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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urllib_parse,
   8 )
   9
  10
  11 class MalemotionIE(InfoExtractor):
  12     _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
  13     _TEST = {
  14         'url': 'http://malemotion.com/video/bien-dur.10ew',
  15         'file': '10ew.mp4',
  16         'md5': 'b3cc49f953b107e4a363cdff07d100ce',
  17         'info_dict': {
  18             "title": "Bien dur",
  19             "age_limit": 18,
  20         },
  21         'skip': 'This video has been deleted.'
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group("id")
  27
  28         webpage = self._download_webpage(url, video_id)
  29
  30         self.report_extraction(video_id)
  31
  32         # Extract video URL
  33         video_url = compat_urllib_parse.unquote(
  34             self._search_regex(r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
  35
  36         # Extract title
  37         video_title = self._html_search_regex(
  38             r'<title>(.*?)</title', webpage, 'title')
  39
  40         # Extract video thumbnail
  41         video_thumbnail = self._search_regex(
  42             r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False)
  43
  44         formats = [{
  45             'url': video_url,
  46             'ext': 'mp4',
  47             'format_id': 'mp4',
  48             'preference': 1,
  49         }]
  50
  51         return {
  52             'id': video_id,
  53             'formats': formats,
  54             'uploader': None,
  55             'upload_date': None,
  56             'title': video_title,
  57             'thumbnail': video_thumbnail,
  58             'description': None,
  59             'age_limit': 18,
  60         }