gronod/headphones
1
0
Fork 0
mirror of https://github.com/rembo10/headphones.git synced 2026-07-20 16:03:59 +01:00
Code Issues Packages Projects Releases Wiki Activity

Initial python3 changes

Browse Source 
Mostly just updating libraries, removing string encoding/decoding,
fixing some edge cases. No new functionality was added in this
commit.
This commit is contained in:
rembo10
2022-01-14 10:38:03 +05:30
parent 9a7006ad14
commit ab4dd18be4
813 changed files with 146338 additions and 65753 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/bs4/__init__.py
+464 -128
View File
@@ -1,32 +1,40 @@
"""Beautiful Soup
Elixir and Tonic
"The Screen-Scraper's Friend"
"""Beautiful Soup Elixir and Tonic - "The Screen-Scraper's Friend".
http://www.crummy.com/software/BeautifulSoup/
Beautiful Soup uses a pluggable XML or HTML parser to parse a
(possibly invalid) document into a tree representation. Beautiful Soup
provides provides methods and Pythonic idioms that make it easy to
navigate, search, and modify the parse tree.
provides methods and Pythonic idioms that make it easy to navigate,
search, and modify the parse tree.
Beautiful Soup works with Python 2.6 and up. It works better if lxml
Beautiful Soup works with Python 3.5 and up. It works better if lxml
and/or html5lib is installed.
For more than you ever wanted to know about Beautiful Soup, see the
documentation:
http://www.crummy.com/software/BeautifulSoup/bs4/doc/
documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
"""
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "4.4.0"
__copyright__ = "Copyright (c) 2004-2015 Leonard Richardson"
__version__ = "4.10.0"
__copyright__ = "Copyright (c) 2004-2021 Leonard Richardson"
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = ['BeautifulSoup']
from collections import Counter
import os
import re
import sys
import traceback
import warnings
# The very first thing we do is give a useful error if someone is
# running this code under Python 2.
if sys.version_info.major < 3:
raise ImportError('You are trying to use a Python 3-specific version of Beautiful Soup under Python 2. This will not work. The final version of Beautiful Soup to support Python 2 was 4.9.3.')
from .builder import builder_registry, ParserRejectedMarkup
from .dammit import UnicodeDammit
from .element import (
@@ -38,28 +46,49 @@ from .element import (
NavigableString,
PageElement,
ProcessingInstruction,
PYTHON_SPECIFIC_ENCODINGS,
ResultSet,
Script,
Stylesheet,
SoupStrainer,
Tag,
TemplateString,
)
# The very first thing we do is give a useful error if someone is
# running this code under Python 3 without converting it.
'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work.'<>'You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
# Define some custom warnings.
class GuessedAtParserWarning(UserWarning):
"""The warning issued when BeautifulSoup has to guess what parser to
use -- probably because no parser was specified in the constructor.
"""
class MarkupResemblesLocatorWarning(UserWarning):
"""The warning issued when BeautifulSoup is given 'markup' that
actually looks like a resource locator -- a URL or a path to a file
on disk.
"""
class BeautifulSoup(Tag):
"""
This class defines the basic interface called by the tree builders.
"""A data structure representing a parsed HTML or XML document.
These methods will be called by the parser:
reset()
feed(markup)
Most of the methods you'll call on a BeautifulSoup object are inherited from
PageElement or Tag.
Internally, this class defines the basic interface called by the
tree builders when converting an HTML/XML document into a data
structure. The interface abstracts away the differences between
parsers. To write a new tree builder, you'll need to understand
these methods as a whole.
These methods will be called by the BeautifulSoup constructor:
* reset()
* feed(markup)
The tree builder may call these methods from its feed() implementation:
handle_starttag(name, attrs) # See note about return value
handle_endtag(name)
handle_data(data) # Appends to the current data node
endData(containerClass=NavigableString) # Ends the current data node
* handle_starttag(name, attrs) # See note about return value
* handle_endtag(name)
* handle_data(data) # Appends to the current data node
* endData(containerClass) # Ends the current data node
No matter how complicated the underlying parser is, you should be
able to build a tree using 'start tag' events, 'end tag' events,
@@ -69,24 +98,77 @@ class BeautifulSoup(Tag):
like HTML's <br> tag), call handle_starttag and then
handle_endtag.
"""
ROOT_TAG_NAME = u'[document]'
# Since BeautifulSoup subclasses Tag, it's possible to treat it as
# a Tag with a .name. This name makes it clear the BeautifulSoup
# object isn't a real markup tag.
ROOT_TAG_NAME = '[document]'
# If the end-user gives no indication which tree builder they
# want, look for one with these features.
DEFAULT_BUILDER_FEATURES = ['html', 'fast']
# A string containing all ASCII whitespace characters, used in
# endData() to detect data chunks that seem 'empty'.
ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nTo get rid of this warning, change this:\n\n BeautifulSoup([your markup])\n\nto this:\n\n BeautifulSoup([your markup], \"%(parser)s\")\n"
NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nThe code that caused this warning is on line %(line_number)s of the file %(filename)s. To get rid of this warning, pass the additional argument 'features=\"%(parser)s\"' to the BeautifulSoup constructor.\n"
def __init__(self, markup="", features=None, builder=None,
parse_only=None, from_encoding=None, exclude_encodings=None,
**kwargs):
"""The Soup object is initialized as the 'root tag', and the
provided markup (which can be a string or a file-like object)
is fed into the underlying parser."""
element_classes=None, **kwargs):
"""Constructor.
:param markup: A string or a file-like object representing
markup to be parsed.
:param features: Desirable features of the parser to be
used. This may be the name of a specific parser ("lxml",
"lxml-xml", "html.parser", or "html5lib") or it may be the
type of markup to be used ("html", "html5", "xml"). It's
recommended that you name a specific parser, so that
Beautiful Soup gives you the same results across platforms
and virtual environments.
:param builder: A TreeBuilder subclass to instantiate (or
instance to use) instead of looking one up based on
`features`. You only need to use this if you've implemented a
custom TreeBuilder.
:param parse_only: A SoupStrainer. Only parts of the document
matching the SoupStrainer will be considered. This is useful
when parsing part of a document that would otherwise be too
large to fit into memory.
:param from_encoding: A string indicating the encoding of the
document to be parsed. Pass this in if Beautiful Soup is
guessing wrongly about the document's encoding.
:param exclude_encodings: A list of strings indicating
encodings known to be wrong. Pass this in if you don't know
the document's encoding but you know Beautiful Soup's guess is
wrong.
:param element_classes: A dictionary mapping BeautifulSoup
classes like Tag and NavigableString, to other classes you'd
like to be instantiated instead as the parse tree is
built. This is useful for subclassing Tag or NavigableString
to modify default behavior.
:param kwargs: For backwards compatibility purposes, the
constructor accepts certain keyword arguments used in
Beautiful Soup 3. None of these arguments do anything in
Beautiful Soup 4; they will result in a warning and then be
ignored.
Apart from this, any keyword arguments passed into the
BeautifulSoup constructor are propagated to the TreeBuilder
constructor. This makes it possible to configure a
TreeBuilder by passing in arguments, not just by saying which
one to use.
