Merge pull request #1 from ytdl-org/master

Sync

ChangeLog

@@ -1,3 +1,55 @@
+version <unreleased>
+
+Core
+* [utils] Improve str_to_int
++ [downloader/hls] Add ability to override AES decryption key URL (#17521)
+
+Extractors
++ [tv2dk:bornholm:play] Add support for play.tv2bornholm.dk (#23291)
++ [slideslive] Add support for url and vimeo service names (#23414)
+* [slideslive] Fix extraction (#23413)
+* [twitch:clips] Fix extraction (#23375)
++ [soundcloud] Add support for token protected embeds (#18954)
+* [vk] Improve extraction
+    * Fix User Videos extraction (#23356)
+    * Extract all videos for lists with more than 1000 videos (#23356)
+    + Add support for video albums (#14327, #14492)
+- [kontrtube] Remove extractor
+- [videopremium] Remove extractor
+- [musicplayon] Remove extractor (#9225)
++ [ufctv] Add support for ufcfightpass.imgdge.com and
+  ufcfightpass.imggaming.com (#23343)
++ [twitch] Extract m3u8 formats frame rate (#23333)
++ [imggaming] Add support for playlists and extract subtitles
++ [ufcarabia] Add support for UFC Arabia (#23312)
+* [ufctv] Fix extraction
+* [yahoo] Fix gyao brightcove player id (#23303)
+* [vzaar] Override AES decryption key URL (#17521)
++ [vzaar] Add support for AES HLS manifests (#17521, #23299)
+* [nrl] Fix extraction
+* [teachingchannel] Fix extraction
+* [nintendo] Fix extraction and partially add support for Nintendo Direct
+  videos (#4592)
++ [ooyala] Add better fallback values for domain and streams variables
++ [youtube] Add support youtubekids.com (#23272)
+* [tv2] Detect DRM protection
++ [tv2] Add support for katsomo.fi and mtv.fi (#10543)
+* [tv2] Fix tv2.no article extraction
+* [msn] Improve extraction
+    + Add support for YouTube and NBCSports embeds
+    + Add support for articles with multiple videos
+    * Improve AOL embed support
+    * Improve format extraction
+* [abcotvs] Relax URL regular expression and improve metadata extraction
+  (#18014)
+* [channel9] Reduce response size
+* [adobetv] Improve extaction
+    * Use OnDemandPagedList for list extractors
+    * Reduce show extraction requests
+    * Extract original video format and subtitles
+    + Add support for adobe tv embeds
+
+
 version 2019.11.28
 
 Core
@@ -583,7 +635,7 @@ Extractors
 version 2019.04.17
 
 Extractors
-* [openload] Randomize User-Agent (closes #20688)
+* [openload] Randomize User-Agent (#20688)
 + [openload] Add support for oladblock domains (#20471)
 * [adn] Fix subtitle extraction (#12724)
 + [aol] Add support for localized websites
@@ -1148,7 +1200,7 @@ Extractors
 + [youtube] Extract channel meta fields (#9676, #12939)
 * [porntube] Fix extraction (#17541)
 * [asiancrush] Fix extraction (#15630)
-+ [twitch:clips] Extend URL regular expression (closes #17559)
++ [twitch:clips] Extend URL regular expression (#17559)
 + [vzaar] Add support for HLS
 * [tube8] Fix metadata extraction (#17520)
 * [eporner] Extract JSON-LD (#17519)

test/test_utils.py

@@ -500,6 +500,11 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(str_to_int('123,456'), 123456)
         self.assertEqual(str_to_int('123.456'), 123456)
         self.assertEqual(str_to_int(523), 523)
+        # Python 3 has no long
+        if sys.version_info < (3, 0):
+            eval('self.assertEqual(str_to_int(123456L), 123456)')
+        self.assertEqual(str_to_int('noninteger'), None)
+        self.assertEqual(str_to_int([]), None)
 
     def test_url_basename(self):
         self.assertEqual(url_basename('http://foo.de/'), '')

youtube_dl/extractor/extractors.py

@@ -1168,7 +1168,10 @@ from .tv2 import (
     TV2ArticleIE,
     KatsomoIE,
 )
-from .tv2dk import TV2DKIE
+from .tv2dk import (
+    TV2DKIE,
+    TV2DKBornholmPlayIE,
+)
 from .tv2hu import TV2HuIE
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE

youtube_dl/extractor/slideslive.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import smuggle_url
 
