# Use of this source code is governed by a BSD-style license that can be # found in the LICENSE file. __license__ = "MIT" try: from collections.abc import Callable # Python 3.6 except ImportError as e: from collections import Callable import re import shlex import sys import warnings from bs4.dammit import EntitySubstitution DEFAULT_OUTPUT_ENCODING = "utf-8" PY3K = (sys.version_info[0] > 2) whitespace_re = re.compile(r"\s+") def _alias(attr): """Alias one attribute name to another for backward compatibility""" @property def alias(self): return getattr(self, attr) @alias.setter def alias(self): return setattr(self, attr) return alias class NamespacedAttribute(str): def __new__(cls, prefix, name, namespace=None): if name is None: obj = str.__new__(cls, prefix) elif prefix is None: # Not really namespaced. obj = str.__new__(cls, name) else: obj = str.__new__(cls, prefix + ":" + name) obj.prefix = prefix obj.name = name obj.namespace = namespace return obj class AttributeValueWithCharsetSubstitution(str): """A stand-in object for a character encoding specified in HTML.""" class CharsetMetaAttributeValue(AttributeValueWithCharsetSubstitution): """A generic stand-in for the value of a meta tag's 'charset' attribute. When Beautiful Soup parses the markup '', the value of the 'charset' attribute will be one of these objects. """ def __new__(cls, original_value): obj = str.__new__(cls, original_value) obj.original_value = original_value return obj def encode(self, encoding): return encoding class ContentMetaAttributeValue(AttributeValueWithCharsetSubstitution): """A generic stand-in for the value of a meta tag's 'content' attribute. When Beautiful Soup parses the markup: The value of the 'content' attribute will be one of these objects. """ CHARSET_RE = re.compile(r"((^|;)\s*charset=)([^;]*)", re.M) def __new__(cls, original_value): match = cls.CHARSET_RE.search(original_value) if match is None: # No substitution necessary. return str.__new__(str, original_value) obj = str.__new__(cls, original_value) obj.original_value = original_value return obj def encode(self, encoding): def rewrite(match): return match.group(1) + encoding return self.CHARSET_RE.sub(rewrite, self.original_value) class HTMLAwareEntitySubstitution(EntitySubstitution): """Entity substitution rules that are aware of some HTML quirks. Specifically, the contents of