"""
if 'convertEntities' in kwargs:
del kwargs['convertEntities']
warnings.warn(
"BS4 does not respect the convertEntities argument to the "
"BeautifulSoup constructor. Entities are always converted "
@@ -137,14 +219,24 @@ class BeautifulSoup(Tag):
from_encoding = from_encoding or deprecated_argument(
"fromEncoding", "from_encoding")
if len(kwargs) > 0:
arg = kwargs.keys().pop()
raise TypeError(
"__init__() got an unexpected keyword argument '%s'" % arg)
if from_encoding and isinstance(markup, str):
warnings.warn("You provided Unicode markup but also provided a value for from_encoding. Your from_encoding will be ignored.")
from_encoding = None
if builder is None:
original_features = features
if isinstance(features, basestring):
self.element_classes = element_classes or dict()
# We need this information to track whether or not the builder
# was specified well enough that we can omit the 'you need to
# specify a parser' warning.
original_builder = builder
original_features = features
if isinstance(builder, type):
# A builder class was passed in; it needs to be instantiated.
builder_class = builder
builder = None
elif builder is None:
if isinstance(features, str):
features = [features]
if features is None or len(features) == 0:
features = self.DEFAULT_BUILDER_FEATURES
@@ -154,58 +246,113 @@ class BeautifulSoup(Tag):
"Couldn't find a tree builder with the features you "
"requested: %s. Do you need to install a parser library?"
% ",".join(features))
builder = builder_class()
if not (original_features == builder.NAME or
original_features in builder.ALTERNATE_NAMES):
# At this point either we have a TreeBuilder instance in
# builder, or we have a builder_class that we can instantiate
# with the remaining **kwargs.
if builder is None:
builder = builder_class(**kwargs)
if not original_builder and not (
original_features == builder.NAME or
original_features in builder.ALTERNATE_NAMES
) and markup:
# The user did not tell us which TreeBuilder to use,
# and we had to guess. Issue a warning.
if builder.is_xml:
markup_type = "XML"
else:
markup_type = "HTML"
warnings.warn(self.NO_PARSER_SPECIFIED_WARNING % dict(
parser=builder.NAME,
markup_type=markup_type))
# This code adapted from warnings.py so that we get the same line
# of code as our warnings.warn() call gets, even if the answer is wrong
# (as it may be in a multithreading situation).
caller = None
try:
caller = sys._getframe(1)
except ValueError:
pass
if caller:
globals = caller.f_globals
line_number = caller.f_lineno
else:
globals = sys.__dict__
line_number= 1
filename = globals.get('__file__')
if filename:
fnl = filename.lower()
if fnl.endswith((".pyc", ".pyo")):
filename = filename[:-1]
if filename:
# If there is no filename at all, the user is most likely in a REPL,
# and the warning is not necessary.
values = dict(
filename=filename,
line_number=line_number,
parser=builder.NAME,
markup_type=markup_type
)
warnings.warn(
self.NO_PARSER_SPECIFIED_WARNING % values,
GuessedAtParserWarning, stacklevel=2
)
else:
if kwargs:
warnings.warn("Keyword arguments to the BeautifulSoup constructor will be ignored. These would normally be passed into the TreeBuilder constructor, but a TreeBuilder instance was passed in as `builder`.")
self.builder = builder
self.is_xml = builder.is_xml
self.builder.soup = self
self.known_xml = self.is_xml
self._namespaces = dict()
self.parse_only = parse_only
self.builder.initialize_soup(self)
if hasattr(markup, 'read'): # It's a file-type object.
markup = markup.read()
elif len(markup) <= 256:
elif len(markup) <= 256 and (
(isinstance(markup, bytes) and not b'<' in markup)
or (isinstance(markup, str) and not '<' in markup)
):
# Print out warnings for a couple beginner problems
# involving passing non-markup to Beautiful Soup.
# Beautiful Soup will still parse the input as markup,
# just in case that's what the user really wants.
if (isinstance(markup, unicode)
if (isinstance(markup, str)
and not os.path.supports_unicode_filenames):
possible_filename = markup.encode("utf8")
else:
possible_filename = markup
is_file = False
is_directory = False
try:
is_file = os.path.exists(possible_filename)
except Exception, e:
if is_file:
is_directory = os.path.isdir(possible_filename)
except Exception as e:
# This is almost certainly a problem involving
# characters not valid in filenames on this
# system. Just let it go.
pass
if is_file:
if isinstance(markup, unicode):
markup = markup.encode("utf8")
if is_directory:
warnings.warn(
'"%s" looks like a filename, not markup. You should probably open this file and pass the filehandle into Beautiful Soup.' % markup)
if markup[:5] == "http:" or markup[:6] == "https:":
# TODO: This is ugly but I couldn't get it to work in
# Python 3 otherwise.
if ((isinstance(markup, bytes) and not b' ' in markup)
or (isinstance(markup, unicode) and not u' ' in markup)):
if isinstance(markup, unicode):
markup = markup.encode("utf8")
warnings.warn(
'"%s" looks like a URL. Beautiful Soup is not an HTTP client. You should probably use an HTTP client to get the document behind the URL, and feed that document to Beautiful Soup.' % markup)
'"%s" looks like a directory name, not markup. You may'
' want to open a file found in this directory and pass'
' the filehandle into Beautiful Soup.' % (
self._decode_markup(markup)
),
MarkupResemblesLocatorWarning
)
elif is_file:
warnings.warn(
'"%s" looks like a filename, not markup. You should'
' probably open this file and pass the filehandle into'
' Beautiful Soup.' % self._decode_markup(markup),
MarkupResemblesLocatorWarning
)
self._check_markup_is_url(markup)
rejections = []
success = False
for (self.markup, self.original_encoding, self.declared_html_encoding,
self.contains_replacement_characters) in (
self.builder.prepare_markup(
@@ -213,26 +360,88 @@ class BeautifulSoup(Tag):
self.reset()
try:
self._feed()
success = True
break
except ParserRejectedMarkup:
except ParserRejectedMarkup as e:
rejections.append(e)
pass
if not success:
other_exceptions = [str(e) for e in rejections]
raise ParserRejectedMarkup(
"The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help.\n\nOriginal exception(s) from parser:\n " + "\n ".join(other_exceptions)
)
# Clear out the markup and remove the builder's circular
# reference to this object.
self.markup = None
self.builder.soup = None
def __copy__(self):
return type(self)(self.encode(), builder=self.builder)
"""Copy a BeautifulSoup object by converting the document to a string and parsing it again."""
copy = type(self)(
self.encode('utf-8'), builder=self.builder, from_encoding='utf-8'
)
# Although we encoded the tree to UTF-8, that may not have
# been the encoding of the original markup. Set the copy's
# .original_encoding to reflect the original object's
# .original_encoding.
copy.original_encoding = self.original_encoding
return copy
def __getstate__(self):
# Frequently a tree builder can't be pickled.
d = dict(self.__dict__)
if 'builder' in d and not self.builder.picklable:
del d['builder']
d['builder'] = None
return d
@classmethod
def _decode_markup(cls, markup):
"""Ensure `markup` is bytes so it's safe to send into warnings.warn.
TODO: warnings.warn had this problem back in 2010 but it might not
anymore.
"""
if isinstance(markup, bytes):
decoded = markup.decode('utf-8', 'replace')
else:
decoded = markup
return decoded
@classmethod
def _check_markup_is_url(cls, markup):
"""Error-handling method to raise a warning if incoming markup looks
like a URL.
:param markup: A string.
