ouczbs/anki-word-query
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add bs4 to libs

Browse Source
This commit is contained in:
St.Huang 2018-07-06 02:50:34 +08:00
parent ed57ac6195
commit 07697579dc
6 changed files with 4033 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

529
src/fastwq/libs/bs4/__init__.py Normal file
View File

@ -0,0 +1,529 @@
"""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 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
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/
"""
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "4.6.0"
__copyright__ = "Copyright (c) 2004-2017 Leonard Richardson"
__license__ = "MIT"
__all__ = ['BeautifulSoup']
import os
import re
import traceback
import warnings
from .builder import builder_registry, ParserRejectedMarkup
from .dammit import UnicodeDammit
from .element import (
CData,
Comment,
DEFAULT_OUTPUT_ENCODING,
Declaration,
Doctype,
NavigableString,
PageElement,
ProcessingInstruction,
ResultSet,
SoupStrainer,
Tag,
)
# 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`).'
class BeautifulSoup(Tag):
"""
This class defines the basic interface called by the tree builders.
These methods will be called by the parser:
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
No matter how complicated the underlying parser is, you should be
able to build a tree using 'start tag' events, 'end tag' events,
'data' events, and "done with data" events.
If you encounter an empty-element tag (aka a self-closing tag,
like HTML's <br> tag), call handle_starttag and then
handle_endtag.
"""
ROOT_TAG_NAME = u'[document]'
# If the end-user gives no indication which tree builder they
# want, look for one with these features.
DEFAULT_BUILDER_FEATURES = ['html', 'fast']
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, change code that looks like this:\n\n BeautifulSoup(YOUR_MARKUP})\n\nto this:\n\n BeautifulSoup(YOUR_MARKUP, \"%(parser)s\")\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."""
if 'convertEntities' in kwargs:
warnings.warn(
"BS4 does not respect the convertEntities argument to the "
"BeautifulSoup constructor. Entities are always converted "
"to Unicode characters.")
if 'markupMassage' in kwargs:
del kwargs['markupMassage']
warnings.warn(
"BS4 does not respect the markupMassage argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for any necessary markup massage.")
if 'smartQuotesTo' in kwargs:
del kwargs['smartQuotesTo']
warnings.warn(
"BS4 does not respect the smartQuotesTo argument to the "
"BeautifulSoup constructor. Smart quotes are always converted "
"to Unicode characters.")
if 'selfClosingTags' in kwargs:
del kwargs['selfClosingTags']
warnings.warn(
"BS4 does not respect the selfClosingTags argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for understanding self-closing tags.")
if 'isHTML' in kwargs:
del kwargs['isHTML']
warnings.warn(
"BS4 does not respect the isHTML argument to the "
"BeautifulSoup constructor. Suggest you use "
"features='lxml' for HTML and features='lxml-xml' for "
"XML.")
def deprecated_argument(old_name, new_name):
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
return None
parse_only = parse_only or deprecated_argument(
"parseOnlyThese", "parse_only")
from_encoding = from_encoding or deprecated_argument(
"fromEncoding", "from_encoding")
if from_encoding and isinstance(markup, unicode):
warnings.warn("You provided Unicode markup but also provided a value for from_encoding. Your from_encoding will be ignored.")
from_encoding = None
if len(kwargs) > 0:
arg = kwargs.keys().pop()
raise TypeError(
"__init__() got an unexpected keyword argument '%s'" % arg)
if builder is None:
original_features = features
if isinstance(features, basestring):
features = [features]
if features is None or len(features) == 0:
features = self.DEFAULT_BUILDER_FEATURES
builder_class = builder_registry.lookup(*features)
if builder_class is None:
raise FeatureNotFound(
"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):
if builder.is_xml:
markup_type = "XML"
else:
markup_type = "HTML"
caller = traceback.extract_stack()[0]
filename = caller[0]
line_number = caller[1]
warnings.warn(self.NO_PARSER_SPECIFIED_WARNING % dict(
filename=filename,
line_number=line_number,
parser=builder.NAME,
markup_type=markup_type))
self.builder = builder
self.is_xml = builder.is_xml
self.known_xml = self.is_xml
self.builder.soup = self
self.parse_only = parse_only
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, unicode) and not u'<' 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)
and not os.path.supports_unicode_filenames):
possible_filename = markup.encode("utf8")
else:
possible_filename = markup
is_file = False
try:
is_file = os.path.exists(possible_filename)
except Exception, 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")
warnings.warn(
'"%s" looks like a filename, not markup. You should'
' probably open this file and pass the filehandle into'
' Beautiful Soup.' % markup)
self._check_markup_is_url(markup)
for (self.markup, self.original_encoding, self.declared_html_encoding,
self.contains_replacement_characters) in (
self.builder.prepare_markup(
markup, from_encoding, exclude_encodings=exclude_encodings)):
self.reset()
try:
self._feed()
break
except ParserRejectedMarkup:
pass
# Clear out the markup and remove the builder's circular
# reference to this object.
self.markup = None
self.builder.soup = None
def __copy__(self):
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:
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).
"""
if isinstance(markup, bytes):
space = b' '
cant_start_with = (b"http:", b"https:")
elif isinstance(markup, unicode):
space = u' '
cant_start_with = (u"http:", u"https:")
else:
return
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
)
def _feed(self):
# Convert the document to Unicode.
self.builder.reset()
self.builder.feed(self.markup)
# Close out any unfinished strings and close all the open tags.
self.endData()
while self.currentTag.name != self.ROOT_TAG_NAME:
self.popTag()
def reset(self):
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.preserve_whitespace_tag_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_string(self, s, subclass=NavigableString):
"""Create a new NavigableString associated with this soup."""
return subclass(s)
def insert_before(self, successor):
raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
def insert_after(self, successor):
raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
def popTag(self):
tag = self.tagStack.pop()
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.tagStack:
self.currentTag = self.tagStack[-1]
return self.currentTag
def pushTag(self, tag):
#print "Push", tag.name
if self.currentTag:
self.currentTag.contents.append(tag)
self.tagStack.append(tag)
self.currentTag = self.tagStack[-1]
if tag.name in self.builder.preserve_whitespace_tags:
self.preserve_whitespace_tag_stack.append(tag)
def endData(self, containerClass=NavigableString):
if self.current_data:
current_data = u''.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.
