release 2020.06.06

[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 2020.05.08. 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 Issues with outdated version will be REJECTED.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 2020.06.06. 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 Issues with outdated version will be REJECTED.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 **2020.05.08**
+- [ ] I've verified that I'm running youtube-dl version **2020.06.06**
 - [ ] 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 2020.05.08
+ [debug] youtube-dl version 2020.06.06
  [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 2020.05.08. 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 2020.06.06. 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 **2020.05.08**
+- [ ] I've verified that I'm running youtube-dl version **2020.06.06**
 - [ ] 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 2020.05.08. 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 2020.06.06. 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 **2020.05.08**
+- [ ] I've verified that I'm running youtube-dl version **2020.06.06**
 - [ ] 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 2020.05.08. 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 2020.06.06. 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 **2020.05.08**
+- [ ] I've verified that I'm running youtube-dl version **2020.06.06**
 - [ ] 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 2020.05.08
+ [debug] youtube-dl version 2020.06.06
  [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 2020.05.08. 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 2020.06.06. 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 **2020.05.08**
+- [ ] I've verified that I'm running youtube-dl version **2020.06.06**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

CONTRIBUTING.md

@@ -153,7 +153,7 @@ After you have ensured this site is distributing its content legally, you can fo
 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
-8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):
 
         $ flake8 youtube_dl/extractor/yourextractor.py
 

ChangeLog

@@ -1,3 +1,41 @@
+version 2020.06.06
+
+Extractors
+* [tele5] Bypass geo restriction
++ [jwplatform] Add support for bypass geo restriction
+* [tele5] Prefer jwplatform over nexx (#25533)
+* [twitch:stream] Expect 400 and 410 HTTP errors from API
+* [twitch:stream] Fix extraction (#25528)
+* [twitch] Fix thumbnails extraction (#25531)
++ [twitch] Pass v5 Accept HTTP header (#25531)
+* [brightcove] Fix subtitles extraction (#25540)
++ [malltv] Add support for sk.mall.tv (#25445)
+* [periscope] Fix untitled broadcasts (#25482)
+* [jwplatform] Improve embeds extraction (#25467)
+
+
+version 2020.05.29
+
+Core
+* [postprocessor/ffmpeg] Embed series metadata with --add-metadata
+* [utils] Fix file permissions in write_json_file (#12471, #25122)
+
+Extractors
+* [ard:beta] Extend URL regular expression (#25405)
++ [youtube] Add support for more invidious instances (#25417)
+* [giantbomb] Extend URL regular expression (#25222)
+* [ard] Improve URL regular expression (#25134, #25198)
+* [redtube] Improve formats extraction and extract m3u8 formats (#25311,
+  #25321)
+* [indavideo] Switch to HTTPS for API request (#25191)
+* [redtube] Improve title extraction (#25208)
+* [vimeo] Improve format extraction and sorting (#25285)
+* [soundcloud] Reduce API playlist page limit (#25274)
++ [youtube] Add support for yewtu.be (#25226)
+* [mailru] Fix extraction (#24530, #25239)
+* [bellator] Fix mgid extraction (#25195)
+
+
 version 2020.05.08
 
 Core

README.md

@@ -1032,7 +1032,7 @@ After you have ensured this site is distributing its content legally, you can fo
 5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/ytdl-org/youtube-dl/blob/7f41a598b3fba1bcab2817de64a08941200aa3c8/youtube_dl/extractor/common.py#L94-L303). Add tests and code for as many as you want.
-8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](http://flake8.pycqa.org/en/latest/index.html#quickstart):
+8. Make sure your code follows [youtube-dl coding conventions](#youtube-dl-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):
 
         $ flake8 youtube_dl/extractor/yourextractor.py
 

youtube_dl/extractor/ard.py

@@ -249,7 +249,7 @@ class ARDMediathekIE(ARDMediathekBaseIE):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
     _TESTS = [{
         # available till 14.02.2019
         'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html',
@@ -263,6 +263,9 @@ class ARDIE(InfoExtractor):
             'upload_date': '20180214',
             'thumbnail': r're:^https?://.*\.jpg$',
         },
+    }, {
+        'url': 'https://www.daserste.de/information/reportage-dokumentation/erlebnis-erde/videosextern/woelfe-und-herdenschutzhunde-ungleiche-brueder-102.html',
+        'only_matching': True,
     }, {
         'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
         'only_matching': True,
@@ -310,9 +313,9 @@ class ARDIE(InfoExtractor):
 
