release 2021.03.02

[ci skip]

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.02.10. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running youtube-dl version **2021.02.10**
+- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [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 2021.02.10
+ [debug] youtube-dl version 2021.03.02
  [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: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -19,7 +19,7 @@ labels: 'site-support-request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.02.10. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running youtube-dl version **2021.02.10**
+- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -18,13 +18,13 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.02.10. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running youtube-dl version **2021.02.10**
+- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -18,7 +18,7 @@ title: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.02.10. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
 - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running youtube-dl version **2021.02.10**
+- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
  [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 2021.02.10
+ [debug] youtube-dl version 2021.03.02
  [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: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -19,13 +19,13 @@ labels: 'request'
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
-- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.02.10. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
 - Finally, put x into all relevant boxes (like this [x])
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running youtube-dl version **2021.02.10**
+- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

ChangeLog

@@ -1,3 +1,65 @@
+version 2021.03.02
+
+Extractors
+* [zdf] Rework extractors (#11606, #13473, #17354, #21185, #26711, #27068,
+  #27930, #28198, #28199, #28274)
+    * Generalize cross-extractor video ids for zdf based extractors
+    * Improve extraction
+    * Fix 3sat and phoenix
+* [stretchinternet] Fix extraction (#28297)
+* [urplay] Fix episode data extraction (#28292)
++ [bandaichannel] Add support for b-ch.com (#21404)
+* [srgssr] Improve extraction (#14717, #14725, #27231, #28238)
+    + Extract subtitle
+    * Fix extraction for new videos
+    * Update srf download domains
+* [vvvvid] Reduce season request payload size
++ [vvvvid] Extract series sublists playlist title (#27601, #27618)
++ [dplay] Extract Ad-Free uplynk URLs (#28160)
++ [wat] Detect DRM protected videos (#27958)
+* [tf1] Improve extraction (#27980, #28040)
+* [tmz] Fix and improve extraction (#24603, #24687, 28211)
++ [gedidigital] Add support for Gedi group sites (#7347, #26946)
+* [youtube] Fix get_video_info request
+
+
+version 2021.02.22
+
+Core
++ [postprocessor/embedthumbnail] Recognize atomicparsley binary in lowercase
+  (#28112)
+
+Extractors
+* [apa] Fix and improve extraction (#27750)
++ [youporn] Extract duration (#28019)
++ [peertube] Add support for canard.tube (#28190)
+* [youtube] Fixup m4a_dash formats (#28165)
++ [samplefocus] Add support for samplefocus.com (#27763)
++ [vimeo] Add support for unlisted video source format extraction
+* [viki] Improve extraction (#26522, #28203)
+    * Extract uploader URL and episode number
+    * Report login required error
+    + Extract 480p formats
+    * Fix API v4 calls
+* [ninegag] Unescape title (#28201)
+* [youtube] Improve URL regular expression (#28193)
++ [youtube] Add support for redirect.invidious.io (#28193)
++ [dplay] Add support for de.hgtv.com (#28182)
++ [dplay] Add support for discoveryplus.com (#24698)
++ [simplecast] Add support for simplecast.com (#24107)
+* [youtube] Fix uploader extraction in flat playlist mode (#28045)
+* [yandexmusic:playlist] Request missing tracks in chunks (#27355, #28184)
++ [storyfire] Add support for storyfire.com (#25628, #26349)
++ [zhihu] Add support for zhihu.com (#28177)
+* [youtube] Fix controversial videos when authenticated with cookies (#28174)
+* [ccma] Fix timestamp parsing in python 2
++ [videopress] Add support for video.wordpress.com
+* [kakao] Improve info extraction and detect geo restriction (#26577)
+* [xboxclips] Fix extraction (#27151)
+* [ard] Improve formats extraction (#28155)
++ [canvas] Add support for dagelijksekost.een.be (#28119)
+
+
 version 2021.02.10
 
 Extractors

docs/supportedsites.md

@@ -82,6 +82,7 @@
  - **awaan:video**
  - **AZMedien**: AZ Medien videos
  - **BaiduVideo**: 百度视频
+ - **bandaichannel**
  - **Bandcamp**
  - **Bandcamp:album**
  - **Bandcamp:weekly**
@@ -212,6 +213,7 @@
  - **curiositystream**
  - **curiositystream:collection**
  - **CWTV**
+ - **DagelijkseKost**: dagelijksekost.een.be
  - **DailyMail**
  - **dailymotion**
  - **dailymotion:playlist**
@@ -233,6 +235,7 @@
  - **DiscoveryGo**
  - **DiscoveryGoPlaylist**
  - **DiscoveryNetworksDe**
+ - **DiscoveryPlus**
  - **DiscoveryVR**
  - **Disney**
  - **dlive:stream**
@@ -328,6 +331,7 @@
  - **Gaskrank**
  - **Gazeta**
  - **GDCVault**
+ - **GediDigital**
  - **generic**: Generic downloader that works on some sites
  - **Gfycat**
  - **GiantBomb**
@@ -353,6 +357,7 @@
  - **HentaiStigma**
  - **hetklokhuis**
  - **hgtv.com:show**
+ - **HGTVDe**
  - **HiDive**
  - **HistoricFilms**
  - **history:player**
@@ -803,6 +808,7 @@
  - **safari:course**: safaribooksonline.com online courses
  - **SAKTV**
  - **SaltTV**
+ - **SampleFocus**
  - **Sapo**: SAPO Vídeos
  - **savefrom.net**
  - **SBS**: sbs.com.au
@@ -825,6 +831,9 @@
  - **ShahidShow**
  - **Shared**: shared.sx
  - **ShowRoomLive**
+ - **simplecast**
+ - **simplecast:episode**
+ - **simplecast:podcast**
  - **Sina**
  - **sky.it**
  - **sky:news**
@@ -877,6 +886,9 @@
  - **Steam**
  - **Stitcher**
  - **StitcherShow**
+ - **StoryFire**
+ - **StoryFireSeries**
+ - **StoryFireUser**
  - **Streamable**
  - **streamcloud.eu**
  - **StreamCZ**
@@ -1198,5 +1210,6 @@
  - **ZattooLive**
  - **ZDF**
  - **ZDFChannel**
+ - **Zhihu**
  - **zingmp3**: mp3.zing.vn
  - **Zype**

test/test_youtube_lists.py

@@ -12,6 +12,7 @@ from test.helper import FakeYDL
 
 from youtube_dl.extractor import (
     YoutubePlaylistIE,
+    YoutubeTabIE,
     YoutubeIE,
 )
 
@@ -57,14 +58,22 @@ class TestYoutubeLists(unittest.TestCase):
         entries = result['entries']
         self.assertEqual(len(entries), 100)
 
-    def test_youtube_flat_playlist_titles(self):
+    def test_youtube_flat_playlist_extraction(self):
         dl = FakeYDL()
         dl.params['extract_flat'] = True
-        ie = YoutubePlaylistIE(dl)
-        result = ie.extract('https://www.youtube.com/playlist?list=PL-KKIb8rvtMSrAO9YFbeM6UQrAqoFTUWv')
+        ie = YoutubeTabIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc')
         self.assertIsPlaylist(result)
-        for entry in result['entries']:
-            self.assertTrue(entry.get('title'))
+        entries = list(result['entries'])
+        self.assertTrue(len(entries) == 1)
+        video = entries[0]
+        self.assertEqual(video['_type'], 'url_transparent')
+        self.assertEqual(video['ie_key'], 'Youtube')
+        self.assertEqual(video['id'], 'BaW_jenozKc')
+        self.assertEqual(video['url'], 'BaW_jenozKc')
+        self.assertEqual(video['title'], 'youtube-dl test video "\'/\\ä↭𝕐')
+        self.assertEqual(video['duration'], 10)
+        self.assertEqual(video['uploader'], 'Philipp Hagemeister')
 
 
 if __name__ == '__main__':

youtube_dl/extractor/apa.py

@@ -6,25 +6,21 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
-    js_to_json,
+    int_or_none,
     url_or_none,
 )
 
 
 class APAIE(InfoExtractor):
-    _VALID_URL = r'https?://[^/]+\.apa\.at/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
     _TESTS = [{
         'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
         'md5': '2b12292faeb0a7d930c778c7a5b4759b',
         'info_dict': {
-            'id': 'jjv85FdZ',
+            'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
             'ext': 'mp4',
-            'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
             'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 254,
-            'timestamp': 1519211149,
-            'upload_date': '20180221',
         },
     }, {
         'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
@@ -46,9 +42,11 @@ class APAIE(InfoExtractor):
                 webpage)]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id, base_url = mobj.group('id', 'base_url')
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            '%s/player/%s' % (base_url, video_id), video_id)
 
         jwplatform_id = self._search_regex(
             r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
@@ -59,16 +57,18 @@ class APAIE(InfoExtractor):
                 'jwplatform:' + jwplatform_id, ie='JWPlatform',
                 video_id=video_id)
 
-        sources = self._parse_json(
-            self._search_regex(
-                r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'),
-            video_id, transform_source=js_to_json)
+        def extract(field, name=None):
+            return self._search_regex(
+                r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
+                webpage, name or field, default=None, group='value')
+
+        title = extract('title') or video_id
+        description = extract('description')
+        thumbnail = extract('poster', 'thumbnail')
 
         formats = []
-        for source in sources:
-            if not isinstance(source, dict):
-                continue
-            source_url = url_or_none(source.get('file'))
+        for format_id in ('hls', 'progressive'):
+            source_url = url_or_none(extract(format_id))
             if not source_url:
                 continue
             ext = determine_ext(source_url)
@@ -77,18 +77,19 @@ class APAIE(InfoExtractor):
                     source_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id='hls', fatal=False))
             else:
+                height = int_or_none(self._search_regex(
+                    r'(\d+)\.mp4', source_url, 'height', default=None))
                 formats.append({
                     'url': source_url,
+                    'format_id': format_id,
+                    'height': height,
                 })
         self._sort_formats(formats)
 
-        thumbnail = self._search_regex(
-            r'image\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
-            'thumbnail', fatal=False, group='url')
-
         return {
             'id': video_id,
-            'title': video_id,
+            'title': title,
+            'description': description,
             'thumbnail': thumbnail,
             'formats': formats,
         }

youtube_dl/extractor/ard.py

@@ -284,20 +284,42 @@ class ARDIE(InfoExtractor):
 
         formats = []
         for a in video_node.findall('.//asset'):
+            file_name = xpath_text(a, './fileName', default=None)
+            if not file_name:
+                continue
+            format_type = a.attrib.get('type')
+            format_url = url_or_none(file_name)
+            if format_url:
+                ext = determine_ext(file_name)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, display_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id=format_type or 'hls', fatal=False))
+                    continue
+                elif ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        update_url_query(format_url, {'hdcore': '3.7.0'}),
+                        display_id, f4m_id=format_type or 'hds', fatal=False))
+                    continue
             f = {
-                'format_id': a.attrib['type'],
-                'width': int_or_none(a.find('./frameWidth').text),
-                'height': int_or_none(a.find('./frameHeight').text),
-                'vbr': int_or_none(a.find('./bitrateVideo').text),
-                'abr': int_or_none(a.find('./bitrateAudio').text),
-                'vcodec': a.find('./codecVideo').text,
-                'tbr': int_or_none(a.find('./totalBitrate').text),
+                'format_id': format_type,
+                'width': int_or_none(xpath_text(a, './frameWidth')),
+                'height': int_or_none(xpath_text(a, './frameHeight')),
+                'vbr': int_or_none(xpath_text(a, './bitrateVideo')),
+                'abr': int_or_none(xpath_text(a, './bitrateAudio')),
+                'vcodec': xpath_text(a, './codecVideo'),
+                'tbr': int_or_none(xpath_text(a, './totalBitrate')),
             }
-            if a.find('./serverPrefix').text:
-                f['url'] = a.find('./serverPrefix').text
-                f['playpath'] = a.find('./fileName').text
+            server_prefix = xpath_text(a, './serverPrefix', default=None)
+            if server_prefix:
+                f.update({
+                    'url': server_prefix,
+                    'playpath': file_name,
+                })
             else:
-                f['url'] = a.find('./fileName').text
+                if not format_url:
+                    continue
+                f['url'] = format_url
             formats.append(f)
         self._sort_formats(formats)
 

youtube_dl/extractor/bandaichannel.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .brightcove import BrightcoveNewIE
+from ..utils import extract_attributes
+
+
+class BandaiChannelIE(BrightcoveNewIE):
+    IE_NAME = 'bandaichannel'
+    _VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
+    _TESTS = [{
+        'url': 'https://www.b-ch.com/titles/514/001',
+        'md5': 'a0f2d787baa5729bed71108257f613a4',
+        'info_dict': {
+            'id': '6128044564001',
+            'ext': 'mp4',
+            'title': 'メタルファイターMIKU 第1話',
+            'timestamp': 1580354056,
+            'uploader_id': '5797077852001',
+            'upload_date': '20200130',
+            'duration': 1387.733,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        attrs = extract_attributes(self._search_regex(
+            r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
+        bc = self._download_json(
+            'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
+            video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
+        return self._parse_brightcove_metadata(bc, bc['id'])

youtube_dl/extractor/canvas.py

@@ -7,19 +7,21 @@ from .common import InfoExtractor
 from .gigya import GigyaBaseIE
 from ..compat import compat_HTTPError
 from ..utils import (
-    extract_attributes,
     ExtractorError,
-    strip_or_none,
+    clean_html,
+    extract_attributes,
     float_or_none,
+    get_element_by_class,
     int_or_none,
     merge_dicts,
     str_or_none,
+    strip_or_none,
     url_or_none,
 )
 
 
 class CanvasIE(InfoExtractor):
-    _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza|dako)/assets/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
         'md5': '68993eda72ef62386a15ea2cf3c93107',
@@ -332,3 +334,51 @@ class VrtNUIE(GigyaBaseIE):
             'display_id': display_id,
             'season_number': int_or_none(page.get('episode_season')),
         })
+
+
+class DagelijkseKostIE(InfoExtractor):
+    IE_DESC = 'dagelijksekost.een.be'
+    _VALID_URL = r'https?://dagelijksekost\.een\.be/gerechten/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://dagelijksekost.een.be/gerechten/hachis-parmentier-met-witloof',
+        'md5': '30bfffc323009a3e5f689bef6efa2365',
+        'info_dict': {
+            'id': 'md-ast-27a4d1ff-7d7b-425e-b84f-a4d227f592fa',
+            'display_id': 'hachis-parmentier-met-witloof',
+            'ext': 'mp4',
+            'title': 'Hachis parmentier met witloof',
+            'description': 'md5:9960478392d87f63567b5b117688cdc5',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 283.02,
+        },
+        'expected_warnings': ['is not a supported codec'],
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        title = strip_or_none(get_element_by_class(
+            'dish-metadata__title', webpage
+        ) or self._html_search_meta(
+            'twitter:title', webpage))
+
+        description = clean_html(get_element_by_class(
+            'dish-description', webpage)
+        ) or self._html_search_meta(
+            ('description', 'twitter:description', 'og:description'),
+            webpage)
+
+        video_id = self._html_search_regex(
+            r'data-url=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
+            group='id')
+
+        return {
+            '_type': 'url_transparent',
+            'url': 'https://mediazone.vrt.be/api/v1/dako/assets/%s' % video_id,
+            'ie_key': CanvasIE.ie_key(),
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/ccma.py