 
 class SlidesLiveIE(InfoExtractor):
@@ -14,9 +14,9 @@ class SlidesLiveIE(InfoExtractor):
         'info_dict': {
             'id': 'LMtgR8ba0b0',
             'ext': 'mp4',
-            'title': '38902413: external video',
+            'title': 'GCC IA16 backend',
-            'description': '3890241320170925-9-1yd6ech.mp4',
+            'description': 'Watch full version of this video at https://slideslive.com/38902413.',
-            'uploader': 'SlidesLive Administrator',
+            'uploader': 'SlidesLive Videos - A',
             'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
             'upload_date': '20170925',
         }
@@ -24,16 +24,38 @@ class SlidesLiveIE(InfoExtractor):
         # video_service_name = youtube
         'url': 'https://slideslive.com/38903721/magic-a-scientific-resurrection-of-an-esoteric-legend',
         'only_matching': True,
+    }, {
+        # video_service_name = url
+        'url': 'https://slideslive.com/38922070/learning-transferable-skills-1',
+        'only_matching': True,
+    }, {
+        # video_service_name = vimeo
+        'url': 'https://slideslive.com/38921896/retrospectives-a-venue-for-selfreflection-in-ml-research-3',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         video_data = self._download_json(
-            url, video_id, headers={'Accept': 'application/json'})
+            'https://ben.slideslive.com/player/' + video_id, video_id)
         service_name = video_data['video_service_name'].lower()
-        if service_name == 'youtube':
+        assert service_name in ('url', 'vimeo', 'youtube')
-            yt_video_id = video_data['video_service_id']
+        service_id = video_data['video_service_id']
-            return self.url_result(yt_video_id, 'Youtube', video_id=yt_video_id)
+        info = {
+            'id': video_id,
+            'thumbnail': video_data.get('thumbnail'),
+            'url': service_id,
+        }
+        if service_name == 'url':
+            info['title'] = video_data['title']
         else:
-            raise ExtractorError(
+            info.update({
-                'Unsupported service name: {0}'.format(service_name), expected=True)
+                '_type': 'url_transparent',
+                'ie_key': service_name.capitalize(),
+                'title': video_data.get('title'),
+            })
+            if service_name == 'vimeo':
+                info['url'] = smuggle_url(
+                    'https://player.vimeo.com/video/' + service_id,
+                    {'http_headers': {'Referer': url}})
+        return info

youtube_dl/extractor/tv2dk.py

@@ -1,10 +1,16 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
-from ..utils import extract_attributes
+from ..utils import (
+    determine_ext,
+    extract_attributes,
+    js_to_json,
+    url_or_none,
+)
 
 
 class TV2DKIE(InfoExtractor):
@@ -80,3 +86,69 @@ class TV2DKIE(InfoExtractor):
                 'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
                 video_id=kaltura_id))
         return self.playlist_result(entries)
+
+
+class TV2DKBornholmPlayIE(InfoExtractor):
+    _VALID_URL = r'https?://play\.tv2bornholm\.dk/\?.*?\bid=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://play.tv2bornholm.dk/?area=specifikTV&id=781021',
+        'info_dict': {
+            'id': '781021',
+            'ext': 'mp4',
+            'title': '12Nyheder-27.11.19',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
+            data=json.dumps({
+                'playlist_id': video_id,
+                'serienavn': '',
+            }).encode(), headers={
+                'X-Requested-With': 'XMLHttpRequest',
+                'Content-Type': 'application/json; charset=UTF-8',
+            })['d']
+
+        # TODO: generalize flowplayer
+        title = self._search_regex(
+            r'title\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', video, 'title',
+            group='value')
+        sources = self._parse_json(self._search_regex(
+            r'(?s)sources:\s*(\[.+?\]),', video, 'sources'),
+            video_id, js_to_json)
+
+        formats = []
+        srcs = set()
+        for source in sources:
+            src = url_or_none(source.get('src'))
+            if not src:
+                continue
+            if src in srcs:
+                continue
+            srcs.add(src)
+            ext = determine_ext(src)
+            src_type = source.get('type')
+            if src_type == 'application/x-mpegurl' or ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, ext='mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif src_type == 'application/dash+xml' or ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    src, video_id, mpd_id='dash', fatal=False))
+            else:
+                formats.append({
+                    'url': src,
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }

youtube_dl/extractor/twitch.py

@@ -17,12 +17,10 @@ from ..compat import (
 from ..utils import (
     clean_html,
     ExtractorError,
-    float_or_none,
     int_or_none,
     orderedSet,
     parse_duration,
     parse_iso8601,
-    qualities,
     try_get,
     unified_timestamp,
     update_url_query,
@@ -676,63 +674,81 @@ class TwitchClipsIE(TwitchBaseIE):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        status = self._download_json(
+        clip = self._download_json(
-            'https://clips.twitch.tv/api/v2/clips/%s/status' % video_id,
+            'https://gql.twitch.tv/gql', video_id, data=json.dumps({
-            video_id)
+                'query': '''{
+  clip(slug: "%s") {
+    broadcaster {
+      displayName
+    }
+    createdAt
+    curator {
+      displayName
+      id
+    }
+    durationSeconds
+    id
+    tiny: thumbnailURL(width: 86, height: 45)
+    small: thumbnailURL(width: 260, height: 147)
+    medium: thumbnailURL(width: 480, height: 272)
+    title
+    videoQualities {
+      frameRate
+      quality
+      sourceURL
+    }
+    viewCount
+  }
+}''' % video_id,
+            }).encode(), headers={
+                'Client-ID': self._CLIENT_ID,
+            })['data']['clip']
+
+        if not clip:
+            raise ExtractorError(
+                'This clip is no longer available', expected=True)
 