 
 class ARDBetaMediathekIE(ARDMediathekBaseIE):
-    _VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/(?P<client>[^/]+)/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
+    _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P<client>[^/]+)/(?:player|live|video)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)'
     _TESTS = [{
-        'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
+        'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
         'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f',
         'info_dict': {
             'display_id': 'die-robuste-roswita',
@@ -325,6 +328,15 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
             'upload_date': '20191222',
             'ext': 'mp4',
         },
+    }, {
+        'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
+        'only_matching': True,
+    }, {
+        'url': 'https://ardmediathek.de/ard/video/saartalk/saartalk-gesellschaftsgift-haltung-gegen-hass/sr-fernsehen/Y3JpZDovL3NyLW9ubGluZS5kZS9TVF84MTY4MA/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ardmediathek.de/ard/video/trailer/private-eyes-s01-e01/one/Y3JpZDovL3dkci5kZS9CZWl0cmFnLTE1MTgwYzczLWNiMTEtNGNkMS1iMjUyLTg5MGYzOWQxZmQ1YQ/',
+        'only_matching': True,
     }, {
         'url': 'https://www.ardmediathek.de/ard/player/Y3JpZDovL3N3ci5kZS9hZXgvbzEwNzE5MTU/',
         'only_matching': True,
@@ -336,7 +348,11 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
-        display_id = mobj.group('display_id') or video_id
+        display_id = mobj.group('display_id')
+        if display_id:
+            display_id = display_id.rstrip('/')
+        if not display_id:
+            display_id = video_id
 
         player_page = self._download_json(
             'https://api.ardmediathek.de/public-gateway',

youtube_dl/extractor/bbc.py

@@ -528,7 +528,7 @@ class BBCCoUkIE(InfoExtractor):
 
             def get_programme_id(item):
                 def get_from_attributes(item):
-                    for p in('identifier', 'group'):
+                    for p in ('identifier', 'group'):
                         value = item.get(p)
                         if value and re.match(r'^[pb][\da-z]{7}$', value):
                             return value

youtube_dl/extractor/brightcove.py

@@ -5,32 +5,34 @@ import base64
 import re
 import struct
 
-from .common import InfoExtractor
 from .adobepass import AdobePassIE
+from .common import InfoExtractor
 from ..compat import (
     compat_etree_fromstring,
+    compat_HTTPError,
     compat_parse_qs,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_xml_parse_error,
-    compat_HTTPError,
 )
 from ..utils import (
-    ExtractorError,
+    clean_html,
     extract_attributes,
+    ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
     float_or_none,
-    js_to_json,
     int_or_none,
+    js_to_json,
+    mimetype2ext,
     parse_iso8601,
     smuggle_url,
+    str_or_none,
     unescapeHTML,
     unsmuggle_url,
-    update_url_query,
-    clean_html,
-    mimetype2ext,
     UnsupportedError,
+    update_url_query,
+    url_or_none,
 )
 
 
@@ -553,10 +555,16 @@ class BrightcoveNewIE(AdobePassIE):
 
         subtitles = {}
         for text_track in json_data.get('text_tracks', []):
-            if text_track.get('src'):
-                subtitles.setdefault(text_track.get('srclang'), []).append({
-                    'url': text_track['src'],
-                })
+            if text_track.get('kind') != 'captions':
+                continue
+            text_track_url = url_or_none(text_track.get('src'))
+            if not text_track_url:
+                continue
+            lang = (str_or_none(text_track.get('srclang'))
+                    or str_or_none(text_track.get('label')) or 'en').lower()
+            subtitles.setdefault(lang, []).append({
+                'url': text_track_url,
+            })
 
         is_live = False
         duration = float_or_none(json_data.get('duration'), 1000)

youtube_dl/extractor/giantbomb.py

@@ -13,10 +13,10 @@ from ..utils import (
 
 
 class GiantBombIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/videos/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/(?:videos|shows)/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
+    _TESTS = [{
         'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/',
-        'md5': 'c8ea694254a59246a42831155dec57ac',
+        'md5': '132f5a803e7e0ab0e274d84bda1e77ae',
         'info_dict': {
             'id': '2300-9782',
             'display_id': 'quick-look-destiny-the-dark-below',
@@ -26,7 +26,10 @@ class GiantBombIE(InfoExtractor):
             'duration': 2399,
             'thumbnail': r're:^https?://.*\.jpg$',
         }
-    }
+    }, {
+        'url': 'https://www.giantbomb.com/shows/ben-stranding/2970-20212',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/indavideo.py

