]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/foxgay.py
[teachable] Extract chapter metadata (closes #24421)
[youtube-dl] / youtube_dl / 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_search_regex(
33             r'<title>([^<]+)</title>', webpage, 'title'), ' - Foxgay.com')
34         description = get_element_by_id('inf_tit', webpage)
35
36         # The default user-agent with foxgay cookies leads to pages without videos
37         self._downloader.cookiejar.clear('.foxgay.com')
38         # Find the URL for the iFrame which contains the actual video.
39         iframe_url = self._html_search_regex(
40             r'<iframe[^>]+src=([\'"])(?P<url>[^\'"]+)\1', webpage,
41             'video frame', group='url')
42         iframe = self._download_webpage(
43             iframe_url, video_id, headers={'User-Agent': 'curl/7.50.1'},
44             note='Downloading video frame')
45         video_data = self._parse_json(self._search_regex(
46             r'video_data\s*=\s*([^;]+);', iframe, 'video data'), video_id)
47
48         formats = [{
49             'url': source,
50             'height': int_or_none(resolution),
51         } for source, resolution in zip(
52             video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]
53
54         self._sort_formats(formats)
55
56         return {
57             'id': video_id,
58             'title': title,
59             'formats': formats,
60             'description': description,
61             'thumbnail': video_data.get('act_vid', {}).get('thumb'),
62             'age_limit': 18,
63         }