_ Git - youtube-dl/blob - youtube_dl/extractor/dumpert.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_urllib_request
   9 from ..utils import qualities
  10
  11
  12 class DumpertIE(InfoExtractor):
  13     _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
  14     _TESTS = [{
  15         'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
  16         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
  17         'info_dict': {
  18             'id': '6646981/951bc60f',
  19             'ext': 'mp4',
  20             'title': 'Ik heb nieuws voor je',
  21             'description': 'Niet schrikken hoor',
  22             'thumbnail': 're:^https?://.*\.jpg$',
  23         }
  24     }, {
  25         'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
  26         'only_matching': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         protocol = mobj.group('protocol')
  33
  34         url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
  35         req = compat_urllib_request.Request(url)
  36         req.add_header('Cookie', 'nsfw=1; cpc=10')
  37         webpage = self._download_webpage(req, video_id)
  38
  39         files_base64 = self._search_regex(
  40             r'data-files="([^"]+)"', webpage, 'data files')
  41
  42         files = self._parse_json(
  43             base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
  44             video_id)
  45
  46         quality = qualities(['flv', 'mobile', 'tablet', '720p'])
  47
  48         formats = [{
  49             'url': video_url,
  50             'format_id': format_id,
  51             'quality': quality(format_id),
  52         } for format_id, video_url in files.items() if format_id != 'still']
  53         self._sort_formats(formats)
  54
  55         title = self._html_search_meta(
  56             'title', webpage) or self._og_search_title(webpage)
  57         description = self._html_search_meta(
  58             'description', webpage) or self._og_search_description(webpage)
  59         thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'description': description,
  65             'thumbnail': thumbnail,
  66             'formats': formats
  67         }