@@ -58,7 +58,7 @@ class IndavideoEmbedIE(InfoExtractor):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'http://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
+            'https://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
             video_id)['data']
 
         title = video['title']

youtube_dl/extractor/jwplatform.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import unsmuggle_url
 
 
 class JWPlatformIE(InfoExtractor):
@@ -32,10 +33,14 @@ class JWPlatformIE(InfoExtractor):
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//content\.jwplatform\.com/players/[a-zA-Z0-9]{8})',
+            r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})',
             webpage)
 
     def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        self._initialize_geo_bypass({
+            'countries': smuggled_data.get('geo_countries'),
+        })
         video_id = self._match_id(url)
         json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id)
         return self._parse_jwplayer_data(json_data, video_id)

youtube_dl/extractor/mailru.py

@@ -128,6 +128,12 @@ class MailRuIE(InfoExtractor):
                 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id,
                 video_id, 'Downloading video JSON')
 
+        headers = {}
+
+        video_key = self._get_cookies('https://my.mail.ru').get('video_key')
+        if video_key:
+            headers['Cookie'] = 'video_key=%s' % video_key.value
+
         formats = []
         for f in video_data['videos']:
             video_url = f.get('url')
@@ -140,6 +146,7 @@ class MailRuIE(InfoExtractor):
                 'url': video_url,
                 'format_id': format_id,
                 'height': height,
+                'http_headers': headers,
             })
         self._sort_formats(formats)
 

youtube_dl/extractor/malltv.py

@@ -8,7 +8,7 @@ from ..utils import merge_dicts
 
 
 class MallTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|sk)\.)?mall\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
         'md5': '1c4a37f080e1f3023103a7b43458e518',
@@ -26,6 +26,9 @@ class MallTVIE(InfoExtractor):
     }, {
         'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
         'only_matching': True,
+    }, {
+        'url': 'https://sk.mall.tv/gejmhaus/reklamacia-nehreje-vyrobnik-tepla-alebo-spekacka',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/periscope.py

@@ -18,7 +18,7 @@ class PeriscopeBaseIE(InfoExtractor):
             item_id, query=query)
 
     def _parse_broadcast_data(self, broadcast, video_id):
-        title = broadcast['status']
+        title = broadcast.get('status') or 'Periscope Broadcast'
         uploader = broadcast.get('user_display_name') or broadcast.get('username')
         title = '%s - %s' % (uploader, title) if uploader else title
         is_live = broadcast.get('state').lower() == 'running'

youtube_dl/extractor/redtube.py

@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     ExtractorError,
     int_or_none,
     merge_dicts,
@@ -57,7 +58,7 @@ class RedTubeIE(InfoExtractor):
 
         if not info.get('title'):
             info['title'] = self._html_search_regex(
-                (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
+                (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle|video_title)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
                  r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
                 webpage, 'title', group='title',
                 default=None) or self._og_search_title(webpage)
@@ -77,7 +78,7 @@ class RedTubeIE(InfoExtractor):
                     })
         medias = self._parse_json(
             self._search_regex(
-                r'mediaDefinition\s*:\s*(\[.+?\])', webpage,
+                r'mediaDefinition["\']?\s*:\s*(\[.+?}\s*\])', webpage,
                 'media definitions', default='{}'),
             video_id, fatal=False)
         if medias and isinstance(medias, list):
@@ -85,6 +86,12 @@ class RedTubeIE(InfoExtractor):
                 format_url = url_or_none(media.get('videoUrl'))
                 if not format_url:
                     continue
+                if media.get('format') == 'hls' or determine_ext(format_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls',
+                        fatal=False))
+                    continue
                 format_id = media.get('quality')
                 formats.append({
                     'url': format_url,

youtube_dl/extractor/soundcloud.py

@@ -559,7 +559,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
 class SoundcloudPagedPlaylistBaseIE(SoundcloudIE):
     def _extract_playlist(self, base_url, playlist_id, playlist_title):
         COMMON_QUERY = {
-            'limit': 2000000000,
+            'limit': 80000,
             'linked_partitioning': '1',
         }
 

