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