requests (non 2xx
+            status code) by explicitly specifying a set of accepted status
+            codes. Can be any of the following entities:
+                - an integer type specifying an exact failed status code to
+                  accept
+                - a list or a tuple of integer types specifying a list of
+                  failed status codes to accept
+                - a callable accepting an actual failed status code and
+                  returning True if it should be accepted
+            Note that this argument does not affect success status codes (2xx)
+            which are always accepted.
+        """
+
         success = False
         try_count = 0
         while success is False:
             try:
-                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query)
+                res = self._download_webpage_handle(
+                    url_or_request, video_id, note, errnote, fatal,
+                    encoding=encoding, data=data, headers=headers, query=query,
+                    expected_status=expected_status)
                 success = True
             except compat_http_client.IncompleteRead as e:
                 try_count += 1
@@ -707,11 +773,17 @@ class InfoExtractor(object):
     def _download_xml_handle(
             self, url_or_request, video_id, note='Downloading XML',
             errnote='Unable to download XML', transform_source=None,
-            fatal=True, encoding=None, data=None, headers={}, query={}):
-        """Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle)"""
+            fatal=True, encoding=None, data=None, headers={}, query={},
+            expected_status=None):
+        """
+        Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle).
+
+        See _download_webpage docstring for arguments specification.
+        """
         res = self._download_webpage_handle(
             url_or_request, video_id, note, errnote, fatal=fatal,
-            encoding=encoding, data=data, headers=headers, query=query)
+            encoding=encoding, data=data, headers=headers, query=query,
+            expected_status=expected_status)
         if res is False:
             return res
         xml_string, urlh = res
@@ -719,15 +791,21 @@ class InfoExtractor(object):
             xml_string, video_id, transform_source=transform_source,
             fatal=fatal), urlh
 
-    def _download_xml(self, url_or_request, video_id,
-                      note='Downloading XML', errnote='Unable to download XML',
-                      transform_source=None, fatal=True, encoding=None,
-                      data=None, headers={}, query={}):
-        """Return the xml as an xml.etree.ElementTree.Element"""
+    def _download_xml(
+            self, url_or_request, video_id,
+            note='Downloading XML', errnote='Unable to download XML',
+            transform_source=None, fatal=True, encoding=None,
+            data=None, headers={}, query={}, expected_status=None):
+        """
+        Return the xml as an xml.etree.ElementTree.Element.
+
+        See _download_webpage docstring for arguments specification.
+        """
         res = self._download_xml_handle(
             url_or_request, video_id, note=note, errnote=errnote,
             transform_source=transform_source, fatal=fatal, encoding=encoding,
-            data=data, headers=headers, query=query)
+            data=data, headers=headers, query=query,
+            expected_status=expected_status)
         return res if res is False else res[0]
 
     def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True):
@@ -745,11 +823,17 @@ class InfoExtractor(object):
     def _download_json_handle(
             self, url_or_request, video_id, note='Downloading JSON metadata',
             errnote='Unable to download JSON metadata', transform_source=None,
-            fatal=True, encoding=None, data=None, headers={}, query={}):
-        """Return a tuple (JSON object, URL handle)"""
+            fatal=True, encoding=None, data=None, headers={}, query={},
+            expected_status=None):
+        """
+        Return a tuple (JSON object, URL handle).
+
+        See _download_webpage docstring for arguments specification.
+        """
         res = self._download_webpage_handle(
             url_or_request, video_id, note, errnote, fatal=fatal,
-            encoding=encoding, data=data, headers=headers, query=query)
+            encoding=encoding, data=data, headers=headers, query=query,
+            expected_status=expected_status)
         if res is False:
             return res
         json_string, urlh = res
@@ -760,11 +844,18 @@ class InfoExtractor(object):
     def _download_json(
             self, url_or_request, video_id, note='Downloading JSON metadata',
             errnote='Unable to download JSON metadata', transform_source=None,
-            fatal=True, encoding=None, data=None, headers={}, query={}):
+            fatal=True, encoding=None, data=None, headers={}, query={},
+            expected_status=None):
+        """
+        Return the JSON object as a dict.
+
+        See _download_webpage docstring for arguments specification.
+        """
         res = self._download_json_handle(
             url_or_request, video_id, note=note, errnote=errnote,
             transform_source=transform_source, fatal=fatal, encoding=encoding,
-            data=data, headers=headers, query=query)
+            data=data, headers=headers, query=query,
+            expected_status=expected_status)
         return res if res is False else res[0]
 
     def _parse_json(self, json_string, video_id, transform_source=None, fatal=True):

youtube_dl/extractor/crackle.py

@@ -19,8 +19,8 @@ from ..utils import (
 
 
 class CrackleIE(InfoExtractor):
-    _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'(?:crackle:|https?://(?:(?:www|m)\.)?(?:sony)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
+    _TESTS = [{
         # geo restricted to CA
         'url': 'https://www.crackle.com/andromeda/2502343',
         'info_dict': {
@@ -45,7 +45,10 @@ class CrackleIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
-    }
+    }, {
+        'url': 'https://www.sonycrackle.com/andromeda/2502343',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/dailymotion.py

@@ -1,12 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
+import base64
+import hashlib
 import itertools
+import json
+import random
+import re
+import string
 
 from .common import InfoExtractor
-
+from ..compat import compat_struct_pack
 from ..utils import (
     determine_ext,
     error_to_compat_str,
@@ -64,7 +68,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'uploader': 'Deadline',
             'uploader_id': 'x1xm8ri',
             'age_limit': 0,
-            'view_count': int,
         },
     }, {
         'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
@@ -167,6 +170,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             player = self._parse_json(player_v5, video_id)
             metadata = player['metadata']
 
+            if metadata.get('error', {}).get('type') == 'password_protected':
+                password = self._downloader.params.get('videopassword')
+                if password:
+                    r = int(metadata['id'][1:], 36)
+                    us64e = lambda x: base64.urlsafe_b64encode(x).decode().strip('=')
+                    t = ''.join(random.choice(string.ascii_letters) for i in range(10))
+                    n = us64e(compat_struct_pack('I', r))
+                    i = us64e(hashlib.md5(('%s%d%s' % (password, r, t)).encode()).digest())
+                    metadata = self._download_json(
+                        'http://www.dailymotion.com/player/metadata/video/p' + i + t + n, video_id)
+
             self._check_error(metadata)
 
             formats = []
@@ -302,8 +316,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
 
     def _check_error(self, info):
         error = info.get('error')
-        if info.get('error') is not None:
-            title = error['title']
+        if error:
+            title = error.get('title') or error['message']
             # See https://developer.dailymotion.com/api#access-error
             if error.get('code') == 'DM007':
                 self.raise_geo_restricted(msg=title)

youtube_dl/extractor/discoverynetworks.py

@@ -3,8 +3,8 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
 from .brightcove import BrightcoveLegacyIE
+from .dplay import DPlayIE
 from ..compat import (
     compat_parse_qs,
     compat_urlparse,
@@ -12,8 +12,13 @@ from ..compat import (
 from ..utils import smuggle_url
 
 
-class DiscoveryNetworksDeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:discovery|tlc|animalplanet|dmax)\.de/(?:.*#(?P<id>\d+)|(?:[^/]+/)*videos/(?P<title>[^/?#]+))'
+class DiscoveryNetworksDeIE(DPlayIE):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/
+                        (?:
+                           .*\#(?P<id>\d+)|
+                           (?:[^/]+/)*videos/(?P<display_id>[^/?#]+)|
+                           programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)
+                        )'''
 
     _TESTS = [{
         'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
@@ -40,6 +45,14 @@ class DiscoveryNetworksDeIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        alternate_id = mobj.group('alternate_id')
+        if alternate_id:
+            self._initialize_geo_bypass({
+                'countries': ['DE'],
+            })
+            return self._get_disco_api_info(
+                url, '%s/%s' % (mobj.group('programme'), alternate_id),
+                'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de')
         brightcove_id = mobj.group('id')
         if not brightcove_id:
             title = mobj.group('title')

youtube_dl/extractor/dplay.py

@@ -97,6 +97,75 @@ class DPlayIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _get_disco_api_info(self, url, display_id, disco_host, realm):
+        disco_base = 'https://' + disco_host
+        token = self._download_json(
+            '%s/token' % disco_base, display_id, 'Downloading token',
+            query={
+                'realm': realm,
+            })['data']['attributes']['token']
+        headers = {
+            'Referer': url,
+            'Authorization': 'Bearer ' + token,
+        }
+        video = self._download_json(
+            '%s/content/videos/%s' % (disco_base, display_id), display_id,
+            headers=headers, query={
+                'include': 'show'
+            })
+        video_id = video['data']['id']
+        info = video['data']['attributes']
+        title = info['name']
+        formats = []
+        for format_id, format_dict in self._download_json(
+                '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id),
+                display_id, headers=headers)['data']['attributes']['streaming'].items():
+            if not isinstance(format_dict, dict):
+                continue
+            format_url = format_dict.get('url')
+            if not format_url:
+                continue
+            ext = determine_ext(format_url)
+            if format_id == 'dash' or ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    format_url, display_id, mpd_id='dash', fatal=False))
+            elif format_id == 'hls' or ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, display_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls',
+                    fatal=False))
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                })
+        self._sort_formats(formats)
+
+        series = None
+        try:
+            included = video.get('included')
+            if isinstance(included, list):
+                show = next(e for e in included if e.get('type') == 'show')
+                series = try_get(
+                    show, lambda x: x['attributes']['name'], compat_str)
+        except StopIteration:
+            pass
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': info.get('description'),
+            'duration': float_or_none(
+                info.get('videoDuration'), scale=1000),
+            'timestamp': unified_timestamp(info.get('publishStart')),
+            'series': series,
+            'season_number': int_or_none(info.get('seasonNumber')),
+            'episode_number': int_or_none(info.get('episodeNumber')),
+            'age_limit': int_or_none(info.get('minimum_age')),
+            'formats': formats,
+        }
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('id')
@@ -113,72 +182,8 @@ class DPlayIE(InfoExtractor):
 
