def convert_entity(m):
groups = m.groupdict()
if groups.get('dec'):
number = int(groups['dec'], 10)
elif groups.get('hex'):
number = int(groups['hex'], 16)
elif groups.get('named'):
entity_name = groups['named']
if entity_name.lower() in keep:
return m.group(0)
else:
number = (name2codepoint.get(entity_name)
or name2codepoint.get(entity_name.lower()))
if number is not None:
# 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
try:
if 0x80 <= number <= 0x9f:
return bytes((number, )).decode('cp1252')
else:
return chr(number)
except ValueError:
pass
return '' if remove_illegal and groups.get('semicolon') else m.group(0)
def convert_entity(m: Match) -> str:
groups = m.groupdict()
number = None
if groups.get("dec"):
number = int(groups["dec"], 10)
elif groups.get("hex"):
number = int(groups["hex"], 16)
elif groups.get("named"):
entity_name = groups["named"]
if entity_name.lower() in keep:
return m.group(0)
else:
number = name2codepoint.get(entity_name) or name2codepoint.get(
entity_name.lower())
if number is not None:
# 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
try:
if 0x80 <= number <= 0x9F:
return bytes((number, )).decode("cp1252")
else:
return chr(number)
except ValueError:
pass
return "" if remove_illegal and groups.get("semicolon") else m.group(0)
def convert_entity(m):
entity_body = m.group(3)
if m.group(1):
try:
if m.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 chr(number).decode('cp1252')
except ValueError:
number = None
else:
if entity_body in keep:
return m.group(0)
else:
number = name2codepoint.get(entity_body)
if number is not None:
try:
return chr(number)
except ValueError:
pass
return '' if remove_illegal else m.group(0)
def convert_entity(m):
entity_body = m.group(3)
if m.group(1):
try:
if m.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 chr(number).decode('cp1252')
except ValueError:
number = None
else:
if entity_body in keep:
return m.group(0)
else:
number = name2codepoint.get(entity_body)
if number is not None:
try:
return chr(number)
except ValueError:
pass
return '' if remove_illegal else m.group(0)
def substitute_entity(match):
ent = match.group(3)
if match.group(1) == "#": # number, decimal or hexadecimal
return unichr(int(ent)) if match.group(2) == '' else unichr(int('0x'+ent,16))
else: # name
cp = name2codepoint.get(ent)
return unichr(cp) if cp else match.group()
def substitute_entity(match):
ent = match.group(3)
if match.group(1) == "#": # number, decimal or hexadecimal
return unichr(int(ent)) if match.group(2) == '' else unichr(
int('0x' + ent, 16))
else: # name
cp = name2codepoint.get(ent)
return unichr(cp) if cp else match.group()
def decode_entity(match):
what = match.group(1)
if what.startswith('#x'):
what = int(what[2:], 16)
elif what.startswith('#'):
what = int(what[1:])
else:
from html.entities import name2codepoint
what = name2codepoint.get(what, match.group(0))
return uchr(what)
def subst_entity(match):
ent = match.group(2)
if match.group(1) == '#':
return unichr(int(ent))
else:
cp = n2cp.get(ent)
if cp:
return unichr(cp)
else:
return match.group()
def decode_entity(match):
what = match.group(1)
if what.startswith('#x'):
what = int(what[2:], 16)
elif what.startswith('#'):
what = int(what[1:])
else:
from html.entities import name2codepoint
what = name2codepoint.get(what, match.group(0))
return uchr(what)
def _substitute_entity(m):
ent = m.group(2)
if m.group(1) == "#":
return chr(int(ent))
else:
cp = name2codepoint.get(ent)
if cp:
return chr(cp)
else:
return m.group()
def inline_entity_repl(self, stack, entity):
if entity[1] == '#':
if entity[2] == 'x':
c = int(entity[3:-1], 16)
else:
c = int(entity[2:-1], 10)
c = chr(c)
else:
c = chr(name2codepoint.get(entity[1:-1], 0xfffe))
stack.top_append(c)
def _substitute_entity(m):
ent = m.group(2)
if m.group(1) == "#":
return chr(int(ent))
else:
cp = name2codepoint.get(ent)
if cp:
return chr(cp)
else:
return m.group()
def substitute(match):
ent = match.group(2)
if match.group(1) == "#":
return chr(int(ent))
else:
cp = n2cp.get(ent)
if cp:
return chr(cp)
else:
return match.group()
def substitute_entity(match):
from html.entities import name2codepoint as n2cp
ent = match.group(2)
if match.group(1) == "#":
return chr(int(ent))
else:
cp = n2cp.get(ent)
if cp:
return chr(cp)
else:
return match.group()
def substitute_entity(match):
ent = match.group(2)
if match.group(1) == "#":
# numeric substitution
return chr(int(ent))
else:
# get the codepoint from the name
cp = n2cp.get(ent)
if cp:
#if a codepoint was found, return it's string value
return chr(cp)
else:
# codepoint wasn't found, return the match untouched
return match.group()
def substitute_entity(match):
ent = match.group(2)
if match.group(1) == "#":
