github/plexpy
1
0
Fork 0
mirror of https://github.com/Tautulli/Tautulli.git synced 2025-08-14 02:26:58 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Update beautifulsoup4-4.10.0

Browse source
This commit is contained in:
JonnyWong16 2021-10-14 20:46:06 -07:00
commit ab8fa4d5b3
No known key found for this signature in database
GPG key ID: B1F1F9807184697A
16 changed files with 4599 additions and 743 deletions
Download patch file Download diff file Expand all files Collapse all files

363
lib/bs4/__init__.py
View file

@ -1,6 +1,5 @@
"""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
@ -8,29 +7,34 @@ Beautiful Soup uses a pluggable XML or HTML parser to parse a
provides methods and Pythonic idioms that make it easy to navigate,
search, and modify the parse tree.
Beautiful Soup works with Python 2.7 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__ = "4.8.1"
__copyright__ = "Copyright (c) 2004-2019 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 (
@ -42,28 +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) # 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,
@ -73,68 +98,75 @@ class BeautifulSoup(Tag):
like HTML's <br> tag), call handle_starttag and then
handle_endtag.
"""
# 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\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,
element_classes=None, **kwargs):
"""Constructor.
:param markup: A string or a file-like object representing
markup to be parsed.
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 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.
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.
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.
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.
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 using subclasses to modify the
default behavior of Tag or NavigableString.
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 beyond saying
which one to use.
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(
@ -223,7 +255,9 @@ class BeautifulSoup(Tag):
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:
@ -257,7 +291,10 @@ class BeautifulSoup(Tag):
parser=builder.NAME,
markup_type=markup_type
)
warnings.warn(self.NO_PARSER_SPECIFIED_WARNING % values, stacklevel=2)
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`.")
@ -286,20 +323,32 @@ class BeautifulSoup(Tag):
else:
possible_filename = markup
is_file = False
is_directory = False
try:
is_file = os.path.exists(possible_filename)
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, str):
markup = markup.encode("utf8")
if is_directory:
warnings.warn(
'"%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.' % markup)
' Beautiful Soup.' % self._decode_markup(markup),
MarkupResemblesLocatorWarning
)
self._check_markup_is_url(markup)
rejections = []
@ -329,6 +378,7 @@ class BeautifulSoup(Tag):
self.builder.soup = None
def __copy__(self):
"""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'
)
@ -347,11 +397,25 @@ class BeautifulSoup(Tag):
d['builder'] = None
return d
@staticmethod
def _check_markup_is_url(markup):
"""
Check if markup looks like it's actually a url and raise a warning
if so. Markup can be unicode or str (py2) / bytes (py3).
@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' '
@ -364,18 +428,20 @@ class BeautifulSoup(Tag):
if any(markup.startswith(prefix) for prefix in cant_start_with):
if not space in markup:
if isinstance(markup, bytes):
decoded_markup = markup.decode('utf-8', 'replace')
else:
decoded_markup = 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.' % decoded_markup
' 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()
@ -386,66 +452,110 @@ 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={},
sourceline=None, sourcepos=None, **kwattrs):
"""Create a new tag associated with this soup."""
"""Create a new Tag associated with this BeautifulSoup object.
: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.
"""
kwattrs.update(attrs)
return self.element_classes.get(Tag, Tag)(
None, self.builder, name, namespace, nsprefix, kwattrs,
sourceline=sourceline, sourcepos=sourcepos
)
def new_string(self, s, subclass=None):
"""Create a new NavigableString associated with this soup."""
subclass = subclass or self.element_classes.get(
NavigableString, NavigableString
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
)
return subclass(s)
def insert_before(self, successor):
# 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
"""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=None):
# Default container is NavigableString.
containerClass = containerClass or NavigableString
# The user may want us to instantiate some alias for the
# container class.
containerClass = self.element_classes.get(
containerClass, containerClass
)
"""Method called by the TreeBuilder when the end of a data segment
occurs.
"""
if self.current_data:
current_data = ''.join(self.current_data)
# If whitespace is not preserved, and this string contains
@ -472,11 +582,12 @@ 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."""
"""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:
@ -545,10 +656,19 @@ class BeautifulSoup(Tag):
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
@ -557,6 +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:
@ -568,15 +690,22 @@ class BeautifulSoup(Tag):
def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
sourcepos=None):
"""Push a start tag on to the stack.
"""Called by the tree builder when a new tag is encountered.
If this method returns None, the tag was rejected by the
: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
@ -598,22 +727,38 @@ class BeautifulSoup(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 = '<?xml version="1.0"%s?>\n' % encoding_part
@ -626,7 +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
@ -642,14 +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()))