release 2016.09.18

- Eliminate segment_urls and initialization_url
+ Introduce manifest_url (manifest may contain unfragmented data in this case url will be used for direct media URL and manifest_url for manifest itself correspondingly)
* Rewrite dashsegments downloader to use fragments data
* Improve generic mpd extraction

.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 *2016.09.08*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.18*. 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 Issues with outdated version will be rejected.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 **2016.09.08**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.09.18**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.09.08
+[debug] youtube-dl version 2016.09.18
 [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: {}
@@ -55,4 +55,4 @@ $ youtube-dl -v <your command line>
 ### Description of your *issue*, suggested solution and other information
 
 Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
-If work on your *issue* required an account credentials please provide them or explain how one can obtain them.
+If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

.github/ISSUE_TEMPLATE_tmpl.md

@@ -55,4 +55,4 @@ $ youtube-dl -v <your command line>
 ### Description of your *issue*, suggested solution and other information
 
 Explanation of your *issue* in arbitrary form goes here. Please make sure the [description is worded well enough to be understood](https://github.com/rg3/youtube-dl#is-the-description-of-the-issue-itself-sufficient). Provide as much context and examples as possible.
-If work on your *issue* required an account credentials please provide them or explain how one can obtain them.
+If work on your *issue* requires account credentials please provide them or explain how one can obtain them.

ChangeLog

@@ -1,3 +1,72 @@
+version 2016.09.18
+
+Core
++ Introduce manifest_url and fragments fields in formats dictionary for
+  fragmented media
++ Provide manifest_url field for DASH segments, HLS and HDS
++ Provide fragments field for DASH segments
+* Rework DASH segments downloader to use fragments field
++ Add helper method for Wowza Streaming Engine formats extraction
+
+Extractors
++ [vyborymos] Add extractor for vybory.mos.ru (#10692)
++ [xfileshare] Add title regular expression for streamin.to (#10646)
++ [globo:article] Add support for multiple videos (#10653)
++ [thisav] Recognize HTML5 videos (#10447)
+* [jwplatform] Improve JWPlayer detection
++ [mangomolo] Add support for Mangomolo embeds
++ [toutv] Add support for authentication (#10669)
+* [franceinter] Fix upload date extraction
+* [tv4] Fix HLS and HDS formats extraction (#10659)
+
+
+version 2016.09.15
+
+Core
+* Improve _hidden_inputs
++ Introduce improved explicit Adobe Pass support
++ Add --ap-mso to provide multiple-system operator identifier
++ Add --ap-username to provide MSO account username
++ Add --ap-password to provide MSO account password
++ Add --ap-list-mso to list all supported MSOs
++ Add support for Rogers Cable multiple-system operator (#10606)
+
+Extractors
+* [crunchyroll] Fix authentication (#10655)
+* [twitch] Fix API calls (#10654, #10660)
++ [bellmedia] Add support for more Bell Media Television sites
+* [franceinter] Fix extraction (#10538, #2105)
+* [kuwo] Improve error detection (#10650)
++ [go] Add support for free full episodes (#10439)
+* [bilibili] Fix extraction for specific videos (#10647)
+* [nhk] Fix extraction (#10633)
+* [kaltura] Improve audio detection
+* [kaltura] Skip chun format
++ [vimeo:ondemand] Pass Referer along with embed URL (#10624)
++ [nbc] Add support for NBC Olympics (#10361)
+
+
+version 2016.09.11.1
+
+Extractors
++ [tube8] Extract categories and tags (#10579)
++ [pornhub] Extract categories and tags (#10499)
+* [openload] Temporary fix (#10408)
++ [foxnews] Add support Fox News articles (#10598)
+* [viafree] Improve video id extraction (#10615)
+* [iwara] Fix extraction after relaunch (#10462, #3215)
++ [tfo] Add extractor for tfo.org
+* [lrt] Fix audio extraction (#10566)
+* [9now] Fix extraction (#10561)
++ [canalplus] Add support for c8.fr (#10577)
+* [newgrounds] Fix uploader extraction (#10584)
++ [polskieradio:category] Add support for category lists (#10576)
++ [ketnet] Add extractor for ketnet.be (#10343)
++ [canvas] Add support for een.be (#10605)
++ [telequebec] Add extractor for telequebec.tv (#1999)
+* [parliamentliveuk] Fix extraction (#9137)
+
+
 version 2016.09.08
 
 Extractors

README.md

@@ -358,6 +358,17 @@ which means you can modify it, redistribute it or use it however you like.
     -n, --netrc                      Use .netrc authentication data
     --video-password PASSWORD        Video password (vimeo, smotri, youku)
 
+## Adobe Pass Options:
+    --ap-mso MSO                     Adobe Pass multiple-system operator (TV
+                                     provider) identifier, use --ap-list-mso for
+                                     a list of available MSOs
+    --ap-username USERNAME           Multiple-system operator account login
+    --ap-password PASSWORD           Multiple-system operator account password.
+                                     If this option is left out, youtube-dl will
+                                     ask interactively.
+    --ap-list-mso                    List all supported multiple-system
+                                     operators
+
 ## Post-processing Options:
     -x, --extract-audio              Convert video files to audio-only files
                                      (requires ffmpeg or avconv and ffprobe or

devscripts/release.sh

@@ -60,6 +60,9 @@ if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; e
 if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
 if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
 
+read -p "Is ChangeLog up to date? (y/n) " -n 1
+if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
+
 /bin/echo -e "\n### First of all, testing..."
 make clean
 if $skip_tests ; then

docs/supportedsites.md

@@ -89,6 +89,7 @@
  - **BeatportPro**
  - **Beeg**
  - **BehindKink**
+ - **BellMedia**
  - **Bet**
  - **Bigflix**
  - **Bild**: Bild.de
@@ -169,7 +170,6 @@
  - **CSNNE**
  - **CSpan**: C-SPAN
  - **CtsNews**: 華視新聞
- - **CTV**
  - **CTVNews**
  - **culturebox.francetvinfo.fr**
  - **CultureUnplugged**
@@ -247,7 +247,8 @@
  - **Formula1**
  - **FOX**
  - **Foxgay**
- - **FoxNews**: Fox News and Fox Business Video
+ - **foxnews**: Fox News and Fox Business Video
+ - **foxnews:article**
  - **foxnews:insider**
  - **FoxSports**
  - **france2.fr:generation-quoi**
@@ -326,6 +327,7 @@
  - **ivi**: ivi.ru
  - **ivi:compilation**: ivi.ru compilations
  - **ivideon**: Ivideon TV
+ - **Iwara**
  - **Izlesene**
  - **JeuxVideo**
  - **Jove**
@@ -339,6 +341,7 @@
  - **KarriereVideos**
  - **keek**
  - **KeezMovies**
+ - **Ketnet**
  - **KhanAcademy**
  - **KickStarter**
  - **KonserthusetPlay**
@@ -385,6 +388,8 @@
  - **mailru**: Видео@Mail.Ru
  - **MakersChannel**
  - **MakerTV**
+ - **mangomolo:live**
+ - **mangomolo:video**
  - **MatchTV**
  - **MDR**: MDR.DE and KiKA
  - **media.ccc.de**
@@ -442,6 +447,7 @@
  - **NBA**
  - **NBC**
  - **NBCNews**
+ - **NBCOlympics**
  - **NBCSports**
  - **NBCSportsVPlayer**
  - **ndr**: NDR.de - Norddeutscher Rundfunk
@@ -540,6 +546,7 @@
  - **podomatic**
  - **Pokemon**
  - **PolskieRadio**
+ - **PolskieRadioCategory**
  - **PornCom**
  - **PornHd**
  - **PornHub**: PornHub and Thumbzilla
@@ -701,9 +708,11 @@
  - **Telecinco**: telecinco.es, cuatro.com and mediaset.es
  - **Telegraaf**
  - **TeleMB**
+ - **TeleQuebec**
  - **TeleTask**
  - **Telewebion**
  - **TF1**
+ - **TFO**
  - **TheIntercept**
  - **ThePlatform**
  - **ThePlatformFeed**
@@ -725,7 +734,6 @@
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict** (Currently broken)
  - **Trilulilu**
- - **trollvids**
  - **TruTV**
  - **Tube8**
  - **TubiTv**
@@ -843,6 +851,7 @@
  - **VRT**
  - **vube**: Vube.com
  - **VuClip**
+ - **VyboryMos**
  - **Walla**
  - **washingtonpost**
  - **washingtonpost:article**

test/test_utils.py

@@ -40,6 +40,7 @@ from youtube_dl.utils import (
     js_to_json,
     limit_length,
     mimetype2ext,
+    month_by_name,
     ohdave_rsa_encrypt,
     OnDemandPagedList,
     orderedSet,
@@ -634,6 +635,14 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
         self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
 
+    def test_month_by_name(self):
+        self.assertEqual(month_by_name(None), None)
+        self.assertEqual(month_by_name('December', 'en'), 12)
+        self.assertEqual(month_by_name('décembre', 'fr'), 12)
+        self.assertEqual(month_by_name('December'), 12)
+        self.assertEqual(month_by_name('décembre'), None)
+        self.assertEqual(month_by_name('Unknown', 'unknown'), None)
+
     def test_parse_codecs(self):
         self.assertEqual(parse_codecs(''), {})
         self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {

youtube_dl/YoutubeDL.py

@@ -131,6 +131,9 @@ class YoutubeDL(object):
     username:          Username for authentication purposes.
     password:          Password for authentication purposes.
     videopassword:     Password for accessing a video.
+    ap_mso:            Adobe Pass multiple-system operator identifier.
+    ap_username:       Multiple-system operator account username.
+    ap_password:       Multiple-system operator account password.
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.

youtube_dl/__init__.py

@@ -34,12 +34,14 @@ from .utils import (
     setproctitle,
     std_headers,
     write_string,
+    render_table,
 )
 from .update import update_self
 from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors, list_extractors
+from .extractor.adobepass import MSO_INFO
 from .YoutubeDL import YoutubeDL
 
 
@@ -118,18 +120,26 @@ def _real_main(argv=None):
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
             write_string(desc + '\n', out=sys.stdout)
         sys.exit(0)
+    if opts.ap_list_mso:
+        table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
+        write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)
+        sys.exit(0)
 
     # Conflicting, missing and erroneous options
     if opts.usenetrc and (opts.username is not None or opts.password is not None):
         parser.error('using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
         parser.error('account username missing\n')
+    if opts.ap_password is not None and opts.ap_username is None:
+        parser.error('TV Provider account username missing\n')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error('using output template conflicts with using title, video ID or auto number')
     if opts.usetitle and opts.useid:
         parser.error('using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
         opts.password = compat_getpass('Type account password and press [Return]: ')
+    if opts.ap_username is not None and opts.ap_password is None:
+        opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
@@ -155,6 +165,8 @@ def _real_main(argv=None):
             parser.error('max sleep interval must be greater than or equal to min sleep interval')
     else:
         opts.max_sleep_interval = opts.sleep_interval
+    if opts.ap_mso and opts.ap_mso not in MSO_INFO:
+        parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
 
     def parse_retries(retries):
         if retries in ('inf', 'infinite'):
@@ -293,6 +305,9 @@ def _real_main(argv=None):
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
+        'ap_mso': opts.ap_mso,
+        'ap_username': opts.ap_username,
+        'ap_password': opts.ap_password,
         'quiet': (opts.quiet or any_getting or any_printing),
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,

youtube_dl/downloader/dash.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 import os
-import re
 
 from .fragment import FragmentFD
 from ..compat import compat_urllib_error
@@ -19,34 +18,32 @@ class DashSegmentsFD(FragmentFD):
     FD_NAME = 'dashsegments'
 
     def real_download(self, filename, info_dict):
-        base_url = info_dict['url']
+        segments = info_dict['fragments'][:1] if self.params.get(
-        segment_urls = [info_dict['segment_urls'][0]] if self.params.get('test', False) else info_dict['segment_urls']
+            'test', False) else info_dict['fragments']
-        initialization_url = info_dict.get('initialization_url')
 
         ctx = {
             'filename': filename,
-            'total_frags': len(segment_urls) + (1 if initialization_url else 0),
+            'total_frags': len(segments),
         }
 
         self._prepare_and_start_frag_download(ctx)
 
-        def combine_url(base_url, target_url):
-            if re.match(r'^https?://', target_url):
-                return target_url
-            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
-
         segments_filenames = []
 
         fragment_retries = self.params.get('fragment_retries', 0)
         skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
-        def process_segment(segment, tmp_filename, fatal):
+        def process_segment(segment, tmp_filename, num):
-            target_url, segment_name = segment
+            segment_url = segment['url']
+            segment_name = 'Frag%d' % num
             target_filename = '%s-%s' % (tmp_filename, segment_name)
+            # In DASH, the first segment contains necessary headers to
+            # generate a valid MP4 file, so always abort for the first segment
+            fatal = num == 0 or not skip_unavailable_fragments
             count = 0
             while count <= fragment_retries:
                 try:
-                    success = ctx['dl'].download(target_filename, {'url': combine_url(base_url, target_url)})
+                    success = ctx['dl'].download(target_filename, {'url': segment_url})
                     if not success:
                         return False
                     down, target_sanitized = sanitize_open(target_filename, 'rb')
@@ -72,16 +69,8 @@ class DashSegmentsFD(FragmentFD):
                 return False
             return True
 
-        segments_to_download = [(initialization_url, 'Init')] if initialization_url else []
+        for i, segment in enumerate(segments):
-        segments_to_download.extend([
+            if not process_segment(segment, ctx['tmpfilename'], i):
-            (segment_url, 'Seg%d' % i)
-            for i, segment_url in enumerate(segment_urls)])
-
-        for i, segment in enumerate(segments_to_download):
-            # In DASH, the first segment contains necessary headers to
-            # generate a valid MP4 file, so always abort for the first segment
-            fatal = i == 0 or not skip_unavailable_fragments
-            if not process_segment(segment, ctx['tmpfilename'], fatal):
                 return False
 
         self._finish_frag_download(ctx)

youtube_dl/extractor/abc.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'https?://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@@ -100,6 +100,7 @@ class ABCIViewIE(InfoExtractor):
     IE_NAME = 'abc.net.au:iview'
     _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
 
