0ecd695f85e6a40929501fb6adc40bace8784d42
[ytdl] / youtube_dl / extractor / tnaflix.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7     parse_duration,
8     fix_xml_ampersands,
9 )
10
11
12 class TNAFlixIE(InfoExtractor):
13     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)'
14
15     _TITLE_REGEX = None
16     _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
17     _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
18
19     _TEST = {
20         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
21         'md5': 'ecf3498417d09216374fc5907f9c6ec0',
22         'info_dict': {
23             'id': '553878',
24             'display_id': 'Carmella-Decesare-striptease',
25             'ext': 'mp4',
26             'title': 'Carmella Decesare - striptease',
27             'description': '',
28             'thumbnail': 're:https?://.*\.jpg$',
29             'duration': 91,
30             'age_limit': 18,
31         }
32     }
33
34     def _real_extract(self, url):
35         mobj = re.match(self._VALID_URL, url)
36         video_id = mobj.group('id')
37         display_id = mobj.group('display_id')
38
39         webpage = self._download_webpage(url, display_id)
40
41         title = self._html_search_regex(
42             self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
43         description = self._html_search_regex(
44             self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
45
46         age_limit = self._rta_search(webpage)
47
48         duration = self._html_search_meta('duration', webpage, 'duration', default=None)
49         if duration:
50             duration = parse_duration(duration[1:])
51
52         cfg_url = self._html_search_regex(
53             self._CONFIG_REGEX, webpage, 'flashvars.config')
54
55         cfg_xml = self._download_xml(
56             cfg_url, display_id, note='Downloading metadata',
57             transform_source=fix_xml_ampersands)
58
59         thumbnail = cfg_xml.find('./startThumb').text
60
61         formats = []
62         for item in cfg_xml.findall('./quality/item'):
63             video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
64             format_id = item.find('res').text
65             fmt = {
66                 'url': video_url,
67                 'format_id': format_id,
68             }
69             m = re.search(r'^(\d+)', format_id)
70             if m:
71                 fmt['height'] = int(m.group(1))
72             formats.append(fmt)
73         self._sort_formats(formats)
74
75         return {
76             'id': video_id,
77             'display_id': display_id,
78             'title': title,
79             'description': description,
80             'thumbnail': thumbnail,
81             'duration': duration,
82             'age_limit': age_limit,
83             'formats': formats,
84         }