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