_ Git - youtube-dl/blob - youtube_dl/extractor/ceskatelevize.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     compat_urllib_request,
  10     compat_urllib_parse,
  11     compat_urllib_parse_urlparse,
  12     ExtractorError,
  13 )
  14
  15
  16 class CeskaTelevizeIE(InfoExtractor):
  17     _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
  22             'info_dict': {
  23                 'id': '213512120230004',
  24                 'ext': 'flv',
  25                 'title': 'První republika: Španělská chřipka',
  26                 'duration': 3107.4,
  27             },
  28             'params': {
  29                 'skip_download': True,  # requires rtmpdump
  30             },
  31             'skip': 'Works only from Czech Republic.',
  32         },
  33         {
  34             'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
  35             'info_dict': {
  36                 'id': '20138143440',
  37                 'ext': 'flv',
  38                 'title': 'Tsatsiki, maminka a policajt',
  39                 'duration': 6754.1,
  40             },
  41             'params': {
  42                 'skip_download': True,  # requires rtmpdump
  43             },
  44             'skip': 'Works only from Czech Republic.',
  45         },
  46         {
  47             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
  48             'info_dict': {
  49                 'id': '14716',
  50                 'ext': 'flv',
  51                 'title': 'První republika: Zpěvačka z Dupárny Bobina',
  52                 'duration': 90,
  53             },
  54             'params': {
  55                 'skip_download': True,  # requires rtmpdump
  56             },
  57         },
  58     ]
  59
  60     def _real_extract(self, url):
  61         url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
  62
  63         mobj = re.match(self._VALID_URL, url)
  64         video_id = mobj.group('id')
  65
  66         webpage = self._download_webpage(url, video_id)
  67
  68         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
  69         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
  70             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
  71
  72         typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
  73         episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
  74
  75         data = {
  76             'playlist[0][type]': typ,
  77             'playlist[0][id]': episode_id,
  78             'requestUrl': compat_urllib_parse_urlparse(url).path,
  79             'requestSource': 'iVysilani',
  80         }
  81
  82         req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
  83                                             data=compat_urllib_parse.urlencode(data))
  84
  85         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  86         req.add_header('x-addr', '127.0.0.1')
  87         req.add_header('X-Requested-With', 'XMLHttpRequest')
  88         req.add_header('Referer', url)
  89
  90         playlistpage = self._download_webpage(req, video_id)
  91
  92         req = compat_urllib_request.Request(compat_urllib_parse.unquote(json.loads(playlistpage)['url']))
  93         req.add_header('Referer', url)
  94
  95         playlist = self._download_xml(req, video_id)
  96
  97         formats = []
  98         for i in playlist.find('smilRoot/body'):
  99             if 'AD' not in i.attrib['id']:
 100                 base_url = i.attrib['base']
 101                 parsedurl = compat_urllib_parse_urlparse(base_url)
 102                 duration = i.attrib['duration']
 103
 104                 for video in i.findall('video'):
 105                     if video.attrib['label'] != 'AD':
 106                         format_id = video.attrib['label']
 107                         play_path = video.attrib['src']
 108                         vbr = int(video.attrib['system-bitrate'])
 109
 110                         formats.append({
 111                             'format_id': format_id,
 112                             'url': base_url,
 113                             'vbr': vbr,
 114                             'play_path': play_path,
 115                             'app': parsedurl.path[1:] + '?' + parsedurl.query,
 116                             'rtmp_live': True,
 117                             'ext': 'flv',
 118                         })
 119
 120         self._sort_formats(formats)
 121
 122         return {
 123             'id': episode_id,
 124             'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
 125             'duration': float(duration),
 126             'formats': formats,
 127         }