octospacc
/
staticoso
mirror of https://gitlab.com/octtspacc/staticoso
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Complete OG support

This commit is contained in:
octospacc 2022-06-23 20:42:43 +02:00
parent ac22d78d9f
commit 543e3de13e
26 changed files with 12036 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -19,7 +19,7 @@ Feel free to experiment with all of this stuff!
- [x] Autodetection of pages and posts
- [x] Info for posts shown on their page
- [x] HTML minification
- [ ] Full Open Graph support
- [x] Full Open Graph support
- [x] Custom categories for posts
- [x] Custom static page parts programmable by context
- [x] Showing creation and modified date for posts

53
Source/Build.py
View File

@ -13,22 +13,31 @@ from Libs import htmlmin
import os
import shutil
from ast import literal_eval
from html.parser import HTMLParser
from Libs.bs4 import BeautifulSoup
#from html.parser import HTMLParser
from markdown import Markdown
from pathlib import Path
Extensions = {
'Pages': ('md', 'pug')}
class MyHTMLParser(HTMLParser):
Tags, Attrs, Data = [], [], []
"""
class HTMLParser(HTMLParser):
Tags = []
def handle_starttag(self, tag, attrs):
self.Tags += [tag]
self.Attrs += [attrs]
#print(tag, attrs)
#self.Tags += [tag, attrs]
self.Tags += [[tag,attrs]]
def handle_data(self, data):
self.Data += [data]
#print(data)
if self.Tags:
#self.Tags += [data]
self.Tags[-1] += [data]
def Clean(self):
self.Tags, self.Attrs, self.Data = [], [], []
self.Tags = []
self.reset()
self.close()
"""
def ReadFile(p):
try:
@ -250,18 +259,30 @@ def PatchHTML(Template, PartsText, ContextParts, ContextPartsText, HTMLPagesList
BodyDescription, BodyImage = '', ''
HTMLTitles = FormatTitles(Titles)
""" # This is broken and somehow always returns the same wrong values? Disabled for now
parser = MyHTMLParser()
parser.feed(Content)
for i,e in enumerate(parser.Tags):
if e == 'p' and not BodyDescription:
BodyDescription = parser.Data[i]
elif e == 'img' and not BodyImage:
BodyImage = parser.Data[i]
print(Content)
#print(Content)
Parser = HTMLParser()
Parser.feed(Content)
for e in Parser.Tags:
if not BodyDescription and e[0] == 'p':
BodyDescription = e[2][:150] + '...'
elif not BodyImage and e[0] == 'img':
for j,f in enumerate(e[1]):
if f == 'src':
BodyImage = e[1][j]
print(BodyDescription)
print(BodyImage)
parser.Clean()
print(len(Parser.Tags))
#print(Parser.Tags)
#exit()
Parser.Clean()
"""
#Content.find("<p ")
Parse = BeautifulSoup(Content, 'html.parser')
if not BodyDescription and Parse.p:
BodyDescription = Parse.p.get_text()[:150].replace('\n', ' ').replace('"', "'") + '...'
if not BodyImage and Parse.img and Parse.img['src']:
BodyImage = Parse.img['src']
for Line in Template.splitlines():
Line = Line.lstrip().rstrip()
if Line.startswith('[HTML:ContextPart:') and Line.endswith(']'):

812
Source/Libs/bs4/__init__.py Normal file
View File

@ -0,0 +1,812 @@
"""Beautiful Soup Elixir and Tonic - "The Screen-Scraper's Friend".
http://www.crummy.com/software/BeautifulSoup/
Beautiful Soup uses a pluggable XML or HTML parser to parse a
(possibly invalid) document into a tree representation. Beautiful Soup
provides methods and Pythonic idioms that make it easy to navigate,
search, and modify the parse tree.
Beautiful Soup works with Python 3.5 and up. It works better if lxml
and/or html5lib is installed.
For more than you ever wanted to know about Beautiful Soup, see the
documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
"""
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "4.11.1"
__copyright__ = "Copyright (c) 2004-2022 Leonard Richardson"
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = ['BeautifulSoup']
from collections import Counter
import os
import re
import sys
import traceback
import warnings
# The very first thing we do is give a useful error if someone is
# running this code under Python 2.
if sys.version_info.major < 3:
raise ImportError('You are trying to use a Python 3-specific version of Beautiful Soup under Python 2. This will not work. The final version of Beautiful Soup to support Python 2 was 4.9.3.')
from .builder import (
builder_registry,
ParserRejectedMarkup,
XMLParsedAsHTMLWarning,
)
from .dammit import UnicodeDammit
from .element import (
CData,
Comment,
DEFAULT_OUTPUT_ENCODING,
Declaration,
Doctype,
NavigableString,
PageElement,
ProcessingInstruction,
PYTHON_SPECIFIC_ENCODINGS,
ResultSet,
Script,
Stylesheet,
SoupStrainer,
Tag,
TemplateString,
)
# Define some custom warnings.
class GuessedAtParserWarning(UserWarning):
"""The warning issued when BeautifulSoup has to guess what parser to
use -- probably because no parser was specified in the constructor.
"""
class MarkupResemblesLocatorWarning(UserWarning):
"""The warning issued when BeautifulSoup is given 'markup' that
actually looks like a resource locator -- a URL or a path to a file
on disk.
"""
class BeautifulSoup(Tag):
"""A data structure representing a parsed HTML or XML document.
Most of the methods you'll call on a BeautifulSoup object are inherited from
PageElement or Tag.
Internally, this class defines the basic interface called by the
tree builders when converting an HTML/XML document into a data
structure. The interface abstracts away the differences between
parsers. To write a new tree builder, you'll need to understand
these methods as a whole.
These methods will be called by the BeautifulSoup constructor:
* reset()
* feed(markup)
The tree builder may call these methods from its feed() implementation:
* handle_starttag(name, attrs) # See note about return value
* handle_endtag(name)
* handle_data(data) # Appends to the current data node
* endData(containerClass) # Ends the current data node
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.
"""
# Since BeautifulSoup subclasses Tag, it's possible to treat it as
# a Tag with a .name. This name makes it clear the BeautifulSoup
# object isn't a real markup tag.
ROOT_TAG_NAME = '[document]'
# If the end-user gives no indication which tree builder they
# want, look for one with these features.
DEFAULT_BUILDER_FEATURES = ['html', 'fast']
# A string containing all ASCII whitespace characters, used in
# endData() to detect data chunks that seem 'empty'.
ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nThe code that caused this warning is on line %(line_number)s of the file %(filename)s. To get rid of this warning, pass the additional argument 'features=\"%(parser)s\"' to the BeautifulSoup constructor.\n"
def __init__(self, markup="", features=None, builder=None,
parse_only=None, from_encoding=None, exclude_encodings=None,
element_classes=None, **kwargs):
"""Constructor.
:param markup: A string or a file-like object representing
markup to be parsed.
:param features: Desirable features of the parser to be
used. This may be the name of a specific parser ("lxml",
"lxml-xml", "html.parser", or "html5lib") or it may be the
type of markup to be used ("html", "html5", "xml"). It's
recommended that you name a specific parser, so that
Beautiful Soup gives you the same results across platforms
and virtual environments.
:param builder: A TreeBuilder subclass to instantiate (or
instance to use) instead of looking one up based on
`features`. You only need to use this if you've implemented a
custom TreeBuilder.
:param parse_only: A SoupStrainer. Only parts of the document
matching the SoupStrainer will be considered. This is useful
when parsing part of a document that would otherwise be too
large to fit into memory.
:param from_encoding: A string indicating the encoding of the
document to be parsed. Pass this in if Beautiful Soup is
guessing wrongly about the document's encoding.
:param exclude_encodings: A list of strings indicating
encodings known to be wrong. Pass this in if you don't know
the document's encoding but you know Beautiful Soup's guess is
wrong.
:param element_classes: A dictionary mapping BeautifulSoup
classes like Tag and NavigableString, to other classes you'd
like to be instantiated instead as the parse tree is
built. This is useful for subclassing Tag or NavigableString
to modify default behavior.
:param kwargs: For backwards compatibility purposes, the
constructor accepts certain keyword arguments used in
Beautiful Soup 3. None of these arguments do anything in
Beautiful Soup 4; they will result in a warning and then be
ignored.
Apart from this, any keyword arguments passed into the
BeautifulSoup constructor are propagated to the TreeBuilder
constructor. This makes it possible to configure a
TreeBuilder by passing in arguments, not just by saying which
one to use.
"""
if 'convertEntities' in kwargs:
del kwargs['convertEntities']
warnings.warn(
"BS4 does not respect the convertEntities argument to the "
"BeautifulSoup constructor. Entities are always converted "
"to Unicode characters.")
if 'markupMassage' in kwargs:
del kwargs['markupMassage']
warnings.warn(
"BS4 does not respect the markupMassage argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for any necessary markup massage.")
if 'smartQuotesTo' in kwargs:
del kwargs['smartQuotesTo']
warnings.warn(
"BS4 does not respect the smartQuotesTo argument to the "
"BeautifulSoup constructor. Smart quotes are always converted "
"to Unicode characters.")
if 'selfClosingTags' in kwargs:
del kwargs['selfClosingTags']
warnings.warn(
"BS4 does not respect the selfClosingTags argument to the "
"BeautifulSoup constructor. The tree builder is responsible "
"for understanding self-closing tags.")
if 'isHTML' in kwargs:
del kwargs['isHTML']
warnings.warn(
"BS4 does not respect the isHTML argument to the "
"BeautifulSoup constructor. Suggest you use "
"features='lxml' for HTML and features='lxml-xml' for "
"XML.")
def deprecated_argument(old_name, new_name):
if old_name in kwargs:
warnings.warn(
'The "%s" argument to the BeautifulSoup constructor '
'has been renamed to "%s."' % (old_name, new_name),
DeprecationWarning
)
return kwargs.pop(old_name)
return None
parse_only = parse_only or deprecated_argument(
"parseOnlyThese", "parse_only")
from_encoding = from_encoding or deprecated_argument(
"fromEncoding", "from_encoding")
if from_encoding and isinstance(markup, str):
warnings.warn("You provided Unicode markup but also provided a value for from_encoding. Your from_encoding will be ignored.")
from_encoding = None
self.element_classes = element_classes or dict()
# We need this information to track whether or not the builder
# was specified well enough that we can omit the 'you need to
# specify a parser' warning.
original_builder = builder
original_features = features
if isinstance(builder, type):
# A builder class was passed in; it needs to be instantiated.
builder_class = builder
builder = None
elif builder is None:
if isinstance(features, str):
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))
# At this point either we have a TreeBuilder instance in
# builder, or we have a builder_class that we can instantiate
# with the remaining **kwargs.
if builder is None:
builder = builder_class(**kwargs)
if not original_builder and not (
original_features == builder.NAME or
original_features in builder.ALTERNATE_NAMES
) and markup:
# The user did not tell us which TreeBuilder to use,
# and we had to guess. Issue a warning.
if builder.is_xml:
markup_type = "XML"
else:
markup_type = "HTML"
# This code adapted from warnings.py so that we get the same line
# of code as our warnings.warn() call gets, even if the answer is wrong
# (as it may be in a multithreading situation).
caller = None
try:
caller = sys._getframe(1)
except ValueError:
pass
if caller:
globals = caller.f_globals
line_number = caller.f_lineno
else:
globals = sys.__dict__
line_number= 1
filename = globals.get('__file__')
if filename:
fnl = filename.lower()
if fnl.endswith((".pyc", ".pyo")):
filename = filename[:-1]
if filename:
# If there is no filename at all, the user is most likely in a REPL,
# and the warning is not necessary.
values = dict(
filename=filename,
line_number=line_number,
parser=builder.NAME,
markup_type=markup_type
)
warnings.warn(
self.NO_PARSER_SPECIFIED_WARNING % values,
GuessedAtParserWarning, stacklevel=2
)
else:
if kwargs:
warnings.warn("Keyword arguments to the BeautifulSoup constructor will be ignored. These would normally be passed into the TreeBuilder constructor, but a TreeBuilder instance was passed in as `builder`.")
self.builder = builder
self.is_xml = builder.is_xml
self.known_xml = self.is_xml
self._namespaces = dict()
self.parse_only = parse_only
if hasattr(markup, 'read'): # It's a file-type object.
markup = markup.read()
elif len(markup) <= 256 and (
(isinstance(markup, bytes) and not b'<' in markup)
or (isinstance(markup, str) and not '<' in markup)
):
# Issue warnings for a couple beginner problems
# involving passing non-markup to Beautiful Soup.
# Beautiful Soup will still parse the input as markup,
# since that is sometimes the intended behavior.
if not self._markup_is_url(markup):
self._markup_resembles_filename(markup)
rejections = []
success = False
for (self.markup, self.original_encoding, self.declared_html_encoding,
self.contains_replacement_characters) in (
self.builder.prepare_markup(
markup, from_encoding, exclude_encodings=exclude_encodings)):
self.reset()
self.builder.initialize_soup(self)
try:
self._feed()
success = True
break
except ParserRejectedMarkup as e:
rejections.append(e)
pass
if not success:
other_exceptions = [str(e) for e in rejections]
raise ParserRejectedMarkup(
"The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help.\n\nOriginal exception(s) from parser:\n " + "\n ".join(other_exceptions)
)
# Clear out the markup and remove the builder's circular
# reference to this object.
self.markup = None
self.builder.soup = None
def __copy__(self):
"""Copy a BeautifulSoup object by converting the document to a string and parsing it again."""
copy = type(self)(
self.encode('utf-8'), builder=self.builder, from_encoding='utf-8'
)
# Although we encoded the tree to UTF-8, that may not have
# been the encoding of the original markup. Set the copy's
# .original_encoding to reflect the original object's
# .original_encoding.
copy.original_encoding = self.original_encoding
return copy
def __getstate__(self):
# Frequently a tree builder can't be pickled.
d = dict(self.__dict__)
if 'builder' in d and d['builder'] is not None and not self.builder.picklable:
d['builder'] = None
return d
@classmethod
def _decode_markup(cls, markup):
"""Ensure `markup` is bytes so it's safe to send into warnings.warn.
TODO: warnings.warn had this problem back in 2010 but it might not
anymore.
"""
if isinstance(markup, bytes):
decoded = markup.decode('utf-8', 'replace')
else:
decoded = markup
return decoded
@classmethod
def _markup_is_url(cls, markup):
"""Error-handling method to raise a warning if incoming markup looks
like a URL.
:param markup: A string.
:return: Whether or not the markup resembles a URL
closely enough to justify a warning.
"""
if isinstance(markup, bytes):
space = b' '
cant_start_with = (b"http:", b"https:")
elif isinstance(markup, str):
space = ' '
cant_start_with = ("http:", "https:")
else:
return False
if any(markup.startswith(prefix) for prefix in cant_start_with):
if not space in markup:
warnings.warn(
'The input looks more like a URL than markup. You may want to use'
' an HTTP client like requests to get the document behind'
' the URL, and feed that document to Beautiful Soup.',
MarkupResemblesLocatorWarning
)
return True
return False
@classmethod
def _markup_resembles_filename(cls, markup):
"""Error-handling method to raise a warning if incoming markup
resembles a filename.
:param markup: A bytestring or string.
:return: Whether or not the markup resembles a filename
closely enough to justify a warning.
"""
path_characters = '/\\'
extensions = ['.html', '.htm', '.xml', '.xhtml', '.txt']
if isinstance(markup, bytes):
path_characters = path_characters.encode("utf8")
extensions = [x.encode('utf8') for x in extensions]
filelike = False
if any(x in markup for x in path_characters):
filelike = True
else:
lower = markup.lower()
if any(lower.endswith(ext) for ext in extensions):
filelike = True
if filelike:
warnings.warn(
'The input looks more like a filename than markup. You may'
' want to open this file and pass the filehandle into'
' Beautiful Soup.',
MarkupResemblesLocatorWarning
)
return True
return False
def _feed(self):
"""Internal method that parses previously set markup, creating a large
number of Tag and NavigableString objects.
"""
# 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):
"""Reset this object to a state as though it had never parsed any
markup.
"""
Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
self.hidden = 1
self.builder.reset()
self.current_data = []
self.currentTag = None
self.tagStack = []
self.open_tag_counter = Counter()
self.preserve_whitespace_tag_stack = []
self.string_container_stack = []
self.pushTag(self)
def new_tag(self, name, namespace=None, nsprefix=None, attrs={},
sourceline=None, sourcepos=None, **kwattrs):
"""Create a new Tag associated with this BeautifulSoup object.
:param name: The name of the new Tag.
:param namespace: The URI of the new Tag's XML namespace, if any.
:param prefix: The prefix for the new Tag's XML namespace, if any.
:param attrs: A dictionary of this Tag's attribute values; can
be used instead of `kwattrs` for attributes like 'class'
that are reserved words in Python.
:param sourceline: The line number where this tag was
(purportedly) found in its source document.
:param sourcepos: The character position within `sourceline` where this
tag was (purportedly) found.
:param kwattrs: Keyword arguments for the new Tag's attribute values.
"""
kwattrs.update(attrs)
return self.element_classes.get(Tag, Tag)(
None, self.builder, name, namespace, nsprefix, kwattrs,
sourceline=sourceline, sourcepos=sourcepos
)
def string_container(self, base_class=None):
container = base_class or NavigableString
# There may be a general override of NavigableString.
container = self.element_classes.get(
container, container
)
# On top of that, we may be inside a tag that needs a special
# container class.
if self.string_container_stack and container is NavigableString:
container = self.builder.string_containers.get(
self.string_container_stack[-1].name, container
)
return container
def new_string(self, s, subclass=None):
"""Create a new NavigableString associated with this BeautifulSoup
object.
"""
container = self.string_container(subclass)
return container(s)
def insert_before(self, *args):
"""This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
it because there is nothing before or after it in the parse tree.
"""
raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
def insert_after(self, *args):
"""This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
it because there is nothing before or after it in the parse tree.
"""
raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
def popTag(self):
"""Internal method called by _popToTag when a tag is closed."""
tag = self.tagStack.pop()
if tag.name in self.open_tag_counter:
self.open_tag_counter[tag.name] -= 1
if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
self.preserve_whitespace_tag_stack.pop()
if self.string_container_stack and tag == self.string_container_stack[-1]:
self.string_container_stack.pop()
#print("Pop", tag.name)
if self.tagStack:
self.currentTag = self.tagStack[-1]
return self.currentTag
def pushTag(self, tag):
"""Internal method called by handle_starttag when a tag is opened."""
#print("Push", tag.name)
if self.currentTag is not None:
self.currentTag.contents.append(tag)
self.tagStack.append(tag)
self.currentTag = self.tagStack[-1]
if tag.name != self.ROOT_TAG_NAME:
self.open_tag_counter[tag.name] += 1
if tag.name in self.builder.preserve_whitespace_tags:
self.preserve_whitespace_tag_stack.append(tag)
if tag.name in self.builder.string_containers:
self.string_container_stack.append(tag)
def endData(self, containerClass=None):
"""Method called by the TreeBuilder when the end of a data segment
occurs.
"""
if self.current_data:
current_data = ''.join(self.current_data)
# If whitespace is not preserved, and this string contains
# 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
containerClass = self.string_container(containerClass)
o = containerClass(current_data)
self.object_was_parsed(o)
def object_was_parsed(self, o, parent=None, most_recent_element=None):
"""Method called by the TreeBuilder to integrate an object into the parse tree."""
if parent is None:
parent = self.currentTag
if most_recent_element is not None:
previous_element = most_recent_element
else:
previous_element = self._most_recent_element
next_element = previous_sibling = next_sibling = None
if isinstance(o, Tag):
next_element = o.next_element
next_sibling = o.next_sibling
previous_sibling = o.previous_sibling
if previous_element is None:
previous_element = o.previous_element
fix = parent.next_element is not None
o.setup(parent, previous_element, next_element, previous_sibling, next_sibling)
self._most_recent_element = o
parent.contents.append(o)
# Check if we are inserting into an already parsed node.
if fix:
self._linkage_fixer(parent)
def _linkage_fixer(self, el):
"""Make sure linkage of this fragment is sound."""
first = el.contents[0]
child = el.contents[-1]
descendant = child
if child is first and el.parent is not None:
# Parent should be linked to first child
el.next_element = child
# We are no longer linked to whatever this element is
prev_el = child.previous_element
if prev_el is not None and prev_el is not el:
prev_el.next_element = None
# First child should be linked to the parent, and no previous siblings.
child.previous_element = el
child.previous_sibling = None
# We have no sibling as we've been appended as the last.
child.next_sibling = None
# This index is a tag, dig deeper for a "last descendant"
if isinstance(child, Tag) and child.contents:
descendant = child._last_descendant(False)
# As the final step, link last descendant. It should be linked
# to the parent's next sibling (if found), else walk up the chain
# and find a parent with a sibling. It should have no next sibling.
descendant.next_element = None
descendant.next_sibling = None
target = el
while True:
if target is None:
break
elif target.next_sibling is not None:
descendant.next_element = target.next_sibling
target.next_sibling.previous_element = child
break
target = target.parent
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 there are no open tags with the given name, nothing will be
popped.
:param name: Pop up to the most recent tag with this name.
:param nsprefix: The namespace prefix that goes with `name`.
:param inclusivePop: It this is false, pops the tag stack up
to but *not* including the most recent instqance of the
given tag.
"""
#print("Popping to %s" % name)
if name == self.ROOT_TAG_NAME:
# The BeautifulSoup object itself can never be popped.
return
most_recently_popped = None
stack_size = len(self.tagStack)
for i in range(stack_size - 1, 0, -1):
if not self.open_tag_counter.get(name):
break
t = self.tagStack[i]
if (name == t.name and nsprefix == t.prefix):
if inclusivePop:
most_recently_popped = self.popTag()
break
most_recently_popped = self.popTag()
return most_recently_popped
def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
sourcepos=None, namespaces=None):
"""Called by the tree builder when a new tag is encountered.
:param name: Name of the tag.
:param nsprefix: Namespace prefix for the tag.
:param attrs: A dictionary of attribute values.
:param sourceline: The line number where this tag was found in its
source document.
:param sourcepos: The character position within `sourceline` where this
tag was found.
:param namespaces: A dictionary of all namespace prefix mappings
currently in scope in the document.
If this method returns None, the tag was rejected by an active
SoupStrainer. You should proceed as if the tag had not occurred
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 = self.element_classes.get(Tag, Tag)(
self, self.builder, name, namespace, nsprefix, attrs,
self.currentTag, self._most_recent_element,
sourceline=sourceline, sourcepos=sourcepos,
namespaces=namespaces
)
if tag is None:
return tag
if self._most_recent_element is not None:
self._most_recent_element.next_element = tag
self._most_recent_element = tag
self.pushTag(tag)
return tag
def handle_endtag(self, name, nsprefix=None):
"""Called by the tree builder when an ending tag is encountered.
:param name: Name of the tag.
:param nsprefix: Namespace prefix for the tag.
"""
#print("End tag: " + name)
self.endData()
self._popToTag(name, nsprefix)
def handle_data(self, data):
"""Called by the tree builder when a chunk of textual data is encountered."""
self.current_data.append(data)
def decode(self, pretty_print=False,
eventual_encoding=DEFAULT_OUTPUT_ENCODING,
formatter="minimal"):
"""Returns a string or Unicode representation of the parse tree
as an HTML or XML document.
:param pretty_print: If this is True, indentation will be used to
make the document more readable.
:param eventual_encoding: The encoding of the final document.
If this is None, the document will be a Unicode string.
"""
if self.is_xml:
# Print the XML declaration
encoding_part = ''
if eventual_encoding in PYTHON_SPECIFIC_ENCODINGS:
# This is a special Python encoding; it can't actually
# go into an XML document because it means nothing
# outside of Python.
eventual_encoding = None
if eventual_encoding != None:
encoding_part = ' encoding="%s"' % eventual_encoding
prefix = '<?xml version="1.0"%s?>\n' % encoding_part
else:
prefix = ''
if not pretty_print:
indent_level = None
else:
indent_level = 0
return prefix + super(BeautifulSoup, self).decode(
indent_level, eventual_encoding, formatter)
# Aliases to make it easier to get started quickly, e.g. '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.',
DeprecationWarning
)
super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
class StopParsing(Exception):
"""Exception raised by a TreeBuilder if it's unable to continue parsing."""
pass
class FeatureNotFound(ValueError):
"""Exception raised by the BeautifulSoup constructor if no parser with the
requested features is found.
"""
pass
#If this file is run as a script, act as an HTML pretty-printer.
if __name__ == '__main__':
import sys
soup = BeautifulSoup(sys.stdin)
print((soup.prettify()))

