Merge branch 'master' into totalwebcasting

[skip ci]

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.14*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.12.14**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.31*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.12.31**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2017.12.14
+[debug] youtube-dl version 2017.12.31
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

.travis.yml

@@ -7,16 +7,21 @@ python:
   - "3.4"
   - "3.5"
   - "3.6"
+  - "pypy"
+  - "pypy3"
 sudo: false
 env:
   - YTDL_TEST_SET=core
   - YTDL_TEST_SET=download
 matrix:
+  include:
+    - env: JYTHON=true; YTDL_TEST_SET=core
+    - env: JYTHON=true; YTDL_TEST_SET=download
   fast_finish: true
   allow_failures:
     - env: YTDL_TEST_SET=download
+    - env: JYTHON=true; YTDL_TEST_SET=core
+    - env: JYTHON=true; YTDL_TEST_SET=download
+before_install:
+  - if [ "$JYTHON" == "true" ]; then ./devscripts/install_jython.sh; export PATH="$HOME/jython/bin:$PATH"; fi
 script: ./devscripts/run_tests.sh
-notifications:
-  email:
-    - filippo.valsorda@gmail.com
-    - yasoob.khld@gmail.com

ChangeLog

@@ -1,3 +1,83 @@
+version <unreleased>
+
+Extractors
+* [youku] Fix list extraction (#15135)
+* [openload] Fix extraction (#15166)
+* [rtve.es:alacarta] Fix extraction of some new URLs
+
+
+version 2017.12.31
+
+Core
++ [extractor/common] Add container meta field for formats extracted
+  in _parse_mpd_formats (#13616)
++ [downloader/hls] Use HTTP headers for key request
+* [common] Use AACL as the default fourcc when AudioTag is 255
+* [extractor/common] Fix extraction of DASH formats with the same
+  representation id (#15111)
+
+Extractors
++ [slutload] Add support for mobile URLs (#14806)
+* [abc:iview] Bypass geo restriction
+* [abc:iview] Fix extraction (#14711, #14782, #14838, #14917, #14963, #14985,
+  #15035, #15057, #15061, #15071, #15095, #15106)
+* [openload] Fix extraction (#15118)
+- [sandia] Remove extractor
+- [collegerama] Remove extractor
++ [mediasite] Add support for sites based on Mediasite Video Platform (#5428,
+  #11185, #14343)
++ [ufctv] Add support for ufc.tv (#14520)
+* [pluralsight] Fix missing first line of subtitles (#11118)
+* [openload] Fallback on f-page extraction (#14665, #14879)
+* [vimeo] Improve password protected videos extraction (#15114)
+* [aws] Fix canonical/signed headers generation on python 2 (#15102)
+
+
+version 2017.12.28
+
+Extractors
++ [internazionale] Add support for internazionale.it (#14973)
+* [playtvak] Relax video regular expression and make description optional
+  (#15037)
++ [filmweb] Add support for filmweb.no (#8773, #10368)
++ [23video] Add support for 23video.com
++ [espn] Add support for fivethirtyeight.com (#6864)
++ [umg:de] Add support for universal-music.de (#11582, #11584)
++ [espn] Add support for espnfc and extract more formats (#8053)
+* [youku] Update ccode (#14880)
++ [openload] Add support for oload.stream (#15070)
+* [youku] Fix list extraction (#15065)
+
+
+version 2017.12.23
+
+Core
+* [extractor/common] Move X-Forwarded-For setup code into _request_webpage
++ [YoutubeDL] Add support for playlist_uploader and playlist_uploader_id in
+  output template (#11427, #15018)
++ [extractor/common] Introduce uploader, uploader_id and uploader_url
+  meta fields for playlists (#11427, #15018)
+* [downloader/fragment] Encode filename of fragment being removed (#15020)
++ [utils] Add another date format pattern (#14999)
+
+Extractors
++ [kaltura] Add another embed pattern for entry_id
++ [7plus] Add support for 7plus.com.au (#15043)
+* [animeondemand] Relax login error regular expression
++ [shahid] Add support for show pages (#7401)
++ [youtube] Extract uploader, uploader_id and uploader_url for playlists
+  (#11427, #15018)
+* [afreecatv] Improve format extraction (#15019)
++ [cspan] Add support for audio only pages and catch page errors (#14995)
++ [mailru] Add support for embed URLs (#14904)
+* [crunchyroll] Future-proof XML element checks (#15013)
+* [cbslocal] Fix timestamp extraction (#14999, #15000)
+* [discoverygo] Correct TTML subtitle extension
+* [vk] Make view count optional (#14979)
+* [disney] Skip Apple FairPlay formats (#14982)
+* [voot] Fix format extraction (#14758)
+
+
 version 2017.12.14
 
 Core
@@ -148,8 +228,8 @@ Extractors
 + [fxnetworks] Extract series metadata (#14603)
 + [younow] Add support for younow.com (#9255, #9432, #12436)
 * [dctptv] Fix extraction (#14599)
-* [youtube] Restrict embed regex (#14600)
-* [vimeo] Restrict iframe embed regex (#14600)
+* [youtube] Restrict embed regular expression (#14600)
+* [vimeo] Restrict iframe embed regular expression (#14600)
 * [soundgasm] Improve extraction (#14588)
 - [myvideo] Remove extractor (#8557)
 + [nbc] Add support for classic-tv videos (#14575)

MANIFEST.in

@@ -1,7 +1,9 @@
 include README.md
-include test/*.py
-include test/*.json
+include LICENSE
+include AUTHORS
+include ChangeLog
 include youtube-dl.bash-completion
 include youtube-dl.fish
 include youtube-dl.1
 recursive-include docs Makefile conf.py *.rst
+recursive-include test *

Makefile

@@ -110,7 +110,7 @@ _EXTRACTOR_FILES = $(shell find youtube_dl/extractor -iname '*.py' -and -not -in
 youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 
-youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog
+youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog AUTHORS
 	@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
@@ -122,7 +122,7 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		--exclude 'docs/_build' \
 		-- \
 		bin devscripts test youtube_dl docs \
-		ChangeLog LICENSE README.md README.txt \
+		ChangeLog AUTHORS LICENSE README.md README.txt \
 		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
 		youtube-dl.zsh youtube-dl.fish setup.py setup.cfg \
 		youtube-dl

README.md

@@ -539,6 +539,8 @@ The basic usage is not to set any template arguments when downloading a single f
  - `playlist_index` (numeric): Index of the video in the playlist padded with leading zeros according to the total length of the playlist
  - `playlist_id` (string): Playlist identifier
  - `playlist_title` (string): Playlist title
+ - `playlist_uploader` (string): Full name of the playlist uploader
+ - `playlist_uploader_id` (string): Nickname or id of the playlist uploader
 
 Available for the video that belongs to some logical chapter or section:
 

devscripts/install_jython.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+wget http://central.maven.org/maven2/org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar
+java -jar jython-installer-2.7.1.jar -s -d "$HOME/jython"
+$HOME/jython/bin/jython -m pip install nose

docs/supportedsites.md

@@ -3,6 +3,7 @@
  - **1up.com**
  - **20min**
  - **220.ro**
+ - **23video**
  - **24video**
  - **3qsdn**: 3Q SDN
  - **3sat**
@@ -10,6 +11,7 @@
  - **56.com**
  - **5min**
  - **6play**
+ - **7plus**
  - **8tracks**
  - **91porn**
  - **9c9media**
@@ -169,7 +171,6 @@
  - **CNN**
  - **CNNArticle**
  - **CNNBlogs**
- - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
  - **ComedyCentralFullEpisodes**
@@ -268,6 +269,8 @@
  - **Fczenit**
  - **filmon**
  - **filmon:channel**
+ - **Filmweb**
+ - **FiveThirtyEight**
  - **FiveTV**
  - **Flickr**
  - **Flipagram**
@@ -358,6 +361,7 @@
  - **InfoQ**
  - **Instagram**
  - **instagram:user**: Instagram user profile
+ - **Internazionale**
  - **InternetVideoArchive**
  - **IPrima**
  - **iqiyi**: 爱奇艺
@@ -444,6 +448,7 @@
  - **media.ccc.de**
  - **Medialaan**
  - **Mediaset**
+ - **Mediasite**
  - **Medici**
  - **megaphone.fm**: megaphone.fm embedded players
  - **Meipai**: 美拍
@@ -712,7 +717,6 @@
  - **safari**: safaribooksonline.com online video
  - **safari:api**
  - **safari:course**: safaribooksonline.com online courses
- - **Sandia**: Sandia National Laboratories
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
@@ -728,6 +732,7 @@
  - **Servus**
  - **Sexu**
  - **Shahid**
+ - **ShahidShow**
  - **Shared**: shared.sx
  - **ShowRoomLive**
  - **Sina**
@@ -886,7 +891,9 @@
  - **udemy**
  - **udemy:course**
  - **UDNEmbed**: 聯合影音
+ - **UFCTV**
  - **UKTVPlay**
+ - **umg:de**: Universal Music Deutschland
  - **Unistra**
  - **Unity**
  - **uol.com.br**

setup.py

@@ -109,6 +109,7 @@ setup(
     author_email='ytdl@yt-dl.org',
     maintainer='Sergey M.',
     maintainer_email='dstftw@gmail.com',
+    license='Unlicense',
     packages=[
         'youtube_dl',
         'youtube_dl.extractor', 'youtube_dl.downloader',

test/test_InfoExtractor.py

@@ -493,9 +493,20 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
         _TEST_CASES = [
             (
                 # https://github.com/rg3/youtube-dl/issues/13919
+                # Also tests duplicate representation ids, see
+                # https://github.com/rg3/youtube-dl/issues/15111
                 'float_duration',
                 'http://unknown/manifest.mpd',
                 [{
+                    'manifest_url': 'http://unknown/manifest.mpd',
+                    'ext': 'm4a',
+                    'format_id': '318597',
+                    'format_note': 'DASH audio',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'mp4a.40.2',
+                    'vcodec': 'none',
+                    'tbr': 61.587,
+                }, {
                     'manifest_url': 'http://unknown/manifest.mpd',
                     'ext': 'mp4',
                     'format_id': '318597',

test/test_utils.py

@@ -343,6 +343,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
         self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
         self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
+        self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
 
     def test_determine_ext(self):
         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')

youtube_dl/YoutubeDL.py

@@ -975,6 +975,8 @@ class YoutubeDL(object):
                     'playlist': playlist,
                     'playlist_id': ie_result.get('id'),
                     'playlist_title': ie_result.get('title'),
+                    'playlist_uploader': ie_result.get('uploader'),
+                    'playlist_uploader_id': ie_result.get('uploader_id'),
                     'playlist_index': i + playliststart,
                     'extractor': ie_result['extractor'],
                     'webpage_url': ie_result['webpage_url'],
@@ -2231,8 +2233,16 @@ class YoutubeDL(object):
                 sys.exc_clear()
             except Exception:
                 pass
-        self._write_string('[debug] Python version %s - %s\n' % (
-            platform.python_version(), platform_name()))
+
+        def python_implementation():
+            impl_name = platform.python_implementation()
+            if impl_name == 'PyPy' and hasattr(sys, 'pypy_version_info'):
+                return impl_name + ' version %d.%d.%d' % sys.pypy_version_info[:3]
+            return impl_name
+
+        self._write_string('[debug] Python version %s (%s) - %s\n' % (
+            platform.python_version(), python_implementation(),
+            platform_name()))
 
         exe_versions = FFmpegPostProcessor.get_versions(self)
         exe_versions['rtmpdump'] = rtmpdump_version()

youtube_dl/compat.py

@@ -3,12 +3,14 @@ from __future__ import unicode_literals
 
 import binascii
 import collections
+import ctypes
 import email
 import getpass
 import io
 import itertools
 import optparse
 import os
+import platform
 import re
 import shlex
 import shutil
@@ -2906,6 +2908,24 @@ except ImportError:  # not 2.6+ or is 3.x
     except ImportError:
         compat_zip = zip
 
+if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4, 0):
+    # PyPy2 prior to version 5.4.0 expects byte strings as Windows function
+    # names, see the original PyPy issue [1] and the youtube-dl one [2].
+    # 1. https://bitbucket.org/pypy/pypy/issues/2360/windows-ctypescdll-typeerror-function-name
+    # 2. https://github.com/rg3/youtube-dl/pull/4392
+    def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
+        real = ctypes.WINFUNCTYPE(*args, **kwargs)
+
+        def resf(tpl, *args, **kwargs):
+            funcname, dll = tpl
+            return real((str(funcname), dll), *args, **kwargs)
+
+        return resf
+else:
+    def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
+        return ctypes.WINFUNCTYPE(*args, **kwargs)
+
+
 __all__ = [
     'compat_HTMLParseError',
     'compat_HTMLParser',
@@ -2914,6 +2934,7 @@ __all__ = [
     'compat_chr',
     'compat_cookiejar',
     'compat_cookies',
+    'compat_ctypes_WINFUNCTYPE',
     'compat_etree_fromstring',
     'compat_etree_register_namespace',
     'compat_expanduser',

youtube_dl/downloader/fragment.py

@@ -112,7 +112,7 @@ class FragmentFD(FileDownloader):
             if self.__do_ytdl_file(ctx):
                 self._write_ytdl_file(ctx)
             if not self.params.get('keep_fragments', False):
-                os.remove(ctx['fragment_filename_sanitized'])
+                os.remove(encodeFilename(ctx['fragment_filename_sanitized']))
             del ctx['fragment_filename_sanitized']
 
     def _prepare_frag_download(self, ctx):

youtube_dl/downloader/hls.py

@@ -163,7 +163,8 @@ class HlsFD(FragmentFD):
                         return False
                     if decrypt_info['METHOD'] == 'AES-128':
                         iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
-                        decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(decrypt_info['URI']).read()
+                        decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
+                            self._prepare_url(info_dict, decrypt_info['URI'])).read()
                         frag_content = AES.new(
                             decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
                     self._append_fragment(ctx, frag_content)

youtube_dl/extractor/abc.py

@@ -1,6 +1,9 @@
 from __future__ import unicode_literals
 
+import hashlib
+import hmac
 import re
+import time
 
 from .common import InfoExtractor
 from ..compat import compat_str
@@ -10,6 +13,7 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     try_get,
+    update_url_query,
 )
 
