projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
854cc54
)
[tagesschau] Restrict playlist entry regex
author
Sergey M․
<dstftw@gmail.com>
Sun, 1 May 2016 01:15:23 +0000
(07:15 +0600)
committer
Sergey M․
<dstftw@gmail.com>
Sun, 1 May 2016 01:15:23 +0000
(07:15 +0600)
youtube_dl/extractor/tagesschau.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/tagesschau.py
b/youtube_dl/extractor/tagesschau.py
index 499bd260b0d3999f7e3f369b5ce174a0c226ba33..136e18f96cadf7bd5701e32b0a3bc7c8767e324e 100644
(file)
--- a/
youtube_dl/extractor/tagesschau.py
+++ b/
youtube_dl/extractor/tagesschau.py
@@
-200,6
+200,10
@@
class TagesschauIE(InfoExtractor):
}, {
'url': 'http://www.tagesschau.de/100sekunden/index.html',
'only_matching': True,
}, {
'url': 'http://www.tagesschau.de/100sekunden/index.html',
'only_matching': True,
+ }, {
+ # playlist article with collapsing sections
+ 'url': 'http://www.tagesschau.de/wirtschaft/faq-freihandelszone-eu-usa-101.html',
+ 'only_matching': True,
}]
@classmethod
}]
@classmethod
@@
-275,7
+279,7
@@
class TagesschauIE(InfoExtractor):
if webpage_type == 'website': # Article
entries = []
for num, (entry_title, media_kind, download_text) in enumerate(re.findall(
if webpage_type == 'website': # Article
entries = []
for num, (entry_title, media_kind, download_text) in enumerate(re.findall(
- r'(?s)<p[^>]+class="infotext"[^>]*>
.*?
<strong>(.+?)</strong>.*?</p>.*?%s' % DOWNLOAD_REGEX,
+ r'(?s)<p[^>]+class="infotext"[^>]*>
\s*(?:<a[^>]+>)?\s*
<strong>(.+?)</strong>.*?</p>.*?%s' % DOWNLOAD_REGEX,
webpage), 1):
entries.append({
'id': '%s-%d' % (display_id, num),
webpage), 1):
entries.append({
'id': '%s-%d' % (display_id, num),