yt_dlp/extractor/foxgay.py

   1 import itertools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     get_element_by_id,
   6     int_or_none,
   7     remove_end,
   8 )
   9
  10
  11 class FoxgayIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
  13     _TEST = {
  14         'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
  15         'md5': '344558ccfea74d33b7adbce22e577f54',
  16         'info_dict': {
  17             'id': '2582',
  18             'ext': 'mp4',
  19             'title': 'Fuck Turkish-style',
  20             'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
  21             'age_limit': 18,
  22             'thumbnail': r're:https?://.*\.jpg$',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         title = remove_end(self._html_extract_title(webpage), ' - Foxgay.com')
  31         description = get_element_by_id('inf_tit', webpage)
  32
  33         # The default user-agent with foxgay cookies leads to pages without videos
  34         self.cookiejar.clear('.foxgay.com')
  35         # Find the URL for the iFrame which contains the actual video.
  36         iframe_url = self._html_search_regex(
  37             r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', webpage,
  38             'video frame', group='url')
  39         iframe = self._download_webpage(
  40             iframe_url, video_id, headers={'User-Agent': 'curl/7.50.1'},
  41             note='Downloading video frame')
  42         video_data = self._parse_json(self._search_regex(
  43             r'video_data\s*=\s*([^;]+);', iframe, 'video data'), video_id)
  44
  45         formats = [{
  46             'url': source,
  47             'height': int_or_none(resolution),
  48         } for source, resolution in zip(
  49             video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]
  50
  51         return {
  52             'id': video_id,
  53             'title': title,
  54             'formats': formats,
  55             'description': description,
  56             'thumbnail': video_data.get('act_vid', {}).get('thumb'),
  57             'age_limit': 18,
  58         }