github/nzbToMedia
1
0
Fork 0
mirror of https://github.com/clinton-hall/nzbToMedia.git synced 2025-08-14 10:36:52 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update vendored beautifulsoup4 to 4.11.1

Browse source 
Adds soupsieve 2.3.2.post1
This commit is contained in:
Labrys of Knossos 2022-11-28 21:11:01 -05:00
commit 968ec8a1d8
33 changed files with 10852 additions and 3694 deletions
Download patch file Download diff file Expand all files Collapse all files

354
libs/common/bs4/builder/__init__.py
View file

@ -1,15 +1,21 @@
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
from collections import defaultdict
import itertools
import re
import warnings
import sys
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
HTMLAwareEntitySubstitution,
whitespace_re
)
RubyParenthesisString,
RubyTextString,
Stylesheet,
Script,
TemplateString,
nonwhitespace_re
)
__all__ = [
'HTMLTreeBuilder',
@ -26,20 +32,41 @@ XML = 'xml'
HTML = 'html'
HTML_5 = 'html5'
class XMLParsedAsHTMLWarning(UserWarning):
"""The warning issued when an HTML parser is used to parse
XML that is not XHTML.
"""
MESSAGE = """It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor."""
class TreeBuilderRegistry(object):
"""A way of looking up TreeBuilder subclasses by their name or by desired
features.
"""
def __init__(self):
self.builders_for_feature = defaultdict(list)
self.builders = []
def register(self, treebuilder_class):
"""Register a treebuilder based on its advertised features."""
"""Register a treebuilder based on its advertised features.
:param treebuilder_class: A subclass of Treebuilder. its .features
attribute should list its features.
"""
for feature in treebuilder_class.features:
self.builders_for_feature[feature].insert(0, treebuilder_class)
self.builders.insert(0, treebuilder_class)
def lookup(self, *features):
"""Look up a TreeBuilder subclass with the desired features.
:param features: A list of features to look for. If none are
provided, the most recently registered TreeBuilder subclass
will be used.
:return: A TreeBuilder subclass, or None if there's no
registered subclass with all the requested features.
"""
if len(self.builders) == 0:
# There are no builders at all.
return None
@ -82,7 +109,7 @@ class TreeBuilderRegistry(object):
builder_registry = TreeBuilderRegistry()
class TreeBuilder(object):
"""Turn a document into a Beautiful Soup object tree."""
"""Turn a textual document into a Beautiful Soup object tree."""
NAME = "[Unknown tree builder]"
ALTERNATE_NAMES = []
@ -90,19 +117,89 @@ class TreeBuilder(object):
is_xml = False
picklable = False
preserve_whitespace_tags = set()
empty_element_tags = None # A tag will be considered an empty-element
# tag when and only when it has no contents.
# A value for these tag/attribute combinations is a space- or
# comma-separated list of CDATA, rather than a single CDATA.
cdata_list_attributes = {}
DEFAULT_CDATA_LIST_ATTRIBUTES = {}
# Whitespace should be preserved inside these tags.
DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
def __init__(self):
# The textual contents of tags with these names should be
# instantiated with some class other than NavigableString.
DEFAULT_STRING_CONTAINERS = {}
USE_DEFAULT = object()
# Most parsers don't keep track of line numbers.
TRACKS_LINE_NUMBERS = False
def __init__(self, multi_valued_attributes=USE_DEFAULT,
preserve_whitespace_tags=USE_DEFAULT,
store_line_numbers=USE_DEFAULT,
string_containers=USE_DEFAULT,
):
"""Constructor.
:param multi_valued_attributes: If this is set to None, the
TreeBuilder will not turn any values for attributes like
'class' into lists. Setting this to a dictionary will
customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES
for an example.
Internally, these are called "CDATA list attributes", but that
probably doesn't make sense to an end-user, so the argument name
is `multi_valued_attributes`.
:param preserve_whitespace_tags: A list of tags to treat
the way <pre> tags are treated in HTML. Tags in this list
are immune from pretty-printing; their contents will always be
output as-is.
:param string_containers: A dictionary mapping tag names to
the classes that should be instantiated to contain the textual
contents of those tags. The default is to use NavigableString
for every tag, no matter what the name. You can override the
default by changing DEFAULT_STRING_CONTAINERS.
:param store_line_numbers: If the parser keeps track of the
line numbers and positions of the original markup, that
information will, by default, be stored in each corresponding
`Tag` object. You can turn this off by passing
store_line_numbers=False. If the parser you're using doesn't
keep track of this information, then setting store_line_numbers=True
will do nothing.
"""
self.soup = None
if multi_valued_attributes is self.USE_DEFAULT:
multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
self.cdata_list_attributes = multi_valued_attributes
if preserve_whitespace_tags is self.USE_DEFAULT:
preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
self.preserve_whitespace_tags = preserve_whitespace_tags
if store_line_numbers == self.USE_DEFAULT:
store_line_numbers = self.TRACKS_LINE_NUMBERS
self.store_line_numbers = store_line_numbers
if string_containers == self.USE_DEFAULT:
string_containers = self.DEFAULT_STRING_CONTAINERS
self.string_containers = string_containers
def initialize_soup(self, soup):
"""The BeautifulSoup object has been initialized and is now
being associated with the TreeBuilder.
