bitbake: bs4: Add beautifulsoup 4.3.2 to assist the fetcher
Added Beautifulsoup module because fetch/wget latest_versionstring method depends on it. This provides support to fetch/wget.py module for search new package versions in upstream sites. (Bitbake rev: 4626c9b77e5eded97507b6f9ca0d891f9a54bb8a) Signed-off-by: Aníbal Limón <anibal.limon@linux.intel.com> Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
This commit is contained in:
parent
bc6330cb7f
commit
25e3e57c55
|
@ -0,0 +1,43 @@
|
|||
Behold, mortal, the origins of Beautiful Soup...
|
||||
================================================
|
||||
|
||||
Leonard Richardson is the primary programmer.
|
||||
|
||||
Aaron DeVore is awesome.
|
||||
|
||||
Mark Pilgrim provided the encoding detection code that forms the base
|
||||
of UnicodeDammit.
|
||||
|
||||
Thomas Kluyver and Ezio Melotti finished the work of getting Beautiful
|
||||
Soup 4 working under Python 3.
|
||||
|
||||
Simon Willison wrote soupselect, which was used to make Beautiful Soup
|
||||
support CSS selectors.
|
||||
|
||||
Sam Ruby helped with a lot of edge cases.
|
||||
|
||||
Jonathan Ellis was awarded the prestigous Beau Potage D'Or for his
|
||||
work in solving the nestable tags conundrum.
|
||||
|
||||
An incomplete list of people have contributed patches to Beautiful
|
||||
Soup:
|
||||
|
||||
Istvan Albert, Andrew Lin, Anthony Baxter, Andrew Boyko, Tony Chang,
|
||||
Zephyr Fang, Fuzzy, Roman Gaufman, Yoni Gilad, Richie Hindle, Peteris
|
||||
Krumins, Kent Johnson, Ben Last, Robert Leftwich, Staffan Malmgren,
|
||||
Ksenia Marasanova, JP Moins, Adam Monsen, John Nagle, "Jon", Ed
|
||||
Oskiewicz, Greg Phillips, Giles Radford, Arthur Rudolph, Marko
|
||||
Samastur, Jouni Seppänen, Alexander Schmolck, Andy Theyers, Glyn
|
||||
Webster, Paul Wright, Danny Yoo
|
||||
|
||||
An incomplete list of people who made suggestions or found bugs or
|
||||
found ways to break Beautiful Soup:
|
||||
|
||||
Hanno Böck, Matteo Bertini, Chris Curvey, Simon Cusack, Bruce Eckel,
|
||||
Matt Ernst, Michael Foord, Tom Harris, Bill de hOra, Donald Howes,
|
||||
Matt Patterson, Scott Roberts, Steve Strassmann, Mike Williams,
|
||||
warchild at redho dot com, Sami Kuisma, Carlos Rocha, Bob Hutchison,
|
||||
Joren Mc, Michal Migurski, John Kleven, Tim Heaney, Tripp Lilley, Ed
|
||||
Summers, Dennis Sutch, Chris Smith, Aaron Sweep^W Swartz, Stuart
|
||||
Turner, Greg Edwards, Kevin J Kalupson, Nikos Kouremenos, Artur de
|
||||
Sousa Rocha, Yichun Wei, Per Vognsen
|
|
@ -0,0 +1,26 @@
|
|||
Beautiful Soup is made available under the MIT license:
|
||||
|
||||
Copyright (c) 2004-2012 Leonard Richardson
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining
|
||||
a copy of this software and associated documentation files (the
|
||||
"Software"), to deal in the Software without restriction, including
|
||||
without limitation the rights to use, copy, modify, merge, publish,
|
||||
distribute, sublicense, and/or sell copies of the Software, and to
|
||||
permit persons to whom the Software is furnished to do so, subject to
|
||||
the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be
|
||||
included in all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
|
||||
BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
|
||||
ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
|
||||
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE, DAMMIT.
|
||||
|
||||
Beautiful Soup incorporates code from the html5lib library, which is
|
||||
also made available under the MIT license.
|
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,406 @@
|
|||
"""Beautiful Soup
|
||||
Elixir and Tonic
|
||||
"The Screen-Scraper's Friend"
|
||||
http://www.crummy.com/software/BeautifulSoup/
|
||||
|
||||
Beautiful Soup uses a pluggable XML or HTML parser to parse a
|
||||
(possibly invalid) document into a tree representation. Beautiful Soup
|
||||
provides provides methods and Pythonic idioms that make it easy to
|
||||
navigate, search, and modify the parse tree.
|
||||
|
||||
Beautiful Soup works with Python 2.6 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/
|
||||
"""
|
||||
|
||||
__author__ = "Leonard Richardson (leonardr@segfault.org)"
|
||||
__version__ = "4.3.2"
|
||||
__copyright__ = "Copyright (c) 2004-2013 Leonard Richardson"
|
||||
__license__ = "MIT"
|
||||
|
||||
__all__ = ['BeautifulSoup']
|
||||
|
||||
import os
|
||||
import re
|
||||
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.
|
||||
syntax_error = u'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'
|
||||
|
||||
def __init__(self, markup="", features=None, builder=None,
|
||||
parse_only=None, from_encoding=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. You can pass in features='html' "
|
||||
"or features='xml' to get a builder capable of handling "
|
||||
"one or the other.")
|
||||
|
||||
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 len(kwargs) > 0:
|
||||
arg = kwargs.keys().pop()
|
||||
raise TypeError(
|
||||
"__init__() got an unexpected keyword argument '%s'" % arg)
|
||||
|
||||
if builder is None:
|
||||
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()
|
||||
self.builder = builder
|
||||
self.is_xml = builder.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:
|
||||
# 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:
|
||||
warnings.warn(
|
||||
'"%s" looks like a filename, not markup. You should probably open this file and pass the filehandle into Beautiful Soup.' % markup)
|
||||
if markup[:5] == "http:" or markup[:6] == "https:":
|
||||
# TODO: This is ugly but I couldn't get it to work in
|
||||
# Python 3 otherwise.
|
||||
if ((isinstance(markup, bytes) and not b' ' in markup)
|
||||
or (isinstance(markup, unicode) and not u' ' in markup)):
|
||||
warnings.warn(
|
||||
'"%s" looks like a URL. Beautiful Soup is not an HTTP client. You should probably use an HTTP client to get the document behind the URL, and feed that document to Beautiful Soup.' % markup)
|
||||
|
||||
for (self.markup, self.original_encoding, self.declared_html_encoding,
|
||||
self.contains_replacement_characters) in (
|
||||
self.builder.prepare_markup(markup, from_encoding)):
|
||||
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 _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."""
|
||||
navigable = subclass(s)
|
||||
navigable.setup()
|
||||
return navigable
|
||||
|
||||
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
|
||||
most_recent_element = most_recent_element or self._most_recent_element
|
||||
o.setup(parent, most_recent_element)
|
||||
|
||||
if most_recent_element is not None:
|
||||
most_recent_element.next_element = o
|
||||
self._most_recent_element = o
|
||||
parent.contents.append(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 occured
|
||||
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()
|
|
@ -0,0 +1,321 @@
|
|||
from collections import defaultdict
|
||||
import itertools
|
||||
import sys
|
||||
from bs4.element import (
|
||||
CharsetMetaAttributeValue,
|
||||
ContentMetaAttributeValue,
|
||||
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."""
|
||||
|
||||
features = []
|
||||
|
||||
is_xml = 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 = set(['pre', 'textarea'])
|
||||
empty_element_tags = set(['br' , 'hr', 'input', 'img', 'meta',
|
||||
'spacer', 'link', 'frame', 'base'])
|
||||
|
||||
# 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['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)
|
||||
try:
|
||||
from . import _html5lib
|
||||
register_treebuilders_from(_html5lib)
|
||||
except ImportError:
|
||||
# They don't have html5lib installed.
|
||||
pass
|
||||
try:
|
||||
from . import _lxml
|
||||
register_treebuilders_from(_lxml)
|
||||
except ImportError:
|
||||
# They don't have lxml installed.
|
||||
pass
|
|
@ -0,0 +1,285 @@
|
|||
__all__ = [
|
||||
'HTML5TreeBuilder',
|
||||
]
|
||||
|
||||
import warnings
|
||||
from bs4.builder import (
|
||||
PERMISSIVE,
|
||||
HTML,
|
||||
HTML_5,
|
||||
HTMLTreeBuilder,
|
||||
)
|
||||
from bs4.element import NamespacedAttribute
|
||||
import html5lib
|
||||
from html5lib.constants import namespaces
|
||||
from bs4.element import (
|
||||
Comment,
|
||||
Doctype,
|
||||
NavigableString,
|
||||
Tag,
|
||||
)
|
||||
|
||||
class HTML5TreeBuilder(HTMLTreeBuilder):
|
||||
"""Use html5lib to build a tree."""
|
||||
|
||||
features = ['html5lib', PERMISSIVE, HTML_5, HTML]
|
||||
|
||||
def prepare_markup(self, markup, user_specified_encoding):
|
||||
# Store the user-specified encoding for use later on.
|
||||
self.user_specified_encoding = user_specified_encoding
|
||||
yield (markup, None, None, False)
|
||||
|
||||
# These methods are defined by Beautiful Soup.
|
||||
def feed(self, markup):
|
||||
if self.soup.parse_only is not None:
|
||||
warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
|
||||
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
|
||||
doc = parser.parse(markup, encoding=self.user_specified_encoding)
|
||||
|
||||
# Set the character encoding detected by the tokenizer.
|
||||
if isinstance(markup, unicode):
|
||||
# We need to special-case this because html5lib sets
|
||||
# charEncoding to UTF-8 if it gets Unicode input.
|
||||
doc.original_encoding = None
|
||||
else:
|
||||
doc.original_encoding = parser.tokenizer.stream.charEncoding[0]
|
||||
|
||||
def create_treebuilder(self, namespaceHTMLElements):
|
||||
self.underlying_builder = TreeBuilderForHtml5lib(
|
||||
self.soup, namespaceHTMLElements)
|
||||
return self.underlying_builder
|
||||
|
||||
def test_fragment_to_document(self, fragment):
|
||||
"""See `TreeBuilder`."""
|
||||
return u'<html><head></head><body>%s</body></html>' % fragment
|
||||
|
||||
|
||||
class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
|
||||
|
||||
def __init__(self, soup, namespaceHTMLElements):
|
||||
self.soup = soup
|
||||
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
|
||||
|
||||
def documentClass(self):
|
||||
self.soup.reset()
|
||||
return Element(self.soup, self.soup, None)
|
||||
|
||||
def insertDoctype(self, token):
|
||||
name = token["name"]
|
||||
publicId = token["publicId"]
|
||||
systemId = token["systemId"]
|
||||
|
||||
doctype = Doctype.for_name_and_ids(name, publicId, systemId)
|
||||
self.soup.object_was_parsed(doctype)
|
||||
|
||||
def elementClass(self, name, namespace):
|
||||
tag = self.soup.new_tag(name, namespace)
|
||||
return Element(tag, self.soup, namespace)
|
||||
|
||||
def commentClass(self, data):
|
||||
return TextNode(Comment(data), self.soup)
|
||||
|
||||
def fragmentClass(self):
|
||||
self.soup = BeautifulSoup("")
|
||||
self.soup.name = "[document_fragment]"
|
||||
return Element(self.soup, self.soup, None)
|
||||
|
||||
def appendChild(self, node):
|
||||
# XXX This code is not covered by the BS4 tests.
|
||||
self.soup.append(node.element)
|
||||
|
||||
def getDocument(self):
|
||||
return self.soup
|
||||
|
||||
def getFragment(self):
|
||||
return html5lib.treebuilders._base.TreeBuilder.getFragment(self).element
|
||||
|
||||
class AttrList(object):
|
||||
def __init__(self, element):
|
||||
self.element = element
|
||||
self.attrs = dict(self.element.attrs)
|
||||
def __iter__(self):
|
||||
return list(self.attrs.items()).__iter__()
|
||||
def __setitem__(self, name, value):
|
||||
"set attr", name, value
|
||||
self.element[name] = value
|
||||
def items(self):
|
||||
return list(self.attrs.items())
|
||||
def keys(self):
|
||||
return list(self.attrs.keys())
|
||||
def __len__(self):
|
||||
return len(self.attrs)
|
||||
def __getitem__(self, name):
|
||||
return self.attrs[name]
|
||||
def __contains__(self, name):
|
||||
return name in list(self.attrs.keys())
|
||||
|
||||
|
||||
class Element(html5lib.treebuilders._base.Node):
|
||||
def __init__(self, element, soup, namespace):
|
||||
html5lib.treebuilders._base.Node.__init__(self, element.name)
|
||||
self.element = element
|
||||
self.soup = soup
|
||||
self.namespace = namespace
|
||||
|
||||
def appendChild(self, node):
|
||||
string_child = child = None
|
||||
if isinstance(node, basestring):
|
||||
# Some other piece of code decided to pass in a string
|
||||
# instead of creating a TextElement object to contain the
|
||||
# string.
|
||||
string_child = child = node
|
||||
elif isinstance(node, Tag):
|
||||
# Some other piece of code decided to pass in a Tag
|
||||
# instead of creating an Element object to contain the
|
||||
# Tag.
|
||||
child = node
|
||||
elif node.element.__class__ == NavigableString:
|
||||
string_child = child = node.element
|
||||
else:
|
||||
child = node.element
|
||||
|
||||
if not isinstance(child, basestring) and child.parent is not None:
|
||||
node.element.extract()
|
||||
|
||||
if (string_child and self.element.contents
|
||||
and self.element.contents[-1].__class__ == NavigableString):
|
||||
# We are appending a string onto another string.
|
||||
# TODO This has O(n^2) performance, for input like
|
||||
# "a</a>a</a>a</a>..."
|
||||
old_element = self.element.contents[-1]
|
||||
new_element = self.soup.new_string(old_element + string_child)
|
||||
old_element.replace_with(new_element)
|
||||
self.soup._most_recent_element = new_element
|
||||
else:
|
||||
if isinstance(node, basestring):
|
||||
# Create a brand new NavigableString from this string.
|
||||
child = self.soup.new_string(node)
|
||||
|
||||
# Tell Beautiful Soup to act as if it parsed this element
|
||||
# immediately after the parent's last descendant. (Or
|
||||
# immediately after the parent, if it has no children.)
|
||||
if self.element.contents:
|
||||
most_recent_element = self.element._last_descendant(False)
|
||||
else:
|
||||
most_recent_element = self.element
|
||||
|
||||
self.soup.object_was_parsed(
|
||||
child, parent=self.element,
|
||||
most_recent_element=most_recent_element)
|
||||
|
||||
def getAttributes(self):
|
||||
return AttrList(self.element)
|
||||
|
||||
def setAttributes(self, attributes):
|
||||
if attributes is not None and len(attributes) > 0:
|
||||
|
||||
converted_attributes = []
|
||||
for name, value in list(attributes.items()):
|
||||
if isinstance(name, tuple):
|
||||
new_name = NamespacedAttribute(*name)
|
||||
del attributes[name]
|
||||
attributes[new_name] = value
|
||||
|
||||
self.soup.builder._replace_cdata_list_attribute_values(
|
||||
self.name, attributes)
|
||||
for name, value in attributes.items():
|
||||
self.element[name] = value
|
||||
|
||||
# The attributes may contain variables that need substitution.
|
||||
# Call set_up_substitutions manually.
|
||||
#
|
||||
# The Tag constructor called this method when the Tag was created,
|
||||
# but we just set/changed the attributes, so call it again.
|
||||
self.soup.builder.set_up_substitutions(self.element)
|
||||
attributes = property(getAttributes, setAttributes)
|
||||
|
||||
def insertText(self, data, insertBefore=None):
|
||||
if insertBefore:
|
||||
text = TextNode(self.soup.new_string(data), self.soup)
|
||||
self.insertBefore(data, insertBefore)
|
||||
else:
|
||||
self.appendChild(data)
|
||||
|
||||
def insertBefore(self, node, refNode):
|
||||
index = self.element.index(refNode.element)
|
||||
if (node.element.__class__ == NavigableString and self.element.contents
|
||||
and self.element.contents[index-1].__class__ == NavigableString):
|
||||
# (See comments in appendChild)
|
||||
old_node = self.element.contents[index-1]
|
||||
new_str = self.soup.new_string(old_node + node.element)
|
||||
old_node.replace_with(new_str)
|
||||
else:
|
||||
self.element.insert(index, node.element)
|
||||
node.parent = self
|
||||
|
||||
def removeChild(self, node):
|
||||
node.element.extract()
|
||||
|
||||
def reparentChildren(self, new_parent):
|
||||
"""Move all of this tag's children into another tag."""
|
||||
element = self.element
|
||||
new_parent_element = new_parent.element
|
||||
# Determine what this tag's next_element will be once all the children
|
||||
# are removed.
|
||||
final_next_element = element.next_sibling
|
||||
|
||||
new_parents_last_descendant = new_parent_element._last_descendant(False, False)
|
||||
if len(new_parent_element.contents) > 0:
|
||||
# The new parent already contains children. We will be
|
||||
# appending this tag's children to the end.
|
||||
new_parents_last_child = new_parent_element.contents[-1]
|
||||
new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
|
||||
else:
|
||||
# The new parent contains no children.
|
||||
new_parents_last_child = None
|
||||
new_parents_last_descendant_next_element = new_parent_element.next_element
|
||||
|
||||
to_append = element.contents
|
||||
append_after = new_parent.element.contents
|
||||
if len(to_append) > 0:
|
||||
# Set the first child's previous_element and previous_sibling
|
||||
# to elements within the new parent
|
||||
first_child = to_append[0]
|
||||
first_child.previous_element = new_parents_last_descendant
|
||||
first_child.previous_sibling = new_parents_last_child
|
||||
|
||||
# Fix the last child's next_element and next_sibling
|
||||
last_child = to_append[-1]
|
||||
last_child.next_element = new_parents_last_descendant_next_element
|
||||
last_child.next_sibling = None
|
||||
|
||||
for child in to_append:
|
||||
child.parent = new_parent_element
|
||||
new_parent_element.contents.append(child)
|
||||
|
||||
# Now that this element has no children, change its .next_element.
|
||||
element.contents = []
|
||||
element.next_element = final_next_element
|
||||
|
||||
def cloneNode(self):
|
||||
tag = self.soup.new_tag(self.element.name, self.namespace)
|
||||
node = Element(tag, self.soup, self.namespace)
|
||||
for key,value in self.attributes:
|
||||
node.attributes[key] = value
|
||||
return node
|
||||
|
||||
def hasContent(self):
|
||||
return self.element.contents
|
||||
|
||||
def getNameTuple(self):
|
||||
if self.namespace == None:
|
||||
return namespaces["html"], self.name
|
||||
else:
|
||||
return self.namespace, self.name
|
||||
|
||||
nameTuple = property(getNameTuple)
|
||||
|
||||
class TextNode(Element):
|
||||
def __init__(self, element, soup):
|
||||
html5lib.treebuilders._base.Node.__init__(self, None)
|
||||
self.element = element
|
||||
self.soup = soup
|
||||
|
||||
def cloneNode(self):
|
||||
raise NotImplementedError
|
|
@ -0,0 +1,258 @@
|
|||
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
|
||||
|
||||
__all__ = [
|
||||
'HTMLParserTreeBuilder',
|
||||
]
|
||||
|
||||
from HTMLParser import (
|
||||
HTMLParser,
|
||||
HTMLParseError,
|
||||
)
|
||||
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
|
||||
or (major == 3 and minor > 2)
|
||||
or (major == 3 and minor == 2 and release >= 3))
|
||||
|
||||
from bs4.element import (
|
||||
CData,
|
||||
Comment,
|
||||
Declaration,
|
||||
Doctype,
|
||||
ProcessingInstruction,
|
||||
)
|
||||
from bs4.dammit import EntitySubstitution, UnicodeDammit
|
||||
|
||||
from bs4.builder import (
|
||||
HTML,
|
||||
HTMLTreeBuilder,
|
||||
STRICT,
|
||||
)
|
||||
|
||||
|
||||
HTMLPARSER = 'html.parser'
|
||||
|
||||
class BeautifulSoupHTMLParser(HTMLParser):
|
||||
def handle_starttag(self, name, attrs):
|
||||
# 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 = '""'
|
||||
self.soup.handle_starttag(name, None, None, attr_dict)
|
||||
|
||||
def handle_endtag(self, name):
|
||||
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.
|
||||
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()
|
||||
if data.endswith("?") and data.lower().startswith("xml"):
|
||||
# "An XHTML processing instruction using the trailing '?'
|
||||
# will cause the '?' to be included in data." - HTMLParser
|
||||
# docs.
|
||||
#
|
||||
# Strip the question mark so we don't end up with two
|
||||
# question marks.
|
||||
data = data[:-1]
|
||||
self.soup.handle_data(data)
|
||||
self.soup.endData(ProcessingInstruction)
|
||||
|
||||
|
||||
class HTMLParserTreeBuilder(HTMLTreeBuilder):
|
||||
|
||||
is_xml = False
|
||||
features = [HTML, STRICT, HTMLPARSER]
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
if CONSTRUCTOR_TAKES_STRICT:
|
||||
kwargs['strict'] = False
|
||||
self.parser_args = (args, kwargs)
|
||||
|
||||
def prepare_markup(self, markup, user_specified_encoding=None,
|
||||
document_declared_encoding=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)
|
||||
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
|
||||
|
||||
# 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
|
|
@ -0,0 +1,233 @@
|
|||
__all__ = [
|
||||
'LXMLTreeBuilderForXML',
|
||||
'LXMLTreeBuilder',
|
||||
]
|
||||
|
||||
from io import BytesIO
|
||||
from StringIO import StringIO
|
||||
import collections
|
||||
from lxml import etree
|
||||
from bs4.element import Comment, Doctype, NamespacedAttribute
|
||||
from bs4.builder import (
|
||||
FAST,
|
||||
HTML,
|
||||
HTMLTreeBuilder,
|
||||
PERMISSIVE,
|
||||
ParserRejectedMarkup,
|
||||
TreeBuilder,
|
||||
XML)
|
||||
from bs4.dammit import EncodingDetector
|
||||
|
||||
LXML = 'lxml'
|
||||
|
||||
class LXMLTreeBuilderForXML(TreeBuilder):
|
||||
DEFAULT_PARSER_CLASS = etree.XMLParser
|
||||
|
||||
is_xml = True
|
||||
|
||||
# Well, it's permissive by XML parser standards.
|
||||
features = [LXML, XML, FAST, PERMISSIVE]
|
||||
|
||||
CHUNK_SIZE = 512
|
||||
|
||||
# This namespace mapping is specified in the XML Namespace
|
||||
# standard.
|
||||
DEFAULT_NSMAPS = {'http://www.w3.org/XML/1998/namespace' : "xml"}
|
||||
|
||||
def default_parser(self, encoding):
|
||||
# This can either return a parser object or a class, which
|
||||
# will be instantiated with default arguments.
|
||||
if self._default_parser is not None:
|
||||
return self._default_parser
|
||||
return etree.XMLParser(
|
||||
target=self, strip_cdata=False, recover=True, encoding=encoding)
|
||||
|
||||
def parser_for(self, encoding):
|
||||
# Use the default parser.
|
||||
parser = self.default_parser(encoding)
|
||||
|
||||
if isinstance(parser, collections.Callable):
|
||||
# Instantiate the parser with default arguments
|
||||
parser = parser(target=self, strip_cdata=False, encoding=encoding)
|
||||
return parser
|
||||
|
||||
def __init__(self, parser=None, empty_element_tags=None):
|
||||
# TODO: Issue a warning if parser is present but not a
|
||||
# callable, since that means there's no way to create new
|
||||
# parsers for different encodings.
|
||||
self._default_parser = parser
|
||||
if empty_element_tags is not None:
|
||||
self.empty_element_tags = set(empty_element_tags)
|
||||
self.soup = None
|
||||
self.nsmaps = [self.DEFAULT_NSMAPS]
|
||||
|
||||
def _getNsTag(self, tag):
|
||||
# Split the namespace URL out of a fully-qualified lxml tag
|
||||
# name. Copied from lxml's src/lxml/sax.py.
|
||||
if tag[0] == '{':
|
||||
return tuple(tag[1:].split('}', 1))
|
||||
else:
|
||||
return (None, tag)
|
||||
|
||||
def prepare_markup(self, markup, user_specified_encoding=None,
|
||||
document_declared_encoding=None):
|
||||
"""
|
||||
:yield: A series of 4-tuples.
