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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6
   7     ExtractorError,
   8 )
   9
  10
  11 class XHamsterIE(InfoExtractor):
  12     """Information Extractor for xHamster"""
  13     _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
  14     _TEST = {
  15         u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  16         u'file': u'1509445.flv',
  17         u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
  18         u'info_dict': {
  19             u"upload_date": u"20121014",
  20             u"uploader_id": u"Ruseful2011",
  21             u"title": u"FemaleAgent Shy beauty takes the bait"
  22         }
  23     }
  24
  25     def _real_extract(self,url):
  26         mobj = re.match(self._VALID_URL, url)
  27
  28         video_id = mobj.group('id')
  29         mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
  30         webpage = self._download_webpage(mrss_url, video_id)
  31
  32         mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
  33         if mobj is None:
  34             raise ExtractorError(u'Unable to extract media URL')
  35         if len(mobj.group('server')) == 0:
  36             video_url = compat_urllib_parse.unquote(mobj.group('file'))
  37         else:
  38             video_url = mobj.group('server')+'/key='+mobj.group('file')
  39         video_extension = video_url.split('.')[-1]
  40
  41         video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
  42             webpage, u'title')
  43
  44         # Can't see the description anywhere in the UI
  45         # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
  46         #     webpage, u'description', fatal=False)
  47         # if video_description: video_description = unescapeHTML(video_description)
  48
  49         mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
  50         if mobj:
  51             video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
  52         else:
  53             video_upload_date = None
  54             self._downloader.report_warning(u'Unable to extract upload date')
  55
  56         video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
  57             webpage, u'uploader id', default=u'anonymous')
  58
  59         video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
  60             webpage, u'thumbnail', fatal=False)
  61
  62         return [{
  63             'id':       video_id,
  64             'url':      video_url,
  65             'ext':      video_extension,
  66             'title':    video_title,
  67             # 'description': video_description,
  68             'upload_date': video_upload_date,
  69             'uploader_id': video_uploader_id,
  70             'thumbnail': video_thumbnail
  71         }]