diff options
Diffstat (limited to 'youtube_dl/extractor/ceskatelevize.py')
| -rw-r--r-- | youtube_dl/extractor/ceskatelevize.py | 106 |
1 files changed, 69 insertions, 37 deletions
diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index dd2529a..e250de1 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -12,13 +12,14 @@ from ..utils import ( ExtractorError, float_or_none, sanitized_Request, + unescapeHTML, urlencode_postdata, USER_AGENTS, ) class CeskaTelevizeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$' + _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)' _TESTS = [{ 'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220', 'info_dict': { @@ -62,40 +63,12 @@ class CeskaTelevizeIE(InfoExtractor): }, 'skip': 'Georestricted to Czech Republic', }, { - # video with 18+ caution trailer - 'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/', - 'info_dict': { - 'id': '215562210900007-bogotart', - 'title': 'Queer: Bogotart', - 'description': 'Alternativní průvodce současným queer světem', - }, - 'playlist': [{ - 'info_dict': { - 'id': '61924494876844842', - 'ext': 'mp4', - 'title': 'Queer: Bogotart (Varování 18+)', - 'duration': 10.2, - }, - }, { - 'info_dict': { - 'id': '61924494877068022', - 'ext': 'mp4', - 'title': 'Queer: Bogotart (Queer)', - 'thumbnail': r're:^https?://.*\.jpg', - 'duration': 1558.3, - }, - }], - 'params': { - # m3u8 download - 'skip_download': True, - }, + 'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25', + 'only_matching': True, }] def _real_extract(self, url): - url = url.replace('/porady/', '/ivysilani/').replace('/video/', '') - - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) @@ -103,13 +76,28 @@ class CeskaTelevizeIE(InfoExtractor): if '%s</p>' % NOT_AVAILABLE_STRING in webpage: raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) - typ = self._html_search_regex( - r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type') - episode_id = self._html_search_regex( - r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id') + type_ = None + episode_id = None + + playlist = self._parse_json( + self._search_regex( + r'getPlaylistUrl\(\[({.+?})\]', webpage, 'playlist', + default='{}'), playlist_id) + if playlist: + type_ = playlist.get('type') + episode_id = playlist.get('id') + + if not type_: + type_ = self._html_search_regex( + r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', + webpage, 'type') + if not episode_id: + episode_id = self._html_search_regex( + r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', + webpage, 'episode_id') data = { - 'playlist[0][type]': typ, + 'playlist[0][type]': type_, 'playlist[0][id]': episode_id, 'requestUrl': compat_urllib_parse_urlparse(url).path, 'requestSource': 'iVysilani', @@ -245,3 +233,47 @@ class CeskaTelevizeIE(InfoExtractor): yield line return '\r\n'.join(_fix_subtitle(subtitles)) + + +class CeskaTelevizePoradyIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)' + _TESTS = [{ + # video with 18+ caution trailer + 'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/', + 'info_dict': { + 'id': '215562210900007-bogotart', + 'title': 'Queer: Bogotart', + 'description': 'Alternativní průvodce současným queer světem', + }, + 'playlist': [{ + 'info_dict': { + 'id': '61924494876844842', + 'ext': 'mp4', + 'title': 'Queer: Bogotart (Varování 18+)', + 'duration': 10.2, + }, + }, { + 'info_dict': { + 'id': '61924494877068022', + 'ext': 'mp4', + 'title': 'Queer: Bogotart (Queer)', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 1558.3, + }, + }], + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + data_url = unescapeHTML(self._search_regex( + r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1', + webpage, 'iframe player url', group='url')) + + return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key()) |