|
||||
(markup, encoding, declared encoding,
|
||||
has undergone character replacement)
|
||||
|
||||
Each 4-tuple represents a strategy for parsing the document.
|
||||
"""
|
||||
if isinstance(markup, unicode):
|
||||
# We were given Unicode. Maybe lxml can parse Unicode on
|
||||
# this system?
|
||||
yield markup, None, document_declared_encoding, False
|
||||
|
||||
if isinstance(markup, unicode):
|
||||
# No, apparently not. Convert the Unicode to UTF-8 and
|
||||
# tell lxml to parse it as UTF-8.
|
||||
yield (markup.encode("utf8"), "utf8",
|
||||
document_declared_encoding, False)
|
||||
|
||||
# Instead of using UnicodeDammit to convert the bytestring to
|
||||
# Unicode using different encodings, use EncodingDetector to
|
||||
# iterate over the encodings, and tell lxml to try to parse
|
||||
# the document as each one in turn.
|
||||
is_html = not self.is_xml
|
||||
try_encodings = [user_specified_encoding, document_declared_encoding]
|
||||
detector = EncodingDetector(markup, try_encodings, is_html)
|
||||
for encoding in detector.encodings:
|
||||
yield (detector.markup, encoding, document_declared_encoding, False)
|
||||
|
||||
def feed(self, markup):
|
||||
if isinstance(markup, bytes):
|
||||
markup = BytesIO(markup)
|
||||
elif isinstance(markup, unicode):
|
||||
markup = StringIO(markup)
|
||||
|
||||
# Call feed() at least once, even if the markup is empty,
|
||||
# or the parser won't be initialized.
|
||||
data = markup.read(self.CHUNK_SIZE)
|
||||
try:
|
||||
self.parser = self.parser_for(self.soup.original_encoding)
|
||||
self.parser.feed(data)
|
||||
while len(data) != 0:
|
||||
# Now call feed() on the rest of the data, chunk by chunk.
|
||||
data = markup.read(self.CHUNK_SIZE)
|
||||
if len(data) != 0:
|
||||
self.parser.feed(data)
|
||||
self.parser.close()
|
||||
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
|
||||
raise ParserRejectedMarkup(str(e))
|
||||
|
||||
def close(self):
|
||||
self.nsmaps = [self.DEFAULT_NSMAPS]
|
||||
|
||||
def start(self, name, attrs, nsmap={}):
|
||||
# Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
|
||||
attrs = dict(attrs)
|
||||
nsprefix = None
|
||||
# Invert each namespace map as it comes in.
|
||||
if len(self.nsmaps) > 1:
|
||||
# There are no new namespaces for this tag, but
|
||||
# non-default namespaces are in play, so we need a
|
||||
# separate tag stack to know when they end.
|
||||
self.nsmaps.append(None)
|
||||
elif len(nsmap) > 0:
|
||||
# A new namespace mapping has come into play.
|
||||
inverted_nsmap = dict((value, key) for key, value in nsmap.items())
|
||||
self.nsmaps.append(inverted_nsmap)
|
||||
# Also treat the namespace mapping as a set of attributes on the
|
||||
# tag, so we can recreate it later.
|
||||
attrs = attrs.copy()
|
||||
for prefix, namespace in nsmap.items():
|
||||
attribute = NamespacedAttribute(
|
||||
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
|
||||
attrs[attribute] = namespace
|
||||
|
||||
# Namespaces are in play. Find any attributes that came in
|
||||
# from lxml with namespaces attached to their names, and
|
||||
# turn then into NamespacedAttribute objects.
|
||||
new_attrs = {}
|
||||
for attr, value in attrs.items():
|
||||
namespace, attr = self._getNsTag(attr)
|
||||
if namespace is None:
|
||||
new_attrs[attr] = value
|
||||
else:
|
||||
nsprefix = self._prefix_for_namespace(namespace)
|
||||
attr = NamespacedAttribute(nsprefix, attr, namespace)
|
||||
new_attrs[attr] = value
|
||||
attrs = new_attrs
|
||||
|
||||
namespace, name = self._getNsTag(name)
|
||||
nsprefix = self._prefix_for_namespace(namespace)
|
||||
self.soup.handle_starttag(name, namespace, nsprefix, attrs)
|
||||
|
||||
def _prefix_for_namespace(self, namespace):
|
||||
"""Find the currently active prefix for the given namespace."""
|
||||
if namespace is None:
|
||||
return None
|
||||
for inverted_nsmap in reversed(self.nsmaps):
|
||||
if inverted_nsmap is not None and namespace in inverted_nsmap:
|
||||
return inverted_nsmap[namespace]
|
||||
return None
|
||||
|
||||
def end(self, name):
|
||||
self.soup.endData()
|
||||
completed_tag = self.soup.tagStack[-1]
|
||||
namespace, name = self._getNsTag(name)
|
||||
nsprefix = None
|
||||
if namespace is not None:
|
||||
for inverted_nsmap in reversed(self.nsmaps):
|
||||
if inverted_nsmap is not None and namespace in inverted_nsmap:
|
||||
nsprefix = inverted_nsmap[namespace]
|
||||
break
|
||||
self.soup.handle_endtag(name, nsprefix)
|
||||
if len(self.nsmaps) > 1:
|
||||
# This tag, or one of its parents, introduced a namespace
|
||||
# mapping, so pop it off the stack.
|
||||
self.nsmaps.pop()
|
||||
|
||||
def pi(self, target, data):
|
||||
pass
|
||||
|
||||
def data(self, content):
|
||||
self.soup.handle_data(content)
|
||||
|
||||
def doctype(self, name, pubid, system):
|
||||
self.soup.endData()
|
||||
doctype = Doctype.for_name_and_ids(name, pubid, system)
|
||||
self.soup.object_was_parsed(doctype)
|
||||
|
||||
def comment(self, content):
|
||||
"Handle comments as Comment objects."
|
||||
self.soup.endData()
|
||||
self.soup.handle_data(content)
|
||||
self.soup.endData(Comment)
|
||||
|
||||
def test_fragment_to_document(self, fragment):
|
||||
"""See `TreeBuilder`."""
|
||||
return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
|
||||
|
||||
|
||||
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
|
||||
|
||||
features = [LXML, HTML, FAST, PERMISSIVE]
|
||||
is_xml = False
|
||||
|
||||
def default_parser(self, encoding):
|
||||
return etree.HTMLParser
|
||||
|
||||
def feed(self, markup):
|
||||
encoding = self.soup.original_encoding
|
||||
try:
|
||||
self.parser = self.parser_for(encoding)
|
||||
self.parser.feed(markup)
|
||||
self.parser.close()
|
||||
except (UnicodeDecodeError, LookupError, etree.ParserError), e:
|
||||
raise ParserRejectedMarkup(str(e))
|
||||
|
||||
|
||||
def test_fragment_to_document(self, fragment):
|
||||
"""See `TreeBuilder`."""
|
||||
return u'<html><body>%s</body></html>' % fragment
|
|
@ -0,0 +1,829 @@
|
|||
# -*- 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 XML, but it does not rewrite the
|
||||
XML or HTML to reflect a new encoding; that's the tree builder's job.
|
||||
"""
|
||||
|
||||
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
|
||||
# ", 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 " 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 "Bob's bar"
|
||||
"""
|
||||
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
|
||||
# """ whether this is HTML or XML. If we
|
||||
# quoted the single quotes, we'd have to decide
|
||||
# between ' and &squot;.
|
||||
replace_with = """
|
||||
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 <, the greater-than sign will become >,
|
||||
and any ampersands will become &. 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 <, the greater-than sign will become >, and any
|
||||
ampersands that are not part of an entity defition will
|
||||
become &.
|
||||
|
||||
: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 "é" 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):
|
||||
self.override_encodings = override_encodings or []
|
||||
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 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 (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')
|
||||
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):
|
||||
self.smart_quotes_to = smart_quotes_to
|
||||
self.tried_encodings = []
|
||||
self.contains_replacement_characters = False
|
||||
self.is_html = is_html
|
||||
|
||||
self.detector = EncodingDetector(markup, override_encodings, is_html)
|
||||
|
||||
# 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:
|
||||
logging.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)
|
||||
|
|
@ -0,0 +1,204 @@
|
|||
"""Diagnostic functions, mainly for use when doing tech support."""
|
||||
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"])
|
||||
from lxml import etree
|
||||
print "Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))
|
||||
|
||||
if 'html5lib' in basic_parsers:
|
||||
import html5lib
|
||||
print "Found html5lib version %s" % html5lib.__version__
|
||||
|
||||
if hasattr(data, 'read'):
|
||||
data = data.read()
|
||||
elif os.path.exists(data):
|
||||
print '"%s" looks like a filename. Reading data from the file.' % data
|
||||
data = open(data).read()
|
||||
elif data.startswith("http:") or data.startswith("https:"):
|
||||
print '"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data
|
||||
print "You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup."
|
||||
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())
|
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,592 @@
|
|||
"""Helper classes for tests."""
|
||||
|
||||
import copy
|
||||
import functools
|
||||
import unittest
|
||||
from unittest import TestCase
|
||||
from bs4 import BeautifulSoup
|
||||
from bs4.element import (
|
||||
CharsetMetaAttributeValue,
|
||||
Comment,
|
||||
ContentMetaAttributeValue,
|
||||
Doctype,
|
||||
SoupStrainer,
|
||||
)
|
||||
|
||||
from bs4.builder import HTMLParserTreeBuilder
|
||||
default_builder = HTMLParserTreeBuilder
|
||||
|
||||
|
||||
class SoupTest(unittest.TestCase):
|
||||
|
||||
@property
|
||||
def default_builder(self):
|
||||
return default_builder()
|
||||
|
||||
def soup(self, markup, **kwargs):
|
||||
"""Build a Beautiful Soup object from markup."""
|
||||
builder = kwargs.pop('builder', self.default_builder)
|
||||
return BeautifulSoup(markup, builder=builder, **kwargs)
|
||||
|
||||
def document_for(self, markup):
|
||||
"""Turn an HTML fragment into a document.
|
||||
|
||||
The details depend on the builder.
|
||||
"""
|
||||
return self.default_builder.test_fragment_to_document(markup)
|
||||
|
||||
def assertSoupEquals(self, to_parse, compare_parsed_to=None):
|
||||
builder = self.default_builder
|
||||
obj = BeautifulSoup(to_parse, builder=builder)
|
||||
if compare_parsed_to is None:
|
||||
compare_parsed_to = to_parse
|
||||
|
||||
self.assertEqual(obj.decode(), self.document_for(compare_parsed_to))
|
||||
|
||||
|
||||
class HTMLTreeBuilderSmokeTest(object):
|
||||
|
||||
"""A basic test of a treebuilder's competence.
|
||||
|
||||
Any HTML treebuilder, present or future, should be able to pass
|
||||
these tests. With invalid markup, there's room for interpretation,
|
||||
and different parsers can handle it differently. But with the
|
||||
markup in these tests, there's not much room for interpretation.
|
||||
"""
|
||||
|
||||
def assertDoctypeHandled(self, doctype_fragment):
|
||||
"""Assert that a given doctype string is handled correctly."""
|
||||
doctype_str, soup = self._document_with_doctype(doctype_fragment)
|
||||
|
||||
# Make sure a Doctype object was created.
|
||||
doctype = soup.contents[0]
|
||||
self.assertEqual(doctype.__class__, Doctype)
|
||||
self.assertEqual(doctype, doctype_fragment)
|
||||
self.assertEqual(str(soup)[:len(doctype_str)], doctype_str)
|
||||
|
||||
# Make sure that the doctype was correctly associated with the
|
||||
# parse tree and that the rest of the document parsed.
|
||||
self.assertEqual(soup.p.contents[0], 'foo')
|
||||
|
||||
def _document_with_doctype(self, doctype_fragment):
|
||||
"""Generate and parse a document with the given doctype."""
|
||||
doctype = '<!DOCTYPE %s>' % doctype_fragment
|
||||
markup = doctype + '\n<p>foo</p>'
|
||||
soup = self.soup(markup)
|
||||
return doctype, soup
|
||||
|
||||
def test_normal_doctypes(self):
|
||||
"""Make sure normal, everyday HTML doctypes are handled correctly."""
