2 from __future__ import unicode_literals
7 from .common import InfoExtractor
10 class BuzzFeedIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
13 'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia',
15 'id': 'this-angry-ram-destroys-a-punching-bag-like-a-boss',
16 'title': 'This Angry Ram Destroys A Punching Bag Like A Boss',
17 'description': 'Rambro!',
23 'upload_date': '20141024',
24 'uploader_id': 'Buddhanz1',
25 'description': 'He likes to stay in shape with his heavy bag, he wont stop until its on the ground\n\nFollow Angry Ram on Facebook for regular updates -\nhttps://www.facebook.com/pages/Angry-Ram/1436897249899558?ref=hl',
26 'uploader': 'Buddhanz',
27 'title': 'Angry Ram destroys a punching bag',
31 'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia',
33 'skip_download': True, # Got enough YouTube download tests
36 'description': 'Munchkin the Teddy Bear is back !',
37 'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
43 'upload_date': '20141124',
44 'uploader_id': 'CindysMunchkin',
45 'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
46 'uploader': 'Munchkin the Shih Tzu',
47 'title': 'Munchkin the Teddy Bear gets her exercise',
52 def _real_extract(self, url):
53 playlist_id = self._match_id(url)
54 webpage = self._download_webpage(url, playlist_id)
56 all_buckets = re.findall(
57 r'(?s)<div class="video-embed[^"]*"..*?rel:bf_bucket_data=\'([^\']+)\'',
61 for bd_json in all_buckets:
62 bd = json.loads(bd_json)
63 video = bd.get('video') or bd.get('progload_video')
66 entries.append(self.url_result(video['url']))
71 'title': self._og_search_title(webpage),
72 'description': self._og_search_description(webpage),