 
@@ -101,21 +105,24 @@ class ABCIE(InfoExtractor):
 class ABCIViewIE(InfoExtractor):
     IE_NAME = 'abc.net.au:iview'
     _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
+    _GEO_COUNTRIES = ['AU']
 
     # ABC iview programs are normally available for 14 days only.
     _TESTS = [{
-        'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00',
+        'url': 'http://iview.abc.net.au/programs/call-the-midwife/ZW0898A003S00',
         'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
         'info_dict': {
-            'id': 'ZX9735A001S00',
+            'id': 'ZW0898A003S00',
             'ext': 'mp4',
-            'title': 'Diaries Of A Broken Mind',
-            'description': 'md5:7de3903874b7a1be279fe6b68718fc9e',
-            'upload_date': '20161010',
-            'uploader_id': 'abc2',
-            'timestamp': 1476064920,
+            'title': 'Series 5 Ep 3',
+            'description': 'md5:e0ef7d4f92055b86c4f33611f180ed79',
+            'upload_date': '20171228',
+            'uploader_id': 'abc1',
+            'timestamp': 1514499187,
+        },
+        'params': {
+            'skip_download': True,
         },
-        'skip': 'Video gone',
     }]
 
     def _real_extract(self, url):
@@ -126,20 +133,30 @@ class ABCIViewIE(InfoExtractor):
         title = video_params.get('title') or video_params['seriesTitle']
         stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
 
-        format_urls = [
-            try_get(stream, lambda x: x['hds-unmetered'], compat_str)]
+        house_number = video_params.get('episodeHouseNumber')
+        path = '/auth/hls/sign?ts={0}&hn={1}&d=android-mobile'.format(
+            int(time.time()), house_number)
+        sig = hmac.new(
+            'android.content.res.Resources'.encode('utf-8'),
+            path.encode('utf-8'), hashlib.sha256).hexdigest()
+        token = self._download_webpage(
+            'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
 
-        # May have higher quality video
-        sd_url = try_get(
-            stream, lambda x: x['streams']['hds']['sd'], compat_str)
-        if sd_url:
-            format_urls.append(sd_url.replace('metered', 'um'))
+        def tokenize_url(url, token):
+            return update_url_query(url, {
+                'hdnea': token,
+            })
 
-        formats = []
-        for format_url in format_urls:
-            if format_url:
-                formats.extend(
-                    self._extract_akamai_formats(format_url, video_id))
+        for sd in ('sd', 'sd-low'):
+            sd_url = try_get(
+                stream, lambda x: x['streams']['hls'][sd], compat_str)
+            if not sd_url:
+                continue
+            formats = self._extract_m3u8_formats(
+                tokenize_url(sd_url, token), video_id, 'mp4',
+                entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+            if formats:
+                break
         self._sort_formats(formats)
 
         subtitles = {}

youtube_dl/extractor/acast.py

@@ -8,7 +8,7 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     int_or_none,
-    parse_iso8601,
+    unified_timestamp,
     OnDemandPagedList,
 )
 
@@ -32,7 +32,7 @@ class ACastIE(InfoExtractor):
     }, {
         # test with multiple blings
         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
-        'md5': '55c0097badd7095f494c99a172f86501',
+        'md5': 'e87d5b8516cd04c0d81b6ee1caca28d0',
         'info_dict': {
             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
             'ext': 'mp3',
@@ -40,23 +40,24 @@ class ACastIE(InfoExtractor):
             'timestamp': 1477346700,
             'upload_date': '20161024',
             'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
-            'duration': 2797,
+            'duration': 2766,
         }
     }]
 
     def _real_extract(self, url):
         channel, display_id = re.match(self._VALID_URL, url).groups()
         cast_data = self._download_json(
-            'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
+            'https://play-api.acast.com/splash/%s/%s' % (channel, display_id), display_id)
+        e = cast_data['result']['episode']
         return {
-            'id': compat_str(cast_data['id']),
+            'id': compat_str(e['id']),
             'display_id': display_id,
-            'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0],
-            'title': cast_data['name'],
-            'description': cast_data.get('description'),
-            'thumbnail': cast_data.get('image'),
-            'timestamp': parse_iso8601(cast_data.get('publishingDate')),
-            'duration': int_or_none(cast_data.get('duration')),
+            'url': e['mediaUrl'],
+            'title': e['name'],
+            'description': e.get('description'),
+            'thumbnail': e.get('image'),
+            'timestamp': unified_timestamp(e.get('publishingDate')),
+            'duration': int_or_none(e.get('duration')),
         }
 
 

youtube_dl/extractor/afreecatv.py

@@ -228,10 +228,19 @@ class AfreecaTVIE(InfoExtractor):
                     r'^(\d{8})_', key, 'upload date', default=None)
                 file_duration = int_or_none(file_element.get('duration'))
                 format_id = key if key else '%s_%s' % (video_id, file_num)
-                formats = self._extract_m3u8_formats(
-                    file_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls',
-                    note='Downloading part %d m3u8 information' % file_num)
+                if determine_ext(file_url) == 'm3u8':
+                    formats = self._extract_m3u8_formats(
+                        file_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls',
+                        note='Downloading part %d m3u8 information' % file_num)
+                else:
+                    formats = [{
+                        'url': file_url,
+                        'format_id': 'http',
+                    }]
+                if not formats:
+                    continue
+                self._sort_formats(formats)
                 file_info = common_entry.copy()
                 file_info.update({
                     'id': format_id,

youtube_dl/extractor/animeondemand.py

@@ -85,8 +85,8 @@ class AnimeOnDemandIE(InfoExtractor):
 
         if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
             error = self._search_regex(
-                r'<p class="alert alert-danger">(.+?)</p>',
-                response, 'error', default=None)
+                r'<p[^>]+\bclass=(["\'])(?:(?!\1).)*\balert\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</p>',
+                response, 'error', default=None, group='error')
             if error:
                 raise ExtractorError('Unable to login: %s' % error, expected=True)
             raise ExtractorError('Unable to log in')

youtube_dl/extractor/aws.py

@@ -0,0 +1,78 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import datetime
+import hashlib
+import hmac
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlencode
+
+
+class AWSIE(InfoExtractor):
+    _AWS_ALGORITHM = 'AWS4-HMAC-SHA256'
+    _AWS_REGION = 'us-east-1'
+
+    def _aws_execute_api(self, aws_dict, video_id, query=None):
+        query = query or {}
+        amz_date = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ')
+        date = amz_date[:8]
+        headers = {
+            'Accept': 'application/json',
+            'Host': self._AWS_PROXY_HOST,
+            'X-Amz-Date': amz_date,
+            'X-Api-Key': self._AWS_API_KEY
+        }
+        session_token = aws_dict.get('session_token')
+        if session_token:
+            headers['X-Amz-Security-Token'] = session_token
+
+        def aws_hash(s):
+            return hashlib.sha256(s.encode('utf-8')).hexdigest()
+
+        # Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
+        canonical_querystring = compat_urllib_parse_urlencode(query)
+        canonical_headers = ''
+        for header_name, header_value in sorted(headers.items()):
+            canonical_headers += '%s:%s\n' % (header_name.lower(), header_value)
+        signed_headers = ';'.join([header.lower() for header in sorted(headers.keys())])
+        canonical_request = '\n'.join([
+            'GET',
+            aws_dict['uri'],
+            canonical_querystring,
+            canonical_headers,
+            signed_headers,
+            aws_hash('')
+        ])
+
+        # Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
+        credential_scope_list = [date, self._AWS_REGION, 'execute-api', 'aws4_request']
+        credential_scope = '/'.join(credential_scope_list)
+        string_to_sign = '\n'.join([self._AWS_ALGORITHM, amz_date, credential_scope, aws_hash(canonical_request)])
+
+        # Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
+        def aws_hmac(key, msg):
+            return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
+
+        def aws_hmac_digest(key, msg):
+            return aws_hmac(key, msg).digest()
+
+        def aws_hmac_hexdigest(key, msg):
+            return aws_hmac(key, msg).hexdigest()
+
+        k_signing = ('AWS4' + aws_dict['secret_key']).encode('utf-8')
+        for value in credential_scope_list:
+            k_signing = aws_hmac_digest(k_signing, value)
+
+        signature = aws_hmac_hexdigest(k_signing, string_to_sign)
+
+        # Task 4: http://docs.aws.amazon.com/general/latest/gr/sigv4-add-signature-to-request.html
+        headers['Authorization'] = ', '.join([
+            '%s Credential=%s/%s' % (self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope),
+            'SignedHeaders=%s' % signed_headers,
+            'Signature=%s' % signature,
+        ])
+
+        return self._download_json(
+            'https://%s%s%s' % (self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''),
+            video_id, headers=headers)

youtube_dl/extractor/brightcove.py

@@ -464,7 +464,7 @@ class BrightcoveNewIE(AdobePassIE):
             'timestamp': 1441391203,
             'upload_date': '20150904',
             'uploader_id': '929656772001',
-            'formats': 'mincount:22',
+            'formats': 'mincount:20',
         },
     }, {
         # with rtmp streams
@@ -478,7 +478,7 @@ class BrightcoveNewIE(AdobePassIE):
             'timestamp': 1433556729,
             'upload_date': '20150606',
             'uploader_id': '4036320279001',
-            'formats': 'mincount:41',
+            'formats': 'mincount:39',
         },
         'params': {
             # m3u8 download
@@ -564,59 +564,7 @@ class BrightcoveNewIE(AdobePassIE):
 
         return entries
 
-    def _real_extract(self, url):
-        url, smuggled_data = unsmuggle_url(url, {})
-        self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
-
-        account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
-
-        webpage = self._download_webpage(
-            'http://players.brightcove.net/%s/%s_%s/index.min.js'
-            % (account_id, player_id, embed), video_id)
-
-        policy_key = None
-
-        catalog = self._search_regex(
-            r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
-        if catalog:
-            catalog = self._parse_json(
-                js_to_json(catalog), video_id, fatal=False)
-            if catalog:
-                policy_key = catalog.get('policyKey')
-
-        if not policy_key:
-            policy_key = self._search_regex(
-                r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
-                webpage, 'policy key', group='pk')
-
-        api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
-        try:
-            json_data = self._download_json(api_url, video_id, headers={
-                'Accept': 'application/json;pk=%s' % policy_key
-            })
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
-                json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
-                message = json_data.get('message') or json_data['error_code']
-                if json_data.get('error_subcode') == 'CLIENT_GEO':
-                    self.raise_geo_restricted(msg=message)
-                raise ExtractorError(message, expected=True)
-            raise
-
-        errors = json_data.get('errors')
-        if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
-            custom_fields = json_data['custom_fields']
-            tve_token = self._extract_mvpd_auth(
-                smuggled_data['source_url'], video_id,
-                custom_fields['bcadobepassrequestorid'],
-                custom_fields['bcadobepassresourceid'])
-            json_data = self._download_json(
-                api_url, video_id, headers={
-                    'Accept': 'application/json;pk=%s' % policy_key
-                }, query={
-                    'tveToken': tve_token,
-                })
-
+    def _parse_brightcove_metadata(self, json_data, video_id):
         title = json_data['name'].strip()
 
         formats = []
@@ -682,6 +630,7 @@ class BrightcoveNewIE(AdobePassIE):
                     })
                 formats.append(f)
 
+        errors = json_data.get('errors')
         if not formats and errors:
             error = errors[0]
             raise ExtractorError(
@@ -708,9 +657,64 @@ class BrightcoveNewIE(AdobePassIE):
             'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
             'duration': duration,
             'timestamp': parse_iso8601(json_data.get('published_at')),
-            'uploader_id': account_id,
+            'uploader_id': json_data.get('account_id'),
             'formats': formats,
             'subtitles': subtitles,
             'tags': json_data.get('tags', []),
             'is_live': is_live,
         }
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
+
+        account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
+
+        webpage = self._download_webpage(
+            'http://players.brightcove.net/%s/%s_%s/index.min.js'
+            % (account_id, player_id, embed), video_id)
+
+        policy_key = None
+
+        catalog = self._search_regex(
+            r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
+        if catalog:
+            catalog = self._parse_json(
+                js_to_json(catalog), video_id, fatal=False)
+            if catalog:
+                policy_key = catalog.get('policyKey')
+
+        if not policy_key:
+            policy_key = self._search_regex(
+                r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
+                webpage, 'policy key', group='pk')
+
+        api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
+        try:
+            json_data = self._download_json(api_url, video_id, headers={
+                'Accept': 'application/json;pk=%s' % policy_key
+            })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
+                message = json_data.get('message') or json_data['error_code']
+                if json_data.get('error_subcode') == 'CLIENT_GEO':
+                    self.raise_geo_restricted(msg=message)
+                raise ExtractorError(message, expected=True)
+            raise
+
+        errors = json_data.get('errors')
+        if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
+            custom_fields = json_data['custom_fields']
+            tve_token = self._extract_mvpd_auth(
+                smuggled_data['source_url'], video_id,
+                custom_fields['bcadobepassrequestorid'],
+                custom_fields['bcadobepassresourceid'])
+            json_data = self._download_json(
+                api_url, video_id, headers={
+                    'Accept': 'application/json;pk=%s' % policy_key
+                }, query={
+                    'tveToken': tve_token,
+                })
+
+        return self._parse_brightcove_metadata(json_data, video_id)

youtube_dl/extractor/cbslocal.py

@@ -91,12 +91,10 @@ class CBSLocalIE(AnvatoIE):
 
         info_dict = self._extract_anvato_videos(webpage, display_id)
 
-        time_str = self._html_search_regex(
-            r'class="entry-date">([^<]+)<', webpage, 'released date', default=None)
-        if time_str:
-            timestamp = unified_timestamp(time_str)
-        else:
-            timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage))
+        timestamp = unified_timestamp(self._html_search_regex(
+            r'class="(?:entry|post)-date"[^>]*>([^<]+)', webpage,
+            'released date', default=None)) or parse_iso8601(
+            self._html_search_meta('uploadDate', webpage))
 
         info_dict.update({
             'display_id': display_id,

youtube_dl/extractor/collegerama.py

@@ -1,93 +0,0 @@
-from __future__ import unicode_literals
-
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    float_or_none,
-    int_or_none,
-    sanitized_Request,
-)
-
-
-class CollegeRamaIE(InfoExtractor):
-    _VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P<id>[\da-f]+)'
-    _TESTS = [
-        {
-            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d',
-            'md5': '481fda1c11f67588c0d9d8fbdced4e39',
-            'info_dict': {
-                'id': '585a43626e544bdd97aeb71a0ec907a01d',
-                'ext': 'mp4',
-                'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
-                'description': '',
-                'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
-                'duration': 7713.088,
-                'timestamp': 1413309600,
-                'upload_date': '20141014',
-            },
-        },
-        {
-            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4',
-            'md5': 'ef1fdded95bdf19b12c5999949419c92',
-            'info_dict': {
-                'id': '86a9ea9f53e149079fbdb4202b521ed21d',
-                'ext': 'wmv',
-                'title': '64ste Vakantiecursus: Afvalwater',
-                'description': 'md5:7fd774865cc69d972f542b157c328305',
-                'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
-                'duration': 10853,
-                'timestamp': 1326446400,
-                'upload_date': '20120113',
-            },
-        },
-    ]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        player_options_request = {
-            'getPlayerOptionsRequest': {
-                'ResourceId': video_id,
-                'QueryString': '',
-            }
-        }
-
-        request = sanitized_Request(
-            'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
-            json.dumps(player_options_request))
-        request.add_header('Content-Type', 'application/json')
-
-        player_options = self._download_json(request, video_id)
-
-        presentation = player_options['d']['Presentation']
-        title = presentation['Title']
-        description = presentation.get('Description')
-        thumbnail = None
-        duration = float_or_none(presentation.get('Duration'), 1000)
-        timestamp = int_or_none(presentation.get('UnixTime'), 1000)
-
-        formats = []
-        for stream in presentation['Streams']:
-            for video in stream['VideoUrls']:
-                thumbnail_url = stream.get('ThumbnailUrl')
-                if thumbnail_url:
-                    thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url
-                format_id = video['MediaType']
-                if format_id == 'SS':
-                    continue
-                formats.append({
-                    'url': video['Location'],
-                    'format_id': format_id,
-                })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'timestamp': timestamp,
-            'formats': formats,
-        }

youtube_dl/extractor/common.py

@@ -301,8 +301,9 @@ class InfoExtractor(object):
     There must be a key "entries", which is a list, an iterable, or a PagedList
     object, each element of which is a valid dictionary by this specification.
 
-    Additionally, playlists can have "title", "description" and "id" attributes
-    with the same semantics as videos (see above).
+    Additionally, playlists can have "id", "title", "description", "uploader",
+    "uploader_id", "uploader_url" attributes with the same semantics as videos
+    (see above).
 
 
     _type "multi_video" indicates that there are multiple videos that
@@ -494,6 +495,16 @@ class InfoExtractor(object):
                 self.to_screen('%s' % (note,))
             else:
                 self.to_screen('%s: %s' % (video_id, note))
+
+        # Some sites check X-Forwarded-For HTTP header in order to figure out
+        # the origin of the client behind proxy. This allows bypassing geo
+        # restriction by faking this header's value to IP that belongs to some
+        # geo unrestricted country. We will do so once we encounter any
+        # geo restriction error.
+        if self._x_forwarded_for_ip:
+            if 'X-Forwarded-For' not in headers:
+                headers['X-Forwarded-For'] = self._x_forwarded_for_ip
+
         if isinstance(url_or_request, compat_urllib_request.Request):
             url_or_request = update_Request(
                 url_or_request, data=data, headers=headers, query=query)
@@ -523,15 +534,6 @@ class InfoExtractor(object):
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 
-        # Some sites check X-Forwarded-For HTTP header in order to figure out
-        # the origin of the client behind proxy. This allows bypassing geo
-        # restriction by faking this header's value to IP that belongs to some
-        # geo unrestricted country. We will do so once we encounter any
-        # geo restriction error.
-        if self._x_forwarded_for_ip:
-            if 'X-Forwarded-For' not in headers:
-                headers['X-Forwarded-For'] = self._x_forwarded_for_ip
-
         urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query)
         if urlh is False:
             assert not fatal
@@ -1878,6 +1880,7 @@ class InfoExtractor(object):
                             'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
                             'format_note': 'DASH %s' % content_type,
                             'filesize': filesize,
+                            'container': mimetype2ext(mime_type) + '_dash',
                         }
                         f.update(parse_codecs(representation_attrib.get('codecs')))
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
@@ -2005,16 +2008,14 @@ class InfoExtractor(object):
                                     f['url'] = initialization_url
                                 f['fragments'].append({location_key(initialization_url): initialization_url})
                             f['fragments'].extend(representation_ms_info['fragments'])
-                        try:
-                            existing_format = next(
-                                fo for fo in formats
-                                if fo['format_id'] == representation_id)
-                        except StopIteration:
-                            full_info = formats_dict.get(representation_id, {}).copy()
-                            full_info.update(f)
-                            formats.append(full_info)
-                        else:
-                            existing_format.update(f)
+                        # According to [1, 5.3.5.2, Table 7, page 35] @id of Representation
+                        # is not necessarily unique within a Period thus formats with
+                        # the same `format_id` are quite possible. There are numerous examples
+                        # of such manifests (see https://github.com/rg3/youtube-dl/issues/15111,
+                        # https://github.com/rg3/youtube-dl/issues/13919)
+                        full_info = formats_dict.get(representation_id, {}).copy()
+                        full_info.update(f)
+                        formats.append(full_info)
                     else:
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
         return formats
@@ -2054,7 +2055,7 @@ class InfoExtractor(object):
             stream_timescale = int_or_none(stream.get('TimeScale')) or timescale
             stream_name = stream.get('Name')
             for track in stream.findall('QualityLevel'):
-                fourcc = track.get('FourCC')
+                fourcc = track.get('FourCC', 'AACL' if track.get('AudioTag') == '255' else None)
                 # TODO: add support for WVC1 and WMAP
                 if fourcc not in ('H264', 'AVC1', 'AACL'):
                     self.report_warning('%s is not a supported codec' % fourcc)

youtube_dl/extractor/crunchyroll.py

@@ -392,7 +392,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 'Downloading subtitles for ' + sub_name, data={
                     'subtitle_script_id': sub_id,
                 })
-            if not sub_doc:
+            if sub_doc is None:
                 continue
             sid = sub_doc.get('id')
             iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@@ -479,9 +479,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                     'video_quality': stream_quality,
                     'current_page': url,
                 })
-            if streamdata:
+            if streamdata is not None:
                 stream_info = streamdata.find('./{default}preload/stream_info')
-                if stream_info:
+                if stream_info is not None:
                     stream_infos.append(stream_info)
             stream_info = self._call_rpc_api(
                 'VideoEncode_GetStreamInfo', video_id,
@@ -490,7 +490,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                     'video_format': stream_format,
                     'video_encode_quality': stream_quality,
                 })
-            if stream_info:
+            if stream_info is not None:
                 stream_infos.append(stream_info)
             for stream_info in stream_infos:
                 video_encode_id = xpath_text(stream_info, './video_encode_id')

youtube_dl/extractor/cspan.py

@@ -4,13 +4,14 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    int_or_none,
-    unescapeHTML,
-    find_xpath_attr,
-    smuggle_url,
     determine_ext,
     ExtractorError,
     extract_attributes,
+    find_xpath_attr,
+    get_element_by_class,
+    int_or_none,
+    smuggle_url,
+    unescapeHTML,
 )
 from .senateisvp import SenateISVPIE
 from .ustream import UstreamIE
@@ -68,6 +69,10 @@ class CSpanIE(InfoExtractor):
             'uploader': 'HouseCommittee',
             'uploader_id': '12987475',
         },
+    }, {
+        # Audio Only
+        'url': 'https://www.c-span.org/video/?437336-1/judiciary-antitrust-competition-policy-consumer-rights',
+        'only_matching': True,
     }]
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
 
@@ -111,7 +116,15 @@ class CSpanIE(InfoExtractor):
                     title = self._og_search_title(webpage)
                     surl = smuggle_url(senate_isvp_url, {'force_title': title})
                     return self.url_result(surl, 'SenateISVP', video_id, title)
+                video_id = self._search_regex(
+                    r'jwsetup\.clipprog\s*=\s*(\d+);',
+                    webpage, 'jwsetup program id', default=None)
+                if video_id:
+                    video_type = 'program'
         if video_type is None or video_id is None:
+            error_message = get_element_by_class('VLplayer-error-message', webpage)
+            if error_message:
+                raise ExtractorError(error_message)
             raise ExtractorError('unable to find video id and type')
 
         def get_text_attr(d, attr):
@@ -138,7 +151,7 @@ class CSpanIE(InfoExtractor):
         entries = []
         for partnum, f in enumerate(files):
             formats = []
-            for quality in f['qualities']:
+            for quality in f.get('qualities', []):
                 formats.append({
                     'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
                     'url': unescapeHTML(get_text_attr(quality, 'file')),

youtube_dl/extractor/discoverygo.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     extract_attributes,
     ExtractorError,
     int_or_none,
@@ -73,7 +74,11 @@ class DiscoveryGoBaseIE(InfoExtractor):
                         not subtitle_url.startswith('http')):
                     continue
                 lang = caption.get('fileLang', 'en')
-                subtitles.setdefault(lang, []).append({'url': subtitle_url})
+                ext = determine_ext(subtitle_url)
+                subtitles.setdefault(lang, []).append({
+                    'url': subtitle_url,
+                    'ext': 'ttml' if ext == 'xml' else ext,
+                })
 
         return {
             'id': video_id,

youtube_dl/extractor/disney.py

@@ -10,6 +10,7 @@ from ..utils import (
     compat_str,
     determine_ext,
     ExtractorError,
+    update_url_query,
 )
 
 
@@ -108,9 +109,16 @@ class DisneyIE(InfoExtractor):
                 continue
             tbr = int_or_none(flavor.get('bitrate'))
             if tbr == 99999:
-                formats.extend(self._extract_m3u8_formats(
+                # wrong ks(Kaltura Signature) causes 404 Error
+                flavor_url = update_url_query(flavor_url, {'ks': ''})
+                m3u8_formats = self._extract_m3u8_formats(
                     flavor_url, video_id, 'mp4',
-                    m3u8_id=flavor_format, fatal=False))
+                    m3u8_id=flavor_format, fatal=False)
+                for f in m3u8_formats:
+                    # Apple FairPlay
+                    if '/fpshls/' in f['url']:
+                        continue
+                    formats.append(f)
                 continue
             format_id = []
             if flavor_format:

youtube_dl/extractor/espn.py

@@ -1,6 +1,9 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from .once import OnceIE
 from ..compat import compat_str
 from ..utils import (
     determine_ext,
@@ -9,22 +12,27 @@ from ..utils import (
 )
 
 
-class ESPNIE(InfoExtractor):
+class ESPNIE(OnceIE):
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:
-                            (?:(?:\w+\.)+)?espn\.go|
-                            (?:www\.)?espn
-                        )\.com/
                         (?:
                             (?:
-                                video/clip|
-                                watch/player
-                            )
-                            (?:
-                                \?.*?\bid=|
-                                /_/id/
-                            )
+                                (?:
+                                    (?:(?:\w+\.)+)?espn\.go|
+                                    (?:www\.)?espn
+                                )\.com/
+                                (?:
+                                    (?:
+                                        video/(?:clip|iframe/twitter)|
+                                        watch/player
+                                    )
+                                    (?:
+                                        .*?\?.*?\bid=|
+                                        /_/id/
+                                    )
+                                )
+                            )|
+                            (?:www\.)espnfc\.(?:com|us)/(?:video/)?[^/]+/\d+/video/
                         )
                         (?P<id>\d+)
                     '''
@@ -77,6 +85,15 @@ class ESPNIE(InfoExtractor):
     }, {
         'url': 'http://www.espn.com/video/clip/_/id/17989860',
         'only_matching': True,
+    }, {
+        'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.espnfc.us/video/espn-fc-tv/86/video/3319154/nashville-unveiled-as-the-newest-club-in-mls',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.espnfc.com/english-premier-league/23/video/3324163/premier-league-in-90-seconds-golden-tweets',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -93,7 +110,9 @@ class ESPNIE(InfoExtractor):
 
         def traverse_source(source, base_source_id=None):
             for source_id, source in source.items():
-                if isinstance(source, compat_str):
+                if source_id == 'alert':
+                    continue
+                elif isinstance(source, compat_str):
                     extract_source(source, base_source_id)
                 elif isinstance(source, dict):
                     traverse_source(
@@ -106,7 +125,9 @@ class ESPNIE(InfoExtractor):
                 return
             format_urls.add(source_url)
             ext = determine_ext(source_url)
-            if ext == 'smil':
+            if OnceIE.suitable(source_url):
+                formats.extend(self._extract_once_formats(source_url))
+            elif ext == 'smil':
                 formats.extend(self._extract_smil_formats(
                     source_url, video_id, fatal=False))
             elif ext == 'f4m':
@@ -117,12 +138,24 @@ class ESPNIE(InfoExtractor):
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id=source_id, fatal=False))
             else:
-                formats.append({
+                f = {
                     'url': source_url,
                     'format_id': source_id,
-                })
+                }
+                mobj = re.search(r'(\d+)p(\d+)_(\d+)k\.', source_url)
+                if mobj:
+                    f.update({
+                        'height': int(mobj.group(1)),
+                        'fps': int(mobj.group(2)),
+                        'tbr': int(mobj.group(3)),
+                    })
+                if source_id == 'mezzanine':
+                    f['preference'] = 1
+                formats.append(f)
 
