mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-11-16 10:32:40 +09:00
[fktv] Correct and improve some regexs
This commit is contained in:
parent
8ddf48d59f
commit
140359fc2c
@ -28,13 +28,13 @@ class FKTVIE(InfoExtractor):
|
|||||||
episode = self._match_id(url)
|
episode = self._match_id(url)
|
||||||
|
|
||||||
webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
|
webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
|
||||||
title = clean_html(self._html_search_regex('<h3>([^<]+?)</h3>', webpage, 'title'))
|
title = clean_html(self._html_search_regex('<h3>([^<]+)</h3>', webpage, 'title'))
|
||||||
matches = re.search(r'(?s)<video[^>]*poster="([^"]+)"[^>]*>(.*?)</video>', webpage)
|
matches = re.search(r'(?s)<video[^>]+poster="([^"]+)"[^>]*>(.*)</video>', webpage)
|
||||||
if matches is None:
|
if matches is None:
|
||||||
raise ExtractorError('Unable to extract the video')
|
raise ExtractorError('Unable to extract the video')
|
||||||
|
|
||||||
poster, sources = matches.groups()
|
poster, sources = matches.groups()
|
||||||
urls = re.findall(r'(?s)<source[^>]*src="([^"]+)"[^>]*>', sources)
|
urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
|
||||||
formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
|
formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
|
||||||
return {
|
return {
|
||||||
'id': episode,
|
'id': episode,
|
||||||
|
Loading…
Reference in New Issue
Block a user