:param soup: A BeautifulSoup object.
"""
self.soup = soup
def reset(self):
"""Do any work necessary to reset the underlying parser
for a new document.
By default, this does nothing.
"""
pass
def can_be_empty_element(self, tag_name):
@ -114,24 +211,58 @@ class TreeBuilder(object):
For instance: an HTMLBuilder does not consider a <p> tag to be
an empty-element tag (it's not in
HTMLBuilder.empty_element_tags). This means an empty <p> tag
will be presented as "<p></p>", not "<p />".
will be presented as "<p></p>", not "<p/>" or "<p>".
The default implementation has no opinion about which tags are
empty-element tags, so a tag will be presented as an
empty-element tag if and only if it has no contents.
"<foo></foo>" will become "<foo />", and "<foo>bar</foo>" will
empty-element tag if and only if it has no children.
"<foo></foo>" will become "<foo/>", and "<foo>bar</foo>" will
be left alone.
:param tag_name: The name of a markup tag.
"""
if self.empty_element_tags is None:
return True
return tag_name in self.empty_element_tags
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
This method is not implemented in TreeBuilder; it must be
implemented in subclasses.
:return: None.
"""
raise NotImplementedError()
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None):
return markup, None, None, False
document_declared_encoding=None, exclude_encodings=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding. NOTE: This argument is not used by the
calling code and can probably be removed.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
By default, the only strategy is to parse the markup
as-is. See `LXMLTreeBuilderForXML` and
`HTMLParserTreeBuilder` for implementations that take into
account the quirks of particular parsers.
"""
yield markup, None, None, False
def test_fragment_to_document(self, fragment):
"""Wrap an HTML fragment to make it look like a document.
@ -143,16 +274,36 @@ class TreeBuilder(object):
results against other HTML fragments.
This method should not be used outside of tests.
:param fragment: A string -- fragment of HTML.
:return: A string -- a full HTML document.
"""
return fragment
def set_up_substitutions(self, tag):
"""Set up any substitutions that will need to be performed on
a `Tag` when it's output as a string.
By default, this does nothing. See `HTMLTreeBuilder` for a
case where this is used.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
return False
def _replace_cdata_list_attribute_values(self, tag_name, attrs):
"""Replaces class="foo bar" with class=["foo", "bar"]
"""When an attribute value is associated with a tag that can
have multiple values for that attribute, convert the string
value to a list of strings.
Modifies its input in place.
Basically, replaces class="foo bar" with class=["foo", "bar"]
NOTE: This method modifies its input in place.
:param tag_name: The name of a tag.
:param attrs: A dictionary containing the tag's attributes.
Any appropriate attribute values will be modified in place.
"""
if not attrs:
return attrs
@ -167,7 +318,7 @@ class TreeBuilder(object):
# values. Split it into a list.
value = attrs[attr]
if isinstance(value, str):
values = whitespace_re.split(value)
values = nonwhitespace_re.findall(value)
else:
# html5lib sometimes calls setAttributes twice
# for the same tag when rearranging the parse
@ -178,9 +329,13 @@ class TreeBuilder(object):
values = value
attrs[attr] = values
return attrs
class SAXTreeBuilder(TreeBuilder):
"""A Beautiful Soup treebuilder that listens for SAX events."""
"""A Beautiful Soup treebuilder that listens for SAX events.
This is not currently used for anything, but it demonstrates
how a simple TreeBuilder would work.
"""
def feed(self, markup):
raise NotImplementedError()
@ -190,11 +345,11 @@ class SAXTreeBuilder(TreeBuilder):
def startElement(self, name, attrs):
attrs = dict((key[1], value) for key, value in list(attrs.items()))
#print "Start %s, %r" % (name, attrs)
#print("Start %s, %r" % (name, attrs))
self.soup.handle_starttag(name, attrs)
def endElement(self, name):
#print "End %s" % name
#print("End %s" % name)
self.soup.handle_endtag(name)
def startElementNS(self, nsTuple, nodeName, attrs):
@ -231,7 +386,6 @@ class HTMLTreeBuilder(TreeBuilder):
Such as which tags are empty-element tags.
"""
preserve_whitespace_tags = HTMLAwareEntitySubstitution.preserve_whitespace_tags
empty_element_tags = set([
# These are from HTML5.
'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
@ -245,6 +399,30 @@ class HTMLTreeBuilder(TreeBuilder):
