1604 lines
58 KiB
Python
1604 lines
58 KiB
Python
# Use of this source code is governed by the MIT license.
|
|
__license__ = "MIT"
|
|
|
|
try:
|
|
from collections.abc import Callable # Python 3.6
|
|
except ImportError as e:
|
|
from collections import Callable
|
|
import re
|
|
import sys
|
|
import warnings
|
|
import collections
|
|
try:
|
|
import soupsieve
|
|
except ImportError as e:
|
|
soupsieve = None
|
|
warnings.warn(
|
|
'The soupsieve package is not installed. CSS selectors cannot be used.'
|
|
)
|
|
|
|
from bs4.formatter import (
|
|
Formatter,
|
|
HTMLFormatter,
|
|
XMLFormatter,
|
|
)
|
|
|
|
DEFAULT_OUTPUT_ENCODING = "utf-8"
|
|
PY3K = (sys.version_info[0] > 2)
|
|
|
|
nonwhitespace_re = re.compile(r"\S+")
|
|
|
|
# NOTE: This isn't used as of 4.7.0. I'm leaving it for a little bit on
|
|
# the off chance someone imported it for their own use.
|
|
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=None, namespace=None):
|
|
if not name:
|
|
# This is the default namespace. Its name "has no value"
|
|
# per https://www.w3.org/TR/xml-names/#defaulting
|
|
name = 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 '<meta charset="utf8">', 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:
|
|
<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(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 PageElement(object):
|
|
"""Contains the navigational information for some part of the page
|
|
(either a tag or a piece of text)"""
|
|
|
|
def setup(self, parent=None, previous_element=None, next_element=None,
|
|
previous_sibling=None, next_sibling=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 = next_element
|
|
if self.next_element is not None:
|
|
self.next_element.previous_element = self
|
|
|
|
self.next_sibling = next_sibling
|
|
if self.next_sibling is not None:
|
|
self.next_sibling.previous_sibling = self
|
|
|
|
if (previous_sibling is None
|
|
and self.parent is not None and self.parent.contents):
|
|
previous_sibling = self.parent.contents[-1]
|
|
|
|
self.previous_sibling = previous_sibling
|
|
if previous_sibling is not None:
|
|
self.previous_sibling.next_sibling = self
|
|
|
|
def format_string(self, s, formatter):
|
|
"""Format the given string using the given formatter."""
|
|
if formatter is None:
|
|
return s
|
|
if not isinstance(formatter, Formatter):
|
|
formatter = self.formatter_for_name(formatter)
|
|
output = formatter.substitute(s)
|
|
return output
|
|
|
|
def formatter_for_name(self, formatter):
|
|
"""Look up or create a Formatter for the given identifier,
|
|
if necessary.
|
|
|
|
:param formatter: Can be a Formatter object (used as-is), a
|
|
function (used as the entity substitution hook for an
|
|
XMLFormatter or HTMLFormatter), or a string (used to look up
|
|
an XMLFormatter or HTMLFormatter in the appropriate registry.
|
|
"""
|
|
if isinstance(formatter, Formatter):
|
|
return formatter
|
|
if self._is_xml:
|
|
c = XMLFormatter
|
|
else:
|
|
c = HTMLFormatter
|
|
if isinstance(formatter, collections.Callable):
|
|
return c(entity_substitution=formatter)
|
|
return c.REGISTRY[formatter]
|
|
|
|
@property
|
|
def _is_xml(self):
|
|
"""Is this element part of an XML tree or an HTML tree?
|
|
|
|
This is used in formatter_for_name, when deciding whether an
|
|
XMLFormatter or HTMLFormatter is more appropriate. It can be
|
|
inefficient, but it should be called very rarely.
|
|
"""
|
|
if self.known_xml is not None:
|
|
# Most of the time we will have determined this when the
|
|
# document is parsed.
|
|
return self.known_xml
|
|
|
|
# Otherwise, it's likely that this element was created by
|
|
# direct invocation of the constructor from within the user's
|
|
# Python code.
|
|
if self.parent is None:
|
|
# This is the top-level object. It should have .known_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
|
|
|
|
nextSibling = _alias("next_sibling") # BS3
|
|
previousSibling = _alias("previous_sibling") # BS3
|
|
|
|
def replace_with(self, replace_with):
|
|
if self.parent is None:
|
|
raise ValueError(
|
|
"Cannot replace one element with another when the "
|
|
"element to be replaced is not part of a tree.")
|
|
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
|
|
if self.parent is None:
|
|
raise ValueError(
|
|
"Cannot replace an element with its contents when that"
|
|
"element is not part of a tree.")
|
|
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 and
|
|
self.previous_element is not next_element):
|
|
self.previous_element.next_element = next_element
|
|
if next_element is not None and next_element is not self.previous_element:
|
|
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
|
|
and self.previous_sibling is not self.next_sibling):
|
|
self.previous_sibling.next_sibling = self.next_sibling
|
|
if (self.next_sibling is not None
|
|
and self.next_sibling is not self.previous_sibling):
|
|
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 is not None:
|
|
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 is 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 None:
|
|
raise ValueError("Cannot insert None into a tag.")
|
|
if new_child is self:
|
|
raise ValueError("Cannot insert a tag into itself.")
|
|
if (isinstance(new_child, str)
|
|
and not isinstance(new_child, NavigableString)):
|
|
new_child = NavigableString(new_child)
|
|
|
|
from bs4 import BeautifulSoup
|
|
if isinstance(new_child, BeautifulSoup):
|
|
# We don't want to end up with a situation where one BeautifulSoup
|
|
# object contains another. Insert the children one at a time.
|
|
for subchild in list(new_child.contents):
|
|
self.insert(position, subchild)
|
|
position += 1
|
|
return
|
|
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 extend(self, tags):
|
|
"""Appends the given tags to the contents of this tag."""
|
|
for tag in tags:
|
|
self.append(tag)
|
|
|
|
def insert_before(self, *args):
|
|
"""Makes the given element(s) the immediate predecessor of this one.
|
|
|
|
The elements will have the same parent, and the given elements
|
|
will be immediately before this one.
|
|
"""
|
|
parent = self.parent
|
|
if parent is None:
|
|
raise ValueError(
|
|
"Element has no parent, so 'before' has no meaning.")
|
|
if any(x is self for x in args):
|
|
raise ValueError("Can't insert an element before itself.")
