]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/breakcom.py
debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.
[youtubedl] / youtube_dl / extractor / breakcom.py
index 1f6620d9158d25323e9aeb1c5f172eb74a26a806..2c0e5eea2e0285ffce1b89340e9ae8894260f866 100644 (file)
@@ -1,25 +1,64 @@
+from __future__ import unicode_literals
+
 import re
+import json
 
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_age_limit,
+)
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+    _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': '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]
-        webpage = self._download_webpage(url, video_id)
-        video_url = re.search(r"videoPath: '(.+?)',",webpage).group(1)
-        key = re.search(r"icon: '(.+?)',",webpage).group(1)
-        final_url = str(video_url)+"?"+str(key)
-        thumbnail_url = re.search(r"thumbnailURL: '(.+?)'",webpage).group(1)
-        title = re.search(r"sVidTitle: '(.+)',",webpage).group(1)
-        ext = video_url.split('.')[-1]
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       ext,
-            'title':     title,
-            'thumbnail': thumbnail_url,
-        }]
+        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))
+
+        youtube_id = info.get('youtubeId')
+        if youtube_id:
+            return self.url_result(youtube_id, 'Youtube')
+
+        formats = [{
+            'url': media['uri'] + '?' + info['AuthToken'],
+            'tbr': media['bitRate'],
+            'width': media['width'],
+            'height': media['height'],
+        } for media in info['media']]
+
+        if not formats:
+            formats.append({
+                'url': info['videoUri']
+            })
+
+        self._sort_formats(formats)
+
+        duration = int_or_none(info.get('videoLengthInSeconds'))
+        age_limit = parse_age_limit(info.get('audienceRating'))
+
+        return {
+            'id': video_id,
+            'title': info['contentName'],
+            'thumbnail': info['thumbUri'],
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
+        }