@@ -1,12 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import calendar
 import datetime
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
+    extract_timezone,
     int_or_none,
     parse_duration,
     parse_resolution,
@@ -97,8 +99,9 @@ class CCMAIE(InfoExtractor):
         timestamp = None
         data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
         try:
-            timestamp = datetime.datetime.strptime(
-                data_utc, '%Y-%d-%mT%H:%M:%S%z').timestamp()
+            timezone, data_utc = extract_timezone(data_utc)
+            timestamp = calendar.timegm((datetime.datetime.strptime(
+                data_utc, '%Y-%d-%mT%H:%M:%S') - timezone).timetuple())
         except TypeError:
             pass
 

youtube_dl/extractor/dplay.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
@@ -10,11 +11,13 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     int_or_none,
+    strip_or_none,
     unified_timestamp,
 )
 
 
 class DPlayIE(InfoExtractor):
+    _PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)'
     _VALID_URL = r'''(?x)https?://
         (?P<domain>
             (?:www\.)?(?P<host>d
@@ -24,7 +27,7 @@ class DPlayIE(InfoExtractor):
                 )
             )|
             (?P<subdomain_country>es|it)\.dplay\.com
-        )/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
+        )/[^/]+''' + _PATH_REGEX
 
     _TESTS = [{
         # non geo restricted, via secure api, unsigned download hls URL
@@ -151,56 +154,79 @@ class DPlayIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _process_errors(self, e, geo_countries):
+        info = self._parse_json(e.cause.read().decode('utf-8'), None)
+        error = info['errors'][0]
+        error_code = error.get('code')
+        if error_code == 'access.denied.geoblocked':
+            self.raise_geo_restricted(countries=geo_countries)
+        elif error_code in ('access.denied.missingpackage', 'invalid.token'):
+            raise ExtractorError(
+                'This video is only available for registered users. You may want to use --cookies.', expected=True)
+        raise ExtractorError(info['errors'][0]['detail'], expected=True)
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['Authorization'] = 'Bearer ' + self._download_json(
+            disco_base + 'token', display_id, 'Downloading token',
+            query={
+                'realm': realm,
+            })['data']['attributes']['token']
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        streaming = self._download_json(
+            disco_base + 'playback/videoPlaybackInfo/' + video_id,
+            video_id, headers=headers)['data']['attributes']['streaming']
+        streaming_list = []
+        for format_id, format_dict in streaming.items():
+            streaming_list.append({
+                'type': format_id,
+                'url': format_dict.get('url'),
+            })
+        return streaming_list
+
     def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
         geo_countries = [country.upper()]
         self._initialize_geo_bypass({
             'countries': geo_countries,
         })
         disco_base = 'https://%s/' % disco_host
-        token = self._download_json(
-            disco_base + 'token', display_id, 'Downloading token',
-            query={
-                'realm': realm,
-            })['data']['attributes']['token']
         headers = {
             'Referer': url,
-            'Authorization': 'Bearer ' + token,
         }
-        video = self._download_json(
-            disco_base + 'content/videos/' + display_id, display_id,
-            headers=headers, query={
-                'fields[channel]': 'name',
-                'fields[image]': 'height,src,width',
-                'fields[show]': 'name',
-                'fields[tag]': 'name',
-                'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
-                'include': 'images,primaryChannel,show,tags'
-            })
+        self._update_disco_api_headers(headers, disco_base, display_id, realm)
+        try:
+            video = self._download_json(
+                disco_base + 'content/videos/' + display_id, display_id,
+                headers=headers, query={
+                    'fields[channel]': 'name',
+                    'fields[image]': 'height,src,width',
+                    'fields[show]': 'name',
+                    'fields[tag]': 'name',
+                    'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
+                    'include': 'images,primaryChannel,show,tags'
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+                self._process_errors(e, geo_countries)
+            raise
         video_id = video['data']['id']
         info = video['data']['attributes']
         title = info['name'].strip()
         formats = []
         try:
-            streaming = self._download_json(
-                disco_base + 'playback/videoPlaybackInfo/' + video_id,
-                display_id, headers=headers)['data']['attributes']['streaming']
+            streaming = self._download_video_playback_info(
+                disco_base, video_id, headers)
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
-                info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
-                error = info['errors'][0]
-                error_code = error.get('code')
-                if error_code == 'access.denied.geoblocked':
-                    self.raise_geo_restricted(countries=geo_countries)
-                elif error_code == 'access.denied.missingpackage':
-                    self.raise_login_required()
-                raise ExtractorError(info['errors'][0]['detail'], expected=True)
+                self._process_errors(e, geo_countries)
             raise
-        for format_id, format_dict in streaming.items():
+        for format_dict in streaming:
             if not isinstance(format_dict, dict):
                 continue
             format_url = format_dict.get('url')
             if not format_url:
                 continue
+            format_id = format_dict.get('type')
             ext = determine_ext(format_url)
             if format_id == 'dash' or ext == 'mpd':
                 formats.extend(self._extract_mpd_formats(
@@ -248,7 +274,7 @@ class DPlayIE(InfoExtractor):
             'id': video_id,
             'display_id': display_id,
             'title': title,
-            'description': info.get('description'),
+            'description': strip_or_none(info.get('description')),
             'duration': float_or_none(info.get('videoDuration'), 1000),
             'timestamp': unified_timestamp(info.get('publishStart')),
             'series': series,
@@ -268,3 +294,76 @@ class DPlayIE(InfoExtractor):
         host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
         return self._get_disco_api_info(
             url, display_id, host, 'dplay' + country, country)
+
+
+class DiscoveryPlusIE(DPlayIE):
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/video' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
+        'info_dict': {
+            'id': '1140794',
+            'display_id': 'property-brothers-forever-home/food-and-family',
+            'ext': 'mp4',
+            'title': 'Food and Family',
+            'description': 'The brothers help a Richmond family expand their single-level home.',
+            'duration': 2583.113,
+            'timestamp': 1609304400,
+            'upload_date': '20201230',
+            'creator': 'HGTV',
+            'series': 'Property Brothers: Forever Home',
+            'season_number': 1,
+            'episode_number': 1,
+        },
+        'skip': 'Available for Premium users',
+    }]
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['x-disco-client'] = 'WEB:UNKNOWN:dplus_us:15.0.0'
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        return self._download_json(
+            disco_base + 'playback/v3/videoPlaybackInfo',
+            video_id, headers=headers, data=json.dumps({
+                'deviceInfo': {
+                    'adBlocker': False,
+                },
+                'videoId': video_id,
+                'wisteriaProperties': {
+                    'platform': 'desktop',
+                    'product': 'dplus_us',
+                },
+            }).encode('utf-8'))['data']['attributes']['streaming']
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'us1-prod-direct.discoveryplus.com', 'go', 'us')
+
+
+class HGTVDeIE(DPlayIE):
+    _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
+        'info_dict': {
+            'id': '151205',
+            'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
+            'ext': 'mp4',
+            'title': 'Wer braucht schon eine Toilette',
+            'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
+            'duration': 1177.024,
+            'timestamp': 1595705400,
+            'upload_date': '20200725',
+            'creator': 'HGTV',
+            'series': 'Tiny House - klein, aber oho',
+            'season_number': 3,
+            'episode_number': 3,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')

youtube_dl/extractor/dreisat.py

@@ -1,193 +1,43 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    unified_strdate,
-    xpath_text,
-    determine_ext,
-    float_or_none,
-    ExtractorError,
-)
+from .zdf import ZDFIE
 
 
-class DreiSatIE(InfoExtractor):
+class DreiSatIE(ZDFIE):
     IE_NAME = '3sat'
-    _GEO_COUNTRIES = ['DE']
-    _VALID_URL = r'https?://(?:www\.)?3sat\.de/mediathek/(?:(?:index|mediathek)\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)'
-    _TESTS = [
-        {
-            'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
-            'md5': 'be37228896d30a88f315b638900a026e',
-            'info_dict': {
-                'id': '45918',
-                'ext': 'mp4',
-                'title': 'Waidmannsheil',
-                'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
-                'uploader': 'SCHWEIZWEIT',
-                'uploader_id': '100000210',
-                'upload_date': '20140913'
-            },
-            'params': {
-                'skip_download': True,  # m3u8 downloads
-            }
+    _VALID_URL = r'https?://(?:www\.)?3sat\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
+    _TESTS = [{
+        # Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html
+        'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html',
+        'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
+        'info_dict': {
+            'id': '141007_ab18_10wochensommer_film',
+            'ext': 'mp4',
+            'title': 'Ab 18! - 10 Wochen Sommer',
+            'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
+            'duration': 2660,
+            'timestamp': 1608604200,
+            'upload_date': '20201222',
         },
-        {
-            'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
-            'only_matching': True,
+    }, {
+        'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html',
+        'info_dict': {
+            'id': '140913_sendung_schweizweit',
+            'ext': 'mp4',
+            'title': 'Waidmannsheil',
+            'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
+            'timestamp': 1410623100,
+            'upload_date': '20140913'
         },
-    ]
-
-    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
-        param_groups = {}
-        for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
-            group_id = param_group.get(self._xpath_ns(
-                'id', 'http://www.w3.org/XML/1998/namespace'))
-            params = {}
-            for param in param_group:
-                params[param.get('name')] = param.get('value')
-            param_groups[group_id] = params
-
-        formats = []
-        for video in smil.findall(self._xpath_ns('.//video', namespace)):
-            src = video.get('src')
-            if not src:
-                continue
-            bitrate = int_or_none(self._search_regex(r'_(\d+)k', src, 'bitrate', None)) or float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
-            group_id = video.get('paramGroup')
-            param_group = param_groups[group_id]
-            for proto in param_group['protocols'].split(','):
-                formats.append({
-                    'url': '%s://%s' % (proto, param_group['host']),
-                    'app': param_group['app'],
-                    'play_path': src,
-                    'ext': 'flv',
-                    'format_id': '%s-%d' % (proto, bitrate),
-                    'tbr': bitrate,
-                })
-        self._sort_formats(formats)
-        return formats
-
-    def extract_from_xml_url(self, video_id, xml_url):
-        doc = self._download_xml(
-            xml_url, video_id,
-            note='Downloading video info',
-            errnote='Failed to download video info')
-
-        status_code = xpath_text(doc, './status/statuscode')
-        if status_code and status_code != 'ok':
-            if status_code == 'notVisibleAnymore':
-                message = 'Video %s is not available' % video_id
-            else:
-                message = '%s returned error: %s' % (self.IE_NAME, status_code)
-            raise ExtractorError(message, expected=True)
-
-        title = xpath_text(doc, './/information/title', 'title', True)
-
-        urls = []
-        formats = []
-        for fnode in doc.findall('.//formitaeten/formitaet'):
-            video_url = xpath_text(fnode, 'url')
-            if not video_url or video_url in urls:
-                continue
-            urls.append(video_url)
-
-            is_available = 'http://www.metafilegenerator' not in video_url
-            geoloced = 'static_geoloced_online' in video_url
-            if not is_available or geoloced:
-                continue
-
-            format_id = fnode.attrib['basetype']
-            format_m = re.match(r'''(?x)
-                (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
-                (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
-            ''', format_id)
-
-            ext = determine_ext(video_url, None) or format_m.group('container')
-
-            if ext == 'meta':
-                continue
-            elif ext == 'smil':
-                formats.extend(self._extract_smil_formats(
-                    video_url, video_id, fatal=False))
-            elif ext == 'm3u8':
-                # the certificates are misconfigured (see
-                # https://github.com/ytdl-org/youtube-dl/issues/8665)
-                if video_url.startswith('https://'):
-                    continue
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id=format_id, fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    video_url, video_id, f4m_id=format_id, fatal=False))
-            else:
-                quality = xpath_text(fnode, './quality')
-                if quality:
-                    format_id += '-' + quality
-
-                abr = int_or_none(xpath_text(fnode, './audioBitrate'), 1000)
-                vbr = int_or_none(xpath_text(fnode, './videoBitrate'), 1000)
-
-                tbr = int_or_none(self._search_regex(
-                    r'_(\d+)k', video_url, 'bitrate', None))
-                if tbr and vbr and not abr:
-                    abr = tbr - vbr
-
-                formats.append({
-                    'format_id': format_id,
-                    'url': video_url,
-                    'ext': ext,
-                    'acodec': format_m.group('acodec'),
-                    'vcodec': format_m.group('vcodec'),
-                    'abr': abr,
-                    'vbr': vbr,
-                    'tbr': tbr,
-                    'width': int_or_none(xpath_text(fnode, './width')),
-                    'height': int_or_none(xpath_text(fnode, './height')),
-                    'filesize': int_or_none(xpath_text(fnode, './filesize')),
-                    'protocol': format_m.group('proto').lower(),
-                })
-
-        geolocation = xpath_text(doc, './/details/geolocation')
-        if not formats and geolocation and geolocation != 'none':
-            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
-
-        self._sort_formats(formats)
-
-        thumbnails = []
-        for node in doc.findall('.//teaserimages/teaserimage'):
-            thumbnail_url = node.text
-            if not thumbnail_url:
-                continue
-            thumbnail = {
-                'url': thumbnail_url,
-            }
-            thumbnail_key = node.get('key')
-            if thumbnail_key:
-                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
-                if m:
-                    thumbnail['width'] = int(m.group(1))
-                    thumbnail['height'] = int(m.group(2))
-            thumbnails.append(thumbnail)
-
-        upload_date = unified_strdate(xpath_text(doc, './/details/airtime'))
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': xpath_text(doc, './/information/detail'),
-            'duration': int_or_none(xpath_text(doc, './/details/lengthSec')),
-            'thumbnails': thumbnails,
-            'uploader': xpath_text(doc, './/details/originChannelTitle'),
-            'uploader_id': xpath_text(doc, './/details/originChannelId'),
-            'upload_date': upload_date,
-            'formats': formats,
+        'params': {
+            'skip_download': True,
         }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?id=%s' % video_id
-        return self.extract_from_xml_url(video_id, details_url)
+    }, {
+        # Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
+        'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+        'url': 'https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html',
+        'only_matching': True,
+    }]

youtube_dl/extractor/extractors.py

@@ -90,6 +90,7 @@ from .awaan import (
 )
 from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
+from .bandaichannel import BandaiChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
 from .bbc import (
     BBCCoUkIE,
@@ -163,6 +164,7 @@ from .canvas import (
     CanvasIE,
     CanvasEenIE,
     VrtNUIE,
+    DagelijkseKostIE,
 )
 from .carambatv import (
     CarambaTVIE,
@@ -287,7 +289,11 @@ from .douyutv import (
     DouyuShowIE,
     DouyuTVIE,
 )
-from .dplay import DPlayIE
+from .dplay import (
+    DPlayIE,
+    DiscoveryPlusIE,
+    HGTVDeIE,
+)
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
@@ -416,6 +422,7 @@ from .gamestar import GameStarIE
 from .gaskrank import GaskrankIE
 from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
+from .gedidigital import GediDigitalIE
 from .generic import GenericIE
 from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
@@ -1024,6 +1031,7 @@ from .safari import (
     SafariApiIE,
     SafariCourseIE,
 )
+from .samplefocus import SampleFocusIE
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .sbs import SBSIE
@@ -1056,6 +1064,11 @@ from .shared import (
     VivoIE,
 )
 from .showroomlive import ShowRoomLiveIE
+from .simplecast import (
+    SimplecastIE,
+    SimplecastEpisodeIE,
+    SimplecastPodcastIE,
+)
 from .sina import SinaIE
 from .sixplay import SixPlayIE
 from .skyit import (
@@ -1140,6 +1153,11 @@ from .srgssr import (
 from .srmediathek import SRMediathekIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
+from .storyfire import (
+    StoryFireIE,
+    StoryFireUserIE,
+    StoryFireSeriesIE,
+)
 from .streamable import StreamableIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
@@ -1602,5 +1620,6 @@ from .zattoo import (
     ZattooLiveIE,
 )
 from .zdf import ZDFIE, ZDFChannelIE
+from .zhihu import ZhihuIE
 from .zingmp3 import ZingMp3IE
 from .zype import ZypeIE