+    # ABC iview programs are normally available for 14 days only.
     _TESTS = [{
         'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
         'md5': '979d10b2939101f0d27a06b79edad536',
@@ -112,6 +113,7 @@ class ABCIViewIE(InfoExtractor):
             'uploader_id': 'abc1',
             'timestamp': 1471719600,
         },
+        'skip': 'Video gone',
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/adobepass.py

@@ -6,16 +6,33 @@ import time
 import xml.etree.ElementTree as etree
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     unescapeHTML,
     urlencode_postdata,
     unified_timestamp,
+    ExtractorError,
 )
 
 
+MSO_INFO = {
+    'DTV': {
+        'name': 'DirecTV',
+        'username_field': 'username',
+        'password_field': 'password',
+    },
+    'Rogers': {
+        'name': 'Rogers Cable',
+        'username_field': 'UserName',
+        'password_field': 'UserPassword',
+    },
+}
+
+
 class AdobePassIE(InfoExtractor):
     _SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
     _USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
+    _MVPD_CACHE = 'ap-mvpd'
 
     @staticmethod
     def _get_mvpd_resource(provider_id, title, guid, rating):
@@ -41,6 +58,24 @@ class AdobePassIE(InfoExtractor):
             token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
             return token_expires and token_expires <= int(time.time())
 
+        def post_form(form_page_res, note, data={}):
+            form_page, urlh = form_page_res
+            post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
+            if not re.match(r'https?://', post_url):
+                post_url = compat_urlparse.urljoin(urlh.geturl(), post_url)
+            form_data = self._hidden_inputs(form_page)
+            form_data.update(data)
+            return self._download_webpage_handle(
+                post_url, video_id, note, data=urlencode_postdata(form_data), headers={
+                    'Content-Type': 'application/x-www-form-urlencoded',
+                })
+
+        def raise_mvpd_required():
+            raise ExtractorError(
+                'This video is only available for users of participating TV providers. '
+                'Use --ap-mso to specify Adobe Pass Multiple-system operator Identifier '
+                'and --ap-username and --ap-password or --netrc to provide account credentials.', expected=True)
+
         mvpd_headers = {
             'ap_42': 'anonymous',
             'ap_11': 'Linux i686',
@@ -49,89 +84,91 @@ class AdobePassIE(InfoExtractor):
         }
 
         guid = xml_text(resource, 'guid')
-        requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
+        count = 0
-        authn_token = requestor_info.get('authn_token')
+        while count < 2:
-        if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
+            requestor_info = self._downloader.cache.load(self._MVPD_CACHE, requestor_id) or {}
-            authn_token = None
+            authn_token = requestor_info.get('authn_token')
-        if not authn_token:
+            if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
-            # TODO add support for other TV Providers
+                authn_token = None
-            mso_id = 'DTV'
+            if not authn_token:
-            username, password = self._get_netrc_login_info(mso_id)
+                # TODO add support for other TV Providers
-            if not username or not password:
+                mso_id = self._downloader.params.get('ap_mso')
-                return ''
+                if not mso_id:
+                    raise_mvpd_required()
+                username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
+                if not username or not password:
+                    raise_mvpd_required()
+                mso_info = MSO_INFO[mso_id]
 
-            def post_form(form_page, note, data={}):
+                provider_redirect_page_res = self._download_webpage_handle(
-                post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
+                    self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
-                return self._download_webpage(
+                    'Downloading Provider Redirect Page', query={
-                    post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
+                        'noflash': 'true',
-                        'Content-Type': 'application/x-www-form-urlencoded',
+                        'mso_id': mso_id,
+                        'requestor_id': requestor_id,
+                        'no_iframe': 'false',
+                        'domain_name': 'adobe.com',
+                        'redirect_url': url,
                     })
-
+                provider_login_page_res = post_form(
-            provider_redirect_page = self._download_webpage(
+                    provider_redirect_page_res, 'Downloading Provider Login Page')
-                self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
+                mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', {
-                'Downloading Provider Redirect Page', query={
+                    mso_info['username_field']: username,
-                    'noflash': 'true',
+                    mso_info['password_field']: password,
-                    'mso_id': mso_id,
-                    'requestor_id': requestor_id,
-                    'no_iframe': 'false',
-                    'domain_name': 'adobe.com',
-                    'redirect_url': url,
                 })
-            provider_login_page = post_form(
+                if mso_id == 'DTV':
-                provider_redirect_page, 'Downloading Provider Login Page')
+                    post_form(mvpd_confirm_page_res, 'Confirming Login')
-            mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
+
-                'username': username,
+                session = self._download_webpage(
-                'password': password,
+                    self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
+                    'Retrieving Session', data=urlencode_postdata({
+                        '_method': 'GET',
+                        'requestor_id': requestor_id,
+                    }), headers=mvpd_headers)
+                if '<pendingLogout' in session:
+                    self._downloader.cache.store(self._MVPD_CACHE, requestor_id, {})
+                    count += 1
+                    continue
+                authn_token = unescapeHTML(xml_text(session, 'authnToken'))
+                requestor_info['authn_token'] = authn_token
+                self._downloader.cache.store(self._MVPD_CACHE, requestor_id, requestor_info)
+
+            authz_token = requestor_info.get(guid)
+            if authz_token and is_expired(authz_token, 'simpleTokenTTL'):
+                authz_token = None
+            if not authz_token:
+                authorize = self._download_webpage(
+                    self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
+                    'Retrieving Authorization Token', data=urlencode_postdata({
+                        'resource_id': resource,
+                        'requestor_id': requestor_id,
+                        'authentication_token': authn_token,
+                        'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
+                        'userMeta': '1',
+                    }), headers=mvpd_headers)
+                if '<pendingLogout' in authorize:
+                    self._downloader.cache.store(self._MVPD_CACHE, requestor_id, {})
+                    count += 1
+                    continue
+                authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
+                requestor_info[guid] = authz_token
+                self._downloader.cache.store(self._MVPD_CACHE, requestor_id, requestor_info)
+
+            mvpd_headers.update({
+                'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
+                'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
             })
-            post_form(mvpd_confirm_page, 'Confirming Login')
 
-            session = self._download_webpage(
+            short_authorize = self._download_webpage(
-                self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
+                self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
-                'Retrieving Session', data=urlencode_postdata({
+                video_id, 'Retrieving Media Token', data=urlencode_postdata({
-                    '_method': 'GET',
+                    'authz_token': authz_token,
                     'requestor_id': requestor_id,
+                    'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
+                    'hashed_guid': 'false',
                 }), headers=mvpd_headers)
-            if '<pendingLogout' in session:
+            if '<pendingLogout' in short_authorize:
-                self._downloader.cache.store('mvpd', requestor_id, {})
+                self._downloader.cache.store(self._MVPD_CACHE, requestor_id, {})
-                return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+                count += 1
-            authn_token = unescapeHTML(xml_text(session, 'authnToken'))
+                continue
-            requestor_info['authn_token'] = authn_token
+            return short_authorize
-            self._downloader.cache.store('mvpd', requestor_id, requestor_info)
-
-        authz_token = requestor_info.get(guid)
-        if authz_token and is_expired(authz_token, 'simpleTokenTTL'):
-            authz_token = None
-        if not authz_token:
-            authorize = self._download_webpage(
-                self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
-                'Retrieving Authorization Token', data=urlencode_postdata({
-                    'resource_id': resource,
-                    'requestor_id': requestor_id,
-                    'authentication_token': authn_token,
-                    'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
-                    'userMeta': '1',
-                }), headers=mvpd_headers)
-            if '<pendingLogout' in authorize:
-                self._downloader.cache.store('mvpd', requestor_id, {})
-                return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
-            authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
-            requestor_info[guid] = authz_token
-            self._downloader.cache.store('mvpd', requestor_id, requestor_info)
-
-        mvpd_headers.update({
-            'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
-            'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
-        })
-
-        short_authorize = self._download_webpage(
-            self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
-            video_id, 'Retrieving Media Token', data=urlencode_postdata({
-                'authz_token': authz_token,
-                'requestor_id': requestor_id,
-                'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
-                'hashed_guid': 'false',
-            }), headers=mvpd_headers)
-        if '<pendingLogout' in short_authorize:
-            self._downloader.cache.store('mvpd', requestor_id, {})
-            return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
-        return short_authorize

youtube_dl/extractor/aljazeera.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class AlJazeeraIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
 
     _TEST = {
         'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',

youtube_dl/extractor/awaan.py

@@ -50,25 +50,6 @@ class AWAANBaseIE(InfoExtractor):
             'is_live': is_live,
         }
 
-    def _extract_video_formats(self, webpage, video_id, m3u8_entry_protocol):
-        formats = []
-        format_url_base = 'http' + self._html_search_regex(
-            [
-                r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8',
-                r'<a[^>]+href="rtsp(://[^"]+)"'
-            ], webpage, 'format url')
-        formats.extend(self._extract_mpd_formats(
-            format_url_base + '/manifest.mpd',
-            video_id, mpd_id='dash', fatal=False))
-        formats.extend(self._extract_m3u8_formats(
-            format_url_base + '/playlist.m3u8', video_id, 'mp4',
-            m3u8_entry_protocol, m3u8_id='hls', fatal=False))
-        formats.extend(self._extract_f4m_formats(
-            format_url_base + '/manifest.f4m',
-            video_id, f4m_id='hds', fatal=False))
-        self._sort_formats(formats)
-        return formats
-
 
 class AWAANVideoIE(AWAANBaseIE):
     IE_NAME = 'awaan:video'
@@ -99,16 +80,18 @@ class AWAANVideoIE(AWAANBaseIE):
             video_id, headers={'Origin': 'http://awaan.ae'})
         info = self._parse_video_data(video_data, video_id, False)
 
-        webpage = self._download_webpage(
+        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + compat_urllib_parse_urlencode({
-            'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
+            'id': video_data['id'],
-            compat_urllib_parse_urlencode({
+            'user_id': video_data['user_id'],
-                'id': video_data['id'],
+            'signature': video_data['signature'],
-                'user_id': video_data['user_id'],
+            'countries': 'Q0M=',
-                'signature': video_data['signature'],
+            'filter': 'DENY',
-                'countries': 'Q0M=',
+        })
-                'filter': 'DENY',
+        info.update({
-            }), video_id)
+            '_type': 'url_transparent',
-        info['formats'] = self._extract_video_formats(webpage, video_id, 'm3u8_native')
+            'url': embed_url,
+            'ie_key': 'MangomoloVideo',
+        })
         return info
 
 
@@ -138,16 +121,18 @@ class AWAANLiveIE(AWAANBaseIE):
             channel_id, headers={'Origin': 'http://awaan.ae'})
         info = self._parse_video_data(channel_data, channel_id, True)
 
-        webpage = self._download_webpage(
+        embed_url = 'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' + compat_urllib_parse_urlencode({
-            'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
+            'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
-            compat_urllib_parse_urlencode({
+            'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
-                'id': base64.b64encode(channel_data['user_id'].encode()).decode(),
+            'signature': channel_data['signature'],
-                'channelid': base64.b64encode(channel_data['id'].encode()).decode(),
+            'countries': 'Q0M=',
-                'signature': channel_data['signature'],
+            'filter': 'DENY',
-                'countries': 'Q0M=',
+        })
-                'filter': 'DENY',
+        info.update({
-            }), channel_id)
+            '_type': 'url_transparent',
-        info['formats'] = self._extract_video_formats(webpage, channel_id, 'm3u8')
+            'url': embed_url,
+            'ie_key': 'MangomoloLive',
+        })
         return info
 
 

youtube_dl/extractor/azubu.py

@@ -103,7 +103,7 @@ class AzubuIE(InfoExtractor):
 
 
 class AzubuLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://www.azubu.tv/(?P<id>[^/]+)$'
+    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/(?P<id>[^/]+)$'
 
     _TEST = {
         'url': 'http://www.azubu.tv/MarsTVMDLen',

youtube_dl/extractor/bbc.py

@@ -1028,7 +1028,7 @@ class BBCIE(BBCCoUkIE):
 
 
 class BBCCoUkArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
     IE_NAME = 'bbc.co.uk:article'
     IE_DESC = 'BBC articles'
 

youtube_dl/extractor/bellmedia.py

@@ -6,8 +6,25 @@ import re
 from .common import InfoExtractor
 
 
-class CTVIE(InfoExtractor):
+class BellMediaIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>ctv|tsn|bnn|thecomedynetwork)\.ca/.*?(?:\bvid=|-vid|~|%7E)(?P<id>[0-9.]+)'
+    _VALID_URL = r'''(?x)https?://(?:www\.)?
+        (?P<domain>
+            (?:
+                ctv|
+                tsn|
+                bnn|
+                thecomedynetwork|
+                discovery|
+                discoveryvelocity|
+                sciencechannel|
+                investigationdiscovery|
+                animalplanet|
+                bravo|
+                mtv|
+                space
+            )\.ca|
+            much\.com
+        )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6})'''
     _TESTS = [{
         'url': 'http://www.ctv.ca/video/player?vid=706966',
         'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@@ -32,15 +49,27 @@ class CTVIE(InfoExtractor):
     }, {
         'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
         'only_matching': True,
+    }, {
+        'url': 'http://www.much.com/shows/atmidnight/episode948007/tuesday-september-13-2016',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6',
+        'only_matching': True,
     }]
+    _DOMAINS = {
+        'thecomedynetwork': 'comedy',
+        'discoveryvelocity': 'discvel',
+        'sciencechannel': 'discsci',
+        'investigationdiscovery': 'invdisc',
+        'animalplanet': 'aniplan',
+    }
 
     def _real_extract(self, url):
         domain, video_id = re.match(self._VALID_URL, url).groups()
-        if domain == 'thecomedynetwork':
+        domain = domain.split('.')[0]
-            domain = 'comedy'
         return {
             '_type': 'url_transparent',
             'id': video_id,
-            'url': '9c9media:%s_web:%s' % (domain, video_id),
+            'url': '9c9media:%s_web:%s' % (self._DOMAINS.get(domain, domain), video_id),
             'ie_key': 'NineCNineMedia',
         }

youtube_dl/extractor/bilibili.py

@@ -17,7 +17,7 @@ from ..utils import (
 class BiliBiliIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/v/)(?P<id>\d+)'
 
