def _convert_entity(match):
entity_body = match.group(3)
if match.group(1):
try:
if match.group(2):
number = int(entity_body, 16)
else:
number = int(entity_body, 10)
# Numeric character references in the 80-9F range are typically
# interpreted by browsers as representing the characters mapped
# to bytes 80-9F in the Windows-1252 encoding. For more info
# see: http://en.wikipedia.org/wiki/Character_encodings_in_HTML
if 0x80 <= number <= 0x9f:
return int2byte(number).decode('cp1252')
except ValueError:
number = None
else:
if entity_body in keep:
return match.group(0)
else:
number = htmlentitydefs.name2codepoint.get(entity_body)
if number is not None:
try:
return unichr(number)
except ValueError:
pass
return "" if remove_illegal else match.group(0)
def _convert_entity(match):
entity_body = match.group(3)
if match.group(1):
try:
if match.group(2):
number = int(entity_body, 16)
else:
number = int(entity_body, 10)
# Numeric character references in the 80-9F range are typically
# interpreted by browsers as representing the characters mapped
# to bytes 80-9F in the Windows-1252 encoding. For more info
# see: http://en.wikipedia.org/wiki/Character_encodings_in_HTML
if 0x80 <= number <= 0x9f:
return int2byte(number).decode('cp1252')
except ValueError:
number = None
else:
if entity_body in keep:
return match.group(0)
else:
number = htmlentitydefs.name2codepoint.get(entity_body)
if number is not None:
try:
return unichr(number)
except ValueError:
pass
return "" if remove_illegal else match.group(0)