[tagesschau] Restrict playlist entry regex
This commit is contained in:
parent
854cc54bc1
commit
68bb2fef95
|
@ -200,6 +200,10 @@ class TagesschauIE(InfoExtractor):
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.tagesschau.de/100sekunden/index.html',
|
'url': 'http://www.tagesschau.de/100sekunden/index.html',
|
||||||
'only_matching': True,
|
'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
|
if webpage_type == 'website': # Article
|
||||||
entries = []
|
entries = []
|
||||||
for num, (entry_title, media_kind, download_text) in enumerate(re.findall(
|
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):
|
webpage), 1):
|
||||||
entries.append({
|
entries.append({
|
||||||
'id': '%s-%d' % (display_id, num),
|
'id': '%s-%d' % (display_id, num),
|
||||||
|
|
Loading…
Reference in New Issue