MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-25 20:55:52 +01:00
Code Issues Projects Releases Wiki Activity

[fktv] Correct and improve some regexs

Browse Source
This commit is contained in:
Yen Chi Hsuan 2015-09-25 17:51:48 +08:00
parent 8ddf48d59f
commit 140359fc2c
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
youtube_dl/extractor/fktv.py
View File

@ -28,13 +28,13 @@ def _real_extract(self, url):
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,