631
Source/Libs/bs4/builder/__init__.py Normal file
View File

@ -0,0 +1,631 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
from collections import defaultdict
import itertools
import re
import warnings
import sys
from ..element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
RubyParenthesisString,
RubyTextString,
Stylesheet,
Script,
TemplateString,
nonwhitespace_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 XMLParsedAsHTMLWarning(UserWarning):
"""The warning issued when an HTML parser is used to parse
XML that is not XHTML.
"""
MESSAGE = """It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor."""
class TreeBuilderRegistry(object):
"""A way of looking up TreeBuilder subclasses by their name or by desired
features.
"""
def __init__(self):
self.builders_for_feature = defaultdict(list)
self.builders = []
def register(self, treebuilder_class):
"""Register a treebuilder based on its advertised features.
:param treebuilder_class: A subclass of Treebuilder. its .features
attribute should list its 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):
"""Look up a TreeBuilder subclass with the desired features.
:param features: A list of features to look for. If none are
provided, the most recently registered TreeBuilder subclass
will be used.
:return: A TreeBuilder subclass, or None if there's no
registered subclass with all the requested 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 textual document into a Beautiful Soup object tree."""
NAME = "[Unknown tree builder]"
ALTERNATE_NAMES = []
features = []
is_xml = False
picklable = False
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.
DEFAULT_CDATA_LIST_ATTRIBUTES = {}
# Whitespace should be preserved inside these tags.
DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
# The textual contents of tags with these names should be
# instantiated with some class other than NavigableString.
DEFAULT_STRING_CONTAINERS = {}
USE_DEFAULT = object()
# Most parsers don't keep track of line numbers.
TRACKS_LINE_NUMBERS = False
def __init__(self, multi_valued_attributes=USE_DEFAULT,
preserve_whitespace_tags=USE_DEFAULT,
store_line_numbers=USE_DEFAULT,
string_containers=USE_DEFAULT,
):
"""Constructor.
:param multi_valued_attributes: If this is set to None, the
TreeBuilder will not turn any values for attributes like
'class' into lists. Setting this to a dictionary will
customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES
for an example.
Internally, these are called "CDATA list attributes", but that
probably doesn't make sense to an end-user, so the argument name
is `multi_valued_attributes`.
:param preserve_whitespace_tags: A list of tags to treat
the way <pre> tags are treated in HTML. Tags in this list
are immune from pretty-printing; their contents will always be
output as-is.
:param string_containers: A dictionary mapping tag names to
the classes that should be instantiated to contain the textual
contents of those tags. The default is to use NavigableString
for every tag, no matter what the name. You can override the
default by changing DEFAULT_STRING_CONTAINERS.
:param store_line_numbers: If the parser keeps track of the
line numbers and positions of the original markup, that
information will, by default, be stored in each corresponding
`Tag` object. You can turn this off by passing
store_line_numbers=False. If the parser you're using doesn't
keep track of this information, then setting store_line_numbers=True
will do nothing.
"""
self.soup = None
if multi_valued_attributes is self.USE_DEFAULT:
multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
self.cdata_list_attributes = multi_valued_attributes
if preserve_whitespace_tags is self.USE_DEFAULT:
preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
self.preserve_whitespace_tags = preserve_whitespace_tags
if store_line_numbers == self.USE_DEFAULT:
store_line_numbers = self.TRACKS_LINE_NUMBERS
self.store_line_numbers = store_line_numbers
if string_containers == self.USE_DEFAULT:
string_containers = self.DEFAULT_STRING_CONTAINERS
self.string_containers = string_containers
def initialize_soup(self, soup):
"""The BeautifulSoup object has been initialized and is now
being associated with the TreeBuilder.
:param soup: A BeautifulSoup object.
"""
self.soup = soup
def reset(self):
"""Do any work necessary to reset the underlying parser
for a new document.
By default, this does nothing.
"""
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/>" or "<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 children.
"<foo></foo>" will become "<foo/>", and "<foo>bar</foo>" will
be left alone.
:param tag_name: The name of a markup tag.
"""
if self.empty_element_tags is None:
return True
return tag_name in self.empty_element_tags
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
This method is not implemented in TreeBuilder; it must be
implemented in subclasses.
:return: None.
"""
raise NotImplementedError()
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding. NOTE: This argument is not used by the
calling code and can probably be removed.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
By default, the only strategy is to parse the markup
as-is. See `LXMLTreeBuilderForXML` and
`HTMLParserTreeBuilder` for implementations that take into
account the quirks of particular parsers.
"""
yield 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.
:param fragment: A string -- fragment of HTML.
:return: A string -- a full HTML document.
"""
return fragment
def set_up_substitutions(self, tag):
"""Set up any substitutions that will need to be performed on
a `Tag` when it's output as a string.
By default, this does nothing. See `HTMLTreeBuilder` for a
case where this is used.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
return False
def _replace_cdata_list_attribute_values(self, tag_name, attrs):
"""When an attribute value is associated with a tag that can
have multiple values for that attribute, convert the string
value to a list of strings.
Basically, replaces class="foo bar" with class=["foo", "bar"]
NOTE: This method modifies its input in place.
:param tag_name: The name of a tag.
:param attrs: A dictionary containing the tag's attributes.
Any appropriate attribute values will be modified 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 list(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, str):
values = nonwhitespace_re.findall(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.
This is not currently used for anything, but it demonstrates
how a simple TreeBuilder would work.
"""
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.
"""
empty_element_tags = set([
# These are from HTML5.
'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
# These are from earlier versions of HTML and are removed in HTML5.
'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
])
# The HTML standard defines these as block-level elements. Beautiful
# Soup does not treat these elements differently from other elements,
# but it may do so eventually, and this information is available if
# you need to use it.
block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
# These HTML tags need special treatment so they can be
# represented by a string class other than NavigableString.
#
# For some of these tags, it's because the HTML standard defines
# an unusual content model for them. I made this list by going
# through the HTML spec
# (https://html.spec.whatwg.org/#metadata-content) and looking for
# "metadata content" elements that can contain strings.
#
# The Ruby tags (<rt> and <rp>) are here despite being normal
# "phrasing content" tags, because the content they contain is
# qualitatively different from other text in the document, and it
# can be useful to be able to distinguish it.
#
# TODO: Arguably <noscript> could go here but it seems
# qualitatively different from the other tags.
DEFAULT_STRING_CONTAINERS = {
'rt' : RubyTextString,
'rp' : RubyParenthesisString,
'style': Stylesheet,
'script': Script,
'template': TemplateString,
}
# 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.
DEFAULT_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"],
}
DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
def set_up_substitutions(self, tag):
"""Replace the declared encoding in a <meta> tag with a placeholder,
to be substituted when the tag is output to a string.
An HTML document may come in to Beautiful Soup as one
encoding, but exit in a different encoding, and the <meta> tag
needs to be changed to reflect this.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
# 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)
class DetectsXMLParsedAsHTML(object):
"""A mixin class for any class (a TreeBuilder, or some class used by a
TreeBuilder) that's in a position to detect whether an XML
document is being incorrectly parsed as HTML, and issue an
appropriate warning.
This requires being able to observe an incoming processing
instruction that might be an XML declaration, and also able to
observe tags as they're opened. If you can't do that for a given
TreeBuilder, there's a less reliable implementation based on
examining the raw markup.
"""
# Regular expression for seeing if markup has an <html> tag.
LOOKS_LIKE_HTML = re.compile("<[^ +]html", re.I)
LOOKS_LIKE_HTML_B = re.compile(b"<[^ +]html", re.I)
XML_PREFIX = '<?xml'
XML_PREFIX_B = b'<?xml'
@classmethod
def warn_if_markup_looks_like_xml(cls, markup):
"""Perform a check on some markup to see if it looks like XML
that's not XHTML. If so, issue a warning.
This is much less reliable than doing the check while parsing,
but some of the tree builders can't do that.
:return: True if the markup looks like non-XHTML XML, False
otherwise.
"""
if isinstance(markup, bytes):
prefix = cls.XML_PREFIX_B
looks_like_html = cls.LOOKS_LIKE_HTML_B
else:
prefix = cls.XML_PREFIX
looks_like_html = cls.LOOKS_LIKE_HTML
if (markup is not None
and markup.startswith(prefix)
and not looks_like_html.search(markup[:500])
):
cls._warn()
return True
return False
@classmethod
def _warn(cls):
"""Issue a warning about XML being parsed as HTML."""
warnings.warn(
XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning
)
def _initialize_xml_detector(self):
"""Call this method before parsing a document."""
self._first_processing_instruction = None
self._root_tag = None
def _document_might_be_xml(self, processing_instruction):
"""Call this method when encountering an XML declaration, or a
"processing instruction" that might be an XML declaration.
"""
if (self._first_processing_instruction is not None
or self._root_tag is not None):
# The document has already started. Don't bother checking
# anymore.
return
self._first_processing_instruction = processing_instruction
# We won't know until we encounter the first tag whether or
# not this is actually a problem.
def _root_tag_encountered(self, name):
"""Call this when you encounter the document's root tag.
This is where we actually check whether an XML document is
being incorrectly parsed as HTML, and issue the warning.
"""
if self._root_tag is not None:
# This method was incorrectly called multiple times. Do
# nothing.
return
self._root_tag = name
if (name != 'html' and self._first_processing_instruction is not None
and self._first_processing_instruction.lower().startswith('xml ')):
# We encountered an XML declaration and then a tag other
# than 'html'. This is a reliable indicator that a
# non-XHTML document is being parsed as XML.
self._warn()
def register_treebuilders_from(module):
"""Copy TreeBuilders from the given module into this module."""
this_module = sys.modules[__name__]
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):
"""An Exception to be raised when the underlying parser simply
refuses to parse the given markup.
"""
def __init__(self, message_or_exception):
"""Explain why the parser rejected the given markup, either
with a textual explanation or another exception.
"""
if isinstance(message_or_exception, Exception):
e = message_or_exception
message_or_exception = "%s: %s" % (e.__class__.__name__, str(e))
super(ParserRejectedMarkup, self).__init__(message_or_exception)
# 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 resort.
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