|
|
for predecessor in args:
|
|
# Extract first so that the index won't be screwed up if they
|
|
# are siblings.
|
|
if isinstance(predecessor, PageElement):
|
|
predecessor.extract()
|
|
index = parent.index(self)
|
|
parent.insert(index, predecessor)
|
|
|
|
def insert_after(self, *args):
|
|
"""Makes the given element(s) the immediate successor of this one.
|
|
|
|
The elements will have the same parent, and the given elements
|
|
will be immediately after this one.
|
|
"""
|
|
# Do all error checking before modifying the tree.
|
|
parent = self.parent
|
|
if parent is None:
|
|
raise ValueError(
|
|
"Element has no parent, so 'after' has no meaning.")
|
|
if any(x is self for x in args):
|
|
raise ValueError("Can't insert an element after itself.")
|
|
|
|
offset = 0
|
|
for successor in args:
|
|
# Extract first so that the index won't be screwed up if they
|
|
# are siblings.
|
|
if isinstance(successor, PageElement):
|
|
successor.extract()
|
|
index = parent.index(self)
|
|
parent.insert(index+1+offset, successor)
|
|
offset += 1
|
|
|
|
def find_next(self, name=None, attrs={}, text=None, **kwargs):
|
|
"""Returns the first item that matches the given criteria and
|
|
appears after this Tag in the document."""
|
|
return self._find_one(self.find_all_next, name, attrs, text, **kwargs)
|
|
findNext = find_next # BS3
|
|
|
|
def find_all_next(self, name=None, attrs={}, text=None, limit=None,
|
|
**kwargs):
|
|
"""Returns all items that match the given criteria and appear
|
|
after this Tag in the document."""
|
|
return self._find_all(name, attrs, text, limit, self.next_elements,
|
|
**kwargs)
|
|
findAllNext = find_all_next # BS3
|
|
|
|
def find_next_sibling(self, name=None, attrs={}, text=None, **kwargs):
|
|
"""Returns the closest sibling to this Tag that matches the
|
|
given criteria and appears after this Tag in the document."""
|
|
return self._find_one(self.find_next_siblings, name, attrs, text,
|
|
**kwargs)
|
|
findNextSibling = find_next_sibling # BS3
|
|
|
|
def find_next_siblings(self, name=None, attrs={}, text=None, limit=None,
|
|
**kwargs):
|
|
"""Returns the siblings of this Tag that match the given
|
|
criteria and appear after this Tag in the document."""
|
|
return self._find_all(name, attrs, text, limit,
|
|
self.next_siblings, **kwargs)
|
|
findNextSiblings = find_next_siblings # BS3
|
|
fetchNextSiblings = find_next_siblings # BS2
|
|
|
|
def find_previous(self, name=None, attrs={}, text=None, **kwargs):
|
|
"""Returns the first item that matches the given criteria and
|
|
appears before this Tag in the document."""
|
|
return self._find_one(
|
|
self.find_all_previous, name, attrs, text, **kwargs)
|
|
findPrevious = find_previous # BS3
|
|
|
|
def find_all_previous(self, name=None, attrs={}, text=None, limit=None,
|
|
**kwargs):
|
|
"""Returns all items that match the given criteria and appear
|
|
before this Tag in the document."""
|
|
return self._find_all(name, attrs, text, limit, self.previous_elements,
|
|
**kwargs)
|
|
findAllPrevious = find_all_previous # BS3
|
|
fetchPrevious = find_all_previous # BS2
|
|
|
|
def find_previous_sibling(self, name=None, attrs={}, text=None, **kwargs):
|
|
"""Returns the closest sibling to this Tag that matches the
|
|
given criteria and appears before this Tag in the document."""
|
|
return self._find_one(self.find_previous_siblings, name, attrs, text,
|
|
**kwargs)
|
|
findPreviousSibling = find_previous_sibling # BS3
|
|
|
|
def find_previous_siblings(self, name=None, attrs={}, text=None,
|
|
limit=None, **kwargs):
|
|
"""Returns the siblings of this Tag that match the given
|
|
criteria and appear before this Tag in the document."""
|
|
return self._find_all(name, attrs, text, limit,
|
|
self.previous_siblings, **kwargs)
|
|
findPreviousSiblings = find_previous_siblings # BS3
|
|
fetchPreviousSiblings = find_previous_siblings # BS2
|
|
|
|
def find_parent(self, name=None, attrs={}, **kwargs):
|
|
"""Returns the closest parent of this Tag that matches the given
|
|
criteria."""
|
|
# NOTE: We can't use _find_one because findParents takes a different
|
|
# set of arguments.
|
|
r = None
|
|
l = self.find_parents(name, attrs, 1, **kwargs)
|
|
if l:
|
|
r = l[0]
|
|
return r
|
|
findParent = find_parent # BS3
|
|
|
|
def find_parents(self, name=None, attrs={}, limit=None, **kwargs):
|
|
"""Returns the parents of this Tag that match the given
|
|
criteria."""
|
|
|
|
return self._find_all(name, attrs, None, limit, self.parents,
|
|
**kwargs)
|
|
findParents = find_parents # BS3
|
|
fetchParents = find_parents # BS2
|
|
|
|
@property
|
|
def next(self):
|
|
return self.next_element
|
|
|
|
@property
|
|
def previous(self):
|
|
return self.previous_element
|
|
|
|
#These methods do the real heavy lifting.
|
|
|
|
def _find_one(self, method, name, attrs, text, **kwargs):
|
|
r = None
|
|
l = method(name, attrs, text, 1, **kwargs)
|
|
if l:
|
|
r = l[0]
|
|
return r
|
|
|
|
def _find_all(self, name, attrs, text, limit, generator, **kwargs):
|
|
"Iterates over a generator looking for things that match."
|
|
|
|
if text is None and 'string' in kwargs:
|
|
text = kwargs['string']
|
|
del kwargs['string']
|
|
|
|
if isinstance(name, SoupStrainer):
|
|
strainer = name
|
|
else:
|
|
strainer = SoupStrainer(name, attrs, text, **kwargs)
|
|
|
|
if text is None and not limit and not attrs and not kwargs:
|
|
if name is True or name is None:
|
|
# Optimization to find all tags.
|
|
result = (element for element in generator
|
|
if isinstance(element, Tag))
|
|
return ResultSet(strainer, result)
|
|
elif isinstance(name, str):
|
|
# Optimization to find all tags with a given name.
|
|
if name.count(':') == 1:
|
|
# This is a name with a prefix. If this is a namespace-aware document,
|
|
# we need to match the local name against tag.name. If not,
|
|
# we need to match the fully-qualified name against tag.name.
|
|
prefix, local_name = name.split(':', 1)
|
|
else:
|
|
prefix = None
|
|
local_name = name
|
|
result = (element for element in generator
|
|
if isinstance(element, Tag)
|
|
and (
|
|
element.name == name
|
|
) or (
|
|
element.name == local_name
|
|
and (prefix is None or element.prefix == prefix)
|
|
)
|
|
)
|
|
return ResultSet(strainer, result)
|
|
results = ResultSet(strainer)
|
|
while True:
|
|
try:
|
|
i = next(generator)
|
|
except StopIteration:
|
|
break
|
|
if i:
|
|
found = strainer.search(i)
|
|
if found:
|
|
results.append(found)
|
|
if limit and len(results) >= limit:
|
|
break
|
|
return results
|
|
|
|
#These generators can be used to navigate starting from both
|
|
#NavigableStrings and Tags.
