Update upstream source from tag 'upstream/2020.05.08'

[youtubedl] / youtube_dl / extractor / dailymail.py

diff --git a/youtube_dl/extractor/dailymail.py b/youtube_dl/extractor/dailymail.py
index 538565c660c159f382fb2799fb5236d6a508f442..67b88fd56234ee9448bd4d6cc33c4d4534eb672d 100644 (file)
--- a/youtube_dl/extractor/dailymail.py
+++ b/youtube_dl/extractor/dailymail.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
@@ -12,8 +14,8 @@ from ..utils import (
 
 
 class DailyMailIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)'
+    _TESTS = [{
         'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html',
         'md5': 'f6129624562251f628296c3a9ffde124',
         'info_dict': {
@@ -22,7 +24,16 @@ class DailyMailIE(InfoExtractor):
             'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
             'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
         }
-    }
+    }, {
+        'url': 'http://www.dailymail.co.uk/embed/video/1295863.html',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)',
+            webpage)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -34,10 +45,13 @@ class DailyMailIE(InfoExtractor):
         sources_url = (try_get(
             video_data,
             (lambda x: x['plugins']['sources']['url'],
-             lambda x: x['sources']['url']), compat_str) or
-            'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
+             lambda x: x['sources']['url']), compat_str)
+            or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
 
         video_sources = self._download_json(sources_url, video_id)
+        body = video_sources.get('body')
+        if body:
+            video_sources = body
 
         formats = []
         for rendition in video_sources['renditions']: