Bump beautifulsoup4 from 4.10.0 to 4.11.1 (#1717)

* Bump beautifulsoup4 from 4.10.0 to 4.11.1

Bumps [beautifulsoup4](https://www.crummy.com/software/BeautifulSoup/bs4/) from 4.10.0 to 4.11.1.

---
updated-dependencies:
- dependency-name: beautifulsoup4
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

* Update beautifulsoup4==4.11.1

* Update soupsieve==2.3.2.post1

* Update requirements.txt

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: JonnyWong16 <9099342+JonnyWong16@users.noreply.github.com>

[skip ci]
This commit is contained in:
dependabot[bot] 2022-05-16 20:46:21 -07:00 committed by GitHub
commit 467ae352f5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
28 changed files with 4846 additions and 2609 deletions

View file

@ -15,14 +15,13 @@ documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
"""
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "4.10.0"
__copyright__ = "Copyright (c) 2004-2021 Leonard Richardson"
__version__ = "4.11.1"
__copyright__ = "Copyright (c) 2004-2022 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
@ -35,7 +34,11 @@ import warnings
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 .builder import (
builder_registry,
ParserRejectedMarkup,
XMLParsedAsHTMLWarning,
)
from .dammit import UnicodeDammit
from .element import (
CData,
@ -67,7 +70,7 @@ class MarkupResemblesLocatorWarning(UserWarning):
on disk.
"""
class BeautifulSoup(Tag):
"""A data structure representing a parsed HTML or XML document.
@ -207,10 +210,10 @@ class BeautifulSoup(Tag):
if old_name in kwargs:
warnings.warn(
'The "%s" argument to the BeautifulSoup constructor '
'has been renamed to "%s."' % (old_name, new_name))
value = kwargs[old_name]
del kwargs[old_name]
return value
'has been renamed to "%s."' % (old_name, new_name),
DeprecationWarning
)
return kwargs.pop(old_name)
return None
parse_only = parse_only or deprecated_argument(
@ -305,51 +308,18 @@ class BeautifulSoup(Tag):
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 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
# Issue 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, 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)
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_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.' % self._decode_markup(markup),
MarkupResemblesLocatorWarning
)
self._check_markup_is_url(markup)
# since that is sometimes the intended behavior.
if not self._markup_is_url(markup):
self._markup_resembles_filename(markup)
rejections = []
success = False
@ -358,6 +328,7 @@ class BeautifulSoup(Tag):
self.builder.prepare_markup(
markup, from_encoding, exclude_encodings=exclude_encodings)):
self.reset()
self.builder.initialize_soup(self)
try:
self._feed()
success = True
@ -393,10 +364,10 @@ class BeautifulSoup(Tag):
def __getstate__(self):
# Frequently a tree builder can't be pickled.
d = dict(self.__dict__)
if 'builder' in d and not self.builder.picklable:
if 'builder' in d and d['builder'] is not None and not self.builder.picklable:
d['builder'] = None
return d
@classmethod
def _decode_markup(cls, markup):
"""Ensure `markup` is bytes so it's safe to send into warnings.warn.
@ -411,11 +382,13 @@ class BeautifulSoup(Tag):
return decoded
@classmethod
def _check_markup_is_url(cls, markup):
def _markup_is_url(cls, markup):
"""Error-handling method to raise a warning if incoming markup looks
like a URL.
:param markup: A string.
:return: Whether or not the markup resembles a URL
closely enough to justify a warning.
"""
if isinstance(markup, bytes):
space = b' '
@ -424,20 +397,50 @@ class BeautifulSoup(Tag):
space = ' '
cant_start_with = ("http:", "https:")
else:
return
return False
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
),
'The input looks more like a URL than markup. You may want to use'
' an HTTP client like requests to get the document behind'
' the URL, and feed that document to Beautiful Soup.',
MarkupResemblesLocatorWarning
)
return True
return False
@classmethod
def _markup_resembles_filename(cls, markup):
"""Error-handling method to raise a warning if incoming markup
resembles a filename.
:param markup: A bytestring or string.
:return: Whether or not the markup resembles a filename
closely enough to justify a warning.
"""
path_characters = '/\\'
extensions = ['.html', '.htm', '.xml', '.xhtml', '.txt']
if isinstance(markup, bytes):
path_characters = path_characters.encode("utf8")
extensions = [x.encode('utf8') for x in extensions]
filelike = False
if any(x in markup for x in path_characters):
filelike = True
else:
lower = markup.lower()
if any(lower.endswith(ext) for ext in extensions):
filelike = True
if filelike:
warnings.warn(
'The input looks more like a filename than markup. You may'
' want to open this file and pass the filehandle into'
' Beautiful Soup.',
MarkupResemblesLocatorWarning
)
return True
return False
def _feed(self):
"""Internal method that parses previously set markup, creating a large
number of Tag and NavigableString objects.
@ -689,7 +692,7 @@ class BeautifulSoup(Tag):
return most_recently_popped
def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
sourcepos=None):
sourcepos=None, namespaces=None):
"""Called by the tree builder when a new tag is encountered.
:param name: Name of the tag.
@ -699,6 +702,8 @@ class BeautifulSoup(Tag):
source document.
:param sourcepos: The character position within `sourceline` where this
tag was found.
:param namespaces: A dictionary of all namespace prefix mappings
currently in scope in the document.
If this method returns None, the tag was rejected by an active
SoupStrainer. You should proceed as if the tag had not occurred
@ -716,7 +721,8 @@ class BeautifulSoup(Tag):
tag = self.element_classes.get(Tag, Tag)(
self, self.builder, name, namespace, nsprefix, attrs,
self.currentTag, self._most_recent_element,
sourceline=sourceline, sourcepos=sourcepos
sourceline=sourceline, sourcepos=sourcepos,
namespaces=namespaces
)
if tag is None:
return tag
@ -735,7 +741,7 @@ class BeautifulSoup(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)
@ -782,7 +788,9 @@ class BeautifulStoneSoup(BeautifulSoup):
kwargs['features'] = 'xml'
warnings.warn(
'The BeautifulStoneSoup class is deprecated. Instead of using '
'it, pass features="xml" into the BeautifulSoup constructor.')
'it, pass features="xml" into the BeautifulSoup constructor.',
DeprecationWarning
)
super(BeautifulStoneSoup, self).__init__(*args, **kwargs)