|
|
@property
|
|
def next_elements(self):
|
|
i = self.next_element
|
|
while i is not None:
|
|
yield i
|
|
i = i.next_element
|
|
|
|
@property
|
|
def next_siblings(self):
|
|
i = self.next_sibling
|
|
while i is not None:
|
|
yield i
|
|
i = i.next_sibling
|
|
|
|
@property
|
|
def previous_elements(self):
|
|
i = self.previous_element
|
|
while i is not None:
|
|
yield i
|
|
i = i.previous_element
|
|
|
|
@property
|
|
def previous_siblings(self):
|
|
i = self.previous_sibling
|
|
while i is not None:
|
|
yield i
|
|
i = i.previous_sibling
|
|
|
|
@property
|
|
def parents(self):
|
|
i = self.parent
|
|
while i is not None:
|
|
yield i
|
|
i = i.parent
|
|
|
|
# Old non-property versions of the generators, for backwards
|
|
# compatibility with BS3.
|
|
def nextGenerator(self):
|
|
return self.next_elements
|
|
|
|
def nextSiblingGenerator(self):
|
|
return self.next_siblings
|
|
|
|
def previousGenerator(self):
|
|
return self.previous_elements
|
|
|
|
def previousSiblingGenerator(self):
|
|
return self.previous_siblings
|
|
|
|
def parentGenerator(self):
|
|
return self.parents
|
|
|
|
|
|
class NavigableString(str, PageElement):
|
|
|
|
PREFIX = ''
|
|
SUFFIX = ''
|
|
|
|
# We can't tell just by looking at a string whether it's contained
|
|
# in an XML document or an HTML document.
|
|
|
|
known_xml = None
|
|
|
|
def __new__(cls, value):
|
|
"""Create a new NavigableString.
|
|
|
|
When unpickling a NavigableString, this method is called with
|
|
the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be
|
|
passed in to the superclass's __new__ or the superclass won't know
|
|
how to handle non-ASCII characters.
|
|
"""
|
|
if isinstance(value, str):
|
|
u = str.__new__(cls, value)
|
|
else:
|
|
u = str.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
|
|
u.setup()
|
|
return u
|
|
|
|
def __copy__(self):
|
|
"""A copy of a NavigableString has the same contents and class
|
|
as the original, but it is not connected to the parse tree.
|
|
"""
|
|
return type(self)(self)
|
|
|
|
def __getnewargs__(self):
|
|
return (str(self),)
|
|
|
|
def __getattr__(self, attr):
|
|
"""text.string gives you text. This is for backwards
|
|
compatibility for Navigable*String, but for CData* it lets you
|
|
get the string without the CData wrapper."""
|
|
if attr == 'string':
|
|
return self
|
|
else:
|
|
raise AttributeError(
|
|
"'%s' object has no attribute '%s'" % (
|
|
self.__class__.__name__, attr))
|
|
|
|
def output_ready(self, formatter="minimal"):
|
|
"""Run the string through the provided formatter."""
|
|
output = self.format_string(self, formatter)
|
|
return self.PREFIX + output + self.SUFFIX
|
|
|
|
@property
|
|
def name(self):
|
|
return None
|
|
|
|
@name.setter
|
|
def name(self, name):
|
|
raise AttributeError("A NavigableString cannot be given a name.")
|
|
|
|
class PreformattedString(NavigableString):
|
|
"""A NavigableString not subject to the normal formatting rules.
|
|
|
|
The string will be passed into the formatter (to trigger side effects),
|
|
but the return value will be ignored.
|
|
"""
|
|
|
|
def output_ready(self, formatter=None):
|
|
"""CData strings are passed into the formatter, purely
|
|
for any side effects. The return value is ignored.
|
|
"""
|
|
if formatter is not None:
|
|
ignore = self.format_string(self, formatter)
|
|
return self.PREFIX + self + self.SUFFIX
|
|
|
|
class CData(PreformattedString):
|
|
|
|
PREFIX = '<![CDATA['
|
|
SUFFIX = ']]>'
|
|
|
|
class ProcessingInstruction(PreformattedString):
|
|
"""A SGML processing instruction."""
|
|
|
|
PREFIX = '<?'
|
|
SUFFIX = '>'
|
|
|
|
class XMLProcessingInstruction(ProcessingInstruction):
|
|
"""An XML processing instruction."""
|
|
PREFIX = '<?'
|
|
SUFFIX = '?>'
|
|
|
|
class Comment(PreformattedString):
|
|
|
|
PREFIX = '<!--'
|
|
SUFFIX = '-->'
|
|
|
|
|
|
class Declaration(PreformattedString):
|
|
PREFIX = '<?'
|
|
SUFFIX = '?>'
|
|
|
|
|
|
class Doctype(PreformattedString):
|
|
|
|
@classmethod
|
|
def for_name_and_ids(cls, name, pub_id, system_id):
|
|
value = name or ''
|
|
if pub_id is not None:
|
|
value += ' PUBLIC "%s"' % pub_id
|
|
if system_id is not None:
|
|
value += ' "%s"' % system_id
|
|
elif system_id is not None:
|
|
value += ' SYSTEM "%s"' % system_id
|
|
|
|
return Doctype(value)
|
|
|
|
PREFIX = '<!DOCTYPE '
|
|
SUFFIX = '>\n'
|
|
|
|
|
|
class Tag(PageElement):
|
|
|
|
"""Represents a found HTML tag with its attributes and contents."""
|
|
|
|
def __init__(self, parser=None, builder=None, name=None, namespace=None,
|
|
prefix=None, attrs=None, parent=None, previous=None,
|
|
is_xml=None, sourceline=None, sourcepos=None,
|
|
can_be_empty_element=None, cdata_list_attributes=None,
|
|
preserve_whitespace_tags=None
|
|
):
|
|
"Basic constructor."
