Raphaël G. Git Repositories - youtubedl/blob - 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_parse,
   9     compat_urllib_parse_unquote,
  10     compat_urllib_parse_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     float_or_none,
  15     sanitized_Request,
  16 )
  17
  18
  19 class CeskaTelevizeIE(InfoExtractor):
  20     _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
  21     _TESTS = [{
  22         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
  23         'info_dict': {
  24             'id': '61924494876951776',
  25             'ext': 'mp4',
  26             'title': 'Hyde Park Civilizace',
  27             'description': 'md5:fe93f6eda372d150759d11644ebbfb4a',
  28             'thumbnail': 're:^https?://.*\.jpg',
  29             'duration': 3350,
  30         },
  31         'params': {
  32             # m3u8 download
  33             'skip_download': True,
  34         },
  35     }, {
  36         'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
  37         'info_dict': {
  38             'id': '61924494876844374',
  39             'ext': 'mp4',
  40             'title': 'První republika: Zpěvačka z Dupárny Bobina',
  41             'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
  42             'thumbnail': 're:^https?://.*\.jpg',
  43             'duration': 88.4,
  44         },
  45         'params': {
  46             # m3u8 download
  47             'skip_download': True,
  48         },
  49     }, {
  50         # video with 18+ caution trailer
  51         'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
  52         'info_dict': {
  53             'id': '215562210900007-bogotart',
  54             'title': 'Queer: Bogotart',
  55             'description': 'Alternativní průvodce současným queer světem',
  56         },
  57         'playlist': [{
  58             'info_dict': {
  59                 'id': '61924494876844842',
  60                 'ext': 'mp4',
  61                 'title': 'Queer: Bogotart (Varování 18+)',
  62                 'duration': 10.2,
  63             },
  64         }, {
  65             'info_dict': {
  66                 'id': '61924494877068022',
  67                 'ext': 'mp4',
  68                 'title': 'Queer: Bogotart (Queer)',
  69                 'thumbnail': 're:^https?://.*\.jpg',
  70                 'duration': 1558.3,
  71             },
  72         }],
  73         'params': {
  74             # m3u8 download
  75             'skip_download': True,
  76         },
  77     }]
  78
  79     def _real_extract(self, url):
  80         url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
  81
  82         mobj = re.match(self._VALID_URL, url)
  83         playlist_id = mobj.group('id')
  84
  85         webpage = self._download_webpage(url, playlist_id)
  86
  87         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
  88         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
  89             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
  90
  91         typ = self._html_search_regex(
  92             r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
  93         episode_id = self._html_search_regex(
  94             r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
  95
  96         data = {
  97             'playlist[0][type]': typ,
  98             'playlist[0][id]': episode_id,
  99             'requestUrl': compat_urllib_parse_urlparse(url).path,
 100             'requestSource': 'iVysilani',
 101         }
 102
 103         req = sanitized_Request(
 104             'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
 105             data=compat_urllib_parse.urlencode(data))
 106
 107         req.add_header('Content-type', 'application/x-www-form-urlencoded')
 108         req.add_header('x-addr', '127.0.0.1')
 109         req.add_header('X-Requested-With', 'XMLHttpRequest')
 110         req.add_header('Referer', url)
 111
 112         playlistpage = self._download_json(req, playlist_id)
 113
 114         playlist_url = playlistpage['url']
 115         if playlist_url == 'error_region':
 116             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 117
 118         req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
 119         req.add_header('Referer', url)
 120
 121         playlist_title = self._og_search_title(webpage)
 122         playlist_description = self._og_search_description(webpage)
 123
 124         playlist = self._download_json(req, playlist_id)['playlist']
 125         playlist_len = len(playlist)
 126
 127         entries = []
 128         for item in playlist:
 129             formats = []
 130             for format_id, stream_url in item['streamUrls'].items():
 131                 formats.extend(self._extract_m3u8_formats(
 132                     stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
 133             self._sort_formats(formats)
 134
 135             item_id = item.get('id') or item['assetId']
 136             title = item['title']
 137
 138             duration = float_or_none(item.get('duration'))
 139             thumbnail = item.get('previewImageUrl')
 140
 141             subtitles = {}
 142             if item.get('type') == 'VOD':
 143                 subs = item.get('subtitles')
 144                 if subs:
 145                     subtitles = self.extract_subtitles(episode_id, subs)
 146
 147             entries.append({
 148                 'id': item_id,
 149                 'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title),
 150                 'description': playlist_description if playlist_len == 1 else None,
 151                 'thumbnail': thumbnail,
 152                 'duration': duration,
 153                 'formats': formats,
 154                 'subtitles': subtitles,
 155             })
 156
 157         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
 158
 159     def _get_subtitles(self, episode_id, subs):
 160         original_subtitles = self._download_webpage(
 161             subs[0]['url'], episode_id, 'Downloading subtitles')
 162         srt_subs = self._fix_subtitles(original_subtitles)
 163         return {
 164             'cs': [{
 165                 'ext': 'srt',
 166                 'data': srt_subs,
 167             }]
 168         }
 169
 170     @staticmethod
 171     def _fix_subtitles(subtitles):
 172         """ Convert millisecond-based subtitles to SRT """
 173
 174         def _msectotimecode(msec):
 175             """ Helper utility to convert milliseconds to timecode """
 176             components = []
 177             for divider in [1000, 60, 60, 100]:
 178                 components.append(msec % divider)
 179                 msec //= divider
 180             return '{3:02}:{2:02}:{1:02},{0:03}'.format(*components)
 181
 182         def _fix_subtitle(subtitle):
 183             for line in subtitle.splitlines():
 184                 m = re.match(r'^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$', line)
 185                 if m:
 186                     yield m.group(1)
 187                     start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
 188                     yield '{0} --> {1}'.format(start, stop)
 189                 else:
 190                     yield line
 191
 192         return '\r\n'.join(_fix_subtitle(subtitles))