import collections
import re
import sys
import warnings
from bs4.dammit import EntitySubstitution
DEFAULT_OUTPUT_ENCODING = "utf-8"
PY3K = (sys.version_info[0] > 2)
whitespace_re = re.compile("\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(unicode):
def __new__(cls, prefix, name, namespace=None):
if name is None:
obj = unicode.__new__(cls, prefix)
elif prefix is None:
# Not really namespaced.
obj = unicode.__new__(cls, name)
else:
obj = unicode.__new__(cls, prefix + ":" + name)
obj.prefix = prefix
obj.name = name
obj.namespace = namespace
return obj
class AttributeValueWithCharsetSubstitution(unicode):
"""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 '<meta charset="utf8">', the
value of the 'charset' attribute will be one of these objects.
"""
def __new__(cls, original_value):
obj = unicode.__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:
<meta http-equiv="content-type" content="text/html; charset=utf8">
The value of the 'content' attribute will be one of these objects.
"""
CHARSET_RE = re.compile("((^|;)\s*charset=)([^;]*)", re.M)
def __new__(cls, original_value):
match = cls.CHARSET_RE.search(original_value)
if match is None:
# No substitution necessary.
return unicode.__new__(unicode, original_value)
obj = unicode.__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 <script> and <style> tags should not
undergo entity substitution.
Incoming NavigableString objects are checked to see if they're the
direct children of a <script> or <style> tag.
"""
cdata_containing_tags = set(["script", "style"])
preformatted_tags = set(["pre"])
@classmethod
def _substitute_if_appropriate(cls, ns, f):
if (isinstance(ns, NavigableString)
and ns.parent is not None
and ns.parent.name in cls.cdata_containing_tags):
# Do nothing.
return ns
# Substitute.
return f(ns)
@classmethod
def substitute_html(cls, ns):
return cls._substitute_if_appropriate(
ns, EntitySubstitution.substitute_html)
@classmethod
def substitute_xml(cls, ns):
return cls._substitute_if_appropriate(
ns, EntitySubstitution.substitute_xml)
class PageElement(object):
"""Contains the navigational information for some part of the page
(either a tag or a piece of text)"""
# There are five possible values for the "formatter" argument passed in
# to methods like encode() and prettify():
#
# "html" - All Unicode characters with corresponding HTML entities
# are converted to those entities on output.
# "minimal" - Bare ampersands and angle brackets are converted to
# XML entities: & < >
# None - The null formatter. Unicode characters are never
# converted to entities. This is not recommended, but it's
# faster than "minimal".
# A function - This function will be called on every string that
# needs to undergo entity substitution.
#
# In an HTML document, the default "html" and "minimal" functions
# will leave the contents of <script> and <style> tags alone. For
# an XML document, all tags will be given the same treatment.
HTML_FORMATTERS = {
"html" : HTMLAwareEntitySubstitution.substitute_html,
"minimal" : HTMLAwareEntitySubstitution.substitute_xml,
None : None
}
XML_FORMATTERS = {
"html" : EntitySubstitution.substitute_html,
"minimal" : EntitySubstitution.substitute_xml,
None : None
}
def format_string(self, s, formatter='minimal'):
"""Format the given string using the given formatter."""
if not callable(formatter):
formatter = self._formatter_for_name(formatter)
if formatter is None:
output = s
else:
output = formatter(s)
return output
@property
def _is_xml(self):
"""Is this element part of an XML tree or an HTML tree?
This is used when mapping a formatter name ("minimal") to an
appropriate function (one that performs entity-substitution on
the contents of <script> and <style> tags, or not). It's
inefficient, but it should be called very rarely.
"""
if self.parent is None:
# This is the top-level object. It should have .is_xml set
# from tree creation. If not, take a guess--BS is usually
# used on HTML markup.
return getattr(self, 'is_xml', False)
return self.parent._is_xml
def _formatter_for_name(self, name):
"Look up a formatter function based on its name and the tree."
if self._is_xml:
return self.XML_FORMATTERS.get(
name, EntitySubstitution.substitute_xml)
else:
return self.HTML_FORMATTERS.get(
name, HTMLAwareEntitySubstitution.substitute_xml)
def setup(self, parent=None, previous_element=None):
"""Sets up the initial relations between this element and
other elements."""