youtube_dl/extractor/gedidigital.py

@@ -0,0 +1,161 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+)
+
+
+class GediDigitalIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://video\.
+        (?:
+            (?:
+                (?:espresso\.)?repubblica
+                |lastampa
+                |ilsecoloxix
+            )|
+            (?:
+                iltirreno
+                |messaggeroveneto
+                |ilpiccolo
+                |gazzettadimantova
+                |mattinopadova
+                |laprovinciapavese
+                |tribunatreviso
+                |nuovavenezia
+                |gazzettadimodena
+                |lanuovaferrara
+                |corrierealpi
+                |lasentinella
+            )\.gelocal
+        )\.it(?:/[^/]+){2,3}?/(?P<id>\d+)(?:[/?&#]|$)'''
+    _TESTS = [{
+        'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
+        'md5': '84658d7fb9e55a6e57ecc77b73137494',
+        'info_dict': {
+            'id': '121559',
+            'ext': 'mp4',
+            'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
+            'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
+            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$',
+            'duration': 125,
+        },
+    }, {
+        'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.messaggeroveneto.gelocal.it/locale/maria-giovanna-elmi-covid-vaccino/138155/139268',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilpiccolo.gelocal.it/dossier/big-john/dinosauro-big-john-al-via-le-visite-guidate-a-trieste/135226/135751',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimantova.gelocal.it/locale/dal-ponte-visconteo-di-valeggio-l-and-8217sos-dei-ristoratori-aprire-anche-a-cena/137310/137818',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.mattinopadova.gelocal.it/dossier/coronavirus-in-veneto/covid-a-vo-un-anno-dopo-un-cuore-tricolore-per-non-dimenticare/138402/138964',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.laprovinciapavese.gelocal.it/locale/mede-zona-rossa-via-alle-vaccinazioni-per-gli-over-80/137545/138120',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.tribunatreviso.gelocal.it/dossier/coronavirus-in-veneto/ecco-le-prima-vaccinazioni-di-massa-nella-marca/134485/135024',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.nuovavenezia.gelocal.it/locale/camion-troppo-alto-per-il-ponte-ferroviario-perde-il-carico/135734/136266',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimodena.gelocal.it/locale/modena-scoperta-la-proteina-che-predice-il-livello-di-gravita-del-covid/139109/139796',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lanuovaferrara.gelocal.it/locale/due-bombole-di-gpl-aperte-e-abbandonate-i-vigili-bruciano-il-gas/134391/134957',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.corrierealpi.gelocal.it/dossier/cortina-2021-i-mondiali-di-sci-alpino/mondiali-di-sci-il-timelapse-sulla-splendida-olympia/133760/134331',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lasentinella.gelocal.it/locale/vestigne-centra-un-auto-e-si-ribalta/138931/139466',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.espresso.repubblica.it/tutti-i-video/01-ted-villa/14772',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_meta(
+            ['twitter:title', 'og:title'], webpage, fatal=True)
+        player_data = re.findall(
+            r"PlayerFactory\.setParam\('(?P<type>format|param)',\s*'(?P<name>[^']+)',\s*'(?P<val>[^']+)'\);",
+            webpage)
+
+        formats = []
+        duration = thumb = None
+        for t, n, v in player_data:
+            if t == 'format':
+                if n in ('video-hds-vod-ec', 'video-hls-vod-ec', 'video-viralize', 'video-youtube-pfp'):
+                    continue
+                elif n.endswith('-vod-ak'):
+                    formats.extend(self._extract_akamai_formats(
+                        v, video_id, {'http': 'media.gedidigital.it'}))
+                else:
+                    ext = determine_ext(v)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            v, video_id, 'mp4', 'm3u8_native', m3u8_id=n, fatal=False))
+                        continue
+                    f = {
+                        'format_id': n,
+                        'url': v,
+                    }
+                    if ext == 'mp3':
+                        abr = int_or_none(self._search_regex(
+                            r'-mp3-audio-(\d+)', v, 'abr', default=None))
+                        f.update({
+                            'abr': abr,
+                            'tbr': abr,
+                            'vcodec': 'none'
+                        })
+                    else:
+                        mobj = re.match(r'^video-rrtv-(\d+)(?:-(\d+))?$', n)
+                        if mobj:
+                            f.update({
+                                'height': int(mobj.group(1)),
+                                'vbr': int_or_none(mobj.group(2)),
+                            })
+                        if not f.get('vbr'):
+                            f['vbr'] = int_or_none(self._search_regex(
+                                r'-video-rrtv-(\d+)', v, 'abr', default=None))
+                    formats.append(f)
+            elif t == 'param':
+                if n in ['image_full', 'image']:
+                    thumb = v
+                elif n == 'videoDuration':
+                    duration = int_or_none(v)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta(
+                ['twitter:description', 'og:description', 'description'], webpage),
+            'thumbnail': thumb or self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'duration': duration,
+        }

youtube_dl/extractor/generic.py

@@ -129,6 +129,7 @@ from .odnoklassniki import OdnoklassnikiIE
 from .kinja import KinjaEmbedIE
 from .arcpublishing import ArcPublishingIE
 from .medialaan import MedialaanIE
+from .simplecast import SimplecastIE
 
 
 class GenericIE(InfoExtractor):
@@ -2238,6 +2239,15 @@ class GenericIE(InfoExtractor):
                 'duration': 159,
             },
         },
+        {
+            # Simplecast player embed
+            'url': 'https://www.bio.org/podcast',
+            'info_dict': {
+                'id': 'podcast',
+                'title': 'I AM BIO Podcast | BIO',
+            },
+            'playlist_mincount': 52,
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -2792,6 +2802,12 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
 
+        # Look for Simplecast embeds
+        simplecast_urls = SimplecastIE._extract_urls(webpage)
+        if simplecast_urls:
+            return self.playlist_from_matches(
+                simplecast_urls, video_id, video_title)
+
         # Look for BBC iPlayer embed
         matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
         if matches:

youtube_dl/extractor/kakao.py

@@ -3,10 +3,13 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import compat_HTTPError
 from ..utils import (
+    ExtractorError,
     int_or_none,
+    str_or_none,
     strip_or_none,
+    try_get,
     unified_timestamp,
     update_url_query,
 )
@@ -23,7 +26,7 @@ class KakaoIE(InfoExtractor):
             'id': '301965083',
             'ext': 'mp4',
             'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動！顔高低差GPも！」 『乃木坂工事中』',
-            'uploader_id': 2671005,
+            'uploader_id': '2671005',
             'uploader': '그랑그랑이',
             'timestamp': 1488160199,
             'upload_date': '20170227',
@@ -36,11 +39,15 @@ class KakaoIE(InfoExtractor):
             'ext': 'mp4',
             'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
             'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
-            'uploader_id': 2653210,
+            'uploader_id': '2653210',
             'uploader': '쇼! 음악중심',
             'timestamp': 1485684628,
             'upload_date': '20170129',
         }
+    }, {
+        # geo restricted
+        'url': 'https://tv.kakao.com/channel/3643855/cliplink/412069491',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -68,8 +75,7 @@ class KakaoIE(InfoExtractor):
             'fields': ','.join([
                 '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
                 'description', 'channelId', 'createTime', 'duration', 'playCount',
-                'likeCount', 'commentCount', 'tagList', 'channel', 'name',
-                'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
+                'likeCount', 'commentCount', 'tagList', 'channel', 'name', 'thumbnailUrl',
                 'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
         }
 
@@ -82,24 +88,28 @@ class KakaoIE(InfoExtractor):
 
         title = clip.get('title') or clip_link.get('displayTitle')
 
-        query['tid'] = impress.get('tid', '')
+        query.update({
+            'fields': '-*,code,message,url',
+            'tid': impress.get('tid') or '',
+        })
 
         formats = []
-        for fmt in clip.get('videoOutputList', []):
+        for fmt in (clip.get('videoOutputList') or []):
             try:
                 profile_name = fmt['profile']
                 if profile_name == 'AUDIO':
                     continue
-                query.update({
-                    'profile': profile_name,
-                    'fields': '-*,url',
-                })
-                fmt_url_json = self._download_json(
-                    api_base + 'raw/videolocation', display_id,
-                    'Downloading video URL for profile %s' % profile_name,
-                    query=query, headers=player_header, fatal=False)
-
-                if fmt_url_json is None:
+                query['profile'] = profile_name
+                try:
+                    fmt_url_json = self._download_json(
+                        api_base + 'raw/videolocation', display_id,
+                        'Downloading video URL for profile %s' % profile_name,
+                        query=query, headers=player_header)
+                except ExtractorError as e:
+                    if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+                        resp = self._parse_json(e.cause.read().decode(), video_id)
+                        if resp.get('code') == 'GeoBlocked':
+                            self.raise_geo_restricted()
                     continue
 
                 fmt_url = fmt_url_json['url']
@@ -116,27 +126,13 @@ class KakaoIE(InfoExtractor):
                 pass
         self._sort_formats(formats)
 
-        thumbs = []
-        for thumb in clip.get('clipChapterThumbnailList', []):
-            thumbs.append({
-                'url': thumb.get('thumbnailUrl'),
-                'id': compat_str(thumb.get('timeInSec')),
-                'preference': -1 if thumb.get('isDefault') else 0
-            })
-        top_thumbnail = clip.get('thumbnailUrl')
-        if top_thumbnail:
-            thumbs.append({
-                'url': top_thumbnail,
-                'preference': 10,
-            })
-
         return {
             'id': display_id,
             'title': title,
             'description': strip_or_none(clip.get('description')),
-            'uploader': clip_link.get('channel', {}).get('name'),
-            'uploader_id': clip_link.get('channelId'),
-            'thumbnails': thumbs,
+            'uploader': try_get(clip_link, lambda x: x['channel']['name']),
+            'uploader_id': str_or_none(clip_link.get('channelId')),
+            'thumbnail': clip.get('thumbnailUrl'),
             'timestamp': unified_timestamp(clip_link.get('createTime')),
             'duration': int_or_none(clip.get('duration')),
             'view_count': int_or_none(clip.get('playCount')),

youtube_dl/extractor/ninegag.py

@@ -2,10 +2,11 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     ExtractorError,
+    determine_ext,
     int_or_none,
     try_get,
+    unescapeHTML,
     url_or_none,
 )
 
@@ -14,7 +15,7 @@ class NineGagIE(InfoExtractor):
     IE_NAME = '9gag'
     _VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'https://9gag.com/gag/ae5Ag7B',
         'info_dict': {
             'id': 'ae5Ag7B',
@@ -29,7 +30,11 @@ class NineGagIE(InfoExtractor):
             'dislike_count': int,
             'comment_count': int,
         }
-    }
+    }, {
+        # HTML escaped title
+        'url': 'https://9gag.com/gag/av5nvyb',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         post_id = self._match_id(url)
@@ -43,7 +48,7 @@ class NineGagIE(InfoExtractor):
                 'The given url does not contain a video',
                 expected=True)
 
-        title = post['title']
+        title = unescapeHTML(post['title'])
 
         duration = None
         formats = []

youtube_dl/extractor/peertube.py

@@ -413,7 +413,8 @@ class PeerTubeIE(InfoExtractor):
                             peertube3\.cpy\.re|
                             peertube2\.cpy\.re|
                             videos\.tcit\.fr|
-                            peertube\.cpy\.re
+                            peertube\.cpy\.re|
+                            canard\.tube
                         )'''
     _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
     _API_BASE = 'https://%s/api/v1/videos/%s/%s'

youtube_dl/extractor/phoenix.py

@@ -1,45 +1,128 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-from .dreisat import DreiSatIE
+import re
+
+from .youtube import YoutubeIE
+from .zdf import ZDFBaseIE
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    merge_dicts,
+    unified_timestamp,
+    xpath_text,
+)
 
 
-class PhoenixIE(DreiSatIE):
+class PhoenixIE(ZDFBaseIE):
     IE_NAME = 'phoenix.de'
-    _VALID_URL = r'''(?x)https?://(?:www\.)?phoenix\.de/content/
-        (?:
-            phoenix/die_sendungen/(?:[^/]+/)?
-        )?
-        (?P<id>[0-9]+)'''
-    _TESTS = [
-        {
-            'url': 'http://www.phoenix.de/content/884301',
-            'md5': 'ed249f045256150c92e72dbb70eadec6',
-            'info_dict': {
-                'id': '884301',
-                'ext': 'mp4',
-                'title': 'Michael Krons mit Hans-Werner Sinn',
-                'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
-                'upload_date': '20141025',
-                'uploader': 'Im Dialog',
-            }
+    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
+    _TESTS = [{
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
+        'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
+        'md5': '34ec321e7eb34231fd88616c65c92db0',
+        'info_dict': {
+            'id': '210222_phx_nachgehakt_corona_protest',
+            'ext': 'mp4',
+            'title': 'Wohin führt der Protest in der Pandemie?',
+            'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
+            'duration': 1691,
+            'timestamp': 1613906100,
+            'upload_date': '20210221',
+            'uploader': 'Phoenix',
+            'channel': 'corona nachgehakt',
         },
-        {
-            'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/869815',
-            'only_matching': True,
+    }, {
+        # Youtube embed
+        'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
+        'info_dict': {
+            'id': 'hMQtqFYjomk',
+            'ext': 'mp4',
+            'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
+            'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
+            'duration': 3509,
+            'upload_date': '20201219',
+            'uploader': 'phoenix',
+            'uploader_id': 'phoenix',
         },
-        {
-            'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/diskussionen/928234',
-            'only_matching': True,
+        'params': {
+            'skip_download': True,
         },
-    ]
+    }, {
+        'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
+        'only_matching': True,
+    }, {
+        # no media
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        article_id = self._match_id(url)
 
-        internal_id = self._search_regex(
-            r'<div class="phx_vod" id="phx_vod_([0-9]+)"',
-            webpage, 'internal video ID')
+        article = self._download_json(
+            'https://www.phoenix.de/response/id/%s' % article_id, article_id,
+            'Downloading article JSON')
 
-        api_url = 'http://www.phoenix.de/php/mediaplayer/data/beitrags_details.php?ak=web&id=%s' % internal_id
-        return self.extract_from_xml_url(video_id, api_url)
+        video = article['absaetze'][0]
+        title = video.get('titel') or article.get('subtitel')
+
+        if video.get('typ') == 'video-youtube':
+            video_id = video['id']
+            return self.url_result(
+                video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
+                video_title=title)
+
+        video_id = compat_str(video.get('basename') or video.get('content'))
+
+        details = self._download_xml(
+            'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
+            video_id, 'Downloading details XML', query={
+                'ak': 'web',
+                'ptmd': 'true',
+                'id': video_id,
+                'profile': 'player2',
+            })
+
+        title = title or xpath_text(
+            details, './/information/title', 'title', fatal=True)
+        content_id = xpath_text(
+            details, './/video/details/basename', 'content id', fatal=True)
+
+        info = self._extract_ptmd(
+            'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
+            content_id, None, url)
+
+        timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
+
+        thumbnails = []
+        for node in details.findall('.//teaserimages/teaserimage'):
+            thumbnail_url = node.text
+            if not thumbnail_url:
+                continue
+            thumbnail = {
+                'url': thumbnail_url,
+            }
+            thumbnail_key = node.get('key')
+            if thumbnail_key:
+                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
+                if m:
+                    thumbnail['width'] = int(m.group(1))
+                    thumbnail['height'] = int(m.group(2))
+            thumbnails.append(thumbnail)
+
+        return merge_dicts(info, {
+            'id': content_id,
+            'title': title,
+            'description': xpath_text(details, './/information/detail'),
+            'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'uploader': xpath_text(details, './/details/channel'),
+            'uploader_id': xpath_text(details, './/details/originChannelId'),
+            'channel': xpath_text(details, './/details/originChannelTitle'),
+        })

youtube_dl/extractor/rts.py

@@ -6,11 +6,12 @@ import re
 from .srgssr import SRGSSRIE
 from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
-    determine_ext,
+    urljoin,
 )
 