|
|
|
|
if parser is None:
|
|
self.parser_class = None
|
|
else:
|
|
# We don't actually store the parser object: that lets extracted
|
|
# chunks be garbage-collected.
|
|
self.parser_class = parser.__class__
|
|
if name is None:
|
|
raise ValueError("No value provided for new tag's name.")
|
|
self.name = name
|
|
self.namespace = namespace
|
|
self.prefix = prefix
|
|
if ((not builder or builder.store_line_numbers)
|
|
and (sourceline is not None or sourcepos is not None)):
|
|
self.sourceline = sourceline
|
|
self.sourcepos = sourcepos
|
|
if attrs is None:
|
|
attrs = {}
|
|
elif attrs:
|
|
if builder is not None and builder.cdata_list_attributes:
|
|
attrs = builder._replace_cdata_list_attribute_values(
|
|
self.name, attrs)
|
|
else:
|
|
attrs = dict(attrs)
|
|
else:
|
|
attrs = dict(attrs)
|
|
|
|
# If possible, determine ahead of time whether this tag is an
|
|
# XML tag.
|
|
if builder:
|
|
self.known_xml = builder.is_xml
|
|
else:
|
|
self.known_xml = is_xml
|
|
self.attrs = attrs
|
|
self.contents = []
|
|
self.setup(parent, previous)
|
|
self.hidden = False
|
|
|
|
if builder is None:
|
|
# In the absence of a TreeBuilder, use whatever values were
|
|
# passed in here. They're probably None, unless this is a copy of some
|
|
# other tag.
|
|
self.can_be_empty_element = can_be_empty_element
|
|
self.cdata_list_attributes = cdata_list_attributes
|
|
self.preserve_whitespace_tags = preserve_whitespace_tags
|
|
else:
|
|
# Set up any substitutions for this tag, such as the charset in a META tag.
|
|
builder.set_up_substitutions(self)
|
|
|
|
# Ask the TreeBuilder whether this tag might be an empty-element tag.
|
|
self.can_be_empty_element = builder.can_be_empty_element(name)
|
|
|
|
# Keep track of the list of attributes of this tag that
|
|
# might need to be treated as a list.
|
|
#
|
|
# For performance reasons, we store the whole data structure
|
|
# rather than asking the question of every tag. Asking would
|
|
# require building a new data structure every time, and
|
|
# (unlike can_be_empty_element), we almost never need
|
|
# to check this.
|
|
self.cdata_list_attributes = builder.cdata_list_attributes
|
|
|
|
# Keep track of the names that might cause this tag to be treated as a
|
|
# whitespace-preserved tag.
|
|
self.preserve_whitespace_tags = builder.preserve_whitespace_tags
|
|
|
|
parserClass = _alias("parser_class") # BS3
|
|
|
|
def __copy__(self):
|
|
"""A copy of a Tag is a new Tag, unconnected to the parse tree.
|
|
Its contents are a copy of the old Tag's contents.
|
|
"""
|
|
clone = type(self)(
|
|
None, self.builder, self.name, self.namespace,
|
|
self.prefix, self.attrs, is_xml=self._is_xml,
|
|
sourceline=self.sourceline, sourcepos=self.sourcepos,
|
|
can_be_empty_element=self.can_be_empty_element,
|
|
cdata_list_attributes=self.cdata_list_attributes,
|
|
preserve_whitespace_tags=self.preserve_whitespace_tags
|
|
)
|
|
for attr in ('can_be_empty_element', 'hidden'):
|
|
setattr(clone, attr, getattr(self, attr))
|
|
for child in self.contents:
|
|
clone.append(child.__copy__())
|
|
return clone
|
|
|
|
@property
|
|
def is_empty_element(self):
|
|
"""Is this tag an empty-element tag? (aka a self-closing tag)
|
|
|
|
A tag that has contents is never an empty-element tag.
|
|
|
|
A tag that has no contents may or may not be an empty-element
|
|
tag. It depends on the builder used to create the tag. If the
|
|
builder has a designated list of empty-element tags, then only
|
|
a tag whose name shows up in that list is considered an
|
|
empty-element tag.
|
|
|
|
If the builder has no designated list of empty-element tags,
|
|
then any tag with no contents is an empty-element tag.
|
|
"""
|
|
return len(self.contents) == 0 and self.can_be_empty_element
|
|
isSelfClosing = is_empty_element # BS3
|
|
|
|
@property
|
|
def string(self):
|
|
"""Convenience property to get the single string within this tag.
|
|
|
|
:Return: If this tag has a single string child, return value
|
|
is that string. If this tag has no children, or more than one
|
|
child, return value is None. If this tag has one child tag,
|
|
return value is the 'string' attribute of the child tag,
|
|
recursively.
|
|
"""
|
|
if len(self.contents) != 1:
|
|
return None
|
|
child = self.contents[0]
|
|
if isinstance(child, NavigableString):
|
|
return child
|
|
return child.string
|
|
|
|
@string.setter
|
|
def string(self, string):
|
|
self.clear()
|
|
self.append(string.__class__(string))
|
|
|
|
def _all_strings(self, strip=False, types=(NavigableString, CData)):
|
|
"""Yield all strings of certain classes, possibly stripping them.
|
|
|
|
By default, yields only NavigableString and CData objects. So
|
|
no comments, processing instructions, etc.
|
|
"""
|
|
for descendant in self.descendants:
|
|
if (
|
|
(types is None and not isinstance(descendant, NavigableString))
|
|
or
|
|
(types is not None and type(descendant) not in types)):
|
|
continue
|
|
if strip:
|
|
descendant = descendant.strip()
|
|
if len(descendant) == 0:
|
|
continue
|
|
yield descendant
|
|
|
|
strings = property(_all_strings)
|
|
|
|
@property
|
|
def stripped_strings(self):
|
|
for string in self._all_strings(True):
|
|
yield string
|
|
|
|
def get_text(self, separator="", strip=False,
|
|
types=(NavigableString, CData)):
|
|
"""
|
|
Get all child strings, concatenated using the given separator.
|
|
"""
|
|
return separator.join([s for s in self._all_strings(
|
|
strip, types=types)])
|
|
getText = get_text
|
|
text = property(get_text)
|
|
|
|
def decompose(self):
|
|
"""Recursively destroys the contents of this tree."""