# but it may do so eventually, and this information is available if
# you need to use it.
block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
# These HTML tags need special treatment so they can be
# represented by a string class other than NavigableString.
#
# For some of these tags, it's because the HTML standard defines
# an unusual content model for them. I made this list by going
# through the HTML spec
# (https://html.spec.whatwg.org/#metadata-content) and looking for
# "metadata content" elements that can contain strings.
#
# The Ruby tags (<rt> and <rp>) are here despite being normal
# "phrasing content" tags, because the content they contain is
# qualitatively different from other text in the document, and it
# can be useful to be able to distinguish it.
#
# TODO: Arguably <noscript> could go here but it seems
# qualitatively different from the other tags.
DEFAULT_STRING_CONTAINERS = {
'rt' : RubyTextString,
'rp' : RubyParenthesisString,
'style': Stylesheet,
'script': Script,
'template': TemplateString,
}
# The HTML standard defines these attributes as containing a
# space-separated list of values, not a single value. That is,
@ -253,7 +431,7 @@ class HTMLTreeBuilder(TreeBuilder):
# encounter one of these attributes, we will parse its value into
# a list of values if possible. Upon output, the list will be
# converted back into a string.
cdata_list_attributes = {
DEFAULT_CDATA_LIST_ATTRIBUTES = {
"*" : ['class', 'accesskey', 'dropzone'],
"a" : ['rel', 'rev'],
"link" : ['rel', 'rev'],
@ -270,7 +448,19 @@ class HTMLTreeBuilder(TreeBuilder):
"output" : ["for"],
}
DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
def set_up_substitutions(self, tag):
"""Replace the declared encoding in a <meta> tag with a placeholder,
to be substituted when the tag is output to a string.
An HTML document may come in to Beautiful Soup as one
encoding, but exit in a different encoding, and the <meta> tag
needs to be changed to reflect this.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
# We are only interested in <meta> tags
if tag.name != 'meta':
return False
@ -303,10 +493,102 @@ class HTMLTreeBuilder(TreeBuilder):
return (meta_encoding is not None)
class DetectsXMLParsedAsHTML(object):
"""A mixin class for any class (a TreeBuilder, or some class used by a
TreeBuilder) that's in a position to detect whether an XML
document is being incorrectly parsed as HTML, and issue an
appropriate warning.
This requires being able to observe an incoming processing
instruction that might be an XML declaration, and also able to
observe tags as they're opened. If you can't do that for a given
TreeBuilder, there's a less reliable implementation based on
examining the raw markup.
"""
# Regular expression for seeing if markup has an <html> tag.
LOOKS_LIKE_HTML = re.compile("<[^ +]html", re.I)
LOOKS_LIKE_HTML_B = re.compile(b"<[^ +]html", re.I)
XML_PREFIX = '<?xml'
XML_PREFIX_B = b'<?xml'
@classmethod
def warn_if_markup_looks_like_xml(cls, markup):
"""Perform a check on some markup to see if it looks like XML
that's not XHTML. If so, issue a warning.
This is much less reliable than doing the check while parsing,
but some of the tree builders can't do that.
:return: True if the markup looks like non-XHTML XML, False
otherwise.
"""
if isinstance(markup, bytes):
prefix = cls.XML_PREFIX_B
looks_like_html = cls.LOOKS_LIKE_HTML_B
else:
prefix = cls.XML_PREFIX
looks_like_html = cls.LOOKS_LIKE_HTML
if (markup is not None
and markup.startswith(prefix)
and not looks_like_html.search(markup[:500])
):
cls._warn()
return True
return False
@classmethod
def _warn(cls):
"""Issue a warning about XML being parsed as HTML."""
warnings.warn(
XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning
)
def _initialize_xml_detector(self):
"""Call this method before parsing a document."""
self._first_processing_instruction = None
self._root_tag = None
def _document_might_be_xml(self, processing_instruction):
"""Call this method when encountering an XML declaration, or a
"processing instruction" that might be an XML declaration.
"""
if (self._first_processing_instruction is not None
or self._root_tag is not None):
# The document has already started. Don't bother checking
# anymore.
return
self._first_processing_instruction = processing_instruction
# We won't know until we encounter the first tag whether or
# not this is actually a problem.
def _root_tag_encountered(self, name):
"""Call this when you encounter the document's root tag.
This is where we actually check whether an XML document is
being incorrectly parsed as HTML, and issue the warning.
"""
if self._root_tag is not None:
# This method was incorrectly called multiple times. Do
# nothing.
return
self._root_tag = name
if (name != 'html' and self._first_processing_instruction is not None
and self._first_processing_instruction.lower().startswith('xml ')):
# We encountered an XML declaration and then a tag other
# than 'html'. This is a reliable indicator that a
# non-XHTML document is being parsed as XML.
self._warn()
def register_treebuilders_from(module):
"""Copy TreeBuilders from the given module into this module."""
# I'm fairly sure this is not the best way to do this.
this_module = sys.modules['bs4.builder']
this_module = sys.modules[__name__]
for name in module.__all__:
obj = getattr(module, name)
@ -317,12 +599,22 @@ def register_treebuilders_from(module):
this_module.builder_registry.register(obj)
class ParserRejectedMarkup(Exception):
pass
"""An Exception to be raised when the underlying parser simply
refuses to parse the given markup.
"""
def __init__(self, message_or_exception):
"""Explain why the parser rejected the given markup, either
with a textual explanation or another exception.