-    _TESTS = [{
+    _TEST = {
         'url': 'http://www.bilibili.tv/video/av1074402/',
         'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
         'info_dict': {
@@ -32,64 +32,7 @@ class BiliBiliIE(InfoExtractor):
             'uploader': '菊子桑',
             'uploader_id': '156160',
         },
-    }, {
+    }
-        'url': 'http://www.bilibili.com/video/av1041170/',
-        'info_dict': {
-            'id': '1041170',
-            'ext': 'mp4',
-            'title': '【BD1080P】刀语【诸神&异域】',
-            'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
-            'duration': 3382.259,
-            'timestamp': 1396530060,
-            'upload_date': '20140403',
-            'thumbnail': 're:^https?://.+\.jpg',
-            'uploader': '枫叶逝去',
-            'uploader_id': '520116',
-        },
-    }, {
-        'url': 'http://www.bilibili.com/video/av4808130/',
-        'info_dict': {
-            'id': '4808130',
-            'ext': 'mp4',
-            'title': '【长篇】哆啦A梦443【钉铛】',
-            'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
-            'duration': 1493.995,
-            'timestamp': 1464564180,
-            'upload_date': '20160529',
-            'thumbnail': 're:^https?://.+\.jpg',
-            'uploader': '喜欢拉面',
-            'uploader_id': '151066',
-        },
-    }, {
-        # Missing upload time
-        'url': 'http://www.bilibili.com/video/av1867637/',
-        'info_dict': {
-            'id': '1867637',
-            'ext': 'mp4',
-            'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
-            'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
-            'duration': 5760.0,
-            'uploader': '黑夜为猫',
-            'uploader_id': '610729',
-            'thumbnail': 're:^https?://.+\.jpg',
-        },
-        'params': {
-            # Just to test metadata extraction
-            'skip_download': True,
-        },
-        'expected_warnings': ['upload time'],
-    }, {
-        'url': 'http://bangumi.bilibili.com/anime/v/40068',
-        'md5': '08d539a0884f3deb7b698fb13ba69696',
-        'info_dict': {
-            'id': '40068',
-            'ext': 'mp4',
-            'duration': 1402.357,
-            'title': '混沌武士 : 第7集 四面楚歌 A Risky Racket',
-            'description': 'md5:6a9622b911565794c11f25f81d6a97d2',
-            'thumbnail': 're:^http?://.+\.jpg',
-        },
-    }]
 
     _APP_KEY = '6f90a59ac58a4123'
     _BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
@@ -124,7 +67,7 @@ class BiliBiliIE(InfoExtractor):
                 'url': durl['url'],
                 'filesize': int_or_none(durl['size']),
             }]
-            for backup_url in durl['backup_url']:
+            for backup_url in durl.get('backup_url', []):
                 formats.append({
                     'url': backup_url,
                     # backup URLs have lower priorities

youtube_dl/extractor/bpb.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 class BpbIE(InfoExtractor):
     IE_DESC = 'Bundeszentrale für politische Bildung'
-    _VALID_URL = r'https?://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?bpb\.de/mediathek/(?P<id>[0-9]+)/'
 
     _TEST = {
         'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',

youtube_dl/extractor/camdemy.py

@@ -112,7 +112,7 @@ class CamdemyIE(InfoExtractor):
 
 
 class CamdemyFolderIE(InfoExtractor):
-    _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?camdemy\.com/folder/(?P<id>\d+)'
     _TESTS = [{
         # links with trailing slash
         'url': 'http://www.camdemy.com/folder/450',

youtube_dl/extractor/canalplus.py

@@ -23,6 +23,7 @@ class CanalplusIE(InfoExtractor):
                                     (?:(?:www|m)\.)?canalplus\.fr|
                                     (?:www\.)?piwiplus\.fr|
                                     (?:www\.)?d8\.tv|
+                                    (?:www\.)?c8\.fr|
                                     (?:www\.)?d17\.tv|
                                     (?:www\.)?itele\.fr
                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
@@ -35,6 +36,7 @@ class CanalplusIE(InfoExtractor):
         'canalplus': 'cplus',
         'piwiplus': 'teletoon',
         'd8': 'd8',
+        'c8': 'd8',
         'd17': 'd17',
         'itele': 'itele',
     }

youtube_dl/extractor/canvas.py

@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import float_or_none
 
 
 class CanvasIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?canvas\.be/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
         'md5': 'ea838375a547ac787d4064d8c7860a6c',
@@ -38,22 +40,42 @@ class CanvasIE(InfoExtractor):
         'params': {
             'skip_download': True,
         }
+    }, {
+        'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles',
+        'info_dict': {
+            'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f',
+            'display_id': 'herbekijk-sorry-voor-alles',
+            'ext': 'mp4',
+            'title': 'Herbekijk Sorry voor alles',
+            'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 3788.06,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        site_id, display_id = mobj.group('site_id'), mobj.group('id')
 
         webpage = self._download_webpage(url, display_id)
 
-        title = self._search_regex(
+        title = (self._search_regex(
             r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
-            webpage, 'title', default=None) or self._og_search_title(webpage)
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage)).strip()
 
         video_id = self._html_search_regex(
-            r'data-video=(["\'])(?P<id>.+?)\1', webpage, 'video id', group='id')
+            r'data-video=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id', group='id')
 
         data = self._download_json(
-            'https://mediazone.vrt.be/api/v1/canvas/assets/%s' % video_id, display_id)
+            'https://mediazone.vrt.be/api/v1/%s/assets/%s'
+            % (site_id, video_id), display_id)
 
         formats = []
         for target in data['targetUrls']:

youtube_dl/extractor/cbssports.py

@@ -4,7 +4,7 @@ from .cbs import CBSBaseIE
 
 
 class CBSSportsIE(CBSBaseIE):
-    _VALID_URL = r'https?://www\.cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',

youtube_dl/extractor/ceskatelevize.py

@@ -17,7 +17,7 @@ from ..utils import (
 
 
 class CeskaTelevizeIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
         'info_dict': {

youtube_dl/extractor/chirbit.py

@@ -65,7 +65,7 @@ class ChirbitIE(InfoExtractor):
 
 class ChirbitProfileIE(InfoExtractor):
     IE_NAME = 'chirbit:profile'
-    _VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://chirbit.com/ScarletBeauty',
         'info_dict': {

youtube_dl/extractor/cmt.py

@@ -6,7 +6,7 @@ from ..utils import ExtractorError
 
 class CMTIE(MTVIE):
     IE_NAME = 'cmt.com'
-    _VALID_URL = r'https?://www\.cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?cmt\.com/(?:videos|shows)/(?:[^/]+/)*(?P<videoid>\d+)'
     _FEED_URL = 'http://www.cmt.com/sitewide/apps/player/embed/rss/'
 
     _TESTS = [{

youtube_dl/extractor/common.py

@@ -87,6 +87,9 @@ class InfoExtractor(object):
 
                     Potential fields:
                     * url        Mandatory. The URL of the video file
+                    * manifest_url
+                                 The URL of the manifest file in case of
+                                 fragmented media (DASH, hls, hds)
                     * ext        Will be calculated from URL if missing
                     * format     A human-readable description of the format
                                  ("mp4 container with h264/opus").
@@ -115,6 +118,11 @@ class InfoExtractor(object):
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
                                  "m3u8", "m3u8_native" or "http_dash_segments".
+                    * fragments  A list of fragments of the fragmented media,
+                                 with the following entries:
+                                 * "url" (mandatory) - fragment's URL
+                                 * "duration" (optional, int or float)
+                                 * "filesize" (optional, int)
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.
@@ -674,33 +682,36 @@ class InfoExtractor(object):
                     username = info[0]
                     password = info[2]
                 else:
-                    raise netrc.NetrcParseError('No authenticators for %s' % netrc_machine)
+                    raise netrc.NetrcParseError(
+                        'No authenticators for %s' % netrc_machine)
             except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
+                self._downloader.report_warning(
+                    'parsing .netrc: %s' % error_to_compat_str(err))
 
-        return (username, password)
+        return username, password
 
-    def _get_login_info(self):
+    def _get_login_info(self, username_option='username', password_option='password', netrc_machine=None):
         """
         Get the login info as (username, password)
-        It will look in the netrc file using the _NETRC_MACHINE value
+        First look for the manually specified credentials using username_option
+        and password_option as keys in params dictionary. If no such credentials
+        available look in the netrc file using the netrc_machine or _NETRC_MACHINE
+        value.
         If there's no info available, return (None, None)
         """
         if self._downloader is None:
             return (None, None)
 
-        username = None
-        password = None
         downloader_params = self._downloader.params
 
         # Attempt to use provided username and password or .netrc data
-        if downloader_params.get('username') is not None:
+        if downloader_params.get(username_option) is not None:
-            username = downloader_params['username']
+            username = downloader_params[username_option]
-            password = downloader_params['password']
+            password = downloader_params[password_option]
         else:
-            username, password = self._get_netrc_login_info()
+            username, password = self._get_netrc_login_info(netrc_machine)
 
-        return (username, password)
+        return username, password
 
     def _get_tfa_info(self, note='two-factor verification code'):
         """
@@ -888,16 +899,16 @@ class InfoExtractor(object):
     def _hidden_inputs(html):
         html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
         hidden_inputs = {}
-        for input in re.findall(r'(?i)<input([^>]+)>', html):
+        for input in re.findall(r'(?i)(<input[^>]+>)', html):
-            if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
+            attrs = extract_attributes(input)
+            if not input:
                 continue
-            name = re.search(r'(?:name|id)=(["\'])(?P<value>.+?)\1', input)
+            if attrs.get('type') not in ('hidden', 'submit'):
-            if not name:
                 continue
-            value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
+            name = attrs.get('name') or attrs.get('id')
-            if not value:
+            value = attrs.get('value')
-                continue
+            if name and value is not None:
-            hidden_inputs[name.group('value')] = value.group('value')
+                hidden_inputs[name] = value
         return hidden_inputs
 
     def _form_hidden_inputs(self, form_id, html):
@@ -1139,6 +1150,7 @@ class InfoExtractor(object):
             formats.append({
                 'format_id': format_id,
                 'url': manifest_url,
+                'manifest_url': manifest_url,
                 'ext': 'flv' if bootstrap_info is not None else None,
                 'tbr': tbr,
                 'width': width,
@@ -1244,9 +1256,11 @@ class InfoExtractor(object):
                 # format_id intact.
                 if not live:
                     format_id.append(stream_name if stream_name else '%d' % (tbr if tbr else len(formats)))
+                manifest_url = format_url(line.strip())
                 f = {
                     'format_id': '-'.join(format_id),
-                    'url': format_url(line.strip()),
+                    'url': manifest_url,
+                    'manifest_url': manifest_url,
                     'tbr': tbr,
                     'ext': ext,
                     'fps': float_or_none(last_info.get('FRAME-RATE')),
@@ -1518,9 +1532,10 @@ class InfoExtractor(object):
         mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
 
         return self._parse_mpd_formats(
-            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
+            compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url,
+            formats_dict=formats_dict, mpd_url=mpd_url)
 
-    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
+    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):
         """
         Parse formats from MPD manifest.
         References:
@@ -1541,42 +1556,52 @@ class InfoExtractor(object):
 
         def extract_multisegment_info(element, ms_parent_info):
             ms_info = ms_parent_info.copy()
+
+            # As per [1, 5.3.9.2.2] SegmentList and SegmentTemplate share some
+            # common attributes and elements.  We will only extract relevant
+            # for us.
+            def extract_common(source):
+                segment_timeline = source.find(_add_ns('SegmentTimeline'))
+                if segment_timeline is not None:
+                    s_e = segment_timeline.findall(_add_ns('S'))
+                    if s_e:
+                        ms_info['total_number'] = 0
+                        ms_info['s'] = []
+                        for s in s_e:
+                            r = int(s.get('r', 0))
+                            ms_info['total_number'] += 1 + r
+                            ms_info['s'].append({
+                                't': int(s.get('t', 0)),
+                                # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
+                                'd': int(s.attrib['d']),
+                                'r': r,
+                            })
+                start_number = source.get('startNumber')
+                if start_number:
+                    ms_info['start_number'] = int(start_number)
+                timescale = source.get('timescale')
+                if timescale:
+                    ms_info['timescale'] = int(timescale)
+                segment_duration = source.get('duration')
+                if segment_duration:
+                    ms_info['segment_duration'] = int(segment_duration)
+
+            def extract_Initialization(source):
+                initialization = source.find(_add_ns('Initialization'))
+                if initialization is not None:
+                    ms_info['initialization_url'] = initialization.attrib['sourceURL']
+
             segment_list = element.find(_add_ns('SegmentList'))
             if segment_list is not None:
+                extract_common(segment_list)
+                extract_Initialization(segment_list)
                 segment_urls_e = segment_list.findall(_add_ns('SegmentURL'))
                 if segment_urls_e:
                     ms_info['segment_urls'] = [segment.attrib['media'] for segment in segment_urls_e]
-                initialization = segment_list.find(_add_ns('Initialization'))
-                if initialization is not None:
-                    ms_info['initialization_url'] = initialization.attrib['sourceURL']
             else:
                 segment_template = element.find(_add_ns('SegmentTemplate'))
                 if segment_template is not None:
-                    start_number = segment_template.get('startNumber')
+                    extract_common(segment_template)
-                    if start_number:
-                        ms_info['start_number'] = int(start_number)
-                    segment_timeline = segment_template.find(_add_ns('SegmentTimeline'))
-                    if segment_timeline is not None:
-                        s_e = segment_timeline.findall(_add_ns('S'))
-                        if s_e:
-                            ms_info['total_number'] = 0
-                            ms_info['s'] = []
-                            for s in s_e:
-                                r = int(s.get('r', 0))
-                                ms_info['total_number'] += 1 + r
-                                ms_info['s'].append({
-                                    't': int(s.get('t', 0)),
-                                    # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
-                                    'd': int(s.attrib['d']),
-                                    'r': r,
-                                })
-                    else:
-                        timescale = segment_template.get('timescale')
-                        if timescale:
-                            ms_info['timescale'] = int(timescale)
-                        segment_duration = segment_template.get('duration')
-                        if segment_duration:
-                            ms_info['segment_duration'] = int(segment_duration)
                     media_template = segment_template.get('media')
                     if media_template:
                         ms_info['media_template'] = media_template
@@ -1584,11 +1609,14 @@ class InfoExtractor(object):
                     if initialization:
                         ms_info['initialization_url'] = initialization
                     else:
-                        initialization = segment_template.find(_add_ns('Initialization'))
+                        extract_Initialization(segment_template)
-                        if initialization is not None:
-                            ms_info['initialization_url'] = initialization.attrib['sourceURL']
             return ms_info
 
