_ Git - youtube-dl/blob - 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>[^/]+)/(?P<display_id>[^/]+)/video(?P<id>\d+)'
  14
  15     _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
  16     _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
  17     _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
  22             'md5': 'ecf3498417d09216374fc5907f9c6ec0',
  23             'info_dict': {
  24                 'id': '553878',
  25                 'display_id': 'Carmella-Decesare-striptease',
  26                 'ext': 'mp4',
  27                 'title': 'Carmella Decesare - striptease',
  28                 'description': '',
  29                 'thumbnail': 're:https?://.*\.jpg$',
  30                 'duration': 91,
  31                 'age_limit': 18,
  32             }
  33         },
  34         {
  35             'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
  36             'matching_only': True,
  37         }
  38     ]
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('id')
  43         display_id = mobj.group('display_id')
  44
  45         webpage = self._download_webpage(url, display_id)
  46
  47         title = self._html_search_regex(
  48             self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
  49         description = self._html_search_regex(
  50             self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='')
  51
  52         age_limit = self._rta_search(webpage)
  53
  54         duration = self._html_search_meta('duration', webpage, 'duration', default=None)
  55         if duration:
  56             duration = parse_duration(duration[1:])
  57
  58         cfg_url = self._proto_relative_url(self._html_search_regex(
  59             self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
  60
  61         cfg_xml = self._download_xml(
  62             cfg_url, display_id, note='Downloading metadata',
  63             transform_source=fix_xml_ampersands)
  64
  65         thumbnail = cfg_xml.find('./startThumb').text
  66
  67         formats = []
  68         for item in cfg_xml.findall('./quality/item'):
  69             video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text)
  70             format_id = item.find('res').text
  71             fmt = {
  72                 'url': video_url,
  73                 'format_id': format_id,
  74             }
  75             m = re.search(r'^(\d+)', format_id)
  76             if m:
  77                 fmt['height'] = int(m.group(1))
  78             formats.append(fmt)
  79         self._sort_formats(formats)
  80
  81         return {
  82             'id': video_id,
  83             'display_id': display_id,
  84             'title': title,
  85             'description': description,
  86             'thumbnail': thumbnail,
  87             'duration': duration,
  88             'age_limit': age_limit,
  89             'formats': formats,
  90         }