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 ..compat import (
   8     compat_urllib_request,
   9     compat_urllib_parse,
  10     compat_urllib_parse_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14 )
  15
  16
  17 class CeskaTelevizeIE(InfoExtractor):
  18     _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
  19
  20     _TESTS = [
  21         {
  22             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
  23             'info_dict': {
  24                 'id': '213512120230004',
  25                 'ext': 'flv',
  26                 'title': 'První republika: Španělská chřipka',
  27                 'duration': 3107.4,
  28             },
  29             'params': {
  30                 'skip_download': True,  # requires rtmpdump
  31             },
  32             'skip': 'Works only from Czech Republic.',
  33         },
  34         {
  35             'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
  36             'info_dict': {
  37                 'id': '20138143440',
  38                 'ext': 'flv',
  39                 'title': 'Tsatsiki, maminka a policajt',
  40                 'duration': 6754.1,
  41             },
  42             'params': {
  43                 'skip_download': True,  # requires rtmpdump
  44             },
  45             'skip': 'Works only from Czech Republic.',
  46         },
  47         {
  48             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
  49             'info_dict': {
  50                 'id': '14716',
  51                 'ext': 'flv',
  52                 'title': 'První republika: Zpěvačka z Dupárny Bobina',
  53                 'duration': 90,
  54             },
  55             'params': {
  56                 'skip_download': True,  # requires rtmpdump
  57             },
  58         },
  59     ]
  60
  61     def _real_extract(self, url):
  62         url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
  63
  64         mobj = re.match(self._VALID_URL, url)
  65         video_id = mobj.group('id')
  66
  67         webpage = self._download_webpage(url, video_id)
  68
  69         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
  70         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
  71             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
  72
  73         typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
  74         episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
  75
  76         data = {
  77             'playlist[0][type]': typ,
  78             'playlist[0][id]': episode_id,
  79             'requestUrl': compat_urllib_parse_urlparse(url).path,
  80             'requestSource': 'iVysilani',
  81         }
  82
  83         req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
  84                                             data=compat_urllib_parse.urlencode(data))
  85
  86         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  87         req.add_header('x-addr', '127.0.0.1')
  88         req.add_header('X-Requested-With', 'XMLHttpRequest')
  89         req.add_header('Referer', url)
  90
  91         playlistpage = self._download_json(req, video_id)
  92
  93         req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
  94         req.add_header('Referer', url)
  95
  96         playlist = self._download_xml(req, video_id)
  97
  98         formats = []
  99         for i in playlist.find('smilRoot/body'):
 100             if 'AD' not in i.attrib['id']:
 101                 base_url = i.attrib['base']
 102                 parsedurl = compat_urllib_parse_urlparse(base_url)
 103                 duration = i.attrib['duration']
 104
 105                 for video in i.findall('video'):
 106                     if video.attrib['label'] != 'AD':
 107                         format_id = video.attrib['label']
 108                         play_path = video.attrib['src']
 109                         vbr = int(video.attrib['system-bitrate'])
 110
 111                         formats.append({
 112                             'format_id': format_id,
 113                             'url': base_url,
 114                             'vbr': vbr,
 115                             'play_path': play_path,
 116                             'app': parsedurl.path[1:] + '?' + parsedurl.query,
 117                             'rtmp_live': True,
 118                             'ext': 'flv',
 119                         })
 120
 121         self._sort_formats(formats)
 122
 123         return {
 124             'id': episode_id,
 125             'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
 126             'duration': float(duration),
 127             'formats': formats,
 128         }