-        traverse_source(clip['links']['source'])
+        links = clip.get('links', {})
+        traverse_source(links.get('source', {}))
+        traverse_source(links.get('mobile', {}))
         self._sort_formats(formats)
 
         description = clip.get('caption') or clip.get('description')
@@ -144,9 +177,6 @@ class ESPNIE(InfoExtractor):
 class ESPNArticleIE(InfoExtractor):
     _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
     _TESTS = [{
-        'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079',
-        'only_matching': True,
-    }, {
         'url': 'http://espn.go.com/nba/recap?gameId=400793786',
         'only_matching': True,
     }, {
@@ -175,3 +205,34 @@ class ESPNArticleIE(InfoExtractor):
 
         return self.url_result(
             'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key())
+
+
+class FiveThirtyEightIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?fivethirtyeight\.com/features/(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://fivethirtyeight.com/features/how-the-6-8-raiders-can-still-make-the-playoffs/',
+        'info_dict': {
+            'id': '21846851',
+            'ext': 'mp4',
+            'title': 'FiveThirtyEight: The Raiders can still make the playoffs',
+            'description': 'Neil Paine breaks down the simplest scenario that will put the Raiders into the playoffs at 8-8.',
+            'timestamp': 1513960621,
+            'upload_date': '20171222',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Unable to download f4m manifest'],
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._search_regex(
+            r'data-video-id=["\'](?P<id>\d+)',
+            webpage, 'video id', group='id')
+
+        return self.url_result(
+            'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key())

youtube_dl/extractor/extractors.py

@@ -205,7 +205,6 @@ from .cnn import (
     CNNArticleIE,
 )
 from .coub import CoubIE
-from .collegerama import CollegeRamaIE
 from .comedycentral import (
     ComedyCentralFullEpisodesIE,
     ComedyCentralIE,
@@ -322,6 +321,7 @@ from .escapist import EscapistIE
 from .espn import (
     ESPNIE,
     ESPNArticleIE,
+    FiveThirtyEightIE,
 )
 from .esri import EsriVideoIE
 from .etonline import ETOnlineIE
@@ -344,6 +344,7 @@ from .filmon import (
     FilmOnIE,
     FilmOnChannelIE,
 )
+from .filmweb import FilmwebIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
 from .fivetv import FiveTVIE
@@ -464,6 +465,7 @@ from .indavideo import (
 )
 from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
+from .internazionale import InternazionaleIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
 from .iqiyi import IqiyiIE
@@ -573,6 +575,7 @@ from .massengeschmacktv import MassengeschmackTVIE
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .mediaset import MediasetIE
+from .mediasite import MediasiteIE
 from .medici import MediciIE
 from .megaphone import MegaphoneIE
 from .meipai import MeipaiIE
@@ -606,7 +609,10 @@ from .mofosex import MofosexIE
 from .mojvideo import MojvideoIE
 from .moniker import MonikerIE
 from .morningstar import MorningstarIE
-from .motherless import MotherlessIE
+from .motherless import (
+    MotherlessIE,
+    MotherlessGroupIE
+)
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviezine import MoviezineIE
@@ -909,7 +915,6 @@ from .rutube import (
 from .rutv import RUTVIE
 from .ruutu import RuutuIE
 from .ruv import RuvIE
-from .sandia import SandiaIE
 from .safari import (
     SafariIE,
     SafariApiIE,
@@ -926,8 +931,12 @@ from .senateisvp import SenateISVPIE
 from .sendtonews import SendtoNewsIE
 from .servingsys import ServingSysIE
 from .servus import ServusIE
+from .sevenplus import SevenPlusIE
 from .sexu import SexuIE
-from .shahid import ShahidIE
+from .shahid import (
+    ShahidIE,
+    ShahidShowIE,
+)
 from .shared import (
     SharedIE,
     VivoIE,
@@ -1059,6 +1068,7 @@ from .tnaflix import (
 from .toggle import ToggleIE
 from .tonline import TOnlineIE
 from .toongoggles import ToonGogglesIE
+from .totalwebcasting import TotalWebCastingIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
@@ -1115,6 +1125,7 @@ from .tvplayer import TVPlayerIE
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
+from .twentythreevideo import TwentyThreeVideoIE
 from .twitch import (
     TwitchVideoIE,
     TwitchChapterIE,
@@ -1137,8 +1148,10 @@ from .udemy import (
     UdemyCourseIE
 )
 from .udn import UDNEmbedIE
+from .ufctv import UFCTVIE
 from .uktvplay import UKTVPlayIE
 from .digiteka import DigitekaIE
+from .umg import UMGDeIE
 from .unistra import UnistraIE
 from .unity import UnityIE
 from .uol import UOLIE

youtube_dl/extractor/filmweb.py

@@ -0,0 +1,42 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class FilmwebIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?filmweb\.no/(?P<type>trailere|filmnytt)/article(?P<id>\d+)\.ece'
+    _TEST = {
+        'url': 'http://www.filmweb.no/trailere/article1264921.ece',
+        'md5': 'e353f47df98e557d67edaceda9dece89',
+        'info_dict': {
+            'id': '13033574',
+            'ext': 'mp4',
+            'title': 'Det som en gang var',
+            'upload_date': '20160316',
+            'timestamp': 1458140101,
+            'uploader_id': '12639966',
+            'uploader': 'Live Roaldset',
+        }
+    }
+
+    def _real_extract(self, url):
+        article_type, article_id = re.match(self._VALID_URL, url).groups()
+        if article_type == 'filmnytt':
+            webpage = self._download_webpage(url, article_id)
+            article_id = self._search_regex(r'data-videoid="(\d+)"', webpage, 'article id')
+        embed_code = self._download_json(
+            'https://www.filmweb.no/template_v2/ajax/json_trailerEmbed.jsp',
+            article_id, query={
+                'articleId': article_id,
+            })['embedCode']
+        iframe_url = self._proto_relative_url(self._search_regex(
+            r'<iframe[^>]+src="([^"]+)', embed_code, 'iframe url'))
+
+        return {
+            '_type': 'url_transparent',
+            'id': article_id,
+            'url': iframe_url,
+            'ie_key': 'TwentyThreeVideo',
+        }

youtube_dl/extractor/generic.py

@@ -100,6 +100,7 @@ from .megaphone import MegaphoneIE
 from .vzaar import VzaarIE
 from .channel9 import Channel9IE
 from .vshare import VShareIE
+from .mediasite import MediasiteIE
 
 
 class GenericIE(InfoExtractor):
@@ -1925,6 +1926,18 @@ class GenericIE(InfoExtractor):
                 'title': 'vl14062007715967',
                 'ext': 'mp4',
             }
+        },
+        {
+            'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
+            'md5': 'aecd089f55b1cb5a59032cb049d3a356',
+            'info_dict': {
+                'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
+                'ext': 'mp4',
+                'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
+                'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
+                'timestamp': 1474354800,
+                'upload_date': '20160920',
+            }
         }
         # {
         #     # TODO: find another test
@@ -2883,6 +2896,16 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
 
+        # Look for Mediasite embeds
+        mediasite_urls = MediasiteIE._extract_urls(webpage)
+        if mediasite_urls:
+            entries = [
+                self.url_result(smuggle_url(
+                    compat_urlparse.urljoin(url, mediasite_url),
+                    {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
+                for mediasite_url in mediasite_urls]
+            return self.playlist_result(entries, video_id, video_title)
+
         def merge_dicts(dict1, dict2):
             merged = {}
             for k, v in dict1.items():

youtube_dl/extractor/internazionale.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import unified_timestamp
+
+
+class InternazionaleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood',
+        'md5': '3e39d32b66882c1218e305acbf8348ca',
+        'info_dict': {
+            'id': '265968',
+            'display_id': 'richard-linklater-racconta-una-scena-di-boyhood',
+            'ext': 'mp4',
+            'title': 'Richard Linklater racconta una scena di Boyhood',
+            'description': 'md5:efb7e5bbfb1a54ae2ed5a4a015f0e665',
+            'timestamp': 1424354635,
+            'upload_date': '20150219',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        DATA_RE = r'data-%s=(["\'])(?P<value>(?:(?!\1).)+)\1'
+
+        title = self._search_regex(
+            DATA_RE % 'video-title', webpage, 'title', default=None,
+            group='value') or self._og_search_title(webpage)
+
+        video_id = self._search_regex(
+            DATA_RE % 'job-id', webpage, 'video id', group='value')
+        video_path = self._search_regex(
+            DATA_RE % 'video-path', webpage, 'video path', group='value')
+
+        video_base = 'https://video.internazionale.it/%s/%s.' % (video_path, video_id)
+
+        formats = self._extract_m3u8_formats(
+            video_base + 'm3u8', display_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+        formats.extend(self._extract_mpd_formats(
+            video_base + 'mpd', display_id, mpd_id='dash', fatal=False))
+        self._sort_formats(formats)
+
+        timestamp = unified_timestamp(self._html_search_meta(
+            'article:published_time', webpage, 'timestamp'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+            'timestamp': timestamp,
+            'formats': formats,
+        }

youtube_dl/extractor/kaltura.py

@@ -125,9 +125,12 @@ class KalturaIE(InfoExtractor):
                         (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
                     (?P=q1).*?
                     (?:
-                        entry_?[Ii]d|
-                        (?P<q2>["'])entry_?[Ii]d(?P=q2)
-                    )\s*:\s*
+                        (?:
+                            entry_?[Ii]d|
+                            (?P<q2>["'])entry_?[Ii]d(?P=q2)
+                        )\s*:\s*|
+                        \[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
+                    )
                     (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
                 ''', webpage) or
             re.search(

youtube_dl/extractor/lynda.py

@@ -94,7 +94,15 @@ class LyndaBaseIE(InfoExtractor):
 class LyndaIE(LyndaBaseIE):
     IE_NAME = 'lynda'
     IE_DESC = 'lynda.com videos'
-    _VALID_URL = r'https?://(?:www\.)?(?:lynda\.com|educourse\.ga)/(?:[^/]+/[^/]+/(?P<course_id>\d+)|player/embed)/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?(?:lynda\.com|educourse\.ga)/
+                        (?:
+                            (?:[^/]+/){2,3}(?P<course_id>\d+)|
+                            player/embed
+                        )/
+                        (?P<id>\d+)
+                    '''
 
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 
@@ -113,6 +121,9 @@ class LyndaIE(LyndaBaseIE):
     }, {
         'url': 'https://educourse.ga/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html',
+        'only_matching': True,
     }]
 
     def _raise_unavailable(self, video_id):
@@ -244,8 +255,9 @@ class LyndaIE(LyndaBaseIE):
     def _get_subtitles(self, video_id):
         url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
         subs = self._download_json(url, None, False)
-        if subs:
-            return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]}
+        fixed_subs = self._fix_subtitles(subs)
+        if fixed_subs:
+            return {'en': [{'ext': 'srt', 'data': fixed_subs}]}
         else:
             return {}
 
@@ -256,7 +268,15 @@ class LyndaCourseIE(LyndaBaseIE):
 
     # Course link equals to welcome/introduction video link of same course
     # We will recognize it as course link
-    _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P<coursepath>[^/]+/[^/]+/(?P<courseid>\d+))-\d\.html'
+    _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P<coursepath>(?:[^/]+/){2,3}(?P<courseid>\d+))-2\.html'
+
+    _TESTS = [{
+        'url': 'https://www.lynda.com/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/mailru.py

@@ -13,8 +13,15 @@ from ..utils import (
 class MailRuIE(InfoExtractor):
     IE_NAME = 'mailru'
     IE_DESC = 'Видео@Mail.Ru'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
-
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:(?:www|m)\.)?my\.mail\.ru/
+                        (?:
+                            video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|
+                            (?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
+                            (?:video/embed|\+/video/meta)/(?P<metaid>\d+)
+                        )
+                    '''
     _TESTS = [
         {
             'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
@@ -23,7 +30,7 @@ class MailRuIE(InfoExtractor):
                 'id': '46301138_76',
                 'ext': 'mp4',
                 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
-                'timestamp': 1393232740,
+                'timestamp': 1393235077,
                 'upload_date': '20140224',
                 'uploader': 'sonypicturesrus',
                 'uploader_id': 'sonypicturesrus@mail.ru',
@@ -40,7 +47,7 @@ class MailRuIE(InfoExtractor):
                 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
                 'timestamp': 1397039888,
                 'upload_date': '20140409',
-                'uploader': 'hitech@corp.mail.ru',
+                'uploader': 'hitech',
                 'uploader_id': 'hitech@corp.mail.ru',
                 'duration': 245,
             },
@@ -65,28 +72,42 @@ class MailRuIE(InfoExtractor):
         {
             'url': 'http://m.my.mail.ru/mail/3sktvtr/video/_myvideo/138.html',
             'only_matching': True,
+        },
+        {
+            'url': 'https://my.mail.ru/video/embed/7949340477499637815',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://my.mail.ru/+/video/meta/7949340477499637815',
+            'only_matching': True,
         }
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('idv1')
+        meta_id = mobj.group('metaid')
 
-        if not video_id:
-            video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
-
-        webpage = self._download_webpage(url, video_id)
+        video_id = None
+        if meta_id:
+            meta_url = 'https://my.mail.ru/+/video/meta/%s' % meta_id
+        else:
+            video_id = mobj.group('idv1')
+            if not video_id:
+                video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
+            webpage = self._download_webpage(url, video_id)
+            page_config = self._parse_json(self._search_regex(
+                r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
+                webpage, 'page config', default='{}'), video_id, fatal=False)
+            if page_config:
+                meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl')
+            else:
+                meta_url = None
 
         video_data = None
-
-        page_config = self._parse_json(self._search_regex(
-            r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
-            webpage, 'page config', default='{}'), video_id, fatal=False)
-        if page_config:
-            meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl')
-            if meta_url:
-                video_data = self._download_json(
-                    meta_url, video_id, 'Downloading video meta JSON', fatal=False)
+        if meta_url:
+            video_data = self._download_json(
+                meta_url, video_id or meta_id, 'Downloading video meta JSON',
+                fatal=not video_id)
 