if not self.preserve_whitespace_tag_stack:
strippable = True
for i in current_data:
if i not in self.ASCII_SPACES:
strippable = False
break
if strippable:
if '\n' in current_data:
current_data = '\n'
else:
current_data = ' '
# Reset the data collector.
self.current_data = []
# Should we add this string to the tree at all?
if self.parse_only and len(self.tagStack) <= 1 and \
(not self.parse_only.text or \
not self.parse_only.search(current_data)):
return
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
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:
previous_element = o.previous_element
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 = len(parent.contents)-1
while index >= 0:
if parent.contents[index] is o:
break
index -= 1
else:
raise ValueError(
"Error building tree: supposedly %r was inserted "
"into %r after the fact, but I don't see it!" % (
o, parent
)
)
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]
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 _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
if name == self.ROOT_TAG_NAME:
# The BeautifulSoup object itself can never be popped.
return
most_recently_popped = None
stack_size = len(self.tagStack)
for i in range(stack_size - 1, 0, -1):
t = self.tagStack[i]
if (name == t.name and nsprefix == t.prefix):
if inclusivePop:
most_recently_popped = self.popTag()
break
most_recently_popped = self.popTag()
return most_recently_popped
def handle_starttag(self, name, namespace, nsprefix, attrs):
"""Push a start tag on to the stack.
If this method returns None, the tag was rejected by the
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)
self.endData()
if (self.parse_only and len(self.tagStack) <= 1
and (self.parse_only.text
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)
if tag is None:
return tag
if self._most_recent_element:
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
self.endData()
self._popToTag(name, nsprefix)
def handle_data(self, data):
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."""
if self.is_xml:
# Print the XML declaration
encoding_part = ''
if eventual_encoding != None:
encoding_part = ' encoding="%s"' % eventual_encoding
prefix = u'<?xml version="1.0"%s?>\n' % encoding_part
else:
prefix = u''
if not pretty_print:
indent_level = None
else:
indent_level = 0
return prefix + super(BeautifulSoup, self).decode(
indent_level, eventual_encoding, formatter)
# Alias to make it easier to type import: 'from bs4 import _soup'
_s = BeautifulSoup
_soup = BeautifulSoup
class BeautifulStoneSoup(BeautifulSoup):
"""Deprecated interface to an XML parser."""
def __init__(self, *args, **kwargs):
kwargs['features'] = 'xml'
warnings.warn(
'The BeautifulStoneSoup class is deprecated. Instead of using '
'it, pass features="xml" into the BeautifulSoup constructor.')
super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
class StopParsing(Exception):
pass
class FeatureNotFound(ValueError):
pass
#By default, act as an HTML pretty-printer.
if __name__ == '__main__':
import sys
soup = BeautifulSoup(sys.stdin)
print soup.prettify()

321
src/fastwq/libs/bs4/builder/__init__.py Normal file
View File

@ -0,0 +1,321 @@
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
from collections import defaultdict
import itertools
import sys
from ..element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
HTMLAwareEntitySubstitution,
whitespace_re
)
__all__ = [
'HTMLTreeBuilder',
'SAXTreeBuilder',
'TreeBuilder',
'TreeBuilderRegistry',
]
# Some useful features for a TreeBuilder to have.
FAST = 'fast'
PERMISSIVE = 'permissive'
STRICT = 'strict'
XML = 'xml'
HTML = 'html'
HTML_5 = 'html5'
class TreeBuilderRegistry(object):
def __init__(self):
self.builders_for_feature = defaultdict(list)
self.builders = []
def register(self, treebuilder_class):
"""Register a treebuilder based on its advertised 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):
if len(self.builders) == 0:
# There are no builders at all.
return None
if len(features) == 0:
# They didn't ask for any features. Give them the most
# recently registered builder.
return self.builders[0]
# Go down the list of features in order, and eliminate any builders
# that don't match every feature.
features = list(features)
features.reverse()
candidates = None
candidate_set = None
while len(features) > 0:
feature = features.pop()
we_have_the_feature = self.builders_for_feature.get(feature, [])
if len(we_have_the_feature) > 0:
if candidates is None:
candidates = we_have_the_feature
candidate_set = set(candidates)
else:
# Eliminate any candidates that don't have this feature.
candidate_set = candidate_set.intersection(
set(we_have_the_feature))
# The only valid candidates are the ones in candidate_set.
# Go through the original list of candidates and pick the first one
# that's in candidate_set.
if candidate_set is None:
return None
for candidate in candidates:
if candidate in candidate_set:
return candidate
return None
# The BeautifulSoup class will take feature lists from developers and use them
# to look up builders in this registry.
builder_registry = TreeBuilderRegistry()
class TreeBuilder(object):
"""Turn a document into a Beautiful Soup object tree."""
NAME = "[Unknown tree builder]"
ALTERNATE_NAMES = []
features = []
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 = {}
def __init__(self):
self.soup = None
def reset(self):
pass
def can_be_empty_element(self, tag_name):
"""Might a tag with this name be an empty-element tag?
The final markup may or may not actually present this tag as
self-closing.
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 />".
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
be left alone.
"""
if self.empty_element_tags is None:
return True
return tag_name in self.empty_element_tags
def feed(self, markup):
raise NotImplementedError()
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None):
return markup, None, None, False
def test_fragment_to_document(self, fragment):
"""Wrap an HTML fragment to make it look like a document.
Different parsers do this differently. For instance, lxml
introduces an empty <head> tag, and html5lib
doesn't. Abstracting this away lets us write simple tests
which run HTML fragments through the parser and compare the
results against other HTML fragments.
This method should not be used outside of tests.
"""
return fragment
def set_up_substitutions(self, tag):
return False
def _replace_cdata_list_attribute_values(self, tag_name, attrs):
"""Replaces class="foo bar" with class=["foo", "bar"]
Modifies its input in place.
