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

   1 from __future__ import unicode_literals
   2
   3 import datetime
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   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             'upload_date': '20130504',
  18             'uploader': 'rachaneronas',
  19             'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26         video_extension = mobj.group('ext')
  27
  28         webpage = self._download_webpage(url, video_id)
  29
  30         # Extract URL, uploader, and title from webpage
  31         self.report_extraction(video_id)
  32         info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
  33             webpage, 'info json')
  34         info = json.loads(info_json)
  35         return {
  36             'id': video_id,
  37             'url': info['downloadUrl'],
  38             'uploader': info['username'],
  39             'upload_date': datetime.date.fromtimestamp(info['creationDate']).strftime('%Y%m%d'),
  40             'title': info['title'],
  41             'ext': video_extension,
  42             'thumbnail': info['thumbUrl'],
  43         }