Raphaël G. Git Repositories - youtubedl/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 ..utils import (
   9     qualities,
  10     sanitized_Request,
  11 )
  12
  13
  14 class DumpertIE(InfoExtractor):
  15     _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
  16     _TESTS = [{
  17         'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
  18         'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
  19         'info_dict': {
  20             'id': '6646981/951bc60f',
  21             'ext': 'mp4',
  22             'title': 'Ik heb nieuws voor je',
  23             'description': 'Niet schrikken hoor',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25         }
  26     }, {
  27         'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34         protocol = mobj.group('protocol')
  35
  36         url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
  37         req = sanitized_Request(url)
  38         req.add_header('Cookie', 'nsfw=1; cpc=10')
  39         webpage = self._download_webpage(req, video_id)
  40
  41         files_base64 = self._search_regex(
  42             r'data-files="([^"]+)"', webpage, 'data files')
  43
  44         files = self._parse_json(
  45             base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
  46             video_id)
  47
  48         quality = qualities(['flv', 'mobile', 'tablet', '720p'])
  49
  50         formats = [{
  51             'url': video_url,
  52             'format_id': format_id,
  53             'quality': quality(format_id),
  54         } for format_id, video_url in files.items() if format_id != 'still']
  55         self._sort_formats(formats)
  56
  57         title = self._html_search_meta(
  58             'title', webpage) or self._og_search_title(webpage)
  59         description = self._html_search_meta(
  60             'description', webpage) or self._og_search_description(webpage)
  61         thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
  62
  63         return {
  64             'id': video_id,
  65             'title': title,
  66             'description': description,
  67             'thumbnail': thumbnail,
  68             'formats': formats
  69         }