"""
if not attrs:
return attrs
if self.cdata_list_attributes:
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
for attr in 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)
else:
# html5lib sometimes calls setAttributes twice
# for the same tag when rearranging the parse
# tree. On the second call the attribute value
# here is already a list. If this happens,
# leave the value alone rather than trying to
# split it again.
values = value
attrs[attr] = values
return attrs
class SAXTreeBuilder(TreeBuilder):
"""A Beautiful Soup treebuilder that listens for SAX events."""
def feed(self, markup):
raise NotImplementedError()
def close(self):
pass
def startElement(self, name, attrs):
attrs = dict((key[1], value) for key, value in list(attrs.items()))
#print "Start %s, %r" % (name, attrs)
self.soup.handle_starttag(name, attrs)
def endElement(self, name):
#print "End %s" % name
self.soup.handle_endtag(name)
def startElementNS(self, nsTuple, nodeName, attrs):
# Throw away (ns, nodeName) for now.
self.startElement(nodeName, attrs)
def endElementNS(self, nsTuple, nodeName):
# Throw away (ns, nodeName) for now.
self.endElement(nodeName)
#handler.endElementNS((ns, node.nodeName), node.nodeName)
def startPrefixMapping(self, prefix, nodeValue):
# Ignore the prefix for now.
pass
def endPrefixMapping(self, prefix):
# Ignore the prefix for now.
# handler.endPrefixMapping(prefix)
pass
def characters(self, content):
self.soup.handle_data(content)
def startDocument(self):
pass
def endDocument(self):
pass
class HTMLTreeBuilder(TreeBuilder):
"""This TreeBuilder knows facts about HTML.
Such as which tags are empty-element tags.
"""
preserve_whitespace_tags = HTMLAwareEntitySubstitution.preserve_whitespace_tags
empty_element_tags = set([
# These are from HTML5.
'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
# These are from HTML4, removed in HTML5.
'spacer', 'frame'
])
# 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,
# 'foo' and 'bar', not the single value 'foo bar'. When we
# 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 = {
"*" : ['class', 'accesskey', 'dropzone'],
"a" : ['rel', 'rev'],
"link" : ['rel', 'rev'],
"td" : ["headers"],
"th" : ["headers"],
"td" : ["headers"],
"form" : ["accept-charset"],
"object" : ["archive"],
# These are HTML5 specific, as are *.accesskey and *.dropzone above.
"area" : ["rel"],
"icon" : ["sizes"],
"iframe" : ["sandbox"],
"output" : ["for"],
}
def set_up_substitutions(self, tag):
# We are only interested in <meta> tags
if tag.name != 'meta':
return False
http_equiv = tag.get('http-equiv')
content = tag.get('content')
charset = tag.get('charset')
# We are interested in <meta> tags that say what encoding the
# document was originally in. This means HTML 5-style <meta>
# tags that provide the "charset" attribute. It also means
# HTML 4-style <meta> tags that provide the "content"
# attribute and have "http-equiv" set to "content-type".
#
# In both cases we will replace the value of the appropriate
# attribute with a standin object that can take on any
# encoding.
meta_encoding = None
if charset is not None:
# HTML 5 style:
# <meta charset="utf8">
meta_encoding = charset
tag['charset'] = CharsetMetaAttributeValue(charset)
elif (content is not None and http_equiv is not None
and http_equiv.lower() == 'content-type'):
# HTML 4 style:
# <meta http-equiv="content-type" content="text/html; charset=utf8">
tag['content'] = ContentMetaAttributeValue(content)
return (meta_encoding is not None)
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['fastwq.libs.bs4.builder']
for name in module.__all__:
obj = getattr(module, name)
if issubclass(obj, TreeBuilder):
setattr(this_module, name, obj)
this_module.__all__.append(name)
# Register the builder while we're at it.
this_module.builder_registry.register(obj)
class ParserRejectedMarkup(Exception):
pass
# 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.
from . import _htmlparser
register_treebuilders_from(_htmlparser)

314
src/fastwq/libs/bs4/builder/_htmlparser.py Normal file
View File

@ -0,0 +1,314 @@
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
__all__ = [
'HTMLParserTreeBuilder',
]
from HTMLParser import HTMLParser
try:
from HTMLParser import HTMLParseError
except ImportError, 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 ..element import (
CData,
Comment,
Declaration,
Doctype,
ProcessingInstruction,
)
from ..dammit import EntitySubstitution, UnicodeDammit
from ..builder import (
HTML,
HTMLTreeBuilder,
STRICT,
)
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser):
def __init__(self, *args, **kwargs):
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 handle_startendtag(self, name, attrs):
# This is only called when the markup looks like
# <tag/>.
# 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):
# XXX namespace
attr_dict = {}
for key, value in attrs:
# Change None attribute values to the empty string
# for consistency with the other tree builders.
if value is None:
value = ''
attr_dict[key] = value
attrvalue = '""'
#print "START", name
tag = self.soup.handle_starttag(name, None, None, attr_dict)
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)
# 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):
#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):
self.soup.handle_data(data)
def handle_charref(self, name):
# XXX workaround for a bug in HTMLParser. Remove this once
# it's fixed in all supported versions.
# http://bugs.python.org/issue13633
if name.startswith('x'):
real_name = int(name.lstrip('x'), 16)
elif name.startswith('X'):
real_name = int(name.lstrip('X'), 16)
else:
real_name = int(name)
try:
data = unichr(real_name)
except (ValueError, OverflowError), e:
data = u"\N{REPLACEMENT CHARACTER}"
self.handle_data(data)
def handle_entityref(self, name):
character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
if character is not None:
data = character
else:
data = "&%s;" % name
self.handle_data(data)
def handle_comment(self, data):
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(Comment)
def handle_decl(self, data):
self.soup.endData()
if data.startswith("DOCTYPE "):
data = data[len("DOCTYPE "):]
elif data == 'DOCTYPE':
# i.e. "<!DOCTYPE>"
data = ''
self.soup.handle_data(data)
self.soup.endData(Doctype)
def unknown_decl(self, data):
if data.upper().startswith('CDATA['):
cls = CData
data = data[len('CDATA['):]
else:
cls = Declaration
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(cls)
def handle_pi(self, data):
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(ProcessingInstruction)
class HTMLParserTreeBuilder(HTMLTreeBuilder):
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)
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""
:return: A 4-tuple (markup, original encoding, encoding
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
"""
if isinstance(markup, unicode):
yield (markup, None, None, False)
return
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(markup, try_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):
args, kwargs = self.parser_args
parser = BeautifulSoupHTMLParser(*args, **kwargs)
parser.soup = self.soup
try:
parser.feed(markup)
except HTMLParseError, 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
# 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

842
src/fastwq/libs/bs4/dammit.py Normal file
View File

@ -0,0 +1,842 @@
# -*- coding: utf-8 -*-
"""Beautiful Soup bonus library: Unicode, Dammit
This library converts a bytestream to Unicode through any means
necessary. It is heavily based on code from Mark Pilgrim's Universal
Feed Parser. It works best on XML and HTML, but it does not rewrite the
XML or HTML to reflect a new encoding; that's the tree builder's job.