|
||||
self.assertDoctypeHandled("html")
|
||||
self.assertDoctypeHandled(
|
||||
'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"')
|
||||
|
||||
def test_empty_doctype(self):
|
||||
soup = self.soup("<!DOCTYPE>")
|
||||
doctype = soup.contents[0]
|
||||
self.assertEqual("", doctype.strip())
|
||||
|
||||
def test_public_doctype_with_url(self):
|
||||
doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"'
|
||||
self.assertDoctypeHandled(doctype)
|
||||
|
||||
def test_system_doctype(self):
|
||||
self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"')
|
||||
|
||||
def test_namespaced_system_doctype(self):
|
||||
# We can handle a namespaced doctype with a system ID.
|
||||
self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"')
|
||||
|
||||
def test_namespaced_public_doctype(self):
|
||||
# Test a namespaced doctype with a public id.
|
||||
self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"')
|
||||
|
||||
def test_real_xhtml_document(self):
|
||||
"""A real XHTML document should come out more or less the same as it went in."""
|
||||
markup = b"""<?xml version="1.0" encoding="utf-8"?>
|
||||
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
|
||||
<html xmlns="http://www.w3.org/1999/xhtml">
|
||||
<head><title>Hello.</title></head>
|
||||
<body>Goodbye.</body>
|
||||
</html>"""
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(
|
||||
soup.encode("utf-8").replace(b"\n", b""),
|
||||
markup.replace(b"\n", b""))
|
||||
|
||||
def test_deepcopy(self):
|
||||
"""Make sure you can copy the tree builder.
|
||||
|
||||
This is important because the builder is part of a
|
||||
BeautifulSoup object, and we want to be able to copy that.
|
||||
"""
|
||||
copy.deepcopy(self.default_builder)
|
||||
|
||||
def test_p_tag_is_never_empty_element(self):
|
||||
"""A <p> tag is never designated as an empty-element tag.
|
||||
|
||||
Even if the markup shows it as an empty-element tag, it
|
||||
shouldn't be presented that way.
|
||||
"""
|
||||
soup = self.soup("<p/>")
|
||||
self.assertFalse(soup.p.is_empty_element)
|
||||
self.assertEqual(str(soup.p), "<p></p>")
|
||||
|
||||
def test_unclosed_tags_get_closed(self):
|
||||
"""A tag that's not closed by the end of the document should be closed.
|
||||
|
||||
This applies to all tags except empty-element tags.
|
||||
"""
|
||||
self.assertSoupEquals("<p>", "<p></p>")
|
||||
self.assertSoupEquals("<b>", "<b></b>")
|
||||
|
||||
self.assertSoupEquals("<br>", "<br/>")
|
||||
|
||||
def test_br_is_always_empty_element_tag(self):
|
||||
"""A <br> tag is designated as an empty-element tag.
|
||||
|
||||
Some parsers treat <br></br> as one <br/> tag, some parsers as
|
||||
two tags, but it should always be an empty-element tag.
|
||||
"""
|
||||
soup = self.soup("<br></br>")
|
||||
self.assertTrue(soup.br.is_empty_element)
|
||||
self.assertEqual(str(soup.br), "<br/>")
|
||||
|
||||
def test_nested_formatting_elements(self):
|
||||
self.assertSoupEquals("<em><em></em></em>")
|
||||
|
||||
def test_comment(self):
|
||||
# Comments are represented as Comment objects.
|
||||
markup = "<p>foo<!--foobar-->baz</p>"
|
||||
self.assertSoupEquals(markup)
|
||||
|
||||
soup = self.soup(markup)
|
||||
comment = soup.find(text="foobar")
|
||||
self.assertEqual(comment.__class__, Comment)
|
||||
|
||||
# The comment is properly integrated into the tree.
|
||||
foo = soup.find(text="foo")
|
||||
self.assertEqual(comment, foo.next_element)
|
||||
baz = soup.find(text="baz")
|
||||
self.assertEqual(comment, baz.previous_element)
|
||||
|
||||
def test_preserved_whitespace_in_pre_and_textarea(self):
|
||||
"""Whitespace must be preserved in <pre> and <textarea> tags."""
|
||||
self.assertSoupEquals("<pre> </pre>")
|
||||
self.assertSoupEquals("<textarea> woo </textarea>")
|
||||
|
||||
def test_nested_inline_elements(self):
|
||||
"""Inline elements can be nested indefinitely."""
|
||||
b_tag = "<b>Inside a B tag</b>"
|
||||
self.assertSoupEquals(b_tag)
|
||||
|
||||
nested_b_tag = "<p>A <i>nested <b>tag</b></i></p>"
|
||||
self.assertSoupEquals(nested_b_tag)
|
||||
|
||||
double_nested_b_tag = "<p>A <a>doubly <i>nested <b>tag</b></i></a></p>"
|
||||
self.assertSoupEquals(nested_b_tag)
|
||||
|
||||
def test_nested_block_level_elements(self):
|
||||
"""Block elements can be nested."""
|
||||
soup = self.soup('<blockquote><p><b>Foo</b></p></blockquote>')
|
||||
blockquote = soup.blockquote
|
||||
self.assertEqual(blockquote.p.b.string, 'Foo')
|
||||
self.assertEqual(blockquote.b.string, 'Foo')
|
||||
|
||||
def test_correctly_nested_tables(self):
|
||||
"""One table can go inside another one."""
|
||||
markup = ('<table id="1">'
|
||||
'<tr>'
|
||||
"<td>Here's another table:"
|
||||
'<table id="2">'
|
||||
'<tr><td>foo</td></tr>'
|
||||
'</table></td>')
|
||||
|
||||
self.assertSoupEquals(
|
||||
markup,
|
||||
'<table id="1"><tr><td>Here\'s another table:'
|
||||
'<table id="2"><tr><td>foo</td></tr></table>'
|
||||
'</td></tr></table>')
|
||||
|
||||
self.assertSoupEquals(
|
||||
"<table><thead><tr><td>Foo</td></tr></thead>"
|
||||
"<tbody><tr><td>Bar</td></tr></tbody>"
|
||||
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
|
||||
|
||||
def test_deeply_nested_multivalued_attribute(self):
|
||||
# html5lib can set the attributes of the same tag many times
|
||||
# as it rearranges the tree. This has caused problems with
|
||||
# multivalued attributes.
|
||||
markup = '<table><div><div class="css"></div></div></table>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(["css"], soup.div.div['class'])
|
||||
|
||||
def test_angle_brackets_in_attribute_values_are_escaped(self):
|
||||
self.assertSoupEquals('<a b="<a>"></a>', '<a b="<a>"></a>')
|
||||
|
||||
def test_entities_in_attributes_converted_to_unicode(self):
|
||||
expect = u'<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
|
||||
self.assertSoupEquals('<p id="piñata"></p>', expect)
|
||||
self.assertSoupEquals('<p id="piñata"></p>', expect)
|
||||
self.assertSoupEquals('<p id="piñata"></p>', expect)
|
||||
self.assertSoupEquals('<p id="piñata"></p>', expect)
|
||||
|
||||
def test_entities_in_text_converted_to_unicode(self):
|
||||
expect = u'<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
|
||||
self.assertSoupEquals("<p>piñata</p>", expect)
|
||||
self.assertSoupEquals("<p>piñata</p>", expect)
|
||||
self.assertSoupEquals("<p>piñata</p>", expect)
|
||||
self.assertSoupEquals("<p>piñata</p>", expect)
|
||||
|
||||
def test_quot_entity_converted_to_quotation_mark(self):
|
||||
self.assertSoupEquals("<p>I said "good day!"</p>",
|
||||
'<p>I said "good day!"</p>')
|
||||
|
||||
def test_out_of_range_entity(self):
|
||||
expect = u"\N{REPLACEMENT CHARACTER}"
|
||||
self.assertSoupEquals("�", expect)
|
||||
self.assertSoupEquals("�", expect)
|
||||
self.assertSoupEquals("�", expect)
|
||||
|
||||
def test_multipart_strings(self):
|
||||
"Mostly to prevent a recurrence of a bug in the html5lib treebuilder."
|
||||
soup = self.soup("<html><h2>\nfoo</h2><p></p></html>")
|
||||
self.assertEqual("p", soup.h2.string.next_element.name)
|
||||
self.assertEqual("p", soup.p.name)
|
||||
|
||||
def test_basic_namespaces(self):
|
||||
"""Parsers don't need to *understand* namespaces, but at the
|
||||
very least they should not choke on namespaces or lose
|
||||
data."""
|
||||
|
||||
markup = b'<html xmlns="http://www.w3.org/1999/xhtml" xmlns:mathml="http://www.w3.org/1998/Math/MathML" xmlns:svg="http://www.w3.org/2000/svg"><head></head><body><mathml:msqrt>4</mathml:msqrt><b svg:fill="red"></b></body></html>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(markup, soup.encode())
|
||||
html = soup.html
|
||||
self.assertEqual('http://www.w3.org/1999/xhtml', soup.html['xmlns'])
|
||||
self.assertEqual(
|
||||
'http://www.w3.org/1998/Math/MathML', soup.html['xmlns:mathml'])
|
||||
self.assertEqual(
|
||||
'http://www.w3.org/2000/svg', soup.html['xmlns:svg'])
|
||||
|
||||
def test_multivalued_attribute_value_becomes_list(self):
|
||||
markup = b'<a class="foo bar">'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(['foo', 'bar'], soup.a['class'])
|
||||
|
||||
#
|
||||
# Generally speaking, tests below this point are more tests of
|
||||
# Beautiful Soup than tests of the tree builders. But parsers are
|
||||
# weird, so we run these tests separately for every tree builder
|
||||
# to detect any differences between them.
|
||||
#
|
||||
|
||||
def test_can_parse_unicode_document(self):
|
||||
# A seemingly innocuous document... but it's in Unicode! And
|
||||
# it contains characters that can't be represented in the
|
||||
# encoding found in the declaration! The horror!
|
||||
markup = u'<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(u'Sacr\xe9 bleu!', soup.body.string)
|
||||
|
||||
def test_soupstrainer(self):
|
||||
"""Parsers should be able to work with SoupStrainers."""
|
||||
strainer = SoupStrainer("b")
|
||||
soup = self.soup("A <b>bold</b> <meta/> <i>statement</i>",
|
||||
parse_only=strainer)
|
||||
self.assertEqual(soup.decode(), "<b>bold</b>")
|
||||
|
||||
def test_single_quote_attribute_values_become_double_quotes(self):
|
||||
self.assertSoupEquals("<foo attr='bar'></foo>",
|
||||
'<foo attr="bar"></foo>')
|
||||
|
||||
def test_attribute_values_with_nested_quotes_are_left_alone(self):
|
||||
text = """<foo attr='bar "brawls" happen'>a</foo>"""
|
||||
self.assertSoupEquals(text)
|
||||
|
||||
def test_attribute_values_with_double_nested_quotes_get_quoted(self):
|
||||
text = """<foo attr='bar "brawls" happen'>a</foo>"""
|
||||
soup = self.soup(text)
|
||||
soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
|
||||
self.assertSoupEquals(
|
||||
soup.foo.decode(),
|
||||
"""<foo attr="Brawls happen at "Bob\'s Bar"">a</foo>""")
|
||||
|
||||
def test_ampersand_in_attribute_value_gets_escaped(self):
|
||||
self.assertSoupEquals('<this is="really messed up & stuff"></this>',
|
||||
'<this is="really messed up & stuff"></this>')
|
||||
|
||||
self.assertSoupEquals(
|
||||
'<a href="http://example.org?a=1&b=2;3">foo</a>',
|
||||
'<a href="http://example.org?a=1&b=2;3">foo</a>')
|
||||
|
||||
def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
|
||||
self.assertSoupEquals('<a href="http://example.org?a=1&b=2;3"></a>')
|
||||
|
||||
def test_entities_in_strings_converted_during_parsing(self):
|
||||
# Both XML and HTML entities are converted to Unicode characters
|
||||
# during parsing.
|
||||
text = "<p><<sacré bleu!>></p>"
|
||||
expected = u"<p><<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></p>"
|
||||
self.assertSoupEquals(text, expected)
|
||||
|
||||
def test_smart_quotes_converted_on_the_way_in(self):
|
||||
# Microsoft smart quotes are converted to Unicode characters during
|
||||
# parsing.
|
||||
quote = b"<p>\x91Foo\x92</p>"
|
||||
soup = self.soup(quote)
|
||||
self.assertEqual(
|
||||
soup.p.string,
|
||||
u"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
|
||||
|
||||
def test_non_breaking_spaces_converted_on_the_way_in(self):
|
||||
soup = self.soup("<a> </a>")
|
||||
self.assertEqual(soup.a.string, u"\N{NO-BREAK SPACE}" * 2)
|
||||
|
||||
def test_entities_converted_on_the_way_out(self):
|
||||
text = "<p><<sacré bleu!>></p>"
|
||||
expected = u"<p><<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></p>".encode("utf-8")
|
||||
soup = self.soup(text)
|
||||
self.assertEqual(soup.p.encode("utf-8"), expected)
|
||||
|
||||
def test_real_iso_latin_document(self):
|
||||
# Smoke test of interrelated functionality, using an
|
||||
# easy-to-understand document.
|
||||
|
||||
# Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
|
||||
unicode_html = u'<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
|
||||
|
||||
# That's because we're going to encode it into ISO-Latin-1, and use
|
||||
# that to test.
|
||||
iso_latin_html = unicode_html.encode("iso-8859-1")
|
||||
|
||||
# Parse the ISO-Latin-1 HTML.
|
||||
soup = self.soup(iso_latin_html)
|
||||
# Encode it to UTF-8.
|
||||
result = soup.encode("utf-8")
|
||||
|
||||
# What do we expect the result to look like? Well, it would
|
||||
# look like unicode_html, except that the META tag would say
|
||||
# UTF-8 instead of ISO-Latin-1.
|
||||
expected = unicode_html.replace("ISO-Latin-1", "utf-8")
|
||||
|
||||
# And, of course, it would be in UTF-8, not Unicode.
|
||||
expected = expected.encode("utf-8")
|
||||
|
||||
# Ta-da!
|
||||
self.assertEqual(result, expected)
|
||||
|
||||
def test_real_shift_jis_document(self):
|
||||
# Smoke test to make sure the parser can handle a document in
|
||||
# Shift-JIS encoding, without choking.
|
||||
shift_jis_html = (
|
||||
b'<html><head></head><body><pre>'
|
||||
b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
|
||||
b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
|
||||
b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
|
||||
b'</pre></body></html>')
|
||||
unicode_html = shift_jis_html.decode("shift-jis")
|
||||
soup = self.soup(unicode_html)
|
||||
|
||||
# Make sure the parse tree is correctly encoded to various
|
||||
# encodings.
|
||||
self.assertEqual(soup.encode("utf-8"), unicode_html.encode("utf-8"))
|
||||
self.assertEqual(soup.encode("euc_jp"), unicode_html.encode("euc_jp"))
|
||||
|
||||
def test_real_hebrew_document(self):
|
||||
# A real-world test to make sure we can convert ISO-8859-9 (a
|
||||
# Hebrew encoding) to UTF-8.
|
||||
hebrew_document = b'<html><head><title>Hebrew (ISO 8859-8) in Visual Directionality</title></head><body><h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\xed\xe5\xec\xf9</body></html>'
|
||||
soup = self.soup(
|
||||
hebrew_document, from_encoding="iso8859-8")
|
||||
self.assertEqual(soup.original_encoding, 'iso8859-8')
|
||||
self.assertEqual(
|
||||
soup.encode('utf-8'),
|
||||
hebrew_document.decode("iso8859-8").encode("utf-8"))
|
||||
|
||||
def test_meta_tag_reflects_current_encoding(self):
|
||||
# Here's the <meta> tag saying that a document is
|
||||
# encoded in Shift-JIS.
|
||||
meta_tag = ('<meta content="text/html; charset=x-sjis" '
|
||||
'http-equiv="Content-type"/>')
|
||||
|
||||
# Here's a document incorporating that meta tag.
|
||||
shift_jis_html = (
|
||||
'<html><head>\n%s\n'
|
||||
'<meta http-equiv="Content-language" content="ja"/>'
|
||||
'</head><body>Shift-JIS markup goes here.') % meta_tag
|
||||
soup = self.soup(shift_jis_html)
|
||||
|
||||
# Parse the document, and the charset is seemingly unaffected.
|
||||
parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
|
||||
content = parsed_meta['content']
|
||||
self.assertEqual('text/html; charset=x-sjis', content)
|
||||
|
||||
# But that value is actually a ContentMetaAttributeValue object.
|
||||
self.assertTrue(isinstance(content, ContentMetaAttributeValue))
|
||||
|
||||
# And it will take on a value that reflects its current
|
||||
# encoding.
|
||||
self.assertEqual('text/html; charset=utf8', content.encode("utf8"))
|
||||
|
||||
# For the rest of the story, see TestSubstitutions in
|
||||
# test_tree.py.
|
||||
|
||||
def test_html5_style_meta_tag_reflects_current_encoding(self):
|
||||
# Here's the <meta> tag saying that a document is
|
||||
# encoded in Shift-JIS.
|
||||
meta_tag = ('<meta id="encoding" charset="x-sjis" />')
|
||||
|
||||
# Here's a document incorporating that meta tag.
|
||||
shift_jis_html = (
|
||||
'<html><head>\n%s\n'
|
||||
'<meta http-equiv="Content-language" content="ja"/>'
|
||||
'</head><body>Shift-JIS markup goes here.') % meta_tag
|
||||
soup = self.soup(shift_jis_html)
|
||||
|
||||
# Parse the document, and the charset is seemingly unaffected.
|
||||
parsed_meta = soup.find('meta', id="encoding")
|
||||
charset = parsed_meta['charset']
|
||||
self.assertEqual('x-sjis', charset)
|
||||
|
||||
# But that value is actually a CharsetMetaAttributeValue object.
|
||||
self.assertTrue(isinstance(charset, CharsetMetaAttributeValue))
|
||||
|
||||
# And it will take on a value that reflects its current
|
||||
# encoding.
|
||||
self.assertEqual('utf8', charset.encode("utf8"))
|
||||
|
||||
def test_tag_with_no_attributes_can_have_attributes_added(self):
|
||||
data = self.soup("<a>text</a>")
|
||||
data.a['foo'] = 'bar'
|
||||
self.assertEqual('<a foo="bar">text</a>', data.a.decode())
|
||||
|
||||
class XMLTreeBuilderSmokeTest(object):
|
||||
|
||||
def test_docstring_generated(self):
|
||||
soup = self.soup("<root/>")
|
||||
self.assertEqual(
|
||||
soup.encode(), b'<?xml version="1.0" encoding="utf-8"?>\n<root/>')
|
||||
|
||||
def test_real_xhtml_document(self):
|
||||
"""A real XHTML document should come out *exactly* the same as it went in."""
|
||||
markup = b"""<?xml version="1.0" encoding="utf-8"?>
|
||||
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
|
||||
<html xmlns="http://www.w3.org/1999/xhtml">
|
||||
<head><title>Hello.</title></head>
|
||||
<body>Goodbye.</body>
|
||||
</html>"""
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(
|
||||
soup.encode("utf-8"), markup)
|
||||
|
||||
def test_formatter_processes_script_tag_for_xml_documents(self):
|
||||
doc = """
|
||||
<script type="text/javascript">
|
||||
</script>
|
||||
"""
|
||||
soup = BeautifulSoup(doc, "xml")
|
||||
# lxml would have stripped this while parsing, but we can add
|
||||
# it later.
|
||||
soup.script.string = 'console.log("< < hey > > ");'
|
||||
encoded = soup.encode()
|
||||
self.assertTrue(b"< < hey > >" in encoded)
|
||||
|
||||
def test_can_parse_unicode_document(self):
|
||||
markup = u'<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(u'Sacr\xe9 bleu!', soup.root.string)
|
||||
|
||||
def test_popping_namespaced_tag(self):
|
||||
markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(
|
||||
unicode(soup.rss), markup)
|
||||
|
||||
def test_docstring_includes_correct_encoding(self):
|
||||
soup = self.soup("<root/>")
|
||||
self.assertEqual(
|
||||
soup.encode("latin1"),
|
||||
b'<?xml version="1.0" encoding="latin1"?>\n<root/>')
|
||||
|
||||
def test_large_xml_document(self):
|
||||
"""A large XML document should come out the same as it went in."""
|
||||
markup = (b'<?xml version="1.0" encoding="utf-8"?>\n<root>'
|
||||
+ b'0' * (2**12)
|
||||
+ b'</root>')
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(soup.encode("utf-8"), markup)
|
||||
|
||||
|
||||
def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
|
||||
self.assertSoupEquals("<p>", "<p/>")
|
||||
self.assertSoupEquals("<p>foo</p>")
|
||||
|
||||
def test_namespaces_are_preserved(self):
|
||||
markup = '<root xmlns:a="http://example.com/" xmlns:b="http://example.net/"><a:foo>This tag is in the a namespace</a:foo><b:foo>This tag is in the b namespace</b:foo></root>'
|
||||
soup = self.soup(markup)
|
||||
root = soup.root
|
||||
self.assertEqual("http://example.com/", root['xmlns:a'])
|
||||
self.assertEqual("http://example.net/", root['xmlns:b'])
|
||||
|
||||
def test_closing_namespaced_tag(self):
|
||||
markup = '<p xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:date>20010504</dc:date></p>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(unicode(soup.p), markup)
|
||||
|
||||
def test_namespaced_attributes(self):
|
||||
markup = '<foo xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><bar xsi:schemaLocation="http://www.example.com"/></foo>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(unicode(soup.foo), markup)
|
||||
|
||||
def test_namespaced_attributes_xml_namespace(self):
|
||||
markup = '<foo xml:lang="fr">bar</foo>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(unicode(soup.foo), markup)
|
||||
|
||||
class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
|
||||
"""Smoke test for a tree builder that supports HTML5."""
|
||||
|
||||
def test_real_xhtml_document(self):
|
||||
# Since XHTML is not HTML5, HTML5 parsers are not tested to handle
|
||||
# XHTML documents in any particular way.
|
||||
pass
|
||||
|
||||
def test_html_tags_have_namespace(self):
|
||||
markup = "<a>"
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual("http://www.w3.org/1999/xhtml", soup.a.namespace)
|
||||
|
||||
def test_svg_tags_have_namespace(self):
|
||||
markup = '<svg><circle/></svg>'
|
||||
soup = self.soup(markup)
|
||||
namespace = "http://www.w3.org/2000/svg"
|
||||
self.assertEqual(namespace, soup.svg.namespace)
|
||||
self.assertEqual(namespace, soup.circle.namespace)
|
||||
|
||||
|
||||
def test_mathml_tags_have_namespace(self):
|
||||
markup = '<math><msqrt>5</msqrt></math>'
|
||||
soup = self.soup(markup)
|
||||
namespace = 'http://www.w3.org/1998/Math/MathML'
|
||||
self.assertEqual(namespace, soup.math.namespace)
|
||||
self.assertEqual(namespace, soup.msqrt.namespace)
|
||||
|
||||
def test_xml_declaration_becomes_comment(self):
|
||||
markup = '<?xml version="1.0" encoding="utf-8"?><html></html>'
|
||||
soup = self.soup(markup)
|
||||
self.assertTrue(isinstance(soup.contents[0], Comment))
|
||||
self.assertEqual(soup.contents[0], '?xml version="1.0" encoding="utf-8"?')
|
||||
self.assertEqual("html", soup.contents[0].next_element.name)
|
||||
|
||||
def skipIf(condition, reason):
|
||||
def nothing(test, *args, **kwargs):
|
||||
return None
|
||||
|
||||
def decorator(test_item):
|
||||
if condition:
|
||||
return nothing
|
||||
else:
|
||||
return test_item
|
||||
|
||||
return decorator
|
|
@ -0,0 +1 @@
|
|||
"The beautifulsoup tests."
|
|
@ -0,0 +1,141 @@
|
|||
"""Tests of the builder registry."""