473
Source/Libs/bs4/builder/_html5lib.py Normal file
View File

@ -0,0 +1,473 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTML5TreeBuilder',
]
import warnings
import re
from bs4.builder import (
DetectsXMLParsedAsHTML,
PERMISSIVE,
HTML,
HTML_5,
HTMLTreeBuilder,
)
from bs4.element import (
NamespacedAttribute,
nonwhitespace_re,
)
import html5lib
from html5lib.constants import (
namespaces,
prefixes,
)
from bs4.element import (
Comment,
Doctype,
NavigableString,
Tag,
)
try:
# Pre-0.99999999
from html5lib.treebuilders import _base as treebuilder_base
new_html5lib = False
except ImportError as e:
# 0.99999999 and up
from html5lib.treebuilders import base as treebuilder_base
new_html5lib = True
class HTML5TreeBuilder(HTMLTreeBuilder):
"""Use html5lib to build a tree.
Note that this TreeBuilder does not support some features common
to HTML TreeBuilders. Some of these features could theoretically
be implemented, but at the very least it's quite difficult,
because html5lib moves the parse tree around as it's being built.
* This TreeBuilder doesn't use different subclasses of NavigableString
based on the name of the tag in which the string was found.
* You can't use a SoupStrainer to parse only part of a document.
"""
NAME = "html5lib"
features = [NAME, PERMISSIVE, HTML_5, HTML]
# html5lib can tell us which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def prepare_markup(self, markup, user_specified_encoding,
document_declared_encoding=None, exclude_encodings=None):
# Store the user-specified encoding for use later on.
self.user_specified_encoding = user_specified_encoding
# document_declared_encoding and exclude_encodings aren't used
# ATM because the html5lib TreeBuilder doesn't use
# UnicodeDammit.
if exclude_encodings:
warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
# html5lib only parses HTML, so if it's given XML that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
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)
self.underlying_builder.parser = parser
extra_kwargs = dict()
if not isinstance(markup, str):
if new_html5lib:
extra_kwargs['override_encoding'] = self.user_specified_encoding
else:
extra_kwargs['encoding'] = self.user_specified_encoding
doc = parser.parse(markup, **extra_kwargs)
# Set the character encoding detected by the tokenizer.
if isinstance(markup, str):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
else:
original_encoding = parser.tokenizer.stream.charEncoding[0]
if not isinstance(original_encoding, str):
# In 0.99999999 and up, the encoding is an html5lib
# Encoding object. We want to use a string for compatibility
# with other tree builders.
original_encoding = original_encoding.name
doc.original_encoding = original_encoding
self.underlying_builder.parser = None
def create_treebuilder(self, namespaceHTMLElements):
self.underlying_builder = TreeBuilderForHtml5lib(
namespaceHTMLElements, self.soup,
store_line_numbers=self.store_line_numbers
)
return self.underlying_builder
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
def __init__(self, namespaceHTMLElements, soup=None,
store_line_numbers=True, **kwargs):
if soup:
self.soup = soup
else:
from bs4 import BeautifulSoup
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup(
"", "html.parser", store_line_numbers=store_line_numbers,
**kwargs
)
# TODO: What are **kwargs exactly? Should they be passed in
# here in addition to/instead of being passed to the BeautifulSoup
# constructor?
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
# This will be set later to an html5lib.html5parser.HTMLParser
# object, which we can use to track the current line number.
self.parser = None
self.store_line_numbers = store_line_numbers
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):
kwargs = {}
if self.parser and self.store_line_numbers:
# This represents the point immediately after the end of the
# tag. We don't know when the tag started, but we do know
# where it ended -- the character just before this one.
sourceline, sourcepos = self.parser.tokenizer.stream.position()
kwargs['sourceline'] = sourceline
kwargs['sourcepos'] = sourcepos-1
tag = self.soup.new_tag(name, namespace, **kwargs)
return Element(tag, self.soup, namespace)
def commentClass(self, data):
return TextNode(Comment(data), self.soup)
def fragmentClass(self):
from bs4 import BeautifulSoup
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup("", "html.parser")
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 treebuilder_base.TreeBuilder.getFragment(self).element
def testSerializer(self, element):
from bs4 import BeautifulSoup
rv = []
doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
def serializeElement(element, indent=0):
if isinstance(element, BeautifulSoup):
pass
if isinstance(element, Doctype):
m = doctype_re.match(element)
if m:
name = m.group(1)
if m.lastindex > 1:
publicId = m.group(2) or ""
systemId = m.group(3) or m.group(4) or ""
rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
(' ' * indent, name, publicId, systemId))
else:
rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
else:
rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
elif isinstance(element, Comment):
rv.append("|%s<!-- %s -->" % (' ' * indent, element))
elif isinstance(element, NavigableString):
rv.append("|%s\"%s\"" % (' ' * indent, element))
else:
if element.namespace:
name = "%s %s" % (prefixes[element.namespace],
element.name)
else:
name = element.name
rv.append("|%s<%s>" % (' ' * indent, name))
if element.attrs:
attributes = []
for name, value in list(element.attrs.items()):
if isinstance(name, NamespacedAttribute):
name = "%s %s" % (prefixes[name.namespace], name.name)
if isinstance(value, list):
value = " ".join(value)
attributes.append((name, value))
for name, value in sorted(attributes):
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
indent += 2
for child in element.children:
serializeElement(child, indent)
serializeElement(element, 0)
return "\n".join(rv)
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):
# If this attribute is a multi-valued attribute for this element,
# turn its value into a list.
list_attr = self.element.cdata_list_attributes or {}
if (name in list_attr.get('*')
or (self.element.name in list_attr
and name in list_attr[self.element.name])):
# A node that is being cloned may have already undergone
# this procedure.
if not isinstance(value, list):
value = nonwhitespace_re.findall(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(treebuilder_base.Node):
def __init__(self, element, soup, namespace):
treebuilder_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, str):
# 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
node.parent = self
else:
child = node.element
node.parent = self
if not isinstance(child, str) and child.parent is not None:
node.element.extract()
if (string_child is not None 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, str):
# 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)
elif self.element.next_element is not None:
# Something from further ahead in the parse tree is
# being inserted into this earlier element. This is
# very annoying because it means an expensive search
# for the last element in the tree.
most_recent_element = self.soup._last_descendant()
else:
most_recent_element = self.element
self.soup.object_was_parsed(
child, parent=self.element,
most_recent_element=most_recent_element)
def getAttributes(self):
if isinstance(self.element, Comment):
return {}
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 list(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):
text = TextNode(self.soup.new_string(data), self.soup)
if insertBefore:
self.insertBefore(text, insertBefore)
else:
self.appendChild(text)
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."""
# print("MOVE", self.element.contents)
# print("FROM", self.element)
# print("TO", new_parent.element)
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
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]
if new_parents_last_descendant is not None:
first_child.previous_element = new_parents_last_descendant
else:
first_child.previous_element = new_parent_element
first_child.previous_sibling = new_parents_last_child
if new_parents_last_descendant is not None:
new_parents_last_descendant.next_element = first_child
else:
new_parent_element.next_element = first_child
if new_parents_last_child is not None:
new_parents_last_child.next_sibling = first_child
# Find the very last element being moved. It is now the
# parent's last descendant. It has no .next_sibling and
# its .next_element is whatever the previous last
# descendant had.
last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
if new_parents_last_descendant_next_element is not None:
# TODO: This code has no test coverage and I'm not sure
# how to get html5lib to go through this path, but it's
# just the other side of the previous line.
new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
last_childs_last_descendant.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
# print("DONE WITH MOVE")
# print("FROM", self.element)
# print("TO", new_parent_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):
treebuilder_base.Node.__init__(self, None)
self.element = element
self.soup = soup
def cloneNode(self):
raise NotImplementedError

499
Source/Libs/bs4/builder/_htmlparser.py Normal file
View File

@ -0,0 +1,499 @@
# encoding: utf-8
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTMLParserTreeBuilder',
]
from html.parser import HTMLParser
try:
from html.parser import HTMLParseError
except ImportError as e:
# HTMLParseError is removed in Python 3.5. Since it can never be
# thrown in 3.5, we can just define our own class as a placeholder.
class HTMLParseError(Exception):
pass
import sys
import warnings
# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
# argument, which we'd like to set to False. Unfortunately,
# http://bugs.python.org/issue13273 makes strict=True a better bet
# before Python 3.2.3.
#
# At the end of this file, we monkeypatch HTMLParser so that
# strict=True works well on Python 3.2.2.
major, minor, release = sys.version_info[:3]
CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
from ..element import (
CData,
Comment,
Declaration,
Doctype,
ProcessingInstruction,
)
from ..dammit import EntitySubstitution, UnicodeDammit
from ..builder import (
DetectsXMLParsedAsHTML,
HTML,
HTMLTreeBuilder,
STRICT,
)
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser, DetectsXMLParsedAsHTML):
"""A subclass of the Python standard library's HTMLParser class, which
listens for HTMLParser events and translates them into calls
to Beautiful Soup's tree construction API.
"""
# Strategies for handling duplicate attributes
IGNORE = 'ignore'
REPLACE = 'replace'
def __init__(self, *args, **kwargs):
"""Constructor.
:param on_duplicate_attribute: A strategy for what to do if a
tag includes the same attribute more than once. Accepted
values are: REPLACE (replace earlier values with later
ones, the default), IGNORE (keep the earliest value
encountered), or a callable. A callable must take three
arguments: the dictionary of attributes already processed,
the name of the duplicate attribute, and the most recent value
encountered.
"""
self.on_duplicate_attribute = kwargs.pop(
'on_duplicate_attribute', self.REPLACE
)
HTMLParser.__init__(self, *args, **kwargs)
# Keep a list of empty-element tags that were encountered
# without an explicit closing tag. If we encounter a closing tag
# of this type, we'll associate it with one of those entries.
#
# This isn't a stack because we don't care about the
# order. It's a list of closing tags we've already handled and
# will ignore, assuming they ever show up.
self.already_closed_empty_element = []
self._initialize_xml_detector()
def error(self, msg):
"""In Python 3, HTMLParser subclasses must implement error(), although
this requirement doesn't appear to be documented.
In Python 2, HTMLParser implements error() by raising an exception,
which we don't want to do.
In any event, this method is called only on very strange
markup and our best strategy is to pretend it didn't happen
and keep going.
"""
warnings.warn(msg)
def handle_startendtag(self, name, attrs):
"""Handle an incoming empty-element tag.
This is only called when the markup looks like <tag/>.
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
"""
# is_startend() tells handle_starttag not to close the tag
# just because its name matches a known empty-element tag. We
# know that this is an empty-element tag and we want to call
# handle_endtag ourselves.
tag = self.handle_starttag(name, attrs, handle_empty_element=False)
self.handle_endtag(name)
def handle_starttag(self, name, attrs, handle_empty_element=True):
"""Handle an opening tag, e.g. '<tag>'
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
:param handle_empty_element: True if this tag is known to be
an empty-element tag (i.e. there is not expected to be any
closing tag).
"""
# 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 = ''
if key in attr_dict:
# A single attribute shows up multiple times in this
# tag. How to handle it depends on the
# on_duplicate_attribute setting.
on_dupe = self.on_duplicate_attribute
if on_dupe == self.IGNORE:
pass
elif on_dupe in (None, self.REPLACE):
attr_dict[key] = value
else:
on_dupe(attr_dict, key, value)
else:
attr_dict[key] = value
attrvalue = '""'
#print("START", name)
sourceline, sourcepos = self.getpos()
tag = self.soup.handle_starttag(
name, None, None, attr_dict, sourceline=sourceline,
sourcepos=sourcepos
)
if tag and tag.is_empty_element and handle_empty_element:
# Unlike other parsers, html.parser doesn't send separate end tag
# events for empty-element tags. (It's handled in
# handle_startendtag, but only if the original markup looked like
# <tag/>.)
#
# So we need to call handle_endtag() ourselves. Since we
# know the start event is identical to the end event, we
# don't want handle_endtag() to cross off any previous end
# events for tags of this name.
self.handle_endtag(name, check_already_closed=False)
# But we might encounter an explicit closing tag for this tag
# later on. If so, we want to ignore it.
self.already_closed_empty_element.append(name)
if self._root_tag is None:
self._root_tag_encountered(name)
def handle_endtag(self, name, check_already_closed=True):
"""Handle a closing tag, e.g. '</tag>'
:param name: A tag name.
:param check_already_closed: True if this tag is expected to
be the closing portion of an empty-element tag,
e.g. '<tag></tag>'.
"""
#print("END", name)
if check_already_closed and name in self.already_closed_empty_element:
# This is a redundant end tag for an empty-element tag.
# We've already called handle_endtag() for it, so just
# check it off the list.
#print("ALREADY CLOSED", name)
self.already_closed_empty_element.remove(name)
else:
self.soup.handle_endtag(name)
def handle_data(self, data):
"""Handle some textual data that shows up between tags."""
self.soup.handle_data(data)
def handle_charref(self, name):
"""Handle a numeric character reference by converting it to the
corresponding Unicode character and treating it as textual
data.
:param name: Character number, possibly in hexadecimal.
"""
# XXX workaround for a bug in HTMLParser. Remove this once
# it's fixed in all supported versions.
# http://bugs.python.org/issue13633
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)
data = None
if real_name < 256:
# HTML numeric entities are supposed to reference Unicode
# code points, but sometimes they reference code points in
# some other encoding (ahem, Windows-1252). E.g. &#147;
# instead of &#201; for LEFT DOUBLE QUOTATION MARK. This
# code tries to detect this situation and compensate.
for encoding in (self.soup.original_encoding, 'windows-1252'):
if not encoding:
continue
try:
data = bytearray([real_name]).decode(encoding)
except UnicodeDecodeError as e:
pass
if not data:
try:
data = chr(real_name)
except (ValueError, OverflowError) as e:
pass
data = data or "\N{REPLACEMENT CHARACTER}"
self.handle_data(data)
def handle_entityref(self, name):
"""Handle a named entity reference by converting it to the
corresponding Unicode character(s) and treating it as textual
data.
:param name: Name of the entity reference.
"""
character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
if character is not None:
data = character
else:
# If this were XML, it would be ambiguous whether "&foo"
# was an character entity reference with a missing
# semicolon or the literal string "&foo". Since this is
# HTML, we have a complete list of all character entity references,
# and this one wasn't found, so assume it's the literal string "&foo".
data = "&%s" % name
self.handle_data(data)
def handle_comment(self, data):
"""Handle an HTML comment.
:param data: The text of the comment.
"""
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(Comment)
def handle_decl(self, data):
"""Handle a DOCTYPE declaration.
:param data: The text of the declaration.
"""
self.soup.endData()
data = data[len("DOCTYPE "):]
self.soup.handle_data(data)
self.soup.endData(Doctype)
def unknown_decl(self, data):
"""Handle a declaration of unknown type -- probably a CDATA block.
:param data: The text of the declaration.
"""
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):
"""Handle a processing instruction.
:param data: The text of the instruction.
"""
self.soup.endData()
self.soup.handle_data(data)
self._document_might_be_xml(data)
self.soup.endData(ProcessingInstruction)
class HTMLParserTreeBuilder(HTMLTreeBuilder):
"""A Beautiful soup `TreeBuilder` that uses the `HTMLParser` parser,
found in the Python standard library.
"""
is_xml = False
picklable = True
NAME = HTMLPARSER
features = [NAME, HTML, STRICT]
# The html.parser knows which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def __init__(self, parser_args=None, parser_kwargs=None, **kwargs):
"""Constructor.
:param parser_args: Positional arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param parser_kwargs: Keyword arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param kwargs: Keyword arguments for the superclass constructor.
"""
# Some keyword arguments will be pulled out of kwargs and placed
# into parser_kwargs.
extra_parser_kwargs = dict()
for arg in ('on_duplicate_attribute',):
if arg in kwargs:
value = kwargs.pop(arg)
extra_parser_kwargs[arg] = value
super(HTMLParserTreeBuilder, self).__init__(**kwargs)
parser_args = parser_args or []
parser_kwargs = parser_kwargs or {}
parser_kwargs.update(extra_parser_kwargs)
if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
parser_kwargs['strict'] = False
if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
parser_kwargs['convert_charrefs'] = False
self.parser_args = (parser_args, parser_kwargs)
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
if isinstance(markup, str):
# Parse Unicode as-is.
yield (markup, None, None, False)
return
# Ask UnicodeDammit to sniff the most likely encoding.
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(
markup,
known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings,
is_html=True,
exclude_encodings=exclude_encodings
)
yield (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
"""
args, kwargs = self.parser_args
parser = BeautifulSoupHTMLParser(*args, **kwargs)
parser.soup = self.soup
try:
parser.feed(markup)
parser.close()
except HTMLParseError as e:
warnings.warn(RuntimeWarning(
"Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
raise e
parser.already_closed_empty_element = []
# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
# string.
#
# XXX This code can be removed once most Python 3 users are on 3.2.3.
if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
import re
attrfind_tolerant = re.compile(
r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
""", re.VERBOSE)
BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
from html.parser import tagfind, attrfind
def parse_starttag(self, i):
self.__starttag_text = None
endpos = self.check_for_whole_start_tag(i)
if endpos < 0:
return endpos
rawdata = self.rawdata
self.__starttag_text = rawdata[i:endpos]
# Now parse the data between i+1 and j into a tag and attrs
attrs = []
match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
self.lasttag = tag = rawdata[i+1:k].lower()
while k < endpos:
if self.strict:
m = attrfind.match(rawdata, k)
else:
m = attrfind_tolerant.match(rawdata, k)
if not m:
break
attrname, rest, attrvalue = m.group(1, 2, 3)
if not rest:
attrvalue = None
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1]
if attrvalue:
attrvalue = self.unescape(attrvalue)
attrs.append((attrname.lower(), attrvalue))
k = m.end()
end = rawdata[k:endpos].strip()
if end not in (">", "/>"):
lineno, offset = self.getpos()
if "\n" in self.__starttag_text:
lineno = lineno + self.__starttag_text.count("\n")
offset = len(self.__starttag_text) \
- self.__starttag_text.rfind("\n")
else:
offset = offset + len(self.__starttag_text)
if self.strict:
self.error("junk characters in start tag: %r"
% (rawdata[k:endpos][:20],))
self.handle_data(rawdata[i:endpos])
return endpos
if end.endswith('/>'):
# XHTML-style empty tag: <span attr="value" />
self.handle_startendtag(tag, attrs)
else:
self.handle_starttag(tag, attrs)
if tag in self.CDATA_CONTENT_ELEMENTS:
self.set_cdata_mode(tag)
return endpos
def set_cdata_mode(self, elem):
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
BeautifulSoupHTMLParser.parse_starttag = parse_starttag
BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
CONSTRUCTOR_TAKES_STRICT = True

