gronod/headphones
1
0
Fork 1
mirror of https://github.com/rembo10/headphones.git synced 2026-05-02 01:39:29 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update Beautiful Soup

Browse Source
This commit is contained in:
AdeHub
2024-08-24 16:18:38 +12:00
parent 5b1d9c0750
commit d6f22a2326
11 changed files with 1126 additions and 3471 deletions
Download Patch File Download Diff File Expand all files Collapse all files

173
lib/bs4/builder/_htmlparser.py
View File

@@ -10,30 +10,9 @@ __all__ = [
from html.parser import HTMLParser
try:
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):
pass
import sys
import warnings
# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
# argument, which we'd like to set to False. Unfortunately,
# http://bugs.python.org/issue13273 makes strict=True a better bet
# before Python 3.2.3.
#
# At the end of this file, we monkeypatch HTMLParser so that
# strict=True works well on Python 3.2.2.
major, minor, release = sys.version_info[:3]
CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
from bs4.element import (
CData,
Comment,
@@ -44,6 +23,8 @@ from bs4.element import (
from bs4.dammit import EntitySubstitution, UnicodeDammit
from bs4.builder import (
DetectsXMLParsedAsHTML,
ParserRejectedMarkup,
HTML,
HTMLTreeBuilder,
STRICT,
@@ -52,7 +33,7 @@ from bs4.builder import (
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser):
class BeautifulSoupHTMLParser(HTMLParser, DetectsXMLParsedAsHTML):
"""A subclass of the Python standard library's HTMLParser class, which
listens for HTMLParser events and translates them into calls
to Beautiful Soup's tree construction API.
@@ -88,19 +69,24 @@ class BeautifulSoupHTMLParser(HTMLParser):
# 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.
self._initialize_xml_detector()
In Python 2, HTMLParser implements error() by raising an exception,
which we don't want to do.
def error(self, message):
# NOTE: This method is required so long as Python 3.9 is
# supported. The corresponding code is removed from HTMLParser
# in 3.5, but not removed from ParserBase until 3.10.
# https://github.com/python/cpython/issues/76025
#
# The original implementation turned the error into a warning,
# but in every case I discovered, this made HTMLParser
# immediately crash with an error message that was less
# helpful than the warning. The new implementation makes it
# more clear that html.parser just can't parse this
# markup. The 3.10 implementation does the same, though it
# raises AssertionError rather than calling a method. (We
# catch this error and wrap it in a ParserRejectedMarkup.)
raise ParserRejectedMarkup(message)
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.
@@ -167,6 +153,9 @@ class BeautifulSoupHTMLParser(HTMLParser):
# But we might encounter an explicit closing tag for this tag
# later on. If so, we want to ignore it.
self.already_closed_empty_element.append(name)
if self._root_tag is None:
self._root_tag_encountered(name)
def handle_endtag(self, name, check_already_closed=True):
"""Handle a closing tag, e.g. '</tag>'
@@ -185,7 +174,7 @@ class BeautifulSoupHTMLParser(HTMLParser):
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)
@@ -197,9 +186,10 @@ class BeautifulSoupHTMLParser(HTMLParser):
: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
# TODO: This was originally a workaround for a bug in
# HTMLParser. (http://bugs.python.org/issue13633) The bug has
# been fixed, but removing this code still makes some
# Beautiful Soup tests fail. This needs investigation.
if name.startswith('x'):
real_name = int(name.lstrip('x'), 16)
elif name.startswith('X'):
@@ -288,6 +278,7 @@ class BeautifulSoupHTMLParser(HTMLParser):
"""
self.soup.endData()
self.soup.handle_data(data)
self._document_might_be_xml(data)
self.soup.endData(ProcessingInstruction)
@@ -326,10 +317,7 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder):
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
parser_kwargs['convert_charrefs'] = False
self.parser_args = (parser_args, parser_kwargs)
def prepare_markup(self, markup, user_specified_encoding=None,
@@ -391,102 +379,9 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder):
try:
parser.feed(markup)
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
except AssertionError as e:
# html.parser raises AssertionError in rare cases to
# indicate a fatal problem with the markup, especially
# when there's an error in the doctype declaration.
raise ParserRejectedMarkup(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
# string.
#
# XXX This code can be removed once most Python 3 users are on 3.2.3.
if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
import re
attrfind_tolerant = re.compile(
r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
""", re.VERBOSE)
BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
from html.parser import tagfind, attrfind
def parse_starttag(self, i):
self.__starttag_text = None
endpos = self.check_for_whole_start_tag(i)
if endpos < 0:
return endpos
rawdata = self.rawdata
self.__starttag_text = rawdata[i:endpos]
# Now parse the data between i+1 and j into a tag and attrs
attrs = []
match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
self.lasttag = tag = rawdata[i+1:k].lower()
while k < endpos:
if self.strict:
m = attrfind.match(rawdata, k)
else:
m = attrfind_tolerant.match(rawdata, k)
if not m:
break
attrname, rest, attrvalue = m.group(1, 2, 3)
if not rest:
attrvalue = None
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1]
if attrvalue:
attrvalue = self.unescape(attrvalue)
attrs.append((attrname.lower(), attrvalue))
k = m.end()
end = rawdata[k:endpos].strip()
if end not in (">", "/>"):
lineno, offset = self.getpos()
if "\n" in self.__starttag_text:
lineno = lineno + self.__starttag_text.count("\n")
offset = len(self.__starttag_text) \
- self.__starttag_text.rfind("\n")
else:
offset = offset + len(self.__starttag_text)
if self.strict:
self.error("junk characters in start tag: %r"
% (rawdata[k:endpos][:20],))
self.handle_data(rawdata[i:endpos])
return endpos
if end.endswith('/>'):
# XHTML-style empty tag: <span attr="value" />
self.handle_startendtag(tag, attrs)
else:
self.handle_starttag(tag, attrs)
if tag in self.CDATA_CONTENT_ELEMENTS:
self.set_cdata_mode(tag)
return endpos
def set_cdata_mode(self, elem):
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
BeautifulSoupHTMLParser.parse_starttag = parse_starttag
BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
CONSTRUCTOR_TAKES_STRICT = True