|
||||
|
||||
import unittest
|
||||
|
||||
from bs4 import BeautifulSoup
|
||||
from bs4.builder import (
|
||||
builder_registry as registry,
|
||||
HTMLParserTreeBuilder,
|
||||
TreeBuilderRegistry,
|
||||
)
|
||||
|
||||
try:
|
||||
from bs4.builder import HTML5TreeBuilder
|
||||
HTML5LIB_PRESENT = True
|
||||
except ImportError:
|
||||
HTML5LIB_PRESENT = False
|
||||
|
||||
try:
|
||||
from bs4.builder import (
|
||||
LXMLTreeBuilderForXML,
|
||||
LXMLTreeBuilder,
|
||||
)
|
||||
LXML_PRESENT = True
|
||||
except ImportError:
|
||||
LXML_PRESENT = False
|
||||
|
||||
|
||||
class BuiltInRegistryTest(unittest.TestCase):
|
||||
"""Test the built-in registry with the default builders registered."""
|
||||
|
||||
def test_combination(self):
|
||||
if LXML_PRESENT:
|
||||
self.assertEqual(registry.lookup('fast', 'html'),
|
||||
LXMLTreeBuilder)
|
||||
|
||||
if LXML_PRESENT:
|
||||
self.assertEqual(registry.lookup('permissive', 'xml'),
|
||||
LXMLTreeBuilderForXML)
|
||||
self.assertEqual(registry.lookup('strict', 'html'),
|
||||
HTMLParserTreeBuilder)
|
||||
if HTML5LIB_PRESENT:
|
||||
self.assertEqual(registry.lookup('html5lib', 'html'),
|
||||
HTML5TreeBuilder)
|
||||
|
||||
def test_lookup_by_markup_type(self):
|
||||
if LXML_PRESENT:
|
||||
self.assertEqual(registry.lookup('html'), LXMLTreeBuilder)
|
||||
self.assertEqual(registry.lookup('xml'), LXMLTreeBuilderForXML)
|
||||
else:
|
||||
self.assertEqual(registry.lookup('xml'), None)
|
||||
if HTML5LIB_PRESENT:
|
||||
self.assertEqual(registry.lookup('html'), HTML5TreeBuilder)
|
||||
else:
|
||||
self.assertEqual(registry.lookup('html'), HTMLParserTreeBuilder)
|
||||
|
||||
def test_named_library(self):
|
||||
if LXML_PRESENT:
|
||||
self.assertEqual(registry.lookup('lxml', 'xml'),
|
||||
LXMLTreeBuilderForXML)
|
||||
self.assertEqual(registry.lookup('lxml', 'html'),
|
||||
LXMLTreeBuilder)
|
||||
if HTML5LIB_PRESENT:
|
||||
self.assertEqual(registry.lookup('html5lib'),
|
||||
HTML5TreeBuilder)
|
||||
|
||||
self.assertEqual(registry.lookup('html.parser'),
|
||||
HTMLParserTreeBuilder)
|
||||
|
||||
def test_beautifulsoup_constructor_does_lookup(self):
|
||||
# You can pass in a string.
|
||||
BeautifulSoup("", features="html")
|
||||
# Or a list of strings.
|
||||
BeautifulSoup("", features=["html", "fast"])
|
||||
|
||||
# You'll get an exception if BS can't find an appropriate
|
||||
# builder.
|
||||
self.assertRaises(ValueError, BeautifulSoup,
|
||||
"", features="no-such-feature")
|
||||
|
||||
class RegistryTest(unittest.TestCase):
|
||||
"""Test the TreeBuilderRegistry class in general."""
|
||||
|
||||
def setUp(self):
|
||||
self.registry = TreeBuilderRegistry()
|
||||
|
||||
def builder_for_features(self, *feature_list):
|
||||
cls = type('Builder_' + '_'.join(feature_list),
|
||||
(object,), {'features' : feature_list})
|
||||
|
||||
self.registry.register(cls)
|
||||
return cls
|
||||
|
||||
def test_register_with_no_features(self):
|
||||
builder = self.builder_for_features()
|
||||
|
||||
# Since the builder advertises no features, you can't find it
|
||||
# by looking up features.
|
||||
self.assertEqual(self.registry.lookup('foo'), None)
|
||||
|
||||
# But you can find it by doing a lookup with no features, if
|
||||
# this happens to be the only registered builder.
|
||||
self.assertEqual(self.registry.lookup(), builder)
|
||||
|
||||
def test_register_with_features_makes_lookup_succeed(self):
|
||||
builder = self.builder_for_features('foo', 'bar')
|
||||
self.assertEqual(self.registry.lookup('foo'), builder)
|
||||
self.assertEqual(self.registry.lookup('bar'), builder)
|
||||
|
||||
def test_lookup_fails_when_no_builder_implements_feature(self):
|
||||
builder = self.builder_for_features('foo', 'bar')
|
||||
self.assertEqual(self.registry.lookup('baz'), None)
|
||||
|
||||
def test_lookup_gets_most_recent_registration_when_no_feature_specified(self):
|
||||
builder1 = self.builder_for_features('foo')
|
||||
builder2 = self.builder_for_features('bar')
|
||||
self.assertEqual(self.registry.lookup(), builder2)
|
||||
|
||||
def test_lookup_fails_when_no_tree_builders_registered(self):
|
||||
self.assertEqual(self.registry.lookup(), None)
|
||||
|
||||
def test_lookup_gets_most_recent_builder_supporting_all_features(self):
|
||||
has_one = self.builder_for_features('foo')
|
||||
has_the_other = self.builder_for_features('bar')
|
||||
has_both_early = self.builder_for_features('foo', 'bar', 'baz')
|
||||
has_both_late = self.builder_for_features('foo', 'bar', 'quux')
|
||||
lacks_one = self.builder_for_features('bar')
|
||||
has_the_other = self.builder_for_features('foo')
|
||||
|
||||
# There are two builders featuring 'foo' and 'bar', but
|
||||
# the one that also features 'quux' was registered later.
|
||||
self.assertEqual(self.registry.lookup('foo', 'bar'),
|
||||
has_both_late)
|
||||
|
||||
# There is only one builder featuring 'foo', 'bar', and 'baz'.
|
||||
self.assertEqual(self.registry.lookup('foo', 'bar', 'baz'),
|
||||
has_both_early)
|
||||
|
||||
def test_lookup_fails_when_cannot_reconcile_requested_features(self):
|
||||
builder1 = self.builder_for_features('foo', 'bar')
|
||||
builder2 = self.builder_for_features('foo', 'baz')
|
||||
self.assertEqual(self.registry.lookup('bar', 'baz'), None)
|
|
@ -0,0 +1,36 @@
|
|||
"Test harness for doctests."
|
||||
|
||||
# pylint: disable-msg=E0611,W0142
|
||||
|
||||
__metaclass__ = type
|
||||
__all__ = [
|
||||
'additional_tests',
|
||||
]
|
||||
|
||||
import atexit
|
||||
import doctest
|
||||
import os
|
||||
#from pkg_resources import (
|
||||
# resource_filename, resource_exists, resource_listdir, cleanup_resources)
|
||||
import unittest
|
||||
|
||||
DOCTEST_FLAGS = (
|
||||
doctest.ELLIPSIS |
|
||||
doctest.NORMALIZE_WHITESPACE |
|
||||
doctest.REPORT_NDIFF)
|
||||
|
||||
|
||||
# def additional_tests():
|
||||
# "Run the doc tests (README.txt and docs/*, if any exist)"
|
||||
# doctest_files = [
|
||||
# os.path.abspath(resource_filename('bs4', 'README.txt'))]
|
||||
# if resource_exists('bs4', 'docs'):
|
||||
# for name in resource_listdir('bs4', 'docs'):
|
||||
# if name.endswith('.txt'):
|
||||
# doctest_files.append(
|
||||
# os.path.abspath(
|
||||
# resource_filename('bs4', 'docs/%s' % name)))
|
||||
# kwargs = dict(module_relative=False, optionflags=DOCTEST_FLAGS)
|
||||
# atexit.register(cleanup_resources)
|
||||
# return unittest.TestSuite((
|
||||
# doctest.DocFileSuite(*doctest_files, **kwargs)))
|
|
@ -0,0 +1,85 @@
|
|||
"""Tests to ensure that the html5lib tree builder generates good trees."""
|
||||
|
||||
import warnings
|
||||
|
||||
try:
|
||||
from bs4.builder import HTML5TreeBuilder
|
||||
HTML5LIB_PRESENT = True
|
||||
except ImportError, e:
|
||||
HTML5LIB_PRESENT = False
|
||||
from bs4.element import SoupStrainer
|
||||
from bs4.testing import (
|
||||
HTML5TreeBuilderSmokeTest,
|
||||
SoupTest,
|
||||
skipIf,
|
||||
)
|
||||
|
||||
@skipIf(
|
||||
not HTML5LIB_PRESENT,
|
||||
"html5lib seems not to be present, not testing its tree builder.")
|
||||
class HTML5LibBuilderSmokeTest(SoupTest, HTML5TreeBuilderSmokeTest):
|
||||
"""See ``HTML5TreeBuilderSmokeTest``."""
|
||||
|
||||
@property
|
||||
def default_builder(self):
|
||||
return HTML5TreeBuilder()
|
||||
|
||||
def test_soupstrainer(self):
|
||||
# The html5lib tree builder does not support SoupStrainers.
|
||||
strainer = SoupStrainer("b")
|
||||
markup = "<p>A <b>bold</b> statement.</p>"
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
soup = self.soup(markup, parse_only=strainer)
|
||||
self.assertEqual(
|
||||
soup.decode(), self.document_for(markup))
|
||||
|
||||
self.assertTrue(
|
||||
"the html5lib tree builder doesn't support parse_only" in
|
||||
str(w[0].message))
|
||||
|
||||
def test_correctly_nested_tables(self):
|
||||
"""html5lib inserts <tbody> tags where other parsers don't."""
|
||||
markup = ('<table id="1">'
|
||||
'<tr>'
|
||||
"<td>Here's another table:"
|
||||
'<table id="2">'
|
||||
'<tr><td>foo</td></tr>'
|
||||
'</table></td>')
|
||||
|
||||
self.assertSoupEquals(
|
||||
markup,
|
||||
'<table id="1"><tbody><tr><td>Here\'s another table:'
|
||||
'<table id="2"><tbody><tr><td>foo</td></tr></tbody></table>'
|
||||
'</td></tr></tbody></table>')
|
||||
|
||||
self.assertSoupEquals(
|
||||
"<table><thead><tr><td>Foo</td></tr></thead>"
|
||||
"<tbody><tr><td>Bar</td></tr></tbody>"
|
||||
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
|
||||
|
||||
def test_xml_declaration_followed_by_doctype(self):
|
||||
markup = '''<?xml version="1.0" encoding="utf-8"?>
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
</head>
|
||||
<body>
|
||||
<p>foo</p>
|
||||
</body>
|
||||
</html>'''
|
||||
soup = self.soup(markup)
|
||||
# Verify that we can reach the <p> tag; this means the tree is connected.
|
||||
self.assertEqual(b"<p>foo</p>", soup.p.encode())
|
||||
|
||||
def test_reparented_markup(self):
|
||||
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>", soup.body.decode())
|
||||
self.assertEqual(2, len(soup.find_all('p')))
|
||||
|
||||
|
||||
def test_reparented_markup_ends_with_whitespace(self):
|
||||
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>\n'
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(u"<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>", soup.body.decode())
|
||||
self.assertEqual(2, len(soup.find_all('p')))
|
|
@ -0,0 +1,19 @@
|
|||
"""Tests to ensure that the html.parser tree builder generates good
|
||||
trees."""
|
||||
|
||||
from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest
|
||||
from bs4.builder import HTMLParserTreeBuilder
|
||||
|
||||
class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
|
||||
|
||||
@property
|
||||
def default_builder(self):
|
||||
return HTMLParserTreeBuilder()
|
||||
|
||||
def test_namespaced_system_doctype(self):
|
||||
# html.parser can't handle namespaced doctypes, so skip this one.
|
||||
pass
|
||||
|
||||
def test_namespaced_public_doctype(self):
|
||||
# html.parser can't handle namespaced doctypes, so skip this one.
|
||||
pass
|
|
@ -0,0 +1,91 @@
|
|||
"""Tests to ensure that the lxml tree builder generates good trees."""
