yt_dlp/extractor/foxgay.py

   1 from __future__ import unicode_literals
   2
   3 import itertools
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     get_element_by_id,
   8     int_or_none,
   9     remove_end,
  10 )
  11
  12
  13 class FoxgayIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
  15     _TEST = {
  16         'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
  17         'md5': '344558ccfea74d33b7adbce22e577f54',
  18         'info_dict': {
  19             'id': '2582',
  20             'ext': 'mp4',
  21             'title': 'Fuck Turkish-style',
  22             'description': 'md5:6ae2d9486921891efe89231ace13ffdf',
  23             'age_limit': 18,
  24             'thumbnail': r're:https?://.*\.jpg$',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31
  32         title = remove_end(self._html_extract_title(webpage), ' - Foxgay.com')
  33         description = get_element_by_id('inf_tit', webpage)
  34
  35         # The default user-agent with foxgay cookies leads to pages without videos
  36         self._downloader.cookiejar.clear('.foxgay.com')
  37         # Find the URL for the iFrame which contains the actual video.
  38         iframe_url = self._html_search_regex(
  39             r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', webpage,
  40             'video frame', group='url')
  41         iframe = self._download_webpage(
  42             iframe_url, video_id, headers={'User-Agent': 'curl/7.50.1'},
  43             note='Downloading video frame')
  44         video_data = self._parse_json(self._search_regex(
  45             r'video_data\s*=\s*([^;]+);', iframe, 'video data'), video_id)
  46
  47         formats = [{
  48             'url': source,
  49             'height': int_or_none(resolution),
  50         } for source, resolution in zip(
  51             video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]
  52
  53         self._sort_formats(formats)
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'formats': formats,
  59             'description': description,
  60             'thumbnail': video_data.get('act_vid', {}).get('thumb'),
  61             'age_limit': 18,
  62         }