         # Fallback old approach
         if not video_data:

youtube_dl/extractor/mediasite.py

@@ -0,0 +1,214 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    mimetype2ext,
+    unescapeHTML,
+    unsmuggle_url,
+    urljoin,
+)
+
+
+class MediasiteIE(InfoExtractor):
+    _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?P<id>[0-9a-f]{32,34})(?P<query>\?[^#]+|)'
+    _TESTS = [
+        {
+            'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d',
+            'info_dict': {
+                'id': '2db6c271681e4f199af3c60d1f82869b1d',
+                'ext': 'mp4',
+                'title': 'Lecture: Tuesday, September 20, 2016 - Sir Andrew Wiles',
+                'description': 'Sir Andrew Wiles: “Equations in arithmetic”\\n\\nI will describe some of the interactions between modern number theory and the problem of solving equations in rational numbers or integers\\u0027.',
+                'timestamp': 1474268400.0,
+                'upload_date': '20160919',
+            },
+        },
+        {
+            'url': 'http://mediasite.uib.no/Mediasite/Play/90bb363295d945d6b548c867d01181361d?catalog=a452b7df-9ae1-46b7-a3ba-aceeb285f3eb',
+            'info_dict': {
+                'id': '90bb363295d945d6b548c867d01181361d',
+                'ext': 'mp4',
+                'upload_date': '20150429',
+                'title': '5) IT-forum 2015-Dag 1  - Dungbeetle -  How and why Rain created a tiny bug tracker for Unity',
+                'timestamp': 1430311380.0,
+            },
+        },
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d',
+            'md5': '481fda1c11f67588c0d9d8fbdced4e39',
+            'info_dict': {
+                'id': '585a43626e544bdd97aeb71a0ec907a01d',
+                'ext': 'mp4',
+                'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
+                'description': '',
+                'thumbnail': r're:^https?://.*\.jpg(?:\?.*)?$',
+                'duration': 7713.088,
+                'timestamp': 1413309600,
+                'upload_date': '20141014',
+            },
+        },
+        {
+            'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4',
+            'md5': 'ef1fdded95bdf19b12c5999949419c92',
+            'info_dict': {
+                'id': '86a9ea9f53e149079fbdb4202b521ed21d',
+                'ext': 'wmv',
+                'title': '64ste Vakantiecursus: Afvalwater',
+                'description': 'md5:7fd774865cc69d972f542b157c328305',
+                'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
+                'duration': 10853,
+                'timestamp': 1326446400,
+                'upload_date': '20120113',
+            },
+        },
+        {
+            'url': 'http://digitalops.sandia.gov/Mediasite/Play/24aace4429fc450fb5b38cdbf424a66e1d',
+            'md5': '9422edc9b9a60151727e4b6d8bef393d',
+            'info_dict': {
+                'id': '24aace4429fc450fb5b38cdbf424a66e1d',
+                'ext': 'mp4',
+                'title': 'Xyce Software Training - Section 1',
+                'description': r're:(?s)SAND Number: SAND 2013-7800.{200,}',
+                'upload_date': '20120409',
+                'timestamp': 1333983600,
+                'duration': 7794,
+            }
+        }
+    ]
+
+    # look in Mediasite.Core.js (Mediasite.ContentStreamType[*])
+    _STREAM_TYPES = {
+        0: 'video1',  # the main video
+        2: 'slide',
+        3: 'presentation',
+        4: 'video2',  # screencast?
+        5: 'video3',
+    }
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            unescapeHTML(mobj.group('url'))
+            for mobj in re.finditer(
+                r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/[0-9a-f]{32,34}(?:\?.*?)?)\1',
+                webpage)]
+
+    def _real_extract(self, url):
+        url, data = unsmuggle_url(url, {})
+        mobj = re.match(self._VALID_URL, url)
+        resource_id = mobj.group('id')
+        query = mobj.group('query')
+
+        webpage, urlh = self._download_webpage_handle(url, resource_id)  # XXX: add UrlReferrer?
+        redirect_url = compat_str(urlh.geturl())
+
+        # XXX: might have also extracted UrlReferrer and QueryString from the html
+        service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex(
+            r'<div[^>]+\bid=["\']ServicePath[^>]+>(.+?)</div>', webpage, resource_id,
+            default='/Mediasite/PlayerService/PlayerService.svc/json'))
+
+        player_options = self._download_json(
+            '%s/GetPlayerOptions' % service_path, resource_id,
+            headers={
+                'Content-type': 'application/json; charset=utf-8',
+                'X-Requested-With': 'XMLHttpRequest',
+            },
+            data=json.dumps({
+                'getPlayerOptionsRequest': {
+                    'ResourceId': resource_id,
+                    'QueryString': query,
+                    'UrlReferrer': data.get('UrlReferrer', ''),
+                    'UseScreenReader': False,
+                }
+            }).encode('utf-8'))['d']
+
+        presentation = player_options['Presentation']
+        title = presentation['Title']
+
+        if presentation is None:
+            raise ExtractorError(
+                'Mediasite says: %s' % player_options['PlayerPresentationStatusMessage'],
+                expected=True)
+
+        thumbnails = []
+        formats = []
+        for snum, Stream in enumerate(presentation['Streams']):
+            stream_type = Stream.get('StreamType')
+            if stream_type is None:
+                continue
+
+            video_urls = Stream.get('VideoUrls')
+            if not isinstance(video_urls, list):
+                video_urls = []
+
+            stream_id = self._STREAM_TYPES.get(
+                stream_type, 'type%u' % stream_type)
+
+            stream_formats = []
+            for unum, VideoUrl in enumerate(video_urls):
+                video_url = VideoUrl.get('Location')
+                if not video_url or not isinstance(video_url, compat_str):
+                    continue
+                # XXX: if Stream.get('CanChangeScheme', False), switch scheme to HTTP/HTTPS
+
+                media_type = VideoUrl.get('MediaType')
+                if media_type == 'SS':
+                    stream_formats.extend(self._extract_ism_formats(
+                        video_url, resource_id,
+                        ism_id='%s-%u.%u' % (stream_id, snum, unum),
+                        fatal=False))
+                elif media_type == 'Dash':
+                    stream_formats.extend(self._extract_mpd_formats(
+                        video_url, resource_id,
+                        mpd_id='%s-%u.%u' % (stream_id, snum, unum),
+                        fatal=False))
+                else:
+                    stream_formats.append({
+                        'format_id': '%s-%u.%u' % (stream_id, snum, unum),
+                        'url': video_url,
+                        'ext': mimetype2ext(VideoUrl.get('MimeType')),
+                    })
+
+            # TODO: if Stream['HasSlideContent']:
+            # synthesise an MJPEG video stream '%s-%u.slides' % (stream_type, snum)
+            # from Stream['Slides']
+            # this will require writing a custom downloader...
+
+            # disprefer 'secondary' streams
+            if stream_type != 0:
+                for fmt in stream_formats:
+                    fmt['preference'] = -1
+
+            thumbnail_url = Stream.get('ThumbnailUrl')
+            if thumbnail_url:
+                thumbnails.append({
+                    'id': '%s-%u' % (stream_id, snum),
+                    'url': urljoin(redirect_url, thumbnail_url),
+                    'preference': -1 if stream_type != 0 else 0,
+                })
+            formats.extend(stream_formats)
+
+        self._sort_formats(formats)
+
+        # XXX: Presentation['Presenters']
+        # XXX: Presentation['Transcript']
+
+        return {
+            'id': resource_id,
+            'title': title,
+            'description': presentation.get('Description'),
+            'duration': float_or_none(presentation.get('Duration'), 1000),
+            'timestamp': float_or_none(presentation.get('UnixTime'), 1000),
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/mitele.py

@@ -1,13 +1,13 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import uuid
 
 from .common import InfoExtractor
 from .ooyala import OoyalaIE
 from ..compat import (
     compat_str,
-    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
@@ -42,31 +42,33 @@ class MiTeleBaseIE(InfoExtractor):
                 duration = int_or_none(mmc.get('duration'))
             for location in mmc['locations']:
                 gat = self._proto_relative_url(location.get('gat'), 'http:')
-                bas = location.get('bas')
-                loc = location.get('loc')
+                gcp = location.get('gcp')
                 ogn = location.get('ogn')
-                if None in (gat, bas, loc, ogn):
+                if None in (gat, gcp, ogn):
                     continue
                 token_data = {
-                    'bas': bas,
-                    'icd': loc,
+                    'gcp': gcp,
                     'ogn': ogn,
-                    'sta': '0',
+                    'sta': 0,
                 }
                 media = self._download_json(
-                    '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)),
-                    video_id, 'Downloading %s JSON' % location['loc'])
-                file_ = media.get('file')
-                if not file_:
+                    gat, video_id, data=json.dumps(token_data).encode('utf-8'),
+                    headers={
+                        'Content-Type': 'application/json;charset=utf-8',
+                        'Referer': url,
+                    })
+                stream = media.get('stream') or media.get('file')
+                if not stream:
                     continue
-                ext = determine_ext(file_)
+                ext = determine_ext(stream)
                 if ext == 'f4m':
                     formats.extend(self._extract_f4m_formats(
-                        file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
+                        stream + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
                         video_id, f4m_id='hds', fatal=False))
                 elif ext == 'm3u8':
                     formats.extend(self._extract_m3u8_formats(
-                        file_, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+                        stream, video_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/motherless.py

@@ -4,8 +4,11 @@ import datetime
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     ExtractorError,
+    InAdvancePagedList,
+    orderedSet,
     str_to_int,
     unified_strdate,
 )
@@ -114,3 +117,86 @@ class MotherlessIE(InfoExtractor):
             'age_limit': age_limit,
             'url': video_url,
         }
+
+
+class MotherlessGroupIE(InfoExtractor):
+    _VALID_URL = 'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
+    _TESTS = [{
+        'url': 'http://motherless.com/g/movie_scenes',
+        'info_dict': {
+            'id': 'movie_scenes',
+            'title': 'Movie Scenes',
+            'description': 'Hot and sexy scenes from "regular" movies... '
+                           'Beautiful actresses fully nude... A looot of '
+                           'skin! :)Enjoy!',
+        },
+        'playlist_mincount': 662,
+    }, {
+        'url': 'http://motherless.com/gv/sex_must_be_funny',
+        'info_dict': {
+            'id': 'sex_must_be_funny',
+            'title': 'Sex must be funny',
+            'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
+                           'any kind!'
+        },
+        'playlist_mincount': 9,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return (False if MotherlessIE.suitable(url)
+                else super(MotherlessGroupIE, cls).suitable(url))
+
+    def _extract_entries(self, webpage, base):
+        entries = []
+        for mobj in re.finditer(
+                r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
+                webpage):
+            video_url = compat_urlparse.urljoin(base, mobj.group('href'))
+            if not MotherlessIE.suitable(video_url):
+                continue
+            video_id = MotherlessIE._match_id(video_url)
+            title = mobj.group('title')
+            entries.append(self.url_result(
+                video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
+                video_title=title))
+        # Alternative fallback
+        if not entries:
+            entries = [
+                self.url_result(
+                    compat_urlparse.urljoin(base, '/' + video_id),
+                    ie=MotherlessIE.ie_key(), video_id=video_id)
+                for video_id in orderedSet(re.findall(
+                    r'data-codename=["\']([A-Z0-9]+)', webpage))]
+        return entries
+
+    def _real_extract(self, url):
+        group_id = self._match_id(url)
+        page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
+        webpage = self._download_webpage(page_url, group_id)
+        title = self._search_regex(
+            r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
+        description = self._html_search_meta(
+            'description', webpage, fatal=False)
+        page_count = self._int(self._search_regex(
+            r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
+            webpage, 'page_count'), 'page_count')
+        PAGE_SIZE = 80
+
+        def _get_page(idx):
+            webpage = self._download_webpage(
+                page_url, group_id, query={'page': idx + 1},
+                note='Downloading page %d/%d' % (idx + 1, page_count)
+            )
+            for entry in self._extract_entries(webpage, url):
+                yield entry
+
+        playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
+
+        return {
+            '_type': 'playlist',
+            'id': group_id,
+            'title': title,
+            'description': description,
+            'entries': playlist
+        }

youtube_dl/extractor/openload.py

@@ -112,6 +112,8 @@ class PhantomJSwrapper(object):
         return get_exe_version('phantomjs', version_re=r'([0-9.]+)')
 
     def __init__(self, extractor, required_version=None, timeout=10000):
+        self._TMP_FILES = {}
+
         self.exe = check_executable('phantomjs', ['-v'])
         if not self.exe:
             raise ExtractorError('PhantomJS executable not found in PATH, '
@@ -130,7 +132,6 @@ class PhantomJSwrapper(object):
         self.options = {
             'timeout': timeout,
         }
-        self._TMP_FILES = {}
         for name in self._TMP_FILE_NAMES:
             tmp = tempfile.NamedTemporaryFile(delete=False)
             tmp.close()
@@ -140,7 +141,7 @@ class PhantomJSwrapper(object):
         for name in self._TMP_FILE_NAMES:
             try:
                 os.remove(self._TMP_FILES[name].name)
-            except (IOError, OSError):
+            except (IOError, OSError, KeyError):
                 pass
 
     def _save_cookies(self, url):
@@ -242,7 +243,7 @@ class PhantomJSwrapper(object):
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -283,12 +284,20 @@ class OpenloadIE(InfoExtractor):
         # for title and ext
         'url': 'https://openload.co/embed/Sxz5sADo82g/',
         'only_matching': True,
+    }, {
+        # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available
+        # via https://openload.co/f/e-Ixz9ZR5L0/
+        'url': 'https://openload.co/f/e-Ixz9ZR5L0/',
+        'only_matching': True,
     }, {
         'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
         'only_matching': True,
     }, {
         'url': 'http://www.openload.link/f/KnG-kKZdcfY',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.stream/f/KnG-kKZdcfY',
+        'only_matching': True,
     }]
 