         if not video_id:
             host = mobj.group('host')
-            disco_base = 'https://disco-api.%s' % host
-            self._download_json(
-                '%s/token' % disco_base, display_id, 'Downloading token',
-                query={
-                    'realm': host.replace('.', ''),
-                })
-            video = self._download_json(
-                '%s/content/videos/%s' % (disco_base, display_id), display_id,
-                headers={
-                    'Referer': url,
-                    'x-disco-client': 'WEB:UNKNOWN:dplay-client:0.0.1',
-                }, query={
-                    'include': 'show'
-                })
-            video_id = video['data']['id']
-            info = video['data']['attributes']
-            title = info['name']
-            formats = []
-            for format_id, format_dict in self._download_json(
-                    '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id),
-                    display_id)['data']['attributes']['streaming'].items():
-                if not isinstance(format_dict, dict):
-                    continue
-                format_url = format_dict.get('url')
-                if not format_url:
-                    continue
-                ext = determine_ext(format_url)
-                if format_id == 'dash' or ext == 'mpd':
-                    formats.extend(self._extract_mpd_formats(
-                        format_url, display_id, mpd_id='dash', fatal=False))
-                elif format_id == 'hls' or ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        format_url, display_id, 'mp4',
-                        entry_protocol='m3u8_native', m3u8_id='hls',
-                        fatal=False))
-                else:
-                    formats.append({
-                        'url': format_url,
-                        'format_id': format_id,
-                    })
-            self._sort_formats(formats)
-
-            series = None
-            try:
-                included = video.get('included')
-                if isinstance(included, list):
-                    show = next(e for e in included if e.get('type') == 'show')
-                    series = try_get(
-                        show, lambda x: x['attributes']['name'], compat_str)
-            except StopIteration:
-                pass
-
-            return {
-                'id': video_id,
-                'display_id': display_id,
-                'title': title,
-                'description': info.get('description'),
-                'duration': float_or_none(
-                    info.get('videoDuration'), scale=1000),
-                'timestamp': unified_timestamp(info.get('publishStart')),
-                'series': series,
-                'season_number': int_or_none(info.get('seasonNumber')),
-                'episode_number': int_or_none(info.get('episodeNumber')),
-                'age_limit': int_or_none(info.get('minimum_age')),
-                'formats': formats,
-            }
+            return self._get_disco_api_info(
+                url, display_id, 'disco-api.' + host, host.replace('.', ''))
 
         info = self._download_json(
             'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),

youtube_dl/extractor/expressen.py

@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    unescapeHTML,
+    unified_timestamp,
+)
+
+
+class ExpressenIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?expressen\.se/tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.expressen.se/tv/ledare/ledarsnack/ledarsnack-om-arbetslosheten-bland-kvinnor-i-speciellt-utsatta-omraden/',
+        'md5': '2fbbe3ca14392a6b1b36941858d33a45',
+        'info_dict': {
+            'id': '8690962',
+            'ext': 'mp4',
+            'title': 'Ledarsnack: Om arbetslösheten bland kvinnor i speciellt utsatta områden',
+            'description': 'md5:f38c81ff69f3de4d269bbda012fcbbba',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 788,
+            'timestamp': 1526639109,
+            'upload_date': '20180518',
+        },
+    }, {
+        'url': 'https://www.expressen.se/tv/kultur/kulturdebatt-med-expressens-karin-olsson/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        def extract_data(name):
+            return self._parse_json(
+                self._search_regex(
+                    r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1' % name,
+                    webpage, 'info', group='value'),
+                display_id, transform_source=unescapeHTML)
+
+        info = extract_data('video-tracking-info')
+        video_id = info['videoId']
+
+        data = extract_data('article-data')
+        stream = data['stream']
+
+        if determine_ext(stream) == 'm3u8':
+            formats = self._extract_m3u8_formats(
+                stream, display_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls')
+        else:
+            formats = [{
+                'url': stream,
+            }]
+        self._sort_formats(formats)
+
+        title = info.get('titleRaw') or data['title']
+        description = info.get('descriptionRaw')
+        thumbnail = info.get('socialMediaImage') or data.get('image')
+        duration = int_or_none(info.get('videoTotalSecondsDuration') or
+                               data.get('totalSecondsDuration'))
+        timestamp = unified_timestamp(info.get('publishDate'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/extractors.py

@@ -147,6 +147,7 @@ from .camdemy import (
     CamdemyFolderIE
 )
 from .cammodels import CamModelsIE
+from .camtube import CamTubeIE
 from .camwithher import CamWithHerIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
@@ -334,6 +335,7 @@ from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .expotv import ExpoTVIE
+from .expressen import ExpressenIE
 from .extremetube import ExtremeTubeIE
 from .eyedotv import EyedoTVIE
 from .facebook import (
@@ -588,6 +590,10 @@ from .mangomolo import (
     MangomoloLiveIE,
 )
 from .manyvids import ManyVidsIE
+from .markiza import (
+    MarkizaIE,
+    MarkizaPageIE,
+)
 from .massengeschmacktv import MassengeschmackTVIE
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
@@ -1138,6 +1144,7 @@ from .tvc import (
 from .tvigle import TvigleIE
 from .tvland import TVLandIE
 from .tvn24 import TVN24IE
+from .tvnet import TVNetIE
 from .tvnoe import TVNoeIE
 from .tvnow import (
     TVNowIE,

youtube_dl/extractor/generic.py

@@ -3076,7 +3076,7 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
 
-        peertube_urls = PeerTubeIE._extract_urls(webpage)
+        peertube_urls = PeerTubeIE._extract_urls(webpage, url)
         if peertube_urls:
             return self.playlist_from_matches(
                 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())

youtube_dl/extractor/inc.py

@@ -21,6 +21,21 @@ class IncIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # div with id=kaltura_player_1_kqs38cgm
+        'url': 'https://www.inc.com/oscar-raymundo/richard-branson-young-entrepeneurs.html',
+        'info_dict': {
+            'id': '1_kqs38cgm',
+            'ext': 'mp4',
+            'title': 'Branson: "In the end, you have to say, Screw it. Just do it."',
+            'description': 'md5:21b832d034f9af5191ca5959da5e9cb6',
+            'timestamp': 1364403232,
+            'upload_date': '20130327',
+            'uploader_id': 'incdigital@inc.com',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html',
         'only_matching': True,
@@ -31,10 +46,13 @@ class IncIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         partner_id = self._search_regex(
-            r'var\s+_?bizo_data_partner_id\s*=\s*["\'](\d+)', webpage, 'partner id')
+            r'var\s+_?bizo_data_partner_id\s*=\s*["\'](\d+)', webpage,
+            'partner id', default='1034971')
 
-        kaltura_id = self._parse_json(self._search_regex(
-            r'pageInfo\.videos\s*=\s*\[(.+)\];', webpage, 'kaltura id'),
+        kaltura_id = self._search_regex(
+            r'id=(["\'])kaltura_player_(?P<id>.+?)\1', webpage, 'kaltura id',
+            default=None, group='id') or self._parse_json(self._search_regex(
+                r'pageInfo\.videos\s*=\s*\[(.+)\];', webpage, 'kaltura id'),
             display_id)['vid_kaltura_id']
 
         return self.url_result(

youtube_dl/extractor/markiza.py

@@ -0,0 +1,125 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    orderedSet,
+    parse_duration,
+    try_get,
+)
+
+
+class MarkizaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?videoarchiv\.markiza\.sk/(?:video/(?:[^/]+/)*|embed/)(?P<id>\d+)(?:[_/]|$)'
+    _TESTS = [{
+        'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723_oteckovia-109',
+        'md5': 'ada4e9fad038abeed971843aa028c7b0',
+        'info_dict': {
+            'id': '139078',
+            'ext': 'mp4',
+            'title': 'Oteckovia 109',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 2760,
+        },
+    }, {
+        'url': 'http://videoarchiv.markiza.sk/video/televizne-noviny/televizne-noviny/85430_televizne-noviny',
+        'info_dict': {
+            'id': '85430',
+            'title': 'Televízne noviny',
+        },
+        'playlist_count': 23,
+    }, {
+        'url': 'http://videoarchiv.markiza.sk/video/oteckovia/84723',
+        'only_matching': True,
+    }, {
+        'url': 'http://videoarchiv.markiza.sk/video/84723',
+        'only_matching': True,
+    }, {
+        'url': 'http://videoarchiv.markiza.sk/video/filmy/85190_kamenak',
+        'only_matching': True,
+    }, {
+        'url': 'http://videoarchiv.markiza.sk/video/reflex/zo-zakulisia/84651_pribeh-alzbetky',
+        'only_matching': True,
+    }, {
+        'url': 'http://videoarchiv.markiza.sk/embed/85295',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        data = self._download_json(
+            'http://videoarchiv.markiza.sk/json/video_jwplayer7.json',
+            video_id, query={'id': video_id})
+
+        info = self._parse_jwplayer_data(data, m3u8_id='hls', mpd_id='dash')
+
+        if info.get('_type') == 'playlist':
+            info.update({
+                'id': video_id,
+                'title': try_get(
+                    data, lambda x: x['details']['name'], compat_str),
+            })
+        else:
+            info['duration'] = parse_duration(
+                try_get(data, lambda x: x['details']['duration'], compat_str))
+        return info
+
+
+class MarkizaPageIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:(?:[^/]+\.)?markiza|tvnoviny)\.sk/(?:[^/]+/)*(?P<id>\d+)_'
+    _TESTS = [{
+        'url': 'http://www.markiza.sk/soubiz/zahranicny/1923705_oteckovia-maju-svoj-den-ti-slavni-nie-su-o-nic-menej-rozkosni',
+        'md5': 'ada4e9fad038abeed971843aa028c7b0',
+        'info_dict': {
+            'id': '139355',
+            'ext': 'mp4',
+            'title': 'Oteckovia 110',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 2604,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://dajto.markiza.sk/filmy-a-serialy/1774695_frajeri-vo-vegas',
+        'only_matching': True,
+    }, {
+        'url': 'http://superstar.markiza.sk/aktualne/1923870_to-je-ale-telo-spevacka-ukazala-sexy-postavicku-v-bikinach',
+        'only_matching': True,
+    }, {
+        'url': 'http://hybsa.markiza.sk/aktualne/1923790_uzasna-atmosfera-na-hybsa-v-poprade-superstaristi-si-prve-koncerty-pred-davom-ludi-poriadne-uzili',
+        'only_matching': True,
+    }, {
+        'url': 'http://doma.markiza.sk/filmy/1885250_moja-vysnivana-svadba',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tvnoviny.sk/domace/1923887_po-smrti-manzela-ju-cakalo-poriadne-prekvapenie',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if MarkizaIE.suitable(url) else super(MarkizaPageIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            # Downloading for some hosts (e.g. dajto, doma) fails with 500
+            # although everything seems to be OK, so considering 500
+            # status code to be expected.
+            url, playlist_id, expected_status=500)
+
+        entries = [
+            self.url_result('http://videoarchiv.markiza.sk/video/%s' % video_id)
+            for video_id in orderedSet(re.findall(
+                r'(?:initPlayer_|data-entity=["\']|id=["\']player_)(\d+)',
+                webpage))]
+
+        return self.playlist_result(entries, playlist_id)

