[extractor/common] Skip html comment tags (Closes #6822)
This commit is contained in:
parent
73eb13dfc7
commit
586f1cc532
1 changed files with 1 additions and 0 deletions
|
@ -731,6 +731,7 @@ class InfoExtractor(object):
|
|||
|
||||
@staticmethod
|
||||
def _hidden_inputs(html):
|
||||
html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
|
||||
hidden_inputs = {}
|
||||
for input in re.findall(r'(?i)<input([^>]+)>', html):
|
||||
if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
|
||||
|
|
Loading…
Reference in a new issue