youtube_dl/extractor/ceskatelevize.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_request,
   9     compat_urllib_parse,
  10     compat_urllib_parse_urlparse,
  11     ExtractorError,
  12 )
  13
  14
  15 class CeskaTelevizeIE(InfoExtractor):
  16     _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
  17
  18     _TESTS = [
  19         {
  20             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
  21             'info_dict': {
  22                 'id': '213512120230004',
  23                 'ext': 'flv',
  24                 'title': 'První republika: Španělská chřipka',
  25                 'duration': 3107.4,
  26             },
  27             'params': {
  28                 'skip_download': True,  # requires rtmpdump
  29             },
  30             'skip': 'Works only from Czech Republic.',
  31         },
  32         {
  33             'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
  34             'info_dict': {
  35                 'id': '20138143440',
  36                 'ext': 'flv',
  37                 'title': 'Tsatsiki, maminka a policajt',
  38                 'duration': 6754.1,
  39             },
  40             'params': {
  41                 'skip_download': True,  # requires rtmpdump
  42             },
  43             'skip': 'Works only from Czech Republic.',
  44         },
  45         {
  46             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
  47             'info_dict': {
  48                 'id': '14716',
  49                 'ext': 'flv',
  50                 'title': 'První republika: Zpěvačka z Dupárny Bobina',
  51                 'duration': 90,
  52             },
  53             'params': {
  54                 'skip_download': True,  # requires rtmpdump
  55             },
  56         },
  57     ]
  58
  59     def _real_extract(self, url):
  60         url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
  61
  62         mobj = re.match(self._VALID_URL, url)
  63         video_id = mobj.group('id')
  64
  65         webpage = self._download_webpage(url, video_id)
  66
  67         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
  68         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
  69             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
  70
  71         typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
  72         episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
  73
  74         data = {
  75             'playlist[0][type]': typ,
  76             'playlist[0][id]': episode_id,
  77             'requestUrl': compat_urllib_parse_urlparse(url).path,
  78             'requestSource': 'iVysilani',
  79         }
  80
  81         req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
  82                                             data=compat_urllib_parse.urlencode(data))
  83
  84         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  85         req.add_header('x-addr', '127.0.0.1')
  86         req.add_header('X-Requested-With', 'XMLHttpRequest')
  87         req.add_header('Referer', url)
  88
  89         playlistpage = self._download_json(req, video_id)
  90
  91         req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
  92         req.add_header('Referer', url)
  93
  94         playlist = self._download_xml(req, video_id)
  95
  96         formats = []
  97         for i in playlist.find('smilRoot/body'):
  98             if 'AD' not in i.attrib['id']:
  99                 base_url = i.attrib['base']
 100                 parsedurl = compat_urllib_parse_urlparse(base_url)
 101                 duration = i.attrib['duration']
 102
 103                 for video in i.findall('video'):
 104                     if video.attrib['label'] != 'AD':
 105                         format_id = video.attrib['label']
 106                         play_path = video.attrib['src']
 107                         vbr = int(video.attrib['system-bitrate'])
 108
 109                         formats.append({
 110                             'format_id': format_id,
 111                             'url': base_url,
 112                             'vbr': vbr,
 113                             'play_path': play_path,
 114                             'app': parsedurl.path[1:] + '?' + parsedurl.query,
 115                             'rtmp_live': True,
 116                             'ext': 'flv',
 117                         })
 118
 119         self._sort_formats(formats)
 120
 121         return {
 122             'id': episode_id,
 123             'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
 124             'duration': float(duration),
 125             'formats': formats,
 126         }