|
||||
|
||||
import re
|
||||
import warnings
|
||||
|
||||
try:
|
||||
import lxml.etree
|
||||
LXML_PRESENT = True
|
||||
LXML_VERSION = lxml.etree.LXML_VERSION
|
||||
except ImportError, e:
|
||||
LXML_PRESENT = False
|
||||
LXML_VERSION = (0,)
|
||||
|
||||
if LXML_PRESENT:
|
||||
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
|
||||
|
||||
from bs4 import (
|
||||
BeautifulSoup,
|
||||
BeautifulStoneSoup,
|
||||
)
|
||||
from bs4.element import Comment, Doctype, SoupStrainer
|
||||
from bs4.testing import skipIf
|
||||
from bs4.tests import test_htmlparser
|
||||
from bs4.testing import (
|
||||
HTMLTreeBuilderSmokeTest,
|
||||
XMLTreeBuilderSmokeTest,
|
||||
SoupTest,
|
||||
skipIf,
|
||||
)
|
||||
|
||||
@skipIf(
|
||||
not LXML_PRESENT,
|
||||
"lxml seems not to be present, not testing its tree builder.")
|
||||
class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
|
||||
"""See ``HTMLTreeBuilderSmokeTest``."""
|
||||
|
||||
@property
|
||||
def default_builder(self):
|
||||
return LXMLTreeBuilder()
|
||||
|
||||
def test_out_of_range_entity(self):
|
||||
self.assertSoupEquals(
|
||||
"<p>foo�bar</p>", "<p>foobar</p>")
|
||||
self.assertSoupEquals(
|
||||
"<p>foo�bar</p>", "<p>foobar</p>")
|
||||
self.assertSoupEquals(
|
||||
"<p>foo�bar</p>", "<p>foobar</p>")
|
||||
|
||||
# In lxml < 2.3.5, an empty doctype causes a segfault. Skip this
|
||||
# test if an old version of lxml is installed.
|
||||
|
||||
@skipIf(
|
||||
not LXML_PRESENT or LXML_VERSION < (2,3,5,0),
|
||||
"Skipping doctype test for old version of lxml to avoid segfault.")
|
||||
def test_empty_doctype(self):
|
||||
soup = self.soup("<!DOCTYPE>")
|
||||
doctype = soup.contents[0]
|
||||
self.assertEqual("", doctype.strip())
|
||||
|
||||
def test_beautifulstonesoup_is_xml_parser(self):
|
||||
# Make sure that the deprecated BSS class uses an xml builder
|
||||
# if one is installed.
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
soup = BeautifulStoneSoup("<b />")
|
||||
self.assertEqual(u"<b/>", unicode(soup.b))
|
||||
self.assertTrue("BeautifulStoneSoup class is deprecated" in str(w[0].message))
|
||||
|
||||
def test_real_xhtml_document(self):
|
||||
"""lxml strips the XML definition from an XHTML doc, which is fine."""
|
||||
markup = b"""<?xml version="1.0" encoding="utf-8"?>
|
||||
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
|
||||
<html xmlns="http://www.w3.org/1999/xhtml">
|
||||
<head><title>Hello.</title></head>
|
||||
<body>Goodbye.</body>
|
||||
</html>"""
|
||||
soup = self.soup(markup)
|
||||
self.assertEqual(
|
||||
soup.encode("utf-8").replace(b"\n", b''),
|
||||
markup.replace(b'\n', b'').replace(
|
||||
b'<?xml version="1.0" encoding="utf-8"?>', b''))
|
||||
|
||||
|
||||
@skipIf(
|
||||
not LXML_PRESENT,
|
||||
"lxml seems not to be present, not testing its XML tree builder.")
|
||||
class LXMLXMLTreeBuilderSmokeTest(SoupTest, XMLTreeBuilderSmokeTest):
|
||||
"""See ``HTMLTreeBuilderSmokeTest``."""
|
||||
|
||||
@property
|
||||
def default_builder(self):
|
||||
return LXMLTreeBuilderForXML()
|
|
@ -0,0 +1,434 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
"""Tests of Beautiful Soup as a whole."""
|
||||
|
||||
import logging
|
||||
import unittest
|
||||
import sys
|
||||
import tempfile
|
||||
|
||||
from bs4 import (
|
||||
BeautifulSoup,
|
||||
BeautifulStoneSoup,
|
||||
)
|
||||
from bs4.element import (
|
||||
CharsetMetaAttributeValue,
|
||||
ContentMetaAttributeValue,
|
||||
SoupStrainer,
|
||||
NamespacedAttribute,
|
||||
)
|
||||
import bs4.dammit
|
||||
from bs4.dammit import (
|
||||
EntitySubstitution,
|
||||
UnicodeDammit,
|
||||
)
|
||||
from bs4.testing import (
|
||||
SoupTest,
|
||||
skipIf,
|
||||
)
|
||||
import warnings
|
||||
|
||||
try:
|
||||
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
|
||||
LXML_PRESENT = True
|
||||
except ImportError, e:
|
||||
LXML_PRESENT = False
|
||||
|
||||
PYTHON_2_PRE_2_7 = (sys.version_info < (2,7))
|
||||
PYTHON_3_PRE_3_2 = (sys.version_info[0] == 3 and sys.version_info < (3,2))
|
||||
|
||||
class TestConstructor(SoupTest):
|
||||
|
||||
def test_short_unicode_input(self):
|
||||
data = u"<h1>éé</h1>"
|
||||
soup = self.soup(data)
|
||||
self.assertEqual(u"éé", soup.h1.string)
|
||||
|
||||
def test_embedded_null(self):
|
||||
data = u"<h1>foo\0bar</h1>"
|
||||
soup = self.soup(data)
|
||||
self.assertEqual(u"foo\0bar", soup.h1.string)
|
||||
|
||||
|
||||
class TestDeprecatedConstructorArguments(SoupTest):
|
||||
|
||||
def test_parseOnlyThese_renamed_to_parse_only(self):
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
soup = self.soup("<a><b></b></a>", parseOnlyThese=SoupStrainer("b"))
|
||||
msg = str(w[0].message)
|
||||
self.assertTrue("parseOnlyThese" in msg)
|
||||
self.assertTrue("parse_only" in msg)
|
||||
self.assertEqual(b"<b></b>", soup.encode())
|
||||
|
||||
def test_fromEncoding_renamed_to_from_encoding(self):
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
utf8 = b"\xc3\xa9"
|
||||
soup = self.soup(utf8, fromEncoding="utf8")
|
||||
msg = str(w[0].message)
|
||||
self.assertTrue("fromEncoding" in msg)
|
||||
self.assertTrue("from_encoding" in msg)
|
||||
self.assertEqual("utf8", soup.original_encoding)
|
||||
|
||||
def test_unrecognized_keyword_argument(self):
|
||||
self.assertRaises(
|
||||
TypeError, self.soup, "<a>", no_such_argument=True)
|
||||
|
||||
class TestWarnings(SoupTest):
|
||||
|
||||
def test_disk_file_warning(self):
|
||||
filehandle = tempfile.NamedTemporaryFile()
|
||||
filename = filehandle.name
|
||||
try:
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
soup = self.soup(filename)
|
||||
msg = str(w[0].message)
|
||||
self.assertTrue("looks like a filename" in msg)
|
||||
finally:
|
||||
filehandle.close()
|
||||
|
||||
# The file no longer exists, so Beautiful Soup will no longer issue the warning.
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
soup = self.soup(filename)
|
||||
self.assertEqual(0, len(w))
|
||||
|
||||
def test_url_warning(self):
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
soup = self.soup("http://www.crummy.com/")
|
||||
msg = str(w[0].message)
|
||||
self.assertTrue("looks like a URL" in msg)
|
||||
|
||||
with warnings.catch_warnings(record=True) as w:
|
||||
soup = self.soup("http://www.crummy.com/ is great")
|
||||
self.assertEqual(0, len(w))
|
||||
|
||||
class TestSelectiveParsing(SoupTest):
|
||||
|
||||
def test_parse_with_soupstrainer(self):
|
||||
markup = "No<b>Yes</b><a>No<b>Yes <c>Yes</c></b>"
|
||||
strainer = SoupStrainer("b")
|
||||
soup = self.soup(markup, parse_only=strainer)
|
||||
self.assertEqual(soup.encode(), b"<b>Yes</b><b>Yes <c>Yes</c></b>")
|
||||
|
||||
|
||||
class TestEntitySubstitution(unittest.TestCase):
|
||||
"""Standalone tests of the EntitySubstitution class."""
|
||||
def setUp(self):
|
||||
self.sub = EntitySubstitution
|
||||
|
||||
def test_simple_html_substitution(self):
|
||||
# Unicode characters corresponding to named HTML entites
|
||||
# are substituted, and no others.
|
||||
s = u"foo\u2200\N{SNOWMAN}\u00f5bar"
|
||||
self.assertEqual(self.sub.substitute_html(s),
|
||||
u"foo∀\N{SNOWMAN}õbar")
|
||||
|
||||
def test_smart_quote_substitution(self):
|
||||
# MS smart quotes are a common source of frustration, so we
|
||||
# give them a special test.
|
||||
quotes = b"\x91\x92foo\x93\x94"
|
||||
dammit = UnicodeDammit(quotes)
|
||||
self.assertEqual(self.sub.substitute_html(dammit.markup),
|
||||
"‘’foo“”")
|
||||
|
||||
def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
|
||||
s = 'Welcome to "my bar"'
|
||||
self.assertEqual(self.sub.substitute_xml(s, False), s)
|
||||
|
||||
def test_xml_attribute_quoting_normally_uses_double_quotes(self):
|
||||
self.assertEqual(self.sub.substitute_xml("Welcome", True),
|
||||
'"Welcome"')
|
||||
self.assertEqual(self.sub.substitute_xml("Bob's Bar", True),
|
||||
'"Bob\'s Bar"')
|
||||
|
||||
def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
|
||||
s = 'Welcome to "my bar"'
|
||||
self.assertEqual(self.sub.substitute_xml(s, True),
|
||||
"'Welcome to \"my bar\"'")
|
||||
|
||||
def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
|
||||
s = 'Welcome to "Bob\'s Bar"'
|
||||
self.assertEqual(
|
||||
self.sub.substitute_xml(s, True),
|
||||
'"Welcome to "Bob\'s Bar""')
|
||||
|
||||
def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
|
||||
quoted = 'Welcome to "Bob\'s Bar"'
|
||||
self.assertEqual(self.sub.substitute_xml(quoted), quoted)
|
||||
|
||||
def test_xml_quoting_handles_angle_brackets(self):
|
||||
self.assertEqual(
|
||||
self.sub.substitute_xml("foo<bar>"),
|
||||
"foo<bar>")
|
||||
|
||||
def test_xml_quoting_handles_ampersands(self):
|
||||
self.assertEqual(self.sub.substitute_xml("AT&T"), "AT&T")
|
||||
|
||||
def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
|
||||
self.assertEqual(
|
||||
self.sub.substitute_xml("ÁT&T"),
|
||||
"&Aacute;T&T")
|
||||
|
||||
def test_xml_quoting_ignoring_ampersands_when_they_are_part_of_an_entity(self):
|
||||
self.assertEqual(
|
||||
self.sub.substitute_xml_containing_entities("ÁT&T"),
|
||||
"ÁT&T")
|
||||
|
||||
def test_quotes_not_html_substituted(self):
|
||||
"""There's no need to do this except inside attribute values."""
|
||||
text = 'Bob\'s "bar"'
|
||||
self.assertEqual(self.sub.substitute_html(text), text)
|
||||
|
||||
|
||||
class TestEncodingConversion(SoupTest):
|
||||
# Test Beautiful Soup's ability to decode and encode from various
|
||||
# encodings.
|
||||
|
||||
def setUp(self):
|
||||
super(TestEncodingConversion, self).setUp()
|
||||
self.unicode_data = u'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</foo></body></html>'
|
||||
self.utf8_data = self.unicode_data.encode("utf-8")
|
||||
# Just so you know what it looks like.
|
||||
self.assertEqual(
|
||||
self.utf8_data,
|
||||
b'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\xc3\xa9 bleu!</foo></body></html>')
|
||||
|
||||
def test_ascii_in_unicode_out(self):
|
||||
# ASCII input is converted to Unicode. The original_encoding
|
||||
# attribute is set to 'utf-8', a superset of ASCII.
|
||||
chardet = bs4.dammit.chardet_dammit
|
||||
logging.disable(logging.WARNING)
|
||||
try:
|
||||
def noop(str):
|
||||
return None
|
||||
# Disable chardet, which will realize that the ASCII is ASCII.
|
||||
bs4.dammit.chardet_dammit = noop
|
||||
ascii = b"<foo>a</foo>"
|
||||
soup_from_ascii = self.soup(ascii)
|
||||
unicode_output = soup_from_ascii.decode()
|
||||
self.assertTrue(isinstance(unicode_output, unicode))
|
||||
self.assertEqual(unicode_output, self.document_for(ascii.decode()))
|
||||
self.assertEqual(soup_from_ascii.original_encoding.lower(), "utf-8")
|
||||
finally:
|
||||
logging.disable(logging.NOTSET)
|
||||
bs4.dammit.chardet_dammit = chardet
|
||||
|
||||
def test_unicode_in_unicode_out(self):
|
||||
# Unicode input is left alone. The original_encoding attribute
|
||||
# is not set.
|
||||
soup_from_unicode = self.soup(self.unicode_data)
|
||||
self.assertEqual(soup_from_unicode.decode(), self.unicode_data)
|
||||
self.assertEqual(soup_from_unicode.foo.string, u'Sacr\xe9 bleu!')