"""
if isinstance(markup, bytes):
space = b' '
cant_start_with = (b"http:", b"https:")
elif isinstance(markup, str):
space = ' '
cant_start_with = ("http:", "https:")
else:
return
if any(markup.startswith(prefix) for prefix in cant_start_with):
if not space in markup:
warnings.warn(
'"%s" looks like a URL. Beautiful Soup is not an'
' HTTP client. You should probably use an HTTP client like'
' requests to get the document behind the URL, and feed'
' that document to Beautiful Soup.' % cls._decode_markup(
markup
),
MarkupResemblesLocatorWarning
)
def _feed(self):
"""Internal method that parses previously set markup, creating a large
number of Tag and NavigableString objects.
"""
# Convert the document to Unicode.
self.builder.reset()
@@ -243,50 +452,112 @@ class BeautifulSoup(Tag):
self.popTag()
def reset(self):
"""Reset this object to a state as though it had never parsed any
markup.
"""
Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
self.hidden = 1
self.builder.reset()
self.current_data = []
self.currentTag = None
self.tagStack = []
self.open_tag_counter = Counter()
self.preserve_whitespace_tag_stack = []
self.string_container_stack = []
self.pushTag(self)
def new_tag(self, name, namespace=None, nsprefix=None, **attrs):
"""Create a new tag associated with this soup."""
return Tag(None, self.builder, name, namespace, nsprefix, attrs)
def new_tag(self, name, namespace=None, nsprefix=None, attrs={},
sourceline=None, sourcepos=None, **kwattrs):
"""Create a new Tag associated with this BeautifulSoup object.
def new_string(self, s, subclass=NavigableString):
"""Create a new NavigableString associated with this soup."""
return subclass(s)
:param name: The name of the new Tag.
:param namespace: The URI of the new Tag's XML namespace, if any.
:param prefix: The prefix for the new Tag's XML namespace, if any.
:param attrs: A dictionary of this Tag's attribute values; can
be used instead of `kwattrs` for attributes like 'class'
that are reserved words in Python.
:param sourceline: The line number where this tag was
(purportedly) found in its source document.
:param sourcepos: The character position within `sourceline` where this
tag was (purportedly) found.
:param kwattrs: Keyword arguments for the new Tag's attribute values.
def insert_before(self, successor):
"""
kwattrs.update(attrs)
return self.element_classes.get(Tag, Tag)(
None, self.builder, name, namespace, nsprefix, kwattrs,
sourceline=sourceline, sourcepos=sourcepos
)
def string_container(self, base_class=None):
container = base_class or NavigableString
# There may be a general override of NavigableString.
container = self.element_classes.get(
container, container
)
# On top of that, we may be inside a tag that needs a special
# container class.
if self.string_container_stack and container is NavigableString:
container = self.builder.string_containers.get(
self.string_container_stack[-1].name, container
)
return container
def new_string(self, s, subclass=None):
"""Create a new NavigableString associated with this BeautifulSoup
object.
"""
container = self.string_container(subclass)
return container(s)
def insert_before(self, *args):
"""This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
it because there is nothing before or after it in the parse tree.
"""
raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
def insert_after(self, successor):
def insert_after(self, *args):
"""This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
it because there is nothing before or after it in the parse tree.
"""
raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
def popTag(self):
"""Internal method called by _popToTag when a tag is closed."""
tag = self.tagStack.pop()
if tag.name in self.open_tag_counter:
self.open_tag_counter[tag.name] -= 1
if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
self.preserve_whitespace_tag_stack.pop()
#print "Pop", tag.name
if self.string_container_stack and tag == self.string_container_stack[-1]:
self.string_container_stack.pop()
#print("Pop", tag.name)
if self.tagStack:
self.currentTag = self.tagStack[-1]
return self.currentTag
def pushTag(self, tag):
#print "Push", tag.name
if self.currentTag:
"""Internal method called by handle_starttag when a tag is opened."""
#print("Push", tag.name)
if self.currentTag is not None:
self.currentTag.contents.append(tag)
self.tagStack.append(tag)
self.currentTag = self.tagStack[-1]
if tag.name != self.ROOT_TAG_NAME:
self.open_tag_counter[tag.name] += 1
if tag.name in self.builder.preserve_whitespace_tags:
self.preserve_whitespace_tag_stack.append(tag)
if tag.name in self.builder.string_containers:
self.string_container_stack.append(tag)
def endData(self, containerClass=NavigableString):
def endData(self, containerClass=None):
"""Method called by the TreeBuilder when the end of a data segment
occurs.
"""
if self.current_data:
current_data = u''.join(self.current_data)
current_data = ''.join(self.current_data)
# If whitespace is not preserved, and this string contains
# nothing but ASCII spaces, replace it with a single space
# or newline.
@@ -311,61 +582,93 @@ class BeautifulSoup(Tag):
not self.parse_only.search(current_data)):
return
containerClass = self.string_container(containerClass)
o = containerClass(current_data)
self.object_was_parsed(o)
def object_was_parsed(self, o, parent=None, most_recent_element=None):
"""Add an object to the parse tree."""
parent = parent or self.currentTag
previous_element = most_recent_element or self._most_recent_element
"""Method called by the TreeBuilder to integrate an object into the parse tree."""
if parent is None:
parent = self.currentTag
if most_recent_element is not None:
previous_element = most_recent_element
else:
previous_element = self._most_recent_element
next_element = previous_sibling = next_sibling = None
if isinstance(o, Tag):
next_element = o.next_element
next_sibling = o.next_sibling
previous_sibling = o.previous_sibling
if not previous_element:
if previous_element is None:
previous_element = o.previous_element
fix = parent.next_element is not None
o.setup(parent, previous_element, next_element, previous_sibling, next_sibling)
self._most_recent_element = o
parent.contents.append(o)
if parent.next_sibling:
# This node is being inserted into an element that has
# already been parsed. Deal with any dangling references.
index = parent.contents.index(o)
if index == 0:
previous_element = parent
previous_sibling = None
else:
previous_element = previous_sibling = parent.contents[index-1]
if index == len(parent.contents)-1:
next_element = parent.next_sibling
next_sibling = None
else:
next_element = next_sibling = parent.contents[index+1]
# Check if we are inserting into an already parsed node.
if fix:
self._linkage_fixer(parent)
o.previous_element = previous_element
if previous_element:
previous_element.next_element = o
o.next_element = next_element
if next_element:
next_element.previous_element = o
o.next_sibling = next_sibling
if next_sibling:
next_sibling.previous_sibling = o
o.previous_sibling = previous_sibling
if previous_sibling:
previous_sibling.next_sibling = o
def _linkage_fixer(self, el):
"""Make sure linkage of this fragment is sound."""
first = el.contents[0]
child = el.contents[-1]
descendant = child
if child is first and el.parent is not None:
# Parent should be linked to first child
el.next_element = child
# We are no longer linked to whatever this element is
prev_el = child.previous_element
if prev_el is not None and prev_el is not el:
prev_el.next_element = None
# First child should be linked to the parent, and no previous siblings.
child.previous_element = el
child.previous_sibling = None
# We have no sibling as we've been appended as the last.
child.next_sibling = None
# This index is a tag, dig deeper for a "last descendant"
if isinstance(child, Tag) and child.contents:
descendant = child._last_descendant(False)
# As the final step, link last descendant. It should be linked
# to the parent's next sibling (if found), else walk up the chain
# and find a parent with a sibling. It should have no next sibling.
descendant.next_element = None
descendant.next_sibling = None
target = el
while True:
if target is None:
break
elif target.next_sibling is not None:
descendant.next_element = target.next_sibling
target.next_sibling.previous_element = child
break
target = target.parent
def _popToTag(self, name, nsprefix=None, inclusivePop=True):
"""Pops the tag stack up to and including the most recent
instance of the given tag. If inclusivePop is false, pops the tag
stack up to but *not* including the most recent instqance of
the given tag."""