386
Source/Libs/bs4/builder/_lxml.py Normal file
View File

@ -0,0 +1,386 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
]
try:
from collections.abc import Callable # Python 3.6
except ImportError as e:
from collections import Callable
from io import BytesIO
from io import StringIO
from lxml import etree
from bs4.element import (
Comment,
Doctype,
NamespacedAttribute,
ProcessingInstruction,
XMLProcessingInstruction,
)
from bs4.builder import (
DetectsXMLParsedAsHTML,
FAST,
HTML,
HTMLTreeBuilder,
PERMISSIVE,
ParserRejectedMarkup,
TreeBuilder,
XML)
from bs4.dammit import EncodingDetector
LXML = 'lxml'
def _invert(d):
"Invert a dictionary."
return dict((v,k) for k, v in list(d.items()))
class LXMLTreeBuilderForXML(TreeBuilder):
DEFAULT_PARSER_CLASS = etree.XMLParser
is_xml = True
processing_instruction_class = XMLProcessingInstruction
NAME = "lxml-xml"
ALTERNATE_NAMES = ["xml"]
# Well, it's permissive by XML parser standards.
features = [NAME, LXML, XML, FAST, PERMISSIVE]
CHUNK_SIZE = 512
# This namespace mapping is specified in the XML Namespace
# standard.
DEFAULT_NSMAPS = dict(xml='http://www.w3.org/XML/1998/namespace')
DEFAULT_NSMAPS_INVERTED = _invert(DEFAULT_NSMAPS)
# NOTE: If we parsed Element objects and looked at .sourceline,
# we'd be able to see the line numbers from the original document.
# But instead we build an XMLParser or HTMLParser object to serve
# as the target of parse messages, and those messages don't include
# line numbers.
# See: https://bugs.launchpad.net/lxml/+bug/1846906
def initialize_soup(self, soup):
"""Let the BeautifulSoup object know about the standard namespace
mapping.
:param soup: A `BeautifulSoup`.
"""
super(LXMLTreeBuilderForXML, self).initialize_soup(soup)
self._register_namespaces(self.DEFAULT_NSMAPS)
def _register_namespaces(self, mapping):
"""Let the BeautifulSoup object know about namespaces encountered
while parsing the document.
This might be useful later on when creating CSS selectors.
This will track (almost) all namespaces, even ones that were
only in scope for part of the document. If two namespaces have
the same prefix, only the first one encountered will be
tracked. Un-prefixed namespaces are not tracked.
:param mapping: A dictionary mapping namespace prefixes to URIs.
"""
for key, value in list(mapping.items()):
# This is 'if key' and not 'if key is not None' because we
# don't track un-prefixed namespaces. Soupselect will
# treat an un-prefixed namespace as the default, which
# causes confusion in some cases.
if key and key not in self.soup._namespaces:
# Let the BeautifulSoup object know about a new namespace.
# If there are multiple namespaces defined with the same
# prefix, the first one in the document takes precedence.
self.soup._namespaces[key] = value
def default_parser(self, encoding):
"""Find the default parser for the given encoding.
:param encoding: A string.
:return: Either 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):
"""Instantiate an appropriate parser for the given encoding.
:param encoding: A string.
:return: A parser object such as an `etree.XMLParser`.
"""
# Use the default parser.
parser = self.default_parser(encoding)
if isinstance(parser, Callable):
# Instantiate the parser with default arguments
parser = parser(
target=self, strip_cdata=False, recover=True, encoding=encoding
)
return parser
def __init__(self, parser=None, empty_element_tags=None, **kwargs):
# 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_INVERTED]
self.active_namespace_prefixes = [dict(self.DEFAULT_NSMAPS)]
super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
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,
exclude_encodings=None,
document_declared_encoding=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
lxml really wants to get a bytestring and convert it to
Unicode itself. So instead of using UnicodeDammit to convert
the bytestring to Unicode using different encodings, this
implementation uses EncodingDetector to iterate over the
encodings, and tell lxml to try to parse the document as each
one in turn.
:param markup: Some markup -- hopefully a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
is_html = not self.is_xml
if is_html:
self.processing_instruction_class = ProcessingInstruction
# We're in HTML mode, so if we're given XML, that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
else:
self.processing_instruction_class = XMLProcessingInstruction
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
# TODO: This is a workaround for
# https://bugs.launchpad.net/lxml/+bug/1948551.
# We can remove it once the upstream issue is fixed.
if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}':
markup = markup[1:]
yield markup, None, document_declared_encoding, False
if isinstance(markup, str):
# 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)
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
detector = EncodingDetector(
markup, known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings, is_html=is_html,
exclude_encodings=exclude_encodings
)
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, str):
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) as e:
raise ParserRejectedMarkup(e)
def close(self):
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
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(nsmap) == 0 and 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.
# First, Let the BeautifulSoup object know about it.
self._register_namespaces(nsmap)
# Then, add it to our running list of inverted namespace
# mappings.
self.nsmaps.append(_invert(nsmap))
# The currently active namespace prefixes have
# changed. Calculate the new mapping so it can be stored
# with all Tag objects created while these prefixes are in
# scope.
current_mapping = dict(self.active_namespace_prefixes[-1])
current_mapping.update(nsmap)
# We should not track un-prefixed namespaces as we can only hold one
# and it will be recognized as the default namespace by soupsieve,
# which may be confusing in some situations.
if '' in current_mapping:
del current_mapping['']
self.active_namespace_prefixes.append(current_mapping)
# 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 list(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 list(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,
namespaces=self.active_namespace_prefixes[-1]
)
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.
out_of_scope_nsmap = self.nsmaps.pop()
if out_of_scope_nsmap is not None:
# This tag introduced a namespace mapping which is no
# longer in scope. Recalculate the currently active
# namespace prefixes.
self.active_namespace_prefixes.pop()
def pi(self, target, data):
self.soup.endData()
data = target + ' ' + data
self.soup.handle_data(data)
self.soup.endData(self.processing_instruction_class)
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 '<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
NAME = LXML
ALTERNATE_NAMES = ["lxml-html"]
features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
is_xml = False
processing_instruction_class = ProcessingInstruction
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) as e:
raise ParserRejectedMarkup(e)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<html><body>%s</body></html>' % fragment

1095
Source/Libs/bs4/dammit.py Normal file
View File

File diff suppressed because it is too large Load Diff

248
Source/Libs/bs4/diagnose.py Normal file
View File

@ -0,0 +1,248 @@
"""Diagnostic functions, mainly for use when doing tech support."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
import cProfile
from io import BytesIO
from html.parser 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.
:param data: A string containing markup that needs to be explained.
:return: None; diagnostics are printed to standard output.
"""
print(("Diagnostic running on Beautiful Soup %s" % __version__))
print(("Python version %s" % sys.version))
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append("lxml-xml")
try:
from lxml import etree
print(("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))))
except ImportError as e:
print(
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print(("Found html5lib version %s" % html5lib.__version__))
except ImportError as e:
print(
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = 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
else:
try:
if os.path.exists(data):
print(('"%s" looks like a filename. Reading data from the file.' % data))
with open(data) as fp:
data = fp.read()
except ValueError:
# This can happen on some platforms when the 'filename' is
# too long. Assume it's data and not a filename.
pass
print("")
for parser in basic_parsers:
print(("Trying to parse your markup with %s" % parser))
success = False
try:
soup = BeautifulSoup(data, features=parser)
success = True
except Exception as 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. You can use this to determine whether
an lxml-specific problem is in Beautiful Soup's lxml tree builders
or in lxml itself.
:param data: Some markup.
:param html: If True, markup will be parsed with lxml's HTML parser.
if False, lxml's XML parser will be used.
"""
from lxml import etree
recover = kwargs.pop('recover', True)
if isinstance(data, str):
data = data.encode("utf8")
reader = BytesIO(data)
for event, element in etree.iterparse(
reader, html=html, recover=recover, **kwargs
):
print(("%s, %4s, %s" % (event, element.tag, element.text)))
class AnnouncingParser(HTMLParser):
"""Subclass of HTMLParser that announces parse events, without doing
anything else.
You can use this to get a picture of how html.parser sees a given
document. The easiest way to do this is to call `htmlparser_trace`.
"""
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.
:param data: Some markup.
"""
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 as 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"):
"""Use Python's profiler on a randomly generated document."""
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 this file is run as a script, standard input is diagnosed.
if __name__ == '__main__':
diagnose(sys.stdin.read())

2291
Source/Libs/bs4/element.py Normal file
View File

File diff suppressed because it is too large Load Diff

185
Source/Libs/bs4/formatter.py Normal file
View File

@ -0,0 +1,185 @@
from .dammit import EntitySubstitution
class Formatter(EntitySubstitution):
"""Describes a strategy to use when outputting a parse tree to a string.
Some parts of this strategy come from the distinction between
HTML4, HTML5, and XML. Others are configurable by the user.
Formatters are passed in as the `formatter` argument to methods
like `PageElement.encode`. Most people won't need to think about
formatters, and most people who need to think about them can pass
in one of these predefined strings as `formatter` rather than
making a new Formatter object:
For HTML documents:
* 'html' - HTML entity substitution for generic HTML documents. (default)
* 'html5' - HTML entity substitution for HTML5 documents, as
well as some optimizations in the way tags are rendered.
* 'minimal' - Only make the substitutions necessary to guarantee
valid HTML.
* None - Do not perform any substitution. This will be faster
but may result in invalid markup.
For XML documents:
* 'html' - Entity substitution for XHTML documents.
* 'minimal' - Only make the substitutions necessary to guarantee
valid XML. (default)
* None - Do not perform any substitution. This will be faster
but may result in invalid markup.
"""
# Registries of XML and HTML formatters.
XML_FORMATTERS = {}
HTML_FORMATTERS = {}
HTML = 'html'
XML = 'xml'
HTML_DEFAULTS = dict(
cdata_containing_tags=set(["script", "style"]),
)
def _default(self, language, value, kwarg):
if value is not None:
return value
if language == self.XML:
return set()
return self.HTML_DEFAULTS[kwarg]
def __init__(
self, language=None, entity_substitution=None,
void_element_close_prefix='/', cdata_containing_tags=None,
empty_attributes_are_booleans=False, indent=1,
):
"""Constructor.
:param language: This should be Formatter.XML if you are formatting
XML markup and Formatter.HTML if you are formatting HTML markup.
:param entity_substitution: A function to call to replace special
characters with XML/HTML entities. For examples, see
bs4.dammit.EntitySubstitution.substitute_html and substitute_xml.
:param void_element_close_prefix: By default, void elements
are represented as <tag/> (XML rules) rather than <tag>
(HTML rules). To get <tag>, pass in the empty string.
:param cdata_containing_tags: The list of tags that are defined
as containing CDATA in this dialect. For example, in HTML,
<script> and <style> tags are defined as containing CDATA,
and their contents should not be formatted.
:param blank_attributes_are_booleans: Render attributes whose value
is the empty string as HTML-style boolean attributes.
(Attributes whose value is None are always rendered this way.)
:param indent: If indent is a non-negative integer or string,
then the contents of elements will be indented
appropriately when pretty-printing. An indent level of 0,
negative, or "" will only insert newlines. Using a
positive integer indent indents that many spaces per
level. If indent is a string (such as "\t"), that string
is used to indent each level. The default behavior to
indent one space per level.
"""
self.language = language
self.entity_substitution = entity_substitution
self.void_element_close_prefix = void_element_close_prefix
self.cdata_containing_tags = self._default(
language, cdata_containing_tags, 'cdata_containing_tags'
)
self.empty_attributes_are_booleans=empty_attributes_are_booleans
if indent is None:
indent = 0
if isinstance(indent, int):
if indent < 0:
indent = 0
indent = ' ' * indent
elif isinstance(indent, str):
indent = indent
else:
indent = ' '
self.indent = indent
def substitute(self, ns):
"""Process a string that needs to undergo entity substitution.
This may be a string encountered in an attribute value or as
text.
:param ns: A string.
:return: A string with certain characters replaced by named
or numeric entities.
"""
if not self.entity_substitution:
return ns
from .element import NavigableString
if (isinstance(ns, NavigableString)
and ns.parent is not None
and ns.parent.name in self.cdata_containing_tags):
# Do nothing.
return ns
# Substitute.
return self.entity_substitution(ns)
def attribute_value(self, value):
"""Process the value of an attribute.
:param ns: A string.
:return: A string with certain characters replaced by named
or numeric entities.
"""
return self.substitute(value)
def attributes(self, tag):
"""Reorder a tag's attributes however you want.
By default, attributes are sorted alphabetically. This makes
behavior consistent between Python 2 and Python 3, and preserves
backwards compatibility with older versions of Beautiful Soup.
If `empty_boolean_attributes` is True, then attributes whose
values are set to the empty string will be treated as boolean
attributes.
"""
if tag.attrs is None:
return []
return sorted(
(k, (None if self.empty_attributes_are_booleans and v == '' else v))
for k, v in list(tag.attrs.items())
)
class HTMLFormatter(Formatter):
"""A generic Formatter for HTML."""
REGISTRY = {}
def __init__(self, *args, **kwargs):
return super(HTMLFormatter, self).__init__(self.HTML, *args, **kwargs)
class XMLFormatter(Formatter):
"""A generic Formatter for XML."""
REGISTRY = {}
def __init__(self, *args, **kwargs):
return super(XMLFormatter, self).__init__(self.XML, *args, **kwargs)
# Set up aliases for the default formatters.
HTMLFormatter.REGISTRY['html'] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_html
)
HTMLFormatter.REGISTRY["html5"] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_html,
void_element_close_prefix=None,
empty_attributes_are_booleans=True,
)
HTMLFormatter.REGISTRY["minimal"] = HTMLFormatter(
entity_substitution=EntitySubstitution.substitute_xml
)
HTMLFormatter.REGISTRY[None] = HTMLFormatter(
entity_substitution=None
)
XMLFormatter.REGISTRY["html"] = XMLFormatter(
entity_substitution=EntitySubstitution.substitute_html
)
XMLFormatter.REGISTRY["minimal"] = XMLFormatter(
entity_substitution=EntitySubstitution.substitute_xml
)
XMLFormatter.REGISTRY[None] = Formatter(
Formatter(Formatter.XML, entity_substitution=None)
)

1191
Source/Libs/bs4/tests/__init__.py Normal file
View File

File diff suppressed because it is too large Load Diff

29
Source/Libs/bs4/tests/test_builder.py Normal file
View File

@ -0,0 +1,29 @@
import pytest
from unittest.mock import patch
from bs4.builder import DetectsXMLParsedAsHTML
class TestDetectsXMLParsedAsHTML(object):
@pytest.mark.parametrize(
"markup,looks_like_xml",
[("No xml declaration", False),
("<html>obviously HTML</html", False),
("<?xml ><html>Actually XHTML</html>", False),
("<?xml> < html>Tricky XHTML</html>", False),
("<?xml ><no-html-tag>", True),
]
)
def test_warn_if_markup_looks_like_xml(self, markup, looks_like_xml):
# Test of our ability to guess at whether markup looks XML-ish
# _and_ not HTML-ish.
with patch('bs4.builder.DetectsXMLParsedAsHTML._warn') as mock:
for data in markup, markup.encode('utf8'):
result = DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
data
)
assert result == looks_like_xml
if looks_like_xml:
assert mock.called
else:
assert not mock.called
mock.reset_mock()

136
Source/Libs/bs4/tests/test_builder_registry.py Normal file
View File

@ -0,0 +1,136 @@
"""Tests of the builder registry."""
import pytest
import warnings
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 TestBuiltInRegistry(object):
"""Test the built-in registry with the default builders registered."""
def test_combination(self):
assert registry.lookup('strict', 'html') == HTMLParserTreeBuilder
if LXML_PRESENT:
assert registry.lookup('fast', 'html') == LXMLTreeBuilder
assert registry.lookup('permissive', 'xml') == LXMLTreeBuilderForXML
if HTML5LIB_PRESENT:
assert registry.lookup('html5lib', 'html') == HTML5TreeBuilder
def test_lookup_by_markup_type(self):
if LXML_PRESENT:
assert registry.lookup('html') == LXMLTreeBuilder
assert registry.lookup('xml') == LXMLTreeBuilderForXML
else:
assert registry.lookup('xml') == None
if HTML5LIB_PRESENT:
assert registry.lookup('html') == HTML5TreeBuilder
else:
assert registry.lookup('html') == HTMLParserTreeBuilder
def test_named_library(self):
if LXML_PRESENT:
assert registry.lookup('lxml', 'xml') == LXMLTreeBuilderForXML
assert registry.lookup('lxml', 'html') == LXMLTreeBuilder
if HTML5LIB_PRESENT:
assert registry.lookup('html5lib') == HTML5TreeBuilder
assert registry.lookup('html.parser') == HTMLParserTreeBuilder
def test_beautifulsoup_constructor_does_lookup(self):
with warnings.catch_warnings(record=True) as w:
# This will create a warning about not explicitly
# specifying a parser, but we'll ignore it.
# You can pass in a string.
BeautifulSoup("", features="html")
# Or a list of strings.
BeautifulSoup("", features=["html", "fast"])
pass
# You'll get an exception if BS can't find an appropriate
# builder.
with pytest.raises(ValueError):
BeautifulSoup("", features="no-such-feature")
class TestRegistry(object):
"""Test the TreeBuilderRegistry class in general."""
def setup_method(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.
assert self.registry.lookup('foo') is None
# But you can find it by doing a lookup with no features, if
# this happens to be the only registered builder.
assert self.registry.lookup() == builder
def test_register_with_features_makes_lookup_succeed(self):
builder = self.builder_for_features('foo', 'bar')
assert self.registry.lookup('foo') is builder
assert self.registry.lookup('bar') is builder
def test_lookup_fails_when_no_builder_implements_feature(self):
builder = self.builder_for_features('foo', 'bar')
assert self.registry.lookup('baz') is 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')
assert self.registry.lookup() == builder2
def test_lookup_fails_when_no_tree_builders_registered(self):
assert self.registry.lookup() is 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.
assert self.registry.lookup('foo', 'bar') == has_both_late
# There is only one builder featuring 'foo', 'bar', and 'baz'.
assert 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')
assert self.registry.lookup('bar', 'baz') is None