+        def combine_url(base_url, target_url):
+            if re.match(r'^https?://', target_url):
+                return target_url
+            return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url)
+
         mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
         formats = []
         for period in mpd_doc.findall(_add_ns('Period')):
@@ -1631,6 +1659,7 @@ class InfoExtractor(object):
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
+                            'manifest_url': mpd_url,
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
@@ -1645,9 +1674,7 @@ class InfoExtractor(object):
                         }
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
                         if 'segment_urls' not in representation_ms_info and 'media_template' in representation_ms_info:
-                            if 'total_number' not in representation_ms_info and 'segment_duration':
+
-                                segment_duration = float(representation_ms_info['segment_duration']) / float(representation_ms_info['timescale'])
-                                representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
                             media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
@@ -1656,46 +1683,79 @@ class InfoExtractor(object):
 
                             # As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
                             # can't be used at the same time
-                            if '%(Number' in media_template:
+                            if '%(Number' in media_template and 's' not in representation_ms_info:
-                                representation_ms_info['segment_urls'] = [
+                                segment_duration = None
-                                    media_template % {
+                                if 'total_number' not in representation_ms_info and 'segment_duration':
+                                    segment_duration = float_or_none(representation_ms_info['segment_duration'], representation_ms_info['timescale'])
+                                    representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
+                                representation_ms_info['fragments'] = [{
+                                    'url': media_template % {
                                         'Number': segment_number,
                                         'Bandwidth': representation_attrib.get('bandwidth'),
-                                    }
+                                    },
-                                    for segment_number in range(
+                                    'duration': segment_duration,
-                                        representation_ms_info['start_number'],
+                                } for segment_number in range(
-                                        representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+                                    representation_ms_info['start_number'],
+                                    representation_ms_info['total_number'] + representation_ms_info['start_number'])]
                             else:
-                                representation_ms_info['segment_urls'] = []
+                                # $Number*$ or $Time$ in media template with S list available
+                                # Example $Number*$: http://www.svtplay.se/klipp/9023742/stopptid-om-bjorn-borg
+                                # Example $Time$: https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411
+                                representation_ms_info['fragments'] = []
                                 segment_time = 0
+                                segment_d = None
+                                segment_number = representation_ms_info['start_number']
 
                                 def add_segment_url():
-                                    representation_ms_info['segment_urls'].append(
+                                    segment_url = media_template % {
-                                        media_template % {
+                                        'Time': segment_time,
-                                            'Time': segment_time,
+                                        'Bandwidth': representation_attrib.get('bandwidth'),
-                                            'Bandwidth': representation_attrib.get('bandwidth'),
+                                        'Number': segment_number,
-                                        }
+                                    }
-                                    )
+                                    representation_ms_info['fragments'].append({
+                                        'url': segment_url,
+                                        'duration': float_or_none(segment_d, representation_ms_info['timescale']),
+                                    })
 
                                 for num, s in enumerate(representation_ms_info['s']):
                                     segment_time = s.get('t') or segment_time
+                                    segment_d = s['d']
                                     add_segment_url()
+                                    segment_number += 1
                                     for r in range(s.get('r', 0)):
-                                        segment_time += s['d']
+                                        segment_time += segment_d
                                         add_segment_url()
-                                    segment_time += s['d']
+                                        segment_number += 1
-                        if 'segment_urls' in representation_ms_info:
+                                    segment_time += segment_d
+                        elif 'segment_urls' in representation_ms_info and 's' in representation_ms_info:
+                            # No media template
+                            # Example: https://www.youtube.com/watch?v=iXZV5uAYMJI
+                            # or any YouTube dashsegments video
+                            fragments = []
+                            s_num = 0
+                            for segment_url in representation_ms_info['segment_urls']:
+                                s = representation_ms_info['s'][s_num]
+                                for r in range(s.get('r', 0) + 1):
+                                    fragments.append({
+                                        'url': segment_url,
+                                        'duration': float_or_none(s['d'], representation_ms_info['timescale']),
+                                    })
+                            representation_ms_info['fragments'] = fragments
+                        # NB: MPD manifest may contain direct URLs to unfragmented media.
+                        # No fragments key is present in this case.
+                        if 'fragments' in representation_ms_info:
                             f.update({
-                                'segment_urls': representation_ms_info['segment_urls'],
+                                'fragments': [],
                                 'protocol': 'http_dash_segments',
                             })
                             if 'initialization_url' in representation_ms_info:
                                 initialization_url = representation_ms_info['initialization_url'].replace('$RepresentationID$', representation_id)
-                                f.update({
-                                    'initialization_url': initialization_url,
-                                })
                                 if not f.get('url'):
                                     f['url'] = initialization_url
+                                f['fragments'].append({'url': initialization_url})
+                            f['fragments'].extend(representation_ms_info['fragments'])
+                            for fragment in f['fragments']:
+                                fragment['url'] = combine_url(base_url, fragment['url'])
                         try:
                             existing_format = next(
                                 fo for fo in formats
@@ -1792,6 +1852,49 @@ class InfoExtractor(object):
             m3u8_id='hls', fatal=False))
         return formats
 
+    def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
+        url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)
+        url_base = self._search_regex(r'(?:https?|rtmp|rtsp)(://[^?]+)', url, 'format url')
+        http_base_url = 'http' + url_base
+        formats = []
+        if 'm3u8' not in skip_protocols:
+            formats.extend(self._extract_m3u8_formats(
+                http_base_url + '/playlist.m3u8', video_id, 'mp4',
+                m3u8_entry_protocol, m3u8_id='hls', fatal=False))
+        if 'f4m' not in skip_protocols:
+            formats.extend(self._extract_f4m_formats(
+                http_base_url + '/manifest.f4m',
+                video_id, f4m_id='hds', fatal=False))
+        if re.search(r'(?:/smil:|\.smil)', url_base):
+            if 'dash' not in skip_protocols:
+                formats.extend(self._extract_mpd_formats(
+                    http_base_url + '/manifest.mpd',
+                    video_id, mpd_id='dash', fatal=False))
+            if 'smil' not in skip_protocols:
+                rtmp_formats = self._extract_smil_formats(
+                    http_base_url + '/jwplayer.smil',
+                    video_id, fatal=False)
+                for rtmp_format in rtmp_formats:
+                    rtsp_format = rtmp_format.copy()
+                    rtsp_format['url'] = '%s/%s' % (rtmp_format['url'], rtmp_format['play_path'])
+                    del rtsp_format['play_path']
+                    del rtsp_format['ext']
+                    rtsp_format.update({
+                        'url': rtsp_format['url'].replace('rtmp://', 'rtsp://'),
+                        'format_id': rtmp_format['format_id'].replace('rtmp', 'rtsp'),
+                        'protocol': 'rtsp',
+                    })
+                    formats.extend([rtmp_format, rtsp_format])
+        else:
+            for protocol in ('rtmp', 'rtsp'):
+                if protocol not in skip_protocols:
+                    formats.append({
+                        'url': protocol + url_base,
+                        'format_id': protocol,
+                        'protocol': protocol,
+                    })
+        return formats
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()

youtube_dl/extractor/criterion.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class CriterionIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.criterion\.com/films/(?P<id>[0-9]+)-.+'
+    _VALID_URL = r'https?://(?:www\.)?criterion\.com/films/(?P<id>[0-9]+)-.+'
     _TEST = {
         'url': 'http://www.criterion.com/films/184-le-samourai',
         'md5': 'bc51beba55685509883a9a7830919ec3',

youtube_dl/extractor/crunchyroll.py

@@ -34,22 +34,51 @@ from ..aes import (
 
 
 class CrunchyrollBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://www.crunchyroll.com/login'
+    _LOGIN_FORM = 'login_form'
     _NETRC_MACHINE = 'crunchyroll'
 
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
             return
-        self.report_login()
+
-        login_url = 'https://www.crunchyroll.com/?a=formhandler'
+        login_page = self._download_webpage(
-        data = urlencode_postdata({
+            self._LOGIN_URL, None, 'Downloading login page')
-            'formname': 'RpcApiUser_Login',
+
-            'name': username,
+        login_form_str = self._search_regex(
-            'password': password,
+            r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
+            login_page, 'login form', group='form')
+
+        post_url = extract_attributes(login_form_str).get('action')
+        if not post_url:
+            post_url = self._LOGIN_URL
+        elif not post_url.startswith('http'):
+            post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
+
+        login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page)
+
+        login_form.update({
+            'login_form[name]': username,
+            'login_form[password]': password,
         })
-        login_request = sanitized_Request(login_url, data)
+
-        login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        response = self._download_webpage(
-        self._download_webpage(login_request, None, False, 'Wrong login info')
+            post_url, None, 'Logging in', 'Wrong login info',
+            data=urlencode_postdata(login_form),
+            headers={'Content-Type': 'application/x-www-form-urlencoded'})
+
+        # Successful login
+        if '<title>Redirecting' in response:
+            return
+
+        error = self._html_search_regex(
+            '(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>',
+            response, 'error message', default=None)
+        if error:
+            raise ExtractorError('Unable to login: %s' % error, expected=True)
+
+        raise ExtractorError('Unable to log in')
 
     def _real_initialize(self):
         self._login()

youtube_dl/extractor/dctp.py

@@ -6,7 +6,7 @@ from ..compat import compat_str
 
 
 class DctpTvIE(InfoExtractor):
-    _VALID_URL = r'https?://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
+    _VALID_URL = r'https?://(?:www\.)?dctp\.tv/(#/)?filme/(?P<id>.+?)/$'
     _TEST = {
         'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
         'info_dict': {

youtube_dl/extractor/democracynow.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class DemocracynowIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?democracynow.org/(?P<id>[^\?]*)'
+    _VALID_URL = r'https?://(?:www\.)?democracynow\.org/(?P<id>[^\?]*)'
     IE_NAME = 'democracynow'
     _TESTS = [{
         'url': 'http://www.democracynow.org/shows/2015/7/3',

youtube_dl/extractor/engadget.py

@@ -4,7 +4,7 @@ from .common import InfoExtractor
 
 
 class EngadgetIE(InfoExtractor):
-    _VALID_URL = r'https?://www.engadget.com/video/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?engadget\.com/video/(?P<id>[^/?#]+)'
 
     _TESTS = [{
         # video with 5min ID

youtube_dl/extractor/expotv.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class ExpoTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
     _TEST = {
         'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
         'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',

youtube_dl/extractor/extractors.py

@@ -93,6 +93,7 @@ from .bbc import (
 )
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .bellmedia import BellMediaIE
 from .beatportpro import BeatportProIE
 from .bet import BetIE
 from .bigflix import BigflixIE
@@ -195,7 +196,6 @@ from .crunchyroll import (
 )
 from .cspan import CSpanIE
 from .ctsnews import CtsNewsIE
-from .ctv import CTVIE
 from .ctvnews import CTVNewsIE
 from .cultureunplugged import CultureUnpluggedIE
 from .curiositystream import (
@@ -293,6 +293,7 @@ from .fox import FOXIE
 from .foxgay import FoxgayIE
 from .foxnews import (
     FoxNewsIE,
+    FoxNewsArticleIE,
     FoxNewsInsiderIE,
 )
 from .foxsports import FoxSportsIE
@@ -395,6 +396,7 @@ from .ivi import (
     IviCompilationIE
 )
 from .ivideon import IvideonIE
+from .iwara import IwaraIE
 from .izlesene import IzleseneIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
@@ -407,6 +409,7 @@ from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE
+from .ketnet import KetnetIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
@@ -469,6 +472,10 @@ from .macgamestore import MacGameStoreIE
 from .mailru import MailRuIE
 from .makerschannel import MakersChannelIE
 from .makertv import MakerTVIE
+from .mangomolo import (
+    MangomoloVideoIE,
+    MangomoloLiveIE,
+)
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .meta import METAIE
@@ -531,6 +538,7 @@ from .nbc import (
     CSNNEIE,
     NBCIE,
     NBCNewsIE,
+    NBCOlympicsIE,
     NBCSportsIE,
     NBCSportsVPlayerIE,
 )
@@ -670,7 +678,10 @@ from .pluralsight import (
 )
 from .podomatic import PodomaticIE
 from .pokemon import PokemonIE
-from .polskieradio import PolskieRadioIE
+from .polskieradio import (
+    PolskieRadioIE,
+    PolskieRadioCategoryIE,
+)
 from .porn91 import Porn91IE
 from .porncom import PornComIE
 from .pornhd import PornHdIE
@@ -861,10 +872,12 @@ from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
+from .telequebec import TeleQuebecIE
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
+from .tfo import TFOIE
 from .theintercept import TheInterceptIE
 from .theplatform import (
     ThePlatformIE,
@@ -893,7 +906,6 @@ from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
-from .trollvids import TrollvidsIE
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
 from .tubitv import TubiTvIE
@@ -1057,6 +1069,7 @@ from .vporn import VpornIE
 from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vyborymos import VyboryMosIE
 from .walla import WallaIE
 from .washingtonpost import (
     WashingtonPostIE,

youtube_dl/extractor/foxnews.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 
 
 class FoxNewsIE(AMPIE):
+    IE_NAME = 'foxnews'
     IE_DESC = 'Fox News and Fox Business Video'
     _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
     _TESTS = [
@@ -66,6 +67,35 @@ class FoxNewsIE(AMPIE):
         return info
 