youtube_dl/extractor/nexx.py

@@ -29,14 +29,13 @@ class NexxIE(InfoExtractor):
     _TESTS = [{
         # movie
         'url': 'https://api.nexx.cloud/v3/748/videos/byid/128907',
-        'md5': '828cea195be04e66057b846288295ba1',
+        'md5': '31899fd683de49ad46f4ee67e53e83fe',
         'info_dict': {
             'id': '128907',
             'ext': 'mp4',
             'title': 'Stiftung Warentest',
             'alt_title': 'Wie ein Test abläuft',
             'description': 'md5:d1ddb1ef63de721132abd38639cc2fd2',
-            'release_year': 2013,
             'creator': 'SPIEGEL TV',
             'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 2509,
@@ -62,6 +61,7 @@ class NexxIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'HTTP Error 404: Not Found',
     }, {
         # does not work via arc
         'url': 'nexx:741:1269984',
@@ -71,12 +71,26 @@ class NexxIE(InfoExtractor):
             'ext': 'mp4',
             'title': '1 TAG ohne KLO... wortwörtlich! 😑',
             'alt_title': '1 TAG ohne KLO... wortwörtlich! 😑',
-            'description': 'md5:4604539793c49eda9443ab5c5b1d612f',
             'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 607,
             'timestamp': 1518614955,
             'upload_date': '20180214',
         },
+    }, {
+        # free cdn from http://www.spiegel.de/video/eifel-zoo-aufregung-um-ausgebrochene-raubtiere-video-99018031.html
+        'url': 'nexx:747:1533779',
+        'md5': '6bf6883912b82b7069fb86c2297e9893',
+        'info_dict': {
+            'id': '1533779',
+            'ext': 'mp4',
+            'title': 'Aufregung um ausgebrochene Raubtiere',
+            'alt_title': 'Eifel-Zoo',
+            'description': 'md5:f21375c91c74ad741dcb164c427999d2',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 111,
+            'timestamp': 1527874460,
+            'upload_date': '20180601',
+        },
     }, {
         'url': 'https://api.nexxcdn.com/v3/748/videos/byid/128907',
         'only_matching': True,
@@ -141,6 +155,139 @@ class NexxIE(InfoExtractor):
         self._handle_error(result)
         return result['result']
 
+    def _extract_free_formats(self, video, video_id):
+        stream_data = video['streamdata']
+        cdn = stream_data['cdnType']
+        assert cdn == 'free'
+
+        hash = video['general']['hash']
+
+        ps = compat_str(stream_data['originalDomain'])
+        if stream_data['applyFolderHierarchy'] == 1:
+            s = ('%04d' % int(video_id))[::-1]
+            ps += '/%s/%s' % (s[0:2], s[2:4])
+        ps += '/%s/%s_' % (video_id, hash)
+
+        t = 'http://%s' + ps
+        fd = stream_data['azureFileDistribution'].split(',')
+        cdn_provider = stream_data['cdnProvider']
+
+        def p0(p):
+            return '_%s' % p if stream_data['applyAzureStructure'] == 1 else ''
+
+        formats = []
+        if cdn_provider == 'ak':
+            t += ','
+            for i in fd:
+                p = i.split(':')
+                t += p[1] + p0(int(p[0])) + ','
+            t += '.mp4.csmil/master.%s'
+        elif cdn_provider == 'ce':
+            k = t.split('/')
+            h = k.pop()
+            http_base = t = '/'.join(k)
+            http_base = http_base % stream_data['cdnPathHTTP']
+            t += '/asset.ism/manifest.%s?dcp_ver=aos4&videostream='
+            for i in fd:
+                p = i.split(':')
+                tbr = int(p[0])
+                filename = '%s%s%s.mp4' % (h, p[1], p0(tbr))
+                f = {
+                    'url': http_base + '/' + filename,
+                    'format_id': '%s-http-%d' % (cdn, tbr),
+                    'tbr': tbr,
+                }
+                width_height = p[1].split('x')
+                if len(width_height) == 2:
+                    f.update({
+                        'width': int_or_none(width_height[0]),
+                        'height': int_or_none(width_height[1]),
+                    })
+                formats.append(f)
+                a = filename + ':%s' % (tbr * 1000)
+                t += a + ','
+            t = t[:-1] + '&audiostream=' + a.split(':')[0]
+        else:
+            assert False
+
+        if cdn_provider == 'ce':
+            formats.extend(self._extract_mpd_formats(
+                t % (stream_data['cdnPathDASH'], 'mpd'), video_id,
+                mpd_id='%s-dash' % cdn, fatal=False))
+        formats.extend(self._extract_m3u8_formats(
+            t % (stream_data['cdnPathHLS'], 'm3u8'), video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='%s-hls' % cdn, fatal=False))
+
+        return formats
+
+    def _extract_azure_formats(self, video, video_id):
+        stream_data = video['streamdata']
+        cdn = stream_data['cdnType']
+        assert cdn == 'azure'
+
+        azure_locator = stream_data['azureLocator']
+
+        def get_cdn_shield_base(shield_type='', static=False):
+            for secure in ('', 's'):
+                cdn_shield = stream_data.get('cdnShield%sHTTP%s' % (shield_type, secure.upper()))
+                if cdn_shield:
+                    return 'http%s://%s' % (secure, cdn_shield)
+            else:
+                if 'fb' in stream_data['azureAccount']:
+                    prefix = 'df' if static else 'f'
+                else:
+                    prefix = 'd' if static else 'p'
+                account = int(stream_data['azureAccount'].replace('nexxplayplus', '').replace('nexxplayfb', ''))
+                return 'http://nx-%s%02d.akamaized.net/' % (prefix, account)
+
+        language = video['general'].get('language_raw') or ''
+
+        azure_stream_base = get_cdn_shield_base()
+        is_ml = ',' in language
+        azure_manifest_url = '%s%s/%s_src%s.ism/Manifest' % (
+            azure_stream_base, azure_locator, video_id, ('_manifest' if is_ml else '')) + '%s'
+
+        protection_token = try_get(
+            video, lambda x: x['protectiondata']['token'], compat_str)
+        if protection_token:
+            azure_manifest_url += '?hdnts=%s' % protection_token
+
+        formats = self._extract_m3u8_formats(
+            azure_manifest_url % '(format=m3u8-aapl)',
+            video_id, 'mp4', 'm3u8_native',
+            m3u8_id='%s-hls' % cdn, fatal=False)
+        formats.extend(self._extract_mpd_formats(
+            azure_manifest_url % '(format=mpd-time-csf)',
+            video_id, mpd_id='%s-dash' % cdn, fatal=False))
+        formats.extend(self._extract_ism_formats(
+            azure_manifest_url % '', video_id, ism_id='%s-mss' % cdn, fatal=False))
+
+        azure_progressive_base = get_cdn_shield_base('Prog', True)
+        azure_file_distribution = stream_data.get('azureFileDistribution')
+        if azure_file_distribution:
+            fds = azure_file_distribution.split(',')
+            if fds:
+                for fd in fds:
+                    ss = fd.split(':')
+                    if len(ss) == 2:
+                        tbr = int_or_none(ss[0])
+                        if tbr:
+                            f = {
+                                'url': '%s%s/%s_src_%s_%d.mp4' % (
+                                    azure_progressive_base, azure_locator, video_id, ss[1], tbr),
+                                'format_id': '%s-http-%d' % (cdn, tbr),
+                                'tbr': tbr,
+                            }
+                            width_height = ss[1].split('x')
+                            if len(width_height) == 2:
+                                f.update({
+                                    'width': int_or_none(width_height[0]),
+                                    'height': int_or_none(width_height[1]),
+                                })
+                            formats.append(f)
+
+        return formats
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         domain_id = mobj.group('domain_id') or mobj.group('domain_id_s')
@@ -220,72 +367,15 @@ class NexxIE(InfoExtractor):
         general = video['general']
         title = general['title']
 
-        stream_data = video['streamdata']
-        language = general.get('language_raw') or ''
+        cdn = video['streamdata']['cdnType']
 
-        # TODO: reverse more cdns
-
-        cdn = stream_data['cdnType']
-        assert cdn == 'azure'
-
-        azure_locator = stream_data['azureLocator']
-
-        def get_cdn_shield_base(shield_type='', static=False):
-            for secure in ('', 's'):
-                cdn_shield = stream_data.get('cdnShield%sHTTP%s' % (shield_type, secure.upper()))
-                if cdn_shield:
-                    return 'http%s://%s' % (secure, cdn_shield)
-            else:
-                if 'fb' in stream_data['azureAccount']:
-                    prefix = 'df' if static else 'f'
-                else:
-                    prefix = 'd' if static else 'p'
-                account = int(stream_data['azureAccount'].replace('nexxplayplus', '').replace('nexxplayfb', ''))
-                return 'http://nx-%s%02d.akamaized.net/' % (prefix, account)
-
-        azure_stream_base = get_cdn_shield_base()
-        is_ml = ',' in language
-        azure_manifest_url = '%s%s/%s_src%s.ism/Manifest' % (
-            azure_stream_base, azure_locator, video_id, ('_manifest' if is_ml else '')) + '%s'
-
-        protection_token = try_get(
-            video, lambda x: x['protectiondata']['token'], compat_str)
-        if protection_token:
-            azure_manifest_url += '?hdnts=%s' % protection_token
-
-        formats = self._extract_m3u8_formats(
-            azure_manifest_url % '(format=m3u8-aapl)',
-            video_id, 'mp4', 'm3u8_native',
-            m3u8_id='%s-hls' % cdn, fatal=False)
-        formats.extend(self._extract_mpd_formats(
-            azure_manifest_url % '(format=mpd-time-csf)',
-            video_id, mpd_id='%s-dash' % cdn, fatal=False))
-        formats.extend(self._extract_ism_formats(
-            azure_manifest_url % '', video_id, ism_id='%s-mss' % cdn, fatal=False))
-
-        azure_progressive_base = get_cdn_shield_base('Prog', True)
-        azure_file_distribution = stream_data.get('azureFileDistribution')
-        if azure_file_distribution:
-            fds = azure_file_distribution.split(',')
-            if fds:
-                for fd in fds:
-                    ss = fd.split(':')
-                    if len(ss) == 2:
-                        tbr = int_or_none(ss[0])
-                        if tbr:
-                            f = {
-                                'url': '%s%s/%s_src_%s_%d.mp4' % (
-                                    azure_progressive_base, azure_locator, video_id, ss[1], tbr),
-                                'format_id': '%s-http-%d' % (cdn, tbr),
-                                'tbr': tbr,
-                            }
-                            width_height = ss[1].split('x')
-                            if len(width_height) == 2:
-                                f.update({
-                                    'width': int_or_none(width_height[0]),
-                                    'height': int_or_none(width_height[1]),
-                                })
-                            formats.append(f)
+        if cdn == 'azure':
+            formats = self._extract_azure_formats(video, video_id)
+        elif cdn == 'free':
+            formats = self._extract_free_formats(video, video_id)
+        else:
+            # TODO: reverse more cdns
+            assert False
 
         self._sort_formats(formats)
 

youtube_dl/extractor/npo.py

@@ -36,8 +36,8 @@ class NPOIE(NPOBaseIE):
                         https?://
                             (?:www\.)?
                             (?:
-                                npo\.nl/(?!(?:live|radio)/)(?:[^/]+/){2}|
-                                ntr\.nl/(?:[^/]+/){2,}|
+                                npo\.nl/(?:[^/]+/)*|
+                                (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
                                 omroepwnl\.nl/video/fragment/[^/]+__|
                                 (?:zapp|npo3)\.nl/(?:[^/]+/){2,}
                             )
@@ -160,8 +160,20 @@ class NPOIE(NPOBaseIE):
     }, {
         'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
         'only_matching': True,
+    }, {
+        'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
+        'only_matching': True,
+    }, {
+        'url': 'https://npo.nl/KN_1698996',
+        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return (False if any(ie.suitable(url)
+                for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
+                else super(NPOIE, cls).suitable(url))
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         return self._get_info(video_id)
@@ -389,7 +401,7 @@ class NPOLiveIE(NPOBaseIE):
 
 class NPORadioIE(InfoExtractor):
     IE_NAME = 'npo.nl:radio'
-    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
+    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
 