|
|
self.extract()
|
|
i = self
|
|
while i is not None:
|
|
next = i.next_element
|
|
i.__dict__.clear()
|
|
i.contents = []
|
|
i = next
|
|
|
|
def clear(self, decompose=False):
|
|
"""
|
|
Extract all children. If decompose is True, decompose instead.
|
|
"""
|
|
if decompose:
|
|
for element in self.contents[:]:
|
|
if isinstance(element, Tag):
|
|
element.decompose()
|
|
else:
|
|
element.extract()
|
|
else:
|
|
for element in self.contents[:]:
|
|
element.extract()
|
|
|
|
def smooth(self):
|
|
"""Smooth out this element's children by consolidating consecutive strings.
|
|
|
|
This makes pretty-printed output look more natural following a
|
|
lot of operations that modified the tree.
|
|
"""
|
|
# Mark the first position of every pair of children that need
|
|
# to be consolidated. Do this rather than making a copy of
|
|
# self.contents, since in most cases very few strings will be
|
|
# affected.
|
|
marked = []
|
|
for i, a in enumerate(self.contents):
|
|
if isinstance(a, Tag):
|
|
# Recursively smooth children.
|
|
a.smooth()
|
|
if i == len(self.contents)-1:
|
|
# This is the last item in .contents, and it's not a
|
|
# tag. There's no chance it needs any work.
|
|
continue
|
|
b = self.contents[i+1]
|
|
if (isinstance(a, NavigableString)
|
|
and isinstance(b, NavigableString)
|
|
and not isinstance(a, PreformattedString)
|
|
and not isinstance(b, PreformattedString)
|
|
):
|
|
marked.append(i)
|
|
|
|
# Go over the marked positions in reverse order, so that
|
|
# removing items from .contents won't affect the remaining
|
|
# positions.
|
|
for i in reversed(marked):
|
|
a = self.contents[i]
|
|
b = self.contents[i+1]
|
|
b.extract()
|
|
n = NavigableString(a+b)
|
|
a.replace_with(n)
|
|
|
|
def index(self, element):
|
|
"""
|
|
Find the index of a child by identity, not value. Avoids issues with
|
|
tag.contents.index(element) getting the index of equal elements.
|
|
"""
|
|
for i, child in enumerate(self.contents):
|
|
if child is element:
|
|
return i
|
|
raise ValueError("Tag.index: element not in tag")
|
|
|
|
def get(self, key, default=None):
|
|
"""Returns the value of the 'key' attribute for the tag, or
|
|
the value given for 'default' if it doesn't have that
|
|
attribute."""
|
|
return self.attrs.get(key, default)
|
|
|
|
def get_attribute_list(self, key, default=None):
|
|
"""The same as get(), but always returns a list."""
|
|
value = self.get(key, default)
|
|
if not isinstance(value, list):
|
|
value = [value]
|
|
return value
|
|
|
|
def has_attr(self, key):
|
|
return key in self.attrs
|
|
|
|
def __hash__(self):
|
|
return str(self).__hash__()
|
|
|
|
def __getitem__(self, key):
|
|
"""tag[key] returns the value of the 'key' attribute for the tag,
|
|
and throws an exception if it's not there."""
|
|
return self.attrs[key]
|
|
|
|
def __iter__(self):
|
|
"Iterating over a tag iterates over its contents."
|
|
return iter(self.contents)
|
|
|
|
def __len__(self):
|
|
"The length of a tag is the length of its list of contents."
|
|
return len(self.contents)
|
|
|
|
def __contains__(self, x):
|
|
return x in self.contents
|
|
|
|
def __bool__(self):
|
|
"A tag is non-None even if it has no contents."
|
|
return True
|
|
|
|
def __setitem__(self, key, value):
|
|
"""Setting tag[key] sets the value of the 'key' attribute for the
|
|
tag."""
|
|
self.attrs[key] = value
|
|
|
|
def __delitem__(self, key):
|
|
"Deleting tag[key] deletes all 'key' attributes for the tag."
|
|
self.attrs.pop(key, None)
|
|
|
|
def __call__(self, *args, **kwargs):
|
|
"""Calling a tag like a function is the same as calling its
|
|
find_all() method. Eg. tag('a') returns a list of all the A tags
|
|
found within this tag."""
|
|
return self.find_all(*args, **kwargs)
|
|
|
|
def __getattr__(self, tag):
|
|
#print "Getattr %s.%s" % (self.__class__, tag)
|
|
if len(tag) > 3 and tag.endswith('Tag'):
|
|
# BS3: soup.aTag -> "soup.find("a")
|
|
tag_name = tag[:-3]
|
|
warnings.warn(
|
|
'.%(name)sTag is deprecated, use .find("%(name)s") instead. If you really were looking for a tag called %(name)sTag, use .find("%(name)sTag")' % dict(
|
|
name=tag_name
|
|
)
|
|
)
|
|
return self.find(tag_name)
|
|
# We special case contents to avoid recursion.
|
|
elif not tag.startswith("__") and not tag == "contents":
|
|
return self.find(tag)
|
|
raise AttributeError(
|
|
"'%s' object has no attribute '%s'" % (self.__class__, tag))
|
|
|
|
def __eq__(self, other):
|
|
"""Returns true iff this tag has the same name, the same attributes,
|
|
and the same contents (recursively) as the given tag."""
|
|
if self is other:
|
|
return True
|
|
if (not hasattr(other, 'name') or
|
|
not hasattr(other, 'attrs') or
|
|
not hasattr(other, 'contents') or
|
|
self.name != other.name or
|
|
self.attrs != other.attrs or
|
|
len(self) != len(other)):
|
|
return False
|
|
for i, my_child in enumerate(self.contents):
|
|
if my_child != other.contents[i]:
|
|
return False
|
|
return True
|
|
|
|
def __ne__(self, other):
|
|
"""Returns true iff this tag is not identical to the other tag,
|
|
as defined in __eq__."""
|
|
return not self == other
|
|
|
|
def __repr__(self, encoding="unicode-escape"):
|
|
"""Renders this tag as a string."""
|
|
if PY3K:
|
|
# "The return value must be a string object", i.e. Unicode
|
|
return self.decode()
|
|
else:
|
|
# "The return value must be a string object", i.e. a bytestring.
|
|
# By convention, the return value of __repr__ should also be
|
|
# an ASCII string.
|
|
return self.encode(encoding)
|
|
|
|
def __unicode__(self):
|
|
return self.decode()
|
|
|
|
def __str__(self):
|
|
if PY3K:
|
|
return self.decode()
|
|
else:
|
|
return self.encode()
|
|
|
|
if PY3K:
|
|
__str__ = __repr__ = __unicode__
|
|
|
|
def encode(self, encoding=DEFAULT_OUTPUT_ENCODING,
|
|
indent_level=None, formatter="minimal",
|
|
errors="xmlcharrefreplace"):
|
|
# Turn the data structure into Unicode, then encode the
|
|
# Unicode.
|
|
u = self.decode(indent_level, encoding, formatter)
|
|
return u.encode(encoding, errors)
|
|
|
|
def decode(self, indent_level=None,
|
|
eventual_encoding=DEFAULT_OUTPUT_ENCODING,
|
|
formatter="minimal"):
|
|
"""Returns a Unicode representation of this tag and its contents.