"""
if isinstance(message_or_exception, Exception):
e = message_or_exception
message_or_exception = "%s: %s" % (e.__class__.__name__, str(e))
super(ParserRejectedMarkup, self).__init__(message_or_exception)
# Builders are registered in reverse order of priority, so that custom
# builder registrations will take precedence. In general, we want lxml
# to take precedence over html5lib, because it's faster. And we only
# want to use HTMLParser as a last result.
# want to use HTMLParser as a last resort.
from . import _htmlparser
register_treebuilders_from(_htmlparser)
try:

103
libs/common/bs4/builder/_html5lib.py
View file

@ -1,5 +1,5 @@
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTML5TreeBuilder',
@ -8,6 +8,7 @@ __all__ = [
import warnings
import re
from bs4.builder import (
DetectsXMLParsedAsHTML,
PERMISSIVE,
HTML,
HTML_5,
@ -15,7 +16,7 @@ from bs4.builder import (
)
from bs4.element import (
NamespacedAttribute,
whitespace_re,
nonwhitespace_re,
)
import html5lib
from html5lib.constants import (
@ -39,12 +40,27 @@ except ImportError as e:
new_html5lib = True
class HTML5TreeBuilder(HTMLTreeBuilder):
"""Use html5lib to build a tree."""
"""Use html5lib to build a tree.
Note that this TreeBuilder does not support some features common
to HTML TreeBuilders. Some of these features could theoretically
be implemented, but at the very least it's quite difficult,
because html5lib moves the parse tree around as it's being built.
* This TreeBuilder doesn't use different subclasses of NavigableString
based on the name of the tag in which the string was found.
* You can't use a SoupStrainer to parse only part of a document.
"""
NAME = "html5lib"
features = [NAME, PERMISSIVE, HTML_5, HTML]
# html5lib can tell us which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def prepare_markup(self, markup, user_specified_encoding,
document_declared_encoding=None, exclude_encodings=None):
# Store the user-specified encoding for use later on.
@ -55,6 +71,11 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
# UnicodeDammit.
if exclude_encodings:
warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
# html5lib only parses HTML, so if it's given XML that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
yield (markup, None, None, False)
# These methods are defined by Beautiful Soup.
@ -62,7 +83,7 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
if self.soup.parse_only is not None:
warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
self.underlying_builder.parser = parser
extra_kwargs = dict()
if not isinstance(markup, str):
if new_html5lib:
@ -70,7 +91,7 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
else:
extra_kwargs['encoding'] = self.user_specified_encoding
doc = parser.parse(markup, **extra_kwargs)
# Set the character encoding detected by the tokenizer.
if isinstance(markup, str):
# We need to special-case this because html5lib sets
@ -84,10 +105,13 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
# with other tree builders.
original_encoding = original_encoding.name
doc.original_encoding = original_encoding
self.underlying_builder.parser = None
def create_treebuilder(self, namespaceHTMLElements):
self.underlying_builder = TreeBuilderForHtml5lib(
namespaceHTMLElements, self.soup)
namespaceHTMLElements, self.soup,
store_line_numbers=self.store_line_numbers
)
return self.underlying_builder
def test_fragment_to_document(self, fragment):
@ -96,15 +120,29 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
def __init__(self, namespaceHTMLElements, soup=None):
def __init__(self, namespaceHTMLElements, soup=None,
store_line_numbers=True, **kwargs):
if soup:
self.soup = soup
else:
from bs4 import BeautifulSoup
self.soup = BeautifulSoup("", "html.parser")
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup(
"", "html.parser", store_line_numbers=store_line_numbers,
**kwargs
)
# TODO: What are **kwargs exactly? Should they be passed in
# here in addition to/instead of being passed to the BeautifulSoup
# constructor?
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
# This will be set later to an html5lib.html5parser.HTMLParser
# object, which we can use to track the current line number.
self.parser = None
self.store_line_numbers = store_line_numbers
def documentClass(self):
self.soup.reset()
return Element(self.soup, self.soup, None)
@ -118,7 +156,16 @@ class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
self.soup.object_was_parsed(doctype)
def elementClass(self, name, namespace):
tag = self.soup.new_tag(name, namespace)
kwargs = {}
if self.parser and self.store_line_numbers:
# This represents the point immediately after the end of the
# tag. We don't know when the tag started, but we do know
# where it ended -- the character just before this one.
sourceline, sourcepos = self.parser.tokenizer.stream.position()
kwargs['sourceline'] = sourceline
kwargs['sourcepos'] = sourcepos-1
tag = self.soup.new_tag(name, namespace, **kwargs)
return Element(tag, self.soup, namespace)
def commentClass(self, data):
@ -126,6 +173,8 @@ class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
def fragmentClass(self):
from bs4 import BeautifulSoup
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup("", "html.parser")
self.soup.name = "[document_fragment]"
return Element(self.soup, self.soup, None)
@ -199,14 +248,14 @@ class AttrList(object):
def __setitem__(self, name, value):
# If this attribute is a multi-valued attribute for this element,
# turn its value into a list.
list_attr = HTML5TreeBuilder.cdata_list_attributes
if (name in list_attr['*']
list_attr = self.element.cdata_list_attributes or {}
if (name in list_attr.get('*')
or (self.element.name in list_attr
and name in list_attr[self.element.name])):
# A node that is being cloned may have already undergone
# this procedure.
if not isinstance(value, list):
value = whitespace_re.split(value)
value = nonwhitespace_re.findall(value)
self.element[name] = value
def items(self):
return list(self.attrs.items())
@ -249,7 +298,7 @@ class Element(treebuilder_base.Node):
if not isinstance(child, str) and child.parent is not None:
node.element.extract()
if (string_child and self.element.contents
if (string_child is not None and self.element.contents
and self.element.contents[-1].__class__ == NavigableString):
