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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8
   9
  10 class StreamCZIE(InfoExtractor):
  11     _VALID_URL = r'https?://www\.stream\.cz/((?P<category>.+)/)?(?P<videogroup>.+)/(?P<videoid>.+)'
  12
  13     _TESTS = [{
  14         'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
  15         'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
  16         'info_dict': {
  17             'id': '765767',
  18             'ext': 'mp4',
  19             'title': 'Peklo na talíři: Éčka pro děti',
  20             'description': 'md5:49ace0df986e95e331d0fe239d421519',
  21             'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
  22         },
  23     },
  24     ]
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('videoid')
  29
  30         webpage = self._download_webpage(url, video_id)
  31
  32         data = self._html_search_regex(r'Stream\.Data\.Episode\((.+?)\);', webpage, 'stream data')
  33
  34         jsonData = json.loads(data)
  35
  36         formats = []
  37         for video in jsonData['instances']:
  38             format_id = video['instances'][0]['quality']
  39
  40             if format_id == '240p':
  41                 quality = 0
  42             elif format_id == '360p':
  43                 quality = 1
  44             elif format_id == '480p':
  45                 quality = 2
  46             elif format_id == '720p':
  47                 quality = 3
  48
  49             formats.append({
  50                 'format_id': format_id,
  51                 'url': video['instances'][0]['source'],
  52                 'quality': quality,
  53                 'ext': 'mp4',
  54             })
  55
  56         self._sort_formats(formats)
  57
  58         return {
  59             'id': str(jsonData['id']),
  60             'title': self._og_search_title(webpage),
  61             'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'),
  62             'formats': formats,
  63             'description': self._og_search_description(webpage),
  64         }