youtube_dl/extractor/spike.py

@@ -8,15 +8,10 @@ class BellatorIE(MTVServicesInfoExtractor):
     _TESTS = [{
         'url': 'http://www.bellator.com/fight/atwr7k/bellator-158-michael-page-vs-evangelista-cyborg',
         'info_dict': {
-            'id': 'b55e434e-fde1-4a98-b7cc-92003a034de4',
-            'ext': 'mp4',
-            'title': 'Douglas Lima vs. Paul Daley - Round 1',
-            'description': 'md5:805a8dd29310fd611d32baba2f767885',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
+            'title': 'Michael Page vs. Evangelista Cyborg',
+            'description': 'md5:0d917fc00ffd72dd92814963fc6cbb05',
         },
+        'playlist_count': 3,
     }, {
         'url': 'http://www.bellator.com/video-clips/bw6k7n/bellator-158-foundations-michael-venom-page',
         'only_matching': True,
@@ -25,6 +20,9 @@ class BellatorIE(MTVServicesInfoExtractor):
     _FEED_URL = 'http://www.bellator.com/feeds/mrss/'
     _GEO_COUNTRIES = ['US']
 
+    def _extract_mgid(self, webpage):
+        return self._extract_triforce_mgid(webpage)
+
 
 class ParamountNetworkIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)'

youtube_dl/extractor/tele5.py

@@ -6,18 +6,16 @@ import re
 from .common import InfoExtractor
 from .jwplatform import JWPlatformIE
 from .nexx import NexxIE
-from ..compat import (
-    compat_str,
-    compat_urlparse,
-)
+from ..compat import compat_urlparse
 from ..utils import (
     NO_DEFAULT,
-    try_get,
+    smuggle_url,
 )
 
 
 class Tele5IE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _GEO_COUNTRIES = ['DE']
     _TESTS = [{
         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
         'info_dict': {
@@ -30,6 +28,21 @@ class Tele5IE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        # jwplatform, nexx unavailable
+        'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/',
+        'info_dict': {
+            'id': 'WJuiOlUp',
+            'ext': 'mp4',
+            'upload_date': '20200603',
+            'timestamp': 1591214400,
+            'title': 'Ghoul - Das Geheimnis des Friedhofmonsters',
+            'description': 'md5:42002af1d887ff3d5b2b3ca1f8137d97',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': [JWPlatformIE.ie_key()],
     }, {
         'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
         'only_matching': True,
@@ -88,15 +101,8 @@ class Tele5IE(InfoExtractor):
             if not jwplatform_id:
                 jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
 
-            media = self._download_json(
-                'https://cdn.jwplayer.com/v2/media/' + jwplatform_id,
-                display_id)
-            nexx_id = try_get(
-                media, lambda x: x['playlist'][0]['nexx_id'], compat_str)
-
-            if nexx_id:
-                return nexx_result(nexx_id)
-
         return self.url_result(
-            'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
-            video_id=jwplatform_id)
+            smuggle_url(
+                'jwplatform:%s' % jwplatform_id,
+                {'geo_countries': self._GEO_COUNTRIES}),
+            ie=JWPlatformIE.ie_key(), video_id=jwplatform_id)

youtube_dl/extractor/twitch.py

@@ -21,6 +21,8 @@ from ..utils import (
     orderedSet,
     parse_duration,
     parse_iso8601,
+    qualities,
+    str_or_none,
     try_get,
     unified_timestamp,
     update_url_query,
@@ -50,8 +52,14 @@ class TwitchBaseIE(InfoExtractor):
 