# We are appending a string onto another string.
# TODO This has O(n^2) performance, for input like
@ -287,9 +336,7 @@ class Element(treebuilder_base.Node):
return AttrList(self.element)
def setAttributes(self, attributes):
if attributes is not None and len(attributes) > 0:
converted_attributes = []
for name, value in list(attributes.items()):
if isinstance(name, tuple):
@ -334,9 +381,9 @@ class Element(treebuilder_base.Node):
def reparentChildren(self, new_parent):
"""Move all of this tag's children into another tag."""
# print "MOVE", self.element.contents
# print "FROM", self.element
# print "TO", new_parent.element
# print("MOVE", self.element.contents)
# print("FROM", self.element)
# print("TO", new_parent.element)
element = self.element
new_parent_element = new_parent.element
@ -360,16 +407,16 @@ class Element(treebuilder_base.Node):
# Set the first child's previous_element and previous_sibling
# to elements within the new parent
first_child = to_append[0]
if new_parents_last_descendant:
if new_parents_last_descendant is not None:
first_child.previous_element = new_parents_last_descendant
else:
first_child.previous_element = new_parent_element
first_child.previous_sibling = new_parents_last_child
if new_parents_last_descendant:
if new_parents_last_descendant is not None:
new_parents_last_descendant.next_element = first_child
else:
new_parent_element.next_element = first_child
if new_parents_last_child:
if new_parents_last_child is not None:
new_parents_last_child.next_sibling = first_child
# Find the very last element being moved. It is now the
@ -379,7 +426,7 @@ class Element(treebuilder_base.Node):
last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
if new_parents_last_descendant_next_element:
if new_parents_last_descendant_next_element is not None:
# TODO: This code has no test coverage and I'm not sure
# how to get html5lib to go through this path, but it's
# just the other side of the previous line.
@ -394,9 +441,9 @@ class Element(treebuilder_base.Node):
element.contents = []
element.next_element = final_next_element
# print "DONE WITH MOVE"
# print "FROM", self.element
# print "TO", new_parent_element
# print("DONE WITH MOVE")
# print("FROM", self.element)
# print("TO", new_parent_element)
def cloneNode(self):
tag = self.soup.new_tag(self.element.name, self.namespace)

220
libs/common/bs4/builder/_htmlparser.py
View file

@ -1,8 +1,8 @@
# encoding: utf-8
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTMLParserTreeBuilder',
@ -44,6 +44,7 @@ from bs4.element import (
from bs4.dammit import EntitySubstitution, UnicodeDammit
from bs4.builder import (
DetectsXMLParsedAsHTML,
HTML,
HTMLTreeBuilder,
STRICT,
@ -52,9 +53,31 @@ from bs4.builder import (
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser):
class BeautifulSoupHTMLParser(HTMLParser, DetectsXMLParsedAsHTML):
"""A subclass of the Python standard library's HTMLParser class, which
listens for HTMLParser events and translates them into calls
to Beautiful Soup's tree construction API.
"""
# Strategies for handling duplicate attributes
IGNORE = 'ignore'
REPLACE = 'replace'
def __init__(self, *args, **kwargs):
"""Constructor.
:param on_duplicate_attribute: A strategy for what to do if a
tag includes the same attribute more than once. Accepted
values are: REPLACE (replace earlier values with later
ones, the default), IGNORE (keep the earliest value
encountered), or a callable. A callable must take three
arguments: the dictionary of attributes already processed,
the name of the duplicate attribute, and the most recent value
encountered.
"""
self.on_duplicate_attribute = kwargs.pop(
'on_duplicate_attribute', self.REPLACE
)
HTMLParser.__init__(self, *args, **kwargs)
# Keep a list of empty-element tags that were encountered
@ -66,21 +89,29 @@ class BeautifulSoupHTMLParser(HTMLParser):
# will ignore, assuming they ever show up.
self.already_closed_empty_element = []
self._initialize_xml_detector()
def error(self, msg):
"""In Python 3, HTMLParser subclasses must implement error(), although this
requirement doesn't appear to be documented.
"""In Python 3, HTMLParser subclasses must implement error(), although
this requirement doesn't appear to be documented.
In Python 2, HTMLParser implements error() as raising an exception.
In Python 2, HTMLParser implements error() by raising an exception,
which we don't want to do.
In any event, this method is called only on very strange markup and our best strategy
is to pretend it didn't happen and keep going.
In any event, this method is called only on very strange
markup and our best strategy is to pretend it didn't happen
and keep going.
"""
warnings.warn(msg)
def handle_startendtag(self, name, attrs):
# This is only called when the markup looks like
# <tag/>.
"""Handle an incoming empty-element tag.
This is only called when the markup looks like <tag/>.
