Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tinypic.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class TinyPicIE(InfoExtractor):
  10     IE_NAME = 'tinypic'
  11     IE_DESC = 'tinypic.com videos'
  12     _VALID_URL = r'http://(?:.+?\.)?tinypic\.com/player\.php\?v=(?P<id>[^&]+)&s=\d+'
  13
  14     _TESTS = [
  15         {
  16             'url': 'http://tinypic.com/player.php?v=6xw7tc%3E&s=5#.UtqZmbRFCM8',
  17             'md5': '609b74432465364e72727ebc6203f044',
  18             'info_dict': {
  19                 'id': '6xw7tc',
  20                 'ext': 'flv',
  21                 'title': 'shadow phenomenon weird',
  22             },
  23         },
  24         {
  25             'url': 'http://de.tinypic.com/player.php?v=dy90yh&s=8',
  26             'only_matching': True,
  27         }
  28     ]
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33
  34         webpage = self._download_webpage(url, video_id, 'Downloading page')
  35
  36         mobj = re.search(r'(?m)fo\.addVariable\("file",\s"(?P<fileid>[\da-z]+)"\);\n'
  37                          '\s+fo\.addVariable\("s",\s"(?P<serverid>\d+)"\);', webpage)
  38         if mobj is None:
  39             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  40
  41         file_id = mobj.group('fileid')
  42         server_id = mobj.group('serverid')
  43
  44         KEYWORDS_SUFFIX = ', Video, images, photos, videos, myspace, ebay, video hosting, photo hosting'
  45         keywords = self._html_search_meta('keywords', webpage, 'title')
  46         title = keywords[:-len(KEYWORDS_SUFFIX)] if keywords.endswith(KEYWORDS_SUFFIX) else ''
  47
  48         video_url = 'http://v%s.tinypic.com/%s.flv' % (server_id, file_id)
  49         thumbnail = 'http://v%s.tinypic.com/%s_th.jpg' % (server_id, file_id)
  50
  51         return {
  52             'id': file_id,
  53             'url': video_url,
  54             'thumbnail': thumbnail,
  55             'title': title
  56         }