     _TEST = {
         'url': 'http://www.npo.nl/radio/radio-1',
@@ -404,6 +416,10 @@ class NPORadioIE(InfoExtractor):
         }
     }
 
+    @classmethod
+    def suitable(cls, url):
+        return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
+
     @staticmethod
     def _html_get_attribute_regex(attribute):
         return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)

youtube_dl/extractor/nrk.py

@@ -16,12 +16,22 @@ from ..utils import (
 class NRKBaseIE(InfoExtractor):
     _GEO_COUNTRIES = ['NO']
 
+    _api_host = None
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        data = self._download_json(
-            'http://%s/mediaelement/%s' % (self._API_HOST, video_id),
-            video_id, 'Downloading mediaelement JSON')
+        api_hosts = (self._api_host, ) if self._api_host else self._API_HOSTS
+
+        for api_host in api_hosts:
+            data = self._download_json(
+                'http://%s/mediaelement/%s' % (api_host, video_id),
+                video_id, 'Downloading mediaelement JSON',
+                fatal=api_host == api_hosts[-1])
+            if not data:
+                continue
+            self._api_host = api_host
+            break
 
         title = data.get('fullTitle') or data.get('mainTitle') or data['title']
         video_id = data.get('id') or video_id
@@ -191,7 +201,7 @@ class NRKIE(NRKBaseIE):
                             )
                             (?P<id>[^?#&]+)
                         '''
-    _API_HOST = 'v8-psapi.nrk.no'
+    _API_HOSTS = ('psapi.nrk.no', 'v8-psapi.nrk.no')
     _TESTS = [{
         # video
         'url': 'http://www.nrk.no/video/PS*150533',
@@ -237,8 +247,7 @@ class NRKTVIE(NRKBaseIE):
                             (?:/\d{2}-\d{2}-\d{4})?
                             (?:\#del=(?P<part_id>\d+))?
                     ''' % _EPISODE_RE
-    _API_HOST = 'psapi-we.nrk.no'
-
+    _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
     _TESTS = [{
         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
         'md5': '4e9ca6629f09e588ed240fb11619922a',

youtube_dl/extractor/pbs.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     determine_ext,
@@ -360,6 +361,50 @@ class PBSIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/',
+            'info_dict': {
+                'id': '2365936247',
+                'ext': 'mp4',
+                'title': 'Antiques Roadshow - Indianapolis, Hour 2',
+                'description': 'md5:524b32249db55663e7231b6b8d1671a2',
+                'duration': 3180,
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': ['HTTP Error 403: Forbidden'],
+        },
+        {
+            'url': 'https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/',
+            'info_dict': {
+                'id': '3007193718',
+                'ext': 'mp4',
+                'title': "Victoria - A Soldier's Daughter / The Green-Eyed Monster",
+                'description': 'md5:37efbac85e0c09b009586523ec143652',
+                'duration': 6292,
+                'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': ['HTTP Error 403: Forbidden'],
+        },
+        {
+            'url': 'https://player.pbs.org/partnerplayer/tOz9tM5ljOXQqIIWke53UA==/',
+            'info_dict': {
+                'id': '3011407934',
+                'ext': 'mp4',
+                'title': 'Stories from the Stage - Road Trip',
+                'duration': 1619,
+                'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': ['HTTP Error 403: Forbidden'],
+        },
         {
             'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
             'only_matching': True,
@@ -422,6 +467,8 @@ class PBSIE(InfoExtractor):
                 r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
                 r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
+                r'<div[^>]+\bdata-cove-id=["\'](\d+)"',  # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/
+                r'<iframe[^>]+\bsrc=["\'](?:https?:)?//video\.pbs\.org/widget/partnerplayer/(\d+)',  # https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/
             ]
 
             media_id = self._search_regex(
@@ -456,7 +503,8 @@ class PBSIE(InfoExtractor):
             if not url:
                 url = self._og_search_url(webpage)
 
-            mobj = re.match(self._VALID_URL, url)
+            mobj = re.match(
+                self._VALID_URL, self._proto_relative_url(url.strip()))
 
         player_id = mobj.group('player_id')
         if not display_id:
@@ -466,13 +514,27 @@ class PBSIE(InfoExtractor):
                 url, display_id, note='Downloading player page',
                 errnote='Could not download player page')
             video_id = self._search_regex(
-                r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
+                r'<div\s+id=["\']video_(\d+)', player_page, 'video ID',
+                default=None)
+            if not video_id:
+                video_info = self._extract_video_data(
+                    player_page, 'video data', display_id)
+                video_id = compat_str(
+                    video_info.get('id') or video_info['contentID'])
         else:
             video_id = mobj.group('id')
             display_id = video_id
 
         return video_id, display_id, None, description
 
+    def _extract_video_data(self, string, name, video_id, fatal=True):
+        return self._parse_json(
+            self._search_regex(
+                [r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
+                 r'window\.videoBridge\s*=\s*({.+?});'],
+                string, name, default='{}'),
+            video_id, transform_source=js_to_json, fatal=fatal)
+
     def _real_extract(self, url):
         video_id, display_id, upload_date, description = self._extract_webpage(url)
 
@@ -503,11 +565,8 @@ class PBSIE(InfoExtractor):
                 'http://player.pbs.org/%s/%s' % (page, video_id),
                 display_id, 'Downloading %s page' % page, fatal=False)
             if player:
-                video_info = self._parse_json(
-                    self._search_regex(
-                        [r'(?s)PBS\.videoData\s*=\s*({.+?});\n', r'window\.videoBridge\s*=\s*({.+?});'],
-                        player, '%s video data' % page, default='{}'),
-                    display_id, transform_source=js_to_json, fatal=False)
+                video_info = self._extract_video_data(
+                    player, '%s video data' % page, display_id, fatal=False)
                 if video_info:
                     extract_redirect_urls(video_info)
                     if not info:

youtube_dl/extractor/peertube.py

@@ -116,12 +116,14 @@ class PeerTubeIE(InfoExtractor):
                             videos\.tcit\.fr|
                             peertube\.cpy\.re
                         )'''
+    _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
     _VALID_URL = r'''(?x)
-                    https?://
-                        %s
-                        /(?:videos/(?:watch|embed)|api/v\d/videos)/
-                        (?P<id>[^/?\#&]+)
-                    ''' % _INSTANCES_RE
+                    (?:
+                        peertube:(?P<host>[^:]+):|
+                        https?://(?P<host_2>%s)/(?:videos/(?:watch|embed)|api/v\d/videos)/
+                    )
+                    (?P<id>%s)
+                    ''' % (_INSTANCES_RE, _UUID_RE)
     _TESTS = [{
         'url': 'https://peertube.moe/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c',
         'md5': '80f24ff364cc9d333529506a263e7feb',
@@ -157,21 +159,40 @@ class PeerTubeIE(InfoExtractor):
     }, {
         'url': 'https://tube.openalgeria.org/api/v1/videos/c1875674-97d0-4c94-a058-3f7e64c962e8',
         'only_matching': True,
+    }, {
+        'url': 'peertube:video.blender.org:b37a5b9f-e6b5-415c-b700-04a5cd6ec205',
+        'only_matching': True,
     }]
 
     @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'''(?x)<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//%s/videos/embed/[^/?\#&]+)\1'''
-                % PeerTubeIE._INSTANCES_RE, webpage)]
+    def _extract_peertube_url(webpage, source_url):
+        mobj = re.match(
+            r'https?://(?P<host>[^/]+)/videos/watch/(?P<id>%s)'
+            % PeerTubeIE._UUID_RE, source_url)
+        if mobj and any(p in webpage for p in (
+                '<title>PeerTube<',
+                'There will be other non JS-based clients to access PeerTube',
+                '>We are sorry but it seems that PeerTube is not compatible with your web browser.<')):
+            return 'peertube:%s:%s' % mobj.group('host', 'id')
+
+    @staticmethod
+    def _extract_urls(webpage, source_url):
+        entries = re.findall(
+            r'''(?x)<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//%s/videos/embed/%s)'''
+            % (PeerTubeIE._INSTANCES_RE, PeerTubeIE._UUID_RE), webpage)
+        if not entries:
+            peertube_url = PeerTubeIE._extract_peertube_url(webpage, source_url)
+            if peertube_url:
+                entries = [peertube_url]
+        return entries
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host') or mobj.group('host_2')
+        video_id = mobj.group('id')
 
         video = self._download_json(
-            urljoin(url, '/api/v1/videos/%s' % video_id), video_id)
+            'https://%s/api/v1/videos/%s' % (host, video_id), video_id)
 
         title = video['name']
 

youtube_dl/extractor/rbmaradio.py

@@ -53,7 +53,7 @@ class RBMARadioIE(InfoExtractor):
             'format_id': compat_str(abr),
             'abr': abr,
             'vcodec': 'none',
-        } for abr in (96, 128, 256)]
+        } for abr in (96, 128, 192, 256)]
         self._check_formats(formats, episode_id)
 
         description = clean_html(episode.get('longTeaser'))

youtube_dl/extractor/rtbf.py

@@ -1,10 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
-    int_or_none,
     ExtractorError,
+    float_or_none,
+    int_or_none,
+    strip_or_none,
 )
 