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
"""
# is_startend() tells handle_starttag not to close the tag
# just because its name matches a known empty-element tag. We
# know that this is an empty-element tag and we want to call
@ -89,6 +120,14 @@ class BeautifulSoupHTMLParser(HTMLParser):
self.handle_endtag(name)
def handle_starttag(self, name, attrs, handle_empty_element=True):
"""Handle an opening tag, e.g. '<tag>'
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
:param handle_empty_element: True if this tag is known to be
an empty-element tag (i.e. there is not expected to be any
closing tag).
"""
# XXX namespace
attr_dict = {}
for key, value in attrs:
@ -96,10 +135,26 @@ class BeautifulSoupHTMLParser(HTMLParser):
# for consistency with the other tree builders.
if value is None:
value = ''
attr_dict[key] = value
if key in attr_dict:
# A single attribute shows up multiple times in this
# tag. How to handle it depends on the
# on_duplicate_attribute setting.
on_dupe = self.on_duplicate_attribute
if on_dupe == self.IGNORE:
pass
elif on_dupe in (None, self.REPLACE):
attr_dict[key] = value
else:
on_dupe(attr_dict, key, value)
else:
attr_dict[key] = value
attrvalue = '""'
#print "START", name
tag = self.soup.handle_starttag(name, None, None, attr_dict)
#print("START", name)
sourceline, sourcepos = self.getpos()
tag = self.soup.handle_starttag(
name, None, None, attr_dict, sourceline=sourceline,
sourcepos=sourcepos
)
if tag and tag.is_empty_element and handle_empty_element:
# Unlike other parsers, html.parser doesn't send separate end tag
# events for empty-element tags. (It's handled in
@ -115,22 +170,39 @@ class BeautifulSoupHTMLParser(HTMLParser):
# But we might encounter an explicit closing tag for this tag
# later on. If so, we want to ignore it.
self.already_closed_empty_element.append(name)
if self._root_tag is None:
self._root_tag_encountered(name)
def handle_endtag(self, name, check_already_closed=True):
#print "END", name
"""Handle a closing tag, e.g. '</tag>'
:param name: A tag name.
:param check_already_closed: True if this tag is expected to
be the closing portion of an empty-element tag,
e.g. '<tag></tag>'.
"""
#print("END", name)
if check_already_closed and name in self.already_closed_empty_element:
# This is a redundant end tag for an empty-element tag.
# We've already called handle_endtag() for it, so just
# check it off the list.
# print "ALREADY CLOSED", name
#print("ALREADY CLOSED", name)
self.already_closed_empty_element.remove(name)
else:
self.soup.handle_endtag(name)
def handle_data(self, data):
"""Handle some textual data that shows up between tags."""
self.soup.handle_data(data)
def handle_charref(self, name):
"""Handle a numeric character reference by converting it to the
corresponding Unicode character and treating it as textual
data.
:param name: Character number, possibly in hexadecimal.
"""
# XXX workaround for a bug in HTMLParser. Remove this once
# it's fixed in all supported versions.
# http://bugs.python.org/issue13633
@ -164,6 +236,12 @@ class BeautifulSoupHTMLParser(HTMLParser):
self.handle_data(data)
def handle_entityref(self, name):
"""Handle a named entity reference by converting it to the
corresponding Unicode character(s) and treating it as textual
data.
:param name: Name of the entity reference.
"""
character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
if character is not None:
data = character
@ -177,21 +255,29 @@ class BeautifulSoupHTMLParser(HTMLParser):
self.handle_data(data)
def handle_comment(self, data):
"""Handle an HTML comment.
:param data: The text of the comment.
"""
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(Comment)
def handle_decl(self, data):
"""Handle a DOCTYPE declaration.
:param data: The text of the declaration.
"""
self.soup.endData()
if data.startswith("DOCTYPE "):
data = data[len("DOCTYPE "):]
elif data == 'DOCTYPE':
# i.e. "<!DOCTYPE>"
data = ''
data = data[len("DOCTYPE "):]
self.soup.handle_data(data)
self.soup.endData(Doctype)
def unknown_decl(self, data):
"""Handle a declaration of unknown type -- probably a CDATA block.
:param data: The text of the declaration.
"""
if data.upper().startswith('CDATA['):
cls = CData
data = data[len('CDATA['):]
@ -202,44 +288,110 @@ class BeautifulSoupHTMLParser(HTMLParser):
self.soup.endData(cls)
def handle_pi(self, data):
"""Handle a processing instruction.
:param data: The text of the instruction.
"""
self.soup.endData()
self.soup.handle_data(data)
self._document_might_be_xml(data)
self.soup.endData(ProcessingInstruction)
class HTMLParserTreeBuilder(HTMLTreeBuilder):
"""A Beautiful soup `TreeBuilder` that uses the `HTMLParser` parser,
found in the Python standard library.
"""
is_xml = False
picklable = True
NAME = HTMLPARSER
features = [NAME, HTML, STRICT]
def __init__(self, *args, **kwargs):
if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
kwargs['strict'] = False
if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
kwargs['convert_charrefs'] = False
self.parser_args = (args, kwargs)
# The html.parser knows which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def __init__(self, parser_args=None, parser_kwargs=None, **kwargs):
"""Constructor.
