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_request,
   9     compat_urllib_parse,
  10     compat_urllib_parse_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     float_or_none,
  15 )
  16
  17
  18 class CeskaTelevizeIE(InfoExtractor):
  19     _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
  20
  21     _TESTS = [
  22         {
  23             'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
  24             'info_dict': {
  25                 'id': '214411058091220',
  26                 'ext': 'mp4',
  27                 'title': 'Hyde Park Civilizace',
  28                 'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře',
  29                 'thumbnail': 're:^https?://.*\.jpg',
  30                 'duration': 3350,
  31             },
  32             'params': {
  33                 # m3u8 download
  34                 'skip_download': True,
  35             },
  36         },
  37         {
  38             'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
  39             'info_dict': {
  40                 'id': '14716',
  41                 'ext': 'mp4',
  42                 'title': 'První republika: Zpěvačka z Dupárny Bobina',
  43                 'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
  44                 'thumbnail': 're:^https?://.*\.jpg',
  45                 'duration': 88.4,
  46             },
  47             'params': {
  48                 # m3u8 download
  49                 'skip_download': True,
  50             },
  51         },
  52     ]
  53
  54     def _real_extract(self, url):
  55         url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
  56
  57         mobj = re.match(self._VALID_URL, url)
  58         video_id = mobj.group('id')
  59
  60         webpage = self._download_webpage(url, video_id)
  61
  62         NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
  63         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
  64             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
  65
  66         typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
  67         episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
  68
  69         data = {
  70             'playlist[0][type]': typ,
  71             'playlist[0][id]': episode_id,
  72             'requestUrl': compat_urllib_parse_urlparse(url).path,
  73             'requestSource': 'iVysilani',
  74         }
  75
  76         req = compat_urllib_request.Request(
  77             'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
  78             data=compat_urllib_parse.urlencode(data))
  79
  80         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  81         req.add_header('x-addr', '127.0.0.1')
  82         req.add_header('X-Requested-With', 'XMLHttpRequest')
  83         req.add_header('Referer', url)
  84
  85         playlistpage = self._download_json(req, video_id)
  86
  87         playlist_url = playlistpage['url']
  88         if playlist_url == 'error_region':
  89             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
  90
  91         req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url))
  92         req.add_header('Referer', url)
  93
  94         playlist = self._download_json(req, video_id)
  95
  96         item = playlist['playlist'][0]
  97         formats = []
  98         for format_id, stream_url in item['streamUrls'].items():
  99             formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4'))
 100         self._sort_formats(formats)
 101
 102         title = self._og_search_title(webpage)
 103         description = self._og_search_description(webpage)
 104         duration = float_or_none(item.get('duration'))
 105         thumbnail = item.get('previewImageUrl')
 106
 107         subtitles = {}
 108         subs = item.get('subtitles')
 109         if subs:
 110             subtitles = self.extract_subtitles(episode_id, subs)
 111
 112         return {
 113             'id': episode_id,
 114             'title': title,
 115             'description': description,
 116             'thumbnail': thumbnail,
 117             'duration': duration,
 118             'formats': formats,
 119             'subtitles': subtitles,
 120         }
 121
 122     def _get_subtitles(self, episode_id, subs):
 123         original_subtitles = self._download_webpage(
 124             subs[0]['url'], episode_id, 'Downloading subtitles')
 125         srt_subs = self._fix_subtitles(original_subtitles)
 126         return {
 127             'cs': [{
 128                 'ext': 'srt',
 129                 'data': srt_subs,
 130             }]
 131         }
 132
 133     @staticmethod
 134     def _fix_subtitles(subtitles):
 135         """ Convert millisecond-based subtitles to SRT """
 136
 137         def _msectotimecode(msec):
 138             """ Helper utility to convert milliseconds to timecode """
 139             components = []
 140             for divider in [1000, 60, 60, 100]:
 141                 components.append(msec % divider)
 142                 msec //= divider
 143             return "{3:02}:{2:02}:{1:02},{0:03}".format(*components)
 144
 145         def _fix_subtitle(subtitle):
 146             for line in subtitle.splitlines():
 147                 m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line)
 148                 if m:
 149                     yield m.group(1)
 150                     start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:])
 151                     yield "{0} --> {1}".format(start, stop)
 152                 else:
 153                     yield line
 154
 155         return "\r\n".join(_fix_subtitle(subtitles))