#print "Popping to %s" % name
instance of the given tag.
If there are no open tags with the given name, nothing will be
popped.
:param name: Pop up to the most recent tag with this name.
:param nsprefix: The namespace prefix that goes with `name`.
:param inclusivePop: It this is false, pops the tag stack up
to but *not* including the most recent instqance of the
given tag.
"""
#print("Popping to %s" % name)
if name == self.ROOT_TAG_NAME:
# The BeautifulSoup object itself can never be popped.
return
@@ -374,6 +677,8 @@ class BeautifulSoup(Tag):
stack_size = len(self.tagStack)
for i in range(stack_size - 1, 0, -1):
if not self.open_tag_counter.get(name):
break
t = self.tagStack[i]
if (name == t.name and nsprefix == t.prefix):
if inclusivePop:
@@ -383,16 +688,24 @@ class BeautifulSoup(Tag):
return most_recently_popped
def handle_starttag(self, name, namespace, nsprefix, attrs):
"""Push a start tag on to the stack.
def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
sourcepos=None):
"""Called by the tree builder when a new tag is encountered.
If this method returns None, the tag was rejected by the
SoupStrainer. You should proceed as if the tag had not occured
:param name: Name of the tag.
:param nsprefix: Namespace prefix for the tag.
:param attrs: A dictionary of attribute values.
:param sourceline: The line number where this tag was found in its
source document.
:param sourcepos: The character position within `sourceline` where this
tag was found.
If this method returns None, the tag was rejected by an active
SoupStrainer. You should proceed as if the tag had not occurred
in the document. For instance, if this was a self-closing tag,
don't call handle_endtag.
"""
# print "Start tag %s: %s" % (name, attrs)
# print("Start tag %s: %s" % (name, attrs))
self.endData()
if (self.parse_only and len(self.tagStack) <= 1
@@ -400,38 +713,57 @@ class BeautifulSoup(Tag):
or not self.parse_only.search_tag(name, attrs))):
return None
tag = Tag(self, self.builder, name, namespace, nsprefix, attrs,
self.currentTag, self._most_recent_element)
tag = self.element_classes.get(Tag, Tag)(
self, self.builder, name, namespace, nsprefix, attrs,
self.currentTag, self._most_recent_element,
sourceline=sourceline, sourcepos=sourcepos
)
if tag is None:
return tag
if self._most_recent_element:
if self._most_recent_element is not None:
self._most_recent_element.next_element = tag
self._most_recent_element = tag
self.pushTag(tag)
return tag
def handle_endtag(self, name, nsprefix=None):
#print "End tag: " + name
"""Called by the tree builder when an ending tag is encountered.
:param name: Name of the tag.
:param nsprefix: Namespace prefix for the tag.
"""
#print("End tag: " + name)
self.endData()
self._popToTag(name, nsprefix)
def handle_data(self, data):
"""Called by the tree builder when a chunk of textual data is encountered."""
self.current_data.append(data)
def decode(self, pretty_print=False,
eventual_encoding=DEFAULT_OUTPUT_ENCODING,
formatter="minimal"):
"""Returns a string or Unicode representation of this document.
To get Unicode, pass None for encoding."""
"""Returns a string or Unicode representation of the parse tree
as an HTML or XML document.
:param pretty_print: If this is True, indentation will be used to
make the document more readable.
:param eventual_encoding: The encoding of the final document.
If this is None, the document will be a Unicode string.
"""
if self.is_xml:
# Print the XML declaration
encoding_part = ''
if eventual_encoding in PYTHON_SPECIFIC_ENCODINGS:
# This is a special Python encoding; it can't actually
# go into an XML document because it means nothing
# outside of Python.
eventual_encoding = None
if eventual_encoding != None:
encoding_part = ' encoding="%s"' % eventual_encoding
prefix = u'<?xml version="1.0"%s?>\n' % encoding_part
prefix = '<?xml version="1.0"%s?>\n' % encoding_part
else:
prefix = u''
prefix = ''
if not pretty_print:
indent_level = None
else:
@@ -439,7 +771,7 @@ class BeautifulSoup(Tag):
return prefix + super(BeautifulSoup, self).decode(
indent_level, eventual_encoding, formatter)
# Alias to make it easier to type import: 'from bs4 import _soup'
# Aliases to make it easier to get started quickly, e.g. 'from bs4 import _soup'
_s = BeautifulSoup
_soup = BeautifulSoup
@@ -455,14 +787,18 @@ class BeautifulStoneSoup(BeautifulSoup):
class StopParsing(Exception):
"""Exception raised by a TreeBuilder if it's unable to continue parsing."""
pass
class FeatureNotFound(ValueError):
"""Exception raised by the BeautifulSoup constructor if no parser with the
requested features is found.
"""
pass
#By default, act as an HTML pretty-printer.
#If this file is run as a script, act as an HTML pretty-printer.
if __name__ == '__main__':
import sys
soup = BeautifulSoup(sys.stdin)
print soup.prettify()
print((soup.prettify()))
lib/bs4/builder/__init__.py
+228 -32
View File
@@ -1,11 +1,17 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
from collections import defaultdict
import itertools
import sys
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
whitespace_re
)
Stylesheet,
Script,
TemplateString,
nonwhitespace_re
)
__all__ = [
'HTMLTreeBuilder',
@@ -24,18 +30,33 @@ HTML_5 = 'html5'
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
@@ -78,7 +99,7 @@ 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 = []
@@ -86,19 +107,89 @@ 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):
@@ -110,24 +201,58 @@ 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.
@@ -139,16 +264,36 @@ 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
@@ -156,14 +301,14 @@ class TreeBuilder(object):
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
for attr in attrs.keys():
for attr in list(attrs.keys()):
if attr in universal or (tag_specific and attr in tag_specific):
# We have a "class"-type attribute whose string
# value is a whitespace-separated list of
# values. Split it into a list.
value = attrs[attr]
if isinstance(value, basestring):
values = whitespace_re.split(value)
if isinstance(value, str):
values = nonwhitespace_re.findall(value)
else:
# html5lib sometimes calls setAttributes twice
# for the same tag when rearranging the parse
@@ -176,7 +321,11 @@ class TreeBuilder(object):
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()
@@ -186,11 +335,11 @@ 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):
@@ -227,10 +376,36 @@ class HTMLTreeBuilder(TreeBuilder):
Such as which tags are empty-element tags.
