youtube-dl

commit f78c01f68b1e16e385ec319c7f5d351b173c7ec5
parent 8489578df42620a4e60fa233458520986b510105
Author: Sergey M․ <dstftw@gmail.com>
Date:   Fri,  3 Oct 2014 18:57:18 +0700

[breakcom] Cover more URLs with _VALID_URL (Closes #3876)

Diffstat:
M
youtube_dl/extractor/breakcom.py
 | 
24
+++++++++++++-----------

1 file changed, 13 insertions(+), 11 deletions(-)
diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py
@@ -7,25 +7,27 @@ from .common import InfoExtractor
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
-    _TEST = {
+    _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
+    _TESTS = [{
         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
-        'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
+        'md5': '33aa4ff477ecd124d18d7b5d23b87ce5',
         'info_dict': {
             'id': '2468056',
             'ext': 'mp4',
             'title': 'When Girls Act Like D-Bags',
         }
-    }
+    }, {
+        'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1).split("-")[-1]
-        embed_url = 'http://www.break.com/embed/%s' % video_id
-        webpage = self._download_webpage(embed_url, video_id)
-        info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
-            webpage, 'info json', flags=re.DOTALL)
-        info = json.loads(info_json)
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            'http://www.break.com/embed/%s' % video_id, video_id)
+        info = json.loads(self._search_regex(
+            r'var embedVars = ({.*})\s*?</script>',
+            webpage, 'info json', flags=re.DOTALL))
         video_url = info['videoUri']
         youtube_id = info.get('youtubeId')
         if youtube_id: