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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import compat_urllib_request
   5
   6 class FourTubeIE(InfoExtractor):
   7     IE_NAME = '4tube'
   8     _VALID_URL = r'(?:https?://)?www\.4tube\.com/videos/(?P<id>\d+)/.*'
   9
  10     _TEST = {
  11             'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
  12             'md5': '6516c8ac63b03de06bc8eac14362db4f',
  13             'info_dict': {
  14                 'id': '209733',
  15                 'ext': 'mp4',
  16                 'title': 'Hot Babe Holly Michaels gets her ass stuffed by black'
  17                 }
  18             }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22
  23         video_id = mobj.group('id')
  24         webpage_url = 'http://www.4tube.com/videos/' + video_id
  25         webpage = self._download_webpage(webpage_url, video_id)
  26
  27         self.report_extraction(video_id)
  28
  29         playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, u'Playlist')
  30         media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, u"Media Id")
  31         thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, u'Thumbnail')
  32         sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, u'Sources').split(',')
  33         title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, u'Title')
  34
  35         token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
  36         headers = {
  37                 b'Content-Type': b'application/x-www-form-urlencoded',
  38                 b'Origin': b'http://www.4tube.com',
  39                 }
  40         token_req = compat_urllib_request.Request(token_url, b'{}', headers)
  41         tokens = self._download_json(token_req, video_id)
  42
  43         formats = [{
  44             'url': tokens[format]['token'],
  45             'format_id': format + 'p',
  46             'resolution': format + 'p',
  47             'quality': int(format),
  48             } for format in sources]
  49
  50         return [{
  51             'id': video_id,
  52             'title': title,
  53             'formats': formats,
  54             'thumbnail': thumbnail_url,
  55             'age_limit': 18,
  56             'webpage_url': webpage_url,
  57             }]