Raphaël G. Git Repositories - youtubedl/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 from .facebook import FacebookIE
   9
  10
  11 class BuzzFeedIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
  13     _TESTS = [{
  14         'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia',
  15         'info_dict': {
  16             'id': 'this-angry-ram-destroys-a-punching-bag-like-a-boss',
  17             'title': 'This Angry Ram Destroys A Punching Bag Like A Boss',
  18             'description': 'Rambro!',
  19         },
  20         'playlist': [{
  21             'info_dict': {
  22                 'id': 'aVCR29aE_OQ',
  23                 'ext': 'mp4',
  24                 'title': 'Angry Ram destroys a punching bag..',
  25                 'description': 'md5:c59533190ef23fd4458a5e8c8c872345',
  26                 'upload_date': '20141024',
  27                 'uploader_id': 'Buddhanz1',
  28                 'uploader': 'Angry Ram',
  29             }
  30         }]
  31     }, {
  32         'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia',
  33         'params': {
  34             'skip_download': True,  # Got enough YouTube download tests
  35         },
  36         'info_dict': {
  37             'id': 'look-at-this-cute-dog-omg',
  38             'description': 're:Munchkin the Teddy Bear is back ?!',
  39             'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
  40         },
  41         'playlist': [{
  42             'info_dict': {
  43                 'id': 'mVmBL8B-In0',
  44                 'ext': 'mp4',
  45                 'title': 're:Munchkin the Teddy Bear gets her exercise',
  46                 'description': 'md5:28faab95cda6e361bcff06ec12fc21d8',
  47                 'upload_date': '20141124',
  48                 'uploader_id': 'CindysMunchkin',
  49                 'uploader': 're:^Munchkin the',
  50             },
  51         }]
  52     }, {
  53         'url': 'http://www.buzzfeed.com/craigsilverman/the-most-adorable-crash-landing-ever#.eq7pX0BAmK',
  54         'info_dict': {
  55             'id': 'the-most-adorable-crash-landing-ever',
  56             'title': 'Watch This Baby Goose Make The Most Adorable Crash Landing',
  57             'description': 'This gosling knows how to stick a landing.',
  58         },
  59         'playlist': [{
  60             'md5': '763ca415512f91ca62e4621086900a23',
  61             'info_dict': {
  62                 'id': '971793786185728',
  63                 'ext': 'mp4',
  64                 'title': 'We set up crash pads so that the goslings on our roof would have a safe landi...',
  65                 'uploader': 'Calgary Outdoor Centre-University of Calgary',
  66             },
  67         }],
  68         'add_ie': ['Facebook'],
  69     }]
  70
  71     def _real_extract(self, url):
  72         playlist_id = self._match_id(url)
  73         webpage = self._download_webpage(url, playlist_id)
  74
  75         all_buckets = re.findall(
  76             r'(?s)<div class="video-embed[^"]*"..*?rel:bf_bucket_data=\'([^\']+)\'',
  77             webpage)
  78
  79         entries = []
  80         for bd_json in all_buckets:
  81             bd = json.loads(bd_json)
  82             video = bd.get('video') or bd.get('progload_video')
  83             if not video:
  84                 continue
  85             entries.append(self.url_result(video['url']))
  86
  87         facebook_urls = FacebookIE._extract_urls(webpage)
  88         entries.extend([
  89             self.url_result(facebook_url)
  90             for facebook_url in facebook_urls])
  91
  92         return {
  93             '_type': 'playlist',
  94             'id': playlist_id,
  95             'title': self._og_search_title(webpage),
  96             'description': self._og_search_description(webpage),
  97             'entries': entries,
  98         }