 
@@ -21,7 +22,7 @@ class RTSIE(SRGSSRIE):
     _TESTS = [
         {
             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
-            'md5': 'ff7f8450a90cf58dacb64e29707b4a8e',
+            'md5': '753b877968ad8afaeddccc374d4256a5',
             'info_dict': {
                 'id': '3449373',
                 'display_id': 'les-enfants-terribles',
@@ -35,6 +36,7 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': r're:^https?://.*\.image',
                 'view_count': int,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
         },
         {
             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
@@ -63,11 +65,12 @@ class RTSIE(SRGSSRIE):
                 # m3u8 download
                 'skip_download': True,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
             'skip': 'Blocked outside Switzerland',
         },
         {
             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
-            'md5': '1bae984fe7b1f78e94abc74e802ed99f',
+            'md5': '9bb06503773c07ce83d3cbd793cebb91',
             'info_dict': {
                 'id': '5745356',
                 'display_id': 'londres-cachee-par-un-epais-smog',
@@ -81,6 +84,7 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': r're:^https?://.*\.image',
                 'view_count': int,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
         },
         {
             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
@@ -160,7 +164,7 @@ class RTSIE(SRGSSRIE):
         media_type = 'video' if 'video' in all_info else 'audio'
 
         # check for errors
-        self.get_media_data('rts', media_type, media_id)
+        self._get_media_data('rts', media_type, media_id)
 
         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 
@@ -194,6 +198,7 @@ class RTSIE(SRGSSRIE):
                     'tbr': extract_bitrate(format_url),
                 })
 
+        download_base = 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type == 'audio' else '')
         for media in info.get('media', []):
             media_url = media.get('url')
             if not media_url or re.match(r'https?://', media_url):
@@ -205,7 +210,7 @@ class RTSIE(SRGSSRIE):
                 format_id += '-%dk' % rate
             formats.append({
                 'format_id': format_id,
-                'url': 'http://download-video.rts.ch/' + media_url,
+                'url': urljoin(download_base, media_url),
                 'tbr': rate or extract_bitrate(media_url),
             })
 

youtube_dl/extractor/samplefocus.py

@@ -0,0 +1,100 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    get_element_by_attribute,
+    int_or_none,
+)
+
+
+class SampleFocusIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar',
+        'md5': '48c8d62d60be467293912e0e619a5120',
+        'info_dict': {
+            'id': '40316',
+            'display_id': 'lil-peep-sad-emo-guitar',
+            'ext': 'mp3',
+            'title': 'Lil Peep Sad Emo Guitar',
+            'thumbnail': r're:^https?://.+\.png',
+            'license': 'Standard License',
+            'uploader': 'CapsCtrl',
+            'uploader_id': 'capsctrl',
+            'like_count': int,
+            'comment_count': int,
+            'categories': ['Samples', 'Guitar', 'Electric guitar'],
+        },
+    }, {
+        'url': 'https://samplefocus.com/samples/dababy-style-bass-808',
+        'only_matching': True
+    }, {
+        'url': 'https://samplefocus.com/samples/young-chop-kick',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        sample_id = self._search_regex(
+            r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
+            webpage, 'sample id', group='id')
+
+        title = self._og_search_title(webpage, fatal=False) or self._html_search_regex(
+            r'<h1>(.+?)</h1>', webpage, 'title')
+
+        mp3_url = self._search_regex(
+            r'<input[^>]+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P<url>(?:(?!\2).)+)',
+            webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex(
+                r'<meta[^>]+itemprop=(["\'])contentUrl\1[^>]*>',
+                webpage, 'mp3 url', group=0))['content']
+
+        thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex(
+            r'<img[^>]+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P<url>(?:(?!\1).)+)',
+            webpage, 'mp3', fatal=False, group='url')
+
+        comments = []
+        for author_id, author, body in re.findall(r'(?s)<p[^>]+class="comment-author"><a[^>]+href="/users/([^"]+)">([^"]+)</a>.+?<p[^>]+class="comment-body">([^>]+)</p>', webpage):
+            comments.append({
+                'author': author,
+                'author_id': author_id,
+                'text': body,
+            })
+
+        uploader_id = uploader = None
+        mobj = re.search(r'>By <a[^>]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage)
+        if mobj:
+            uploader_id, uploader = mobj.groups()
+
+        breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage)
+        categories = []
+        if breadcrumb:
+            for _, name in re.findall(r'<span[^>]+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb):
+                categories.append(name)
+
+        def extract_count(klass):
+            return int_or_none(self._html_search_regex(
+                r'<span[^>]+class=(?:["\'])?%s-count[^>]*>(\d+)' % klass,
+                webpage, klass, fatal=False))
+
+        return {
+            'id': sample_id,
+            'title': title,
+            'url': mp3_url,
+            'display_id': display_id,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'license': self._html_search_regex(
+                r'<a[^>]+href=(["\'])/license\1[^>]*>(?P<license>[^<]+)<',
+                webpage, 'license', fatal=False, group='license'),
+            'uploader_id': uploader_id,
+            'like_count': extract_count('sample-%s-favorites' % sample_id),
+            'comment_count': extract_count('comments'),
+            'comments': comments,
+            'categories': categories,
+        }

youtube_dl/extractor/simplecast.py

@@ -0,0 +1,160 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_podcast_url,
+    int_or_none,
+    parse_iso8601,
+    strip_or_none,
+    try_get,
+    urlencode_postdata,
+)
+
+
+class SimplecastBaseIE(InfoExtractor):
+    _UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
+    _API_BASE = 'https://api.simplecast.com/'
+
+    def _call_api(self, path_tmpl, video_id):
+        return self._download_json(
+            self._API_BASE + path_tmpl % video_id, video_id)
+
+    def _call_search_api(self, resource, resource_id, resource_url):
+        return self._download_json(
+            'https://api.simplecast.com/%ss/search' % resource, resource_id,
+            data=urlencode_postdata({'url': resource_url}))
+
+    def _parse_episode(self, episode):
+        episode_id = episode['id']
+        title = episode['title'].strip()
+        audio_file = episode.get('audio_file') or {}
+        audio_file_url = audio_file.get('url') or episode.get('audio_file_url') or episode['enclosure_url']
+
+        season = episode.get('season') or {}
+        season_href = season.get('href')
+        season_id = None
+        if season_href:
+            season_id = self._search_regex(
+                r'https?://api.simplecast.com/seasons/(%s)' % self._UUID_REGEX,
+                season_href, 'season id', default=None)
+
+        webpage_url = episode.get('episode_url')
+        channel_url = None
+        if webpage_url:
+            channel_url = self._search_regex(
+                r'(https?://[^/]+\.simplecast\.com)',
+                webpage_url, 'channel url', default=None)
+
+        return {
+            'id': episode_id,
+            'display_id': episode.get('slug'),
+            'title': title,
+            'url': clean_podcast_url(audio_file_url),
+            'webpage_url': webpage_url,
+            'channel_url': channel_url,
+            'series': try_get(episode, lambda x: x['podcast']['title']),
+            'season_number': int_or_none(season.get('number')),
+            'season_id': season_id,
+            'thumbnail': episode.get('image_url'),
+            'episode_id': episode_id,
+            'episode_number': int_or_none(episode.get('number')),
+            'description': strip_or_none(episode.get('description')),
+            'timestamp': parse_iso8601(episode.get('published_at')),
+            'duration': int_or_none(episode.get('duration')),
+            'filesize': int_or_none(audio_file.get('size') or episode.get('audio_file_size')),
+        }
+
+
+class SimplecastIE(SimplecastBaseIE):
+    IE_NAME = 'simplecast'
+    _VALID_URL = r'https?://(?:api\.simplecast\.com/episodes|player\.simplecast\.com)/(?P<id>%s)' % SimplecastBaseIE._UUID_REGEX
+    _COMMON_TEST_INFO = {
+        'display_id': 'errant-signal-chris-franklin-new-wave-video-essays',
+        'id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
+        'ext': 'mp3',
+        'title': 'Errant Signal - Chris Franklin & New Wave Video Essays',
+        'episode_number': 1,
+        'episode_id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
+        'description': 'md5:34752789d3d2702e2d2c975fbd14f357',
+        'season_number': 1,
+        'season_id': 'e23df0da-bae4-4531-8bbf-71364a88dc13',
+        'series': 'The RE:BIND.io Podcast',
+        'duration': 5343,
+        'timestamp': 1580979475,
+        'upload_date': '20200206',
+        'webpage_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
+        'channel_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com$',
+    }
+    _TESTS = [{
+        'url': 'https://api.simplecast.com/episodes/b6dc49a2-9404-4853-9aa9-9cfc097be876',
+        'md5': '8c93be7be54251bf29ee97464eabe61c',
+        'info_dict': _COMMON_TEST_INFO,
+    }, {
+        'url': 'https://player.simplecast.com/b6dc49a2-9404-4853-9aa9-9cfc097be876',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'''(?x)<iframe[^>]+src=["\']
+                (
+                    https?://(?:embed\.simplecast\.com/[0-9a-f]{8}|
+                    player\.simplecast\.com/%s
+                ))''' % SimplecastBaseIE._UUID_REGEX, webpage)
+
+    def _real_extract(self, url):
+        episode_id = self._match_id(url)
+        episode = self._call_api('episodes/%s', episode_id)
+        return self._parse_episode(episode)
+
+
+class SimplecastEpisodeIE(SimplecastBaseIE):
+    IE_NAME = 'simplecast:episode'
+    _VALID_URL = r'https?://(?!api\.)[^/]+\.simplecast\.com/episodes/(?P<id>[^/?&#]+)'
+    _TEST = {
+        'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
+        'md5': '8c93be7be54251bf29ee97464eabe61c',
+        'info_dict': SimplecastIE._COMMON_TEST_INFO,
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        episode = self._call_search_api(
+            'episode', mobj.group(1), mobj.group(0))
+        return self._parse_episode(episode)
+
+
+class SimplecastPodcastIE(SimplecastBaseIE):
+    IE_NAME = 'simplecast:podcast'
+    _VALID_URL = r'https?://(?!(?:api|cdn|embed|feeds|player)\.)(?P<id>[^/]+)\.simplecast\.com(?!/episodes/[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://the-re-bind-io-podcast.simplecast.com',
+        'playlist_mincount': 33,
+        'info_dict': {
+            'id': '07d28d26-7522-42eb-8c53-2bdcfc81c43c',
+            'title': 'The RE:BIND.io Podcast',
+        },
+    }, {
+        'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        subdomain = self._match_id(url)
+        site = self._call_search_api('site', subdomain, url)
+        podcast = site['podcast']
+        podcast_id = podcast['id']
+        podcast_title = podcast.get('title')
+
+        def entries():
+            episodes = self._call_api('podcasts/%s/episodes', podcast_id)
+            for episode in (episodes.get('collection') or []):
+                info = self._parse_episode(episode)
+                info['series'] = podcast_title
+                yield info
+
+        return self.playlist_result(entries(), podcast_id, podcast_title)

youtube_dl/extractor/srgssr.py

@@ -4,16 +4,32 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     ExtractorError,
+    float_or_none,
+    int_or_none,
     parse_iso8601,
     qualities,
+    try_get,
 )
 
 
 class SRGSSRIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
+    _VALID_URL = r'''(?x)
+                    (?:
+                        https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|
+                        srgssr
+                    ):
+                    (?P<bu>
+                        srf|rts|rsi|rtr|swi
+                    ):(?:[^:]+:)?
+                    (?P<type>
+                        video|audio
+                    ):
+                    (?P<id>
+                        [0-9a-f\-]{36}|\d+
+                    )
+                    '''
     _GEO_BYPASS = False
     _GEO_COUNTRIES = ['CH']
 
@@ -25,25 +41,39 @@ class SRGSSRIE(InfoExtractor):
         'LEGAL': 'The video cannot be transmitted for legal reasons.',
         'STARTDATE': 'This video is not yet available. Please try again later.',
     }
+    _DEFAULT_LANGUAGE_CODES = {
+        'srf': 'de',
+        'rts': 'fr',
+        'rsi': 'it',
+        'rtr': 'rm',
+        'swi': 'en',
+    }
 
     def _get_tokenized_src(self, url, video_id, format_id):
-        sp = compat_urllib_parse_urlparse(url).path.split('/')
         token = self._download_json(
-            'http://tp.srgssr.ch/akahd/token?acl=/%s/%s/*' % (sp[1], sp[2]),
+            'http://tp.srgssr.ch/akahd/token?acl=*',
             video_id, 'Downloading %s token' % format_id, fatal=False) or {}
-        auth_params = token.get('token', {}).get('authparams')
+        auth_params = try_get(token, lambda x: x['token']['authparams'])
         if auth_params:
-            url += '?' + auth_params
+            url += ('?' if '?' not in url else '&') + auth_params
         return url
 
-    def get_media_data(self, bu, media_type, media_id):
-        media_data = self._download_json(
-            'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
-            media_id)[media_type.capitalize()]
+    def _get_media_data(self, bu, media_type, media_id):
+        query = {'onlyChapters': True} if media_type == 'video' else {}
+        full_media_data = self._download_json(
+            'https://il.srgssr.ch/integrationlayer/2.0/%s/mediaComposition/%s/%s.json'
+            % (bu, media_type, media_id),
+            media_id, query=query)['chapterList']
+        try:
+            media_data = next(
+                x for x in full_media_data if x.get('id') == media_id)
+        except StopIteration:
+            raise ExtractorError('No media information found')
 
-        if media_data.get('block') and media_data['block'] in self._ERRORS:
-            message = self._ERRORS[media_data['block']]
-            if media_data['block'] == 'GEOBLOCK':
+        block_reason = media_data.get('blockReason')
+        if block_reason and block_reason in self._ERRORS:
+            message = self._ERRORS[block_reason]
+            if block_reason == 'GEOBLOCK':
                 self.raise_geo_restricted(
                     msg=message, countries=self._GEO_COUNTRIES)
             raise ExtractorError(
@@ -53,53 +83,75 @@ class SRGSSRIE(InfoExtractor):
 
     def _real_extract(self, url):
         bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
+        media_data = self._get_media_data(bu, media_type, media_id)
+        title = media_data['title']
 
-        media_data = self.get_media_data(bu, media_type, media_id)
-
-        metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
-        title = metadata['title']
-        description = metadata.get('description')
-        created_date = media_data.get('createdDate') or metadata.get('createdDate')
-        timestamp = parse_iso8601(created_date)
-
-        thumbnails = [{
-            'id': image.get('id'),
-            'url': image['url'],
-        } for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])]
-
-        preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
         formats = []
-        for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []):
-            protocol = source.get('@protocol')
-            for asset in source['url']:
-                asset_url = asset['text']
-                quality = asset['@quality']
-                format_id = '%s-%s' % (protocol, quality)
-                if protocol.startswith('HTTP-HDS') or protocol.startswith('HTTP-HLS'):
-                    asset_url = self._get_tokenized_src(asset_url, media_id, format_id)
-                    if protocol.startswith('HTTP-HDS'):
-                        formats.extend(self._extract_f4m_formats(
-                            asset_url + ('?' if '?' not in asset_url else '&') + 'hdcore=3.4.0',
-                            media_id, f4m_id=format_id, fatal=False))
-                    elif protocol.startswith('HTTP-HLS'):
-                        formats.extend(self._extract_m3u8_formats(
-                            asset_url, media_id, 'mp4', 'm3u8_native',
-                            m3u8_id=format_id, fatal=False))
-                else:
-                    formats.append({
-                        'format_id': format_id,
-                        'url': asset_url,
-                        'preference': preference(quality),
-                        'ext': 'flv' if protocol == 'RTMP' else None,
-                    })
+        q = qualities(['SD', 'HD'])
+        for source in (media_data.get('resourceList') or []):
+            format_url = source.get('url')
+            if not format_url:
+                continue
+            protocol = source.get('protocol')
+            quality = source.get('quality')
+            format_id = []
+            for e in (protocol, source.get('encoding'), quality):
+                if e:
+                    format_id.append(e)
+            format_id = '-'.join(format_id)
+
+            if protocol in ('HDS', 'HLS'):
+                if source.get('tokenType') == 'AKAMAI':
+                    format_url = self._get_tokenized_src(
+                        format_url, media_id, format_id)
+                    formats.extend(self._extract_akamai_formats(
+                        format_url, media_id))
+                elif protocol == 'HLS':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, media_id, 'mp4', 'm3u8_native',
+                        m3u8_id=format_id, fatal=False))
+            elif protocol in ('HTTP', 'HTTPS'):
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                    'quality': q(quality),
+                })
+
+        # This is needed because for audio medias the podcast url is usually
+        # always included, even if is only an audio segment and not the
+        # whole episode.
+        if int_or_none(media_data.get('position')) == 0:
+            for p in ('S', 'H'):
+                podcast_url = media_data.get('podcast%sdUrl' % p)
+                if not podcast_url:
+                    continue
+                quality = p + 'D'
+                formats.append({
+                    'format_id': 'PODCAST-' + quality,
+                    'url': podcast_url,
+                    'quality': q(quality),
+                })
         self._sort_formats(formats)
 