|
|
|
|
:param eventual_encoding: The tag is destined to be
|
|
encoded into this encoding. This method is _not_
|
|
responsible for performing that encoding. This information
|
|
is passed in so that it can be substituted in if the
|
|
document contains a <META> tag that mentions the document's
|
|
encoding.
|
|
"""
|
|
|
|
# First off, turn a non-Formatter `formatter` into a Formatter
|
|
# object. This will stop the lookup from happening over and
|
|
# over again.
|
|
if not isinstance(formatter, Formatter):
|
|
formatter = self.formatter_for_name(formatter)
|
|
attributes = formatter.attributes(self)
|
|
attrs = []
|
|
for key, val in attributes:
|
|
if val is None:
|
|
decoded = key
|
|
else:
|
|
if isinstance(val, list) or isinstance(val, tuple):
|
|
val = ' '.join(val)
|
|
elif not isinstance(val, str):
|
|
val = str(val)
|
|
elif (
|
|
isinstance(val, AttributeValueWithCharsetSubstitution)
|
|
and eventual_encoding is not None
|
|
):
|
|
val = val.encode(eventual_encoding)
|
|
|
|
text = formatter.attribute_value(val)
|
|
decoded = (
|
|
str(key) + '='
|
|
+ formatter.quoted_attribute_value(text))
|
|
attrs.append(decoded)
|
|
close = ''
|
|
closeTag = ''
|
|
|
|
prefix = ''
|
|
if self.prefix:
|
|
prefix = self.prefix + ":"
|
|
|
|
if self.is_empty_element:
|
|
close = formatter.void_element_close_prefix or ''
|
|
else:
|
|
closeTag = '</%s%s>' % (prefix, self.name)
|
|
|
|
pretty_print = self._should_pretty_print(indent_level)
|
|
space = ''
|
|
indent_space = ''
|
|
if indent_level is not None:
|
|
indent_space = (' ' * (indent_level - 1))
|
|
if pretty_print:
|
|
space = indent_space
|
|
indent_contents = indent_level + 1
|
|
else:
|
|
indent_contents = None
|
|
contents = self.decode_contents(
|
|
indent_contents, eventual_encoding, formatter
|
|
)
|
|
|
|
if self.hidden:
|
|
# This is the 'document root' object.
|
|
s = contents
|
|
else:
|
|
s = []
|
|
attribute_string = ''
|
|
if attrs:
|
|
attribute_string = ' ' + ' '.join(attrs)
|
|
if indent_level is not None:
|
|
# Even if this particular tag is not pretty-printed,
|
|
# we should indent up to the start of the tag.
|
|
s.append(indent_space)
|
|
s.append('<%s%s%s%s>' % (
|
|
prefix, self.name, attribute_string, close))
|
|
if pretty_print:
|
|
s.append("\n")
|
|
s.append(contents)
|
|
if pretty_print and contents and contents[-1] != "\n":
|
|
s.append("\n")
|
|
if pretty_print and closeTag:
|
|
s.append(space)
|
|
s.append(closeTag)
|
|
if indent_level is not None and closeTag and self.next_sibling:
|
|
# Even if this particular tag is not pretty-printed,
|
|
# we're now done with the tag, and we should add a
|
|
# newline if appropriate.
|
|
s.append("\n")
|
|
s = ''.join(s)
|
|
return s
|
|
|
|
def _should_pretty_print(self, indent_level):
|
|
"""Should this tag be pretty-printed?"""
|
|
return (
|
|
indent_level is not None
|
|
and (
|
|
not self.preserve_whitespace_tags
|
|
or self.name not in self.preserve_whitespace_tags
|
|
)
|
|
)
|
|
|
|
def prettify(self, encoding=None, formatter="minimal"):
|
|
if encoding is None:
|
|
return self.decode(True, formatter=formatter)
|
|
else:
|
|
return self.encode(encoding, True, formatter=formatter)
|
|
|
|
def decode_contents(self, indent_level=None,
|
|
eventual_encoding=DEFAULT_OUTPUT_ENCODING,
|
|
formatter="minimal"):
|
|
"""Renders the contents of this tag as a Unicode string.
|
|
|
|
:param indent_level: Each line of the rendering will be
|
|
indented this many spaces.
|
|
|
|
:param eventual_encoding: The tag is destined to be
|
|
encoded into this encoding. decode_contents() is _not_
|
|
responsible for performing that encoding. This information
|
|
is passed in so that it can be substituted in if the
|
|
document contains a <META> tag that mentions the document's
|
|
encoding.
|
|
|
|
:param formatter: A Formatter object, or a string naming one of
|
|
the standard Formatters.
|
|
"""
|
|
# First off, turn a string formatter into a Formatter object. This
|
|
# will stop the lookup from happening over and over again.
|
|
if not isinstance(formatter, Formatter):
|
|
formatter = self.formatter_for_name(formatter)
|
|
|
|
pretty_print = (indent_level is not None)
|
|
s = []
|
|
for c in self:
|
|
text = None
|
|
if isinstance(c, NavigableString):
|
|
text = c.output_ready(formatter)
|
|
elif isinstance(c, Tag):
|
|
s.append(c.decode(indent_level, eventual_encoding,
|
|
formatter))
|
|
preserve_whitespace = (
|
|
self.preserve_whitespace_tags and self.name in self.preserve_whitespace_tags
|
|
)
|
|
if text and indent_level and not preserve_whitespace:
|
|
text = text.strip()
|
|
if text:
|
|
if pretty_print and not preserve_whitespace:
|
|
s.append(" " * (indent_level - 1))
|
|
s.append(text)
|
|
if pretty_print and not preserve_whitespace:
|
|
s.append("\n")
|
|
return ''.join(s)
|
|
|
|
def encode_contents(
|
|
self, indent_level=None, encoding=DEFAULT_OUTPUT_ENCODING,
|
|
formatter="minimal"):
|
|
"""Renders the contents of this tag as a bytestring.