"""
preserve_whitespace_tags = set(['pre', 'textarea'])
empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta',
'spacer', 'link', 'frame', 'base'])
empty_element_tags = set([
# These are from HTML5.
'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
# These are from earlier versions of HTML and are removed in HTML5.
'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
])
# The HTML standard defines these as block-level elements. Beautiful
# Soup does not treat these elements differently from other elements,
# 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"])
# The HTML standard defines an unusual content model for these tags.
# We represent this by using a string class other than NavigableString
# inside these tags.
#
# 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.
#
# TODO: Arguably <noscript> could go here but it seems
# qualitatively different from the other tags.
DEFAULT_STRING_CONTAINERS = {
'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,
# class="foo bar" means that the 'class' attribute has two values,
@@ -238,7 +413,7 @@ 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'],
@@ -255,7 +430,19 @@ 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
@@ -290,8 +477,7 @@ class HTMLTreeBuilder(TreeBuilder):
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)
@@ -302,12 +488,22 @@ 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:
lib/bs4/builder/_html5lib.py
+187 -49
View File
@@ -1,9 +1,12 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTML5TreeBuilder',
]
from pdb import set_trace
import warnings
import re
from bs4.builder import (
PERMISSIVE,
HTML,
@@ -12,10 +15,13 @@ from bs4.builder import (
)
from bs4.element import (
NamespacedAttribute,
whitespace_re,
nonwhitespace_re,
)
import html5lib
from html5lib.constants import namespaces
from html5lib.constants import (
namespaces,
prefixes,
)
from bs4.element import (
Comment,
Doctype,
@@ -23,13 +29,37 @@ from bs4.element import (
Tag,
)
try:
# Pre-0.99999999
from html5lib.treebuilders import _base as treebuilder_base
new_html5lib = False
except ImportError as e:
# 0.99999999 and up
from html5lib.treebuilders import base as treebuilder_base
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.
@@ -47,32 +77,66 @@ 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)
doc = parser.parse(markup, encoding=self.user_specified_encoding)
self.underlying_builder.parser = parser
extra_kwargs = dict()
if not isinstance(markup, str):
if new_html5lib:
extra_kwargs['override_encoding'] = self.user_specified_encoding
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, unicode):
if isinstance(markup, str):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
else:
doc.original_encoding = parser.tokenizer.stream.charEncoding[0]
original_encoding = parser.tokenizer.stream.charEncoding[0]
if not isinstance(original_encoding, str):
# In 0.99999999 and up, the encoding is an html5lib
# Encoding object. We want to use a string for compatibility
# 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(
self.soup, namespaceHTMLElements)
namespaceHTMLElements, self.soup,
store_line_numbers=self.store_line_numbers
)
return self.underlying_builder
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><head></head><body>%s</body></html>' % fragment
return '<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
def __init__(self, soup, namespaceHTMLElements):
self.soup = soup
class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
def __init__(self, namespaceHTMLElements, soup=None,
store_line_numbers=True, **kwargs):
if soup:
self.soup = soup
else:
from bs4 import BeautifulSoup
# 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)
@@ -86,14 +150,26 @@ class TreeBuilderForHtml5lib(html5lib.treebuilders._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):
return TextNode(Comment(data), self.soup)
def fragmentClass(self):
self.soup = BeautifulSoup("")
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)
@@ -105,7 +181,57 @@ class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
return self.soup
def getFragment(self):
return html5lib.treebuilders._base.TreeBuilder.getFragment(self).element
return treebuilder_base.TreeBuilder.getFragment(self).element
def testSerializer(self, element):
from bs4 import BeautifulSoup
rv = []
doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
def serializeElement(element, indent=0):
if isinstance(element, BeautifulSoup):
pass
if isinstance(element, Doctype):
m = doctype_re.match(element)
if m:
name = m.group(1)
if m.lastindex > 1:
publicId = m.group(2) or ""
systemId = m.group(3) or m.group(4) or ""
rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
(' ' * indent, name, publicId, systemId))
else:
rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
else:
rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
elif isinstance(element, Comment):
rv.append("|%s<!-- %s -->" % (' ' * indent, element))
elif isinstance(element, NavigableString):
rv.append("|%s\"%s\"" % (' ' * indent, element))
else:
if element.namespace:
name = "%s %s" % (prefixes[element.namespace],
element.name)
else:
name = element.name
rv.append("|%s<%s>" % (' ' * indent, name))
if element.attrs:
attributes = []
for name, value in list(element.attrs.items()):
if isinstance(name, NamespacedAttribute):
name = "%s %s" % (prefixes[name.namespace], name.name)
if isinstance(value, list):
value = " ".join(value)
attributes.append((name, value))
for name, value in sorted(attributes):
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
indent += 2
for child in element.children:
serializeElement(child, indent)
serializeElement(element, 0)
return "\n".join(rv)
class AttrList(object):
def __init__(self, element):
@@ -116,11 +242,14 @@ 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
list_attr = self.element.cdata_list_attributes
if (name in list_attr['*']
or (self.element.name in list_attr
and name in list_attr[self.element.name])):
value = whitespace_re.split(value)
# A node that is being cloned may have already undergone
# this procedure.
if not isinstance(value, list):
value = nonwhitespace_re.findall(value)
self.element[name] = value
def items(self):
return list(self.attrs.items())
@@ -134,16 +263,16 @@ class AttrList(object):
return name in list(self.attrs.keys())
class Element(html5lib.treebuilders._base.Node):
class Element(treebuilder_base.Node):
def __init__(self, element, soup, namespace):
html5lib.treebuilders._base.Node.__init__(self, element.name)
treebuilder_base.Node.__init__(self, element.name)
self.element = element
self.soup = soup
self.namespace = namespace
def appendChild(self, node):
string_child = child = None
if isinstance(node, basestring):
if isinstance(node, str):
# Some other piece of code decided to pass in a string
# instead of creating a TextElement object to contain the
# string.
@@ -155,13 +284,15 @@ class Element(html5lib.treebuilders._base.Node):
child = node
elif node.element.__class__ == NavigableString:
string_child = child = node.element
node.parent = self
else:
child = node.element
node.parent = self
if not isinstance(child, basestring) and child.parent is not None:
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
@@ -171,7 +302,7 @@ class Element(html5lib.treebuilders._base.Node):
old_element.replace_with(new_element)
self.soup._most_recent_element = new_element
else:
if isinstance(node, basestring):
if isinstance(node, str):
# Create a brand new NavigableString from this string.
child = self.soup.new_string(node)
@@ -194,12 +325,12 @@ class Element(html5lib.treebuilders._base.Node):
most_recent_element=most_recent_element)
def getAttributes(self):
if isinstance(self.element, Comment):
return {}
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):
@@ -209,7 +340,7 @@ class Element(html5lib.treebuilders._base.Node):
self.soup.builder._replace_cdata_list_attribute_values(
self.name, attributes)
for name, value in attributes.items():
for name, value in list(attributes.items()):
self.element[name] = value
# The attributes may contain variables that need substitution.
@@ -221,11 +352,11 @@ class Element(html5lib.treebuilders._base.Node):
attributes = property(getAttributes, setAttributes)
def insertText(self, data, insertBefore=None):
text = TextNode(self.soup.new_string(data), self.soup)
if insertBefore:
text = TextNode(self.soup.new_string(data), self.soup)
self.insertBefore(data, insertBefore)
self.insertBefore(text, insertBefore)
else:
self.appendChild(data)
self.appendChild(text)
def insertBefore(self, node, refNode):
index = self.element.index(refNode.element)
@@ -244,9 +375,10 @@ class Element(html5lib.treebuilders._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
# Determine what this tag's next_element will be once all the children
@@ -265,29 +397,35 @@ class Element(html5lib.treebuilders._base.Node):
new_parents_last_descendant_next_element = new_parent_element.next_element
to_append = element.contents
append_after = new_parent_element.contents
if len(to_append) > 0:
# 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
# Fix the last child's next_element and next_sibling
last_child = to_append[-1]
last_child.next_element = new_parents_last_descendant_next_element
if new_parents_last_descendant_next_element:
new_parents_last_descendant_next_element.previous_element = last_child
last_child.next_sibling = None
# Find the very last element being moved. It is now the
# parent's last descendant. It has no .next_sibling and
# its .next_element is whatever the previous last
# descendant had.
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 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.