371
Source/Libs/bs4/tests/test_dammit.py Normal file
View File

@ -0,0 +1,371 @@
# encoding: utf-8
import pytest
import logging
import bs4
from bs4 import BeautifulSoup
from bs4.dammit import (
EntitySubstitution,
EncodingDetector,
UnicodeDammit,
)
class TestUnicodeDammit(object):
"""Standalone tests of UnicodeDammit."""
def test_unicode_input(self):
markup = "I'm already Unicode! \N{SNOWMAN}"
dammit = UnicodeDammit(markup)
assert dammit.unicode_markup == markup
def test_smart_quotes_to_unicode(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup)
assert dammit.unicode_markup == "<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")
assert dammit.unicode_markup == "<foo>&#x2018;&#x2019;&#x201C;&#x201D;</foo>"
def test_smart_quotes_to_html_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="html")
assert dammit.unicode_markup == "<foo>&lsquo;&rsquo;&ldquo;&rdquo;</foo>"
def test_smart_quotes_to_ascii(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="ascii")
assert dammit.unicode_markup == """<foo>''""</foo>"""
def test_detect_utf8(self):
utf8 = b"Sacr\xc3\xa9 bleu! \xe2\x98\x83"
dammit = UnicodeDammit(utf8)
assert dammit.original_encoding.lower() == 'utf-8'
assert dammit.unicode_markup == 'Sacr\xe9 bleu! \N{SNOWMAN}'
def test_convert_hebrew(self):
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
assert dammit.original_encoding.lower() == 'iso-8859-8'
assert dammit.unicode_markup == '\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)
assert dammit.original_encoding.lower() == 'utf-8'
assert dammit.unicode_markup.encode("utf-8") == utf_8
def test_ignore_inappropriate_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
assert dammit.original_encoding.lower() == 'utf-8'
def test_ignore_invalid_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
for bad_encoding in ['.utf8', '...', 'utF---16.!']:
dammit = UnicodeDammit(utf8_data, [bad_encoding])
assert dammit.original_encoding.lower() == 'utf-8'
def test_exclude_encodings(self):
# This is UTF-8.
utf8_data = "Räksmörgås".encode("utf-8")
# But if we exclude UTF-8 from consideration, the guess is
# Windows-1252.
dammit = UnicodeDammit(utf8_data, exclude_encodings=["utf-8"])
assert dammit.original_encoding.lower() == 'windows-1252'
# And if we exclude that, there is no valid guess at all.
dammit = UnicodeDammit(
utf8_data, exclude_encodings=["utf-8", "windows-1252"])
assert dammit.original_encoding == None
class TestEncodingDetector(object):
def test_encoding_detector_replaces_junk_in_encoding_name_with_replacement_character(self):
detected = EncodingDetector(
b'<?xml version="1.0" encoding="UTF-\xdb" ?>')
encodings = list(detected.encodings)
assert 'utf-\N{REPLACEMENT CHARACTER}' in encodings
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)
assert "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)
assert True == dammit.contains_replacement_characters
assert "\ufffd" in dammit.unicode_markup
soup = BeautifulSoup(doc, "html.parser")
assert 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)
assert "<a>áé</a>" == dammit.unicode_markup
assert "utf-16le" == dammit.original_encoding
def test_known_definite_versus_user_encodings(self):
# The known_definite_encodings are used before sniffing the
# byte-order mark; the user_encodings are used afterwards.
# Here's a document in UTF-16LE.
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
dammit = UnicodeDammit(data)
# We can process it as UTF-16 by passing it in as a known
# definite encoding.
before = UnicodeDammit(data, known_definite_encodings=["utf-16"])
assert "utf-16" == before.original_encoding
# If we pass UTF-18 as a user encoding, it's not even
# tried--the encoding sniffed from the byte-order mark takes
# precedence.
after = UnicodeDammit(data, user_encodings=["utf-8"])
assert "utf-16le" == after.original_encoding
assert ["utf-16le"] == [x[0] for x in dammit.tried_encodings]
# Here's a document in ISO-8859-8.
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, known_definite_encodings=["utf-8"],
user_encodings=["iso-8859-8"])
# The known_definite_encodings don't work, BOM sniffing does
# nothing (it only works for a few UTF encodings), but one of
# the user_encodings does work.
assert "iso-8859-8" == dammit.original_encoding
assert ["utf-8", "iso-8859-8"] == [x[0] for x in dammit.tried_encodings]
def test_deprecated_override_encodings(self):
# override_encodings is a deprecated alias for
# known_definite_encodings.
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(
hebrew,
known_definite_encodings=["shift-jis"],
override_encodings=["utf-8"],
user_encodings=["iso-8859-8"],
)
assert "iso-8859-8" == dammit.original_encoding
# known_definite_encodings and override_encodings were tried
# before user_encodings.
assert ["shift-jis", "utf-8", "iso-8859-8"] == (
[x[0] for x in dammit.tried_encodings]
)
def test_detwingle(self):
# Here's a UTF8 document.
utf8 = ("\N{SNOWMAN}" * 3).encode("utf8")
# Here's a Windows-1252 document.
windows_1252 = (
"\N{LEFT DOUBLE QUOTATION MARK}Hi, I like Windows!"
"\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:
with pytest.raises(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)
assert "☃☃☃“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 (
"\N{LATIN SMALL LIGATURE OE}", # 2-byte char '\xc5\x93'
"\N{LATIN SUBSCRIPT SMALL LETTER X}", # 3-byte char '\xe2\x82\x93'
"\xf0\x90\x90\x93", # This is a CJK character, not sure which one.
):
input = tricky_unicode_char.encode("utf8")
assert input.endswith(b'\x93')
output = UnicodeDammit.detwingle(input)
assert output == input
def test_find_declared_encoding(self):
# Test our ability to find a declared encoding inside an
# XML or HTML document.
#
# Even if the document comes in as Unicode, it may be
# interesting to know what encoding was claimed
# originally.
html_unicode = '<html><head><meta charset="utf-8"></head></html>'
html_bytes = html_unicode.encode("ascii")
xml_unicode= '<?xml version="1.0" encoding="ISO-8859-1" ?>'
xml_bytes = xml_unicode.encode("ascii")
m = EncodingDetector.find_declared_encoding
assert m(html_unicode, is_html=False) is None
assert "utf-8" == m(html_unicode, is_html=True)
assert "utf-8" == m(html_bytes, is_html=True)
assert "iso-8859-1" == m(xml_unicode)
assert "iso-8859-1" == m(xml_bytes)
# Normally, only the first few kilobytes of a document are checked for
# an encoding.
spacer = b' ' * 5000
assert m(spacer + html_bytes) is None
assert m(spacer + xml_bytes) is None
# But you can tell find_declared_encoding to search an entire
# HTML document.
assert (
m(spacer + html_bytes, is_html=True, search_entire_document=True)
== "utf-8"
)
# The XML encoding declaration has to be the very first thing
# in the document. We'll allow whitespace before the document
# starts, but nothing else.
assert m(xml_bytes, search_entire_document=True) == "iso-8859-1"
assert m(b' ' + xml_bytes, search_entire_document=True) == "iso-8859-1"
assert m(b'a' + xml_bytes, search_entire_document=True) is None
class TestEntitySubstitution(object):
"""Standalone tests of the EntitySubstitution class."""
def setup_method(self):
self.sub = EntitySubstitution
def test_simple_html_substitution(self):
# Unicode characters corresponding to named HTML entites
# are substituted, and no others.
s = "foo\u2200\N{SNOWMAN}\u00f5bar"
assert self.sub.substitute_html(s) == "foo&forall;\N{SNOWMAN}&otilde;bar"
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)
assert self.sub.substitute_html(dammit.markup) == "&lsquo;&rsquo;foo&ldquo;&rdquo;"
def test_html5_entity(self):
# Some HTML5 entities correspond to single- or multi-character
# Unicode sequences.
for entity, u in (
# A few spot checks of our ability to recognize
# special character sequences and convert them
# to named entities.
('&models;', '\u22a7'),
('&Nfr;', '\U0001d511'),
('&ngeqq;', '\u2267\u0338'),
('&not;', '\xac'),
('&Not;', '\u2aec'),
# We _could_ convert | to &verbarr;, but we don't, because
# | is an ASCII character.
('|' '|'),
# Similarly for the fj ligature, which we could convert to
# &fjlig;, but we don't.
("fj", "fj"),
# We do convert _these_ ASCII characters to HTML entities,
# because that's required to generate valid HTML.
('&gt;', '>'),
('&lt;', '<'),
('&amp;', '&'),
):
template = '3 %s 4'
raw = template % u
with_entities = template % entity
assert self.sub.substitute_html(raw) == with_entities
def test_html5_entity_with_variation_selector(self):
# Some HTML5 entities correspond either to a single-character
# Unicode sequence _or_ to the same character plus U+FE00,
# VARIATION SELECTOR 1. We can handle this.
data = "fjords \u2294 penguins"
markup = "fjords &sqcup; penguins"
assert self.sub.substitute_html(data) == markup
data = "fjords \u2294\ufe00 penguins"
markup = "fjords &sqcups; penguins"
assert self.sub.substitute_html(data) == markup
def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
s = 'Welcome to "my bar"'
assert self.sub.substitute_xml(s, False) == s
def test_xml_attribute_quoting_normally_uses_double_quotes(self):
assert self.sub.substitute_xml("Welcome", True) == '"Welcome"'
assert 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"'
assert 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"'
assert self.sub.substitute_xml(s, True) == '"Welcome to &quot;Bob\'s Bar&quot;"'
def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
quoted = 'Welcome to "Bob\'s Bar"'
assert self.sub.substitute_xml(quoted) == quoted
def test_xml_quoting_handles_angle_brackets(self):
assert self.sub.substitute_xml("foo<bar>") == "foo&lt;bar&gt;"
def test_xml_quoting_handles_ampersands(self):
assert self.sub.substitute_xml("AT&T") == "AT&amp;T"
def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
assert self.sub.substitute_xml("&Aacute;T&T") == "&amp;Aacute;T&amp;T"
def test_xml_quoting_ignoring_ampersands_when_they_are_part_of_an_entity(self):
assert self.sub.substitute_xml_containing_entities("&Aacute;T&T") == "&Aacute;T&amp;T"
def test_quotes_not_html_substituted(self):
"""There's no need to do this except inside attribute values."""
text = 'Bob\'s "bar"'
assert self.sub.substitute_html(text) == text

38
Source/Libs/bs4/tests/test_docs.py Normal file
View File

@ -0,0 +1,38 @@
"Test harness for doctests."
# TODO: Pretty sure this isn't used and should be deleted.
# 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)))

74
Source/Libs/bs4/tests/test_element.py Normal file
View File

@ -0,0 +1,74 @@
"""Tests of classes in element.py.
The really big classes -- Tag, PageElement, and NavigableString --
are tested in separate files.
"""
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
NamespacedAttribute,
)
from . import SoupTest
class TestNamedspacedAttribute(object):
def test_name_may_be_none_or_missing(self):
a = NamespacedAttribute("xmlns", None)
assert a == "xmlns"
a = NamespacedAttribute("xmlns", "")
assert a == "xmlns"
a = NamespacedAttribute("xmlns")
assert a == "xmlns"
def test_namespace_may_be_none_or_missing(self):
a = NamespacedAttribute(None, "tag")
assert a == "tag"
a = NamespacedAttribute("", "tag")
assert a == "tag"
def test_attribute_is_equivalent_to_colon_separated_string(self):
a = NamespacedAttribute("a", "b")
assert "a:b" == a
def test_attributes_are_equivalent_if_prefix_and_name_identical(self):
a = NamespacedAttribute("a", "b", "c")
b = NamespacedAttribute("a", "b", "c")
assert a == b
# The actual namespace is not considered.
c = NamespacedAttribute("a", "b", None)
assert a == c
# But name and prefix are important.
d = NamespacedAttribute("a", "z", "c")
assert a != d
e = NamespacedAttribute("z", "b", "c")
assert a != e
class TestAttributeValueWithCharsetSubstitution(object):
"""Certain attributes are designed to have the charset of the
final document substituted into their value.
"""
def test_content_meta_attribute_value(self):
# The value of a CharsetMetaAttributeValue is whatever
# encoding the string is in.
value = CharsetMetaAttributeValue("euc-jp")
assert "euc-jp" == value
assert "euc-jp" == value.original_value
assert "utf8" == value.encode("utf8")
assert "ascii" == value.encode("ascii")
def test_content_meta_attribute_value(self):
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
assert "text/html; charset=euc-jp" == value
assert "text/html; charset=euc-jp" == value.original_value
assert "text/html; charset=utf8" == value.encode("utf8")
assert "text/html; charset=ascii" == value.encode("ascii")

113
Source/Libs/bs4/tests/test_formatter.py Normal file
View File

@ -0,0 +1,113 @@
import pytest
from bs4.element import Tag
from bs4.formatter import (
Formatter,
HTMLFormatter,
XMLFormatter,
)
from . import SoupTest
class TestFormatter(SoupTest):
def test_default_attributes(self):
# Test the default behavior of Formatter.attributes().
formatter = Formatter()
tag = Tag(name="tag")
tag['b'] = 1
tag['a'] = 2
# Attributes come out sorted by name. In Python 3, attributes
# normally come out of a dictionary in the order they were
# added.
assert [('a', 2), ('b', 1)] == formatter.attributes(tag)
# This works even if Tag.attrs is None, though this shouldn't
# normally happen.
tag.attrs = None
assert [] == formatter.attributes(tag)
assert ' ' == formatter.indent
def test_sort_attributes(self):
# Test the ability to override Formatter.attributes() to,
# e.g., disable the normal sorting of attributes.
class UnsortedFormatter(Formatter):
def attributes(self, tag):
self.called_with = tag
for k, v in sorted(tag.attrs.items()):
if k == 'ignore':
continue
yield k,v
soup = self.soup('<p cval="1" aval="2" ignore="ignored"></p>')
formatter = UnsortedFormatter()
decoded = soup.decode(formatter=formatter)
# attributes() was called on the <p> tag. It filtered out one
# attribute and sorted the other two.
assert formatter.called_with == soup.p
assert '<p aval="2" cval="1"></p>' == decoded
def test_empty_attributes_are_booleans(self):
# Test the behavior of empty_attributes_are_booleans as well
# as which Formatters have it enabled.
for name in ('html', 'minimal', None):
formatter = HTMLFormatter.REGISTRY[name]
assert False == formatter.empty_attributes_are_booleans
formatter = XMLFormatter.REGISTRY[None]
assert False == formatter.empty_attributes_are_booleans
formatter = HTMLFormatter.REGISTRY['html5']
assert True == formatter.empty_attributes_are_booleans
# Verify that the constructor sets the value.
formatter = Formatter(empty_attributes_are_booleans=True)
assert True == formatter.empty_attributes_are_booleans
# Now demonstrate what it does to markup.
for markup in (
"<option selected></option>",
'<option selected=""></option>'
):
soup = self.soup(markup)
for formatter in ('html', 'minimal', 'xml', None):
assert b'<option selected=""></option>' == soup.option.encode(formatter='html')
assert b'<option selected></option>' == soup.option.encode(formatter='html5')
@pytest.mark.parametrize(
"indent,expect",
[
(None, '<a>\n<b>\ntext\n</b>\n</a>'),
(-1, '<a>\n<b>\ntext\n</b>\n</a>'),
(0, '<a>\n<b>\ntext\n</b>\n</a>'),
("", '<a>\n<b>\ntext\n</b>\n</a>'),
(1, '<a>\n <b>\n text\n </b>\n</a>'),
(2, '<a>\n <b>\n text\n </b>\n</a>'),
("\t", '<a>\n\t<b>\n\t\ttext\n\t</b>\n</a>'),
('abc', '<a>\nabc<b>\nabcabctext\nabc</b>\n</a>'),
# Some invalid inputs -- the default behavior is used.
(object(), '<a>\n <b>\n text\n </b>\n</a>'),
(b'bytes', '<a>\n <b>\n text\n </b>\n</a>'),
]
)
def test_indent(self, indent, expect):
# Pretty-print a tree with a Formatter set to
# indent in a certain way and verify the results.
soup = self.soup("<a><b>text</b></a>")
formatter = Formatter(indent=indent)
assert soup.prettify(formatter=formatter) == expect
# Pretty-printing only happens with prettify(), not
# encode().
assert soup.encode(formatter=formatter) != expect
def test_default_indent_value(self):
formatter = Formatter()
assert formatter.indent == ' '