+        subtitles = {}
+        if media_type == 'video':
+            for sub in (media_data.get('subtitleList') or []):
+                sub_url = sub.get('url')
+                if not sub_url:
+                    continue
+                lang = sub.get('locale') or self._DEFAULT_LANGUAGE_CODES[bu]
+                subtitles.setdefault(lang, []).append({
+                    'url': sub_url,
+                })
+
         return {
             'id': media_id,
             'title': title,
-            'description': description,
-            'timestamp': timestamp,
-            'thumbnails': thumbnails,
+            'description': media_data.get('description'),
+            'timestamp': parse_iso8601(media_data.get('date')),
+            'thumbnail': media_data.get('imageUrl'),
+            'duration': float_or_none(media_data.get('duration'), 1000),
+            'subtitles': subtitles,
             'formats': formats,
         }
 
@@ -119,26 +171,17 @@ class SRGSSRPlayIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
-        'md5': 'da6b5b3ac9fa4761a942331cef20fcb3',
+        'md5': '6db2226ba97f62ad42ce09783680046c',
         'info_dict': {
             'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
             'ext': 'mp4',
             'upload_date': '20130701',
             'title': 'Snowden beantragt Asyl in Russland',
-            'timestamp': 1372713995,
-        }
-    }, {
-        # No Speichern (Save) button
-        'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
-        'md5': '0a274ce38fda48c53c01890651985bc6',
-        'info_dict': {
-            'id': '677f5829-e473-4823-ac83-a1087fe97faa',
-            'ext': 'flv',
-            'upload_date': '20130710',
-            'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
-            'description': 'md5:88604432b60d5a38787f152dec89cd56',
-            'timestamp': 1373493600,
+            'timestamp': 1372708215,
+            'duration': 113.827,
+            'thumbnail': r're:^https?://.*1383719781\.png$',
         },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
         'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
         'info_dict': {
@@ -146,7 +189,8 @@ class SRGSSRPlayIE(InfoExtractor):
             'ext': 'mp3',
             'upload_date': '20151013',
             'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
-            'timestamp': 1444750398,
+            'timestamp': 1444709160,
+            'duration': 336.816,
         },
         'params': {
             # rtmp download
@@ -159,19 +203,32 @@ class SRGSSRPlayIE(InfoExtractor):
             'id': '6348260',
             'display_id': '6348260',
             'ext': 'mp4',
-            'duration': 1796,
+            'duration': 1796.76,
             'title': 'Le 19h30',
-            'description': '',
-            'uploader': '19h30',
             'upload_date': '20141201',
             'timestamp': 1417458600,
             'thumbnail': r're:^https?://.*\.image',
-            'view_count': int,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        'url': 'http://play.swissinfo.ch/play/tv/business/video/why-people-were-against-tax-reforms?id=42960270',
+        'info_dict': {
+            'id': '42960270',
+            'ext': 'mp4',
+            'title': 'Why people were against tax reforms',
+            'description': 'md5:7ac442c558e9630e947427469c4b824d',
+            'duration': 94.0,
+            'upload_date': '20170215',
+            'timestamp': 1487173560,
+            'thumbnail': r're:https?://www\.swissinfo\.ch/srgscalableimage/42961964',
+            'subtitles': 'count:9',
+        },
+        'params': {
+            'skip_download': True,
+        }
     }, {
         'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
         'only_matching': True,
@@ -181,6 +238,10 @@ class SRGSSRPlayIE(InfoExtractor):
     }, {
         'url': 'https://www.rts.ch/play/tv/19h30/video/le-19h30?urn=urn:rts:video:6348260',
         'only_matching': True,
+    }, {
+        # audio segment, has podcastSdUrl of the full episode
+        'url': 'https://www.srf.ch/play/radio/popupaudioplayer?id=50b20dc8-f05b-4972-bf03-e438ff2833eb',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -188,5 +249,4 @@ class SRGSSRPlayIE(InfoExtractor):
         bu = mobj.group('bu')
         media_type = mobj.group('type') or mobj.group('type_2')
         media_id = mobj.group('id')
-        # other info can be extracted from url + '&layout=json'
         return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')

youtube_dl/extractor/storyfire.py

@@ -0,0 +1,151 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import functools
+
+from .common import InfoExtractor
+from ..utils import (
+    # HEADRequest,
+    int_or_none,
+    OnDemandPagedList,
+    smuggle_url,
+)
+
+
+class StoryFireBaseIE(InfoExtractor):
+    _VALID_URL_BASE = r'https?://(?:www\.)?storyfire\.com/'
+
+    def _call_api(self, path, video_id, resource, query=None):
+        return self._download_json(
+            'https://storyfire.com/app/%s/%s' % (path, video_id), video_id,
+            'Downloading %s JSON metadata' % resource, query=query)
+
+    def _parse_video(self, video):
+        title = video['title']
+        vimeo_id = self._search_regex(
+            r'https?://player\.vimeo\.com/external/(\d+)',
+            video['vimeoVideoURL'], 'vimeo id')
+
+        # video_url = self._request_webpage(
+        #    HEADRequest(video['vimeoVideoURL']), video_id).geturl()
+        # formats = []
+        # for v_url, suffix in [(video_url, '_sep'), (video_url.replace('/sep/video/', '/video/'), '')]:
+        #    formats.extend(self._extract_m3u8_formats(
+        #        v_url, video_id, 'mp4', 'm3u8_native',
+        #        m3u8_id='hls' + suffix, fatal=False))
+        #    formats.extend(self._extract_mpd_formats(
+        #        v_url.replace('.m3u8', '.mpd'), video_id,
+        #        mpd_id='dash' + suffix, fatal=False))
+        # self._sort_formats(formats)
+
+        uploader_id = video.get('hostID')
+
+        return {
+            '_type': 'url_transparent',
+            'id': vimeo_id,
+            'title': title,
+            'description': video.get('description'),
+            'url': smuggle_url(
+                'https://player.vimeo.com/video/' + vimeo_id, {
+                    'http_headers': {
+                        'Referer': 'https://storyfire.com/',
+                    }
+                }),
+            # 'formats': formats,
+            'thumbnail': video.get('storyImage'),
+            'view_count': int_or_none(video.get('views')),
+            'like_count': int_or_none(video.get('likesCount')),
+            'comment_count': int_or_none(video.get('commentsCount')),
+            'duration': int_or_none(video.get('videoDuration')),
+            'timestamp': int_or_none(video.get('publishDate')),
+            'uploader': video.get('username'),
+            'uploader_id': uploader_id,
+            'uploader_url': 'https://storyfire.com/user/%s/video' % uploader_id if uploader_id else None,
+            'episode_number': int_or_none(video.get('episodeNumber') or video.get('episode_number')),
+        }
+
+
+class StoryFireIE(StoryFireBaseIE):
+    _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'video-details/(?P<id>[0-9a-f]{24})'
+    _TEST = {
+        'url': 'https://storyfire.com/video-details/5df1d132b6378700117f9181',
+        'md5': 'caec54b9e4621186d6079c7ec100c1eb',
+        'info_dict': {
+            'id': '378954662',
+            'ext': 'mp4',
+            'title': 'Buzzfeed Teaches You About Memes',
+            'uploader_id': 'ntZAJFECERSgqHSxzonV5K2E89s1',
+            'timestamp': 1576129028,
+            'description': 'md5:0b4e28021548e144bed69bb7539e62ea',
+            'uploader': 'whang!',
+            'upload_date': '20191212',
+            'duration': 418,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Unable to download JSON metadata']
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        video = self._call_api(
+            'generic/video-detail', video_id, 'video')['video']
+        return self._parse_video(video)
+
+
+class StoryFireUserIE(StoryFireBaseIE):
+    _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'user/(?P<id>[^/]+)/video'
+    _TEST = {
+        'url': 'https://storyfire.com/user/UQ986nFxmAWIgnkZQ0ftVhq4nOk2/video',
+        'info_dict': {
+            'id': 'UQ986nFxmAWIgnkZQ0ftVhq4nOk2',
+        },
+        'playlist_mincount': 151,
+    }
+    _PAGE_SIZE = 20
+
+    def _fetch_page(self, user_id, page):
+        videos = self._call_api(
+            'publicVideos', user_id, 'page %d' % (page + 1), {
+                'skip': page * self._PAGE_SIZE,
+            })['videos']
+        for video in videos:
+            yield self._parse_video(video)
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+        entries = OnDemandPagedList(functools.partial(
+            self._fetch_page, user_id), self._PAGE_SIZE)
+        return self.playlist_result(entries, user_id)
+
+
+class StoryFireSeriesIE(StoryFireBaseIE):
+    _VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'write/series/stories/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://storyfire.com/write/series/stories/-Lq6MsuIHLODO6d2dDkr/',
+        'info_dict': {
+            'id': '-Lq6MsuIHLODO6d2dDkr',
+        },
+        'playlist_mincount': 13,
+    }, {
+        'url': 'https://storyfire.com/write/series/stories/the_mortal_one/',
+        'info_dict': {
+            'id': 'the_mortal_one',
+        },
+        'playlist_count': 0,
+    }]
+
+    def _extract_videos(self, stories):
+        for story in stories.values():
+            if story.get('hasVideo'):
+                yield self._parse_video(story)
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        stories = self._call_api(
+            'seriesStories', series_id, 'series stories')
+        return self.playlist_result(self._extract_videos(stories), series_id)

youtube_dl/extractor/stretchinternet.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
 
 
 class StretchInternetIE(InfoExtractor):
@@ -11,22 +10,28 @@ class StretchInternetIE(InfoExtractor):
         'info_dict': {
             'id': '573272',
             'ext': 'mp4',
-            'title': 'University of Mary Wrestling vs. Upper Iowa',
-            'timestamp': 1575668361,
-            'upload_date': '20191206',
+            'title': 'UNIVERSITY OF MARY WRESTLING VS UPPER IOWA',
+            # 'timestamp': 1575668361,
+            # 'upload_date': '20191206',
+            'uploader_id': '99997',
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        media_url = self._download_json(
+            'https://core.stretchlive.com/trinity/event/tcg/' + video_id,
+            video_id)[0]['media'][0]['url']
         event = self._download_json(
-            'https://api.stretchinternet.com/trinity/event/tcg/' + video_id,
-            video_id)[0]
+            'https://neo-client.stretchinternet.com/portal-ws/getEvent.json',
+            video_id, query={'eventID': video_id, 'token': 'asdf'})['event']
 
         return {
             'id': video_id,
             'title': event['title'],
-            'timestamp': int_or_none(event.get('dateCreated'), 1000),
-            'url': 'https://' + event['media'][0]['url'],
+            # TODO: parse US timezone abbreviations
+            # 'timestamp': event.get('dateTimeString'),
+            'url': 'https://' + media_url,
+            'uploader_id': event.get('ownerID'),
         }

youtube_dl/extractor/tf1.py

@@ -1,92 +1,87 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
+import re
+
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
 
 
 class TF1IE(InfoExtractor):
-    """TF1 uses the wat.tv player."""
-    _VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|(?:www\.)?(?:tfou|ushuaiatv|histoire|tvbreizh))\.fr/(?:[^/]+/)*(?P<id>[^/?#.]+)'
+    _VALID_URL = r'https?://(?:www\.)?tf1\.fr/[^/]+/(?P<program_slug>[^/]+)/videos/(?P<id>[^/?&#]+)\.html'
     _TESTS = [{
-        'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
-        'info_dict': {
-            'id': '10635995',
-            'ext': 'mp4',
-            'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
-            'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
-        },
-        'params': {
-            # Sometimes wat serves the whole file with the --test option
-            'skip_download': True,
-        },
-        'expected_warnings': ['HTTP Error 404'],
-    }, {
-        'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
-        'info_dict': {
-            'id': 'le-grand-mysterioso-chuggington-7085291-739',
-            'ext': 'mp4',
-            'title': 'Le grand Mystérioso - Chuggington',
-            'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
-            'upload_date': '20150103',
-        },
-        'params': {
-            # Sometimes wat serves the whole file with the --test option
-            'skip_download': True,
-        },
-        'skip': 'HTTP Error 410: Gone',
-    }, {
-        'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
-        'only_matching': True,
-    }, {
-        'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
-        'only_matching': True,
-    }, {
         'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
         'info_dict': {
             'id': '13641379',
             'ext': 'mp4',
             'title': 'md5:f392bc52245dc5ad43771650c96fb620',
-            'description': 'md5:44bc54f0a21322f5b91d68e76a544eae',
+            'description': 'md5:a02cdb217141fb2d469d6216339b052f',
             'upload_date': '20190611',
+            'timestamp': 1560273989,
+            'duration': 1738,
+            'series': 'Quotidien avec Yann Barthès',
+            'tags': ['intégrale', 'quotidien', 'Replay'],
         },
         'params': {
             # Sometimes wat serves the whole file with the --test option
             'skip_download': True,
+            'format': 'bestvideo',
         },
+    }, {
+        'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        program_slug, slug = re.match(self._VALID_URL, url).groups()
+        video = self._download_json(
+            'https://www.tf1.fr/graphql/web', slug, query={
+                'id': '9b80783950b85247541dd1d851f9cc7fa36574af015621f853ab111a679ce26f',
+                'variables': json.dumps({
+                    'programSlug': program_slug,
+                    'slug': slug,
+                })
+            })['data']['videoBySlug']
+        wat_id = video['streamId']
 
-        webpage = self._download_webpage(url, video_id)
+        tags = []
+        for tag in (video.get('tags') or []):
+            label = tag.get('label')
+            if not label:
+                continue
+            tags.append(label)
 
-        wat_id = None
+        decoration = video.get('decoration') or {}
 
-        data = self._parse_json(
-            self._search_regex(
-                r'__APOLLO_STATE__\s*=\s*({.+?})\s*(?:;|</script>)', webpage,
-                'data', default='{}'), video_id, fatal=False)
+        thumbnails = []
+        for source in (try_get(decoration, lambda x: x['image']['sources'], list) or []):
+            source_url = source.get('url')
+            if not source_url:
+                continue
+            thumbnails.append({
+                'url': source_url,
+                'width': int_or_none(source.get('width')),
+            })
 
