youtube_dl/extractor/photobucket.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import compat_urllib_parse
   8
   9
  10 class PhotobucketIE(InfoExtractor):
  11     _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
  12     _TEST = {
  13         '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',
  14         'file': 'zpsc0c3b9fa.mp4',
  15         'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
  16         'info_dict': {
  17             'timestamp': 1367669341,
  18             'upload_date': '20130504',
  19             'uploader': 'rachaneronas',
  20             'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27         video_extension = mobj.group('ext')
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         # Extract URL, uploader, and title from webpage
  32         self.report_extraction(video_id)
  33         info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
  34             webpage, 'info json')
  35         info = json.loads(info_json)
  36         url = compat_urllib_parse.unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url'))
  37         return {
  38             'id': video_id,
  39             'url': url,
  40             'uploader': info['username'],
  41             'timestamp': info['creationDate'],
  42             'title': info['title'],
  43             'ext': video_extension,
  44             'thumbnail': info['thumbUrl'],
  45         }