"""
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
__license__ = "MIT"
import codecs
from htmlentitydefs import codepoint2name
import re
import logging
import string
# Import a library to autodetect character encodings.
chardet_type = None
try:
# First try the fast C implementation.
# PyPI package: cchardet
import cchardet
def chardet_dammit(s):
return cchardet.detect(s)['encoding']
except ImportError:
try:
# Fall back to the pure Python implementation
# Debian package: python-chardet
# PyPI package: chardet
import chardet
def chardet_dammit(s):
return chardet.detect(s)['encoding']
#import chardet.constants
#chardet.constants._debug = 1
except ImportError:
# No chardet available.
def chardet_dammit(s):
return None
# Available from http://cjkpython.i18n.org/.
try:
import iconv_codec
except ImportError:
pass
xml_encoding_re = re.compile(
'^<\?.*encoding=[\'"](.*?)[\'"].*\?>'.encode(), re.I)
html_meta_re = re.compile(
'<\s*meta[^>]+charset\s*=\s*["\']?([^>]*?)[ /;\'">]'.encode(), re.I)
class EntitySubstitution(object):
"""Substitute XML or HTML entities for the corresponding characters."""
def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters_for_re = []
for codepoint, name in list(codepoint2name.items()):
character = unichr(codepoint)
if codepoint != 34:
# There's no point in turning the quotation mark into
# &quot;, unless it happens within an attribute value, which
# is handled elsewhere.
characters_for_re.append(character)
lookup[character] = name
# But we do want to turn &quot; into the quotation mark.
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters_for_re)
return lookup, reverse_lookup, re.compile(re_definition)
(CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER,
CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables()
CHARACTER_TO_XML_ENTITY = {
"'": "apos",
'"': "quot",
"&": "amp",
"<": "lt",
">": "gt",
}
BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
"&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)"
")")
AMPERSAND_OR_BRACKET = re.compile("([<>&])")
@classmethod
def _substitute_html_entity(cls, matchobj):
entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0))
return "&%s;" % entity
@classmethod
def _substitute_xml_entity(cls, matchobj):
"""Used with a regular expression to substitute the
appropriate XML entity for an XML special character."""
entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)]
return "&%s;" % entity
@classmethod
def quoted_attribute_value(self, value):
"""Make a value into a quoted XML attribute, possibly escaping it.
Most strings will be quoted using double quotes.
Bob's Bar -> "Bob's Bar"
If a string contains double quotes, it will be quoted using
single quotes.
Welcome to "my bar" -> 'Welcome to "my bar"'
If a string contains both single and double quotes, the
double quotes will be escaped, and the string will be quoted
using double quotes.
Welcome to "Bob's Bar" -> "Welcome to &quot;Bob's bar&quot;
"""
quote_with = '"'
if '"' in value:
if "'" in value:
# The string contains both single and double
# quotes. Turn the double quotes into
# entities. We quote the double quotes rather than
# the single quotes because the entity name is
# "&quot;" whether this is HTML or XML. If we
# quoted the single quotes, we'd have to decide
# between &apos; and &squot;.
replace_with = "&quot;"
value = value.replace('"', replace_with)
else:
# There are double quotes but no single quotes.
# We can use single quotes to quote the attribute.
quote_with = "'"
return quote_with + value + quote_with
@classmethod
def substitute_xml(cls, value, make_quoted_attribute=False):
"""Substitute XML entities for special XML characters.
:param value: A string to be substituted. The less-than sign
will become &lt;, the greater-than sign will become &gt;,
and any ampersands will become &amp;. If you want ampersands
that appear to be part of an entity definition to be left
alone, use substitute_xml_containing_entities() instead.
:param make_quoted_attribute: If True, then the string will be
quoted, as befits an attribute value.
"""
# Escape angle brackets and ampersands.
value = cls.AMPERSAND_OR_BRACKET.sub(
cls._substitute_xml_entity, value)
if make_quoted_attribute:
value = cls.quoted_attribute_value(value)
return value
@classmethod
def substitute_xml_containing_entities(
cls, value, make_quoted_attribute=False):
"""Substitute XML entities for special XML characters.
:param value: A string to be substituted. The less-than sign will
become &lt;, the greater-than sign will become &gt;, and any
ampersands that are not part of an entity defition will
become &amp;.
:param make_quoted_attribute: If True, then the string will be
quoted, as befits an attribute value.
"""
# Escape angle brackets, and ampersands that aren't part of
# entities.
value = cls.BARE_AMPERSAND_OR_BRACKET.sub(
cls._substitute_xml_entity, value)
if make_quoted_attribute:
value = cls.quoted_attribute_value(value)
return value
@classmethod
def substitute_html(cls, s):
"""Replace certain Unicode characters with named HTML entities.
This differs from data.encode(encoding, 'xmlcharrefreplace')
in that the goal is to make the result more readable (to those
with ASCII displays) rather than to recover from
errors. There's absolutely nothing wrong with a UTF-8 string
containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that
character with "&eacute;" will make it more readable to some
people.
"""
return cls.CHARACTER_TO_HTML_ENTITY_RE.sub(
cls._substitute_html_entity, s)
class EncodingDetector:
"""Suggests a number of possible encodings for a bytestring.
Order of precedence:
1. Encodings you specifically tell EncodingDetector to try first
(the override_encodings argument to the constructor).
2. An encoding declared within the bytestring itself, either in an
XML declaration (if the bytestring is to be interpreted as an XML
document), or in a <meta> tag (if the bytestring is to be
interpreted as an HTML document.)
3. An encoding detected through textual analysis by chardet,
cchardet, or a similar external library.