self.parent = parent
self.previous_element = previous_element
if previous_element is not None:
self.previous_element.next_element = self
self.next_element = None
self.previous_sibling = None
self.next_sibling = None
if self.parent is not None and self.parent.contents:
self.previous_sibling = self.parent.contents[-1]
self.previous_sibling.next_sibling = self
nextSibling = _alias("next_sibling") # BS3
previousSibling = _alias("previous_sibling") # BS3
def replace_with(self, replace_with):
if replace_with is self:
return
if replace_with is self.parent:
raise ValueError("Cannot replace a Tag with its parent.")
old_parent = self.parent
my_index = self.parent.index(self)
self.extract()
old_parent.insert(my_index, replace_with)
return self
replaceWith = replace_with # BS3
def unwrap(self):
my_parent = self.parent
my_index = self.parent.index(self)
self.extract()
for child in reversed(self.contents[:]):
my_parent.insert(my_index, child)
return self
replace_with_children = unwrap
replaceWithChildren = unwrap # BS3
def wrap(self, wrap_inside):
me = self.replace_with(wrap_inside)
wrap_inside.append(me)
return wrap_inside
def extract(self):
"""Destructively rips this element out of the tree."""
if self.parent is not None:
del self.parent.contents[self.parent.index(self)]
#Find the two elements that would be next to each other if
#this element (and any children) hadn't been parsed. Connect
#the two.
last_child = self._last_descendant()
next_element = last_child.next_element
if self.previous_element is not None:
self.previous_element.next_element = next_element
if next_element is not None:
next_element.previous_element = self.previous_element
self.previous_element = None
last_child.next_element = None
self.parent = None
if self.previous_sibling is not None:
self.previous_sibling.next_sibling = self.next_sibling
if self.next_sibling is not None:
self.next_sibling.previous_sibling = self.previous_sibling
self.previous_sibling = self.next_sibling = None
return self
def _last_descendant(self, is_initialized=True, accept_self=True):
"Finds the last element beneath this object to be parsed."
if is_initialized and self.next_sibling:
last_child = self.next_sibling.previous_element
else:
last_child = self
while isinstance(last_child, Tag) and last_child.contents:
last_child = last_child.contents[-1]
if not accept_self and last_child == self:
last_child = None
return last_child
# BS3: Not part of the API!
_lastRecursiveChild = _last_descendant
def insert(self, position, new_child):
if new_child is self:
raise ValueError("Cannot insert a tag into itself.")
if (isinstance(new_child, basestring)
and not isinstance(new_child, NavigableString)):
new_child = NavigableString(new_child)
position = min(position, len(self.contents))
if hasattr(new_child, 'parent') and new_child.parent is not None:
# We're 'inserting' an element that's already one
# of this object's children.
if new_child.parent is self:
current_index = self.index(new_child)
if current_index < position:
# We're moving this element further down the list
# of this object's children. That means that when
# we extract this element, our target index will
# jump down one.
position -= 1
new_child.extract()
new_child.parent = self
previous_child = None
if position == 0:
new_child.previous_sibling = None
new_child.previous_element = self
else:
previous_child = self.contents[position - 1]
new_child.previous_sibling = previous_child
new_child.previous_sibling.next_sibling = new_child
new_child.previous_element = previous_child._last_descendant(False)
if new_child.previous_element is not None:
new_child.previous_element.next_element = new_child
new_childs_last_element = new_child._last_descendant(False)
if position >= len(self.contents):
new_child.next_sibling = None
parent = self
parents_next_sibling = None
while parents_next_sibling is None and parent is not None:
parents_next_sibling = parent.next_sibling
parent = parent.parent
if parents_next_sibling is not None:
# We found the element that comes next in the document.
break
if parents_next_sibling is not None:
new_childs_last_element.next_element = parents_next_sibling
else:
# The last element of this tag is the last element in
# the document.
new_childs_last_element.next_element = None
else:
next_child = self.contents[position]
new_child.next_sibling = next_child
if new_child.next_sibling is not None:
new_child.next_sibling.previous_sibling = new_child
new_childs_last_element.next_element = next_child
if new_childs_last_element.next_element is not None:
new_childs_last_element.next_element.previous_element = new_childs_last_element
self.contents.insert(position, new_child)
def append(self, tag):
"""Appends the given tag to the contents of this tag."""
self.insert(len(self.contents), tag)
def insert_before(self, predecessor):
"""Makes the given element the immediate predecessor of this one.
The two elements will have the same parent, and the given element
will be immediately before this one.
"""
Loading ...