|
|
|
|
:param indent_level: Each line of the rendering will be
|
|
indented this many spaces.
|
|
|
|
:param eventual_encoding: The bytestring will be in this encoding.
|
|
|
|
:param formatter: The output formatter responsible for converting
|
|
entities to Unicode characters.
|
|
"""
|
|
|
|
contents = self.decode_contents(indent_level, encoding, formatter)
|
|
return contents.encode(encoding)
|
|
|
|
# Old method for BS3 compatibility
|
|
def renderContents(self, encoding=DEFAULT_OUTPUT_ENCODING,
|
|
prettyPrint=False, indentLevel=0):
|
|
if not prettyPrint:
|
|
indentLevel = None
|
|
return self.encode_contents(
|
|
indent_level=indentLevel, encoding=encoding)
|
|
|
|
#Soup methods
|
|
|
|
def find(self, name=None, attrs={}, recursive=True, text=None,
|
|
**kwargs):
|
|
"""Return only the first child of this Tag matching the given
|
|
criteria."""
|
|
r = None
|
|
l = self.find_all(name, attrs, recursive, text, 1, **kwargs)
|
|
if l:
|
|
r = l[0]
|
|
return r
|
|
findChild = find
|
|
|
|
def find_all(self, name=None, attrs={}, recursive=True, text=None,
|
|
limit=None, **kwargs):
|
|
"""Extracts a list of Tag objects that match the given
|
|
criteria. You can specify the name of the Tag and any
|
|
attributes you want the Tag to have.
|
|
|
|
The value of a key-value pair in the 'attrs' map can be a
|
|
string, a list of strings, a regular expression object, or a
|
|
callable that takes a string and returns whether or not the
|
|
string matches for some custom definition of 'matches'. The
|
|
same is true of the tag name."""
|
|
|
|
generator = self.descendants
|
|
if not recursive:
|
|
generator = self.children
|
|
return self._find_all(name, attrs, text, limit, generator, **kwargs)
|
|
findAll = find_all # BS3
|
|
findChildren = find_all # BS2
|
|
|
|
#Generator methods
|
|
@property
|
|
def children(self):
|
|
# return iter() to make the purpose of the method clear
|
|
return iter(self.contents) # XXX This seems to be untested.
|
|
|
|
@property
|
|
def descendants(self):
|
|
if not len(self.contents):
|
|
return
|
|
stopNode = self._last_descendant().next_element
|
|
current = self.contents[0]
|
|
while current is not stopNode:
|
|
yield current
|
|
current = current.next_element
|
|
|
|
# CSS selector code
|
|
def select_one(self, selector, namespaces=None, **kwargs):
|
|
"""Perform a CSS selection operation on the current element."""
|
|
value = self.select(selector, namespaces, 1, **kwargs)
|
|
if value:
|
|
return value[0]
|
|
return None
|
|
|
|
def select(self, selector, namespaces=None, limit=None, **kwargs):
|
|
"""Perform a CSS selection operation on the current element.
|
|
|
|
This uses the SoupSieve library.
|
|
|
|
:param selector: A string containing a CSS selector.
|
|
|
|
:param namespaces: A dictionary mapping namespace prefixes
|
|
used in the CSS selector to namespace URIs. By default,
|
|
Beautiful Soup will use the prefixes it encountered while
|
|
parsing the document.
|
|
|
|
:param limit: After finding this number of results, stop looking.
|
|
|
|
:param kwargs: Any extra arguments you'd like to pass in to
|
|
soupsieve.select().
|
|
"""
|
|
if namespaces is None:
|
|
namespaces = self._namespaces
|
|
|
|
if limit is None:
|
|
limit = 0
|
|
if soupsieve is None:
|
|
raise NotImplementedError(
|
|
"Cannot execute CSS selectors because the soupsieve package is not installed."
|
|
)
|
|
|
|
return soupsieve.select(selector, self, namespaces, limit, **kwargs)
|
|
|
|
# Old names for backwards compatibility
|
|
def childGenerator(self):
|
|
return self.children
|
|
|
|
def recursiveChildGenerator(self):
|
|
return self.descendants
|
|
|
|
def has_key(self, key):
|
|
"""This was kind of misleading because has_key() (attributes)
|
|
was different from __in__ (contents). has_key() is gone in
|
|
Python 3, anyway."""
|
|
warnings.warn('has_key is deprecated. Use has_attr("%s") instead.' % (
|
|
key))
|
|
return self.has_attr(key)
|
|
|
|
# Next, a couple classes to represent queries and their results.
|
|
class SoupStrainer(object):
|
|
"""Encapsulates a number of ways of matching a markup element (tag or
|
|
text)."""
|
|
|
|
def __init__(self, name=None, attrs={}, text=None, **kwargs):
|
|
self.name = self._normalize_search_value(name)
|
|
if not isinstance(attrs, dict):
|
|
# Treat a non-dict value for attrs as a search for the 'class'
|
|
# attribute.
|
|
kwargs['class'] = attrs
|
|
attrs = None
|
|
|
|
if 'class_' in kwargs:
|
|
# Treat class_="foo" as a search for the 'class'
|
|
# attribute, overriding any non-dict value for attrs.
|
|
kwargs['class'] = kwargs['class_']
|
|
del kwargs['class_']
|
|
|
|
if kwargs:
|
|
if attrs:
|
|
attrs = attrs.copy()
|
|
attrs.update(kwargs)
|
|
else:
|
|
attrs = kwargs
|
|
normalized_attrs = {}
|
|
for key, value in list(attrs.items()):
|
|
normalized_attrs[key] = self._normalize_search_value(value)
|
|
|
|
self.attrs = normalized_attrs
|
|
self.text = self._normalize_search_value(text)
|
|
|
|
def _normalize_search_value(self, value):
|
|
# Leave it alone if it's a Unicode string, a callable, a
|
|
# regular expression, a boolean, or None.
|
|
if (isinstance(value, str) or isinstance(value, Callable) or hasattr(value, 'match')
|
|
or isinstance(value, bool) or value is None):
|
|
return value
|
|
|
|
# If it's a bytestring, convert it to Unicode, treating it as UTF-8.
|
|
if isinstance(value, bytes):
|
|
return value.decode("utf8")
|
|
|
|
# If it's listlike, convert it into a list of strings.
|
|
if hasattr(value, '__iter__'):
|
|
new_value = []
|
|
for v in value:
|
|
if (hasattr(v, '__iter__') and not isinstance(v, bytes)
|
|
and not isinstance(v, str)):