new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
last_childs_last_descendant.next_sibling = None
for child in to_append:
child.parent = new_parent_element
@@ -297,9 +435,9 @@ class Element(html5lib.treebuilders._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)
@@ -321,7 +459,7 @@ class Element(html5lib.treebuilders._base.Node):
class TextNode(Element):
def __init__(self, element, soup):
html5lib.treebuilders._base.Node.__init__(self, None)
treebuilder_base.Node.__init__(self, None)
self.element = element
self.soup = soup
lib/bs4/builder/_htmlparser.py
+264 -34
View File
@@ -1,14 +1,18 @@
# encoding: utf-8
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTMLParserTreeBuilder',
]
from HTMLParser import HTMLParser
from html.parser import HTMLParser
try:
from HTMLParser import HTMLParseError
except ImportError, e:
from html.parser import HTMLParseError
except ImportError as e:
# HTMLParseError is removed in Python 3.5. Since it can never be
# thrown in 3.5, we can just define our own class as a placeholder.
class HTMLParseError(Exception):
@@ -49,7 +53,78 @@ from bs4.builder import (
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser):
def handle_starttag(self, name, attrs):
"""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
# without an explicit closing tag. If we encounter a closing tag
# of this type, we'll associate it with one of those entries.
#
# This isn't a stack because we don't care about the
# order. It's a list of closing tags we've already handled and
# will ignore, assuming they ever show up.
self.already_closed_empty_element = []
def error(self, msg):
"""In Python 3, HTMLParser subclasses must implement error(), although
this requirement doesn't appear to be documented.
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.
"""
warnings.warn(msg)
def handle_startendtag(self, name, attrs):
"""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
# handle_endtag ourselves.
tag = self.handle_starttag(name, attrs, handle_empty_element=False)
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:
@@ -57,17 +132,71 @@ 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 = '""'
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
# handle_startendtag, but only if the original markup looked like
# <tag/>.)
#
# So we need to call handle_endtag() ourselves. Since we
# know the start event is identical to the end event, we
# don't want handle_endtag() to cross off any previous end
# events for tags of this name.
self.handle_endtag(name, check_already_closed=False)
def handle_endtag(self, name):
self.soup.handle_endtag(name)
# 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)
def handle_endtag(self, name, check_already_closed=True):
"""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)
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
@@ -78,37 +207,71 @@ class BeautifulSoupHTMLParser(HTMLParser):
else:
real_name = int(name)
try:
data = unichr(real_name)
except (ValueError, OverflowError), e:
data = u"\N{REPLACEMENT CHARACTER}"
data = None
if real_name < 256:
# HTML numeric entities are supposed to reference Unicode
# code points, but sometimes they reference code points in
# some other encoding (ahem, Windows-1252). E.g. &#147;
# instead of &#201; for LEFT DOUBLE QUOTATION MARK. This
# code tries to detect this situation and compensate.
for encoding in (self.soup.original_encoding, 'windows-1252'):
if not encoding:
continue
try:
data = bytearray([real_name]).decode(encoding)
except UnicodeDecodeError as e:
pass
if not data:
try:
data = chr(real_name)
except (ValueError, OverflowError) as e:
pass
data = data or "\N{REPLACEMENT CHARACTER}"
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
else:
data = "&%s;" % name
# If this were XML, it would be ambiguous whether "&foo"
# was an character entity reference with a missing
# semicolon or the literal string "&foo". Since this is
# HTML, we have a complete list of all character entity references,
# and this one wasn't found, so assume it's the literal string "&foo".
data = "&%s" % name
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['):]
@@ -119,53 +282,120 @@ 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.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):
"""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.
"""
:return: A 4-tuple (markup, original encoding, encoding
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
"""
if isinstance(markup, unicode):
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
try:
parser.feed(markup)
except HTMLParseError, e:
parser.close()
except HTMLParseError as e:
warnings.warn(RuntimeWarning(
"Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
raise e
parser.already_closed_empty_element = []
# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
lib/bs4/builder/_lxml.py
+134 -40
View File
@@ -1,17 +1,25 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
]
try:
from collections.abc import Callable # Python 3.6
except ImportError as e:
from collections import Callable
from io import BytesIO
from StringIO import StringIO
import collections
from io import StringIO
from lxml import etree
from bs4.element import (
Comment,
Doctype,
NamespacedAttribute,
ProcessingInstruction,
XMLProcessingInstruction,
)
from bs4.builder import (
FAST,
@@ -25,10 +33,15 @@ 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
is_xml = True
processing_instruction_class = XMLProcessingInstruction
NAME = "lxml-xml"
ALTERNATE_NAMES = ["xml"]
@@ -40,26 +53,70 @@ 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.
:param mapping: A dictionary mapping namespace prefixes to URIs.
"""
for key, value in list(mapping.items()):
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, collections.Callable):
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.
@@ -67,8 +124,9 @@ 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]
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.
@@ -80,39 +138,68 @@ 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.
"""
if isinstance(markup, unicode):
is_html = not self.is_xml
if is_html:
self.processing_instruction_class = ProcessingInstruction
else:
self.processing_instruction_class = XMLProcessingInstruction
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
yield markup, None, document_declared_encoding, False
if isinstance(markup, unicode):
if isinstance(markup, str):
# No, apparently not. Convert the Unicode to UTF-8 and
# tell lxml to parse it as UTF-8.
yield (markup.encode("utf8"), "utf8",
document_declared_encoding, False)
# 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
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)
def feed(self, markup):
if isinstance(markup, bytes):
markup = BytesIO(markup)
elif isinstance(markup, unicode):
elif isinstance(markup, str):
markup = StringIO(markup)
# Call feed() at least once, even if the markup is empty,
@@ -127,30 +214,36 @@ class LXMLTreeBuilderForXML(TreeBuilder):
if len(data) != 0:
self.parser.feed(data)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
raise ParserRejectedMarkup(str(e))
except (UnicodeDecodeError, LookupError, etree.ParserError) as 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.
attrs = dict(attrs)
nsprefix = None
# Invert each namespace map as it comes in.
if len(self.nsmaps) > 1:
# There are no new namespaces for this tag, but
# non-default namespaces are in play, so we need a
# separate tag stack to know when they end.
self.nsmaps.append(None)
if len(nsmap) == 0 and len(self.nsmaps) > 1:
# There are no new namespaces for this tag, but
# non-default namespaces are in play, so we need a
# separate tag stack to know when they end.
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 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))
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
for prefix, namespace in nsmap.items():
for prefix, namespace in list(nsmap.items()):
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
@@ -159,7 +252,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
for attr, value in attrs.items():
for attr, value in list(attrs.items()):
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
@@ -201,7 +294,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
def pi(self, target, data):
self.soup.endData()
self.soup.handle_data(target + ' ' + data)
self.soup.endData(ProcessingInstruction)
self.soup.endData(self.processing_instruction_class)
def data(self, content):
self.soup.handle_data(content)
@@ -219,7 +312,7 @@ class LXMLTreeBuilderForXML(TreeBuilder):
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
return '<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
@@ -229,6 +322,7 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
is_xml = False
processing_instruction_class = ProcessingInstruction
def default_parser(self, encoding):
return etree.HTMLParser
@@ -239,10 +333,10 @@ class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
self.parser = self.parser_for(encoding)
self.parser.feed(markup)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
raise ParserRejectedMarkup(str(e))
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(e)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><body>%s</body></html>' % fragment
return '<html><body>%s</body></html>' % fragment
lib/bs4/dammit.py
+2561 -62
View File
File diff suppressed because it is too large Load Diff
lib/bs4/diagnose.py
+67 -38
View File
@@ -1,7 +1,11 @@
"""Diagnostic functions, mainly for use when doing tech support."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
import cProfile
from StringIO import StringIO
from HTMLParser import HTMLParser
from io import StringIO
from html.parser import HTMLParser
import bs4
from bs4 import BeautifulSoup, __version__
from bs4.builder import builder_registry
@@ -16,9 +20,13 @@ import sys
import cProfile
def diagnose(data):
"""Diagnostic suite for isolating common problems."""
print "Diagnostic running on Beautiful Soup %s" % __version__
print "Python version %s" % sys.version
"""Diagnostic suite for isolating common problems.