 
+class FoxNewsArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
+    IE_NAME = 'foxnews:article'
+
+    _TEST = {
+        'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
+        'md5': '62aa5a781b308fdee212ebb6f33ae7ef',
+        'info_dict': {
+            'id': '5116295019001',
+            'ext': 'mp4',
+            'title': 'Trump and Clinton asked to defend positions on Iraq War',
+            'description': 'Veterans react on \'The Kelly File\'',
+            'timestamp': 1473299755,
+            'upload_date': '20160908',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        video_id = self._html_search_regex(
+            r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
+            webpage, 'video ID', group='id')
+        return self.url_result(
+            'http://video.foxnews.com/v/' + video_id,
+            FoxNewsIE.ie_key())
+
+
 class FoxNewsInsiderIE(InfoExtractor):
     _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
     IE_NAME = 'foxnews:insider'
@@ -83,6 +113,10 @@ class FoxNewsInsiderIE(InfoExtractor):
             'upload_date': '20160825',
             'thumbnail': 're:^https?://.*\.jpg$',
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
         'add_ie': [FoxNewsIE.ie_key()],
     }
 

youtube_dl/extractor/franceinter.py

@@ -2,21 +2,21 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import month_by_name
 
 
 class FranceInterIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P<id>[^?#]+)'
+
     _TEST = {
-        'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
+        'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016',
-        'md5': '4764932e466e6f6c79c317d2e74f6884',
+        'md5': '9e54d7bdb6fdc02a841007f8a975c094',
         'info_dict': {
-            'id': '793962',
+            'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016',
             'ext': 'mp3',
-            'title': 'L’Histoire dans les jeux vidéo',
+            'title': 'Affaire Cahuzac : le contentieux du compte en Suisse',
-            'description': 'md5:7e93ddb4451e7530022792240a3049c7',
+            'description': 'md5:401969c5d318c061f86bda1fa359292b',
-            'timestamp': 1387369800,
+            'upload_date': '20160907',
-            'upload_date': '20131218',
         },
     }
 
@@ -25,23 +25,30 @@ class FranceInterIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        path = self._search_regex(
+        video_url = self._search_regex(
-            r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
+            r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
-        video_url = 'http://www.franceinter.fr/' + path
+            webpage, 'video url', group='url')
 
-        title = self._html_search_regex(
+        title = self._og_search_title(webpage)
-            r'<span class="title-diffusion">(.+?)</span>', webpage, 'title')
+        description = self._og_search_description(webpage)
-        description = self._html_search_regex(
+
-            r'<span class="description">(.*?)</span>',
+        upload_date_str = self._search_regex(
-            webpage, 'description', fatal=False)
+            r'class=["\']cover-emission-period["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
-        timestamp = int_or_none(self._search_regex(
+            webpage, 'upload date', fatal=False)
-            r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
+        if upload_date_str:
+            upload_date_list = upload_date_str.split()
+            upload_date_list.reverse()
+            upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0)
+            upload_date_list[2] = '%02d' % int(upload_date_list[2])
+            upload_date = ''.join(upload_date_list)
+        else:
+            upload_date = None
 
         return {
             'id': video_id,
             'title': title,
             'description': description,
-            'timestamp': timestamp,
+            'upload_date': upload_date,
             'formats': [{
                 'url': video_url,
                 'vcodec': 'none',

youtube_dl/extractor/freespeech.py

@@ -8,7 +8,7 @@ from .common import InfoExtractor
 
 class FreespeechIE(InfoExtractor):
     IE_NAME = 'freespeech.org'
-    _VALID_URL = r'https://www\.freespeech\.org/video/(?P<title>.+)'
+    _VALID_URL = r'https?://(?:www\.)?freespeech\.org/video/(?P<title>.+)'
     _TEST = {
         'add_ie': ['Youtube'],
         'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',

youtube_dl/extractor/gamestar.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class GameStarIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
     _TEST = {
         'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
         'md5': '96974ecbb7fd8d0d20fca5a00810cea7',

youtube_dl/extractor/generic.py

@@ -1369,6 +1369,11 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Vimeo'],
         },
+        {
+            # generic vimeo embed that requires original URL passed as Referer
+            'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
+            'only_matching': True,
+        },
         {
             'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
             'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
@@ -1652,7 +1657,9 @@ class GenericIE(InfoExtractor):
                 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
                 info_dict['formats'] = self._parse_mpd_formats(
-                    doc, video_id, mpd_base_url=url.rpartition('/')[0])
+                    doc, video_id,
+                    mpd_base_url=full_response.geturl().rpartition('/')[0],
+                    mpd_url=url)
                 self._sort_formats(info_dict['formats'])
                 return info_dict
             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
@@ -2249,6 +2256,35 @@ class GenericIE(InfoExtractor):
             return self.url_result(
                 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
 
+        # Look for Mangomolo embeds
+        mobj = re.search(
+            r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
+                (?:
+                    video\?.*?\bid=(?P<video_id>\d+)|
+                    index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
+                ).+?)\1''', webpage)
+        if mobj is not None:
+            info = {
+                '_type': 'url_transparent',
+                'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
+                'title': video_title,
+                'description': video_description,
+                'thumbnail': video_thumbnail,
+                'uploader': video_uploader,
+            }
+            video_id = mobj.group('video_id')
+            if video_id:
+                info.update({
+                    'ie_key': 'MangomoloVideo',
+                    'id': video_id,
+                })
+            else:
+                info.update({
+                    'ie_key': 'MangomoloLive',
+                    'id': mobj.group('channel_id'),
+                })
+            return info
+
         # Look for Instagram embeds
         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
         if instagram_embed_url is not None:

youtube_dl/extractor/globo.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import random
+import re
 import math
 
 from .common import InfoExtractor
@@ -14,6 +15,7 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    orderedSet,
     str_or_none,
 )
 
@@ -63,6 +65,9 @@ class GloboIE(InfoExtractor):
     }, {
         'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html',
         'only_matching': True,
+    }, {
+        'url': 'globo:3607726',
+        'only_matching': True,
     }]
 
     class MD5(object):
@@ -396,7 +401,7 @@ class GloboIE(InfoExtractor):
 
 
 class GloboArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
+    _VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/.]+)(?:\.html)?'
 
     _VIDEOID_REGEXES = [
         r'\bdata-video-id=["\'](\d{7,})',
@@ -408,15 +413,20 @@ class GloboArticleIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
-        'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
         'info_dict': {
-            'id': '3652183',
+            'id': 'novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes',
-            'ext': 'mp4',
+            'title': 'Novidade na fiscalização de bagagem pela Receita provoca discussões',
-            'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião',
+            'description': 'md5:c3c4b4d4c30c32fce460040b1ac46b12',
-            'duration': 110.711,
+        },
-            'uploader': 'Rede Globo',
+        'playlist_count': 1,
-            'uploader_id': '196',
+    }, {
-        }
+        'url': 'http://g1.globo.com/pr/parana/noticia/2016/09/mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato.html',
+        'info_dict': {
+            'id': 'mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato',
+            'title': "Lula era o 'comandante máximo' do esquema da Lava Jato, diz MPF",
+            'description': 'md5:8aa7cc8beda4dc71cc8553e00b77c54c',
+        },
+        'playlist_count': 6,
     }, {
         'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html',
         'only_matching': True,
@@ -435,5 +445,12 @@ class GloboArticleIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id')
+        video_ids = []
-        return self.url_result('globo:%s' % video_id, 'Globo')
+        for video_regex in self._VIDEOID_REGEXES:
+            video_ids.extend(re.findall(video_regex, webpage))
+        entries = [
+            self.url_result('globo:%s' % video_id, GloboIE.ie_key())
+            for video_id in orderedSet(video_ids)]
+        title = self._og_search_title(webpage, fatal=False)
+        description = self._html_search_meta('description', webpage)
+        return self.playlist_result(entries, display_id, title, description)

youtube_dl/extractor/go.py

@@ -8,6 +8,8 @@ from ..utils import (
     int_or_none,
     determine_ext,
     parse_age_limit,
+    urlencode_postdata,
+    ExtractorError,
 )
 
 
@@ -19,7 +21,7 @@ class GoIE(InfoExtractor):
         'watchdisneyjunior': '008',
         'watchdisneyxd': '009',
     }
-    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/.*?vdka(?P<id>\w+)' % '|'.join(_BRANDS.keys())
+    _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys())
     _TESTS = [{
         'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
         'info_dict': {
@@ -38,9 +40,13 @@ class GoIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        sub_domain, video_id = re.match(self._VALID_URL, url).groups()
+        sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
+        if not video_id:
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(r'data-video-id=["\']VDKA(\w+)', webpage, 'video id')
+        brand = self._BRANDS[sub_domain]
         video_data = self._download_json(
-            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (self._BRANDS[sub_domain], video_id),
+            'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
             video_id)['video'][0]
         title = video_data['title']
 
@@ -52,6 +58,21 @@ class GoIE(InfoExtractor):
             format_id = asset.get('format')
             ext = determine_ext(asset_url)
             if ext == 'm3u8':
+                video_type = video_data.get('type')
+                if video_type == 'lf':
+                    entitlement = self._download_json(
+                        'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
+                        video_id, data=urlencode_postdata({
+                            'video_id': video_data['id'],
+                            'video_type': video_type,
+                            'brand': brand,
+                            'device': '001',
+                        }))
+                    errors = entitlement.get('errors', {}).get('errors', [])
+                    if errors:
+                        error_message = ', '.join([error['message'] for error in errors])
+                        raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
+                    asset_url += '?' + entitlement['uplynkData']['sessionKey']
                 formats.extend(self._extract_m3u8_formats(
                     asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
             else:

youtube_dl/extractor/googleplus.py

@@ -10,7 +10,7 @@ from ..utils import unified_strdate
 
 class GooglePlusIE(InfoExtractor):
     IE_DESC = 'Google Plus'
-    _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
+    _VALID_URL = r'https?://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
     IE_NAME = 'plus.google'
     _TEST = {
         'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',

youtube_dl/extractor/goshgay.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class GoshgayIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)'
+    _VALID_URL = r'https?://(?:www\.)?goshgay\.com/video(?P<id>\d+?)($|/)'
     _TEST = {
         'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
         'md5': '4b6db9a0a333142eb9f15913142b0ed1',

youtube_dl/extractor/hark.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class HarkIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.hark\.com/clips/(?P<id>.+?)-.+'
+    _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+'
     _TEST = {
         'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
         'md5': '6783a58491b47b92c7c1af5a77d4cbee',

youtube_dl/extractor/hotnewhiphop.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class HotNewHipHopIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
+    _VALID_URL = r'https?://(?:www\.)?hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
     _TEST = {
         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
         'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',

youtube_dl/extractor/imdb.py

@@ -94,7 +94,7 @@ class ImdbIE(InfoExtractor):
 class ImdbListIE(InfoExtractor):
     IE_NAME = 'imdb:list'
     IE_DESC = 'Internet Movie Database lists'
-    _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+    _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
     _TEST = {
         'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
         'info_dict': {

youtube_dl/extractor/iwara.py

@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import remove_end
+
+
+class IwaraIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.|ecchi\.)?iwara\.tv/videos/(?P<id>[a-zA-Z0-9]+)'
+    _TESTS = [{
+        'url': 'http://iwara.tv/videos/amVwUl1EHpAD9RD',
+        'md5': '1d53866b2c514b23ed69e4352fdc9839',
+        'info_dict': {
+            'id': 'amVwUl1EHpAD9RD',
+            'ext': 'mp4',
+            'title': '【MMD R-18】ガールフレンド carry_me_off',
+            'age_limit': 18,
+        },
+    }, {
+        'url': 'http://ecchi.iwara.tv/videos/Vb4yf2yZspkzkBO',
+        'md5': '7e5f1f359cd51a027ba4a7b7710a50f0',
+        'info_dict': {
+            'id': '0B1LvuHnL-sRFNXB1WHNqbGw4SXc',
+            'ext': 'mp4',
+            'title': '[3D Hentai] Kyonyu Ã\x97 Genkai Ã\x97 Emaki Shinobi Girls.mp4',
+            'age_limit': 18,
+        },
+        'add_ie': ['GoogleDrive'],
+    }, {
+        'url': 'http://www.iwara.tv/videos/nawkaumd6ilezzgq',
+        'md5': '1d85f1e5217d2791626cff5ec83bb189',
+        'info_dict': {
+            'id': '6liAP9s2Ojc',
+            'ext': 'mp4',
+            'age_limit': 0,
+            'title': '[MMD] Do It Again Ver.2 [1080p 60FPS] (Motion,Camera,Wav+DL)',
+            'description': 'md5:590c12c0df1443d833fbebe05da8c47a',
+            'upload_date': '20160910',
+            'uploader': 'aMMDsork',
+            'uploader_id': 'UCVOFyOSCyFkXTYYHITtqB7A',
+        },
+        'add_ie': ['Youtube'],
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        hostname = compat_urllib_parse_urlparse(urlh.geturl()).hostname
+        # ecchi is 'sexy' in Japanese
+        age_limit = 18 if hostname.split('.')[0] == 'ecchi' else 0
+
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
+
+        if not entries:
+            iframe_url = self._html_search_regex(
+                r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1',
+                webpage, 'iframe URL', group='url')
+            return {
+                '_type': 'url_transparent',
+                'url': iframe_url,
+                'age_limit': age_limit,
+            }
+
+        title = remove_end(self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title'), ' | Iwara')
+
+        info_dict = entries[0]
+        info_dict.update({
+            'id': video_id,
+            'title': title,
+            'age_limit': age_limit,
+        })
+
+        return info_dict

youtube_dl/extractor/jwplatform.py

@@ -9,6 +9,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    js_to_json,
     mimetype2ext,
 )
 
