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 from ..utils import (
   9     int_or_none,
  10     compat_str,
  11 )
  12
  13
  14 class StreamCZIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)'
  16
  17     _TESTS = [{
  18         'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
  19         'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
  20         'info_dict': {
  21             'id': '765767',
  22             'ext': 'mp4',
  23             'title': 'Peklo na talíři: Éčka pro děti',
  24             'description': 'md5:49ace0df986e95e331d0fe239d421519',
  25             'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
  26             'duration': 256,
  27         },
  28     }, {
  29         'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
  30         'md5': '246272e753e26bbace7fcd9deca0650c',
  31         'info_dict': {
  32             'id': '10002447',
  33             'ext': 'mp4',
  34             'title': 'Kancelář Blaník: Tři roky pro Mazánka',
  35             'description': 'md5:9177695a8b756a0a8ab160de4043b392',
  36             'thumbnail': 'http://im.stream.cz/episode/537f838c50c11f8d21320000',
  37             'duration': 368,
  38         },
  39     }]
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43         video_id = mobj.group('videoid')
  44
  45         webpage = self._download_webpage(url, video_id)
  46
  47         data = self._html_search_regex(r'Stream\.Data\.Episode\((.+?)\);', webpage, 'stream data')
  48
  49         jsonData = json.loads(data)
  50
  51         formats = []
  52         for video in jsonData['instances']:
  53             for video_format in video['instances']:
  54                 format_id = video_format['quality']
  55
  56                 if format_id == '240p':
  57                     quality = 0
  58                 elif format_id == '360p':
  59                     quality = 1
  60                 elif format_id == '480p':
  61                     quality = 2
  62                 elif format_id == '720p':
  63                     quality = 3
  64
  65                 formats.append({
  66                     'format_id': '%s-%s' % (video_format['type'].split('/')[1], format_id),
  67                     'url': video_format['source'],
  68                     'quality': quality,
  69                 })
  70
  71         self._sort_formats(formats)
  72
  73         return {
  74             'id': compat_str(jsonData['episode_id']),
  75             'title': self._og_search_title(webpage),
  76             'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'),
  77             'formats': formats,
  78             'description': self._og_search_description(webpage),
  79             'duration': int_or_none(jsonData['duration']),
  80             'view_count': int_or_none(jsonData['stats_total']),
  81         }