     def _call_api(self, path, item_id, *args, **kwargs):
         headers = kwargs.get('headers', {}).copy()
-        headers['Client-ID'] = self._CLIENT_ID
-        kwargs['headers'] = headers
+        headers.update({
+            'Accept': 'application/vnd.twitchtv.v5+json; charset=UTF-8',
+            'Client-ID': self._CLIENT_ID,
+        })
+        kwargs.update({
+            'headers': headers,
+            'expected_status': (400, 410),
+        })
         response = self._download_json(
             '%s/%s' % (self._API_BASE, path), item_id,
             *args, **compat_kwargs(kwargs))
@@ -186,12 +194,27 @@ class TwitchItemBaseIE(TwitchBaseIE):
             is_live = False
         else:
             is_live = None
+        _QUALITIES = ('small', 'medium', 'large')
+        quality_key = qualities(_QUALITIES)
+        thumbnails = []
+        preview = info.get('preview')
+        if isinstance(preview, dict):
+            for thumbnail_id, thumbnail_url in preview.items():
+                thumbnail_url = url_or_none(thumbnail_url)
+                if not thumbnail_url:
+                    continue
+                if thumbnail_id not in _QUALITIES:
+                    continue
+                thumbnails.append({
+                    'url': thumbnail_url,
+                    'preference': quality_key(thumbnail_id),
+                })
         return {
             'id': info['_id'],
             'title': info.get('title') or 'Untitled Broadcast',
             'description': info.get('description'),
             'duration': int_or_none(info.get('length')),
-            'thumbnail': info.get('preview'),
+            'thumbnails': thumbnails,
             'uploader': info.get('channel', {}).get('display_name'),
             'uploader_id': info.get('channel', {}).get('name'),
             'timestamp': parse_iso8601(info.get('recorded_at')),
@@ -572,10 +595,18 @@ class TwitchStreamIE(TwitchBaseIE):
                 else super(TwitchStreamIE, cls).suitable(url))
 
     def _real_extract(self, url):
-        channel_id = self._match_id(url)
+        channel_name = self._match_id(url)
+
+        access_token = self._call_api(
+            'api/channels/%s/access_token' % channel_name, channel_name,
+            'Downloading access token JSON')
+
+        token = access_token['token']
+        channel_id = compat_str(self._parse_json(
+            token, channel_name)['channel_id'])
 
         stream = self._call_api(
-            'kraken/streams/%s?stream_type=all' % channel_id.lower(),
+            'kraken/streams/%s?stream_type=all' % channel_id,
             channel_id, 'Downloading stream JSON').get('stream')
 
         if not stream:
@@ -585,11 +616,9 @@ class TwitchStreamIE(TwitchBaseIE):
         # (e.g. http://www.twitch.tv/TWITCHPLAYSPOKEMON) that will lead to constructing
         # an invalid m3u8 URL. Working around by use of original channel name from stream
         # JSON and fallback to lowercase if it's not available.
-        channel_id = stream.get('channel', {}).get('name') or channel_id.lower()
-
-        access_token = self._call_api(
-            'api/channels/%s/access_token' % channel_id, channel_id,
-            'Downloading channel access token')
+        channel_name = try_get(
+            stream, lambda x: x['channel']['name'],
+            compat_str) or channel_name.lower()
 
         query = {
             'allow_source': 'true',
@@ -600,11 +629,11 @@ class TwitchStreamIE(TwitchBaseIE):
             'playlist_include_framerate': 'true',
             'segment_preference': '4',
             'sig': access_token['sig'].encode('utf-8'),
-            'token': access_token['token'].encode('utf-8'),
+            'token': token.encode('utf-8'),
         }
         formats = self._extract_m3u8_formats(
             '%s/api/channel/hls/%s.m3u8?%s'
-            % (self._USHER_BASE, channel_id, compat_urllib_parse_urlencode(query)),
+            % (self._USHER_BASE, channel_name, compat_urllib_parse_urlencode(query)),
             channel_id, 'mp4')
         self._prefer_source(formats)
 
@@ -627,8 +656,8 @@ class TwitchStreamIE(TwitchBaseIE):
             })
 
         return {
-            'id': compat_str(stream['_id']),
-            'display_id': channel_id,
+            'id': str_or_none(stream.get('_id')) or channel_id,
+            'display_id': channel_name,
             'title': title,
             'description': description,
             'thumbnails': thumbnails,

youtube_dl/extractor/twitter.py

@@ -578,6 +578,18 @@ class TwitterBroadcastIE(TwitterBaseIE, PeriscopeBaseIE):
     IE_NAME = 'twitter:broadcast'
     _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/broadcasts/(?P<id>[0-9a-zA-Z]{13})'
 
+    _TEST = {
+        # untitled Periscope video
+        'url': 'https://twitter.com/i/broadcasts/1yNGaQLWpejGj',
+        'info_dict': {
+            'id': '1yNGaQLWpejGj',
+            'ext': 'mp4',
+            'title': 'Andrea May Sahouri - Periscope Broadcast',
+            'uploader': 'Andrea May Sahouri',
+            'uploader_id': '1PXEdBZWpGwKe',
+        },
+    }
+
     def _real_extract(self, url):
         broadcast_id = self._match_id(url)
         broadcast = self._call_api(

youtube_dl/extractor/vimeo.py

@@ -140,28 +140,28 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             })
 