|
||||
self.assertEqual(soup_from_unicode.original_encoding, None)
|
||||
|
||||
def test_utf8_in_unicode_out(self):
|
||||
# UTF-8 input is converted to Unicode. The original_encoding
|
||||
# attribute is set.
|
||||
soup_from_utf8 = self.soup(self.utf8_data)
|
||||
self.assertEqual(soup_from_utf8.decode(), self.unicode_data)
|
||||
self.assertEqual(soup_from_utf8.foo.string, u'Sacr\xe9 bleu!')
|
||||
|
||||
def test_utf8_out(self):
|
||||
# The internal data structures can be encoded as UTF-8.
|
||||
soup_from_unicode = self.soup(self.unicode_data)
|
||||
self.assertEqual(soup_from_unicode.encode('utf-8'), self.utf8_data)
|
||||
|
||||
@skipIf(
|
||||
PYTHON_2_PRE_2_7 or PYTHON_3_PRE_3_2,
|
||||
"Bad HTMLParser detected; skipping test of non-ASCII characters in attribute name.")
|
||||
def test_attribute_name_containing_unicode_characters(self):
|
||||
markup = u'<div><a \N{SNOWMAN}="snowman"></a></div>'
|
||||
self.assertEqual(self.soup(markup).div.encode("utf8"), markup.encode("utf8"))
|
||||
|
||||
class TestUnicodeDammit(unittest.TestCase):
|
||||
"""Standalone tests of UnicodeDammit."""
|
||||
|
||||
def test_unicode_input(self):
|
||||
markup = u"I'm already Unicode! \N{SNOWMAN}"
|
||||
dammit = UnicodeDammit(markup)
|
||||
self.assertEqual(dammit.unicode_markup, markup)
|
||||
|
||||
def test_smart_quotes_to_unicode(self):
|
||||
markup = b"<foo>\x91\x92\x93\x94</foo>"
|
||||
dammit = UnicodeDammit(markup)
|
||||
self.assertEqual(
|
||||
dammit.unicode_markup, u"<foo>\u2018\u2019\u201c\u201d</foo>")
|
||||
|
||||
def test_smart_quotes_to_xml_entities(self):
|
||||
markup = b"<foo>\x91\x92\x93\x94</foo>"
|
||||
dammit = UnicodeDammit(markup, smart_quotes_to="xml")
|
||||
self.assertEqual(
|
||||
dammit.unicode_markup, "<foo>‘’“”</foo>")
|
||||
|
||||
def test_smart_quotes_to_html_entities(self):
|
||||
markup = b"<foo>\x91\x92\x93\x94</foo>"
|
||||
dammit = UnicodeDammit(markup, smart_quotes_to="html")
|
||||
self.assertEqual(
|
||||
dammit.unicode_markup, "<foo>‘’“”</foo>")
|
||||
|
||||
def test_smart_quotes_to_ascii(self):
|
||||
markup = b"<foo>\x91\x92\x93\x94</foo>"
|
||||
dammit = UnicodeDammit(markup, smart_quotes_to="ascii")
|
||||
self.assertEqual(
|
||||
dammit.unicode_markup, """<foo>''""</foo>""")
|
||||
|
||||
def test_detect_utf8(self):
|
||||
utf8 = b"\xc3\xa9"
|
||||
dammit = UnicodeDammit(utf8)
|
||||
self.assertEqual(dammit.unicode_markup, u'\xe9')
|
||||
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
|
||||
|
||||
def test_convert_hebrew(self):
|
||||
hebrew = b"\xed\xe5\xec\xf9"
|
||||
dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
|
||||
self.assertEqual(dammit.original_encoding.lower(), 'iso-8859-8')
|
||||
self.assertEqual(dammit.unicode_markup, u'\u05dd\u05d5\u05dc\u05e9')
|
||||
|
||||
def test_dont_see_smart_quotes_where_there_are_none(self):
|
||||
utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
|
||||
dammit = UnicodeDammit(utf_8)
|
||||
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
|
||||
self.assertEqual(dammit.unicode_markup.encode("utf-8"), utf_8)
|
||||
|
||||
def test_ignore_inappropriate_codecs(self):
|
||||
utf8_data = u"Räksmörgås".encode("utf-8")
|
||||
dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
|
||||
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
|
||||
|
||||
def test_ignore_invalid_codecs(self):
|
||||
utf8_data = u"Räksmörgås".encode("utf-8")
|
||||
for bad_encoding in ['.utf8', '...', 'utF---16.!']:
|
||||
dammit = UnicodeDammit(utf8_data, [bad_encoding])
|
||||
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
|
||||
|
||||
def test_detect_html5_style_meta_tag(self):
|
||||
|
||||
for data in (
|
||||
b'<html><meta charset="euc-jp" /></html>',
|
||||
b"<html><meta charset='euc-jp' /></html>",
|
||||
b"<html><meta charset=euc-jp /></html>",
|
||||
b"<html><meta charset=euc-jp/></html>"):
|
||||
dammit = UnicodeDammit(data, is_html=True)
|
||||
self.assertEqual(
|
||||
"euc-jp", dammit.original_encoding)
|
||||
|
||||
def test_last_ditch_entity_replacement(self):
|
||||
# This is a UTF-8 document that contains bytestrings
|
||||
# completely incompatible with UTF-8 (ie. encoded with some other
|
||||
# encoding).
|
||||
#
|
||||
# Since there is no consistent encoding for the document,
|
||||
# Unicode, Dammit will eventually encode the document as UTF-8
|
||||
# and encode the incompatible characters as REPLACEMENT
|
||||
# CHARACTER.
|
||||
#
|
||||
# If chardet is installed, it will detect that the document
|
||||
# can be converted into ISO-8859-1 without errors. This happens
|
||||
# to be the wrong encoding, but it is a consistent encoding, so the
|
||||
# code we're testing here won't run.
|
||||
#
|
||||
# So we temporarily disable chardet if it's present.
|
||||
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
|
||||
<html><b>\330\250\330\252\330\261</b>
|
||||
<i>\310\322\321\220\312\321\355\344</i></html>"""
|
||||
chardet = bs4.dammit.chardet_dammit
|
||||
logging.disable(logging.WARNING)
|
||||
try:
|
||||
def noop(str):
|
||||
return None
|
||||
bs4.dammit.chardet_dammit = noop
|
||||
dammit = UnicodeDammit(doc)
|
||||
self.assertEqual(True, dammit.contains_replacement_characters)
|
||||
self.assertTrue(u"\ufffd" in dammit.unicode_markup)
|
||||
|
||||
soup = BeautifulSoup(doc, "html.parser")
|
||||
self.assertTrue(soup.contains_replacement_characters)
|
||||
finally:
|
||||
logging.disable(logging.NOTSET)
|
||||
bs4.dammit.chardet_dammit = chardet
|
||||
|
||||
def test_byte_order_mark_removed(self):
|
||||
# A document written in UTF-16LE will have its byte order marker stripped.
|
||||
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
|
||||
dammit = UnicodeDammit(data)
|
||||
self.assertEqual(u"<a>áé</a>", dammit.unicode_markup)
|
||||
self.assertEqual("utf-16le", dammit.original_encoding)
|
||||
|
||||
def test_detwingle(self):
|
||||
# Here's a UTF8 document.
|
||||
utf8 = (u"\N{SNOWMAN}" * 3).encode("utf8")
|
||||
|
||||
# Here's a Windows-1252 document.
|
||||
windows_1252 = (
|
||||
u"\N{LEFT DOUBLE QUOTATION MARK}Hi, I like Windows!"
|
||||
u"\N{RIGHT DOUBLE QUOTATION MARK}").encode("windows_1252")
|
||||
|
||||
# Through some unholy alchemy, they've been stuck together.
|
||||
doc = utf8 + windows_1252 + utf8
|
||||
|
||||
# The document can't be turned into UTF-8:
|
||||
self.assertRaises(UnicodeDecodeError, doc.decode, "utf8")
|
||||
|
||||
# Unicode, Dammit thinks the whole document is Windows-1252,
|
||||
# and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
|
||||
|
||||
# But if we run it through fix_embedded_windows_1252, it's fixed:
|
||||
|
||||
fixed = UnicodeDammit.detwingle(doc)
|
||||
self.assertEqual(
|
||||
u"☃☃☃“Hi, I like Windows!”☃☃☃", fixed.decode("utf8"))
|
||||
|
||||
def test_detwingle_ignores_multibyte_characters(self):
|
||||
# Each of these characters has a UTF-8 representation ending
|
||||
# in \x93. \x93 is a smart quote if interpreted as
|
||||
# Windows-1252. But our code knows to skip over multibyte
|
||||
# UTF-8 characters, so they'll survive the process unscathed.
|
||||
for tricky_unicode_char in (
|
||||
u"\N{LATIN SMALL LIGATURE OE}", # 2-byte char '\xc5\x93'
|
||||
u"\N{LATIN SUBSCRIPT SMALL LETTER X}", # 3-byte char '\xe2\x82\x93'
|
||||
u"\xf0\x90\x90\x93", # This is a CJK character, not sure which one.
|
||||
):
|
||||
input = tricky_unicode_char.encode("utf8")
|
||||
self.assertTrue(input.endswith(b'\x93'))
|
||||
output = UnicodeDammit.detwingle(input)
|
||||
self.assertEqual(output, input)
|
||||
|
||||
class TestNamedspacedAttribute(SoupTest):
|
||||
|
||||
def test_name_may_be_none(self):
|
||||
a = NamespacedAttribute("xmlns", None)
|
||||
self.assertEqual(a, "xmlns")
|
||||
|
||||
def test_attribute_is_equivalent_to_colon_separated_string(self):
|
||||
a = NamespacedAttribute("a", "b")
|
||||
self.assertEqual("a:b", a)
|
||||
|
||||
def test_attributes_are_equivalent_if_prefix_and_name_identical(self):
|
||||
a = NamespacedAttribute("a", "b", "c")
|
||||
b = NamespacedAttribute("a", "b", "c")
|
||||
self.assertEqual(a, b)
|
||||
|
||||
# The actual namespace is not considered.
|
||||
c = NamespacedAttribute("a", "b", None)
|
||||
self.assertEqual(a, c)
|
||||
|
||||
# But name and prefix are important.
|
||||
d = NamespacedAttribute("a", "z", "c")
|
||||
self.assertNotEqual(a, d)
|
||||
|
||||
e = NamespacedAttribute("z", "b", "c")
|
||||
self.assertNotEqual(a, e)
|
||||
|
||||
|
||||
class TestAttributeValueWithCharsetSubstitution(unittest.TestCase):
|
||||
|
||||
def test_content_meta_attribute_value(self):
|
||||
value = CharsetMetaAttributeValue("euc-jp")
|
||||
self.assertEqual("euc-jp", value)
|
||||
self.assertEqual("euc-jp", value.original_value)
|
||||
self.assertEqual("utf8", value.encode("utf8"))
|
||||
|
||||
|
||||
def test_content_meta_attribute_value(self):
|
||||
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
|
||||
self.assertEqual("text/html; charset=euc-jp", value)
|
||||
self.assertEqual("text/html; charset=euc-jp", value.original_value)
|
||||
self.assertEqual("text/html; charset=utf8", value.encode("utf8"))
|
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue