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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_urllib_parse,
   7 )
   8
   9
  10 class MalemotionIE(InfoExtractor):
  11     _VALID_URL = r'https?://malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
  12     _TEST = {
  13         'url': 'http://malemotion.com/video/bete-de-concours.ltc',
  14         'md5': '3013e53a0afbde2878bc39998c33e8a5',
  15         'info_dict': {
  16             'id': 'ltc',
  17             'ext': 'mp4',
  18             'title': 'Bête de Concours',
  19             'age_limit': 18,
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  27         video_url = compat_urllib_parse.unquote(self._search_regex(
  28             r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
  29         video_title = self._html_search_regex(
  30             r'<title>(.*?)</title', webpage, 'title')
  31         video_thumbnail = self._search_regex(
  32             r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False)
  33
  34         formats = [{
  35             'url': video_url,
  36             'ext': 'mp4',
  37             'format_id': 'mp4',
  38             'preference': 1,
  39         }]
  40         self._sort_formats(formats)
  41
  42         return {
  43             'id': video_id,
  44             'formats': formats,
  45             'title': video_title,
  46             'thumbnail': video_thumbnail,
  47             'age_limit': 18,
  48         }