_ Git - youtube-dl/blob - youtube_dl/extractor/buzzfeed.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8
   9
  10 class BuzzFeedIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
  12     _TEST = {
  13         'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia',
  14         'info_dict': {
  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!',
  18         },
  19         'playlist': [{
  20             'info_dict': {
  21                 'id': 'aVCR29aE_OQ',
  22                 'ext': 'mp4',
  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',
  28             }
  29         }]
  30     }
  31
  32     def _real_extract(self, url):
  33         playlist_id = self._match_id(url)
  34         webpage = self._download_webpage(url, playlist_id)
  35
  36         all_buckets = re.findall(
  37             r'<div class="video-embed-videopost[^"]*".*?rel:bf_bucket_data=\'([^\']+)\'',
  38             webpage)
  39         entries = []
  40         for bd_json in all_buckets:
  41             bd = json.loads(bd_json)
  42             if 'video' not in bd:
  43                 continue
  44             entries.append(self.url_result(bd['video']['url']))
  45
  46         return {
  47             '_type': 'playlist',
  48             'id': playlist_id,
  49             'title': self._og_search_title(webpage),
  50             'description': self._og_search_description(webpage),
  51             'entries': entries,
  52         }