@@ -19,14 +20,15 @@ class JWPlatformBaseIE(InfoExtractor):
         # TODO: Merge this with JWPlayer-related codes in generic.py
 
         mobj = re.search(
-            'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\((?P<options>[^)]+)\)',
+            r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)',
             webpage)
         if mobj:
             return mobj.group('options')
 
     def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
         jwplayer_data = self._parse_json(
-            self._find_jwplayer_data(webpage), video_id)
+            self._find_jwplayer_data(webpage), video_id,
+            transform_source=js_to_json)
         return self._parse_jwplayer_data(
             jwplayer_data, video_id, *args, **kwargs)
 

youtube_dl/extractor/kaltura.py

@@ -262,8 +262,16 @@ class KalturaIE(InfoExtractor):
             # Continue if asset is not ready
             if f.get('status') != 2:
                 continue
+            # Original format that's not available (e.g. kaltura:1926081:0_c03e1b5g)
+            # skip for now.
+            if f.get('fileExt') == 'chun':
+                continue
             video_url = sign_url(
                 '%s/flavorId/%s' % (data_url, f['id']))
+            # audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g
+            # -f mp4-56)
+            vcodec = 'none' if 'videoCodecId' not in f and f.get(
+                'frameRate') == 0 else f.get('videoCodecId')
             formats.append({
                 'format_id': '%(fileExt)s-%(bitrate)s' % f,
                 'ext': f.get('fileExt'),
@@ -271,7 +279,7 @@ class KalturaIE(InfoExtractor):
                 'fps': int_or_none(f.get('frameRate')),
                 'filesize_approx': int_or_none(f.get('size'), invscale=1024),
                 'container': f.get('containerFormat'),
-                'vcodec': f.get('videoCodecId'),
+                'vcodec': vcodec,
                 'height': int_or_none(f.get('height')),
                 'width': int_or_none(f.get('width')),
                 'url': video_url,

youtube_dl/extractor/karaoketv.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class KaraoketvIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.karaoketv\.co\.il/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?karaoketv\.co\.il/[^/]+/(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.karaoketv.co.il/%D7%A9%D7%99%D7%A8%D7%99_%D7%A7%D7%A8%D7%99%D7%95%D7%A7%D7%99/58356/%D7%90%D7%99%D7%96%D7%95%D7%9F',
         'info_dict': {

youtube_dl/extractor/ketnet.py

@@ -0,0 +1,52 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class KetnetIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.ketnet.be/kijken/zomerse-filmpjes',
+        'md5': 'd907f7b1814ef0fa285c0475d9994ed7',
+        'info_dict': {
+            'id': 'zomerse-filmpjes',
+            'ext': 'mp4',
+            'title': 'Gluur mee op de filmset en op Pennenzakkenrock',
+            'description': 'Gluur mee met Ghost Rockers op de filmset',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        }
+    }, {
+        'url': 'https://www.ketnet.be/kijken/karrewiet/uitzending-8-september-2016',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ketnet.be/achter-de-schermen/sien-repeteert-voor-stars-for-life',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        config = self._parse_json(
+            self._search_regex(
+                r'(?s)playerConfig\s*=\s*({.+?})\s*;', webpage,
+                'player config'),
+            video_id)
+
+        title = config['title']
+
+        formats = self._extract_m3u8_formats(
+            config['source']['hls'], video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': config.get('description'),
+            'thumbnail': config.get('image'),
+            'series': config.get('program'),
+            'episode': config.get('episode'),
+            'formats': formats,
+        }

youtube_dl/extractor/kickstarter.py

@@ -6,7 +6,7 @@ from ..utils import smuggle_url
 
 
 class KickStarterIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*'
+    _VALID_URL = r'https?://(?:www\.)?kickstarter\.com/projects/(?P<id>[^/]*)/.*'
     _TESTS = [{
         'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant/description',
         'md5': 'c81addca81327ffa66c642b5d8b08cab',

youtube_dl/extractor/kuwo.py

@@ -59,7 +59,7 @@ class KuwoBaseIE(InfoExtractor):
 class KuwoIE(KuwoBaseIE):
     IE_NAME = 'kuwo:song'
     IE_DESC = '酷我音乐'
-    _VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/yinyue/635632/',
         'info_dict': {
@@ -82,7 +82,7 @@ class KuwoIE(KuwoBaseIE):
             'upload_date': '20150518',
         },
         'params': {
-            'format': 'mp3-320'
+            'format': 'mp3-320',
         },
     }, {
         'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
@@ -91,10 +91,10 @@ class KuwoIE(KuwoBaseIE):
 
     def _real_extract(self, url):
         song_id = self._match_id(url)
-        webpage = self._download_webpage(
+        webpage, urlh = self._download_webpage_handle(
             url, song_id, note='Download song detail info',
             errnote='Unable to get song detail info')
-        if '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
+        if song_id not in urlh.geturl() or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
             raise ExtractorError('this song has been offline because of copyright issues', expected=True)
 
         song_name = self._html_search_regex(
@@ -139,7 +139,7 @@ class KuwoIE(KuwoBaseIE):
 class KuwoAlbumIE(InfoExtractor):
     IE_NAME = 'kuwo:album'
     IE_DESC = '酷我音乐 - 专辑'
-    _VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/album/502294/',
         'info_dict': {
@@ -181,7 +181,7 @@ class KuwoChartIE(InfoExtractor):
         'info_dict': {
             'id': '香港中文龙虎榜',
         },
-        'playlist_mincount': 10,
+        'playlist_mincount': 7,
     }
 
     def _real_extract(self, url):
@@ -200,7 +200,7 @@ class KuwoChartIE(InfoExtractor):
 class KuwoSingerIE(InfoExtractor):
     IE_NAME = 'kuwo:singer'
     IE_DESC = '酷我音乐 - 歌手'
-    _VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
         'info_dict': {
@@ -296,14 +296,14 @@ class KuwoCategoryIE(InfoExtractor):
 class KuwoMvIE(KuwoBaseIE):
     IE_NAME = 'kuwo:mv'
     IE_DESC = '酷我音乐 - MV'
-    _VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'
     _TEST = {
         'url': 'http://www.kuwo.cn/mv/6480076/',
         'info_dict': {
             'id': '6480076',
             'ext': 'mp4',
             'title': 'My HouseMV',
-            'creator': 'PM02:00',
+            'creator': '2PM',
         },
         # In this video, music URLs (anti.s) are blocked outside China and
         # USA, while the MV URL (mvurl) is available globally, so force the MV

youtube_dl/extractor/litv.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class LiTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
+    _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
 
     _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?id=%s'
 

youtube_dl/extractor/lrt.py

@@ -1,8 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     int_or_none,
     parse_duration,
     remove_end,
@@ -12,8 +15,10 @@ from ..utils import (
 class LRTIE(InfoExtractor):
     IE_NAME = 'lrt.lt'
     _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
+        # m3u8 download
         'url': 'http://www.lrt.lt/mediateka/irasas/54391/',
+        'md5': 'fe44cf7e4ab3198055f2c598fc175cb0',
         'info_dict': {
             'id': '54391',
             'ext': 'mp4',
@@ -23,20 +28,45 @@ class LRTIE(InfoExtractor):
             'view_count': int,
             'like_count': int,
         },
-        'params': {
+    }, {
-            'skip_download': True,  # m3u8 download
+        # direct mp3 download
+        'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/',
+        'md5': '389da8ca3cad0f51d12bed0c844f6a0a',
+        'info_dict': {
+            'id': '1013074524',
+            'ext': 'mp3',
+            'title': 'Kita tema 2016-09-05 15:05',
+            'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
+            'duration': 3008,
+            'view_count': int,
+            'like_count': int,
         },
-    }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = remove_end(self._og_search_title(webpage), ' - LRT')
-        m3u8_url = self._search_regex(
+
-            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)',
+        formats = []
-            webpage, 'm3u8 url', group='url')
+        for _, file_url in re.findall(
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
+                r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage):
+            ext = determine_ext(file_url)
+            if ext not in ('m3u8', 'mp3'):
+                continue
+            # mp3 served as m3u8 produces stuttered media file
+            if ext == 'm3u8' and '.mp3' in file_url:
+                continue
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    file_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    fatal=False))
+            elif ext == 'mp3':
+                formats.append({
+                    'url': file_url,
+                    'vcodec': 'none',
+                })
         self._sort_formats(formats)
 
         thumbnail = self._og_search_thumbnail(webpage)

youtube_dl/extractor/lynda.py

@@ -94,7 +94,7 @@ class LyndaBaseIE(InfoExtractor):
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'
-    _VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(?P<id>\d+)'
 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 

youtube_dl/extractor/macgamestore.py

@@ -7,7 +7,7 @@ from ..utils import ExtractorError
 class MacGameStoreIE(InfoExtractor):
     IE_NAME = 'macgamestore'
     IE_DESC = 'MacGameStore trailers'
-    _VALID_URL = r'https?://www\.macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',

youtube_dl/extractor/mangomolo.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import base64
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_unquote
+from ..utils import (
+    int_or_none,
+)
+
+
+class MangomoloBaseIE(InfoExtractor):
+    def _get_real_id(self, page_id):
+        return page_id
+
+    def _real_extract(self, url):
+        page_id = self._get_real_id(self._match_id(url))
+        webpage = self._download_webpage(url, page_id)
+        hidden_inputs = self._hidden_inputs(webpage)
+        m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native'
+
+        format_url = self._html_search_regex(
+            [
+                r'file\s*:\s*"(https?://[^"]+?/playlist.m3u8)',
+                r'<a[^>]+href="(rtsp://[^"]+)"'
+            ], webpage, 'format url')
+        formats = self._extract_wowza_formats(
+            format_url, page_id, m3u8_entry_protocol, ['smil'])
+        self._sort_formats(formats)
+
+        return {
+            'id': page_id,
+            'title': self._live_title(page_id) if self._IS_LIVE else page_id,
+            'uploader_id': hidden_inputs.get('userid'),
+            'duration': int_or_none(hidden_inputs.get('duration')),
+            'is_live': self._IS_LIVE,
+            'formats': formats,
+        }
+
+
+class MangomoloVideoIE(MangomoloBaseIE):
+    IE_NAME = 'mangomolo:video'
+    _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/video\?.*?\bid=(?P<id>\d+)'
+    _IS_LIVE = False
+
+
+class MangomoloLiveIE(MangomoloBaseIE):
+    IE_NAME = 'mangomolo:live'
+    _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/index\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
+    _IS_LIVE = True
+
+    def _get_real_id(self, page_id):
+        return base64.b64decode(compat_urllib_parse_unquote(page_id).encode()).decode()

youtube_dl/extractor/metacritic.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class MetacriticIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.metacritic\.com/.+?/trailers/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?metacritic\.com/.+?/trailers/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',

youtube_dl/extractor/mgtv.py

@@ -6,7 +6,7 @@ from ..utils import int_or_none
 
 
 class MGTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
     IE_DESC = '芒果TV'
 
     _TESTS = [{

youtube_dl/extractor/ministrygrid.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class MinistryGridIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?ministrygrid\.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
 
     _TEST = {
         'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers',

youtube_dl/extractor/mitele.py

@@ -74,7 +74,7 @@ class MiTeleBaseIE(InfoExtractor):
 
 class MiTeleIE(MiTeleBaseIE):
     IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://www\.mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
+    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
 
     _TESTS = [{
         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',

youtube_dl/extractor/motorsport.py

@@ -9,7 +9,7 @@ from ..compat import (
 
 class MotorsportIE(InfoExtractor):
     IE_DESC = 'motorsport.com'
-    _VALID_URL = r'https?://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
+    _VALID_URL = r'https?://(?:www\.)?motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
     _TEST = {
         'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
         'info_dict': {

youtube_dl/extractor/moviezine.py

@@ -7,7 +7,7 @@ from .common import InfoExtractor
 
 
 class MoviezineIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.moviezine\.se/video/(?P<id>[^?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?moviezine\.se/video/(?P<id>[^?#]+)'
 
     _TEST = {
         'url': 'http://www.moviezine.se/video/205866',

youtube_dl/extractor/myspass.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class MySpassIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.myspass\.de/.*'
+    _VALID_URL = r'https?://(?:www\.)?myspass\.de/.*'
     _TEST = {
         'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
         'md5': '0b49f4844a068f8b33f4b7c88405862b',

youtube_dl/extractor/nbc.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class NBCIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
+    _VALID_URL = r'https?://(?:www\.)?nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
 
     _TESTS = [
         {
@@ -138,7 +138,7 @@ class NBCSportsVPlayerIE(InfoExtractor):
 
 class NBCSportsIE(InfoExtractor):
     # Does not include https because its certificate is invalid
-    _VALID_URL = r'https?://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
 
     _TEST = {
         'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
@@ -161,7 +161,7 @@ class NBCSportsIE(InfoExtractor):
 
 
 class CSNNEIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.csnne\.com/video/(?P<id>[0-9a-z-]+)'
+    _VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
 
     _TEST = {
         'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
@@ -335,3 +335,43 @@ class NBCNewsIE(ThePlatformIE):
                 'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byId=%s' % video_id,
                 'ie_key': 'ThePlatformFeed',
             }
+
+
+class NBCOlympicsIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
+
+    _TEST = {
+        # Geo-restricted to US
+        'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
+        'md5': '54fecf846d05429fbaa18af557ee523a',
+        'info_dict': {
+            'id': 'WjTBzDXx5AUq',
+            'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
+            'ext': 'mp4',
+            'title': 'Rose\'s son Leo was in tears after his dad won gold',
+            'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
+            'timestamp': 1471274964,
+            'upload_date': '20160815',
+            'uploader': 'NBCU-SPORTS',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        drupal_settings = self._parse_json(self._search_regex(
+            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
+            webpage, 'drupal settings'), display_id)
+
+        iframe_url = drupal_settings['vod']['iframe_url']
+        theplatform_url = iframe_url.replace(
+            'vplayer.nbcolympics.com', 'player.theplatform.com')
+
+        return {
+            '_type': 'url_transparent',
+            'url': theplatform_url,
+            'ie_key': ThePlatformIE.ie_key(),
+            'display_id': display_id,
+        }

youtube_dl/extractor/ndr.py

@@ -23,7 +23,7 @@ class NDRBaseIE(InfoExtractor):
 class NDRIE(NDRBaseIE):
     IE_NAME = 'ndr'
     IE_DESC = 'NDR.de - Norddeutscher Rundfunk'
-    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
+    _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[^/?#]+),[\da-z]+\.html'
     _TESTS = [{
         # httpVideo, same content id
         'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html',
@@ -105,7 +105,7 @@ class NDRIE(NDRBaseIE):
 class NJoyIE(NDRBaseIE):
     IE_NAME = 'njoy'
     IE_DESC = 'N-JOY'
-    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
     _TESTS = [{
         # httpVideo, same content id
         'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
@@ -238,7 +238,7 @@ class NDREmbedBaseIE(InfoExtractor):
 
 class NDREmbedIE(NDREmbedBaseIE):
     IE_NAME = 'ndr:embed'
-    _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
+    _VALID_URL = r'https?://(?:www\.)?ndr\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)\.html'
     _TESTS = [{
         'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html',
         'md5': '8b9306142fe65bbdefb5ce24edb6b0a9',
@@ -332,7 +332,7 @@ class NDREmbedIE(NDREmbedBaseIE):
 
 class NJoyEmbedIE(NDREmbedBaseIE):
     IE_NAME = 'njoy:embed'
-    _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
+    _VALID_URL = r'https?://(?:www\.)?n-joy\.de/(?:[^/]+/)*(?P<id>[\da-z]+)-(?:player|externalPlayer)_[^/]+\.html'
     _TESTS = [{
         # httpVideo
         'url': 'http://www.n-joy.de/events/reeperbahnfestival/doku948-player_image-bc168e87-5263-4d6d-bd27-bb643005a6de_theme-n-joy.html',

youtube_dl/extractor/newgrounds.py

@@ -1,15 +1,12 @@
 from __future__ import unicode_literals
 
-import json
-import re
-
 from .common import InfoExtractor
 
 
 class NewgroundsIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'http://www.newgrounds.com/audio/listen/549479',
+        'url': 'https://www.newgrounds.com/audio/listen/549479',
         'md5': 'fe6033d297591288fa1c1f780386f07a',
         'info_dict': {
             'id': '549479',
@@ -18,7 +15,7 @@ class NewgroundsIE(InfoExtractor):
             'uploader': 'Burn7',
         }
     }, {
-        'url': 'http://www.newgrounds.com/portal/view/673111',
+        'url': 'https://www.newgrounds.com/portal/view/673111',
         'md5': '3394735822aab2478c31b1004fe5e5bc',
         'info_dict': {
             'id': '673111',
@@ -29,24 +26,20 @@ class NewgroundsIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        media_id = self._match_id(url)
-        music_id = mobj.group('id')
+        webpage = self._download_webpage(url, media_id)
-        webpage = self._download_webpage(url, music_id)
 
         title = self._html_search_regex(
             r'<title>([^>]+)</title>', webpage, 'title')
 
         uploader = self._html_search_regex(
-            [r',"artist":"([^"]+)",', r'[\'"]owner[\'"]\s*:\s*[\'"]([^\'"]+)[\'"],'],
+            r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
-            webpage, 'uploader')
 