:param data: A string containing markup that needs to be explained.
:return: None; diagnostics are printed to standard output.
"""
print(("Diagnostic running on Beautiful Soup %s" % __version__))
print(("Python version %s" % sys.version))
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
@@ -27,66 +35,84 @@ def diagnose(data):
break
else:
basic_parsers.remove(name)
print (
print((
"I noticed that %s is not installed. Installing it may help." %
name)
name))
if 'lxml' in basic_parsers:
basic_parsers.append(["lxml", "xml"])
basic_parsers.append("lxml-xml")
try:
from lxml import etree
print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
except ImportError, e:
print (
print(("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))))
except ImportError as e:
print(
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print "Found html5lib version %s" % html5lib.__version__
except ImportError, e:
print (
print(("Found html5lib version %s" % html5lib.__version__))
except ImportError as e:
print(
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif os.path.exists(data):
print '"%s" looks like a filename. Reading data from the file.' % data
data = open(data).read()
elif data.startswith("http:") or data.startswith("https:"):
print '"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data
print "You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup."
print(('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data))
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
print
else:
try:
if os.path.exists(data):
print(('"%s" looks like a filename. Reading data from the file.' % data))
with open(data) as fp:
data = fp.read()
except ValueError:
# This can happen on some platforms when the 'filename' is
# too long. Assume it's data and not a filename.
pass
print("")
for parser in basic_parsers:
print "Trying to parse your markup with %s" % parser
print(("Trying to parse your markup with %s" % parser))
success = False
try:
soup = BeautifulSoup(data, parser)
soup = BeautifulSoup(data, features=parser)
success = True
except Exception, e:
print "%s could not parse the markup." % parser
except Exception as e:
print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
print "Here's what %s did with the markup:" % parser
print soup.prettify()
print(("Here's what %s did with the markup:" % parser))
print((soup.prettify()))
print "-" * 80
print(("-" * 80))
def lxml_trace(data, html=True, **kwargs):
"""Print out the lxml events that occur during parsing.
This lets you see how lxml parses a document when no Beautiful
Soup code is running.
Soup code is running. You can use this to determine whether
an lxml-specific problem is in Beautiful Soup's lxml tree builders
or in lxml itself.
:param data: Some markup.
:param html: If True, markup will be parsed with lxml's HTML parser.
if False, lxml's XML parser will be used.
"""
from lxml import etree
for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
print("%s, %4s, %s" % (event, element.tag, element.text))
print(("%s, %4s, %s" % (event, element.tag, element.text)))
class AnnouncingParser(HTMLParser):
"""Announces HTMLParser parse events, without doing anything else."""
"""Subclass of HTMLParser that announces parse events, without doing
anything else.
You can use this to get a picture of how html.parser sees a given
document. The easiest way to do this is to call `htmlparser_trace`.
"""
def _p(self, s):
print(s)
@@ -123,6 +149,8 @@ def htmlparser_trace(data):
This lets you see how HTMLParser parses a document when no
Beautiful Soup code is running.
:param data: Some markup.
"""
parser = AnnouncingParser()
parser.feed(data)
@@ -165,9 +193,9 @@ def rdoc(num_elements=1000):
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print "Comparative parser benchmark on Beautiful Soup %s" % __version__
print(("Comparative parser benchmark on Beautiful Soup %s" % __version__))
data = rdoc(num_elements)
print "Generated a large invalid HTML document (%d bytes)." % len(data)
print(("Generated a large invalid HTML document (%d bytes)." % len(data)))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
@@ -176,27 +204,27 @@ def benchmark_parsers(num_elements=100000):
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception, e:
print "%s could not parse the markup." % parser
except Exception as e:
print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
print "BS4+%s parsed the markup in %.2fs." % (parser, b-a)
print(("BS4+%s parsed the markup in %.2fs." % (parser, b-a)))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print "Raw lxml parsed the markup in %.2fs." % (b-a)
print(("Raw lxml parsed the markup in %.2fs." % (b-a)))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print "Raw html5lib parsed the markup in %.2fs." % (b-a)
print(("Raw html5lib parsed the markup in %.2fs." % (b-a)))
def profile(num_elements=100000, parser="lxml"):
"""Use Python's profiler on a randomly generated document."""
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
@@ -209,5 +237,6 @@ def profile(num_elements=100000, parser="lxml"):
stats.sort_stats("cumulative")
stats.print_stats('_html5lib|bs4', 50)
# If this file is run as a script, standard input is diagnosed.
if __name__ == '__main__':
diagnose(sys.stdin.read())
lib/bs4/element.py
+1205 -663
View File
File diff suppressed because it is too large Load Diff
lib/bs4/formatter.py
+165
View File
@@ -0,0 +1,165 @@
from bs4.dammit import EntitySubstitution
class Formatter(EntitySubstitution):
"""Describes a strategy to use when outputting a parse tree to a string.
Some parts of this strategy come from the distinction between
HTML4, HTML5, and XML. Others are configurable by the user.
Formatters are passed in as the `formatter` argument to methods
like `PageElement.encode`. Most people won't need to think about
formatters, and most people who need to think about them can pass
in one of these predefined strings as `formatter` rather than
making a new Formatter object:
For HTML documents:
* 'html' - HTML entity substitution for generic HTML documents. (default)
* 'html5' - HTML entity substitution for HTML5 documents, as
well as some optimizations in the way tags are rendered.
* 'minimal' - Only make the substitutions necessary to guarantee
valid HTML.
* None - Do not perform any substitution. This will be faster
but may result in invalid markup.
For XML documents:
* 'html' - Entity substitution for XHTML documents.
* 'minimal' - Only make the substitutions necessary to guarantee
valid XML. (default)
* None - Do not perform any substitution. This will be faster
but may result in invalid markup.
"""
# Registries of XML and HTML formatters.
XML_FORMATTERS = {}
HTML_FORMATTERS = {}
HTML = 'html'
XML = 'xml'
HTML_DEFAULTS = dict(
cdata_containing_tags=set(["script", "style"]),
)
def _default(self, language, value, kwarg):
if value is not None:
return value
if language == self.XML:
return set()
return self.HTML_DEFAULTS[kwarg]
def __init__(
self, language=None, entity_substitution=None,
void_element_close_prefix='/', cdata_containing_tags=None,
empty_attributes_are_booleans=False,
):
"""Constructor.
:param language: This should be Formatter.XML if you are formatting
XML markup and Formatter.HTML if you are formatting HTML markup.