 
@@ -14,20 +18,19 @@ class RTBFIE(InfoExtractor):
         (?:
             video/[^?]+\?.*\bid=|
             ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=|
-            auvio/[^/]+\?.*id=
+            auvio/[^/]+\?.*\b(?P<live>l)?id=
         )(?P<id>\d+)'''
     _TESTS = [{
         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
-        'md5': '799f334ddf2c0a582ba80c44655be570',
+        'md5': '8c876a1cceeb6cf31b476461ade72384',
         'info_dict': {
             'id': '1921274',
             'ext': 'mp4',
             'title': 'Les Diables au coeur (épisode 2)',
-            'description': 'Football - Diables Rouges',
-            'duration': 3099,
+            'description': '(du 25/04/2014)',
+            'duration': 3099.54,
             'upload_date': '20140425',
-            'timestamp': 1398456336,
-            'uploader': 'rtbfsport',
+            'timestamp': 1398456300,
         }
     }, {
         # geo restricted
@@ -39,6 +42,18 @@ class RTBFIE(InfoExtractor):
     }, {
         'url': 'http://www.rtbf.be/auvio/detail_jeudi-en-prime-siegfried-bracke?id=2102996',
         'only_matching': True,
+    }, {
+        # Live
+        'url': 'https://www.rtbf.be/auvio/direct_pure-fm?lid=134775',
+        'only_matching': True,
+    }, {
+        # Audio
+        'url': 'https://www.rtbf.be/auvio/detail_cinq-heures-cinema?id=2360811',
+        'only_matching': True,
+    }, {
+        # With Subtitle
+        'url': 'https://www.rtbf.be/auvio/detail_les-carnets-du-bourlingueur?id=2361588',
+        'only_matching': True,
     }]
     _IMAGE_HOST = 'http://ds1.ds.static.rtbf.be'
     _PROVIDERS = {
@@ -53,46 +68,94 @@ class RTBFIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        data = self._download_json(
-            'http://www.rtbf.be/api/media/video?method=getVideoDetail&args[]=%s' % video_id, video_id)
+        live, media_id = re.match(self._VALID_URL, url).groups()
+        embed_page = self._download_webpage(
+            'https://www.rtbf.be/auvio/embed/' + ('direct' if live else 'media'),
+            media_id, query={'id': media_id})
+        data = self._parse_json(self._html_search_regex(
+            r'data-media="([^"]+)"', embed_page, 'media data'), media_id)
 
         error = data.get('error')
         if error:
             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
 
-        data = data['data']
-
         provider = data.get('provider')
         if provider in self._PROVIDERS:
             return self.url_result(data['url'], self._PROVIDERS[provider])
 
+        title = data['title']
+        is_live = data.get('isLive')
+        if is_live:
+            title = self._live_title(title)
+        height_re = r'-(\d+)p\.'
         formats = []
-        for key, format_id in self._QUALITIES:
-            format_url = data.get(key + 'Url')
-            if format_url:
+
+        m3u8_url = data.get('urlHlsAes128') or data.get('urlHls')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False))
+
+        fix_url = lambda x: x.replace('//rtbf-vod.', '//rtbf.') if '/geo/drm/' in x else x
+        http_url = data.get('url')
+        if formats and http_url and re.search(height_re, http_url):
+            http_url = fix_url(http_url)
+            for m3u8_f in formats[:]:
+                height = m3u8_f.get('height')
+                if not height:
+                    continue
+                f = m3u8_f.copy()
+                del f['protocol']
+                f.update({
+                    'format_id': m3u8_f['format_id'].replace('hls-', 'http-'),
+                    'url': re.sub(height_re, '-%dp.' % height, http_url),
+                })
+                formats.append(f)
+        else:
+            sources = data.get('sources') or {}
+            for key, format_id in self._QUALITIES:
+                format_url = sources.get(key)
+                if not format_url:
+                    continue
+                height = int_or_none(self._search_regex(
+                    height_re, format_url, 'height', default=None))
                 formats.append({
                     'format_id': format_id,
-                    'url': format_url,
+                    'url': fix_url(format_url),
+                    'height': height,
                 })
 
-        thumbnails = []
-        for thumbnail_id, thumbnail_url in data.get('thumbnail', {}).items():
-            if thumbnail_id != 'default':
-                thumbnails.append({
-                    'url': self._IMAGE_HOST + thumbnail_url,
-                    'id': thumbnail_id,
-                })
+        mpd_url = data.get('urlDash')
+        if not data.get('drm') and mpd_url:
+            formats.extend(self._extract_mpd_formats(
+                mpd_url, media_id, mpd_id='dash', fatal=False))
+
+        audio_url = data.get('urlAudio')
+        if audio_url:
+            formats.append({
+                'format_id': 'audio',
+                'url': audio_url,
+                'vcodec': 'none',
+            })
+        self._sort_formats(formats)
+
+        subtitles = {}
+        for track in (data.get('tracks') or {}).values():
+            sub_url = track.get('url')
+            if not sub_url:
+                continue
+            subtitles.setdefault(track.get('lang') or 'fr', []).append({
+                'url': sub_url,
+            })
 
         return {
-            'id': video_id,
+            'id': media_id,
             'formats': formats,
-            'title': data['title'],
-            'description': data.get('description') or data.get('subtitle'),
-            'thumbnails': thumbnails,
-            'duration': data.get('duration') or data.get('realDuration'),
-            'timestamp': int_or_none(data.get('created')),
-            'view_count': int_or_none(data.get('viewCount')),
-            'uploader': data.get('channel'),
-            'tags': data.get('tags'),
+            'title': title,
+            'description': strip_or_none(data.get('description')),
+            'thumbnail': data.get('thumbnail'),
+            'duration': float_or_none(data.get('realDuration')),
+            'timestamp': int_or_none(data.get('liveFrom')),
+            'series': data.get('programLabel'),
+            'subtitles': subtitles,
+            'is_live': is_live,
         }

youtube_dl/extractor/safari.py

@@ -74,7 +74,14 @@ class SafariBaseIE(InfoExtractor):
 class SafariIE(SafariBaseIE):
     IE_NAME = 'safari'
     IE_DESC = 'safaribooksonline.com online video'
-    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:www\.)?safaribooksonline\.com/
+                            (?:
+                                library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html|
+                                videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+)
+                            )
+                    '''
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
@@ -94,22 +101,41 @@ class SafariIE(SafariBaseIE):
     }, {
         'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314/9780134217314-PYMC_13_00',
+        'only_matching': True,
     }]
 
+    _PARTNER_ID = '1926081'
+    _UICONF_ID = '29375172'
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))
 
-        webpage = self._download_webpage(url, video_id)
-        reference_id = self._search_regex(
-            r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'kaltura reference id', group='id')
-        partner_id = self._search_regex(
-            r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'kaltura widget id', group='id')
-        ui_id = self._search_regex(
-            r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'kaltura uiconf id', group='id')
+        reference_id = mobj.group('reference_id')
+        if reference_id:
+            video_id = reference_id
+            partner_id = self._PARTNER_ID
+            ui_id = self._UICONF_ID
+        else:
+            video_id = '%s-%s' % (mobj.group('course_id'), mobj.group('part'))
+
+            webpage, urlh = self._download_webpage_handle(url, video_id)
+
+            mobj = re.match(self._VALID_URL, urlh.geturl())
+            reference_id = mobj.group('reference_id')
+            if not reference_id:
+                reference_id = self._search_regex(
+                    r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                    webpage, 'kaltura reference id', group='id')
+            partner_id = self._search_regex(
+                r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura widget id', default=self._PARTNER_ID,
+                group='id')
+            ui_id = self._search_regex(
+                r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
+                webpage, 'kaltura uiconf id', default=self._UICONF_ID,
+                group='id')
 
         query = {
             'wid': '_%s' % partner_id,
@@ -159,10 +185,15 @@ class SafariCourseIE(SafariBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
+                            (?:www\.)?safaribooksonline\.com/
+                            (?:
+                                library/view/[^/]+|
+                                api/v1/book|
+                                videos/[^/]+
+                            )|
                             techbus\.safaribooksonline\.com
                         )
-                        /(?P<id>[^/]+)/?(?:[#?]|$)
+                        /(?P<id>[^/]+)
                     '''
 
     _TESTS = [{
@@ -179,8 +210,16 @@ class SafariCourseIE(SafariBaseIE):
     }, {
         'url': 'http://techbus.safaribooksonline.com/9780134426365',
         'only_matching': True,
+    }, {
+        'url': 'https://www.safaribooksonline.com/videos/python-programming-language/9780134217314',
+        'only_matching': True,
     }]
 
+    @classmethod
+    def suitable(cls, url):
+        return (False if SafariIE.suitable(url) or SafariApiIE.suitable(url)
+                else super(SafariCourseIE, cls).suitable(url))
+
     def _real_extract(self, url):
         course_id = self._match_id(url)
 

youtube_dl/extractor/sixplay.py

@@ -19,29 +19,33 @@ from ..utils import (
 
 class SixPlayIE(InfoExtractor):
     IE_NAME = '6play'
-    _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.6play.fr/le-meilleur-patissier-p_1807/le-meilleur-patissier-special-fetes-mercredi-a-21-00-sur-m6-c_11638450',
-        'md5': '42310bffe4ba3982db112b9cd3467328',
+    _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay.be)/.+?-c_)(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
+        'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
         'info_dict': {
-            'id': '11638450',
+            'id': '12041051',
             'ext': 'mp4',
-            'title': 'Le Meilleur Pâtissier, spécial fêtes mercredi à 21:00 sur M6',
-            'description': 'md5:308853f6a5f9e2d55a30fc0654de415f',
-            'duration': 39,
-            'series': 'Le meilleur pâtissier',
+            'title': 'Le but qui a marqué l\'histoire du football français !',
+            'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851',
         },
-        'params': {
-            'skip_download': True,
-        },
-    }
+    }, {
+        'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        domain, video_id = re.search(self._VALID_URL, url).groups()
+        service, consumer_name = {
+            '6play.fr': ('6play', 'm6web'),
+            'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
+        }.get(domain, ('6play', 'm6web'))
 
         data = self._download_json(
-            'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/6play/videos/clip_%s' % video_id,
-            video_id, query={
+            'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/%s/videos/clip_%s' % (service, video_id),
+            video_id, headers={
+                'x-customer-name': consumer_name
+            }, query={
                 'csa': 5,
                 'with': 'clips',
             })
@@ -65,7 +69,14 @@ class SixPlayIE(InfoExtractor):
                 subtitles.setdefault('fr', []).append({'url': asset_url})
                 continue
             if container == 'm3u8' or ext == 'm3u8':
-                if protocol == 'usp' and not compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]:
+                if protocol == 'usp':
+                    if compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]:
+                        urlh = self._request_webpage(
+                            asset_url, video_id, fatal=False,
+                            headers=self.geo_verification_headers())
+                        if not urlh:
+                            continue
+                        asset_url = urlh.geturl()
                     asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
                     formats.extend(self._extract_m3u8_formats(
                         asset_url, video_id, 'mp4', 'm3u8_native',

youtube_dl/extractor/tf1.py

@@ -19,6 +19,7 @@ class TF1IE(InfoExtractor):
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
         },
+        'expected_warnings': ['HTTP Error 404'],
     }, {
         'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
         'info_dict': {

youtube_dl/extractor/tv4.py

@@ -1,13 +1,12 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_iso8601,
-    try_get,
-    determine_ext,
 )
 
