projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
140359f
)
[fktv] Correct thumbnail extraction and add the test
author
Yen Chi Hsuan
<yan12125@gmail.com>
Fri, 25 Sep 2015 09:58:44 +0000
(17:58 +0800)
committer
Yen Chi Hsuan
<yan12125@gmail.com>
Fri, 25 Sep 2015 09:58:44 +0000
(17:58 +0800)
youtube_dl/extractor/fktv.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/fktv.py
b/youtube_dl/extractor/fktv.py
index b081eb535ba490928c24ed4fb6a2d82d2b49cb6e..289cbb8c87a374d82f41f2d9840f57f6c4de63dd 100644
(file)
--- a/
youtube_dl/extractor/fktv.py
+++ b/
youtube_dl/extractor/fktv.py
@@
-21,6
+21,7
@@
class FKTVIE(InfoExtractor):
'id': '1',
'ext': 'mp4',
'title': 'Folge 1 vom 10. April 2007',
'id': '1',
'ext': 'mp4',
'title': 'Folge 1 vom 10. April 2007',
+ 'thumbnail': 're:^https?://.*\.jpg$',
},
}
},
}
@@
-29,11
+30,14
@@
class FKTVIE(InfoExtractor):
webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
title = clean_html(self._html_search_regex('<h3>([^<]+)</h3>', webpage, 'title'))
webpage = self._download_webpage('http://fernsehkritik.tv/folge-%s/play' % episode, episode)
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:
raise ExtractorError('Unable to extract the video')
poster, sources = matches.groups()
if matches is None:
raise ExtractorError('Unable to extract the video')
poster, sources = matches.groups()
+ if poster is None:
+ self.report_warning('unable to extract thumbnail')
+
urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
return {
urls = re.findall(r'<source[^>]+src="([^"]+)"', sources)
formats = [{'url': url, 'format_id': determine_ext(url)} for url in urls]
return {