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 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         'skip': 'This video has been deleted.'
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group("id")
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         self.report_extraction(video_id)
  30
  31         # Extract video URL
  32         video_url = compat_urllib_parse.unquote(
  33             self._search_regex(r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
  34
  35         # Extract title
  36         video_title = self._html_search_regex(
  37             r'<title>(.*?)</title', webpage, 'title')
  38
  39         # Extract video thumbnail
  40         video_thumbnail = self._search_regex(
  41             r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False)
  42
  43         formats = [{
  44             'url': video_url,
  45             'ext': 'mp4',
  46             'format_id': 'mp4',
  47             'preference': 1,
  48         }]
  49
  50         return {
  51             'id': video_id,
  52             'formats': formats,
  53             'uploader': None,
  54             'upload_date': None,
  55             'title': video_title,
  56             'thumbnail': video_thumbnail,
  57             'description': None,
  58             'age_limit': 18,
  59         }