Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/spankbang.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     parse_duration,
   9     parse_resolution,
  10     str_to_int,
  11 )
  12
  13
  14 class SpankBangIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
  16     _TESTS = [{
  17         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
  18         'md5': '1cc433e1d6aa14bc376535b8679302f7',
  19         'info_dict': {
  20             'id': '3vvn',
  21             'ext': 'mp4',
  22             'title': 'fantasy solo',
  23             'description': 'dillion harper masturbates on a bed',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'uploader': 'silly2587',
  26             'age_limit': 18,
  27         }
  28     }, {
  29         # 480p only
  30         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  31         'only_matching': True,
  32     }, {
  33         # no uploader
  34         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  35         'only_matching': True,
  36     }, {
  37         # mobile page
  38         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
  39         'only_matching': True,
  40     }, {
  41         # 4k
  42         'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
  43         'only_matching': True,
  44     }]
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48         webpage = self._download_webpage(url, video_id, headers={
  49             'Cookie': 'country=US'
  50         })
  51
  52         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
  53             raise ExtractorError(
  54                 'Video %s is not available' % video_id, expected=True)
  55
  56         formats = []
  57         for mobj in re.finditer(
  58                 r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
  59                 webpage):
  60             format_id, format_url = mobj.group('id', 'url')
  61             f = parse_resolution(format_id)
  62             f.update({
  63                 'url': format_url,
  64                 'format_id': format_id,
  65             })
  66             formats.append(f)
  67         self._sort_formats(formats)
  68
  69         title = self._html_search_regex(
  70             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
  71         description = self._search_regex(
  72             r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
  73             webpage, 'description', fatal=False)
  74         thumbnail = self._og_search_thumbnail(webpage)
  75         uploader = self._search_regex(
  76             r'class="user"[^>]*><img[^>]+>([^<]+)',
  77             webpage, 'uploader', default=None)
  78         duration = parse_duration(self._search_regex(
  79             r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
  80             webpage, 'duration', fatal=False))
  81         view_count = str_to_int(self._search_regex(
  82             r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
  83
  84         age_limit = self._rta_search(webpage)
  85
  86         return {
  87             'id': video_id,
  88             'title': title,
  89             'description': description,
  90             'thumbnail': thumbnail,
  91             'uploader': uploader,
  92             'duration': duration,
  93             'view_count': view_count,
  94             'formats': formats,
  95             'age_limit': age_limit,
  96         }