         formats = []
-
+        for option in clip.get('videoQualities', []):
-        for option in status['quality_options']:
             if not isinstance(option, dict):
                 continue
-            source = url_or_none(option.get('source'))
+            source = url_or_none(option.get('sourceURL'))
             if not source:
                 continue
             formats.append({
                 'url': source,
                 'format_id': option.get('quality'),
                 'height': int_or_none(option.get('quality')),
-                'fps': int_or_none(option.get('frame_rate')),
+                'fps': int_or_none(option.get('frameRate')),
             })
-
         self._sort_formats(formats)
 
-        info = {
+        thumbnails = []
+        for thumbnail_id in ('tiny', 'small', 'medium'):
+            thumbnail_url = clip.get(thumbnail_id)
+            if not thumbnail_url:
+                continue
+            thumb = {
+                'id': thumbnail_id,
+                'url': thumbnail_url,
+            }
+            mobj = re.search(r'-(\d+)x(\d+)\.', thumbnail_url)
+            if mobj:
+                thumb.update({
+                    'height': int(mobj.group(2)),
+                    'width': int(mobj.group(1)),
+                })
+            thumbnails.append(thumb)
+
+        return {
+            'id': clip.get('id') or video_id,
+            'title': clip.get('title') or video_id,
             'formats': formats,
+            'duration': int_or_none(clip.get('durationSeconds')),
+            'views': int_or_none(clip.get('viewCount')),
+            'timestamp': unified_timestamp(clip.get('createdAt')),
+            'thumbnails': thumbnails,
+            'creator': try_get(clip, lambda x: x['broadcaster']['displayName'], compat_str),
+            'uploader': try_get(clip, lambda x: x['curator']['displayName'], compat_str),
+            'uploader_id': try_get(clip, lambda x: x['curator']['id'], compat_str),
         }
-
-        clip = self._call_api(
-            'kraken/clips/%s' % video_id, video_id, fatal=False, headers={
-                'Accept': 'application/vnd.twitchtv.v5+json',
-            })
-
-        if clip:
-            quality_key = qualities(('tiny', 'small', 'medium'))
-            thumbnails = []
-            thumbnails_dict = clip.get('thumbnails')
-            if isinstance(thumbnails_dict, dict):
-                for thumbnail_id, thumbnail_url in thumbnails_dict.items():
-                    thumbnails.append({
-                        'id': thumbnail_id,
-                        'url': thumbnail_url,
-                        'preference': quality_key(thumbnail_id),
-                    })
-
-            info.update({
-                'id': clip.get('tracking_id') or video_id,
-                'title': clip.get('title') or video_id,
-                'duration': float_or_none(clip.get('duration')),
-                'views': int_or_none(clip.get('views')),
-                'timestamp': unified_timestamp(clip.get('created_at')),
-                'thumbnails': thumbnails,
-                'creator': try_get(clip, lambda x: x['broadcaster']['display_name'], compat_str),
-                'uploader': try_get(clip, lambda x: x['curator']['display_name'], compat_str),
-                'uploader_id': try_get(clip, lambda x: x['curator']['id'], compat_str),
-            })
-        else:
-            info.update({
-                'title': video_id,
-                'id': video_id,
-            })
-
-        return info

youtube_dl/utils.py

@@ -46,6 +46,7 @@ from .compat import (
     compat_html_entities,
     compat_html_entities_html5,
     compat_http_client,
+    compat_integer_types,
     compat_kwargs,
     compat_os_name,
     compat_parse_qs,
@@ -3519,10 +3520,11 @@ def str_or_none(v, default=None):
 
 def str_to_int(int_str):
     """ A more relaxed version of int_or_none """
-    if not isinstance(int_str, compat_str):
+    if isinstance(int_str, compat_integer_types):
         return int_str
-    int_str = re.sub(r'[,\.\+]', '', int_str)
+    elif isinstance(int_str, compat_str):
-    return int(int_str)
+        int_str = re.sub(r'[,\.\+]', '', int_str)
+        return int_or_none(int_str)
 
 
 def float_or_none(v, scale=1, invscale=1, default=None):