 
@@ -78,42 +77,25 @@ class TV4IE(InfoExtractor):
 
         title = info['title']
 
-        subtitles = {}
-        formats = []
-        # http formats are linked with unresolvable host
-        for kind in ('hls3', ''):
-            data = self._download_json(
-                'https://prima.tv4play.se/api/web/asset/%s/play.json' % video_id,
-                video_id, 'Downloading sources JSON', query={
-                    'protocol': kind,
-                    'videoFormat': 'MP4+WEBVTT',
-                })
-            items = try_get(data, lambda x: x['playback']['items']['item'])
-            if not items:
-                continue
-            if isinstance(items, dict):
-                items = [items]
-            for item in items:
-                manifest_url = item.get('url')
-                if not isinstance(manifest_url, compat_str):
-                    continue
-                ext = determine_ext(manifest_url)
-                if ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                        m3u8_id=kind, fatal=False))
-                elif ext == 'f4m':
-                    formats.extend(self._extract_akamai_formats(
-                        manifest_url, video_id, {
-                            'hls': 'tv4play-i.akamaihd.net',
-                        }))
-                elif ext == 'webvtt':
-                    subtitles = self._merge_subtitles(
-                        subtitles, {
-                            'sv': [{
-                                'url': manifest_url,
-                                'ext': 'vtt',
-                            }]})
+        manifest_url = self._download_json(
+            'https://playback-api.b17g.net/media/' + video_id,
+            video_id, query={
+                'service': 'tv4',
+                'device': 'browser',
+                'protocol': 'hls',
+            })['playbackItem']['manifestUrl']
+        formats = self._extract_m3u8_formats(
+            manifest_url, video_id, 'mp4',
+            'm3u8_native', m3u8_id='hls', fatal=False)
+        formats.extend(self._extract_mpd_formats(
+            manifest_url.replace('.m3u8', '.mpd'),
+            video_id, mpd_id='dash', fatal=False))
+        formats.extend(self._extract_f4m_formats(
+            manifest_url.replace('.m3u8', '.f4m'),
+            video_id, f4m_id='hds', fatal=False))
+        formats.extend(self._extract_ism_formats(
+            re.sub(r'\.ism/.+?\.m3u8', r'.ism/Manifest', manifest_url),
+            video_id, ism_id='mss', fatal=False))
 
         if not formats and info.get('is_geo_restricted'):
             self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
@@ -124,7 +106,7 @@ class TV4IE(InfoExtractor):
             'id': video_id,
             'title': title,
             'formats': formats,
-            'subtitles': subtitles,
+            # 'subtitles': subtitles,
             'description': info.get('description'),
             'timestamp': parse_iso8601(info.get('broadcast_date_time')),
             'duration': int_or_none(info.get('duration')),

youtube_dl/extractor/tvnet.py

@@ -0,0 +1,148 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    unescapeHTML,
+)
+
+
+class TVNetIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+)\.tvnet\.gov\.vn/[^/]+/(?:\d+/)?(?P<id>\d+)(?:/|$)'
+    _TESTS = [{
+        # video
+        'url': 'http://de.tvnet.gov.vn/video/109788/vtv1---bac-tuyet-tai-lao-cai-va-ha-giang/tin-nong-24h',
+        'md5': 'b4d7abe0252c9b47774760b7519c7558',
+        'info_dict': {
+            'id': '109788',
+            'ext': 'mp4',
+            'title': 'VTV1 - Bắc tuyết tại Lào Cai và Hà Giang',
+            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
+            'is_live': False,
+            'view_count': int,
+        },
+    }, {
+        # audio
+        'url': 'http://vn.tvnet.gov.vn/radio/27017/vov1---ban-tin-chieu-10062018/doi-song-va-xa-hoi',
+        'md5': 'b5875ce9b0a2eecde029216d0e6db2ae',
+        'info_dict': {
+            'id': '27017',
+            'ext': 'm4a',
+            'title': 'VOV1 - Bản tin chiều (10/06/2018)',
+            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
+            'is_live': False,
+        },
+    }, {
+        'url': 'http://us.tvnet.gov.vn/video/118023/129999/ngay-0705',
+        'info_dict': {
+            'id': '129999',
+            'ext': 'mp4',
+            'title': 'VTV1 - Quốc hội với cử tri (11/06/2018)',
+            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
+            'is_live': False,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # live stream
+        'url': 'http://us.tvnet.gov.vn/kenh-truyen-hinh/1011/vtv1',
+        'info_dict': {
+            'id': '1011',
+            'ext': 'mp4',
+            'title': r're:^VTV1 \| LiveTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # radio live stream
+        'url': 'http://vn.tvnet.gov.vn/kenh-truyen-hinh/1014',
+        'info_dict': {
+            'id': '1014',
+            'ext': 'm4a',
+            'title': r're:VOV1 \| LiveTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'thumbnail': r're:(?i)https?://.*\.(?:jpg|png)',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://us.tvnet.gov.vn/phim/6136/25510/vtv3---ca-mot-doi-an-oan-tap-1-50/phim-truyen-hinh',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(
+            webpage, default=None) or self._html_search_meta(
+            'title', webpage, default=None) or self._search_regex(
+            r'<title>([^<]+)<', webpage, 'title')
+        title = re.sub(r'\s*-\s*TV Net\s*$', '', title)
+
+        if '/video/' in url or '/radio/' in url:
+            is_live = False
+        elif '/kenh-truyen-hinh/' in url:
+            is_live = True
+        else:
+            is_live = None
+
+        data_file = unescapeHTML(self._search_regex(
+            r'data-file=(["\'])(?P<url>(?:https?:)?//.+?)\1', webpage,
+            'data file', group='url'))
+
+        stream_urls = set()
+        formats = []
+        for stream in self._download_json(data_file, video_id):
+            if not isinstance(stream, dict):
+                continue
+            stream_url = stream.get('url')
+            if (stream_url in stream_urls or not stream_url or
+                    not isinstance(stream_url, compat_str)):
+                continue
+            stream_urls.add(stream_url)
+            formats.extend(self._extract_m3u8_formats(
+                stream_url, video_id, 'mp4',
+                entry_protocol='m3u8' if is_live else 'm3u8_native',
+                m3u8_id='hls', fatal=False))
+        self._sort_formats(formats)
+
+        # better support for radio streams
+        if title.startswith('VOV'):
+            for f in formats:
+                f.update({
+                    'ext': 'm4a',
+                    'vcodec': 'none',
+                })
+
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None) or unescapeHTML(
+            self._search_regex(
+                r'data-image=(["\'])(?P<url>(?:https?:)?//.+?)\1', webpage,
+                'thumbnail', default=None, group='url'))
+
+        if is_live:
+            title = self._live_title(title)
+
+        view_count = int_or_none(self._search_regex(
+            r'(?s)<div[^>]+\bclass=["\'].*?view-count[^>]+>.*?(\d+).*?</div>',
+            webpage, 'view count', default=None))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'is_live': is_live,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/tvnow.py

@@ -19,8 +19,8 @@ class TVNowBaseIE(InfoExtractor):
     _VIDEO_FIELDS = (
         'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort',
         'broadcastStartDate', 'isDrm', 'duration', 'season', 'episode',
-        'manifest.dashclear', 'format.title', 'format.defaultImage169Format',
-        'format.defaultImage169Logo')
+        'manifest.dashclear', 'manifest.hlsclear', 'manifest.smoothclear',
+        'format.title', 'format.defaultImage169Format', 'format.defaultImage169Logo')
 
     def _call_api(self, path, video_id, query):
         return self._download_json(
@@ -31,27 +31,42 @@ class TVNowBaseIE(InfoExtractor):
         video_id = compat_str(info['id'])
         title = info['title']
 
-        mpd_url = info['manifest']['dashclear']
-        if not mpd_url:
+        paths = []
+        for manifest_url in (info.get('manifest') or {}).values():
+            if not manifest_url:
+                continue
+            manifest_url = update_url_query(manifest_url, {'filter': ''})
+            path = self._search_regex(r'https?://[^/]+/(.+?)\.ism/', manifest_url, 'path')
+            if path in paths:
+                continue
+            paths.append(path)
+
+            def url_repl(proto, suffix):
+                return re.sub(
+                    r'(?:hls|dash|hss)([.-])', proto + r'\1', re.sub(
+                        r'\.ism/(?:[^.]*\.(?:m3u8|mpd)|[Mm]anifest)',
+                        '.ism/' + suffix, manifest_url))
+
+            formats = self._extract_mpd_formats(
+                url_repl('dash', '.mpd'), video_id,
+                mpd_id='dash', fatal=False)
+            formats.extend(self._extract_ism_formats(
+                url_repl('hss', 'Manifest'),
+                video_id, ism_id='mss', fatal=False))
+            formats.extend(self._extract_m3u8_formats(
+                url_repl('hls', '.m3u8'), video_id, 'mp4',
+                'm3u8_native', m3u8_id='hls', fatal=False))
+            if formats:
+                break
+        else:
             if info.get('isDrm'):
                 raise ExtractorError(
                     'Video %s is DRM protected' % video_id, expected=True)
             if info.get('geoblocked'):
-                raise ExtractorError(
-                    'Video %s is not available from your location due to geo restriction' % video_id,
-                    expected=True)
+                raise self.raise_geo_restricted()
             if not info.get('free', True):
                 raise ExtractorError(
                     'Video %s is not available for free' % video_id, expected=True)
-
-        mpd_url = update_url_query(mpd_url, {'filter': ''})
-        formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False)
-        formats.extend(self._extract_ism_formats(
-            mpd_url.replace('dash.', 'hss.').replace('/.mpd', '/Manifest'),
-            video_id, ism_id='mss', fatal=False))
-        formats.extend(self._extract_m3u8_formats(
-            mpd_url.replace('dash.', 'hls.').replace('/.mpd', '/.m3u8'),
-            video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
         self._sort_formats(formats)
 
         description = info.get('articleLong') or info.get('articleShort')
@@ -88,7 +103,7 @@ class TVNowBaseIE(InfoExtractor):
 class TVNowIE(TVNowBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:www\.)?tvnow\.(?:de|at|ch)/[^/]+/
+                        (?:www\.)?tvnow\.(?:de|at|ch)/(?P<station>[^/]+)/
                         (?P<show_id>[^/]+)/
                         (?!(?:list|jahr)(?:/|$))(?P<id>[^/?\#&]+)
                     '''
@@ -140,11 +155,13 @@ class TVNowIE(TVNowBaseIE):
     }]
 
     def _real_extract(self, url):
-        display_id = '%s/%s' % re.match(self._VALID_URL, url).groups()
+        mobj = re.match(self._VALID_URL, url)
+        display_id = '%s/%s' % mobj.group(2, 3)
 
         info = self._call_api(
             'movies/' + display_id, display_id, query={
                 'fields': ','.join(self._VIDEO_FIELDS),
+                'station': mobj.group(1),
             })
 
         return self._extract_video(info, display_id)

youtube_dl/extractor/twitter.py

@@ -108,6 +108,8 @@ class TwitterCardIE(TwitterBaseIE):
         },
     ]
 