     _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
@@ -301,20 +310,34 @@ class OpenloadIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        url = 'https://openload.co/embed/%s/' % video_id
+        url_pattern = 'https://openload.co/%%s/%s/' % video_id
         headers = {
             'User-Agent': self._USER_AGENT,
         }
 
-        webpage = self._download_webpage(url, video_id, headers=headers)
-
-        if 'File not found' in webpage or 'deleted by the owner' in webpage:
-            raise ExtractorError('File not found', expected=True, video_id=video_id)
+        for path in ('embed', 'f'):
+            page_url = url_pattern % path
+            last = path == 'f'
+            webpage = self._download_webpage(
+                page_url, video_id, 'Downloading %s webpage' % path,
+                headers=headers, fatal=last)
+            if not webpage:
+                continue
+            if 'File not found' in webpage or 'deleted by the owner' in webpage:
+                if not last:
+                    continue
+                raise ExtractorError('File not found', expected=True, video_id=video_id)
+            break
 
         phantom = PhantomJSwrapper(self, required_version='2.0')
-        webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers)
+        webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id, headers=headers)
 
-        decoded_id = get_element_by_id('streamurl', webpage)
+        decoded_id = (get_element_by_id('streamurl', webpage) or
+                      get_element_by_id('streamuri', webpage) or
+                      get_element_by_id('streamurj', webpage))
+
+        if not decoded_id:
+            raise ExtractorError('Can\'t find stream URL', video_id=video_id)
 
         video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id
 
@@ -323,7 +346,7 @@ class OpenloadIE(InfoExtractor):
             'title', default=None) or self._html_search_meta(
             'description', webpage, 'title', fatal=True)
 
-        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        entries = self._parse_html5_media_entries(page_url, webpage, video_id)
         entry = entries[0] if entries else {}
         subtitles = entry.get('subtitles')
 

youtube_dl/extractor/playtvak.py

@@ -24,7 +24,7 @@ class PlaytvakIE(InfoExtractor):
             'id': 'A150730_150323_hodinovy-manzel_kuko',
             'ext': 'mp4',
             'title': 'Vyžeňte vosy a sršně ze zahrady',
-            'description': 'md5:f93d398691044d303bc4a3de62f3e976',
+            'description': 'md5:4436e61b7df227a093778efb7e373571',
             'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
             'duration': 279,
             'timestamp': 1438732860,
@@ -36,9 +36,19 @@ class PlaytvakIE(InfoExtractor):
         'info_dict': {
             'id': 'A150624_164934_planespotting_cat',
             'ext': 'flv',
-            'title': 're:^Přímý přenos iDNES.cz [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'title': 're:^Planespotting [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'description': 'Sledujte provoz na ranveji Letiště Václava Havla v Praze',
-            'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }, {  # another live stream, this one without Misc.videoFLV
+        'url': 'https://slowtv.playtvak.cz/zive-sledujte-vlaky-v-primem-prenosu-dwi-/hlavni-nadrazi.aspx?c=A151218_145728_hlavni-nadrazi_plap',
+        'info_dict': {
+            'id': 'A151218_145728_hlavni-nadrazi_plap',
+            'ext': 'flv',
+            'title': 're:^Hlavní nádraží [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'is_live': True,
         },
         'params': {
@@ -95,7 +105,7 @@ class PlaytvakIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         info_url = self._html_search_regex(
-            r'Misc\.videoFLV\(\s*{\s*data\s*:\s*"([^"]+)"', webpage, 'info url')
+            r'Misc\.video(?:FLV)?\(\s*{\s*data\s*:\s*"([^"]+)"', webpage, 'info url')
 
         parsed_url = compat_urlparse.urlparse(info_url)
 
@@ -160,7 +170,7 @@ class PlaytvakIE(InfoExtractor):
         if is_live:
             title = self._live_title(title)
         description = self._og_search_description(webpage, default=None) or self._html_search_meta(
-            'description', webpage, 'description')
+            'description', webpage, 'description', default=None)
         timestamp = None
         duration = None
         if not is_live:

youtube_dl/extractor/pluralsight.py

@@ -171,12 +171,12 @@ class PluralsightIE(PluralsightBaseIE):
         for num, current in enumerate(subs):
             current = subs[num]
             start, text = (
-                float_or_none(dict_get(current, TIME_OFFSET_KEYS)),
+                float_or_none(dict_get(current, TIME_OFFSET_KEYS, skip_false_values=False)),
                 dict_get(current, TEXT_KEYS))
             if start is None or text is None:
                 continue
             end = duration if num == len(subs) - 1 else float_or_none(
-                dict_get(subs[num + 1], TIME_OFFSET_KEYS))
+                dict_get(subs[num + 1], TIME_OFFSET_KEYS, skip_false_values=False))
             if end is None:
                 continue
             srt += os.linesep.join(

youtube_dl/extractor/rtve.py

@@ -31,6 +31,9 @@ def _decrypt_url(png):
     hash_index = data.index('#')
     alphabet_data = data[:hash_index]
     url_data = data[hash_index + 1:]
+    if url_data[0] == 'H' and url_data[3] == '%':
+        # remove useless HQ%% at the start
+        url_data = url_data[4:]
 
     alphabet = []
     e = 0

youtube_dl/extractor/sandia.py

@@ -1,65 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    mimetype2ext,
-)
-
-
-class SandiaIE(InfoExtractor):
-    IE_DESC = 'Sandia National Laboratories'
-    _VALID_URL = r'https?://digitalops\.sandia\.gov/Mediasite/Play/(?P<id>[0-9a-f]+)'
-    _TEST = {
-        'url': 'http://digitalops.sandia.gov/Mediasite/Play/24aace4429fc450fb5b38cdbf424a66e1d',
-        'md5': '9422edc9b9a60151727e4b6d8bef393d',
-        'info_dict': {
-            'id': '24aace4429fc450fb5b38cdbf424a66e1d',
-            'ext': 'mp4',
-            'title': 'Xyce Software Training - Section 1',
-            'description': 're:(?s)SAND Number: SAND 2013-7800.{200,}',
-            'upload_date': '20120409',
-            'timestamp': 1333983600,
-            'duration': 7794,
-        }
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        presentation_data = self._download_json(
-            'http://digitalops.sandia.gov/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions',
-            video_id, data=json.dumps({
-                'getPlayerOptionsRequest': {
-                    'ResourceId': video_id,
-                    'QueryString': '',
-                }
-            }), headers={
-                'Content-Type': 'application/json; charset=utf-8',
-            })['d']['Presentation']
-
-        title = presentation_data['Title']
-
-        formats = []
-        for stream in presentation_data.get('Streams', []):
-            for fd in stream.get('VideoUrls', []):
-                formats.append({
-                    'format_id': fd['MediaType'],
-                    'format_note': fd['MimeType'].partition('/')[2],
-                    'ext': mimetype2ext(fd['MimeType']),
-                    'url': fd['Location'],
-                    'protocol': 'f4m' if fd['MimeType'] == 'video/x-mp4-fragmented' else None,
-                })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': presentation_data.get('Description'),
-            'formats': formats,
-            'timestamp': int_or_none(presentation_data.get('UnixTime'), 1000),
-            'duration': int_or_none(presentation_data.get('Duration'), 1000),
-        }

youtube_dl/extractor/scrippsnetworks.py

@@ -1,13 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import datetime
 import json
 import hashlib
-import hmac
 import re
 
-from .common import InfoExtractor
+from .aws import AWSIE
 from .anvato import AnvatoIE
 from ..utils import (
     smuggle_url,
@@ -16,7 +14,7 @@ from ..utils import (
 )
 
 
-class ScrippsNetworksWatchIE(InfoExtractor):
+class ScrippsNetworksWatchIE(AWSIE):
     IE_NAME = 'scrippsnetworks:watch'
     _VALID_URL = r'''(?x)
                     https?://
@@ -64,44 +62,27 @@ class ScrippsNetworksWatchIE(InfoExtractor):
         'travelchannel': 'trav',
         'geniuskitchen': 'genius',
     }
-    _SNI_HOST = 'web.api.video.snidigital.com'
 
-    _AWS_REGION = 'us-east-1'
-    _AWS_IDENTITY_ID_JSON = json.dumps({
-        'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % _AWS_REGION
-    })
-    _AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback'
     _AWS_API_KEY = 'E7wSQmq0qK6xPrF13WmzKiHo4BQ7tip4pQcSXVl1'
-    _AWS_SERVICE = 'execute-api'
-    _AWS_REQUEST = 'aws4_request'
-    _AWS_SIGNED_HEADERS = ';'.join([
-        'host', 'x-amz-date', 'x-amz-security-token', 'x-api-key'])
-    _AWS_CANONICAL_REQUEST_TEMPLATE = '''GET
-%(uri)s
+    _AWS_PROXY_HOST = 'web.api.video.snidigital.com'
 
-host:%(host)s
-x-amz-date:%(date)s
-x-amz-security-token:%(token)s
-x-api-key:%(key)s
-
-%(signed_headers)s
-%(payload_hash)s'''
+    _AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         site_id, video_id = mobj.group('site', 'id')
 
-        def aws_hash(s):
-            return hashlib.sha256(s.encode('utf-8')).hexdigest()
-
+        aws_identity_id_json = json.dumps({
+            'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % self._AWS_REGION
+        }).encode('utf-8')
         token = self._download_json(
-            'https://cognito-identity.us-east-1.amazonaws.com/', video_id,
-            data=self._AWS_IDENTITY_ID_JSON.encode('utf-8'),
+            'https://cognito-identity.%s.amazonaws.com/' % self._AWS_REGION, video_id,
+            data=aws_identity_id_json,
             headers={
                 'Accept': '*/*',
                 'Content-Type': 'application/x-amz-json-1.1',
                 'Referer': url,
-                'X-Amz-Content-Sha256': aws_hash(self._AWS_IDENTITY_ID_JSON),
+                'X-Amz-Content-Sha256': hashlib.sha256(aws_identity_id_json).hexdigest(),
                 'X-Amz-Target': 'AWSCognitoIdentityService.GetOpenIdToken',
                 'X-Amz-User-Agent': self._AWS_USER_AGENT,
             })['Token']
@@ -124,64 +105,12 @@ x-api-key:%(key)s
                 sts, './/{https://sts.amazonaws.com/doc/2011-06-15/}%s' % key,
                 fatal=True)
 
-        access_key_id = get('AccessKeyId')
-        secret_access_key = get('SecretAccessKey')
-        session_token = get('SessionToken')
-
-        # Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
-        uri = '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id)
-        datetime_now = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ')
-        date = datetime_now[:8]
-        canonical_string = self._AWS_CANONICAL_REQUEST_TEMPLATE % {
-            'uri': uri,
-            'host': self._SNI_HOST,
-            'date': datetime_now,
-            'token': session_token,
-            'key': self._AWS_API_KEY,
-            'signed_headers': self._AWS_SIGNED_HEADERS,
-            'payload_hash': aws_hash(''),
-        }
-
-        # Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
-        credential_string = '/'.join([date, self._AWS_REGION, self._AWS_SERVICE, self._AWS_REQUEST])
-        string_to_sign = '\n'.join([
-            'AWS4-HMAC-SHA256', datetime_now, credential_string,
-            aws_hash(canonical_string)])
-
-        # Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
-        def aws_hmac(key, msg):
-            return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
-
-        def aws_hmac_digest(key, msg):
-            return aws_hmac(key, msg).digest()
-
-        def aws_hmac_hexdigest(key, msg):
-            return aws_hmac(key, msg).hexdigest()
-
-        k_secret = 'AWS4' + secret_access_key
-        k_date = aws_hmac_digest(k_secret.encode('utf-8'), date)
-        k_region = aws_hmac_digest(k_date, self._AWS_REGION)
-        k_service = aws_hmac_digest(k_region, self._AWS_SERVICE)
-        k_signing = aws_hmac_digest(k_service, self._AWS_REQUEST)
-
-        signature = aws_hmac_hexdigest(k_signing, string_to_sign)
-
-        auth_header = ', '.join([
-            'AWS4-HMAC-SHA256 Credential=%s' % '/'.join(
-                [access_key_id, date, self._AWS_REGION, self._AWS_SERVICE, self._AWS_REQUEST]),
-            'SignedHeaders=%s' % self._AWS_SIGNED_HEADERS,
-            'Signature=%s' % signature,
-        ])
-
-        mcp_id = self._download_json(
-            'https://%s%s' % (self._SNI_HOST, uri), video_id, headers={
-                'Accept': '*/*',
-                'Referer': url,
-                'Authorization': auth_header,
-                'X-Amz-Date': datetime_now,
-                'X-Amz-Security-Token': session_token,
-                'X-Api-Key': self._AWS_API_KEY,
-            })['results'][0]['mcpId']
+        mcp_id = self._aws_execute_api({
+            'uri': '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id),
+            'access_key': get('AccessKeyId'),
+            'secret_key': get('SecretAccessKey'),
+            'session_token': get('SessionToken'),
+        }, video_id)['results'][0]['mcpId']
 
         return self.url_result(
             smuggle_url(

youtube_dl/extractor/sevenplus.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .brightcove import BrightcoveNewIE
+from ..utils import update_url_query
+
+
+class SevenPlusIE(BrightcoveNewIE):
+    IE_NAME = '7plus'
+    _VALID_URL = r'https?://(?:www\.)?7plus\.com\.au/(?P<path>[^?]+\?.*?\bepisode-id=(?P<id>[^&#]+))'
+    _TESTS = [{
+        'url': 'https://7plus.com.au/BEAT?episode-id=BEAT-001',
+        'info_dict': {
+            'id': 'BEAT-001',
+            'ext': 'mp4',
+            'title': 'S1 E1 - Help / Lucy In The Sky With Diamonds',
+            'description': 'md5:37718bea20a8eedaca7f7361af566131',
+            'uploader_id': '5303576322001',
+            'upload_date': '20171031',
+            'timestamp': 1509440068,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://7plus.com.au/UUUU?episode-id=AUMS43-001',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        path, episode_id = re.match(self._VALID_URL, url).groups()
+
+        media = self._download_json(
+            'https://videoservice.swm.digital/playback', episode_id, query={
+                'appId': '7plus',
+                'deviceType': 'web',
+                'platformType': 'web',
+                'accountId': 5303576322001,
+                'referenceId': 'ref:' + episode_id,
+                'deliveryId': 'csai',
+                'videoType': 'vod',
+            })['media']
+
+        for source in media.get('sources', {}):
+            src = source.get('src')
+            if not src:
+                continue
+            source['src'] = update_url_query(src, {'rule': ''})
+
+        info = self._parse_brightcove_metadata(media, episode_id)
+
+        content = self._download_json(
+            'https://component-cdn.swm.digital/content/' + path,
+            episode_id, headers={
+                'market-id': 4,
+            }, fatal=False) or {}
+        for item in content.get('items', {}):
+            if item.get('componentData', {}).get('componentType') == 'infoPanel':
+                for src_key, dst_key in [('title', 'title'), ('shortSynopsis', 'description')]:
+                    value = item.get(src_key)
+                    if value:
+                        info[dst_key] = value
+
+        return info

youtube_dl/extractor/shahid.py

@@ -1,22 +1,53 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import json
+import math
+import re
 