-        if data:
-            try:
-                wat_id = next(
-                    video.get('streamId')
-                    for key, video in data.items()
-                    if isinstance(video, dict)
-                    and video.get('slug') == video_id)
-                if not isinstance(wat_id, compat_str) or not wat_id.isdigit():
-                    wat_id = None
-            except StopIteration:
-                pass
-
-        if not wat_id:
-            wat_id = self._html_search_regex(
-                (r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
-                 r'(["\']?)streamId\1\s*:\s*(["\']?)(?P<id>\d+)\2'),
-                webpage, 'wat id', group='id')
-
-        return self.url_result('wat:%s' % wat_id, 'Wat')
+        return {
+            '_type': 'url_transparent',
+            'id': wat_id,
+            'url': 'wat:' + wat_id,
+            'title': video.get('title'),
+            'thumbnails': thumbnails,
+            'description': decoration.get('description'),
+            'timestamp': parse_iso8601(video.get('date')),
+            'duration': int_or_none(try_get(video, lambda x: x['publicPlayingInfos']['duration'])),
+            'tags': tags,
+            'series': decoration.get('programLabel'),
+            'season_number': int_or_none(video.get('season')),
+            'episode_number': int_or_none(video.get('episode')),
+        }

youtube_dl/extractor/tmz.py

@@ -2,55 +2,110 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .jwplatform import JWPlatformIE
+from .kaltura import KalturaIE
+from ..utils import (
+    int_or_none,
+    unified_timestamp,
+)
 
 
 class TMZIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/?#&]+)'
     _TESTS = [{
-        'url': 'http://www.tmz.com/videos/0_okj015ty/',
-        'md5': '4d22a51ef205b6c06395d8394f72d560',
-        'info_dict': {
-            'id': '0_okj015ty',
-            'ext': 'mp4',
-            'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!',
-            'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie???  Or is she just showing off her amazing boobs?',
-            'timestamp': 1394747163,
-            'uploader_id': 'batchUser',
-            'upload_date': '20140313',
-        }
-    }, {
         'url': 'http://www.tmz.com/videos/0-cegprt2p/',
+        'md5': '31f9223e20eef55954973359afa61a20',
+        'info_dict': {
+            'id': 'P6YjLBLk',
+            'ext': 'mp4',
+            'title': "No Charges Against Hillary Clinton? Harvey Says It Ain't Over Yet",
+            'description': 'md5:b714359fc18607715ebccbd2da8ff488',
+            'timestamp': 1467831837,
+            'upload_date': '20160706',
+        },
+        'add_ie': [JWPlatformIE.ie_key()],
+    }, {
+        'url': 'http://www.tmz.com/videos/0_okj015ty/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tmz.com/videos/071119-chris-morgan-women-4590005-0-zcsejvcr/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tmz.com/videos/2021-02-19-021921-floyd-mayweather-1043872/',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url).replace('-', '_')
-        return self.url_result('kaltura:591531:%s' % video_id, 'Kaltura', video_id)
+
+        webpage = self._download_webpage(url, video_id, fatal=False)
+        if webpage:
+            tmz_video_id = self._search_regex(
+                r'nodeRef\s*:\s*["\']tmz:video:([\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12})',
+                webpage, 'video id', default=None)
+            video = self._download_json(
+                'https://www.tmz.com/_/video/%s' % tmz_video_id, video_id,
+                fatal=False)
+            if video:
+                message = video['message']
+                info = {
+                    '_type': 'url_transparent',
+                    'title': message.get('title'),
+                    'description': message.get('description'),
+                    'timestamp': unified_timestamp(message.get('published_at')),
+                    'duration': int_or_none(message.get('duration')),
+                }
+                jwplatform_id = message.get('jwplayer_media_id')
+                if jwplatform_id:
+                    info.update({
+                        'url': 'jwplatform:%s' % jwplatform_id,
+                        'ie_key': JWPlatformIE.ie_key(),
+                    })
+                else:
+                    kaltura_entry_id = message.get('kaltura_entry_id') or video_id
+                    kaltura_partner_id = message.get('kaltura_partner_id') or '591531'
+                    info.update({
+                        'url': 'kaltura:%s:%s' % (kaltura_partner_id, kaltura_entry_id),
+                        'ie_key': KalturaIE.ie_key(),
+                    })
+                return info
+
+        return self.url_result(
+            'kaltura:591531:%s' % video_id, KalturaIE.ie_key(), video_id)
 
 
 class TMZArticleIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
+    _VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/?#&]+)'
     _TEST = {
         'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
-        'md5': '3316ff838ae5bb7f642537825e1e90d2',
         'info_dict': {
-            'id': '0_6snoelag',
-            'ext': 'mov',
+            'id': 'PAKZa97W',
+            'ext': 'mp4',
             'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
             'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake.  She\'s watching me."',
-            'timestamp': 1429467813,
+            'timestamp': 1429466400,
             'upload_date': '20150419',
-            'uploader_id': 'batchUser',
-        }
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [JWPlatformIE.ie_key()],
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
+
+        tmz_url = self._search_regex(
+            r'clickLink\s*\(\s*["\'](?P<url>%s)' % TMZIE._VALID_URL, webpage,
+            'video id', default=None, group='url')
+        if tmz_url:
+            return self.url_result(tmz_url, ie=TMZIE.ie_key())
+
         embedded_video_info = self._parse_json(self._html_search_regex(
             r'tmzVideoEmbed\(({.+?})\);', webpage, 'embedded video info'),
             video_id)
-
         return self.url_result(
-            'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])
+            'http://www.tmz.com/videos/%s/' % embedded_video_info['id'],
+            ie=TMZIE.ie_key())

youtube_dl/extractor/urplay.py

@@ -21,6 +21,11 @@ class URPlayIE(InfoExtractor):
             'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a',
             'timestamp': 1513292400,
             'upload_date': '20171214',
+            'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
+            'duration': 2269,
+            'categories': ['Kultur & historia'],
+            'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
+            'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
         },
     }, {
         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
@@ -31,6 +36,10 @@ class URPlayIE(InfoExtractor):
             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
             'timestamp': 1440086400,
             'upload_date': '20150820',
+            'series': 'Tripp, Trapp, Träd',
+            'duration': 865,
+            'tags': ['Sova'],
+            'episode': 'Sovkudde',
         },
     }, {
         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
@@ -41,9 +50,11 @@ class URPlayIE(InfoExtractor):
         video_id = self._match_id(url)
         url = url.replace('skola.se/Produkter', 'play.se/program')
         webpage = self._download_webpage(url, video_id)
-        urplayer_data = self._parse_json(self._html_search_regex(
+        vid = int(video_id)
+        accessible_episodes = self._parse_json(self._html_search_regex(
             r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
-            webpage, 'urplayer data'), video_id)['accessibleEpisodes'][0]
+            webpage, 'urplayer data'), video_id)['accessibleEpisodes']
+        urplayer_data = next(e for e in accessible_episodes if e.get('id') == vid)
         episode = urplayer_data['title']
         raw_streaming_info = urplayer_data['streamingInfo']['raw']
         host = self._download_json(

youtube_dl/extractor/videopress.py

@@ -4,21 +4,22 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     determine_ext,
     float_or_none,
+    int_or_none,
     parse_age_limit,
     qualities,
     random_birthday,
-    try_get,
     unified_timestamp,
     urljoin,
 )
 
 
 class VideoPressIE(InfoExtractor):
-    _VALID_URL = r'https?://videopress\.com/embed/(?P<id>[\da-zA-Z]+)'
+    _ID_REGEX = r'[\da-zA-Z]{8}'
+    _PATH_REGEX = r'video(?:\.word)?press\.com/embed/'
+    _VALID_URL = r'https?://%s(?P<id>%s)' % (_PATH_REGEX, _ID_REGEX)
     _TESTS = [{
         'url': 'https://videopress.com/embed/kUJmAcSf',
         'md5': '706956a6c875873d51010921310e4bc6',
@@ -36,35 +37,36 @@ class VideoPressIE(InfoExtractor):
         # 17+, requires birth_* params
         'url': 'https://videopress.com/embed/iH3gstfZ',
         'only_matching': True,
+    }, {
+        'url': 'https://video.wordpress.com/embed/kUJmAcSf',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+src=["\']((?:https?://)?videopress\.com/embed/[\da-zA-Z]+)',
+            r'<iframe[^>]+src=["\']((?:https?://)?%s%s)' % (VideoPressIE._PATH_REGEX, VideoPressIE._ID_REGEX),
             webpage)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         query = random_birthday('birth_year', 'birth_month', 'birth_day')
+        query['fields'] = 'description,duration,file_url_base,files,height,original,poster,rating,title,upload_date,width'
         video = self._download_json(
             'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
             video_id, query=query)
 
         title = video['title']
 
-        def base_url(scheme):
-            return try_get(
-                video, lambda x: x['file_url_base'][scheme], compat_str)
-
-        base_url = base_url('https') or base_url('http')
+        file_url_base = video.get('file_url_base') or {}
+        base_url = file_url_base.get('https') or file_url_base.get('http')
 
         QUALITIES = ('std', 'dvd', 'hd')
         quality = qualities(QUALITIES)
 
         formats = []
-        for format_id, f in video['files'].items():
+        for format_id, f in (video.get('files') or {}).items():
             if not isinstance(f, dict):
                 continue
             for ext, path in f.items():
@@ -75,12 +77,14 @@ class VideoPressIE(InfoExtractor):
                         'ext': determine_ext(path, ext),
                         'quality': quality(format_id),
                     })
-        original_url = try_get(video, lambda x: x['original'], compat_str)
+        original_url = video.get('original')
         if original_url:
             formats.append({
                 'url': original_url,
                 'format_id': 'original',
                 'quality': len(QUALITIES),
+                'width': int_or_none(video.get('width')),
+                'height': int_or_none(video.get('height')),
             })
         self._sort_formats(formats)
 

youtube_dl/extractor/viki.py

@@ -21,6 +21,7 @@ from ..utils import (
     parse_iso8601,
     sanitized_Request,
     std_headers,
+    try_get,
 )
 
 
@@ -30,7 +31,7 @@ class VikiBaseIE(InfoExtractor):
     _API_URL_TEMPLATE = 'https://api.viki.io%s&sig=%s'
 
     _APP = '100005a'
-    _APP_VERSION = '2.2.5.1428709186'
+    _APP_VERSION = '6.0.0'
     _APP_SECRET = 'MM_d*yP@`&1@]@!AVrXf_o-HVEnoTnm$O-ti4[G~$JDI/Dc-&piU&z&5.;:}95=Iad'
 
     _GEO_BYPASS = False
@@ -41,7 +42,7 @@ class VikiBaseIE(InfoExtractor):
     _ERRORS = {
         'geo': 'Sorry, this content is not available in your region.',
         'upcoming': 'Sorry, this content is not yet available.',
-        # 'paywall': 'paywall',
+        'paywall': 'Sorry, this content is only available to Viki Pass Plus subscribers',
     }
 
     def _prepare_call(self, path, timestamp=None, post_data=None):
@@ -62,7 +63,8 @@ class VikiBaseIE(InfoExtractor):
 
     def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
         resp = self._download_json(
-            self._prepare_call(path, timestamp, post_data), video_id, note)
+            self._prepare_call(path, timestamp, post_data), video_id, note,
+            headers={'x-viki-app-ver': self._APP_VERSION})
 
         error = resp.get('error')
         if error:
@@ -82,11 +84,13 @@ class VikiBaseIE(InfoExtractor):
             expected=True)
 
     def _check_errors(self, data):
-        for reason, status in data.get('blocking', {}).items():
+        for reason, status in (data.get('blocking') or {}).items():
             if status and reason in self._ERRORS:
                 message = self._ERRORS[reason]
                 if reason == 'geo':
                     self.raise_geo_restricted(msg=message)
+                elif reason == 'paywall':
+                    self.raise_login_required(message)
                 raise ExtractorError('%s said: %s' % (
                     self.IE_NAME, message), expected=True)
 
@@ -131,13 +135,19 @@ class VikiIE(VikiBaseIE):
         'info_dict': {
             'id': '1023585v',
             'ext': 'mp4',
-            'title': 'Heirs Episode 14',
-            'uploader': 'SBS',
-            'description': 'md5:c4b17b9626dd4b143dcc4d855ba3474e',
+            'title': 'Heirs - Episode 14',
+            'uploader': 'SBS Contents Hub',
+            'timestamp': 1385047627,
             'upload_date': '20131121',
             'age_limit': 13,
+            'duration': 3570,
+            'episode_number': 14,
+        },
+        'params': {
+            'format': 'bestvideo',
         },
         'skip': 'Blocked in the US',
+        'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
     }, {
         # clip
         'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
@@ -153,7 +163,8 @@ class VikiIE(VikiBaseIE):
             'uploader': 'Arirang TV',
             'like_count': int,
             'age_limit': 0,
-        }
+        },
+        'skip': 'Sorry. There was an error loading this video',
     }, {
         'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
         'info_dict': {
@@ -171,7 +182,7 @@ class VikiIE(VikiBaseIE):
     }, {
         # episode
         'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
-        'md5': '94e0e34fd58f169f40c184f232356cfe',
+        'md5': '0a53dc252e6e690feccd756861495a8c',
         'info_dict': {
             'id': '44699v',
             'ext': 'mp4',
@@ -183,6 +194,10 @@ class VikiIE(VikiBaseIE):
             'uploader': 'group8',
             'like_count': int,
             'age_limit': 13,
+            'episode_number': 1,
+        },
+        'params': {
+            'format': 'bestvideo',
         },
         'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
     }, {
@@ -209,7 +224,7 @@ class VikiIE(VikiBaseIE):
     }, {
         # non-English description
         'url': 'http://www.viki.com/videos/158036v-love-in-magic',
-        'md5': 'adf9e321a0ae5d0aace349efaaff7691',
+        'md5': '41faaba0de90483fb4848952af7c7d0d',
         'info_dict': {
             'id': '158036v',
             'ext': 'mp4',
@@ -220,6 +235,10 @@ class VikiIE(VikiBaseIE):
             'title': 'Love In Magic',
             'age_limit': 13,
         },
+        'params': {
+            'format': 'bestvideo',
+        },
+        'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
     }]
 
     def _real_extract(self, url):
@@ -229,36 +248,33 @@ class VikiIE(VikiBaseIE):
             'https://www.viki.com/api/videos/' + video_id,
             video_id, 'Downloading video JSON', headers={
                 'x-client-user-agent': std_headers['User-Agent'],
-                'x-viki-app-ver': '4.0.57',
+                'x-viki-app-ver': '3.0.0',
             })
         video = resp['video']
 
         self._check_errors(video)
 
         title = self.dict_selection(video.get('titles', {}), 'en', allow_fallback=False)
+        episode_number = int_or_none(video.get('number'))
         if not title:
-            title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id
-            container_titles = video.get('container', {}).get('titles', {})
+            title = 'Episode %d' % episode_number if video.get('type') == 'episode' else video.get('id') or video_id
+            container_titles = try_get(video, lambda x: x['container']['titles'], dict) or {}
             container_title = self.dict_selection(container_titles, 'en')
             title = '%s - %s' % (container_title, title)
 
         description = self.dict_selection(video.get('descriptions', {}), 'en')
 
-        duration = int_or_none(video.get('duration'))
-        timestamp = parse_iso8601(video.get('created_at'))
-        uploader = video.get('author')
-        like_count = int_or_none(video.get('likes', {}).get('count'))
-        age_limit = parse_age_limit(video.get('rating'))
+        like_count = int_or_none(try_get(video, lambda x: x['likes']['count']))
 
         thumbnails = []
-        for thumbnail_id, thumbnail in video.get('images', {}).items():
+        for thumbnail_id, thumbnail in (video.get('images') or {}).items():
             thumbnails.append({
                 'id': thumbnail_id,
                 'url': thumbnail.get('url'),
             })
 
         subtitles = {}
-        for subtitle_lang, _ in video.get('subtitle_completions', {}).items():
+        for subtitle_lang, _ in (video.get('subtitle_completions') or {}).items():
             subtitles[subtitle_lang] = [{
                 'ext': subtitles_format,
                 'url': self._prepare_call(
@@ -269,13 +285,15 @@ class VikiIE(VikiBaseIE):
             'id': video_id,
             'title': title,
             'description': description,
-            'duration': duration,
-            'timestamp': timestamp,
-            'uploader': uploader,
+            'duration': int_or_none(video.get('duration')),
+            'timestamp': parse_iso8601(video.get('created_at')),
+            'uploader': video.get('author'),
+            'uploader_url': video.get('author_url'),
             'like_count': like_count,
-            'age_limit': age_limit,
+            'age_limit': parse_age_limit(video.get('rating')),
             'thumbnails': thumbnails,
             'subtitles': subtitles,
+            'episode_number': episode_number,
         }
 
         formats = []
@@ -360,7 +378,7 @@ class VikiChannelIE(VikiBaseIE):
         'info_dict': {
             'id': '50c',
             'title': 'Boys Over Flowers',
-            'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
+            'description': 'md5:804ce6e7837e1fd527ad2f25420f4d59',
         },
         'playlist_mincount': 71,
     }, {
@@ -371,6 +389,7 @@ class VikiChannelIE(VikiBaseIE):
             'description': 'md5:05bf5471385aa8b21c18ad450e350525',
         },
         'playlist_count': 127,
+        'skip': 'Page not found',
     }, {
         'url': 'http://www.viki.com/news/24569c-showbiz-korea',
         'only_matching': True,

youtube_dl/extractor/vimeo.py

@@ -226,10 +226,12 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             'is_live': is_live,
         }
 