# numeric substitution
return chr(int(ent))
else:
# get the codepoint from the name
cp = n2cp.get(ent)
if cp:
#if a codepoint was found, return it's string value
return chr(cp)
else:
# codepoint wasn't found, return the match untouched
return match.group()
def substitute_entity(match):
if PY3:
from html.entities import name2codepoint as n2cp
else:
from htmlentitydefs import name2codepoint as n2cp
ent = match.group(2)
if match.group(1) == "#":
return unichr(int(ent)).encode('utf-8')
else:
cp = n2cp.get(ent)
if cp:
return unichr(cp).encode('utf-8')
else:
return match.group()
def substitute(match):
ent = match.group(2)
if match.group(1) == "#":
try:
return unichr(int(ent))
except:
return chr(int(ent))
else:
cp = n2cp.get(ent)
if cp:
try:
return unichr(cp)
except:
return chr(cp)
else:
return match.group()
def substitute_entity(match):
ent = match.group(3)
if match.group(1) == "#":
# decoding by number
if match.group(2) == '':
# number is in decimal
return unichr(int(ent))
elif match.group(2) == 'x':
# number is in hex
return unichr(int('0x' + ent, 16))
else:
# they were using a name
cp = n2cp.get(ent)
if cp:
return unichr(cp)
else:
return match.group()
def substitute_entity(match):
ent = match.group(3)
if match.group(1) == "#":
# decoding by number
if match.group(2) == '':
# number is in decimal
return unichr(int(ent))
elif match.group(2) == 'x':
# number is in hex
return unichr(int('0x' + ent, 16))
else:
# they were using a name
cp = n2cp.get(ent)
if cp:
return unichr(cp)
else:
return match.group()
def substitute_entity(match):
try:
ent = match.group(3)
if match.group(1) == "#":
if match.group(2) == '':
return chr(int(ent))
elif match.group(2) == 'x':
return chr(int('0x' + ent, 16))
else:
cp = n2cp.get(ent)
if cp:
return chr(cp)
else:
return match.group()
except:
return ""
def substitute_entity(match):
try:
ent = match.group(3)
if match.group(1) == "#":
if match.group(2) == '':
return chr(int(ent))
elif match.group(2) == 'x':
return chr(int('0x' + ent, 16))
else:
cp = n2cp.get(ent)
if cp:
return chr(cp)
else:
return match.group()
except:
return ""
def substitute_entity(match):
if PY3:
from html.entities import name2codepoint as n2cp
else:
from htmlentitydefs import name2codepoint as n2cp
ent = match.group(2)
if match.group(1) == "#":
ent = unichr(int(ent)).encode('utf-8')
if PY3 and isinstance(ent, bytes):
ent = ent.decode("utf-8")
return ent
else:
cp = n2cp.get(ent)
if cp:
cp = unichr(cp).encode('utf-8')
if PY3 and isinstance(cp, bytes):
cp = cp.decode("utf-8")
return cp
else:
return match.group()
def substitute_entity(match):
try:
ent = match.group(3)
if match.group(1) == "#":
# decoding by number
if match.group(2) == '':
# number is in decimal
return safe_unichr(int(ent))
elif match.group(2) in ['x', 'X']:
# number is in hex
return safe_unichr(int(ent, 16))
else:
# they were using a name
cp = n2cp.get(ent)
if cp:
return safe_unichr(cp)
else:
return match.group()
except Exception:
# in case of errors, return original input
return match.group()
def substitute_entity(match):
try:
ent = match.group(3)
if match.group(1) == "#":
# decoding by number
if match.group(2) == '':
# number is in decimal
return safe_unichr(int(ent))
elif match.group(2) in ['x', 'X']:
# number is in hex
return safe_unichr(int(ent, 16))
else:
# they were using a name
cp = n2cp.get(ent)
if cp:
return safe_unichr(cp)
else:
return match.group()
except:
# in case of errors, return original input
return match.group()
def handle_entityref(self, name):
cp = name2codepoint.get(name)
if cp:
self.__text.append(chr(cp))
else:
self.__text.append('&' + name)
def decode_xml_replacer(match):
name=match.group(1)
if(name.startswith("#")):
return chr(int(name[1:],16))
return chr(name2codepoint.get(name,'?'))
def handle_entityref(self, name):
"""Handle named entities of the form &aaaa; e.g. ’"""
if name in ['gt', 'lt', 'amp']:
self.handle_data("&%s;" % name)
else:
self.handle_data(chr(name2codepoint.get(name, "&%s;" % name)))
def handle_entityref(self, name):
cp = name2codepoint.get(name)
if cp:
self.__text.append(chr(cp))
else:
self.__text.append('&' + name)
def handle_entityref(self, name):
"""Handle named entities of the form &aaaa; e.g. ’"""
if name in ['gt', 'lt', 'amp']:
self.handle_data("&%s;" % name)
else:
self.handle_data(chr(name2codepoint.get(name, u"&%s;" % name)))
def char_from_entity(match):
code = name2codepoint.get(match.group(1), 0xFFFD)
return chr(code)
def convert_entities(s):
s = re.sub('&#(\d+);', lambda m: chr(int(m.groups(0)[0])), s)
return re.sub('&(\w)+;',
lambda m: n2cp.get(m.groups(0), '&%s;' % m.groups(0)[0]), s)
def handle_entityref(self, name):
num = name2codepoint.get(name)
if num is not None:
self.handle_charref(num)