223
Source/Libs/bs4/tests/test_html5lib.py Normal file
View File

@ -0,0 +1,223 @@
"""Tests to ensure that the html5lib tree builder generates good trees."""
import warnings
try:
from bs4.builder import HTML5TreeBuilder
HTML5LIB_PRESENT = True
except ImportError as e:
HTML5LIB_PRESENT = False
from bs4.element import SoupStrainer
from . import (
HTML5TreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not HTML5LIB_PRESENT,
"html5lib seems not to be present, not testing its tree builder.")
class TestHTML5LibBuilder(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)
assert soup.decode() == self.document_for(markup)
assert "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.assert_soup(
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.assert_soup(
"<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.
assert 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)
assert "<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>" == soup.body.decode()
assert 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)
assert "<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>" == soup.body.decode()
assert 2 == len(soup.find_all('p'))
def test_reparented_markup_containing_identical_whitespace_nodes(self):
"""Verify that we keep the two whitespace nodes in this
document distinct when reparenting the adjacent <tbody> tags.
"""
markup = '<table> <tbody><tbody><ims></tbody> </table>'
soup = self.soup(markup)
space1, space2 = soup.find_all(string=' ')
tbody1, tbody2 = soup.find_all('tbody')
assert space1.next_element is tbody1
assert tbody2.next_element is space2
def test_reparented_markup_containing_children(self):
markup = '<div><a>aftermath<p><noscript>target</noscript>aftermath</a></p></div>'
soup = self.soup(markup)
noscript = soup.noscript
assert "target" == noscript.next_element
target = soup.find(string='target')
# The 'aftermath' string was duplicated; we want the second one.
final_aftermath = soup.find_all(string='aftermath')[-1]
# The <noscript> tag was moved beneath a copy of the <a> tag,
# but the 'target' string within is still connected to the
# (second) 'aftermath' string.
assert final_aftermath == target.next_element
assert target == final_aftermath.previous_element
def test_processing_instruction(self):
"""Processing instructions become comments."""
markup = b"""<?PITarget PIContent?>"""
soup = self.soup(markup)
assert str(soup).startswith("<!--?PITarget PIContent?-->")
def test_cloned_multivalue_node(self):
markup = b"""<a class="my_class"><p></a>"""
soup = self.soup(markup)
a1, a2 = soup.find_all('a')
assert a1 == a2
assert a1 is not a2
def test_foster_parenting(self):
markup = b"""<table><td></tbody>A"""
soup = self.soup(markup)
assert "<body>A<table><tbody><tr><td></td></tr></tbody></table></body>" == soup.body.decode()
def test_extraction(self):
"""
Test that extraction does not destroy the tree.
https://bugs.launchpad.net/beautifulsoup/+bug/1782928
"""
markup = """
<html><head></head>
<style>
</style><script></script><body><p>hello</p></body></html>
"""
soup = self.soup(markup)
[s.extract() for s in soup('script')]
[s.extract() for s in soup('style')]
assert len(soup.find_all("p")) == 1
def test_empty_comment(self):
"""
Test that empty comment does not break structure.
https://bugs.launchpad.net/beautifulsoup/+bug/1806598
"""
markup = """
<html>
<body>
<form>
<!----><input type="text">
</form>
</body>
</html>
"""
soup = self.soup(markup)
inputs = []
for form in soup.find_all('form'):
inputs.extend(form.find_all('input'))
assert len(inputs) == 1
def test_tracking_line_numbers(self):
# The html.parser TreeBuilder keeps track of line number and
# position of each element.
markup = "\n <p>\n\n<sourceline>\n<b>text</b></sourceline><sourcepos></p>"
soup = self.soup(markup)
assert 2 == soup.p.sourceline
assert 5 == soup.p.sourcepos
assert "sourceline" == soup.p.find('sourceline').name
# You can deactivate this behavior.
soup = self.soup(markup, store_line_numbers=False)
assert "sourceline" == soup.p.sourceline.name
assert "sourcepos" == soup.p.sourcepos.name
def test_special_string_containers(self):
# The html5lib tree builder doesn't support this standard feature,
# because there's no way of knowing, when a string is created,
# where in the tree it will eventually end up.
pass
def test_html5_attributes(self):
# The html5lib TreeBuilder can convert any entity named in
# the HTML5 spec to a sequence of Unicode characters, and
# convert those Unicode characters to a (potentially
# different) named entity on the way out.
#
# This is a copy of the same test from
# HTMLParserTreeBuilderSmokeTest. It's not in the superclass
# because the lxml HTML TreeBuilder _doesn't_ work this way.
for input_element, output_unicode, output_element in (
("&RightArrowLeftArrow;", '\u21c4', b'&rlarr;'),
('&models;', '\u22a7', b'&models;'),
('&Nfr;', '\U0001d511', b'&Nfr;'),
('&ngeqq;', '\u2267\u0338', b'&ngeqq;'),
('&not;', '\xac', b'&not;'),
('&Not;', '\u2aec', b'&Not;'),
('&quot;', '"', b'"'),
('&there4;', '\u2234', b'&there4;'),
('&Therefore;', '\u2234', b'&there4;'),
('&therefore;', '\u2234', b'&there4;'),
("&fjlig;", 'fj', b'fj'),
("&sqcup;", '\u2294', b'&sqcup;'),
("&sqcups;", '\u2294\ufe00', b'&sqcups;'),
("&apos;", "'", b"'"),
("&verbar;", "|", b"|"),
):
markup = '<div>%s</div>' % input_element
div = self.soup(markup).div
without_element = div.encode()
expect = b"<div>%s</div>" % output_unicode.encode("utf8")
assert without_element == expect
with_element = div.encode(formatter="html")
expect = b"<div>%s</div>" % output_element
assert with_element == expect

136
Source/Libs/bs4/tests/test_htmlparser.py Normal file
View File

@ -0,0 +1,136 @@
"""Tests to ensure that the html.parser tree builder generates good
trees."""
from pdb import set_trace
import pickle
import warnings
from bs4.builder import (
HTMLParserTreeBuilder,
XMLParsedAsHTMLWarning,
)
from bs4.builder._htmlparser import BeautifulSoupHTMLParser
from . import SoupTest, HTMLTreeBuilderSmokeTest
class TestHTMLParserTreeBuilder(SoupTest, HTMLTreeBuilderSmokeTest):
default_builder = 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
def test_builder_is_pickled(self):
"""Unlike most tree builders, HTMLParserTreeBuilder and will
be restored after pickling.
"""
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
assert isinstance(loaded.builder, type(tree.builder))
def test_redundant_empty_element_closing_tags(self):
self.assert_soup('<br></br><br></br><br></br>', "<br/><br/><br/>")
self.assert_soup('</br></br></br>', "")
def test_empty_element(self):
# This verifies that any buffered data present when the parser
# finishes working is handled.
self.assert_soup("foo &# bar", "foo &amp;# bar")
def test_tracking_line_numbers(self):
# The html.parser TreeBuilder keeps track of line number and
# position of each element.
markup = "\n <p>\n\n<sourceline>\n<b>text</b></sourceline><sourcepos></p>"
soup = self.soup(markup)
assert 2 == soup.p.sourceline
assert 3 == soup.p.sourcepos
assert "sourceline" == soup.p.find('sourceline').name
# You can deactivate this behavior.
soup = self.soup(markup, store_line_numbers=False)
assert "sourceline" == soup.p.sourceline.name
assert "sourcepos" == soup.p.sourcepos.name
def test_on_duplicate_attribute(self):
# The html.parser tree builder has a variety of ways of
# handling a tag that contains the same attribute multiple times.
markup = '<a class="cls" href="url1" href="url2" href="url3" id="id">'
# If you don't provide any particular value for
# on_duplicate_attribute, later values replace earlier values.
soup = self.soup(markup)
assert "url3" == soup.a['href']
assert ["cls"] == soup.a['class']
assert "id" == soup.a['id']
# You can also get this behavior explicitly.
def assert_attribute(on_duplicate_attribute, expected):
soup = self.soup(
markup, on_duplicate_attribute=on_duplicate_attribute
)
assert expected == soup.a['href']
# Verify that non-duplicate attributes are treated normally.
assert ["cls"] == soup.a['class']
assert "id" == soup.a['id']
assert_attribute(None, "url3")
assert_attribute(BeautifulSoupHTMLParser.REPLACE, "url3")
# You can ignore subsequent values in favor of the first.
assert_attribute(BeautifulSoupHTMLParser.IGNORE, "url1")
# And you can pass in a callable that does whatever you want.
def accumulate(attrs, key, value):
if not isinstance(attrs[key], list):
attrs[key] = [attrs[key]]
attrs[key].append(value)
assert_attribute(accumulate, ["url1", "url2", "url3"])
def test_html5_attributes(self):
# The html.parser TreeBuilder can convert any entity named in
# the HTML5 spec to a sequence of Unicode characters, and
# convert those Unicode characters to a (potentially
# different) named entity on the way out.
for input_element, output_unicode, output_element in (
("&RightArrowLeftArrow;", '\u21c4', b'&rlarr;'),
('&models;', '\u22a7', b'&models;'),
('&Nfr;', '\U0001d511', b'&Nfr;'),
('&ngeqq;', '\u2267\u0338', b'&ngeqq;'),
('&not;', '\xac', b'&not;'),
('&Not;', '\u2aec', b'&Not;'),
('&quot;', '"', b'"'),
('&there4;', '\u2234', b'&there4;'),
('&Therefore;', '\u2234', b'&there4;'),
('&therefore;', '\u2234', b'&there4;'),
("&fjlig;", 'fj', b'fj'),
("&sqcup;", '\u2294', b'&sqcup;'),
("&sqcups;", '\u2294\ufe00', b'&sqcups;'),
("&apos;", "'", b"'"),
("&verbar;", "|", b"|"),
):
markup = '<div>%s</div>' % input_element
div = self.soup(markup).div
without_element = div.encode()
expect = b"<div>%s</div>" % output_unicode.encode("utf8")
assert without_element == expect
with_element = div.encode(formatter="html")
expect = b"<div>%s</div>" % output_element
assert with_element == expect
class TestHTMLParserSubclass(SoupTest):
def test_error(self):
"""Verify that our HTMLParser subclass implements error() in a way
that doesn't cause a crash.
"""
parser = BeautifulSoupHTMLParser()
with warnings.catch_warnings(record=True) as warns:
parser.error("don't crash")
[warning] = warns
assert "don't crash" == str(warning.message)

199
Source/Libs/bs4/tests/test_lxml.py Normal file
View File

@ -0,0 +1,199 @@
"""Tests to ensure that the lxml tree builder generates good trees."""
import pickle
import re
import warnings
try:
import lxml.etree
LXML_PRESENT = True
LXML_VERSION = lxml.etree.LXML_VERSION
except ImportError as 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 . import (
HTMLTreeBuilderSmokeTest,
XMLTreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its tree builder.")
class TestLXMLTreeBuilder(SoupTest, HTMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilder
def test_out_of_range_entity(self):
self.assert_soup(
"<p>foo&#10000000000000;bar</p>", "<p>foobar</p>")
self.assert_soup(
"<p>foo&#x10000000000000;bar</p>", "<p>foobar</p>")
self.assert_soup(
"<p>foo&#1000000000;bar</p>", "<p>foobar</p>")
def test_entities_in_foreign_document_encoding(self):
# We can't implement this case correctly because by the time we
# hear about markup like "&#147;", it's been (incorrectly) converted into
# a string like u'\x93'
pass
# 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]
assert "" == 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 />")
assert "<b/>" == str(soup.b)
assert "BeautifulStoneSoup class is deprecated" in str(w[0].message)
def test_tracking_line_numbers(self):
# The lxml TreeBuilder cannot keep track of line numbers from
# the original markup. Even if you ask for line numbers, we
# don't have 'em.
#
# This means that if you have a tag like <sourceline> or
# <sourcepos>, attribute access will find it rather than
# giving you a numeric answer.
soup = self.soup(
"\n <p>\n\n<sourceline>\n<b>text</b></sourceline><sourcepos></p>",
store_line_numbers=True
)
assert "sourceline" == soup.p.sourceline.name
assert "sourcepos" == soup.p.sourcepos.name
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its XML tree builder.")
class TestLXMLXMLTreeBuilder(SoupTest, XMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilderForXML
def test_namespace_indexing(self):
soup = self.soup(
'<?xml version="1.1"?>\n'
'<root>'
'<tag xmlns="http://unprefixed-namespace.com">content</tag>'
'<prefix:tag2 xmlns:prefix="http://prefixed-namespace.com">content</prefix:tag2>'
'<prefix2:tag3 xmlns:prefix2="http://another-namespace.com">'
'<subtag xmlns="http://another-unprefixed-namespace.com">'
'<subsubtag xmlns="http://yet-another-unprefixed-namespace.com">'
'</prefix2:tag3>'
'</root>'
)
# The BeautifulSoup object includes every namespace prefix
# defined in the entire document. This is the default set of
# namespaces used by soupsieve.
#
# Un-prefixed namespaces are not included, and if a given
# prefix is defined twice, only the first prefix encountered
# in the document shows up here.
assert soup._namespaces == {
'xml': 'http://www.w3.org/XML/1998/namespace',
'prefix': 'http://prefixed-namespace.com',
'prefix2': 'http://another-namespace.com'
}
# A Tag object includes only the namespace prefixes
# that were in scope when it was parsed.
# We do not track un-prefixed namespaces as we can only hold
# one (the first one), and it will be recognized as the
# default namespace by soupsieve, even when operating from a
# tag with a different un-prefixed namespace.
assert soup.tag._namespaces == {
'xml': 'http://www.w3.org/XML/1998/namespace',
}
assert soup.tag2._namespaces == {
'prefix': 'http://prefixed-namespace.com',
'xml': 'http://www.w3.org/XML/1998/namespace',
}
assert soup.subtag._namespaces == {
'prefix2': 'http://another-namespace.com',
'xml': 'http://www.w3.org/XML/1998/namespace',
}
assert soup.subsubtag._namespaces == {
'prefix2': 'http://another-namespace.com',
'xml': 'http://www.w3.org/XML/1998/namespace',
}
def test_namespace_interaction_with_select_and_find(self):
# Demonstrate how namespaces interact with select* and
# find* methods.
soup = self.soup(
'<?xml version="1.1"?>\n'
'<root>'
'<tag xmlns="http://unprefixed-namespace.com">content</tag>'
'<prefix:tag2 xmlns:prefix="http://prefixed-namespace.com">content</tag>'
'<subtag xmlns:prefix="http://another-namespace-same-prefix.com">'
'<prefix:tag3>'
'</subtag>'
'</root>'
)
# soupselect uses namespace URIs.
assert soup.select_one('tag').name == 'tag'
assert soup.select_one('prefix|tag2').name == 'tag2'
# If a prefix is declared more than once, only the first usage
# is registered with the BeautifulSoup object.
assert soup.select_one('prefix|tag3') is None
# But you can always explicitly specify a namespace dictionary.
assert soup.select_one(
'prefix|tag3', namespaces=soup.subtag._namespaces
).name == 'tag3'
# And a Tag (as opposed to the BeautifulSoup object) will
# have a set of default namespaces scoped to that Tag.
assert soup.subtag.select_one('prefix|tag3').name=='tag3'
# the find() methods aren't fully namespace-aware; they just
# look at prefixes.
assert soup.find('tag').name == 'tag'
assert soup.find('prefix:tag2').name == 'tag2'
assert soup.find('prefix:tag3').name == 'tag3'
assert soup.subtag.find('prefix:tag3').name == 'tag3'
def test_pickle_removes_builder(self):
# The lxml TreeBuilder is not picklable, so it won't be
# preserved in a pickle/unpickle operation.
soup = self.soup("<a>some markup</a>")
assert isinstance(soup.builder, self.default_builder)
pickled = pickle.dumps(soup)
unpickled = pickle.loads(pickled)
assert "some markup" == unpickled.a.string
assert unpickled.builder is None

144
Source/Libs/bs4/tests/test_navigablestring.py Normal file
View File

@ -0,0 +1,144 @@
import pytest
from bs4.element import (
CData,
Comment,
Declaration,
Doctype,
NavigableString,
RubyParenthesisString,
RubyTextString,
Script,
Stylesheet,
TemplateString,
)
from . import SoupTest
class TestNavigableString(SoupTest):
def test_text_acquisition_methods(self):
# These methods are intended for use against Tag, but they
# work on NavigableString as well,
s = NavigableString("fee ")
cdata = CData("fie ")
comment = Comment("foe ")
assert "fee " == s.get_text()
assert "fee" == s.get_text(strip=True)
assert ["fee "] == list(s.strings)
assert ["fee"] == list(s.stripped_strings)
assert ["fee "] == list(s._all_strings())
assert "fie " == cdata.get_text()
assert "fie" == cdata.get_text(strip=True)
assert ["fie "] == list(cdata.strings)
assert ["fie"] == list(cdata.stripped_strings)
assert ["fie "] == list(cdata._all_strings())
# Since a Comment isn't normally considered 'text',
# these methods generally do nothing.
assert "" == comment.get_text()
assert [] == list(comment.strings)
assert [] == list(comment.stripped_strings)
assert [] == list(comment._all_strings())
# Unless you specifically say that comments are okay.
assert "foe" == comment.get_text(strip=True, types=Comment)
assert "foe " == comment.get_text(types=(Comment, NavigableString))
def test_string_has_immutable_name_property(self):
# string.name is defined as None and can't be modified
string = self.soup("s").string
assert None == string.name
with pytest.raises(AttributeError):
string.name = 'foo'
class TestNavigableStringSubclasses(SoupTest):
def test_cdata(self):
# None of the current builders turn CDATA sections into CData
# objects, but you can create them manually.
soup = self.soup("")
cdata = CData("foo")
soup.insert(1, cdata)
assert str(soup) == "<![CDATA[foo]]>"
assert soup.find(string="foo") == "foo"
assert soup.contents[0] == "foo"
def test_cdata_is_never_formatted(self):
"""Text inside a CData object is passed into the formatter.
But the return value is ignored.
"""
self.count = 0
def increment(*args):
self.count += 1
return "BITTER FAILURE"
soup = self.soup("")
cdata = CData("<><><>")
soup.insert(1, cdata)
assert b"<![CDATA[<><><>]]>" == soup.encode(formatter=increment)
assert 1 == self.count
def test_doctype_ends_in_newline(self):
# Unlike other NavigableString subclasses, a DOCTYPE always ends
# in a newline.
doctype = Doctype("foo")
soup = self.soup("")
soup.insert(1, doctype)
assert soup.encode() == b"<!DOCTYPE foo>\n"
def test_declaration(self):
d = Declaration("foo")
assert "<?foo?>" == d.output_ready()
def test_default_string_containers(self):
# In some cases, we use different NavigableString subclasses for
# the same text in different tags.
soup = self.soup(
"<div>text</div><script>text</script><style>text</style>"
)
assert [NavigableString, Script, Stylesheet] == [
x.__class__ for x in soup.find_all(string=True)
]
# The TemplateString is a little unusual because it's generally found
# _inside_ children of a <template> element, not a direct child of the
# <template> element.
soup = self.soup(
"<template>Some text<p>In a tag</p></template>Some text outside"
)
assert all(
isinstance(x, TemplateString)
for x in soup.template._all_strings(types=None)
)
# Once the <template> tag closed, we went back to using
# NavigableString.
outside = soup.template.next_sibling
assert isinstance(outside, NavigableString)
assert not isinstance(outside, TemplateString)
# The TemplateString is also unusual because it can contain
# NavigableString subclasses of _other_ types, such as
# Comment.
markup = b"<template>Some text<p>In a tag</p><!--with a comment--></template>"
soup = self.soup(markup)
assert markup == soup.template.encode("utf8")
def test_ruby_strings(self):
markup = "<ruby>漢 <rp>(</rp><rt>kan</rt><rp>)</rp> 字 <rp>(</rp><rt>ji</rt><rp>)</rp></ruby>"
soup = self.soup(markup)
assert isinstance(soup.rp.string, RubyParenthesisString)
assert isinstance(soup.rt.string, RubyTextString)
# Just as a demo, here's what this means for get_text usage.
assert "漢字" == soup.get_text(strip=True)
assert "漢(kan)字(ji)" == soup.get_text(
strip=True,
types=(NavigableString, RubyTextString, RubyParenthesisString)
)