-from .common import InfoExtractor
+from .aws import AWSIE
 from ..compat import compat_HTTPError
 from ..utils import (
+    clean_html,
     ExtractorError,
+    InAdvancePagedList,
     int_or_none,
     parse_iso8601,
     str_or_none,
     urlencode_postdata,
-    clean_html,
 )
 
 
-class ShahidIE(InfoExtractor):
+class ShahidBaseIE(AWSIE):
+    _AWS_PROXY_HOST = 'api2.shahid.net'
+    _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh'
+
+    def _handle_error(self, e):
+        fail_data = self._parse_json(
+            e.cause.read().decode('utf-8'), None, fatal=False)
+        if fail_data:
+            faults = fail_data.get('faults', [])
+            faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
+            if faults_message:
+                raise ExtractorError(faults_message, expected=True)
+
+    def _call_api(self, path, video_id, request=None):
+        query = {}
+        if request:
+            query['request'] = json.dumps(request)
+        try:
+            return self._aws_execute_api({
+                'uri': '/proxy/v2/' + path,
+                'access_key': 'AKIAI6X4TYCIXM2B7MUQ',
+                'secret_key': '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',
+            }, video_id, query)
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                self._handle_error(e)
+            raise
+
+
+class ShahidIE(ShahidBaseIE):
     _NETRC_MACHINE = 'shahid'
     _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
     _TESTS = [{
@@ -41,34 +72,25 @@ class ShahidIE(InfoExtractor):
         'only_matching': True
     }]
 
-    def _api2_request(self, *args, **kwargs):
-        try:
-            return self._download_json(*args, **kwargs)
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError):
-                fail_data = self._parse_json(
-                    e.cause.read().decode('utf-8'), None, fatal=False)
-                if fail_data:
-                    faults = fail_data.get('faults', [])
-                    faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
-                    if faults_message:
-                        raise ExtractorError(faults_message, expected=True)
-            raise
-
     def _real_initialize(self):
         email, password = self._get_login_info()
         if email is None:
             return
 
-        user_data = self._api2_request(
-            'https://shahid.mbc.net/wd/service/users/login',
-            None, 'Logging in', data=json.dumps({
-                'email': email,
-                'password': password,
-                'basic': 'false',
-            }).encode('utf-8'), headers={
-                'Content-Type': 'application/json; charset=UTF-8',
-            })['user']
+        try:
+            user_data = self._download_json(
+                'https://shahid.mbc.net/wd/service/users/login',
+                None, 'Logging in', data=json.dumps({
+                    'email': email,
+                    'password': password,
+                    'basic': 'false',
+                }).encode('utf-8'), headers={
+                    'Content-Type': 'application/json; charset=UTF-8',
+                })['user']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError):
+                self._handle_error(e)
+            raise
 
         self._download_webpage(
             'https://shahid.mbc.net/populateContext',
@@ -81,25 +103,13 @@ class ShahidIE(InfoExtractor):
                 'sessionId': user_data['sessionId'],
             }))
 
-    def _get_api_data(self, response):
-        data = response.get('data', {})
-
-        error = data.get('error')
-        if error:
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
-                expected=True)
-
-        return data
-
     def _real_extract(self, url):
         page_type, video_id = re.match(self._VALID_URL, url).groups()
         if page_type == 'clip':
             page_type = 'episode'
 
-        playout = self._api2_request(
-            'https://api2.shahid.net/proxy/v2/playout/url/' + video_id,
-            video_id, 'Downloading player JSON')['playout']
+        playout = self._call_api(
+            'playout/url/' + video_id, video_id)['playout']
 
         if playout.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
@@ -107,13 +117,27 @@ class ShahidIE(InfoExtractor):
         formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')
         self._sort_formats(formats)
 
-        video = self._get_api_data(self._download_json(
+        # video = self._call_api(
+        #     'product/id', video_id, {
+        #         'id': video_id,
+        #         'productType': 'ASSET',
+        #         'productSubType': page_type.upper()
+        #     })['productModel']
+
+        response = self._download_json(
             'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
             video_id, 'Downloading video JSON', query={
                 'apiKey': 'sh@hid0nlin3',
                 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
-            }))[page_type]
+            })
+        data = response.get('data', {})
+        error = data.get('error')
+        if error:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
+                expected=True)
 
+        video = data[page_type]
         title = video['title']
         categories = [
             category['name']
@@ -135,3 +159,57 @@ class ShahidIE(InfoExtractor):
             'episode_id': video_id,
             'formats': formats,
         }
+
+
+class ShahidShowIE(ShahidBaseIE):
+    _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187',
+        'info_dict': {
+            'id': '79187',
+            'title': 'رامز قرش البحر',
+            'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff',
+        },
+        'playlist_mincount': 32,
+    }, {
+        'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861',
+        'only_matching': True
+    }]
+    _PAGE_SIZE = 30
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+
+        product = self._call_api(
+            'playableAsset', show_id, {'showId': show_id})['productModel']
+        playlist = product['playlist']
+        playlist_id = playlist['id']
+        show = product.get('show', {})
+
+        def page_func(page_num):
+            playlist = self._call_api(
+                'product/playlist', show_id, {
+                    'playListId': playlist_id,
+                    'pageNumber': page_num,
+                    'pageSize': 30,
+                    'sorts': [{
+                        'order': 'DESC',
+                        'type': 'SORTDATE'
+                    }],
+                })
+            for product in playlist.get('productList', {}).get('products', []):
+                product_url = product.get('productUrl', []).get('url')
+                if not product_url:
+                    continue
+                yield self.url_result(
+                    product_url, 'Shahid',
+                    str_or_none(product.get('id')),
+                    product.get('title'))
+
+        entries = InAdvancePagedList(
+            page_func,
+            math.ceil(playlist['count'] / self._PAGE_SIZE),
+            self._PAGE_SIZE)
+
+        return self.playlist_result(
+            entries, show_id, show.get('title'), show.get('description'))

youtube_dl/extractor/slutload.py

@@ -1,11 +1,13 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 
 
 class SlutloadIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
         'md5': '868309628ba00fd488cf516a113fd717',
         'info_dict': {
@@ -15,11 +17,17 @@ class SlutloadIE(InfoExtractor):
             'age_limit': 18,
             'thumbnail': r're:https?://.*?\.jpg'
         }
-    }
+    }, {
+        # mobile site
+        'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+
+        desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url)
+        webpage = self._download_webpage(desktop_url, video_id)
 
         video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
                                               webpage, 'title').strip()

youtube_dl/extractor/soundcloud.py

@@ -136,6 +136,25 @@ class SoundcloudIE(InfoExtractor):
                 'license': 'all-rights-reserved',
             },
         },
+        # no album art, use avatar pic for thumbnail
+        {
+            'url': 'https://soundcloud.com/garyvee/sideways-prod-mad-real',
+            'md5': '59c7872bc44e5d99b7211891664760c2',
+            'info_dict': {
+                'id': '309699954',
+                'ext': 'mp3',
+                'title': 'Sideways (Prod. Mad Real)',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'uploader': 'garyvee',
+                'upload_date': '20170226',
+                'duration': 207,
+                'thumbnail': r're:https?://.*\.jpg',
+                'license': 'all-rights-reserved',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
     ]
 
     _CLIENT_ID = 'c6CU49JDMapyrQo06UxU9xouB9ZVzqCn'
@@ -160,7 +179,7 @@ class SoundcloudIE(InfoExtractor):
         name = full_title or track_id
         if quiet:
             self.report_extraction(name)
-        thumbnail = info.get('artwork_url')
+        thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url')
         if isinstance(thumbnail, compat_str):
             thumbnail = thumbnail.replace('-large', '-t500x500')
         ext = 'mp3'

youtube_dl/extractor/totalwebcasting.py

@@ -0,0 +1,50 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class TotalWebCastingIE(InfoExtractor):
+    IE_NAME = 'totalwebcasting.com'
+    _VALID_URL = r'https?://www\.totalwebcasting\.com/view/\?func=VOFF.*'
+    _TEST = {
+        'url': 'https://www.totalwebcasting.com/view/?func=VOFF&id=columbia&date=2017-01-04&seq=1',
+        'info_dict': {
+            'id': '270e1c415d443924485f547403180906731570466a42740764673853041316737548',
+            'title': 'Real World Cryptography Conference 2017',
+            'description': 'md5:47a31e91ed537a2bb0d3a091659dc80c',
+        },
+        'playlist_count': 6,
+    }
+
+    def _real_extract(self, url):
+        params = url.split('?', 1)[1]
+        webpage = self._download_webpage(url, params)
+        aprm = self._search_regex(r"startVideo\('(\w+)'", webpage, 'aprm')
+        VLEV = self._download_json("https://www.totalwebcasting.com/view/?func=VLEV&aprm=%s&style=G" % aprm, aprm)
+        parts = []
+        for s in VLEV["aiTimes"].values():
+            n = int(s[:-5])
+            if n == 99:
+                continue
+            if n not in parts:
+                parts.append(n)
+        parts.sort()
+        title = VLEV["title"]
+        entries = []
+        for p in parts:
+            VLEV = self._download_json("https://www.totalwebcasting.com/view/?func=VLEV&aprm=%s&style=G&refP=1&nf=%d&time=1&cs=1&ns=1" % (aprm, p), aprm)
+            for s in VLEV["playerObj"]["clip"]["sources"]:
+                if s["type"] != "video/mp4":
+                    continue
+                entries.append({
+                    "id": "%s_part%d" % (aprm, p),
+                    "url": "https:" + s["src"],
+                    "title": title,
+                })
+        return {
+            '_type': 'multi_video',
+            'id': aprm,
+            'entries': entries,
+            'title': title,
+            'description': VLEV.get("desc"),
+        }

youtube_dl/extractor/twentythreevideo.py

@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class TwentyThreeVideoIE(InfoExtractor):
+    IE_NAME = '23video'
+    _VALID_URL = r'https?://video\.(?P<domain>twentythree\.net|23video\.com|filmweb\.no)/v\.ihtml/player\.html\?(?P<query>.*?\bphoto(?:_|%5f)id=(?P<id>\d+).*)'
+    _TEST = {
+        'url': 'https://video.twentythree.net/v.ihtml/player.html?showDescriptions=0&source=site&photo%5fid=20448876&autoPlay=1',
+        'md5': '75fcf216303eb1dae9920d651f85ced4',
+        'info_dict': {
+            'id': '20448876',
+            'ext': 'mp4',
+            'title': 'Video Marketing Minute: Personalized Video',
+            'timestamp': 1513855354,
+            'upload_date': '20171221',
+            'uploader_id': '12258964',
+            'uploader': 'Rasmus Bysted',
+        }
+    }
+
+    def _real_extract(self, url):
+        domain, query, photo_id = re.match(self._VALID_URL, url).groups()
+        base_url = 'https://video.%s' % domain
+        photo_data = self._download_json(
+            base_url + '/api/photo/list?' + query, photo_id, query={
+                'format': 'json',
+            }, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photo data'))['photo']
+        title = photo_data['title']
+
+        formats = []
+
+        audio_path = photo_data.get('audio_download')
+        if audio_path:
+            formats.append({
+                'format_id': 'audio',
+                'url': base_url + audio_path,
+                'filesize': int_or_none(photo_data.get('audio_size')),
+                'vcodec': 'none',
+            })
+
+        def add_common_info_to_list(l, template, id_field, id_value):
+            f_base = template % id_value
+            f_path = photo_data.get(f_base + 'download')
+            if not f_path:
+                return
+            l.append({
+                id_field: id_value,
+                'url': base_url + f_path,
+                'width': int_or_none(photo_data.get(f_base + 'width')),
+                'height': int_or_none(photo_data.get(f_base + 'height')),
+                'filesize': int_or_none(photo_data.get(f_base + 'size')),
+            })
+
+        for f in ('mobile_high', 'medium', 'hd', '1080p', '4k'):
+            add_common_info_to_list(formats, 'video_%s_', 'format_id', f)
+
+        thumbnails = []
+        for t in ('quad16', 'quad50', 'quad75', 'quad100', 'small', 'portrait', 'standard', 'medium', 'large', 'original'):
+            add_common_info_to_list(thumbnails, '%s_', 'id', t)
+
+        return {
+            'id': photo_id,
+            'title': title,
+            'timestamp': int_or_none(photo_data.get('creation_date_epoch')),
+            'duration': int_or_none(photo_data.get('video_length')),
+            'view_count': int_or_none(photo_data.get('view_count')),
+            'comment_count': int_or_none(photo_data.get('number_of_comments')),
+            'uploader_id': photo_data.get('user_id'),
+            'uploader': photo_data.get('display_name'),
+            'thumbnails': thumbnails,
+            'formats': formats,
+        }

youtube_dl/extractor/twitch.py

@@ -358,9 +358,16 @@ class TwitchPlaylistBaseIE(TwitchBaseIE):
                 break
             offset += limit
         return self.playlist_result(
-            [self.url_result(entry) for entry in orderedSet(entries)],
+            [self._make_url_result(entry) for entry in orderedSet(entries)],
             channel_id, channel_name)
 