+    _API_BASE = 'https://api.twitter.com/1.1'
+
     def _parse_media_info(self, media_info, video_id):
         formats = []
         for media_variant in media_info.get('variants', []):
@@ -149,7 +151,7 @@ class TwitterCardIE(TwitterBaseIE):
             main_script, 'bearer token')
         # https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id
         api_data = self._download_json(
-            'https://api.twitter.com/1.1/statuses/show/%s.json' % video_id,
+            '%s/statuses/show/%s.json' % (self._API_BASE, video_id),
             video_id, 'Downloading API data',
             headers={
                 'Authorization': 'Bearer ' + bearer_token,
@@ -229,11 +231,22 @@ class TwitterCardIE(TwitterBaseIE):
                 break
 
         if not formats:
+            headers = {
+                'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw',
+                'Referer': url,
+            }
+            ct0 = self._get_cookies(url).get('ct0')
+            if ct0:
+                headers['csrf_token'] = ct0.value
+            guest_token = self._download_json(
+                '%s/guest/activate.json' % self._API_BASE, video_id,
+                'Downloading guest token', data=b'',
+                headers=headers)['guest_token']
+            headers['x-guest-token'] = guest_token
+            self._set_cookie('api.twitter.com', 'gt', guest_token)
             config = self._download_json(
-                'https://api.twitter.com/1.1/videos/tweet/config/%s.json' % video_id,
-                video_id, headers={
-                    'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAIK1zgAAAAAA2tUWuhGZ2JceoId5GwYWU5GspY4%3DUq7gzFoCZs1QfwGoVdvSac3IniczZEYXIcDyumCauIXpcAPorE',
-                })
+                '%s/videos/tweet/config/%s.json' % (self._API_BASE, video_id),
+                video_id, headers=headers)
             track = config['track']
             vmap_url = track.get('vmapUrl')
             if vmap_url:

youtube_dl/extractor/vgtv.py

@@ -24,6 +24,7 @@ class VGTVIE(XstreamIE):
         'aftenposten.no/webtv': 'aptv',
         'ap.vgtv.no/webtv': 'aptv',
         'tv.aftonbladet.se/abtv': 'abtv',
+        'www.aftonbladet.se/tv': 'abtv',
     }
 
     _APP_NAME_TO_VENDOR = {
@@ -44,7 +45,7 @@ class VGTVIE(XstreamIE):
                     (?:
                         (?:\#!/)?(?:video|live)/|
                         embed?.*id=|
-                        articles/
+                        a(?:rticles)?/
                     )|
                     (?P<appname>
                         %s
@@ -143,6 +144,10 @@ class VGTVIE(XstreamIE):
             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
             'only_matching': True,
         },
+        {
+            'url': 'https://www.aftonbladet.se/tv/a/36015',
+            'only_matching': True,
+        },
         {
             'url': 'abtv:140026',
             'only_matching': True,
@@ -178,13 +183,15 @@ class VGTVIE(XstreamIE):
 
         streams = data['streamUrls']
         stream_type = data.get('streamType')
-
+        is_live = stream_type == 'live'
         formats = []
 
         hls_url = streams.get('hls')
         if hls_url:
             formats.extend(self._extract_m3u8_formats(
-                hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                hls_url, video_id, 'mp4',
+                entry_protocol='m3u8' if is_live else 'm3u8_native',
+                m3u8_id='hls', fatal=False))
 
         hds_url = streams.get('hds')
         if hds_url:
@@ -229,13 +236,13 @@ class VGTVIE(XstreamIE):
 
         info.update({
             'id': video_id,
-            'title': self._live_title(data['title']) if stream_type == 'live' else data['title'],
+            'title': self._live_title(data['title']) if is_live else data['title'],
             'description': data['description'],
             'thumbnail': data['images']['main'] + '?t[]=900x506q80',
             'timestamp': data['published'],
             'duration': float_or_none(data['duration'], 1000),
             'view_count': data['displays'],
-            'is_live': True if stream_type == 'live' else False,
+            'is_live': is_live,
         })
         return info
 

youtube_dl/extractor/vidzi.py

@@ -54,7 +54,8 @@ class VidziIE(InfoExtractor):
                 self._search_regex(
                     r'setup\(([^)]+)\)', code, 'jwplayer data',
                     default=NO_DEFAULT if num == len(codes) else '{}'),
-                video_id, transform_source=js_to_json)
+                video_id, transform_source=lambda s: js_to_json(
+                    re.sub(r'\s*\+\s*window\[.+?\]', '', s)))
             if jwplayer_data:
                 break
 

youtube_dl/extractor/wat.py

@@ -19,7 +19,6 @@ class WatIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
-            'md5': '83d882d9de5c9d97f0bb2c6273cde56a',
             'info_dict': {
                 'id': '11713067',
                 'ext': 'mp4',
@@ -28,10 +27,15 @@ class WatIE(InfoExtractor):
                 'upload_date': '20140819',
                 'duration': 120,
             },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+            'expected_warnings': ['HTTP Error 404'],
         },
         {
             'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
-            'md5': '34bdfa5ca9fd3c7eb88601b635b0424c',
+            'md5': 'b16574df2c3cd1a36ca0098f2a791925',
             'info_dict': {
                 'id': '11713075',
                 'ext': 'mp4',
@@ -98,38 +102,25 @@ class WatIE(InfoExtractor):
 
         formats = []
         try:
+            alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')]
             manifest_urls = self._download_json(
                 'http://www.wat.tv/get/webhtml/' + video_id, video_id)
             m3u8_url = manifest_urls.get('hls')
             if m3u8_url:
                 m3u8_url = remove_bitrate_limit(m3u8_url)
-                m3u8_formats = self._extract_m3u8_formats(
-                    m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                for m3u8_alt_url in alt_urls(m3u8_url):
+                    formats.extend(self._extract_m3u8_formats(
+                        m3u8_alt_url, video_id, 'mp4',
+                        'm3u8_native', m3u8_id='hls', fatal=False))
                     formats.extend(self._extract_f4m_formats(
-                        m3u8_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
+                        m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
                         video_id, f4m_id='hds', fatal=False))
-                    http_url = extract_url('android5/%s.mp4', 'http')
-                    if http_url:
-                        for m3u8_format in m3u8_formats:
-                            vbr, abr = m3u8_format.get('vbr'), m3u8_format.get('abr')
-                            if not vbr or not abr:
-                                continue
-                            format_id = m3u8_format['format_id'].replace('hls', 'http')
-                            fmt_url = re.sub(r'%s-\d+00-\d+' % video_id, '%s-%d00-%d' % (video_id, round(vbr / 100), round(abr)), http_url)
-                            if self._is_valid_url(fmt_url, video_id, format_id):
-                                f = m3u8_format.copy()
-                                f.update({
-                                    'url': fmt_url,
-                                    'format_id': format_id,
-                                    'protocol': 'http',
-                                })
-                                formats.append(f)
             mpd_url = manifest_urls.get('mpd')
             if mpd_url:
-                formats.extend(self._extract_mpd_formats(remove_bitrate_limit(
-                    mpd_url), video_id, mpd_id='dash', fatal=False))
+                mpd_url = remove_bitrate_limit(mpd_url)
+                for mpd_alt_url in alt_urls(mpd_url):
+                    formats.extend(self._extract_mpd_formats(
+                        mpd_alt_url, video_id, mpd_id='dash', fatal=False))
             self._sort_formats(formats)
         except ExtractorError:
             abr = 64

youtube_dl/extractor/wimp.py

@@ -36,7 +36,8 @@ class WimpIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         youtube_id = self._search_regex(
-            r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']",
+            (r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']",
+             r'data-id=["\']([0-9A-Za-z_-]{11})'),
             webpage, 'video URL', default=None)
         if youtube_id:
             return {