751
Source/Libs/bs4/tests/test_pageelement.py Normal file
View File

@ -0,0 +1,751 @@
"""Tests of the bs4.element.PageElement class"""
import copy
import pickle
import pytest
from soupsieve import SelectorSyntaxError
from bs4 import BeautifulSoup
from bs4.element import (
Comment,
SoupStrainer,
)
from . import SoupTest
class TestEncoding(SoupTest):
"""Test the ability to encode objects into strings."""
def test_unicode_string_can_be_encoded(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert soup.b.string.encode("utf-8") == "\N{SNOWMAN}".encode("utf-8")
def test_tag_containing_unicode_string_can_be_encoded(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert soup.b.encode("utf-8") == html.encode("utf-8")
def test_encoding_substitutes_unrecognized_characters_by_default(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert soup.b.encode("ascii") == b"<b>&#9731;</b>"
def test_encoding_can_be_made_strict(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
with pytest.raises(UnicodeEncodeError):
soup.encode("ascii", errors="strict")
def test_decode_contents(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert "\N{SNOWMAN}" == soup.b.decode_contents()
def test_encode_contents(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert "\N{SNOWMAN}".encode("utf8") == soup.b.encode_contents(
encoding="utf8"
)
def test_deprecated_renderContents(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert "\N{SNOWMAN}".encode("utf8") == soup.b.renderContents()
def test_repr(self):
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
assert html == repr(soup)
class TestFormatters(SoupTest):
"""Test the formatting feature, used by methods like decode() and
prettify(), and the formatters themselves.
"""
def test_default_formatter_is_minimal(self):
markup = "<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="minimal")
# The < is converted back into &lt; but the e-with-acute is left alone.
assert decoded == self.document_for(
"<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
)
def test_formatter_html(self):
markup = "<br><b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="html")
assert decoded == self.document_for(
"<br/><b>&lt;&lt;Sacr&eacute; bleu!&gt;&gt;</b>"
)
def test_formatter_html5(self):
markup = "<br><b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="html5")
assert decoded == self.document_for(
"<br><b>&lt;&lt;Sacr&eacute; bleu!&gt;&gt;</b>"
)
def test_formatter_minimal(self):
markup = "<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter="minimal")
# The < is converted back into &lt; but the e-with-acute is left alone.
assert decoded == self.document_for(
"<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
)
def test_formatter_null(self):
markup = "<b>&lt;&lt;Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</b>"
soup = self.soup(markup)
decoded = soup.decode(formatter=None)
# Neither the angle brackets nor the e-with-acute are converted.
# This is not valid HTML, but it's what the user wanted.
assert decoded == self.document_for(
"<b><<Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>></b>"
)
def test_formatter_custom(self):
markup = "<b>&lt;foo&gt;</b><b>bar</b><br/>"
soup = self.soup(markup)
decoded = soup.decode(formatter = lambda x: x.upper())
# Instead of normal entity conversion code, the custom
# callable is called on every string.
assert decoded == self.document_for("<b><FOO></b><b>BAR</b><br/>")
def test_formatter_is_run_on_attribute_values(self):
markup = '<a href="http://a.com?a=b&c=é">e</a>'
soup = self.soup(markup)
a = soup.a
expect_minimal = '<a href="http://a.com?a=b&amp;c=é">e</a>'
assert expect_minimal == a.decode()
assert expect_minimal == a.decode(formatter="minimal")
expect_html = '<a href="http://a.com?a=b&amp;c=&eacute;">e</a>'
assert expect_html == a.decode(formatter="html")
assert markup == a.decode(formatter=None)
expect_upper = '<a href="HTTP://A.COM?A=B&C=É">E</a>'
assert expect_upper == a.decode(formatter=lambda x: x.upper())
def test_formatter_skips_script_tag_for_html_documents(self):
doc = """
<script type="text/javascript">
console.log("< < hey > > ");
</script>
"""
encoded = BeautifulSoup(doc, 'html.parser').encode()
assert b"< < hey > >" in encoded
def test_formatter_skips_style_tag_for_html_documents(self):
doc = """
<style type="text/css">
console.log("< < hey > > ");
</style>
"""
encoded = BeautifulSoup(doc, 'html.parser').encode()
assert b"< < hey > >" in encoded
def test_prettify_leaves_preformatted_text_alone(self):
soup = self.soup("<div> foo <pre> \tbar\n \n </pre> baz <textarea> eee\nfff\t</textarea></div>")
# Everything outside the <pre> tag is reformatted, but everything
# inside is left alone.
assert '<div>\n foo\n <pre> \tbar\n \n </pre>\n baz\n <textarea> eee\nfff\t</textarea>\n</div>' == soup.div.prettify()
def test_prettify_accepts_formatter_function(self):
soup = BeautifulSoup("<html><body>foo</body></html>", 'html.parser')
pretty = soup.prettify(formatter = lambda x: x.upper())
assert "FOO" in pretty
def test_prettify_outputs_unicode_by_default(self):
soup = self.soup("<a></a>")
assert str == type(soup.prettify())
def test_prettify_can_encode_data(self):
soup = self.soup("<a></a>")
assert bytes == type(soup.prettify("utf-8"))
def test_html_entity_substitution_off_by_default(self):
markup = "<b>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</b>"
soup = self.soup(markup)
encoded = soup.b.encode("utf-8")
assert encoded == markup.encode('utf-8')
def test_encoding_substitution(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"/>')
soup = self.soup(meta_tag)
# Parse the document, and the charset apprears unchanged.
assert soup.meta['content'] == 'text/html; charset=x-sjis'
# Encode the document into some encoding, and the encoding is
# substituted into the meta tag.
utf_8 = soup.encode("utf-8")
assert b"charset=utf-8" in utf_8
euc_jp = soup.encode("euc_jp")
assert b"charset=euc_jp" in euc_jp
shift_jis = soup.encode("shift-jis")
assert b"charset=shift-jis" in shift_jis
utf_16_u = soup.encode("utf-16").decode("utf-16")
assert "charset=utf-16" in utf_16_u
def test_encoding_substitution_doesnt_happen_if_tag_is_strained(self):
markup = ('<head><meta content="text/html; charset=x-sjis" '
'http-equiv="Content-type"/></head><pre>foo</pre>')
# Beautiful Soup used to try to rewrite the meta tag even if the
# meta tag got filtered out by the strainer. This test makes
# sure that doesn't happen.
strainer = SoupStrainer('pre')
soup = self.soup(markup, parse_only=strainer)
assert soup.contents[0].name == 'pre'
class TestCSSSelectors(SoupTest):
"""Test basic CSS selector functionality.
This functionality is implemented in soupsieve, which has a much
more comprehensive test suite, so this is basically an extra check
that soupsieve works as expected.
"""
HTML = """
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<title>The title</title>
<link rel="stylesheet" href="blah.css" type="text/css" id="l1">
</head>
<body>
<custom-dashed-tag class="dashed" id="dash1">Hello there.</custom-dashed-tag>
<div id="main" class="fancy">
<div id="inner">
<h1 id="header1">An H1</h1>
<p>Some text</p>
<p class="onep" id="p1">Some more text</p>
<h2 id="header2">An H2</h2>
<p class="class1 class2 class3" id="pmulti">Another</p>
<a href="http://bob.example.org/" rel="friend met" id="bob">Bob</a>
<h2 id="header3">Another H2</h2>
<a id="me" href="http://simonwillison.net/" rel="me">me</a>
<span class="s1">
<a href="#" id="s1a1">span1a1</a>
<a href="#" id="s1a2">span1a2 <span id="s1a2s1">test</span></a>
<span class="span2">
<a href="#" id="s2a1">span2a1</a>
</span>
<span class="span3"></span>
<custom-dashed-tag class="dashed" id="dash2"/>
<div data-tag="dashedvalue" id="data1"/>
</span>
</div>
<x id="xid">
<z id="zida"/>
<z id="zidab"/>
<z id="zidac"/>
</x>
<y id="yid">
<z id="zidb"/>
</y>
<p lang="en" id="lang-en">English</p>
<p lang="en-gb" id="lang-en-gb">English UK</p>
<p lang="en-us" id="lang-en-us">English US</p>
<p lang="fr" id="lang-fr">French</p>
</div>
<div id="footer">
</div>
"""
def setup_method(self):
self.soup = BeautifulSoup(self.HTML, 'html.parser')
def assert_selects(self, selector, expected_ids, **kwargs):
el_ids = [el['id'] for el in self.soup.select(selector, **kwargs)]
el_ids.sort()
expected_ids.sort()
assert expected_ids == el_ids, "Selector %s, expected [%s], got [%s]" % (
selector, ', '.join(expected_ids), ', '.join(el_ids)
)
assertSelect = assert_selects
def assert_select_multiple(self, *tests):
for selector, expected_ids in tests:
self.assert_selects(selector, expected_ids)
def test_one_tag_one(self):
els = self.soup.select('title')
assert len(els) == 1
assert els[0].name == 'title'
assert els[0].contents == ['The title']
def test_one_tag_many(self):
els = self.soup.select('div')
assert len(els) == 4
for div in els:
assert div.name == 'div'
el = self.soup.select_one('div')
assert 'main' == el['id']
def test_select_one_returns_none_if_no_match(self):
match = self.soup.select_one('nonexistenttag')
assert None == match
def test_tag_in_tag_one(self):
els = self.soup.select('div div')
self.assert_selects('div div', ['inner', 'data1'])
def test_tag_in_tag_many(self):
for selector in ('html div', 'html body div', 'body div'):
self.assert_selects(selector, ['data1', 'main', 'inner', 'footer'])
def test_limit(self):
self.assert_selects('html div', ['main'], limit=1)
self.assert_selects('html body div', ['inner', 'main'], limit=2)
self.assert_selects('body div', ['data1', 'main', 'inner', 'footer'],
limit=10)
def test_tag_no_match(self):
assert len(self.soup.select('del')) == 0
def test_invalid_tag(self):
with pytest.raises(SelectorSyntaxError):
self.soup.select('tag%t')
def test_select_dashed_tag_ids(self):
self.assert_selects('custom-dashed-tag', ['dash1', 'dash2'])
def test_select_dashed_by_id(self):
dashed = self.soup.select('custom-dashed-tag[id=\"dash2\"]')
assert dashed[0].name == 'custom-dashed-tag'
assert dashed[0]['id'] == 'dash2'
def test_dashed_tag_text(self):
assert self.soup.select('body > custom-dashed-tag')[0].text == 'Hello there.'
def test_select_dashed_matches_find_all(self):
assert self.soup.select('custom-dashed-tag') == self.soup.find_all('custom-dashed-tag')
def test_header_tags(self):
self.assert_select_multiple(
('h1', ['header1']),
('h2', ['header2', 'header3']),
)
def test_class_one(self):
for selector in ('.onep', 'p.onep', 'html p.onep'):
els = self.soup.select(selector)
assert len(els) == 1
assert els[0].name == 'p'
assert els[0]['class'] == ['onep']
def test_class_mismatched_tag(self):
els = self.soup.select('div.onep')
assert len(els) == 0
def test_one_id(self):
for selector in ('div#inner', '#inner', 'div div#inner'):
self.assert_selects(selector, ['inner'])
def test_bad_id(self):
els = self.soup.select('#doesnotexist')
assert len(els) == 0
def test_items_in_id(self):
els = self.soup.select('div#inner p')
assert len(els) == 3
for el in els:
assert el.name == 'p'
assert els[1]['class'] == ['onep']
assert not els[0].has_attr('class')
def test_a_bunch_of_emptys(self):
for selector in ('div#main del', 'div#main div.oops', 'div div#main'):
assert len(self.soup.select(selector)) == 0
def test_multi_class_support(self):
for selector in ('.class1', 'p.class1', '.class2', 'p.class2',
'.class3', 'p.class3', 'html p.class2', 'div#inner .class2'):
self.assert_selects(selector, ['pmulti'])
def test_multi_class_selection(self):
for selector in ('.class1.class3', '.class3.class2',
'.class1.class2.class3'):
self.assert_selects(selector, ['pmulti'])
def test_child_selector(self):
self.assert_selects('.s1 > a', ['s1a1', 's1a2'])
self.assert_selects('.s1 > a span', ['s1a2s1'])
def test_child_selector_id(self):
self.assert_selects('.s1 > a#s1a2 span', ['s1a2s1'])
def test_attribute_equals(self):
self.assert_select_multiple(
('p[class="onep"]', ['p1']),
('p[id="p1"]', ['p1']),
('[class="onep"]', ['p1']),
('[id="p1"]', ['p1']),
('link[rel="stylesheet"]', ['l1']),
('link[type="text/css"]', ['l1']),
('link[href="blah.css"]', ['l1']),
('link[href="no-blah.css"]', []),
('[rel="stylesheet"]', ['l1']),
('[type="text/css"]', ['l1']),
('[href="blah.css"]', ['l1']),
('[href="no-blah.css"]', []),
('p[href="no-blah.css"]', []),
('[href="no-blah.css"]', []),
)
def test_attribute_tilde(self):
self.assert_select_multiple(
('p[class~="class1"]', ['pmulti']),
('p[class~="class2"]', ['pmulti']),
('p[class~="class3"]', ['pmulti']),
('[class~="class1"]', ['pmulti']),
('[class~="class2"]', ['pmulti']),
('[class~="class3"]', ['pmulti']),
('a[rel~="friend"]', ['bob']),
('a[rel~="met"]', ['bob']),
('[rel~="friend"]', ['bob']),
('[rel~="met"]', ['bob']),
)
def test_attribute_startswith(self):
self.assert_select_multiple(
('[rel^="style"]', ['l1']),
('link[rel^="style"]', ['l1']),
('notlink[rel^="notstyle"]', []),
('[rel^="notstyle"]', []),
('link[rel^="notstyle"]', []),
('link[href^="bla"]', ['l1']),
('a[href^="http://"]', ['bob', 'me']),
('[href^="http://"]', ['bob', 'me']),
('[id^="p"]', ['pmulti', 'p1']),
('[id^="m"]', ['me', 'main']),
('div[id^="m"]', ['main']),
('a[id^="m"]', ['me']),
('div[data-tag^="dashed"]', ['data1'])
)
def test_attribute_endswith(self):
self.assert_select_multiple(
('[href$=".css"]', ['l1']),
('link[href$=".css"]', ['l1']),
('link[id$="1"]', ['l1']),
('[id$="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's2a1', 's1a2s1', 'dash1']),
('div[id$="1"]', ['data1']),
('[id$="noending"]', []),
)
def test_attribute_contains(self):
self.assert_select_multiple(
# From test_attribute_startswith
('[rel*="style"]', ['l1']),
('link[rel*="style"]', ['l1']),
('notlink[rel*="notstyle"]', []),
('[rel*="notstyle"]', []),
('link[rel*="notstyle"]', []),
('link[href*="bla"]', ['l1']),
('[href*="http://"]', ['bob', 'me']),
('[id*="p"]', ['pmulti', 'p1']),
('div[id*="m"]', ['main']),
('a[id*="m"]', ['me']),
# From test_attribute_endswith
('[href*=".css"]', ['l1']),
('link[href*=".css"]', ['l1']),
('link[id*="1"]', ['l1']),
('[id*="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's1a2', 's2a1', 's1a2s1', 'dash1']),
('div[id*="1"]', ['data1']),
('[id*="noending"]', []),
# New for this test
('[href*="."]', ['bob', 'me', 'l1']),
('a[href*="."]', ['bob', 'me']),
('link[href*="."]', ['l1']),
('div[id*="n"]', ['main', 'inner']),
('div[id*="nn"]', ['inner']),
('div[data-tag*="edval"]', ['data1'])
)
def test_attribute_exact_or_hypen(self):
self.assert_select_multiple(
('p[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
('[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
('p[lang|="fr"]', ['lang-fr']),
('p[lang|="gb"]', []),
)
def test_attribute_exists(self):
self.assert_select_multiple(
('[rel]', ['l1', 'bob', 'me']),
('link[rel]', ['l1']),
('a[rel]', ['bob', 'me']),
('[lang]', ['lang-en', 'lang-en-gb', 'lang-en-us', 'lang-fr']),
('p[class]', ['p1', 'pmulti']),
('[blah]', []),
('p[blah]', []),
('div[data-tag]', ['data1'])
)
def test_quoted_space_in_selector_name(self):
html = """<div style="display: wrong">nope</div>
<div style="display: right">yes</div>
"""
soup = BeautifulSoup(html, 'html.parser')
[chosen] = soup.select('div[style="display: right"]')
assert "yes" == chosen.string
def test_unsupported_pseudoclass(self):
with pytest.raises(NotImplementedError):
self.soup.select("a:no-such-pseudoclass")
with pytest.raises(SelectorSyntaxError):
self.soup.select("a:nth-of-type(a)")
def test_nth_of_type(self):
# Try to select first paragraph
els = self.soup.select('div#inner p:nth-of-type(1)')
assert len(els) == 1
assert els[0].string == 'Some text'
# Try to select third paragraph
els = self.soup.select('div#inner p:nth-of-type(3)')
assert len(els) == 1
assert els[0].string == 'Another'
# Try to select (non-existent!) fourth paragraph
els = self.soup.select('div#inner p:nth-of-type(4)')
assert len(els) == 0
# Zero will select no tags.
els = self.soup.select('div p:nth-of-type(0)')
assert len(els) == 0
def test_nth_of_type_direct_descendant(self):
els = self.soup.select('div#inner > p:nth-of-type(1)')
assert len(els) == 1
assert els[0].string == 'Some text'
def test_id_child_selector_nth_of_type(self):
self.assert_selects('#inner > p:nth-of-type(2)', ['p1'])
def test_select_on_element(self):
# Other tests operate on the tree; this operates on an element
# within the tree.
inner = self.soup.find("div", id="main")
selected = inner.select("div")
# The <div id="inner"> tag was selected. The <div id="footer">
# tag was not.
self.assert_selects_ids(selected, ['inner', 'data1'])
def test_overspecified_child_id(self):
self.assert_selects(".fancy #inner", ['inner'])
self.assert_selects(".normal #inner", [])
def test_adjacent_sibling_selector(self):
self.assert_selects('#p1 + h2', ['header2'])
self.assert_selects('#p1 + h2 + p', ['pmulti'])
self.assert_selects('#p1 + #header2 + .class1', ['pmulti'])
assert [] == self.soup.select('#p1 + p')
def test_general_sibling_selector(self):
self.assert_selects('#p1 ~ h2', ['header2', 'header3'])
self.assert_selects('#p1 ~ #header2', ['header2'])
self.assert_selects('#p1 ~ h2 + a', ['me'])
self.assert_selects('#p1 ~ h2 + [rel="me"]', ['me'])
assert [] == self.soup.select('#inner ~ h2')
def test_dangling_combinator(self):
with pytest.raises(SelectorSyntaxError):
self.soup.select('h1 >')
def test_sibling_combinator_wont_select_same_tag_twice(self):
self.assert_selects('p[lang] ~ p', ['lang-en-gb', 'lang-en-us', 'lang-fr'])
# Test the selector grouping operator (the comma)
def test_multiple_select(self):
self.assert_selects('x, y', ['xid', 'yid'])
def test_multiple_select_with_no_space(self):
self.assert_selects('x,y', ['xid', 'yid'])
def test_multiple_select_with_more_space(self):
self.assert_selects('x, y', ['xid', 'yid'])
def test_multiple_select_duplicated(self):
self.assert_selects('x, x', ['xid'])
def test_multiple_select_sibling(self):
self.assert_selects('x, y ~ p[lang=fr]', ['xid', 'lang-fr'])
def test_multiple_select_tag_and_direct_descendant(self):
self.assert_selects('x, y > z', ['xid', 'zidb'])
def test_multiple_select_direct_descendant_and_tags(self):
self.assert_selects('div > x, y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
def test_multiple_select_indirect_descendant(self):
self.assert_selects('div x,y, z', ['xid', 'yid', 'zida', 'zidb', 'zidab', 'zidac'])
def test_invalid_multiple_select(self):
with pytest.raises(SelectorSyntaxError):
self.soup.select(',x, y')
with pytest.raises(SelectorSyntaxError):
self.soup.select('x,,y')
def test_multiple_select_attrs(self):
self.assert_selects('p[lang=en], p[lang=en-gb]', ['lang-en', 'lang-en-gb'])
def test_multiple_select_ids(self):
self.assert_selects('x, y > z[id=zida], z[id=zidab], z[id=zidb]', ['xid', 'zidb', 'zidab'])
def test_multiple_select_nested(self):
self.assert_selects('body > div > x, y > z', ['xid', 'zidb'])
def test_select_duplicate_elements(self):
# When markup contains duplicate elements, a multiple select
# will find all of them.
markup = '<div class="c1"/><div class="c2"/><div class="c1"/>'
soup = BeautifulSoup(markup, 'html.parser')
selected = soup.select(".c1, .c2")
assert 3 == len(selected)
# Verify that find_all finds the same elements, though because
# of an implementation detail it finds them in a different
# order.
for element in soup.find_all(class_=['c1', 'c2']):
assert element in selected
class TestPersistence(SoupTest):
"Testing features like pickle and deepcopy."
def setup_method(self):
self.page = """<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
"http://www.w3.org/TR/REC-html40/transitional.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<title>Beautiful Soup: We called him Tortoise because he taught us.</title>
<link rev="made" href="mailto:leonardr@segfault.org">
<meta name="Description" content="Beautiful Soup: an HTML parser optimized for screen-scraping.">
<meta name="generator" content="Markov Approximation 1.4 (module: leonardr)">
<meta name="author" content="Leonard Richardson">
</head>
<body>
<a href="foo">foo</a>
<a href="foo"><b>bar</b></a>
</body>
</html>"""
self.tree = self.soup(self.page)
def test_pickle_and_unpickle_identity(self):
# Pickling a tree, then unpickling it, yields a tree identical
# to the original.
dumped = pickle.dumps(self.tree, 2)
loaded = pickle.loads(dumped)
assert loaded.__class__ == BeautifulSoup
assert loaded.decode() == self.tree.decode()
def test_deepcopy_identity(self):
# Making a deepcopy of a tree yields an identical tree.
copied = copy.deepcopy(self.tree)
assert copied.decode() == self.tree.decode()
def test_copy_preserves_encoding(self):
soup = BeautifulSoup(b'<p>&nbsp;</p>', 'html.parser')
encoding = soup.original_encoding
copy = soup.__copy__()
assert "<p> </p>" == str(copy)
assert encoding == copy.original_encoding
def test_copy_preserves_builder_information(self):
tag = self.soup('<p></p>').p
# Simulate a tag obtained from a source file.
tag.sourceline = 10
tag.sourcepos = 33
copied = tag.__copy__()
# The TreeBuilder object is no longer availble, but information
# obtained from it gets copied over to the new Tag object.
assert tag.sourceline == copied.sourceline
assert tag.sourcepos == copied.sourcepos
assert tag.can_be_empty_element == copied.can_be_empty_element
assert tag.cdata_list_attributes == copied.cdata_list_attributes
assert tag.preserve_whitespace_tags == copied.preserve_whitespace_tags
def test_unicode_pickle(self):
# A tree containing Unicode characters can be pickled.
html = "<b>\N{SNOWMAN}</b>"
soup = self.soup(html)
dumped = pickle.dumps(soup, pickle.HIGHEST_PROTOCOL)
loaded = pickle.loads(dumped)
assert loaded.decode() == soup.decode()
def test_copy_navigablestring_is_not_attached_to_tree(self):
html = "<b>Foo<a></a></b><b>Bar</b>"
soup = self.soup(html)
s1 = soup.find(string="Foo")
s2 = copy.copy(s1)
assert s1 == s2
assert None == s2.parent
assert None == s2.next_element
assert None != s1.next_sibling
assert None == s2.next_sibling
assert None == s2.previous_element
def test_copy_navigablestring_subclass_has_same_type(self):
html = "<b><!--Foo--></b>"
soup = self.soup(html)
s1 = soup.string
s2 = copy.copy(s1)
assert s1 == s2
assert isinstance(s2, Comment)
def test_copy_entire_soup(self):
html = "<div><b>Foo<a></a></b><b>Bar</b></div>end"
soup = self.soup(html)
soup_copy = copy.copy(soup)
assert soup == soup_copy
def test_copy_tag_copies_contents(self):
html = "<div><b>Foo<a></a></b><b>Bar</b></div>end"
soup = self.soup(html)
div = soup.div
div_copy = copy.copy(div)
# The two tags look the same, and evaluate to equal.
assert str(div) == str(div_copy)
assert div == div_copy
# But they're not the same object.
assert div is not div_copy
# And they don't have the same relation to the parse tree. The
# copy is not associated with a parse tree at all.
assert None == div_copy.parent
assert None == div_copy.previous_element
assert None == div_copy.find(string='Bar').next_element
assert None != div.find(string='Bar').next_element