4. UTF-8.
5. Windows-1252.
"""
def __init__(self, markup, override_encodings=None, is_html=False,
exclude_encodings=None):
self.override_encodings = override_encodings or []
exclude_encodings = exclude_encodings or []
self.exclude_encodings = set([x.lower() for x in exclude_encodings])
self.chardet_encoding = None
self.is_html = is_html
self.declared_encoding = None
# First order of business: strip a byte-order mark.
self.markup, self.sniffed_encoding = self.strip_byte_order_mark(markup)
def _usable(self, encoding, tried):
if encoding is not None:
encoding = encoding.lower()
if encoding in self.exclude_encodings:
return False
if encoding not in tried:
tried.add(encoding)
return True
return False
@property
def encodings(self):
"""Yield a number of encodings that might work for this markup."""
tried = set()
for e in self.override_encodings:
if self._usable(e, tried):
yield e
# Did the document originally start with a byte-order mark
# that indicated its encoding?
if self._usable(self.sniffed_encoding, tried):
yield self.sniffed_encoding
# Look within the document for an XML or HTML encoding
# declaration.
if self.declared_encoding is None:
self.declared_encoding = self.find_declared_encoding(
self.markup, self.is_html)
if self._usable(self.declared_encoding, tried):
yield self.declared_encoding
# Use third-party character set detection to guess at the
# encoding.
if self.chardet_encoding is None:
self.chardet_encoding = chardet_dammit(self.markup)
if self._usable(self.chardet_encoding, tried):
yield self.chardet_encoding
# As a last-ditch effort, try utf-8 and windows-1252.
for e in ('utf-8', 'windows-1252'):
if self._usable(e, tried):
yield e
@classmethod
def strip_byte_order_mark(cls, data):
"""If a byte-order mark is present, strip it and return the encoding it implies."""
encoding = None
if isinstance(data, unicode):
# Unicode data cannot have a byte-order mark.
return data, encoding
if (len(data) >= 4) and (data[:2] == b'\xfe\xff') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16be'
data = data[2:]
elif (len(data) >= 4) and (data[:2] == b'\xff\xfe') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16le'
data = data[2:]
elif data[:3] == b'\xef\xbb\xbf':
encoding = 'utf-8'
data = data[3:]
elif data[:4] == b'\x00\x00\xfe\xff':
encoding = 'utf-32be'
data = data[4:]
elif data[:4] == b'\xff\xfe\x00\x00':
encoding = 'utf-32le'
data = data[4:]
return data, encoding
@classmethod
def find_declared_encoding(cls, markup, is_html=False, search_entire_document=False):
"""Given a document, tries to find its declared encoding.
An XML encoding is declared at the beginning of the document.
An HTML encoding is declared in a <meta> tag, hopefully near the
beginning of the document.
"""
if search_entire_document:
xml_endpos = html_endpos = len(markup)
else:
xml_endpos = 1024
html_endpos = max(2048, int(len(markup) * 0.05))
declared_encoding = None
declared_encoding_match = xml_encoding_re.search(markup, endpos=xml_endpos)
if not declared_encoding_match and is_html:
declared_encoding_match = html_meta_re.search(markup, endpos=html_endpos)
if declared_encoding_match is not None:
declared_encoding = declared_encoding_match.groups()[0].decode(
'ascii', 'replace')
if declared_encoding:
return declared_encoding.lower()
return None
class UnicodeDammit:
"""A class for detecting the encoding of a *ML document and
converting it to a Unicode string. If the source encoding is
windows-1252, can replace MS smart quotes with their HTML or XML
equivalents."""
# This dictionary maps commonly seen values for "charset" in HTML
# meta tags to the corresponding Python codec names. It only covers
# values that aren't in Python's aliases and can't be determined
# by the heuristics in find_codec.
CHARSET_ALIASES = {"macintosh": "mac-roman",
"x-sjis": "shift-jis"}
ENCODINGS_WITH_SMART_QUOTES = [
"windows-1252",
"iso-8859-1",
"iso-8859-2",
]
def __init__(self, markup, override_encodings=[],
smart_quotes_to=None, is_html=False, exclude_encodings=[]):
self.smart_quotes_to = smart_quotes_to
self.tried_encodings = []
self.contains_replacement_characters = False
self.is_html = is_html
self.log = logging.getLogger(__name__)
self.detector = EncodingDetector(
markup, override_encodings, is_html, exclude_encodings)
# Short-circuit if the data is in Unicode to begin with.
if isinstance(markup, unicode) or markup == '':
self.markup = markup
self.unicode_markup = unicode(markup)
self.original_encoding = None
return
# The encoding detector may have stripped a byte-order mark.
# Use the stripped markup from this point on.
self.markup = self.detector.markup
u = None
for encoding in self.detector.encodings:
markup = self.detector.markup
u = self._convert_from(encoding)
if u is not None:
break
if not u:
# None of the encodings worked. As an absolute last resort,
# try them again with character replacement.
for encoding in self.detector.encodings:
if encoding != "ascii":
u = self._convert_from(encoding, "replace")
if u is not None:
self.log.warning(
"Some characters could not be decoded, and were "
"replaced with REPLACEMENT CHARACTER."
)
self.contains_replacement_characters = True
break
# If none of that worked, we could at this point force it to
# ASCII, but that would destroy so much data that I think
# giving up is better.
self.unicode_markup = u
if not u:
self.original_encoding = None
def _sub_ms_char(self, match):
"""Changes a MS smart quote character to an XML or HTML
entity, or an ASCII character."""
orig = match.group(1)
if self.smart_quotes_to == 'ascii':
sub = self.MS_CHARS_TO_ASCII.get(orig).encode()
else:
sub = self.MS_CHARS.get(orig)
if type(sub) == tuple:
if self.smart_quotes_to == 'xml':
sub = '&#x'.encode() + sub[1].encode() + ';'.encode()
else:
sub = '&'.encode() + sub[0].encode() + ';'.encode()
else:
sub = sub.encode()
return sub
def _convert_from(self, proposed, errors="strict"):
proposed = self.find_codec(proposed)
if not proposed or (proposed, errors) in self.tried_encodings:
return None
self.tried_encodings.append((proposed, errors))
markup = self.markup
# Convert smart quotes to HTML if coming from an encoding
# that might have them.
if (self.smart_quotes_to is not None
and proposed in self.ENCODINGS_WITH_SMART_QUOTES):
smart_quotes_re = b"([\x80-\x9f])"
smart_quotes_compiled = re.compile(smart_quotes_re)
markup = smart_quotes_compiled.sub(self._sub_ms_char, markup)
try:
#print "Trying to convert document to %s (errors=%s)" % (
# proposed, errors)
u = self._to_unicode(markup, proposed, errors)
self.markup = u
self.original_encoding = proposed
except Exception as e:
#print "That didn't work!"