-    def _extract_original_format(self, url, video_id):
+    def _extract_original_format(self, url, video_id, unlisted_hash=None):
+        query = {'action': 'load_download_config'}
+        if unlisted_hash:
+            query['unlisted_hash'] = unlisted_hash
         download_data = self._download_json(
-            url, video_id, fatal=False,
-            query={'action': 'load_download_config'},
+            url, video_id, fatal=False, query=query,
             headers={'X-Requested-With': 'XMLHttpRequest'})
         if download_data:
             source_file = download_data.get('source_file')
@@ -509,6 +511,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
         {
             'url': 'https://vimeo.com/160743502/abd0e13fb4',
             'only_matching': True,
+        },
+        {
+            # requires passing unlisted_hash(a52724358e) to load_download_config request
+            'url': 'https://vimeo.com/392479337/a52724358e',
+            'only_matching': True,
         }
         # https://gettingthingsdone.com/workflowmap/
         # vimeo embed with check-password page protected by Referer header
@@ -673,7 +680,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
             if config.get('view') == 4:
                 config = self._verify_player_video_password(redirect_url, video_id, headers)
 
-        vod = config.get('video', {}).get('vod', {})
+        video = config.get('video') or {}
+        vod = video.get('vod') or {}
 
         def is_rented():
             if '>You rented this title.<' in webpage:
@@ -733,7 +741,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         formats = []
 
         source_format = self._extract_original_format(
-            'https://vimeo.com/' + video_id, video_id)
+            'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
         if source_format:
             formats.append(source_format)
 

youtube_dl/extractor/vvvvid.py

@@ -75,12 +75,15 @@ class VVVVIDIE(InfoExtractor):
             'https://www.vvvvid.it/user/login',
             None, headers=self.geo_verification_headers())['data']['conn_id']
 
-    def _download_info(self, show_id, path, video_id, fatal=True):
+    def _download_info(self, show_id, path, video_id, fatal=True, query=None):
+        q = {
+            'conn_id': self._conn_id,
+        }
+        if query:
+            q.update(query)
         response = self._download_json(
             'https://www.vvvvid.it/vvvvid/ondemand/%s/%s' % (show_id, path),
-            video_id, headers=self.geo_verification_headers(), query={
-                'conn_id': self._conn_id,
-            }, fatal=fatal)
+            video_id, headers=self.geo_verification_headers(), query=q, fatal=fatal)
         if not (response or fatal):
             return
         if response.get('result') == 'error':
@@ -98,7 +101,8 @@ class VVVVIDIE(InfoExtractor):
         show_id, season_id, video_id = re.match(self._VALID_URL, url).groups()
 
         response = self._download_info(
-            show_id, 'season/%s' % season_id, video_id)
+            show_id, 'season/%s' % season_id,
+            video_id, query={'video_id': video_id})
 
         vid = int(video_id)
         video_data = list(filter(
@@ -247,9 +251,13 @@ class VVVVIDShowIE(VVVVIDIE):
         show_info = self._download_info(
             show_id, 'info/', show_title, fatal=False)
 
+        if not show_title:
+            base_url += "/title"
+
         entries = []
         for season in (seasons or []):
             episodes = season.get('episodes') or []
+            playlist_title = season.get('name') or show_info.get('title')
             for episode in episodes:
                 if episode.get('playable') is False:
                     continue
@@ -259,12 +267,13 @@ class VVVVIDShowIE(VVVVIDIE):
                     continue
                 info = self._extract_common_video_info(episode)
                 info.update({
-                    '_type': 'url',
+                    '_type': 'url_transparent',
                     'ie_key': VVVVIDIE.ie_key(),
                     'url': '/'.join([base_url, season_id, video_id]),
                     'title': episode.get('title'),
                     'description': episode.get('description'),
                     'season_id': season_id,
+                    'playlist_title': playlist_title,
                 })
                 entries.append(info)
 

youtube_dl/extractor/wat.py

@@ -4,9 +4,10 @@ from __future__ import unicode_literals
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
-    unified_strdate,
-    HEADRequest,
+    ExtractorError,
     int_or_none,
+    try_get,
+    unified_strdate,
 )
 
 
@@ -29,6 +30,7 @@ class WatIE(InfoExtractor):
                 'skip_download': True,
             },
             'expected_warnings': ['HTTP Error 404'],
+            'skip': 'This content is no longer available',
         },
         {
             'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
@@ -40,8 +42,10 @@ class WatIE(InfoExtractor):
                 'upload_date': '20140816',
             },
             'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
+            'skip': 'This content is no longer available',
         },
     ]
+    _GEO_BYPASS = False
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -49,71 +53,54 @@ class WatIE(InfoExtractor):
 
         # 'contentv4' is used in the website, but it also returns the related
         # videos, we don't need them
+        # video_data = self._download_json(
+        #     'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
         video_data = self._download_json(
-            'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
+            'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
+            video_id, query={'context': 'MYTF1'})
         video_info = video_data['media']
 
         error_desc = video_info.get('error_desc')
         if error_desc:
-            self.report_warning(
-                '%s returned error: %s' % (self.IE_NAME, error_desc))
+            if video_info.get('error_code') == 'GEOBLOCKED':
+                self.raise_geo_restricted(error_desc, video_info.get('geoList'))
+            raise ExtractorError(error_desc, expected=True)
 
-        chapters = video_info['chapters']
-        if chapters:
-            first_chapter = chapters[0]
-
-            def video_id_for_chapter(chapter):
-                return chapter['tc_start'].split('-')[0]
-
-            if video_id_for_chapter(first_chapter) != video_id:
-                self.to_screen('Multipart video detected')
-                entries = [self.url_result('wat:%s' % video_id_for_chapter(chapter)) for chapter in chapters]
-                return self.playlist_result(entries, video_id, video_info['title'])
-            # Otherwise we can continue and extract just one part, we have to use
-            # the video id for getting the video url
-        else:
-            first_chapter = video_info
-
-        title = first_chapter['title']
-
-        def extract_url(path_template, url_type):
-            req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id)
-            head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type, fatal=False)
-            if head:
-                red_url = head.geturl()
-                if req_url != red_url:
-                    return red_url
-            return None
+        title = video_info['title']
 
         formats = []
-        manifest_urls = self._download_json(
-            'http://www.wat.tv/get/webhtml/' + video_id, video_id)
-        m3u8_url = manifest_urls.get('hls')
-        if m3u8_url:
-            formats.extend(self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4',
-                'm3u8_native', m3u8_id='hls', fatal=False))
-        mpd_url = manifest_urls.get('mpd')
-        if mpd_url:
-            formats.extend(self._extract_mpd_formats(
-                mpd_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
-                video_id, mpd_id='dash', fatal=False))
-        self._sort_formats(formats)
 
-        date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4')
-        upload_date = unified_strdate(date_diffusion) if date_diffusion else None
-        duration = None
-        files = video_info['files']
-        if files:
-            duration = int_or_none(files[0].get('duration'))
+        def extract_formats(manifest_urls):
+            for f, f_url in manifest_urls.items():
+                if not f_url:
+                    continue
+                if f in ('dash', 'mpd'):
+                    formats.extend(self._extract_mpd_formats(
+                        f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
+                        video_id, mpd_id='dash', fatal=False))
+                elif f == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        f_url, video_id, 'mp4',
+                        'm3u8_native', m3u8_id='hls', fatal=False))
+
+        delivery = video_data.get('delivery') or {}
+        extract_formats({delivery.get('format'): delivery.get('url')})
+        if not formats:
+            if delivery.get('drm'):
+                raise ExtractorError('This video is DRM protected.', expected=True)
+            manifest_urls = self._download_json(
+                'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False)
+            if manifest_urls:
+                extract_formats(manifest_urls)
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': title,
-            'thumbnail': first_chapter.get('preview'),
-            'description': first_chapter.get('description'),
-            'view_count': int_or_none(video_info.get('views')),
-            'upload_date': upload_date,
-            'duration': duration,
+            'thumbnail': video_info.get('preview'),
+            'upload_date': unified_strdate(try_get(
+                video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])),
+            'duration': int_or_none(video_info.get('duration')),
             'formats': formats,
         }

youtube_dl/extractor/xboxclips.py

@@ -1,40 +1,55 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
     int_or_none,
+    month_by_abbreviation,
     parse_filesize,
-    unified_strdate,
 )
 
 
 class XboxClipsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?xboxclips\.com/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\w-]{36})'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?(?:xboxclips\.com|gameclips\.io)/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
+    _TESTS = [{
         'url': 'http://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
         'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
         'info_dict': {
             'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
             'ext': 'mp4',
-            'title': 'Iabdulelah playing Titanfall',
+            'title': 'iAbdulElah playing Titanfall',
             'filesize_approx': 26800000,
             'upload_date': '20140807',
             'duration': 56,
         }
-    }
+    }, {
+        'url': 'https://gameclips.io/iAbdulElah/074a69a9-5faf-46aa-b93b-9909c1720325',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        if '/video.php' in url:
+            qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+            url = 'https://gameclips.io/%s/%s' % (qs['gamertag'][0], qs['vid'][0])
 
-        video_url = self._html_search_regex(
-            r'>(?:Link|Download): <a[^>]+href="([^"]+)"', webpage, 'video URL')
-        title = self._html_search_regex(
-            r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title')
-        upload_date = unified_strdate(self._html_search_regex(
-            r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False))
+        webpage = self._download_webpage(url, video_id)
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+
+        title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
+        upload_date = None
+        mobj = re.search(
+            r'>Recorded: (\d{2})-(Jan|Feb|Mar|Apr|May|Ju[nl]|Aug|Sep|Oct|Nov|Dec)-(\d{4})',
+            webpage)
+        if mobj:
+            upload_date = '%s%.2d%s' % (mobj.group(3), month_by_abbreviation(mobj.group(2)), mobj.group(1))
         filesize = parse_filesize(self._html_search_regex(
             r'>Size: ([^<]+)<', webpage, 'file size', fatal=False))
         duration = int_or_none(self._html_search_regex(
@@ -42,12 +57,12 @@ class XboxClipsIE(InfoExtractor):
         view_count = int_or_none(self._html_search_regex(
             r'>Views: (\d+)<', webpage, 'view count', fatal=False))
 
-        return {
+        info.update({
             'id': video_id,
-            'url': video_url,
             'title': title,
             'upload_date': upload_date,
             'filesize_approx': filesize,
             'duration': duration,
             'view_count': view_count,
-        }
+        })
+        return info

youtube_dl/extractor/yandexmusic.py

@@ -1,8 +1,9 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
 import hashlib
+import itertools
+import re
 
 from .common import InfoExtractor
 from ..compat import compat_str
@@ -209,17 +210,27 @@ class YandexMusicPlaylistBaseIE(YandexMusicBaseIE):
             missing_track_ids = [
                 track_id for track_id in track_ids
                 if track_id not in present_track_ids]
-            missing_tracks = self._call_api(
-                'track-entries', tld, url, item_id,
-                'Downloading missing tracks JSON', {
-                    'entries': ','.join(missing_track_ids),
-                    'lang': tld,
-                    'external-domain': 'music.yandex.%s' % tld,
-                    'overembed': 'false',
-                    'strict': 'true',
-                })
-            if missing_tracks:
-                tracks.extend(missing_tracks)
+            # Request missing tracks in chunks to avoid exceeding max HTTP header size,
+            # see https://github.com/ytdl-org/youtube-dl/issues/27355
+            _TRACKS_PER_CHUNK = 250
+            for chunk_num in itertools.count(0):
+                start = chunk_num * _TRACKS_PER_CHUNK
+                end = start + _TRACKS_PER_CHUNK
+                missing_track_ids_req = missing_track_ids[start:end]
+                assert missing_track_ids_req
+                missing_tracks = self._call_api(
+                    'track-entries', tld, url, item_id,
+                    'Downloading missing tracks JSON chunk %d' % (chunk_num + 1), {
+                        'entries': ','.join(missing_track_ids_req),
+                        'lang': tld,
+                        'external-domain': 'music.yandex.%s' % tld,
+                        'overembed': 'false',
+                        'strict': 'true',
+                    })
+                if missing_tracks:
+                    tracks.extend(missing_tracks)
+                if end >= len(missing_track_ids):
+                    break
 
         return tracks
 

youtube_dl/extractor/youporn.py

@@ -25,6 +25,7 @@ class YouPornIE(InfoExtractor):
             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
             'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
             'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 210,
             'uploader': 'Ask Dan And Jennifer',
             'upload_date': '20101217',
             'average_rating': int,
@@ -54,6 +55,7 @@ class YouPornIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': '404',
     }, {
         'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
         'only_matching': True,
@@ -153,6 +155,8 @@ class YouPornIE(InfoExtractor):
         thumbnail = self._search_regex(
             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
             webpage, 'thumbnail', fatal=False, group='thumbnail')
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'duration', fatal=False))
 
         uploader = self._html_search_regex(
             r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
@@ -194,6 +198,7 @@ class YouPornIE(InfoExtractor):
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
+            'duration': duration,
             'uploader': uploader,
             'upload_date': upload_date,
             'average_rating': average_rating,

