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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class SexuIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
   8     _TEST = {
   9         'url': 'http://sexu.com/961791/',
  10         'md5': 'ff615aca9691053c94f8f10d96cd7884',
  11         'info_dict': {
  12             'id': '961791',
  13             'ext': 'mp4',
  14             'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b',
  15             'description': 'md5:2b75327061310a3afb3fbd7d09e2e403',
  16             'categories': list,  # NSFW
  17             'thumbnail': r're:https?://.*\.jpg$',
  18             'age_limit': 18,
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(url, video_id)
  25
  26         jwvideo = self._parse_json(
  27             self._search_regex(r'\.setup\(\s*({.+?})\s*\);', webpage, 'jwvideo'),
  28             video_id)
  29
  30         sources = jwvideo['sources']
  31
  32         formats = [{
  33             'url': source['file'].replace('\\', ''),
  34             'format_id': source.get('label'),
  35             'height': int(self._search_regex(
  36                 r'^(\d+)[pP]', source.get('label', ''), 'height',
  37                 default=None)),
  38         } for source in sources if source.get('file')]
  39         self._sort_formats(formats)
  40
  41         title = self._html_search_regex(
  42             r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title')
  43
  44         description = self._html_search_meta(
  45             'description', webpage, 'description')
  46
  47         thumbnail = jwvideo.get('image')
  48
  49         categories_str = self._html_search_meta(
  50             'keywords', webpage, 'categories')
  51         categories = (
  52             None if categories_str is None
  53             else categories_str.split(','))
  54
  55         return {
  56             'id': video_id,
  57             'title': title,
  58             'description': description,
  59             'thumbnail': thumbnail,
  60             'categories': categories,
  61             'formats': formats,
  62             'age_limit': 18,
  63         }