#print e
return None
#print "Correct encoding: %s" % proposed
return self.markup
def _to_unicode(self, data, encoding, errors="strict"):
'''Given a string and its encoding, decodes the string into Unicode.
%encoding is a string recognized by encodings.aliases'''
return unicode(data, encoding, errors)
@property
def declared_html_encoding(self):
if not self.is_html:
return None
return self.detector.declared_encoding
def find_codec(self, charset):
value = (self._codec(self.CHARSET_ALIASES.get(charset, charset))
or (charset and self._codec(charset.replace("-", "")))
or (charset and self._codec(charset.replace("-", "_")))
or (charset and charset.lower())
or charset
)
if value:
return value.lower()
return None
def _codec(self, charset):
if not charset:
return charset
codec = None
try:
codecs.lookup(charset)
codec = charset
except (LookupError, ValueError):
pass
return codec
# A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities.
MS_CHARS = {b'\x80': ('euro', '20AC'),
b'\x81': ' ',
b'\x82': ('sbquo', '201A'),
b'\x83': ('fnof', '192'),
b'\x84': ('bdquo', '201E'),
b'\x85': ('hellip', '2026'),
b'\x86': ('dagger', '2020'),
b'\x87': ('Dagger', '2021'),
b'\x88': ('circ', '2C6'),
b'\x89': ('permil', '2030'),
b'\x8A': ('Scaron', '160'),
b'\x8B': ('lsaquo', '2039'),
b'\x8C': ('OElig', '152'),
b'\x8D': '?',
b'\x8E': ('#x17D', '17D'),
b'\x8F': '?',
b'\x90': '?',
b'\x91': ('lsquo', '2018'),
b'\x92': ('rsquo', '2019'),
b'\x93': ('ldquo', '201C'),
b'\x94': ('rdquo', '201D'),
b'\x95': ('bull', '2022'),
b'\x96': ('ndash', '2013'),
b'\x97': ('mdash', '2014'),
b'\x98': ('tilde', '2DC'),
b'\x99': ('trade', '2122'),
b'\x9a': ('scaron', '161'),
b'\x9b': ('rsaquo', '203A'),
b'\x9c': ('oelig', '153'),
b'\x9d': '?',
b'\x9e': ('#x17E', '17E'),
b'\x9f': ('Yuml', ''),}
# A parochial partial mapping of ISO-Latin-1 to ASCII. Contains
# horrors like stripping diacritical marks to turn á into a, but also
# contains non-horrors like turning “ into ".
MS_CHARS_TO_ASCII = {
b'\x80' : 'EUR',
b'\x81' : ' ',
b'\x82' : ',',
b'\x83' : 'f',
b'\x84' : ',,',
b'\x85' : '...',
b'\x86' : '+',
b'\x87' : '++',
b'\x88' : '^',
b'\x89' : '%',
b'\x8a' : 'S',
b'\x8b' : '<',
b'\x8c' : 'OE',
b'\x8d' : '?',
b'\x8e' : 'Z',
b'\x8f' : '?',
b'\x90' : '?',
b'\x91' : "'",
b'\x92' : "'",
b'\x93' : '"',
b'\x94' : '"',
b'\x95' : '*',
b'\x96' : '-',
b'\x97' : '--',
b'\x98' : '~',
b'\x99' : '(TM)',
b'\x9a' : 's',
b'\x9b' : '>',
b'\x9c' : 'oe',
b'\x9d' : '?',
b'\x9e' : 'z',
b'\x9f' : 'Y',
b'\xa0' : ' ',
b'\xa1' : '!',
b'\xa2' : 'c',
b'\xa3' : 'GBP',
b'\xa4' : '$', #This approximation is especially parochial--this is the
#generic currency symbol.