youtube_dl/extractor/youtube.py

@@ -308,7 +308,9 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
             'view count', default=None))
         uploader = try_get(
-            renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
+            renderer,
+            (lambda x: x['ownerText']['runs'][0]['text'],
+             lambda x: x['shortBylineText']['runs'][0]['text']), compat_str)
         return {
             '_type': 'url_transparent',
             'ie_key': YoutubeIE.ie_key(),
@@ -324,52 +326,57 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
 class YoutubeIE(YoutubeBaseInfoExtractor):
     IE_DESC = 'YouTube.com'
+    _INVIDIOUS_SITES = (
+        # invidious-redirect websites
+        r'(?:www\.)?redirect\.invidious\.io',
+        r'(?:(?:www|dev)\.)?invidio\.us',
+        # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
+        r'(?:(?:www|no)\.)?invidiou\.sh',
+        r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
+        r'(?:www\.)?invidious\.kabi\.tk',
+        r'(?:www\.)?invidious\.13ad\.de',
+        r'(?:www\.)?invidious\.mastodon\.host',
+        r'(?:www\.)?invidious\.zapashcanon\.fr',
+        r'(?:www\.)?invidious\.kavin\.rocks',
+        r'(?:www\.)?invidious\.tube',
+        r'(?:www\.)?invidiou\.site',
+        r'(?:www\.)?invidious\.site',
+        r'(?:www\.)?invidious\.xyz',
+        r'(?:www\.)?invidious\.nixnet\.xyz',
+        r'(?:www\.)?invidious\.drycat\.fr',
+        r'(?:www\.)?tube\.poal\.co',
+        r'(?:www\.)?tube\.connect\.cafe',
+        r'(?:www\.)?vid\.wxzm\.sx',
+        r'(?:www\.)?vid\.mint\.lgbt',
+        r'(?:www\.)?yewtu\.be',
+        r'(?:www\.)?yt\.elukerio\.org',
+        r'(?:www\.)?yt\.lelux\.fi',
+        r'(?:www\.)?invidious\.ggc-project\.de',
+        r'(?:www\.)?yt\.maisputain\.ovh',
+        r'(?:www\.)?invidious\.13ad\.de',
+        r'(?:www\.)?invidious\.toot\.koeln',
+        r'(?:www\.)?invidious\.fdn\.fr',
+        r'(?:www\.)?watch\.nettohikari\.com',
+        r'(?:www\.)?kgg2m7yk5aybusll\.onion',
+        r'(?:www\.)?qklhadlycap4cnod\.onion',
+        r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
+        r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
+        r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
+        r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
+        r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
+        r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
+    )
     _VALID_URL = r"""(?x)^
                      (
                          (?:https?://|//)                                    # http(s):// or protocol-independent URL
-                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
-                            (?:www\.)?deturl\.com/www\.youtube\.com/|
-                            (?:www\.)?pwnyoutube\.com/|
-                            (?:www\.)?hooktube\.com/|
-                            (?:www\.)?yourepeat\.com/|
-                            tube\.majestyc\.net/|
-                            # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
-                            (?:(?:www|dev)\.)?invidio\.us/|
-                            (?:(?:www|no)\.)?invidiou\.sh/|
-                            (?:(?:www|fi)\.)?invidious\.snopyta\.org/|
-                            (?:www\.)?invidious\.kabi\.tk/|
-                            (?:www\.)?invidious\.13ad\.de/|
-                            (?:www\.)?invidious\.mastodon\.host/|
-                            (?:www\.)?invidious\.zapashcanon\.fr/|
-                            (?:www\.)?invidious\.kavin\.rocks/|
-                            (?:www\.)?invidious\.tube/|
-                            (?:www\.)?invidiou\.site/|
-                            (?:www\.)?invidious\.site/|
-                            (?:www\.)?invidious\.xyz/|
-                            (?:www\.)?invidious\.nixnet\.xyz/|
-                            (?:www\.)?invidious\.drycat\.fr/|
-                            (?:www\.)?tube\.poal\.co/|
-                            (?:www\.)?tube\.connect\.cafe/|
-                            (?:www\.)?vid\.wxzm\.sx/|
-                            (?:www\.)?vid\.mint\.lgbt/|
-                            (?:www\.)?yewtu\.be/|
-                            (?:www\.)?yt\.elukerio\.org/|
-                            (?:www\.)?yt\.lelux\.fi/|
-                            (?:www\.)?invidious\.ggc-project\.de/|
-                            (?:www\.)?yt\.maisputain\.ovh/|
-                            (?:www\.)?invidious\.13ad\.de/|
-                            (?:www\.)?invidious\.toot\.koeln/|
-                            (?:www\.)?invidious\.fdn\.fr/|
-                            (?:www\.)?watch\.nettohikari\.com/|
-                            (?:www\.)?kgg2m7yk5aybusll\.onion/|
-                            (?:www\.)?qklhadlycap4cnod\.onion/|
-                            (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
-                            (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
-                            (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
-                            (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
-                            (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
-                            (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
-                            youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
+                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
+                            (?:www\.)?deturl\.com/www\.youtube\.com|
+                            (?:www\.)?pwnyoutube\.com|
+                            (?:www\.)?hooktube\.com|
+                            (?:www\.)?yourepeat\.com|
+                            tube\.majestyc\.net|
+                            %(invidious)s|
+                            youtube\.googleapis\.com)/                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:
                              (?:(?:v|embed|e)/(?!videoseries))                # v/ or embed/ or e/
@@ -384,6 +391,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             youtu\.be|                                        # just youtu.be/xxxx
                             vid\.plus|                                        # or vid.plus/xxxx
                             zwearz\.com/watch|                                # or zwearz.com/watch/xxxx
+                            %(invidious)s
                          )/
                          |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                          )
@@ -396,7 +404,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         )
                      )
                      (?(1).+)?                                                # if we found the ID, everything can follow
-                     $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
+                     $""" % {
+        'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
+        'invidious': '|'.join(_INVIDIOUS_SITES),
+    }
     _PLAYER_INFO_RE = (
         r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
         r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
@@ -904,6 +915,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'https://invidio.us/watch?v=BaW_jenozKc',
             'only_matching': True,
         },
+        {
+            'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
+            'only_matching': True,
+        },
+        {
+            # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
+            'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
+            'only_matching': True,
+        },
         {
             # DRM protected
             'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
@@ -1042,6 +1062,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # controversial video, only works with bpctr when authenticated with cookies
+            'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
+            'only_matching': True,
+        },
     ]
     _formats = {
         '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
@@ -1405,7 +1430,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         video_id = self._match_id(url)
         base_url = self.http_scheme() + '//www.youtube.com/'
         webpage_url = base_url + 'watch?v=' + video_id
-        webpage = self._download_webpage(webpage_url, video_id, fatal=False)
+        webpage = self._download_webpage(
+            webpage_url + '&bpctr=9999999999', video_id, fatal=False)
 
         player_response = None
         if webpage:
@@ -1424,7 +1450,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     'Refetching age-gated info webpage',
                     'unable to download video info webpage', query={
                         'video_id': video_id,
-                        'eurl': 'https://www.youtube.com/embed/' + video_id,
+                        'eurl': 'https://youtube.googleapis.com/v/' + video_id,
                     }, fatal=False)),
                 lambda x: x['player_response'][0],
                 compat_str) or '{}', video_id)
@@ -1577,6 +1603,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     # Youtube throttles chunks >~10M
                     'http_chunk_size': 10485760,
                 }
+                if dct.get('ext'):
+                    dct['container'] = dct['ext'] + '_dash'
             formats.append(dct)
 
         hls_manifest_url = streaming_data.get('hlsManifestUrl')

youtube_dl/extractor/zdf.py

@@ -7,7 +7,9 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     determine_ext,
+    float_or_none,
     int_or_none,
+    merge_dicts,
     NO_DEFAULT,
     orderedSet,
     parse_codecs,
@@ -21,49 +23,17 @@ from ..utils import (
 
 
 class ZDFBaseIE(InfoExtractor):
-    def _call_api(self, url, player, referrer, video_id, item):
-        return self._download_json(
-            url, video_id, 'Downloading JSON %s' % item,
-            headers={
-                'Referer': referrer,
-                'Api-Auth': 'Bearer %s' % player['apiToken'],
-            })
-
-    def _extract_player(self, webpage, video_id, fatal=True):
-        return self._parse_json(
-            self._search_regex(
-                r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage,
-                'player JSON', default='{}' if not fatal else NO_DEFAULT,
-                group='json'),
-            video_id)
-
-
-class ZDFIE(ZDFBaseIE):
-    _VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?]+)\.html'
-    _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
     _GEO_COUNTRIES = ['DE']
+    _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
 
-    _TESTS = [{
-        'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
-        'info_dict': {
-            'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
-            'ext': 'mp4',
-            'title': 'Die Magie der Farben (2/2)',
-            'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
-            'duration': 2615,
-            'timestamp': 1465021200,
-            'upload_date': '20160604',
-        },
-    }, {
-        'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
-        'only_matching': True,
-    }]
+    def _call_api(self, url, video_id, item, api_token=None, referrer=None):
+        headers = {}
+        if api_token:
+            headers['Api-Auth'] = 'Bearer %s' % api_token
+        if referrer:
+            headers['Referer'] = referrer
+        return self._download_json(
+            url, video_id, 'Downloading JSON %s' % item, headers=headers)
 
     @staticmethod
     def _extract_subtitles(src):
@@ -109,20 +79,11 @@ class ZDFIE(ZDFBaseIE):
             })
             formats.append(f)
 
-    def _extract_entry(self, url, player, content, video_id):
-        title = content.get('title') or content['teaserHeadline']
-
-        t = content['mainVideoContent']['http://zdf.de/rels/target']
-
-        ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
-
-        if not ptmd_path:
-            ptmd_path = t[
-                'http://zdf.de/rels/streams/ptmd-template'].replace(
-                '{playerId}', 'ngplayer_2_4')
-
+    def _extract_ptmd(self, ptmd_url, video_id, api_token, referrer):
         ptmd = self._call_api(
-            urljoin(url, ptmd_path), player, url, video_id, 'metadata')
+            ptmd_url, video_id, 'metadata', api_token, referrer)
+
+        content_id = ptmd.get('basename') or ptmd_url.split('/')[-1]
 
         formats = []
         track_uris = set()
@@ -140,7 +101,7 @@ class ZDFIE(ZDFBaseIE):
                         continue
                     for track in tracks:
                         self._extract_format(
-                            video_id, formats, track_uris, {
+                            content_id, formats, track_uris, {
                                 'url': track.get('uri'),
                                 'type': f.get('type'),
                                 'mimeType': f.get('mimeType'),
@@ -149,6 +110,103 @@ class ZDFIE(ZDFBaseIE):
                             })
         self._sort_formats(formats)
 
+        duration = float_or_none(try_get(
+            ptmd, lambda x: x['attributes']['duration']['value']), scale=1000)
+
+        return {
+            'extractor_key': ZDFIE.ie_key(),
+            'id': content_id,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': self._extract_subtitles(ptmd),
+        }
+
+    def _extract_player(self, webpage, video_id, fatal=True):
+        return self._parse_json(
+            self._search_regex(
+                r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage,
+                'player JSON', default='{}' if not fatal else NO_DEFAULT,
+                group='json'),
+            video_id)
+
+
+class ZDFIE(ZDFBaseIE):
+    _VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
+    _TESTS = [{
+        # Same as https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html
+        'url': 'https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html',
+        'md5': '34ec321e7eb34231fd88616c65c92db0',
+        'info_dict': {
+            'id': '210222_phx_nachgehakt_corona_protest',
+            'ext': 'mp4',
+            'title': 'Wohin führt der Protest in der Pandemie?',
+            'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
+            'duration': 1691,
+            'timestamp': 1613948400,
+            'upload_date': '20210221',
+        },
+    }, {
+        # Same as https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html
+        'url': 'https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html',
+        'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
+        'info_dict': {
+            'id': '141007_ab18_10wochensommer_film',
+            'ext': 'mp4',
+            'title': 'Ab 18! - 10 Wochen Sommer',
+            'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
+            'duration': 2660,
+            'timestamp': 1608604200,
+            'upload_date': '20201222',
+        },
+    }, {
+        'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
+        'info_dict': {
+            'id': '151025_magie_farben2_tex',
+            'ext': 'mp4',
+            'title': 'Die Magie der Farben (2/2)',
+            'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
+            'duration': 2615,
+            'timestamp': 1465021200,
+            'upload_date': '20160604',
+        },
+    }, {
+        # Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche
+        'url': 'https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.3sat.de/film/spielfilm/der-hauptmann-100.html
+        'url': 'https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+        'url': 'https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
+        'only_matching': True,
+    }]
+
+    def _extract_entry(self, url, player, content, video_id):
+        title = content.get('title') or content['teaserHeadline']
+
+        t = content['mainVideoContent']['http://zdf.de/rels/target']
+
+        ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
+
+        if not ptmd_path:
+            ptmd_path = t[
+                'http://zdf.de/rels/streams/ptmd-template'].replace(
+                '{playerId}', 'ngplayer_2_4')
+
+        info = self._extract_ptmd(
+            urljoin(url, ptmd_path), video_id, player['apiToken'], url)
+
         thumbnails = []
         layouts = try_get(
             content, lambda x: x['teaserImageRef']['layouts'], dict)
@@ -169,33 +227,33 @@ class ZDFIE(ZDFBaseIE):
                     })
                 thumbnails.append(thumbnail)
 
-        return {
-            'id': video_id,
+        return merge_dicts(info, {
             'title': title,
             'description': content.get('leadParagraph') or content.get('teasertext'),
             'duration': int_or_none(t.get('duration')),
             'timestamp': unified_timestamp(content.get('editorialDate')),
             'thumbnails': thumbnails,
-            'subtitles': self._extract_subtitles(ptmd),
-            'formats': formats,
-        }
+        })
 
     def _extract_regular(self, url, player, video_id):
         content = self._call_api(
-            player['content'], player, url, video_id, 'content')
+            player['content'], video_id, 'content', player['apiToken'], url)
         return self._extract_entry(player['content'], player, content, video_id)
 
     def _extract_mobile(self, video_id):
-        document = self._download_json(
+        video = self._download_json(
             'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
-            video_id)['document']
+            video_id)
+
+        document = video['document']
 
         title = document['titel']
+        content_id = document['basename']
 
         formats = []
         format_urls = set()
         for f in document['formitaeten']:
-            self._extract_format(video_id, formats, format_urls, f)
+            self._extract_format(content_id, formats, format_urls, f)
         self._sort_formats(formats)
 
         thumbnails = []
@@ -213,12 +271,12 @@ class ZDFIE(ZDFBaseIE):
                     })
 
         return {
-            'id': video_id,
+            'id': content_id,
             'title': title,
             'description': document.get('beschreibung'),
             'duration': int_or_none(document.get('length')),
-            'timestamp': unified_timestamp(try_get(
-                document, lambda x: x['meta']['editorialDate'], compat_str)),
+            'timestamp': unified_timestamp(document.get('date')) or unified_timestamp(
+                try_get(video, lambda x: x['meta']['editorialDate'], compat_str)),
             'thumbnails': thumbnails,
             'subtitles': self._extract_subtitles(document),
             'formats': formats,

youtube_dl/extractor/zhihu.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import float_or_none, int_or_none
+
+
+class ZhihuIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?zhihu\.com/zvideo/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://www.zhihu.com/zvideo/1342930761977176064',
+        'md5': 'c8d4c9cd72dd58e6f9bc9c2c84266464',
+        'info_dict': {
+            'id': '1342930761977176064',
+            'ext': 'mp4',
+            'title': '写春联也太难了吧！',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'uploader': '桥半舫',
+            'timestamp': 1612959715,
+            'upload_date': '20210210',
+            'uploader_id': '244ecb13b0fd7daf92235288c8ca3365',
+            'duration': 146.333,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        zvideo = self._download_json(
+            'https://www.zhihu.com/api/v4/zvideos/' + video_id, video_id)
+        title = zvideo['title']
+        video = zvideo.get('video') or {}
+
+        formats = []
+        for format_id, q in (video.get('playlist') or {}).items():
+            play_url = q.get('url') or q.get('play_url')
+            if not play_url:
+                continue
+            formats.append({
+                'asr': int_or_none(q.get('sample_rate')),
+                'filesize': int_or_none(q.get('size')),
+                'format_id': format_id,
+                'fps': int_or_none(q.get('fps')),
+                'height': int_or_none(q.get('height')),
+                'tbr': float_or_none(q.get('bitrate')),
+                'url': play_url,
+                'width': int_or_none(q.get('width')),
+            })
+        self._sort_formats(formats)
+
+        author = zvideo.get('author') or {}
+        url_token = author.get('url_token')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': video.get('thumbnail') or zvideo.get('image_url'),
+            'uploader': author.get('name'),
+            'timestamp': int_or_none(zvideo.get('published_at')),
+            'uploader_id': author.get('id'),
+            'uploader_url': 'https://www.zhihu.com/people/' + url_token if url_token else None,
+            'duration': float_or_none(video.get('duration')),
+            'view_count': int_or_none(zvideo.get('play_count')),
+            'like_count': int_or_none(zvideo.get('liked_count')),
+            'comment_count': int_or_none(zvideo.get('comment_count')),
+        }

youtube_dl/postprocessor/embedthumbnail.py

@@ -89,10 +89,14 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             os.rename(encodeFilename(temp_filename), encodeFilename(filename))
 
         elif info['ext'] in ['m4a', 'mp4']:
-            if not check_executable('AtomicParsley', ['-v']):
+            atomicparsley = next((x
+                                  for x in ['AtomicParsley', 'atomicparsley']
+                                  if check_executable(x, ['-v'])), None)
+
+            if atomicparsley is None:
                 raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
 
-            cmd = [encodeFilename('AtomicParsley', True),
+            cmd = [encodeFilename(atomicparsley, True),
                    encodeFilename(filename, True),
                    encodeArgument('--artwork'),
                    encodeFilename(thumbnail_filename, True),

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2021.02.10'
+__version__ = '2021.03.02'