return unescapeHTML(res)
-def extract_attributes(attributes_str, attributes_regex=r'(?s)\s*([^\s=]+)\s*=\s*["\']([^"\']+)["\']'):
- attributes = re.findall(attributes_regex, attributes_str)
- attributes_dict = {}
- if attributes:
- for (attribute_name, attribute_value) in attributes:
- attributes_dict[attribute_name] = attribute_value
- return attributes_dict
-
-
def clean_html(html):
"""Clean an HTML snippet into a readable string"""
numstr = '0%s' % numstr
else:
base = 10
- return compat_chr(int(numstr, base))
+ # See https://github.com/rg3/youtube-dl/issues/7518
+ try:
+ return compat_chr(int(numstr, base))
+ except ValueError:
+ pass
# Unknown entity in name, return its literal representation
return ('&%s;' % entity)