b'\xa5' : 'YEN',
b'\xa6' : '|',
b'\xa7' : 'S',
b'\xa8' : '..',
b'\xa9' : '',
b'\xaa' : '(th)',
b'\xab' : '<<',
b'\xac' : '!',
b'\xad' : ' ',
b'\xae' : '(R)',
b'\xaf' : '-',
b'\xb0' : 'o',
b'\xb1' : '+-',
b'\xb2' : '2',
b'\xb3' : '3',
b'\xb4' : ("'", 'acute'),
b'\xb5' : 'u',
b'\xb6' : 'P',
b'\xb7' : '*',
b'\xb8' : ',',
b'\xb9' : '1',
b'\xba' : '(th)',
b'\xbb' : '>>',
b'\xbc' : '1/4',
b'\xbd' : '1/2',
b'\xbe' : '3/4',
b'\xbf' : '?',
b'\xc0' : 'A',
b'\xc1' : 'A',
b'\xc2' : 'A',
b'\xc3' : 'A',
b'\xc4' : 'A',
b'\xc5' : 'A',
b'\xc6' : 'AE',
b'\xc7' : 'C',
b'\xc8' : 'E',
b'\xc9' : 'E',
b'\xca' : 'E',
b'\xcb' : 'E',
b'\xcc' : 'I',
b'\xcd' : 'I',
b'\xce' : 'I',
b'\xcf' : 'I',
b'\xd0' : 'D',
b'\xd1' : 'N',
b'\xd2' : 'O',
b'\xd3' : 'O',
b'\xd4' : 'O',
b'\xd5' : 'O',
b'\xd6' : 'O',
b'\xd7' : '*',
b'\xd8' : 'O',
b'\xd9' : 'U',
b'\xda' : 'U',
b'\xdb' : 'U',
b'\xdc' : 'U',
b'\xdd' : 'Y',
b'\xde' : 'b',
b'\xdf' : 'B',
b'\xe0' : 'a',
b'\xe1' : 'a',
b'\xe2' : 'a',
b'\xe3' : 'a',
b'\xe4' : 'a',
b'\xe5' : 'a',
b'\xe6' : 'ae',
b'\xe7' : 'c',
b'\xe8' : 'e',
b'\xe9' : 'e',
b'\xea' : 'e',
b'\xeb' : 'e',
b'\xec' : 'i',
b'\xed' : 'i',
b'\xee' : 'i',
b'\xef' : 'i',
b'\xf0' : 'o',
b'\xf1' : 'n',
b'\xf2' : 'o',
b'\xf3' : 'o',
b'\xf4' : 'o',
b'\xf5' : 'o',
b'\xf6' : 'o',
b'\xf7' : '/',
b'\xf8' : 'o',
b'\xf9' : 'u',
b'\xfa' : 'u',
b'\xfb' : 'u',
b'\xfc' : 'u',
b'\xfd' : 'y',
b'\xfe' : 'b',
b'\xff' : 'y',
}
# A map used when removing rogue Windows-1252/ISO-8859-1
# characters in otherwise UTF-8 documents.
#
# Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in
# Windows-1252.
WINDOWS_1252_TO_UTF8 = {
0x80 : b'\xe2\x82\xac', # €
0x82 : b'\xe2\x80\x9a', # ‚
0x83 : b'\xc6\x92', # ƒ
0x84 : b'\xe2\x80\x9e', # „
0x85 : b'\xe2\x80\xa6', # …
0x86 : b'\xe2\x80\xa0', # †
0x87 : b'\xe2\x80\xa1', # ‡
0x88 : b'\xcb\x86', # ˆ
0x89 : b'\xe2\x80\xb0', # ‰
0x8a : b'\xc5\xa0', # Š
0x8b : b'\xe2\x80\xb9', # ‹
0x8c : b'\xc5\x92', # Œ
0x8e : b'\xc5\xbd', # Ž
0x91 : b'\xe2\x80\x98', # ‘
0x92 : b'\xe2\x80\x99', # ’
0x93 : b'\xe2\x80\x9c', # “
0x94 : b'\xe2\x80\x9d', # ”
0x95 : b'\xe2\x80\xa2', # •
0x96 : b'\xe2\x80\x93', # –
0x97 : b'\xe2\x80\x94', # —
0x98 : b'\xcb\x9c', # ˜
0x99 : b'\xe2\x84\xa2', # ™
0x9a : b'\xc5\xa1', # š
0x9b : b'\xe2\x80\xba', # ›
0x9c : b'\xc5\x93', # œ
0x9e : b'\xc5\xbe', # ž
0x9f : b'\xc5\xb8', # Ÿ
0xa0 : b'\xc2\xa0', #  
0xa1 : b'\xc2\xa1', # ¡
0xa2 : b'\xc2\xa2', # ¢
0xa3 : b'\xc2\xa3', # £
0xa4 : b'\xc2\xa4', # ¤
0xa5 : b'\xc2\xa5', # ¥
0xa6 : b'\xc2\xa6', # ¦
0xa7 : b'\xc2\xa7', # §
0xa8 : b'\xc2\xa8', # ¨
0xa9 : b'\xc2\xa9', # ©
0xaa : b'\xc2\xaa', # ª
0xab : b'\xc2\xab', # «
0xac : b'\xc2\xac', # ¬
0xad : b'\xc2\xad', # ­
0xae : b'\xc2\xae', # ®
0xaf : b'\xc2\xaf', # ¯
0xb0 : b'\xc2\xb0', # °
0xb1 : b'\xc2\xb1', # ±
0xb2 : b'\xc2\xb2', # ²
0xb3 : b'\xc2\xb3', # ³
0xb4 : b'\xc2\xb4', # ´
0xb5 : b'\xc2\xb5', # µ
0xb6 : b'\xc2\xb6', # ¶
0xb7 : b'\xc2\xb7', # ·
0xb8 : b'\xc2\xb8', # ¸
0xb9 : b'\xc2\xb9', # ¹
0xba : b'\xc2\xba', # º
0xbb : b'\xc2\xbb', # »
0xbc : b'\xc2\xbc', # ¼
0xbd : b'\xc2\xbd', # ½
0xbe : b'\xc2\xbe', # ¾
0xbf : b'\xc2\xbf', # ¿
0xc0 : b'\xc3\x80', # À
0xc1 : b'\xc3\x81', # Á
0xc2 : b'\xc3\x82', # Â
0xc3 : b'\xc3\x83', # Ã
0xc4 : b'\xc3\x84', # Ä
0xc5 : b'\xc3\x85', # Å
0xc6 : b'\xc3\x86', # Æ
0xc7 : b'\xc3\x87', # Ç
0xc8 : b'\xc3\x88', # È
0xc9 : b'\xc3\x89', # É
0xca : b'\xc3\x8a', # Ê
0xcb : b'\xc3\x8b', # Ë
0xcc : b'\xc3\x8c', # Ì
0xcd : b'\xc3\x8d', # Í
0xce : b'\xc3\x8e', # Î
0xcf : b'\xc3\x8f', # Ï
0xd0 : b'\xc3\x90', # Ð
0xd1 : b'\xc3\x91', # Ñ
0xd2 : b'\xc3\x92', # Ò
0xd3 : b'\xc3\x93', # Ó
0xd4 : b'\xc3\x94', # Ô
0xd5 : b'\xc3\x95', # Õ
0xd6 : b'\xc3\x96', # Ö
0xd7 : b'\xc3\x97', # ×
0xd8 : b'\xc3\x98', # Ø
0xd9 : b'\xc3\x99', # Ù
0xda : b'\xc3\x9a', # Ú
0xdb : b'\xc3\x9b', # Û
0xdc : b'\xc3\x9c', # Ü
0xdd : b'\xc3\x9d', # Ý
0xde : b'\xc3\x9e', # Þ
0xdf : b'\xc3\x9f', # ß
0xe0 : b'\xc3\xa0', # à
0xe1 : b'\xa1', # á
0xe2 : b'\xc3\xa2', # â
0xe3 : b'\xc3\xa3', # ã
0xe4 : b'\xc3\xa4', # ä
0xe5 : b'\xc3\xa5', # å
0xe6 : b'\xc3\xa6', # æ
0xe7 : b'\xc3\xa7', # ç
0xe8 : b'\xc3\xa8', # è
0xe9 : b'\xc3\xa9', # é
0xea : b'\xc3\xaa', # ê
0xeb : b'\xc3\xab', # ë
0xec : b'\xc3\xac', # ì
0xed : b'\xc3\xad', # í
0xee : b'\xc3\xae', # î
0xef : b'\xc3\xaf', # ï
0xf0 : b'\xc3\xb0', # ð
0xf1 : b'\xc3\xb1', # ñ
0xf2 : b'\xc3\xb2', # ò
0xf3 : b'\xc3\xb3', # ó
0xf4 : b'\xc3\xb4', # ô
0xf5 : b'\xc3\xb5', # õ
0xf6 : b'\xc3\xb6', # ö
0xf7 : b'\xc3\xb7', # ÷
0xf8 : b'\xc3\xb8', # ø
0xf9 : b'\xc3\xb9', # ù
0xfa : b'\xc3\xba', # ú
0xfb : b'\xc3\xbb', # û
0xfc : b'\xc3\xbc', # ü
0xfd : b'\xc3\xbd', # ý
0xfe : b'\xc3\xbe', # þ
}
MULTIBYTE_MARKERS_AND_SIZES = [
(0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF
(0xe0, 0xef, 3), # 3-byte characters start with E0-EF
(0xf0, 0xf4, 4), # 4-byte characters start with F0-F4
]
FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0]
LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1]
@classmethod
def detwingle(cls, in_bytes, main_encoding="utf8",
embedded_encoding="windows-1252"):
"""Fix characters from one encoding embedded in some other encoding.
Currently the only situation supported is Windows-1252 (or its
subset ISO-8859-1), embedded in UTF-8.
The input must be a bytestring. If you've already converted
the document to Unicode, you're too late.
The output is a bytestring in which `embedded_encoding`
characters have been converted to their `main_encoding`
equivalents.
"""
if embedded_encoding.replace('_', '-').lower() not in (
'windows-1252', 'windows_1252'):
raise NotImplementedError(
"Windows-1252 and ISO-8859-1 are the only currently supported "
"embedded encodings.")
if main_encoding.lower() not in ('utf8', 'utf-8'):
raise NotImplementedError(
"UTF-8 is the only currently supported main encoding.")
byte_chunks = []
chunk_start = 0
pos = 0
while pos < len(in_bytes):
byte = in_bytes[pos]
if not isinstance(byte, int):
# Python 2.x
byte = ord(byte)
if (byte >= cls.FIRST_MULTIBYTE_MARKER
and byte <= cls.LAST_MULTIBYTE_MARKER):
# This is the start of a UTF-8 multibyte character. Skip
# to the end.
for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES:
if byte >= start and byte <= end:
pos += size
break
elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8:
# We found a Windows-1252 character!
# Save the string up to this point as a chunk.
byte_chunks.append(in_bytes[chunk_start:pos])
# Now translate the Windows-1252 character into UTF-8
# and add it as another, one-byte chunk.
byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte])
pos += 1
chunk_start = pos
else:
# Go on to the next character.
pos += 1
if chunk_start == 0:
# The string is unchanged.
return in_bytes
else:
# Store the final chunk.
byte_chunks.append(in_bytes[chunk_start:])
return b''.join(byte_chunks)

219
src/fastwq/libs/bs4/diagnose.py Normal file
View File

@ -0,0 +1,219 @@
"""Diagnostic functions, mainly for use when doing tech support."""
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.
__license__ = "MIT"
import cProfile
from StringIO import StringIO
from HTMLParser import HTMLParser
import bs4
from bs4 import BeautifulSoup, __version__
from bs4.builder import builder_registry
import os
import pstats
import random
import tempfile
import time
import traceback
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
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print (
"I noticed that %s is not installed. Installing it may help." %
name)
if 'lxml' in basic_parsers:
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 (
"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 (
"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
with open(data) as fp:
data = fp.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."
return
print
for parser in basic_parsers:
print "Trying to parse your markup with %s" % parser
success = False
try:
soup = BeautifulSoup(data, parser)
success = True
except Exception, 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 "-" * 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.
"""
from lxml import etree
for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
print("%s, %4s, %s" % (event, element.tag, element.text))
class AnnouncingParser(HTMLParser):
"""Announces HTMLParser parse events, without doing anything else."""
def _p(self, s):
print(s)
def handle_starttag(self, name, attrs):
self._p("%s START" % name)
def handle_endtag(self, name):
self._p("%s END" % name)
def handle_data(self, data):
self._p("%s DATA" % data)
def handle_charref(self, name):
self._p("%s CHARREF" % name)
def handle_entityref(self, name):
self._p("%s ENTITYREF" % name)
def handle_comment(self, data):
self._p("%s COMMENT" % data)
def handle_decl(self, data):
self._p("%s DECL" % data)
def unknown_decl(self, data):
self._p("%s UNKNOWN-DECL" % data)
def handle_pi(self, data):
self._p("%s PI" % data)
def htmlparser_trace(data):
"""Print out the HTMLParser events that occur during parsing.
This lets you see how HTMLParser parses a document when no
Beautiful Soup code is running.
"""
parser = AnnouncingParser()
parser.feed(data)
_vowels = "aeiou"
_consonants = "bcdfghjklmnpqrstvwxyz"
def rword(length=5):
"Generate a random word-like string."
s = ''
for i in range(length):
if i % 2 == 0:
t = _consonants
else:
t = _vowels
s += random.choice(t)
return s
def rsentence(length=4):
"Generate a random sentence-like string."
return " ".join(rword(random.randint(4,9)) for i in range(length))
def rdoc(num_elements=1000):
"""Randomly generate an invalid HTML document."""
tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
elements = []
for i in range(num_elements):
choice = random.randint(0,3)
if choice == 0:
# New tag.
tag_name = random.choice(tag_names)
elements.append("<%s>" % tag_name)
elif choice == 1:
elements.append(rsentence(random.randint(1,4)))
elif choice == 2:
# Close a tag.
tag_name = random.choice(tag_names)
elements.append("</%s>" % tag_name)
return "<html>" + "\n".join(elements) + "</html>"
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print "Comparative parser benchmark on Beautiful Soup %s" % __version__
data = rdoc(num_elements)
print "Generated a large invalid HTML document (%d bytes)." % len(data)
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception, 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)
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
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)
def profile(num_elements=100000, parser="lxml"):
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
data = rdoc(num_elements)
vars = dict(bs4=bs4, data=data, parser=parser)
cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
stats = pstats.Stats(filename)
# stats.strip_dirs()
stats.sort_stats("cumulative")
stats.print_stats('_html5lib|bs4', 50)
if __name__ == '__main__':
diagnose(sys.stdin.read())

1808
src/fastwq/libs/bs4/element.py Normal file
View File

File diff suppressed because it is too large Load Diff