         # TODO: fix handling of 308 status code returned for live archive manifest requests
+        sep_pattern = r'/sep/video/'
         for files_type in ('hls', 'dash'):
             for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
                 manifest_url = cdn_data.get('url')
                 if not manifest_url:
                     continue
                 format_id = '%s-%s' % (files_type, cdn_name)
-                if files_type == 'hls':
-                    formats.extend(self._extract_m3u8_formats(
-                        manifest_url, video_id, 'mp4',
-                        'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id,
-                        note='Downloading %s m3u8 information' % cdn_name,
-                        fatal=False))
-                elif files_type == 'dash':
-                    mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
-                    mpd_manifest_urls = []
-                    if re.search(mpd_pattern, manifest_url):
-                        for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
-                            mpd_manifest_urls.append((format_id + suffix, re.sub(
-                                mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
-                    else:
-                        mpd_manifest_urls = [(format_id, manifest_url)]
-                    for f_id, m_url in mpd_manifest_urls:
+                sep_manifest_urls = []
+                if re.search(sep_pattern, manifest_url):
+                    for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
+                        sep_manifest_urls.append((format_id + suffix, re.sub(
+                            sep_pattern, '/%s/' % repl, manifest_url)))
+                else:
+                    sep_manifest_urls = [(format_id, manifest_url)]
+                for f_id, m_url in sep_manifest_urls:
+                    if files_type == 'hls':
+                        formats.extend(self._extract_m3u8_formats(
+                            m_url, video_id, 'mp4',
+                            'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
+                            note='Downloading %s m3u8 information' % cdn_name,
+                            fatal=False))
+                    elif files_type == 'dash':
                         if 'json=1' in m_url:
                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
                             if real_m_url:
@@ -170,11 +170,6 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
                             'Downloading %s MPD information' % cdn_name,
                             fatal=False)
-                        for f in mpd_formats:
-                            if f.get('vcodec') == 'none':
-                                f['preference'] = -50
-                            elif f.get('acodec') == 'none':
-                                f['preference'] = -40
                         formats.extend(mpd_formats)
 
         live_archive = live_event.get('archive') or {}
@@ -186,6 +181,12 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                 'preference': 1,
             })
 
+        for f in formats:
+            if f.get('vcodec') == 'none':
+                f['preference'] = -50
+            elif f.get('acodec') == 'none':
+                f['preference'] = -40
+
         subtitles = {}
         text_tracks = config['request'].get('text_tracks')
         if text_tracks:

youtube_dl/extractor/youtube.py

@@ -388,8 +388,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?invidious\.drycat\.fr/|
                             (?:www\.)?tube\.poal\.co/|
                             (?:www\.)?vid\.wxzm\.sx/|
+                            (?: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/|
@@ -397,6 +404,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
                             (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
                             (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
+                            (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:

youtube_dl/postprocessor/ffmpeg.py

@@ -447,6 +447,13 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
                         metadata[meta_f] = info[info_f]
                     break
 
+        # See [1-4] for some info on media metadata/metadata supported
+        # by ffmpeg.
+        # 1. https://kdenlive.org/en/project/adding-meta-data-to-mp4-video/
+        # 2. https://wiki.multimedia.cx/index.php/FFmpeg_Metadata
+        # 3. https://kodi.wiki/view/Video_file_tagging
+        # 4. http://atomicparsley.sourceforge.net/mpeg-4files.html
+
         add('title', ('track', 'title'))
         add('date', 'upload_date')
         add(('description', 'comment'), 'description')
@@ -457,6 +464,10 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
         add('album')
         add('album_artist')
         add('disc', 'disc_number')
+        add('show', 'series')
+        add('season_number')
+        add('episode_id', ('episode', 'episode_id'))
+        add('episode_sort', 'episode_number')
 
         if not metadata:
             self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')

youtube_dl/utils.py

@@ -1837,6 +1837,12 @@ def write_json_file(obj, fn):
                 os.unlink(fn)
             except OSError:
                 pass
+        try:
+            mask = os.umask(0)
+            os.umask(mask)
+            os.chmod(tf.name, 0o666 & ~mask)
+        except OSError:
+            pass
         os.rename(tf.name, fn)
     except Exception:
         try:

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2020.05.08'
+__version__ = '2020.06.06'