:param parser_args: Positional arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param parser_kwargs: Keyword arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param kwargs: Keyword arguments for the superclass constructor.
"""
# Some keyword arguments will be pulled out of kwargs and placed
# into parser_kwargs.
extra_parser_kwargs = dict()
for arg in ('on_duplicate_attribute',):
if arg in kwargs:
value = kwargs.pop(arg)
extra_parser_kwargs[arg] = value
super(HTMLParserTreeBuilder, self).__init__(**kwargs)
parser_args = parser_args or []
parser_kwargs = parser_kwargs or {}
parser_kwargs.update(extra_parser_kwargs)
if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
parser_kwargs['strict'] = False
if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
parser_kwargs['convert_charrefs'] = False
self.parser_args = (parser_args, parser_kwargs)
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""
:return: A 4-tuple (markup, original encoding, encoding
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
if isinstance(markup, str):
# Parse Unicode as-is.
yield (markup, None, None, False)
return
# Ask UnicodeDammit to sniff the most likely encoding.
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(markup, try_encodings, is_html=True,
exclude_encodings=exclude_encodings)
dammit = UnicodeDammit(
markup,
known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings,
is_html=True,
exclude_encodings=exclude_encodings
)
yield (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
"""
args, kwargs = self.parser_args
parser = BeautifulSoupHTMLParser(*args, **kwargs)
parser.soup = self.soup

180
libs/common/bs4/builder/_lxml.py
View file

@ -1,5 +1,6 @@
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
@ -21,6 +22,7 @@ from bs4.element import (
XMLProcessingInstruction,
)
from bs4.builder import (
DetectsXMLParsedAsHTML,
FAST,
HTML,
HTMLTreeBuilder,
@ -32,6 +34,10 @@ from bs4.dammit import EncodingDetector
LXML = 'lxml'
def _invert(d):
"Invert a dictionary."
return dict((v,k) for k, v in list(d.items()))
class LXMLTreeBuilderForXML(TreeBuilder):
DEFAULT_PARSER_CLASS = etree.XMLParser
@ -48,26 +54,79 @@ class LXMLTreeBuilderForXML(TreeBuilder):
# This namespace mapping is specified in the XML Namespace
# standard.
DEFAULT_NSMAPS = {'http://www.w3.org/XML/1998/namespace' : "xml"}
DEFAULT_NSMAPS = dict(xml='http://www.w3.org/XML/1998/namespace')
DEFAULT_NSMAPS_INVERTED = _invert(DEFAULT_NSMAPS)
# NOTE: If we parsed Element objects and looked at .sourceline,
# we'd be able to see the line numbers from the original document.
# But instead we build an XMLParser or HTMLParser object to serve
# as the target of parse messages, and those messages don't include
# line numbers.
# See: https://bugs.launchpad.net/lxml/+bug/1846906
def initialize_soup(self, soup):
"""Let the BeautifulSoup object know about the standard namespace
mapping.
:param soup: A `BeautifulSoup`.
"""
super(LXMLTreeBuilderForXML, self).initialize_soup(soup)
self._register_namespaces(self.DEFAULT_NSMAPS)
def _register_namespaces(self, mapping):
"""Let the BeautifulSoup object know about namespaces encountered
while parsing the document.
This might be useful later on when creating CSS selectors.
This will track (almost) all namespaces, even ones that were
only in scope for part of the document. If two namespaces have
the same prefix, only the first one encountered will be
tracked. Un-prefixed namespaces are not tracked.
:param mapping: A dictionary mapping namespace prefixes to URIs.
"""
for key, value in list(mapping.items()):
# This is 'if key' and not 'if key is not None' because we
# don't track un-prefixed namespaces. Soupselect will
# treat an un-prefixed namespace as the default, which
# causes confusion in some cases.
if key and key not in self.soup._namespaces:
# Let the BeautifulSoup object know about a new namespace.
# If there are multiple namespaces defined with the same
# prefix, the first one in the document takes precedence.
self.soup._namespaces[key] = value
def default_parser(self, encoding):
# This can either return a parser object or a class, which
# will be instantiated with default arguments.
"""Find the default parser for the given encoding.
:param encoding: A string.
:return: Either a parser object or a class, which
will be instantiated with default arguments.
"""
if self._default_parser is not None:
return self._default_parser
return etree.XMLParser(
target=self, strip_cdata=False, recover=True, encoding=encoding)
def parser_for(self, encoding):
"""Instantiate an appropriate parser for the given encoding.
:param encoding: A string.
:return: A parser object such as an `etree.XMLParser`.
