[ceskatelevize] Extract playlists (Closes #6772)

This commit is contained in:
Sergey M․ 2015-09-07 04:52:26 +06:00
parent 9dbdb65abe
commit 97243fe395
1 changed files with 96 additions and 60 deletions

View File

@ -17,55 +17,81 @@ from ..utils import (
class CeskaTelevizeIE(InfoExtractor): class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)' _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
_TESTS = [{
_TESTS = [ 'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
{ 'info_dict': {
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220', 'id': '61924494876951776',
'info_dict': { 'ext': 'mp4',
'id': '214411058091220', 'title': 'Hyde Park Civilizace',
'ext': 'mp4', 'description': 'md5:fe93f6eda372d150759d11644ebbfb4a',
'title': 'Hyde Park Civilizace', 'thumbnail': 're:^https?://.*\.jpg',
'description': 'Věda a současná civilizace. Interaktivní pořad - prostor pro vaše otázky a komentáře', 'duration': 3350,
'thumbnail': 're:^https?://.*\.jpg',
'duration': 3350,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, },
{ 'params': {
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina', # m3u8 download
'info_dict': { 'skip_download': True,
'id': '14716',
'ext': 'mp4',
'title': 'První republika: Zpěvačka z Dupárny Bobina',
'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 88.4,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, },
] }, {
'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
'info_dict': {
'id': '61924494876844374',
'ext': 'mp4',
'title': 'První republika: Zpěvačka z Dupárny Bobina',
'description': 'Sága mapující atmosféru první republiky od r. 1918 do r. 1945.',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 88.4,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# 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': 're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url): def _real_extract(self, url):
url = url.replace('/porady/', '/ivysilani/').replace('/video/', '') url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') playlist_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, playlist_id)
NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.' NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
if '%s</p>' % NOT_AVAILABLE_STRING in webpage: if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type') typ = self._html_search_regex(
episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id') r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
episode_id = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
data = { data = {
'playlist[0][type]': typ, 'playlist[0][type]': typ,
@ -83,7 +109,7 @@ class CeskaTelevizeIE(InfoExtractor):
req.add_header('X-Requested-With', 'XMLHttpRequest') req.add_header('X-Requested-With', 'XMLHttpRequest')
req.add_header('Referer', url) req.add_header('Referer', url)
playlistpage = self._download_json(req, video_id) playlistpage = self._download_json(req, playlist_id)
playlist_url = playlistpage['url'] playlist_url = playlistpage['url']
if playlist_url == 'error_region': if playlist_url == 'error_region':
@ -92,33 +118,43 @@ class CeskaTelevizeIE(InfoExtractor):
req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url)) req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url) req.add_header('Referer', url)
playlist = self._download_json(req, video_id) playlist_title = self._og_search_title(webpage)
playlist_description = self._og_search_description(webpage)
item = playlist['playlist'][0] playlist = self._download_json(req, playlist_id)['playlist']
formats = [] playlist_len = len(playlist)
for format_id, stream_url in item['streamUrls'].items():
formats.extend(self._extract_m3u8_formats(stream_url, video_id, 'mp4'))
self._sort_formats(formats)
title = self._og_search_title(webpage) entries = []
description = self._og_search_description(webpage) for item in playlist:
duration = float_or_none(item.get('duration')) formats = []
thumbnail = item.get('previewImageUrl') for format_id, stream_url in item['streamUrls'].items():
formats.extend(self._extract_m3u8_formats(
stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
self._sort_formats(formats)
subtitles = {} item_id = item.get('id') or item['assetId']
subs = item.get('subtitles') title = item['title']
if subs:
subtitles = self.extract_subtitles(episode_id, subs)
return { duration = float_or_none(item.get('duration'))
'id': episode_id, thumbnail = item.get('previewImageUrl')
'title': title,
'description': description, subtitles = {}
'thumbnail': thumbnail, if item.get('type') == 'VOD':
'duration': duration, subs = item.get('subtitles')
'formats': formats, if subs:
'subtitles': subtitles, subtitles = self.extract_subtitles(episode_id, subs)
}
entries.append({
'id': item_id,
'title': playlist_title if playlist_len == 1 else '%s (%s)' % (playlist_title, title),
'description': playlist_description if playlist_len == 1 else None,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
})
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
def _get_subtitles(self, episode_id, subs): def _get_subtitles(self, episode_id, subs):
original_subtitles = self._download_webpage( original_subtitles = self._download_webpage(