-        music_url_json_string = self._html_search_regex(
+        music_url = self._parse_json(self._search_regex(
-            r'({"url":"[^"]+"),', webpage, 'music url') + '}'
+            r'"url":("[^"]+"),', webpage, ''), media_id)
-        music_url_json = json.loads(music_url_json_string)
-        music_url = music_url_json['url']
 
         return {
-            'id': music_id,
+            'id': media_id,
             'title': title,
             'url': music_url,
             'uploader': uploader,

youtube_dl/extractor/nextmedia.py

@@ -7,7 +7,7 @@ from ..utils import parse_iso8601
 
 class NextMediaIE(InfoExtractor):
     IE_DESC = '蘋果日報'
-    _VALID_URL = r'https?://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://hk\.apple\.nextmedia\.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
         'md5': 'dff9fad7009311c421176d1ac90bfe4f',
@@ -68,7 +68,7 @@ class NextMediaIE(InfoExtractor):
 
 class NextMediaActionNewsIE(NextMediaIE):
     IE_DESC = '蘋果日報 - 動新聞'
-    _VALID_URL = r'https?://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
+    _VALID_URL = r'https?://hk\.dv\.nextmedia\.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
     _TESTS = [{
         'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
         'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
@@ -93,7 +93,7 @@ class NextMediaActionNewsIE(NextMediaIE):
 
 class AppleDailyIE(NextMediaIE):
     IE_DESC = '臺灣蘋果日報'
-    _VALID_URL = r'https?://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+    _VALID_URL = r'https?://(www|ent)\.appledaily\.com\.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
     _TESTS = [{
         'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
         'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',

youtube_dl/extractor/nfl.py

@@ -165,7 +165,7 @@ class NFLIE(InfoExtractor):
             group='config'))
         # For articles, the id in the url is not the video id
         video_id = self._search_regex(
-            r'(?:<nflcs:avplayer[^>]+data-content[Ii]d\s*=\s*|content[Ii]d\s*:\s*)(["\'])(?P<id>.+?)\1',
+            r'(?:<nflcs:avplayer[^>]+data-content[Ii]d\s*=\s*|content[Ii]d\s*:\s*)(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'video id', default=video_id, group='id')
         config = self._download_json(config_url, video_id, 'Downloading player config')
         url_template = NFLIE.prepend_host(

youtube_dl/extractor/nhk.py

@@ -1,14 +1,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class NhkVodIE(InfoExtractor):
-    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>.+?)\.html'
+    _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>[^/]+/[^/?#&]+)'
     _TEST = {
         # Videos available only for a limited period of time. Visit
         # http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
-        'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815.html',
+        'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815',
         'info_dict': {
             'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
             'ext': 'flv',
@@ -19,25 +20,25 @@ class NhkVodIE(InfoExtractor):
         },
         'skip': 'Videos available only for a limited period of time',
     }
+    _API_URL = 'http://api.nhk.or.jp/nhkworld/vodesdlist/v1/all/all/all.json?apikey=EJfK8jdS57GqlupFgAfAAwr573q01y6k'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        data = self._download_json(self._API_URL, video_id)
 
-        embed_code = self._search_regex(
+        try:
-            r'nw_vod_ooplayer\([^,]+,\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+            episode = next(
-            webpage, 'ooyala embed code', group='id')
+                e for e in data['data']['episodes']
+                if e.get('url') and video_id in e['url'])
+        except StopIteration:
+            raise ExtractorError('Unable to find episode')
 
-        title = self._search_regex(
+        embed_code = episode['vod_id']
-            r'<div[^>]+class=["\']episode-detail["\']>\s*<h\d+>([^<]+)',
+
-            webpage, 'title', default=None)
+        title = episode.get('sub_title_clean') or episode['sub_title']
-        description = self._html_search_regex(
+        description = episode.get('description_clean') or episode.get('description')
-            r'(?s)<p[^>]+class=["\']description["\'][^>]*>(.+?)</p>',
+        series = episode.get('title_clean') or episode.get('title')
-            webpage, 'description', default=None)
-        series = self._search_regex(
-            r'<h2[^>]+class=["\']detail-top-player-title[^>]+><a[^>]+>([^<]+)',
-            webpage, 'series', default=None)
 
         return {
             '_type': 'url_transparent',

youtube_dl/extractor/niconico.py

@@ -252,7 +252,7 @@ class NiconicoIE(InfoExtractor):
 
 
 class NiconicoPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/mylist/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.nicovideo.jp/mylist/27411728',

youtube_dl/extractor/ninenow.py

@@ -44,7 +44,20 @@ class NineNowIE(InfoExtractor):
         page_data = self._parse_json(self._search_regex(
             r'window\.__data\s*=\s*({.*?});', webpage,
             'page data'), display_id)
-        common_data = page_data.get('episode', {}).get('episode') or page_data.get('clip', {}).get('clip')
+
+        for kind in ('episode', 'clip'):
+            current_key = page_data.get(kind, {}).get(
+                'current%sKey' % kind.capitalize())
+            if not current_key:
+                continue
+            cache = page_data.get(kind, {}).get('%sCache' % kind, {})
+            if not cache:
+                continue
+            common_data = (cache.get(current_key) or list(cache.values())[0])[kind]
+            break
+        else:
+            raise ExtractorError('Unable to find video data')
+
         video_data = common_data['video']
 
         if video_data.get('drm'):

youtube_dl/extractor/npo.py

@@ -429,7 +429,7 @@ class SchoolTVIE(InfoExtractor):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
         video_id = self._search_regex(
-            r'data-mid=(["\'])(?P<id>.+?)\1', webpage, 'video_id', group='id')
+            r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
         return {
             '_type': 'url_transparent',
             'ie_key': 'NPO',

youtube_dl/extractor/oktoberfesttv.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class OktoberfestTVIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)'
 
     _TEST = {
         'url': 'http://www.oktoberfest-tv.de/de/kameras/video/hb-zelt',

youtube_dl/extractor/openload.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'https?://openload\.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -60,7 +60,7 @@ class OpenloadIE(InfoExtractor):
             if j >= 33 and j <= 126:
                 j = ((j + 14) % 94) + 33
             if idx == len(enc_data) - 1:
-                j += 1
+                j += 3
             video_url_chars += compat_chr(j)
 
         video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)

youtube_dl/extractor/parliamentliveuk.py

@@ -1,53 +1,40 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class ParliamentLiveUKIE(InfoExtractor):
     IE_NAME = 'parliamentlive.tv'
     IE_DESC = 'UK parliament videos'
-    _VALID_URL = r'https?://www\.parliamentlive\.tv/Main/Player\.aspx\?(?:[^&]+&)*?meetingId=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?parliamentlive\.tv/Event/Index/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
 
     _TEST = {
-        'url': 'http://www.parliamentlive.tv/Main/Player.aspx?meetingId=15121&player=windowsmedia',
+        'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
         'info_dict': {
-            'id': '15121',
+            'id': 'c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
-            'ext': 'asf',
+            'ext': 'mp4',
-            'title': 'hoc home affairs committee, 18 mar 2014.pm',
+            'title': 'Home Affairs Committee',
-            'description': 'md5:033b3acdf83304cd43946b2d5e5798d1',
+            'uploader_id': 'FFMPEG-01',
+            'timestamp': 1422696664,
+            'upload_date': '20150131',
         },
-        'params': {
-            'skip_download': True,  # Requires mplayer (mms)
-        }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
+        webpage = self._download_webpage(
-        webpage = self._download_webpage(url, video_id)
+            'http://vodplayer.parliamentlive.tv/?mid=' + video_id, video_id)
-
+        widget_config = self._parse_json(self._search_regex(
-        asx_url = self._html_search_regex(
+            r'kWidgetConfig\s*=\s*({.+});',
-            r'embed.*?src="([^"]+)" name="MediaPlayer"', webpage,
+            webpage, 'kaltura widget config'), video_id)
-            'metadata URL')
+        kaltura_url = 'kaltura:%s:%s' % (widget_config['wid'][1:], widget_config['entry_id'])
-        asx = self._download_xml(asx_url, video_id, 'Downloading ASX metadata')
+        event_title = self._download_json(
-        video_url = asx.find('.//REF').attrib['HREF']
+            'http://parliamentlive.tv/Event/GetShareVideo/' + video_id, video_id)['event']['title']
-
-        title = self._search_regex(
-            r'''(?x)player\.setClipDetails\(
-                (?:(?:[0-9]+|"[^"]+"),\s*){2}
-                "([^"]+",\s*"[^"]+)"
-                ''',
-            webpage, 'title').replace('", "', ', ')
-        description = self._html_search_regex(
-            r'(?s)<span id="MainContentPlaceHolder_CaptionsBlock_WitnessInfo">(.*?)</span>',
-            webpage, 'description')
-
         return {
+            '_type': 'url_transparent',
             'id': video_id,
-            'ext': 'asf',
+            'title': event_title,
-            'url': video_url,
+            'description': '',
-            'title': title,
+            'url': kaltura_url,
-            'description': description,
+            'ie_key': 'Kaltura',
         }

youtube_dl/extractor/periscope.py

@@ -94,7 +94,7 @@ class PeriscopeIE(PeriscopeBaseIE):
 
 
 class PeriscopeUserIE(PeriscopeBaseIE):
-    _VALID_URL = r'https?://www\.periscope\.tv/(?P<id>[^/]+)/?$'
+    _VALID_URL = r'https?://(?:www\.)?periscope\.tv/(?P<id>[^/]+)/?$'
     IE_DESC = 'Periscope user videos'
     IE_NAME = 'periscope:user'
 

youtube_dl/extractor/playvid.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class PlayvidIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
+    _VALID_URL = r'https?://(?:www\.)?playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
     _TESTS = [{
         'url': 'http://www.playvid.com/watch/RnmBNgtrrJu',
         'md5': 'ffa2f6b2119af359f544388d8c01eb6c',

youtube_dl/extractor/polskieradio.py

@@ -1,14 +1,17 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_urllib_parse_unquote,
+    compat_urlparse
 )
 from ..utils import (
+    extract_attributes,
     int_or_none,
     strip_or_none,
     unified_timestamp,
@@ -97,3 +100,81 @@ class PolskieRadioIE(InfoExtractor):
         description = strip_or_none(self._og_search_description(webpage))
 
         return self.playlist_result(entries, playlist_id, title, description)
+
+
+class PolskieRadioCategoryIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?polskieradio\.pl/\d+(?:,[^/]+)?/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.polskieradio.pl/7/5102,HISTORIA-ZYWA',
+        'info_dict': {
+            'id': '5102',
+            'title': 'HISTORIA ŻYWA',
+        },
+        'playlist_mincount': 38,
+    }, {
+        'url': 'http://www.polskieradio.pl/7/4807',
+        'info_dict': {
+            'id': '4807',
+            'title': 'Vademecum 1050. rocznicy Chrztu Polski'
+        },
+        'playlist_mincount': 5
+    }, {
+        'url': 'http://www.polskieradio.pl/7/129,Sygnaly-dnia?ref=source',
+        'only_matching': True
+    }, {
+        'url': 'http://www.polskieradio.pl/37,RedakcjaKatolicka/4143,Kierunek-Krakow',
+        'info_dict': {
+            'id': '4143',
+            'title': 'Kierunek Kraków',
+        },
+        'playlist_mincount': 61
+    }, {
+        'url': 'http://www.polskieradio.pl/10,czworka/214,muzyka',
+        'info_dict': {
+            'id': '214',
+            'title': 'Muzyka',
+        },
+        'playlist_mincount': 61
+    }, {
+        'url': 'http://www.polskieradio.pl/7,Jedynka/5102,HISTORIA-ZYWA',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.polskieradio.pl/8,Dwojka/196,Publicystyka',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PolskieRadioIE.suitable(url) else super(PolskieRadioCategoryIE, cls).suitable(url)
+
+    def _entries(self, url, page, category_id):
+        content = page
+        for page_num in itertools.count(2):
+            for a_entry, entry_id in re.findall(
+                    r'(?s)<article[^>]+>.*?(<a[^>]+href=["\']/\d+/\d+/Artykul/(\d+)[^>]+>).*?</article>',
+                    content):
+                entry = extract_attributes(a_entry)
+                href = entry.get('href')
+                if not href:
+                    continue
+                yield self.url_result(
+                    compat_urlparse.urljoin(url, href), PolskieRadioIE.ie_key(),
+                    entry_id, entry.get('title'))
+            mobj = re.search(
+                r'<div[^>]+class=["\']next["\'][^>]*>\s*<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1',
+                content)
+            if not mobj:
+                break
+            next_url = compat_urlparse.urljoin(url, mobj.group('url'))
+            content = self._download_webpage(
+                next_url, category_id, 'Downloading page %s' % page_num)
+
+    def _real_extract(self, url):
+        category_id = self._match_id(url)
+        webpage = self._download_webpage(url, category_id)
+        title = self._html_search_regex(
+            r'<title>([^<]+) - [^<]+ - [^<]+</title>',
+            webpage, 'title', fatal=False)
+        return self.playlist_result(
+            self._entries(url, webpage, category_id),
+            category_id, title)

youtube_dl/extractor/pornhub.py

@@ -15,6 +15,7 @@ from ..compat import (
 from ..utils import (
     ExtractorError,
     int_or_none,
+    js_to_json,
     orderedSet,
     sanitized_Request,
     str_to_int,
@@ -48,6 +49,8 @@ class PornHubIE(InfoExtractor):
             'dislike_count': int,
             'comment_count': int,
             'age_limit': 18,
+            'tags': list,
+            'categories': list,
         },
     }, {
         # non-ASCII title
@@ -63,6 +66,8 @@ class PornHubIE(InfoExtractor):
             'dislike_count': int,
             'comment_count': int,
             'age_limit': 18,
+            'tags': list,
+            'categories': list,
         },
         'params': {
             'skip_download': True,
@@ -183,6 +188,15 @@ class PornHubIE(InfoExtractor):
             })
         self._sort_formats(formats)
 
