youtube_dl/extractor/pornotube.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6
   7     unified_strdate,
   8 )
   9
  10
  11 class PornotubeIE(InfoExtractor):
  12     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
  13     _TEST = {
  14         u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
  15         u'file': u'1689755.flv',
  16         u'md5': u'374dd6dcedd24234453b295209aa69b6',
  17         u'info_dict': {
  18             u"upload_date": u"20090708",
  19             u"title": u"Marilyn-Monroe-Bathing",
  20             u"age_limit": 18
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26
  27         video_id = mobj.group('videoid')
  28         video_title = mobj.group('title')
  29
  30         # Get webpage content
  31         webpage = self._download_webpage(url, video_id)
  32
  33         # Get the video URL
  34         VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
  35         video_url = self._search_regex(VIDEO_URL_RE, webpage, u'video url')
  36         video_url = compat_urllib_parse.unquote(video_url)
  37
  38         #Get the uploaded date
  39         VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
  40         upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, u'upload date', fatal=False)
  41         if upload_date: upload_date = unified_strdate(upload_date)
  42         age_limit = self._rta_search(webpage)
  43
  44         info = {'id': video_id,
  45                 'url': video_url,
  46                 'uploader': None,
  47                 'upload_date': upload_date,
  48                 'title': video_title,
  49                 'ext': 'flv',
  50                 'format': 'flv',
  51                 'age_limit': age_limit}
  52
  53         return [info]