|
|
# This is almost certainly the user's mistake. In the
|
|
# interests of avoiding infinite loops, we'll let
|
|
# it through as-is rather than doing a recursive call.
|
|
new_value.append(v)
|
|
else:
|
|
new_value.append(self._normalize_search_value(v))
|
|
return new_value
|
|
|
|
# Otherwise, convert it into a Unicode string.
|
|
# The unicode(str()) thing is so this will do the same thing on Python 2
|
|
# and Python 3.
|
|
return str(str(value))
|
|
|
|
def __str__(self):
|
|
if self.text:
|
|
return self.text
|
|
else:
|
|
return "%s|%s" % (self.name, self.attrs)
|
|
|
|
def search_tag(self, markup_name=None, markup_attrs={}):
|
|
found = None
|
|
markup = None
|
|
if isinstance(markup_name, Tag):
|
|
markup = markup_name
|
|
markup_attrs = markup
|
|
call_function_with_tag_data = (
|
|
isinstance(self.name, Callable)
|
|
and not isinstance(markup_name, Tag))
|
|
|
|
if ((not self.name)
|
|
or call_function_with_tag_data
|
|
or (markup and self._matches(markup, self.name))
|
|
or (not markup and self._matches(markup_name, self.name))):
|
|
if call_function_with_tag_data:
|
|
match = self.name(markup_name, markup_attrs)
|
|
else:
|
|
match = True
|
|
markup_attr_map = None
|
|
for attr, match_against in list(self.attrs.items()):
|
|
if not markup_attr_map:
|
|
if hasattr(markup_attrs, 'get'):
|
|
markup_attr_map = markup_attrs
|
|
else:
|
|
markup_attr_map = {}
|
|
for k, v in markup_attrs:
|
|
markup_attr_map[k] = v
|
|
attr_value = markup_attr_map.get(attr)
|
|
if not self._matches(attr_value, match_against):
|
|
match = False
|
|
break
|
|
if match:
|
|
if markup:
|
|
found = markup
|
|
else:
|
|
found = markup_name
|
|
if found and self.text and not self._matches(found.string, self.text):
|
|
found = None
|
|
return found
|
|
searchTag = search_tag
|
|
|
|
def search(self, markup):
|
|
# print 'looking for %s in %s' % (self, markup)
|
|
found = None
|
|
# If given a list of items, scan it for a text element that
|
|
# matches.
|
|
if hasattr(markup, '__iter__') and not isinstance(markup, (Tag, str)):
|
|
for element in markup:
|
|
if isinstance(element, NavigableString) \
|
|
and self.search(element):
|
|
found = element
|
|
break
|
|
# If it's a Tag, make sure its name or attributes match.
|
|
# Don't bother with Tags if we're searching for text.
|
|
elif isinstance(markup, Tag):
|
|
if not self.text or self.name or self.attrs:
|
|
found = self.search_tag(markup)
|
|
# If it's text, make sure the text matches.
|
|
elif isinstance(markup, NavigableString) or \
|
|
isinstance(markup, str):
|
|
if not self.name and not self.attrs and self._matches(markup, self.text):
|
|
found = markup
|
|
else:
|
|
raise Exception(
|
|
"I don't know how to match against a %s" % markup.__class__)
|
|
return found
|
|
|
|
def _matches(self, markup, match_against, already_tried=None):
|
|
# print u"Matching %s against %s" % (markup, match_against)
|
|
result = False
|
|
if isinstance(markup, list) or isinstance(markup, tuple):
|
|
# This should only happen when searching a multi-valued attribute
|
|
# like 'class'.
|
|
for item in markup:
|
|
if self._matches(item, match_against):
|
|
return True
|
|
# We didn't match any particular value of the multivalue
|
|
# attribute, but maybe we match the attribute value when
|
|
# considered as a string.
|
|
if self._matches(' '.join(markup), match_against):
|
|
return True
|
|
return False
|
|
|
|
if match_against is True:
|
|
# True matches any non-None value.
|
|
return markup is not None
|
|
|
|
if isinstance(match_against, Callable):
|
|
return match_against(markup)
|
|
|
|
# Custom callables take the tag as an argument, but all
|
|
# other ways of matching match the tag name as a string.
|
|
original_markup = markup
|
|
if isinstance(markup, Tag):
|
|
markup = markup.name
|
|
|
|
# Ensure that `markup` is either a Unicode string, or None.
|
|
markup = self._normalize_search_value(markup)
|
|
|
|
if markup is None:
|
|
# None matches None, False, an empty string, an empty list, and so on.
|
|
return not match_against
|
|
|
|
if (hasattr(match_against, '__iter__')
|
|
and not isinstance(match_against, str)):
|
|
# We're asked to match against an iterable of items.
|
|
# The markup must be match at least one item in the
|
|
# iterable. We'll try each one in turn.
|
|
#
|
|
# To avoid infinite recursion we need to keep track of
|
|
# items we've already seen.
|
|
if not already_tried:
|
|
already_tried = set()
|
|
for item in match_against:
|
|
if item.__hash__:
|
|
key = item
|
|
else:
|
|
key = id(item)
|
|
if key in already_tried:
|
|
continue
|
|
else:
|
|
already_tried.add(key)
|
|
if self._matches(original_markup, item, already_tried):
|
|
return True
|
|
else:
|
|
return False
|
|
|
|
# Beyond this point we might need to run the test twice: once against
|
|
# the tag's name and once against its prefixed name.
|
|
match = False
|
|
|
|
if not match and isinstance(match_against, str):
|
|
# Exact string match
|
|
match = markup == match_against
|
|
|
|
if not match and hasattr(match_against, 'search'):
|
|
# Regexp match
|
|
return match_against.search(markup)
|
|
|
|
if (not match
|
|
and isinstance(original_markup, Tag)
|
|
and original_markup.prefix):
|
|
# Try the whole thing again with the prefixed tag name.
|
|
return self._matches(
|
|
original_markup.prefix + ':' + original_markup.name, match_against
|
|
)
|
|
|
|
return match
|
|
|
|
|
|
class ResultSet(list):
|
|
"""A ResultSet is just a list that keeps track of the SoupStrainer
|
|
that created it."""
|
|
def __init__(self, source, result=()):
|
|
super(ResultSet, self).__init__(result)
|
|
self.source = source
|
|
|
|
def __getattr__(self, key):
|
|
raise AttributeError(
|
|
"ResultSet object has no attribute '%s'. You're probably treating a list of items like a single item. Did you call find_all() when you meant to call find()?" % key
|
|
)
|