:param entity_substitution: A function to call to replace special
characters with XML/HTML entities. For examples, see
bs4.dammit.EntitySubstitution.substitute_html and substitute_xml.
:param void_element_close_prefix: By default, void elements
are represented as <tag/> (XML rules) rather than <tag>
(HTML rules). To get <tag>, pass in the empty string.
:param cdata_containing_tags: The list of tags that are defined
as containing CDATA in this dialect. For example, in HTML,
<script> and <style> tags are defined as containing CDATA,
and their contents should not be formatted.
:param blank_attributes_are_booleans: Render attributes whose value
is the empty string as HTML-style boolean attributes.
(Attributes whose value is None are always rendered this way.)
"""
self.language = language
self.entity_substitution = entity_substitution
self.void_element_close_prefix = void_element_close_prefix
self.cdata_containing_tags = self._default(
language, cdata_containing_tags, 'cdata_containing_tags'
)
self.empty_attributes_are_booleans=empty_attributes_are_booleans
def substitute(self, ns):
"""Process a string that needs to undergo entity substitution.
This may be a string encountered in an attribute value or as
text.
:param ns: A string.
:return: A string with certain characters replaced by named
or numeric entities.
"""
if not self.entity_substitution:
return ns
from .element import NavigableString
if (isinstance(ns, NavigableString)
and ns.parent is not None
and ns.parent.name in self.cdata_containing_tags):
# Do nothing.
return ns
# Substitute.
return self.entity_substitution(ns)
def attribute_value(self, value):
"""Process the value of an attribute.
:param ns: A string.
:return: A string with certain characters replaced by named
or numeric entities.
"""
return self.substitute(value)
def attributes(self, tag):
"""Reorder a tag's attributes however you want.
By default, attributes are sorted alphabetically. This makes
behavior consistent between Python 2 and Python 3, and preserves
backwards compatibility with older versions of Beautiful Soup.
If `empty_boolean_attributes` is True, then attributes whose
values are set to the empty string will be treated as boolean
attributes.
"""
if tag.attrs is None:
return []
return sorted(
(k, (None if self.empty_attributes_are_booleans and v == '' else v))
for k, v in list(tag.attrs.items())
)
class HTMLFormatter(Formatter):
"""A generic Formatter for HTML."""
REGISTRY = {}
def __init__(self, *args, **kwargs):
return super(HTMLFormatter, self).__init__(self.HTML, *args, **kwargs)
class XMLFormatter(Formatter):
"""A generic Formatter for XML."""
REGISTRY = {}
def __init__(self, *args, **kwargs):
return super(XMLFormatter, self).__init__(self.XML, *args, **kwargs)
# Set up aliases for the default formatters.
HTMLFormatter.REGISTRY['html'] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_html
)
HTMLFormatter.REGISTRY["html5"] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_html,
void_element_close_prefix=None,
empty_attributes_are_booleans=True,
)
HTMLFormatter.REGISTRY["minimal"] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_xml
)
HTMLFormatter.REGISTRY[None] = HTMLFormatter(
entity_substitution=None
)
XMLFormatter.REGISTRY["html"] = XMLFormatter(
entity_substitution=EntitySubstitution.substitute_html
)
XMLFormatter.REGISTRY["minimal"] = XMLFormatter(
entity_substitution=EntitySubstitution.substitute_xml
)
XMLFormatter.REGISTRY[None] = Formatter(
Formatter(Formatter.XML, entity_substitution=None)
)
lib/bs4/testing.py
+16 -16
View File
@@ -275,14 +275,14 @@ Hello, world!
self.assertSoupEquals('<a b="<a>"></a>', '<a b="&lt;a&gt;"></a>')
def test_entities_in_attributes_converted_to_unicode(self):
expect = u'<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
expect = '<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
self.assertSoupEquals('<p id="pi&#241;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#Xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&ntilde;ata"></p>', expect)
def test_entities_in_text_converted_to_unicode(self):
expect = u'<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
expect = '<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
self.assertSoupEquals("<p>pi&#241;ata</p>", expect)
self.assertSoupEquals("<p>pi&#xf1;ata</p>", expect)
self.assertSoupEquals("<p>pi&#Xf1;ata</p>", expect)
@@ -293,7 +293,7 @@ Hello, world!
'<p>I said "good day!"</p>')
def test_out_of_range_entity(self):
expect = u"\N{REPLACEMENT CHARACTER}"
expect = "\N{REPLACEMENT CHARACTER}"
self.assertSoupEquals("&#10000000000000;", expect)
self.assertSoupEquals("&#x10000000000000;", expect)
self.assertSoupEquals("&#1000000000;", expect)
@@ -364,9 +364,9 @@ Hello, world!
# A seemingly innocuous document... but it's in Unicode! And
# it contains characters that can't be represented in the
# encoding found in the declaration! The horror!
markup = u'<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
markup = '<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
soup = self.soup(markup)
self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string)
self.assertEqual('Sacr\xe9 bleu!', soup.body.string)
def test_soupstrainer(self):
"""Parsers should be able to work with SoupStrainers."""
@@ -406,7 +406,7 @@ Hello, world!
# Both XML and HTML entities are converted to Unicode characters
# during parsing.
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
expected = "<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
self.assertSoupEquals(text, expected)
def test_smart_quotes_converted_on_the_way_in(self):
@@ -416,15 +416,15 @@ Hello, world!
soup = self.soup(quote)
self.assertEqual(
soup.p.string,
u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
def test_non_breaking_spaces_converted_on_the_way_in(self):
soup = self.soup("<a>&nbsp;&nbsp;</a>")
self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
self.assertEqual(soup.a.string, "\N{NO-BREAK SPACE}" * 2)
def test_entities_converted_on_the_way_out(self):
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = u"<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
expected = "<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
soup = self.soup(text)
self.assertEqual(soup.p.encode("utf-8"), expected)
@@ -433,7 +433,7 @@ Hello, world!
# easy-to-understand document.
# Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
unicode_html = u'<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
unicode_html = '<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
# That's because we're going to encode it into ISO-Latin-1, and use
# that to test.
@@ -581,15 +581,15 @@ class XMLTreeBuilderSmokeTest(object):
self.assertTrue(b"&lt; &lt; hey &gt; &gt;" in encoded)
def test_can_parse_unicode_document(self):
markup = u'<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
markup = '<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
soup = self.soup(markup)
self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string)
self.assertEqual('Sacr\xe9 bleu!', soup.root.string)
def test_popping_namespaced_tag(self):
markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>'
soup = self.soup(markup)
self.assertEqual(
unicode(soup.rss), markup)
str(soup.rss), markup)
def test_docstring_includes_correct_encoding(self):
soup = self.soup("<root/>")
@@ -620,17 +620,17 @@ class XMLTreeBuilderSmokeTest(object):
def test_closing_namespaced_tag(self):
markup = '<p xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:date>20010504</dc:date></p>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.p), markup)
self.assertEqual(str(soup.p), markup)
def test_namespaced_attributes(self):
markup = '<foo xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><bar xsi:schemaLocation="http://www.example.com"/></foo>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.foo), markup)
self.assertEqual(str(soup.foo), markup)
def test_namespaced_attributes_xml_namespace(self):
markup = '<foo xml:lang="fr">bar</foo>'
soup = self.soup(markup)
self.assertEqual(unicode(soup.foo), markup)
self.assertEqual(str(soup.foo), markup)
class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
"""Smoke test for a tree builder that supports HTML5."""