mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-12-14 15:22:35 +00:00
[karaoketv] Fix extraction
This commit is contained in:
parent
7e176effb2
commit
b6612c9b11
1 changed files with 39 additions and 12 deletions
|
@ -5,12 +5,6 @@ from .common import InfoExtractor
|
||||||
|
|
||||||
|
|
||||||
class KaraoketvIE(InfoExtractor):
|
class KaraoketvIE(InfoExtractor):
|
||||||
'''
|
|
||||||
In api_play.php there's a video-cdn.com <iframe>. The latter plays an
|
|
||||||
unencrypted RTMP stream. However I can't download it with rtmpdump.
|
|
||||||
'''
|
|
||||||
_WORKING = False
|
|
||||||
|
|
||||||
_VALID_URL = r'http://www.karaoketv.co.il/[^/]+/(?P<id>\d+)'
|
_VALID_URL = r'http://www.karaoketv.co.il/[^/]+/(?P<id>\d+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://www.karaoketv.co.il/%D7%A9%D7%99%D7%A8%D7%99_%D7%A7%D7%A8%D7%99%D7%95%D7%A7%D7%99/58356/%D7%90%D7%99%D7%96%D7%95%D7%9F',
|
'url': 'http://www.karaoketv.co.il/%D7%A9%D7%99%D7%A8%D7%99_%D7%A7%D7%A8%D7%99%D7%95%D7%A7%D7%99/58356/%D7%90%D7%99%D7%96%D7%95%D7%9F',
|
||||||
|
@ -18,20 +12,53 @@ class KaraoketvIE(InfoExtractor):
|
||||||
'id': '58356',
|
'id': '58356',
|
||||||
'ext': 'flv',
|
'ext': 'flv',
|
||||||
'title': 'קריוקי של איזון',
|
'title': 'קריוקי של איזון',
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
# rtmp download
|
||||||
|
'skip_download': True,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, video_id)
|
|
||||||
|
|
||||||
api_page_url = self._html_search_regex(
|
webpage = self._download_webpage(url, video_id)
|
||||||
r'<iframe[^>]+src="(http://www.karaoke.co.il/api_play.php?[^"]+)"',
|
api_page_url = self._search_regex(
|
||||||
webpage, 'API play URL')
|
r'<iframe[^>]+src=(["\'])(?P<url>https?://www\.karaoke\.co\.il/api_play\.php\?.+?)\1',
|
||||||
|
webpage, 'API play URL', group='url')
|
||||||
|
|
||||||
|
api_page = self._download_webpage(api_page_url, video_id)
|
||||||
|
video_cdn_url = self._search_regex(
|
||||||
|
r'<iframe[^>]+src=(["\'])(?P<url>https?://www\.video-cdn\.com/embed/iframe/.+?)\1',
|
||||||
|
api_page, 'video cdn URL', group='url')
|
||||||
|
|
||||||
|
video_cdn = self._download_webpage(video_cdn_url, video_id)
|
||||||
|
play_path = self._parse_json(
|
||||||
|
self._search_regex(
|
||||||
|
r'var\s+options\s*=\s*({.+?});', video_cdn, 'options'),
|
||||||
|
video_id)['clip']['url']
|
||||||
|
|
||||||
|
settings = self._parse_json(
|
||||||
|
self._search_regex(
|
||||||
|
r'var\s+settings\s*=\s*({.+?});', video_cdn, 'servers', default='{}'),
|
||||||
|
video_id, fatal=False) or {}
|
||||||
|
|
||||||
|
servers = settings.get('servers')
|
||||||
|
if not servers or not isinstance(servers, list):
|
||||||
|
servers = ('wowzail.video-cdn.com:80/vodcdn', )
|
||||||
|
|
||||||
|
formats = [{
|
||||||
|
'url': 'rtmp://%s' % server if not server.startswith('rtmp') else server,
|
||||||
|
'play_path': play_path,
|
||||||
|
'app': 'vodcdn',
|
||||||
|
'page_url': video_cdn_url,
|
||||||
|
'player_url': 'http://www.video-cdn.com/assets/flowplayer/flowplayer.commercial-3.2.18.swf',
|
||||||
|
'rtmp_real_time': True,
|
||||||
|
'ext': 'flv',
|
||||||
|
} for server in servers]
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'_type': 'url_transparent',
|
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': self._og_search_title(webpage),
|
'title': self._og_search_title(webpage),
|
||||||
'url': api_page_url,
|
'formats': formats,
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue