Update upstream source from tag 'upstream/2020.06.16.1'

[youtubedl] / youtube_dl / extractor / onionstudios.py

diff --git a/youtube_dl/extractor/onionstudios.py b/youtube_dl/extractor/onionstudios.py
index d7b13a0f1fbc53deba74e47f6d1eefc0bdee8be2..cf5c39e66b95052bd9d297232fb4fe51a966dcc2 100644 (file)
--- a/youtube_dl/extractor/onionstudios.py
+++ b/youtube_dl/extractor/onionstudios.py
@@ -4,36 +4,38 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-    int_or_none,
-)
+from ..compat import compat_str
+from ..utils import js_to_json
 
 
 class OnionStudiosIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:videos/[^/]+-|embed\?.*\bid=)(?P<id>\d+)(?!-)'
+    _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:video(?:s/[^/]+-|/)|embed\?.*\bid=)(?P<id>\d+)(?!-)'
 
     _TESTS = [{
         'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
-        'md5': 'd4851405d31adfadf71cd7a487b765bb',
+        'md5': '5a118d466d62b5cd03647cf2c593977f',
         'info_dict': {
-            'id': '2937',
+            'id': '3459881',
             'ext': 'mp4',
             'title': 'Hannibal charges forward, stops for a cocktail',
-            'description': 'md5:e786add7f280b7f0fe237b64cc73df76',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'uploader': 'The A.V. Club',
-            'uploader_id': 'TheAVClub',
+            'description': 'md5:545299bda6abf87e5ec666548c6a9448',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'a.v. club',
+            'upload_date': '20150619',
+            'timestamp': 1434728546,
         },
     }, {
         'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
         'only_matching': True,
+    }, {
+        'url': 'http://www.onionstudios.com/video/6139.json',
+        'only_matching': True,
     }]
 
     @staticmethod
     def _extract_url(webpage):
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/embed.+?)\1', webpage)
+            r'(?s)<(?:iframe|bulbs-video)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/(?:embed.+?|video/\d+\.json))\1', webpage)
         if mobj:
             return mobj.group('url')
 
@@ -41,49 +43,11 @@ class OnionStudiosIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
-
-        formats = []
-        for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
-            ext = determine_ext(src)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
-            else:
-                height = int_or_none(self._search_regex(
-                    r'/(\d+)\.%s' % ext, src, 'height', default=None))
-                formats.append({
-                    'format_id': ext + ('-%sp' % height if height else ''),
-                    'url': src,
-                    'height': height,
-                    'ext': ext,
-                    'preference': 1,
-                })
-        self._sort_formats(formats)
-
-        title = self._search_regex(
-            r'share_title\s*=\s*(["\'])(?P<title>[^\1]+?)\1',
-            webpage, 'title', group='title')
-        description = self._search_regex(
-            r'share_description\s*=\s*(["\'])(?P<description>[^\'"]+?)\1',
-            webpage, 'description', default=None, group='description')
-        thumbnail = self._search_regex(
-            r'poster\s*=\s*(["\'])(?P<thumbnail>[^\1]+?)\1',
-            webpage, 'thumbnail', default=False, group='thumbnail')
-
-        uploader_id = self._search_regex(
-            r'twitter_handle\s*=\s*(["\'])(?P<uploader_id>[^\1]+?)\1',
-            webpage, 'uploader id', fatal=False, group='uploader_id')
-        uploader = self._search_regex(
-            r'window\.channelName\s*=\s*(["\'])Embedded:(?P<uploader>[^\1]+?)\1',
-            webpage, 'uploader', default=False, group='uploader')
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'formats': formats,
-        }
+            'http://onionstudios.com/embed/dc94dc2899fe644c0e7241fa04c1b732.js',
+            video_id)
+        mcp_id = compat_str(self._parse_json(self._search_regex(
+            r'window\.mcpMapping\s*=\s*({.+?});', webpage,
+            'MCP Mapping'), video_id, js_to_json)[video_id]['mcp_id'])
+        return self.url_result(
+            'http://kinja.com/ajax/inset/iframe?id=mcp-' + mcp_id,
+            'KinjaEmbed', mcp_id)