+        page_params = self._parse_json(self._search_regex(
+            r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
+            webpage, 'page parameters', group='data', default='{}'),
+            video_id, transform_source=js_to_json, fatal=False)
+        tags = categories = None
+        if page_params:
+            tags = page_params.get('tags', '').split(',')
+            categories = page_params.get('categories', '').split(',')
+
         return {
             'id': video_id,
             'uploader': video_uploader,
@@ -195,6 +209,8 @@ class PornHubIE(InfoExtractor):
             'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
+            'tags': tags,
+            'categories': categories,
         }
 
 

youtube_dl/extractor/qqmusic.py

@@ -18,7 +18,7 @@ from ..utils import (
 class QQMusicIE(InfoExtractor):
     IE_NAME = 'qqmusic'
     IE_DESC = 'QQ音乐'
-    _VALID_URL = r'https?://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
+    _VALID_URL = r'https?://y\.qq\.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
     _TESTS = [{
         'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
         'md5': '9ce1c1c8445f561506d2e3cfb0255705',
@@ -172,7 +172,7 @@ class QQPlaylistBaseIE(InfoExtractor):
 class QQMusicSingerIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:singer'
     IE_DESC = 'QQ音乐 - 歌手'
-    _VALID_URL = r'https?://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
+    _VALID_URL = r'https?://y\.qq\.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
     _TEST = {
         'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
         'info_dict': {
@@ -217,7 +217,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
 class QQMusicAlbumIE(QQPlaylistBaseIE):
     IE_NAME = 'qqmusic:album'
     IE_DESC = 'QQ音乐 - 专辑'
-    _VALID_URL = r'https?://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
+    _VALID_URL = r'https?://y\.qq\.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
 
     _TESTS = [{
         'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',

youtube_dl/extractor/radiocanada.py

@@ -13,6 +13,7 @@ from ..utils import (
     xpath_element,
     ExtractorError,
     determine_protocol,
+    unsmuggle_url,
 )
 
 
@@ -35,28 +36,51 @@ class RadioCanadaIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
         app_code, video_id = re.match(self._VALID_URL, url).groups()
 
-        device_types = ['ipad', 'android']
+        metadata = self._download_xml(
+            'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
+            video_id, note='Downloading metadata XML', query={
+                'appCode': app_code,
+                'idMedia': video_id,
+            })
+
+        def get_meta(name):
+            el = find_xpath_attr(metadata, './/Meta', 'name', name)
+            return el.text if el is not None else None
+
+        if get_meta('protectionType'):
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
+        device_types = ['ipad']
         if app_code != 'toutv':
             device_types.append('flash')
+        if not smuggled_data:
+            device_types.append('android')
 
         formats = []
         # TODO: extract f4m formats
         # f4m formats can be extracted using flashhd device_type but they produce unplayable file
         for device_type in device_types:
-            v_data = self._download_xml(
+            validation_url = 'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx'
-                'http://api.radio-canada.ca/validationMedia/v1/Validation.ashx',
+            query = {
-                video_id, note='Downloading %s XML' % device_type, query={
+                'appCode': app_code,
-                    'appCode': app_code,
+                'idMedia': video_id,
-                    'idMedia': video_id,
+                'connectionType': 'broadband',
-                    'connectionType': 'broadband',
+                'multibitrate': 'true',
-                    'multibitrate': 'true',
+                'deviceType': device_type,
-                    'deviceType': device_type,
+            }
+            if smuggled_data:
+                validation_url = 'https://services.radio-canada.ca/media/validation/v2/'
+                query.update(smuggled_data)
+            else:
+                query.update({
                     # paysJ391wsHjbOJwvCs26toz and bypasslock are used to bypass geo-restriction
                     'paysJ391wsHjbOJwvCs26toz': 'CA',
                     'bypasslock': 'NZt5K62gRqfc',
-                }, fatal=False)
+                })
+            v_data = self._download_xml(validation_url, video_id, note='Downloading %s XML' % device_type, query=query, fatal=False)
             v_url = xpath_text(v_data, 'url')
             if not v_url:
                 continue
@@ -101,17 +125,6 @@ class RadioCanadaIE(InfoExtractor):
                                 f4m_id='hds', fatal=False))
         self._sort_formats(formats)
 
-        metadata = self._download_xml(
-            'http://api.radio-canada.ca/metaMedia/v1/index.ashx',
-            video_id, note='Downloading metadata XML', query={
-                'appCode': app_code,
-                'idMedia': video_id,
-            })
-
-        def get_meta(name):
-            el = find_xpath_attr(metadata, './/Meta', 'name', name)
-            return el.text if el is not None else None
-
         return {
             'id': video_id,
             'title': get_meta('Title'),

youtube_dl/extractor/rottentomatoes.py

@@ -5,7 +5,7 @@ from .internetvideoarchive import InternetVideoArchiveIE
 
 
 class RottenTomatoesIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.rottentomatoes\.com/m/[^/]+/trailers/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?rottentomatoes\.com/m/[^/]+/trailers/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',

youtube_dl/extractor/roxwel.py

@@ -7,7 +7,7 @@ from ..utils import unified_strdate, determine_ext
 
 
 class RoxwelIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)'
+    _VALID_URL = r'https?://(?:www\.)?roxwel\.com/player/(?P<filename>.+?)(\.|\?|$)'
 
     _TEST = {
         'url': 'http://www.roxwel.com/player/passionpittakeawalklive.html',

youtube_dl/extractor/rtve.py

@@ -64,7 +64,7 @@ def _decrypt_url(png):
 class RTVEALaCartaIE(InfoExtractor):
     IE_NAME = 'rtve.es:alacarta'
     IE_DESC = 'RTVE a la carta'
-    _VALID_URL = r'https?://www\.rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
@@ -184,7 +184,7 @@ class RTVEInfantilIE(InfoExtractor):
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'
-    _VALID_URL = r'https?://www\.rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/directo/la-1/',
@@ -226,7 +226,7 @@ class RTVELiveIE(InfoExtractor):
 
 class RTVETelevisionIE(InfoExtractor):
     IE_NAME = 'rtve.es:television'
-    _VALID_URL = r'https?://www\.rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
 
     _TEST = {
         'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',

youtube_dl/extractor/safari.py

@@ -103,13 +103,13 @@ class SafariIE(SafariBaseIE):
 
         webpage = self._download_webpage(url, video_id)
         reference_id = self._search_regex(
-            r'data-reference-id=(["\'])(?P<id>.+?)\1',
+            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',
+            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',
+            r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'kaltura uiconf id', group='id')
 
         query = {

youtube_dl/extractor/screenjunkies.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class ScreenJunkiesIE(InfoExtractor):
-    _VALID_URL = r'https?://www.screenjunkies.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?screenjunkies\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
     _TESTS = [{
         'url': 'http://www.screenjunkies.com/video/best-quentin-tarantino-movie-2841915',
         'md5': '5c2b686bec3d43de42bde9ec047536b0',

youtube_dl/extractor/senateisvp.py

@@ -48,7 +48,7 @@ class SenateISVPIE(InfoExtractor):
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
     _IE_NAME = 'senate.gov'
-    _VALID_URL = r'https?://www\.senate\.gov/isvp/?\?(?P<qs>.+)'
+    _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
         'info_dict': {

youtube_dl/extractor/slideshare.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class SlideshareIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
+    _VALID_URL = r'https?://(?:www\.)?slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
 
     _TEST = {
         'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',

youtube_dl/extractor/spiegel.py

@@ -103,7 +103,7 @@ class SpiegelIE(InfoExtractor):
 
 
 class SpiegelArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
     IE_NAME = 'Spiegel:Article'
     IE_DESC = 'Articles on spiegel.de'
     _TESTS = [{

youtube_dl/extractor/svt.py

@@ -16,7 +16,7 @@ class SVTBaseIE(InfoExtractor):
     def _extract_video(self, video_info, video_id):
         formats = []
         for vr in video_info['videoReferences']:
-            player_type = vr.get('playerType')
+            player_type = vr.get('playerType') or vr.get('format')
             vurl = vr['url']
             ext = determine_ext(vurl)
             if ext == 'm3u8':

youtube_dl/extractor/syfy.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class SyfyIE(AdobePassIE):
-    _VALID_URL = r'https?://www\.syfy\.com/(?:[^/]+/)?videos/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?syfy\.com/(?:[^/]+/)?videos/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'http://www.syfy.com/theinternetruinedmylife/videos/the-internet-ruined-my-life-season-1-trailer',
         'info_dict': {

youtube_dl/extractor/teachingchannel.py

@@ -7,7 +7,7 @@ from .ooyala import OoyalaIE
 
 
 class TeachingChannelIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.teachingchannel\.org/videos/(?P<title>.+)'
+    _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos/(?P<title>.+)'
 
     _TEST = {
         'url': 'https://www.teachingchannel.org/videos/teacher-teaming-evolution',

youtube_dl/extractor/telecinco.py

@@ -6,7 +6,7 @@ from .mitele import MiTeleBaseIE
 
 class TelecincoIE(MiTeleBaseIE):
     IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
-    _VALID_URL = r'https?://www\.(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
+    _VALID_URL = r'https?://(?:www\.)?(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
 
     _TESTS = [{
         'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',

youtube_dl/extractor/telequebec.py

@@ -0,0 +1,36 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class TeleQuebecIE(InfoExtractor):
+    _VALID_URL = r'https?://zonevideo\.telequebec\.tv/media/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://zonevideo.telequebec.tv/media/20984/le-couronnement-de-new-york/couronnement-de-new-york',
+        'md5': 'fe95a0957e5707b1b01f5013e725c90f',
+        'info_dict': {
+            'id': '20984',
+            'ext': 'mp4',
+            'title': 'Le couronnement de New York',
+            'description': 'md5:f5b3d27a689ec6c1486132b2d687d432',
+            'upload_date': '20160220',
+            'timestamp': 1455965438,
+        }
+    }
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        media_data = self._download_json(
+            'https://mnmedias.api.telequebec.tv/api/v2/media/' + media_id,
+            media_id)['media']
+        return {
+            '_type': 'url_transparent',
+            'id': media_id,
+            'url': 'limelight:media:' + media_data['streamInfo']['sourceId'],
+            'title': media_data['title'],
+            'description': media_data.get('descriptions', [{'text': None}])[0].get('text'),
+            'duration': int_or_none(media_data.get('durationInMilliseconds'), 1000),
+            'ie_key': 'LimelightMedia',
+        }

youtube_dl/extractor/telewebion.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class TelewebionIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.telewebion\.com/#!/episode/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?telewebion\.com/#!/episode/(?P<id>\d+)'
 
     _TEST = {
         'url': 'http://www.telewebion.com/#!/episode/1263668/',

youtube_dl/extractor/tfo.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    HEADRequest,
+    ExtractorError,
+    int_or_none,
+)
+
+
+class TFOIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
+        'md5': '47c987d0515561114cf03d1226a9d4c7',
+        'info_dict': {
+            'id': '100463871',
+            'ext': 'mp4',
+            'title': 'Video Game Hackathon',
+            'description': 'md5:558afeba217c6c8d96c60e5421795c07',
+            'upload_date': '20160212',
+            'timestamp': 1455310233,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        self._request_webpage(HEADRequest('http://www.tfo.org/'), video_id)
+        infos = self._download_json(
+            'http://www.tfo.org/api/web/video/get_infos', video_id, data=json.dumps({
+                'product_id': video_id,
+            }).encode(), headers={
+                'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
+            })
+        if infos.get('success') == 0:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, infos['msg']), expected=True)
+        video_data = infos['data']
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': 'limelight:media:' + video_data['llid'],
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'series': video_data.get('collection'),
+            'season_number': int_or_none(video_data.get('season')),
+            'episode_number': int_or_none(video_data.get('episode')),
+            'duration': int_or_none(video_data.get('duration')),
+            'ie_key': 'LimelightMedia',
+        }

youtube_dl/extractor/theintercept.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class TheInterceptIE(InfoExtractor):
-    _VALID_URL = r'https://theintercept.com/fieldofvision/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://theintercept\.com/fieldofvision/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://theintercept.com/fieldofvision/thisisacoup-episode-four-surrender-or-die/',
         'md5': '145f28b41d44aab2f87c0a4ac8ec95bd',

youtube_dl/extractor/thescene.py

@@ -7,7 +7,7 @@ from ..utils import qualities
 
 
 class TheSceneIE(InfoExtractor):
-    _VALID_URL = r'https://thescene\.com/watch/[^/]+/(?P<id>[^/#?]+)'
+    _VALID_URL = r'https?://thescene\.com/watch/[^/]+/(?P<id>[^/#?]+)'
 
     _TEST = {
         'url': 'https://thescene.com/watch/vogue/narciso-rodriguez-spring-2013-ready-to-wear',