yt_dlp/extractor/photobucket.py

   1 import json
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5
   6
   7 class PhotobucketIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
   9     _TEST = {
  10         'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
  11         'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
  12         'info_dict': {
  13             'id': 'zpsc0c3b9fa',
  14             'ext': 'mp4',
  15             'timestamp': 1367669341,
  16             'upload_date': '20130504',
  17             'uploader': 'rachaneronas',
  18             'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = self._match_valid_url(url)
  24         video_id = mobj.group('id')
  25         video_extension = mobj.group('ext')
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         # Extract URL, uploader, and title from webpage
  30         self.report_extraction(video_id)
  31         info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
  32                                        webpage, 'info json')
  33         info = json.loads(info_json)
  34         url = urllib.parse.unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url'))
  35         return {
  36             'id': video_id,
  37             'url': url,
  38             'uploader': info['username'],
  39             'timestamp': info['creationDate'],
  40             'title': info['title'],
  41             'ext': video_extension,
  42             'thumbnail': info['thumbUrl'],
  43         }