youtube_dl/extractor/youtube.py

@@ -510,6 +510,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
                 'license': 'Standard YouTube License',
                 'creator': 'Icona Pop',
+                'track': 'I Love It (feat. Charli XCX)',
+                'artist': 'Icona Pop',
             }
         },
         {
@@ -528,6 +530,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
                 'license': 'Standard YouTube License',
                 'creator': 'Justin Timberlake',
+                'track': 'Tunnel Vision',
+                'artist': 'Justin Timberlake',
                 'age_limit': 18,
             }
         },
@@ -597,7 +601,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': 'IB3lcPjvWLA',
                 'ext': 'm4a',
                 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
-                'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
+                'description': 'md5:1900ed86ee514927b9e00fbead6969a5',
                 'duration': 244,
                 'uploader': 'AfrojackVEVO',
                 'uploader_id': 'AfrojackVEVO',
@@ -638,7 +642,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'ext': 'mp4',
                 'duration': 219,
                 'upload_date': '20100909',
-                'uploader': 'The Amazing Atheist',
+                'uploader': 'TJ Kirk',
                 'uploader_id': 'TheAmazingAtheist',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
                 'license': 'Standard YouTube License',
@@ -668,10 +672,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
             'info_dict': {
                 'id': '6kLq3WMV1nU',
-                'ext': 'mp4',
+                'ext': 'webm',
                 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
                 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
-                'duration': 247,
+                'duration': 246,
                 'uploader': 'LloydVEVO',
                 'uploader_id': 'LloydVEVO',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
@@ -733,7 +737,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': 'AllenMeow',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
                 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
-                'uploader': '孫艾倫',
+                'uploader': '孫ᄋᄅ',
                 'license': 'Standard YouTube License',
                 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
             },
@@ -760,7 +764,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
             'info_dict': {
                 'id': 'FIl7x6_3R5Y',
-                'ext': 'mp4',
+                'ext': 'webm',
                 'title': 'md5:7b81415841e02ecd4313668cde88737a',
                 'description': 'md5:116377fd2963b81ec4ce64b542173306',
                 'duration': 220,
@@ -769,8 +773,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
                 'uploader': 'dorappi2000',
                 'license': 'Standard YouTube License',
-                'formats': 'mincount:32',
+                'formats': 'mincount:31',
             },
+            'skip': 'not actual anymore',
         },
         # DASH manifest with segment_list
         {
@@ -885,7 +890,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': 'lsguqyKfVQg',
                 'ext': 'mp4',
                 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
-                'alt_title': 'Dark Walk',
+                'alt_title': 'Dark Walk - Position Music',
                 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
                 'duration': 133,
                 'upload_date': '20151119',
@@ -893,7 +898,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
                 'uploader': 'IronSoulElf',
                 'license': 'Standard YouTube License',
-                'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
+                'creator': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
+                'track': 'Dark Walk - Position Music',
+                'artist': 'Todd Haberman,  Daniel Law Heath and Aaron Kaplan',
             },
             'params': {
                 'skip_download': True,
@@ -950,7 +957,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
                 'duration': 4060,
                 'upload_date': '20151119',
-                'uploader': 'Bernie 2016',
+                'uploader': 'Bernie Sanders',
                 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
                 'license': 'Creative Commons Attribution license (reuse allowed)',
@@ -985,6 +992,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'params': {
                 'skip_download': True,
             },
+            'skip': 'This video is not available.',
         },
         {
             # YouTube Red video with episode data
@@ -993,7 +1001,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'id': 'iqKdEhx-dD4',
                 'ext': 'mp4',
                 'title': 'Isolation - Mind Field (Ep 1)',
-                'description': 'md5:8013b7ddea787342608f63a13ddc9492',
+                'description': 'md5:25b78d2f64ae81719f5c96319889b736',
                 'duration': 2085,
                 'upload_date': '20170118',
                 'uploader': 'Vsauce',
@@ -1026,7 +1034,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
                 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
                 'license': 'Standard YouTube License',
-                'view_count': int,
             },
             'params': {
                 'skip_download': True,
@@ -1694,128 +1701,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
             raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True)
 
-        # Start extracting information
-        self.report_information_extraction(video_id)
-
-        # uploader
-        video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str)
-        if video_uploader:
-            video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
-        else:
-            self._downloader.report_warning('unable to extract uploader name')
-
-        # uploader_id
-        video_uploader_id = None
-        video_uploader_url = None
-        mobj = re.search(
-            r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
-            video_webpage)
-        if mobj is not None:
-            video_uploader_id = mobj.group('uploader_id')
-            video_uploader_url = mobj.group('uploader_url')
-        else:
-            self._downloader.report_warning('unable to extract uploader nickname')
-
-        # thumbnail image
-        # We try first to get a high quality image:
-        m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
-                            video_webpage, re.DOTALL)
-        if m_thumb is not None:
-            video_thumbnail = m_thumb.group(1)
-        elif 'thumbnail_url' not in video_info:
-            self._downloader.report_warning('unable to extract video thumbnail')
-            video_thumbnail = None
-        else:   # don't panic if we can't find it
-            video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
-
-        # upload date
-        upload_date = self._html_search_meta(
-            'datePublished', video_webpage, 'upload date', default=None)
-        if not upload_date:
-            upload_date = self._search_regex(
-                [r'(?s)id="eow-date.*?>(.*?)</span>',
-                 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
-                video_webpage, 'upload date', default=None)
-        upload_date = unified_strdate(upload_date)
-
-        video_license = self._html_search_regex(
-            r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
-            video_webpage, 'license', default=None)
-
-        m_music = re.search(
-            r'''(?x)
-                <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
-                <ul[^>]*>\s*
-                <li>(?P<title>.+?)
-                by (?P<creator>.+?)
-                (?:
-                    \(.+?\)|
-                    <a[^>]*
-                        (?:
-                            \bhref=["\']/red[^>]*>|             # drop possible
-                            >\s*Listen ad-free with YouTube Red # YouTube Red ad
-                        )
-                    .*?
-                )?</li
-            ''',
-            video_webpage)
-        if m_music:
-            video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
-            video_creator = clean_html(m_music.group('creator'))
-        else:
-            video_alt_title = video_creator = None
-
-        m_episode = re.search(
-            r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
-            video_webpage)
-        if m_episode:
-            series = m_episode.group('series')
-            season_number = int(m_episode.group('season'))
-            episode_number = int(m_episode.group('episode'))
-        else:
-            series = season_number = episode_number = None
-
-        m_cat_container = self._search_regex(
-            r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
-            video_webpage, 'categories', default=None)
-        if m_cat_container:
-            category = self._html_search_regex(
-                r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
-                default=None)
-            video_categories = None if category is None else [category]
-        else:
-            video_categories = None
-
-        video_tags = [
-            unescapeHTML(m.group('content'))
-            for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
-
-        def _extract_count(count_name):
-            return str_to_int(self._search_regex(
-                r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
-                % re.escape(count_name),
-                video_webpage, count_name, default=None))
-
-        like_count = _extract_count('like')
-        dislike_count = _extract_count('dislike')
-
-        # subtitles
-        video_subtitles = self.extract_subtitles(video_id, video_webpage)
-        automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
-
-        video_duration = try_get(
-            video_info, lambda x: int_or_none(x['length_seconds'][0]))
-        if not video_duration:
-            video_duration = parse_duration(self._html_search_meta(
-                'duration', video_webpage, 'video duration'))
-
-        # annotations
-        video_annotations = None
-        if self._downloader.params.get('writeannotations', False):
-            video_annotations = self._extract_annotations(video_id)
-
-        chapters = self._extract_chapters(description_original, video_duration)
-
         def _extract_filesize(media_url):
             return int_or_none(self._search_regex(
                 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
@@ -1990,6 +1875,133 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 raise ExtractorError(error_message, expected=True)
             raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
 
+        # uploader
+        video_uploader = try_get(video_info, lambda x: x['author'][0], compat_str)
+        if video_uploader:
+            video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
+        else:
+            self._downloader.report_warning('unable to extract uploader name')
+
+        # uploader_id
+        video_uploader_id = None
+        video_uploader_url = None
+        mobj = re.search(
+            r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
+            video_webpage)
+        if mobj is not None:
+            video_uploader_id = mobj.group('uploader_id')
+            video_uploader_url = mobj.group('uploader_url')
+        else:
+            self._downloader.report_warning('unable to extract uploader nickname')
+
+        # thumbnail image
+        # We try first to get a high quality image:
+        m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
+                            video_webpage, re.DOTALL)
+        if m_thumb is not None:
+            video_thumbnail = m_thumb.group(1)
+        elif 'thumbnail_url' not in video_info:
+            self._downloader.report_warning('unable to extract video thumbnail')
+            video_thumbnail = None
+        else:   # don't panic if we can't find it
+            video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
+
+        # upload date
+        upload_date = self._html_search_meta(
+            'datePublished', video_webpage, 'upload date', default=None)
+        if not upload_date:
+            upload_date = self._search_regex(
+                [r'(?s)id="eow-date.*?>(.*?)</span>',
+                 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
+                video_webpage, 'upload date', default=None)
+        upload_date = unified_strdate(upload_date)
+
+        video_license = self._html_search_regex(
+            r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
+            video_webpage, 'license', default=None)
+
+        m_music = re.search(
+            r'''(?x)
+                <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
+                <ul[^>]*>\s*
+                <li>(?P<title>.+?)
+                by (?P<creator>.+?)
+                (?:
+                    \(.+?\)|
+                    <a[^>]*
+                        (?:
+                            \bhref=["\']/red[^>]*>|             # drop possible
+                            >\s*Listen ad-free with YouTube Red # YouTube Red ad
+                        )
+                    .*?
+                )?</li
+            ''',
+            video_webpage)
+        if m_music:
+            video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
+            video_creator = clean_html(m_music.group('creator'))
+        else:
+            video_alt_title = video_creator = None
+
+        def extract_meta(field):
+            return self._html_search_regex(
+                r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
+                video_webpage, field, default=None)
+
+        track = extract_meta('Song')
+        artist = extract_meta('Artist')
+
+        m_episode = re.search(
+            r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
+            video_webpage)
+        if m_episode:
+            series = m_episode.group('series')
+            season_number = int(m_episode.group('season'))
+            episode_number = int(m_episode.group('episode'))
+        else:
+            series = season_number = episode_number = None
+
+        m_cat_container = self._search_regex(
+            r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
+            video_webpage, 'categories', default=None)
+        if m_cat_container:
+            category = self._html_search_regex(
+                r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
+                default=None)
+            video_categories = None if category is None else [category]
+        else:
+            video_categories = None
+
+        video_tags = [
+            unescapeHTML(m.group('content'))
+            for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
+
+        def _extract_count(count_name):
+            return str_to_int(self._search_regex(
+                r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
+                % re.escape(count_name),
+                video_webpage, count_name, default=None))
+
+        like_count = _extract_count('like')
+        dislike_count = _extract_count('dislike')
+
+        # subtitles
+        video_subtitles = self.extract_subtitles(video_id, video_webpage)
+        automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
+
+        video_duration = try_get(
+            video_info, lambda x: int_or_none(x['length_seconds'][0]))
+        if not video_duration:
+            video_duration = parse_duration(self._html_search_meta(
+                'duration', video_webpage, 'video duration'))
+
+        # annotations
+        video_annotations = None
+        if self._downloader.params.get('writeannotations', False):
+            video_annotations = self._extract_annotations(video_id)
+
+        chapters = self._extract_chapters(description_original, video_duration)
+
         # Look for the DASH manifest
         if self._downloader.params.get('youtube_include_dash_manifest', True):
             dash_mpd_fatal = True
@@ -2055,9 +2067,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'uploader_url': video_uploader_url,
             'upload_date': upload_date,
             'license': video_license,
-            'creator': video_creator,
+            'creator': video_creator or artist,
             'title': video_title,
-            'alt_title': video_alt_title,
+            'alt_title': video_alt_title or track,
             'thumbnail': video_thumbnail,
             'description': video_description,
             'categories': video_categories,
@@ -2080,6 +2092,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'series': series,
             'season_number': season_number,
             'episode_number': episode_number,
+            'track': track,
+            'artist': artist,
         }
 
 

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2018.06.02'
+__version__ = '2018.06.19'