"""
# Use the default parser.
parser = self.default_parser(encoding)
if isinstance(parser, Callable):
# Instantiate the parser with default arguments
parser = parser(target=self, strip_cdata=False, encoding=encoding)
parser = parser(
target=self, strip_cdata=False, recover=True, encoding=encoding
)
return parser
def __init__(self, parser=None, empty_element_tags=None):
def __init__(self, parser=None, empty_element_tags=None, **kwargs):
# TODO: Issue a warning if parser is present but not a
# callable, since that means there's no way to create new
# parsers for different encodings.
@ -75,8 +134,10 @@ class LXMLTreeBuilderForXML(TreeBuilder):
if empty_element_tags is not None:
self.empty_element_tags = set(empty_element_tags)
self.soup = None
self.nsmaps = [self.DEFAULT_NSMAPS]
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
self.active_namespace_prefixes = [dict(self.DEFAULT_NSMAPS)]
super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
def _getNsTag(self, tag):
# Split the namespace URL out of a fully-qualified lxml tag
# name. Copied from lxml's src/lxml/sax.py.
@ -88,26 +149,49 @@ class LXMLTreeBuilderForXML(TreeBuilder):
def prepare_markup(self, markup, user_specified_encoding=None,
exclude_encodings=None,
document_declared_encoding=None):
"""
:yield: A series of 4-tuples.
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
lxml really wants to get a bytestring and convert it to
Unicode itself. So instead of using UnicodeDammit to convert
the bytestring to Unicode using different encodings, this
implementation uses EncodingDetector to iterate over the
encodings, and tell lxml to try to parse the document as each
one in turn.
:param markup: Some markup -- hopefully a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for parsing the document.
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
# Instead of using UnicodeDammit to convert the bytestring to
# Unicode using different encodings, use EncodingDetector to
# iterate over the encodings, and tell lxml to try to parse
# the document as each one in turn.
is_html = not self.is_xml
if is_html:
self.processing_instruction_class = ProcessingInstruction
# We're in HTML mode, so if we're given XML, that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
else:
self.processing_instruction_class = XMLProcessingInstruction
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
# TODO: This is a workaround for
# https://bugs.launchpad.net/lxml/+bug/1948551.
# We can remove it once the upstream issue is fixed.
if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}':
markup = markup[1:]
yield markup, None, document_declared_encoding, False
if isinstance(markup, str):
@ -116,9 +200,19 @@ class LXMLTreeBuilderForXML(TreeBuilder):
yield (markup.encode("utf8"), "utf8",
document_declared_encoding, False)
try_encodings = [user_specified_encoding, document_declared_encoding]
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
detector = EncodingDetector(
markup, try_encodings, is_html, exclude_encodings)
markup, known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings, is_html=is_html,
exclude_encodings=exclude_encodings
)
for encoding in detector.encodings:
yield (detector.markup, encoding, document_declared_encoding, False)
@ -141,10 +235,10 @@ class LXMLTreeBuilderForXML(TreeBuilder):
self.parser.feed(data)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(str(e))
raise ParserRejectedMarkup(e)
def close(self):
self.nsmaps = [self.DEFAULT_NSMAPS]
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
def start(self, name, attrs, nsmap={}):
# Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
@ -158,8 +252,28 @@ class LXMLTreeBuilderForXML(TreeBuilder):
self.nsmaps.append(None)
elif len(nsmap) > 0:
# A new namespace mapping has come into play.
inverted_nsmap = dict((value, key) for key, value in list(nsmap.items()))
self.nsmaps.append(inverted_nsmap)
# First, Let the BeautifulSoup object know about it.
self._register_namespaces(nsmap)
# Then, add it to our running list of inverted namespace
# mappings.
self.nsmaps.append(_invert(nsmap))
# The currently active namespace prefixes have
# changed. Calculate the new mapping so it can be stored
# with all Tag objects created while these prefixes are in
# scope.
current_mapping = dict(self.active_namespace_prefixes[-1])
current_mapping.update(nsmap)
# We should not track un-prefixed namespaces as we can only hold one
# and it will be recognized as the default namespace by soupsieve,
# which may be confusing in some situations.
if '' in current_mapping:
del current_mapping['']
self.active_namespace_prefixes.append(current_mapping)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
@ -184,8 +298,11 @@ class LXMLTreeBuilderForXML(TreeBuilder):
namespace, name = self._getNsTag(name)
nsprefix = self._prefix_for_namespace(namespace)
self.soup.handle_starttag(name, namespace, nsprefix, attrs)
self.soup.handle_starttag(
name, namespace, nsprefix, attrs,
namespaces=self.active_namespace_prefixes[-1]
)
def _prefix_for_namespace(self, namespace):
"""Find the currently active prefix for the given namespace."""
if namespace is None:
@ -209,13 +326,20 @@ class LXMLTreeBuilderForXML(TreeBuilder):
if len(self.nsmaps) > 1:
# This tag, or one of its parents, introduced a namespace
# mapping, so pop it off the stack.
self.nsmaps.pop()
out_of_scope_nsmap = self.nsmaps.pop()
if out_of_scope_nsmap is not None:
# This tag introduced a namespace mapping which is no
# longer in scope. Recalculate the currently active
# namespace prefixes.
self.active_namespace_prefixes.pop()
def pi(self, target, data):
self.soup.endData()
self.soup.handle_data(target + ' ' + data)
data = target + ' ' + data
self.soup.handle_data(data)
self.soup.endData(self.processing_instruction_class)
def data(self, content):
self.soup.handle_data(content)
@ -254,7 +378,7 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
self.parser.feed(markup)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(str(e))
raise ParserRejectedMarkup(e)
def test_fragment_to_document(self, fragment):