+    def _make_url_result(self, url):
+        try:
+            video_id = 'v%s' % TwitchVodIE._match_id(url)
+            return self.url_result(url, TwitchVodIE.ie_key(), video_id=video_id)
+        except AssertionError:
+            return self.url_result(url)
+
     def _extract_playlist_page(self, response):
         videos = response.get('videos')
         return [video['url'] for video in videos] if videos else []

youtube_dl/extractor/ufctv.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    parse_iso8601,
+)
+
+
+class UFCTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ufc\.tv/video/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'https://www.ufc.tv/video/ufc-219-countdown-full-episode',
+        'info_dict': {
+            'id': '34167',
+            'ext': 'mp4',
+            'title': 'UFC 219 Countdown: Full Episode',
+            'description': 'md5:26d4e8bf4665ae5878842d7050c3c646',
+            'timestamp': 1513962360,
+            'upload_date': '20171222',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        video_data = self._download_json(url, display_id, query={
+            'format': 'json',
+        })
+        video_id = str(video_data['id'])
+        title = video_data['name']
+        m3u8_url = self._download_json(
+            'https://www.ufc.tv/service/publishpoint', video_id, query={
+                'type': 'video',
+                'format': 'json',
+                'id': video_id,
+            }, headers={
+                'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0_1 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A402 Safari/604.1',
+            })['path']
+        m3u8_url = m3u8_url.replace('_iphone.', '.')
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'duration': parse_duration(video_data.get('runtime')),
+            'timestamp': parse_iso8601(video_data.get('releaseDate')),
+            'formats': formats,
+        }

youtube_dl/extractor/umg.py

@@ -0,0 +1,103 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_filesize,
+    parse_iso8601,
+)
+
+
+class UMGDeIE(InfoExtractor):
+    IE_NAME = 'umg:de'
+    IE_DESC = 'Universal Music Deutschland'
+    _VALID_URL = r'https?://(?:www\.)?universal-music\.de/[^/]+/videos/[^/?#]+-(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.universal-music.de/sido/videos/jedes-wort-ist-gold-wert-457803',
+        'md5': 'ebd90f48c80dcc82f77251eb1902634f',
+        'info_dict': {
+            'id': '457803',
+            'ext': 'mp4',
+            'title': 'Jedes Wort ist Gold wert',
+            'timestamp': 1513591800,
+            'upload_date': '20171218',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video_data = self._download_json(
+            'https://api.universal-music.de/graphql',
+            video_id, query={
+                'query': '''{
+  universalMusic(channel:16) {
+    video(id:%s) {
+      headline
+      formats {
+        formatId
+        url
+        type
+        width
+        height
+        mimeType
+        fileSize
+      }
+      duration
+      createdDate
+    }
+  }
+}''' % video_id})['data']['universalMusic']['video']
+
+        title = video_data['headline']
+        hls_url_template = 'http://mediadelivery.universal-music-services.de/vod/mp4:autofill/storage/' + '/'.join(list(video_id)) + '/content/%s/file/playlist.m3u8'
+
+        thumbnails = []
+        formats = []
+
+        def add_m3u8_format(format_id):
+            m3u8_formats = self._extract_m3u8_formats(
+                hls_url_template % format_id, video_id, 'mp4',
+                'm3u8_native', m3u8_id='hls', fatal='False')
+            if m3u8_formats and m3u8_formats[0].get('height'):
+                formats.extend(m3u8_formats)
+
+        for f in video_data.get('formats', []):
+            f_url = f.get('url')
+            mime_type = f.get('mimeType')
+            if not f_url or mime_type == 'application/mxf':
+                continue
+            fmt = {
+                'url': f_url,
+                'width': int_or_none(f.get('width')),
+                'height': int_or_none(f.get('height')),
+                'filesize': parse_filesize(f.get('fileSize')),
+            }
+            f_type = f.get('type')
+            if f_type == 'Image':
+                thumbnails.append(fmt)
+            elif f_type == 'Video':
+                format_id = f.get('formatId')
+                if format_id:
+                    fmt['format_id'] = format_id
+                    if mime_type == 'video/mp4':
+                        add_m3u8_format(format_id)
+                urlh = self._request_webpage(f_url, video_id, fatal=False)
+                if urlh:
+                    first_byte = urlh.read(1)
+                    if first_byte not in (b'F', b'\x00'):
+                        continue
+                    formats.append(fmt)
+        if not formats:
+            for format_id in (867, 836, 940):
+                add_m3u8_format(format_id)
+        self._sort_formats(formats, ('width', 'height', 'filesize', 'tbr'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'duration': int_or_none(video_data.get('duration')),
+            'timestamp': parse_iso8601(video_data.get('createdDate'), ' '),
+            'thumbnails': thumbnails,
+            'formats': formats,
+        }

youtube_dl/extractor/vimeo.py

@@ -468,11 +468,12 @@ class VimeoIE(VimeoBaseInfoExtractor):
         request = sanitized_Request(url, headers=headers)
         try:
             webpage, urlh = self._download_webpage_handle(request, video_id)
+            redirect_url = compat_str(urlh.geturl())
             # Some URLs redirect to ondemand can't be extracted with
             # this extractor right away thus should be passed through
             # ondemand extractor (e.g. https://vimeo.com/73445910)
-            if VimeoOndemandIE.suitable(urlh.geturl()):
-                return self.url_result(urlh.geturl(), VimeoOndemandIE.ie_key())
+            if VimeoOndemandIE.suitable(redirect_url):
+                return self.url_result(redirect_url, VimeoOndemandIE.ie_key())
         except ExtractorError as ee:
             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
                 errmsg = ee.cause.read()
@@ -541,15 +542,15 @@ class VimeoIE(VimeoBaseInfoExtractor):
             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
                 if '_video_password_verified' in data:
                     raise ExtractorError('video password verification failed!')
-                self._verify_video_password(url, video_id, webpage)
+                self._verify_video_password(redirect_url, video_id, webpage)
                 return self._real_extract(
-                    smuggle_url(url, {'_video_password_verified': 'verified'}))
+                    smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
             else:
                 raise ExtractorError('Unable to extract info section',
                                      cause=e)
         else:
             if config.get('view') == 4:
-                config = self._verify_player_video_password(url, video_id)
+                config = self._verify_player_video_password(redirect_url, video_id)
 
         def is_rented():
             if '>You rented this title.<' in webpage:

youtube_dl/extractor/vk.py

@@ -414,7 +414,7 @@ class VKIE(VKBaseIE):
 
         view_count = str_to_int(self._search_regex(
             r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
-            info_page, 'view count', fatal=False))
+            info_page, 'view count', default=None))
 
         formats = []
         for format_id, format_url in data.items():

youtube_dl/extractor/voot.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from .kaltura import KalturaIE
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -21,7 +20,6 @@ class VootIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Ishq Ka Rang Safed - Season 01 - Episode 340',
             'description': 'md5:06291fbbbc4dcbe21235c40c262507c1',
-            'uploader_id': 'batchUser',
             'timestamp': 1472162937,
             'upload_date': '20160825',
             'duration': 1146,
@@ -63,6 +61,10 @@ class VootIE(InfoExtractor):
 
         entry_id = media['EntryId']
         title = media['MediaName']
+        formats = self._extract_m3u8_formats(
+            'https://cdnapisec.kaltura.com/p/1982551/playManifest/pt/https/f/applehttp/t/web/e/' + entry_id,
+            video_id, 'mp4', m3u8_id='hls')
+        self._sort_formats(formats)
 
         description, series, season_number, episode, episode_number = [None] * 5
 
@@ -82,9 +84,8 @@ class VootIE(InfoExtractor):
                 episode_number = int_or_none(value)
 
         return {
-            '_type': 'url_transparent',
-            'url': 'kaltura:1982551:%s' % entry_id,
-            'ie_key': KalturaIE.ie_key(),
+            'extractor_key': 'Kaltura',
+            'id': entry_id,
             'title': title,
             'description': description,
             'series': series,
@@ -95,4 +96,5 @@ class VootIE(InfoExtractor):
             'duration': int_or_none(media.get('Duration')),
             'view_count': int_or_none(media.get('ViewCounter')),
             'like_count': int_or_none(media.get('like_counter')),
+            'formats': formats,
         }

youtube_dl/extractor/youku.py

@@ -154,7 +154,7 @@ class YoukuIE(InfoExtractor):
         # request basic data
         basic_data_params = {
             'vid': video_id,
-            'ccode': '0501',
+            'ccode': '0507',
             'client_ip': '192.168.1.1',
             'utid': cna,
             'client_ts': time.time() / 1000,
@@ -241,13 +241,23 @@ class YoukuShowIE(InfoExtractor):
         # Ongoing playlist. The initial page is the last one
         'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
         'only_matching': True,
+    }, {
+        #  No data-id value.
+        'url': 'http://list.youku.com/show/id_zefbfbd61237fefbfbdef.html',
+        'only_matching': True,
+    }, {
+        #  Wrong number of reload_id.
+        'url': 'http://list.youku.com/show/id_z20eb4acaf5c211e3b2ad.html',
+        'only_matching': True,
     }]
 
     def _extract_entries(self, playlist_data_url, show_id, note, query):
         query['callback'] = 'cb'
         playlist_data = self._download_json(
             playlist_data_url, show_id, query=query, note=note,
-            transform_source=lambda s: js_to_json(strip_jsonp(s)))['html']
+            transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html')
+        if playlist_data is None:
+            return [None, None]
         drama_list = (get_element_by_class('p-drama-grid', playlist_data) or
                       get_element_by_class('p-drama-half-row', playlist_data))
         if drama_list is None:
@@ -276,9 +286,9 @@ class YoukuShowIE(InfoExtractor):
             r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id')
         # The first reload_id has the same items as first_page
         reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)
+        entries.extend(initial_entries)
         for idx, reload_id in enumerate(reload_ids):
             if reload_id == first_page_reload_id:
-                entries.extend(initial_entries)
                 continue
             _, new_entries = self._extract_entries(
                 'http://list.youku.com/show/episode', show_id,
@@ -287,8 +297,8 @@ class YoukuShowIE(InfoExtractor):
                     'id': page_config['showid'],
                     'stage': reload_id,
                 })
-            entries.extend(new_entries)
-
+            if new_entries is not None:
+                entries.extend(new_entries)
         desc = self._html_search_meta('description', webpage, fatal=False)
         playlist_title = desc.split(',')[0] if desc else None
         detail_li = get_element_by_class('p-intro', webpage)

youtube_dl/extractor/youtube.py

@@ -2270,6 +2270,19 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
             page, 'title', default=None)
 
+        _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
+        uploader = self._search_regex(
+            r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
+            page, 'uploader', default=None)
+        mobj = re.search(
+            r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
+            page)
+        if mobj:
+            uploader_id = mobj.group('uploader_id')
+            uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
+        else:
+            uploader_id = uploader_url = None
+
         has_videos = True
 
         if not playlist_title:
@@ -2280,8 +2293,15 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             except StopIteration:
                 has_videos = False
 
-        return has_videos, self.playlist_result(
+        playlist = self.playlist_result(
             self._entries(page, playlist_id), playlist_id, playlist_title)
+        playlist.update({
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'uploader_url': uploader_url,
+        })
+
+        return has_videos, playlist
 
     def _check_download_just_video(self, url, playlist_id):
         # Check if it's a video-specific URL

youtube_dl/utils.py

@@ -39,6 +39,7 @@ from .compat import (
     compat_HTMLParser,
     compat_basestring,
     compat_chr,
+    compat_ctypes_WINFUNCTYPE,
     compat_etree_fromstring,
     compat_expanduser,
     compat_html_entities,
@@ -159,6 +160,8 @@ DATE_FORMATS = (
     '%Y-%m-%dT%H:%M',
     '%b %d %Y at %H:%M',
     '%b %d %Y at %H:%M:%S',
+    '%B %d %Y at %H:%M',
+    '%B %d %Y at %H:%M:%S',
 )
 
 DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)
@@ -1328,24 +1331,24 @@ def _windows_write_string(s, out):
     if fileno not in WIN_OUTPUT_IDS:
         return False
 
-    GetStdHandle = ctypes.WINFUNCTYPE(
+    GetStdHandle = compat_ctypes_WINFUNCTYPE(
         ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)(
-        (b'GetStdHandle', ctypes.windll.kernel32))
+        ('GetStdHandle', ctypes.windll.kernel32))
     h = GetStdHandle(WIN_OUTPUT_IDS[fileno])
 
-    WriteConsoleW = ctypes.WINFUNCTYPE(
+    WriteConsoleW = compat_ctypes_WINFUNCTYPE(
         ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR,
         ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD),
-        ctypes.wintypes.LPVOID)((b'WriteConsoleW', ctypes.windll.kernel32))
+        ctypes.wintypes.LPVOID)(('WriteConsoleW', ctypes.windll.kernel32))
     written = ctypes.wintypes.DWORD(0)
 
-    GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)((b'GetFileType', ctypes.windll.kernel32))
+    GetFileType = compat_ctypes_WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)(('GetFileType', ctypes.windll.kernel32))
     FILE_TYPE_CHAR = 0x0002
     FILE_TYPE_REMOTE = 0x8000
-    GetConsoleMode = ctypes.WINFUNCTYPE(
+    GetConsoleMode = compat_ctypes_WINFUNCTYPE(
         ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE,
         ctypes.POINTER(ctypes.wintypes.DWORD))(
-        (b'GetConsoleMode', ctypes.windll.kernel32))
+        ('GetConsoleMode', ctypes.windll.kernel32))
     INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value
 
     def not_a_console(handle):

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2017.12.14'
+__version__ = '2017.12.31'