462
Source/Libs/bs4/tests/test_soup.py Normal file
View File

@ -0,0 +1,462 @@
# -*- coding: utf-8 -*-
"""Tests of Beautiful Soup as a whole."""
from pdb import set_trace
import logging
import os
import pickle
import pytest
import sys
import tempfile
from bs4 import (
BeautifulSoup,
BeautifulStoneSoup,
GuessedAtParserWarning,
MarkupResemblesLocatorWarning,
dammit,
)
from bs4.builder import (
builder_registry,
TreeBuilder,
ParserRejectedMarkup,
)
from bs4.element import (
Comment,
SoupStrainer,
Tag,
NavigableString,
)
from . import (
default_builder,
SoupTest,
skipIf,
)
import warnings
try:
from bs4.builder import LXMLTreeBuilder, LXMLTreeBuilderForXML
LXML_PRESENT = True
except ImportError as e:
LXML_PRESENT = False
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 = "<h1>éé</h1>"
soup = self.soup(data)
assert "éé" == soup.h1.string
def test_embedded_null(self):
data = "<h1>foo\0bar</h1>"
soup = self.soup(data)
assert "foo\0bar" == soup.h1.string
def test_exclude_encodings(self):
utf8_data = "Räksmörgås".encode("utf-8")
soup = self.soup(utf8_data, exclude_encodings=["utf-8"])
assert "windows-1252" == soup.original_encoding
def test_custom_builder_class(self):
# Verify that you can pass in a custom Builder class and
# it'll be instantiated with the appropriate keyword arguments.
class Mock(object):
def __init__(self, **kwargs):
self.called_with = kwargs
self.is_xml = True
self.store_line_numbers = False
self.cdata_list_attributes = []
self.preserve_whitespace_tags = []
self.string_containers = {}
def initialize_soup(self, soup):
pass
def feed(self, markup):
self.fed = markup
def reset(self):
pass
def ignore(self, ignore):
pass
set_up_substitutions = can_be_empty_element = ignore
def prepare_markup(self, *args, **kwargs):
yield "prepared markup", "original encoding", "declared encoding", "contains replacement characters"
kwargs = dict(
var="value",
# This is a deprecated BS3-era keyword argument, which
# will be stripped out.
convertEntities=True,
)
with warnings.catch_warnings(record=True):
soup = BeautifulSoup('', builder=Mock, **kwargs)
assert isinstance(soup.builder, Mock)
assert dict(var="value") == soup.builder.called_with
assert "prepared markup" == soup.builder.fed
# You can also instantiate the TreeBuilder yourself. In this
# case, that specific object is used and any keyword arguments
# to the BeautifulSoup constructor are ignored.
builder = Mock(**kwargs)
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup(
'', builder=builder, ignored_value=True,
)
msg = str(w[0].message)
assert msg.startswith("Keyword arguments to the BeautifulSoup constructor will be ignored.")
assert builder == soup.builder
assert kwargs == builder.called_with
def test_parser_markup_rejection(self):
# If markup is completely rejected by the parser, an
# explanatory ParserRejectedMarkup exception is raised.
class Mock(TreeBuilder):
def feed(self, *args, **kwargs):
raise ParserRejectedMarkup("Nope.")
def prepare_markup(self, *args, **kwargs):
# We're going to try two different ways of preparing this markup,
# but feed() will reject both of them.
yield markup, None, None, False
yield markup, None, None, False
import re
with pytest.raises(ParserRejectedMarkup) as exc_info:
BeautifulSoup('', builder=Mock)
assert "The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help." in str(exc_info.value)
def test_cdata_list_attributes(self):
# Most attribute values are represented as scalars, but the
# HTML standard says that some attributes, like 'class' have
# space-separated lists as values.
markup = '<a id=" an id " class=" a class "></a>'
soup = self.soup(markup)
# Note that the spaces are stripped for 'class' but not for 'id'.
a = soup.a
assert " an id " == a['id']
assert ["a", "class"] == a['class']
# TreeBuilder takes an argument called 'mutli_valued_attributes' which lets
# you customize or disable this. As always, you can customize the TreeBuilder
# by passing in a keyword argument to the BeautifulSoup constructor.
soup = self.soup(markup, builder=default_builder, multi_valued_attributes=None)
assert " a class " == soup.a['class']
# Here are two ways of saying that `id` is a multi-valued
# attribute in this context, but 'class' is not.
for switcheroo in ({'*': 'id'}, {'a': 'id'}):
with warnings.catch_warnings(record=True) as w:
# This will create a warning about not explicitly
# specifying a parser, but we'll ignore it.
soup = self.soup(markup, builder=None, multi_valued_attributes=switcheroo)
a = soup.a
assert ["an", "id"] == a['id']
assert " a class " == a['class']
def test_replacement_classes(self):
# Test the ability to pass in replacements for element classes
# which will be used when building the tree.
class TagPlus(Tag):
pass
class StringPlus(NavigableString):
pass
class CommentPlus(Comment):
pass
soup = self.soup(
"<a><b>foo</b>bar</a><!--whee-->",
element_classes = {
Tag: TagPlus,
NavigableString: StringPlus,
Comment: CommentPlus,
}
)
# The tree was built with TagPlus, StringPlus, and CommentPlus objects,
# rather than Tag, String, and Comment objects.
assert all(
isinstance(x, (TagPlus, StringPlus, CommentPlus))
for x in soup.recursiveChildGenerator()
)
def test_alternate_string_containers(self):
# Test the ability to customize the string containers for
# different types of tags.
class PString(NavigableString):
pass
class BString(NavigableString):
pass
soup = self.soup(
"<div>Hello.<p>Here is <b>some <i>bolded</i></b> text",
string_containers = {
'b': BString,
'p': PString,
}
)
# The string before the <p> tag is a regular NavigableString.
assert isinstance(soup.div.contents[0], NavigableString)
# The string inside the <p> tag, but not inside the <i> tag,
# is a PString.
assert isinstance(soup.p.contents[0], PString)
# Every string inside the <b> tag is a BString, even the one that
# was also inside an <i> tag.
for s in soup.b.strings:
assert isinstance(s, BString)
# Now that parsing was complete, the string_container_stack
# (where this information was kept) has been cleared out.
assert [] == soup.string_container_stack
class TestWarnings(SoupTest):
def _assert_warning(self, warnings, cls):
for w in warnings:
if isinstance(w.message, cls):
return w
raise Exception("%s warning not found in %r" % (cls, warnings))
def _assert_no_parser_specified(self, w):
warning = self._assert_warning(w, GuessedAtParserWarning)
message = str(warning.message)
assert message.startswith(BeautifulSoup.NO_PARSER_SPECIFIED_WARNING[:60])
def test_warning_if_no_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup("<a><b></b></a>")
self._assert_no_parser_specified(w)
def test_warning_if_parser_specified_too_vague(self):
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup("<a><b></b></a>", "html")
self._assert_no_parser_specified(w)
def test_no_warning_if_explicit_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = BeautifulSoup("<a><b></b></a>", "html.parser")
assert [] == w
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)
assert "parseOnlyThese" in msg
assert "parse_only" in msg
assert 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)
assert "fromEncoding" in msg
assert "from_encoding" in msg
assert "utf8" == soup.original_encoding
def test_unrecognized_keyword_argument(self):
with pytest.raises(TypeError):
self.soup("<a>", no_such_argument=True)
@pytest.mark.parametrize(
"extension",
['markup.html', 'markup.htm', 'markup.HTML', 'markup.txt',
'markup.xhtml', 'markup.xml', "/home/user/file", "c:\\user\file"]
)
def test_resembles_filename_warning(self, extension):
# A warning is issued if the "markup" looks like the name of
# an HTML or text file, or a full path to a file on disk.
with warnings.catch_warnings(record=True) as w:
soup = self.soup("markup" + extension)
warning = self._assert_warning(w, MarkupResemblesLocatorWarning)
assert "looks more like a filename" in str(warning.message)
@pytest.mark.parametrize(
"extension",
['markuphtml', 'markup.com', '', 'markup.js']
)
def test_resembles_filename_no_warning(self, extension):
# The 'looks more like a filename' warning is not issued if
# the markup looks like a bare string, a domain name, or a
# file that's not an HTML file.
with warnings.catch_warnings(record=True) as w:
soup = self.soup("markup" + extension)
assert [] == w
def test_url_warning_with_bytes_url(self):
url = b"http://www.crummybytes.com/"
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(url)
warning = self._assert_warning(
warning_list, MarkupResemblesLocatorWarning
)
assert "looks more like a URL" in str(warning.message)
assert url not in str(warning.message).encode("utf8")
def test_url_warning_with_unicode_url(self):
url = "http://www.crummyunicode.com/"
with warnings.catch_warnings(record=True) as warning_list:
# note - this url must differ from the bytes one otherwise
# python's warnings system swallows the second warning
soup = self.soup(url)
warning = self._assert_warning(
warning_list, MarkupResemblesLocatorWarning
)
assert "looks more like a URL" in str(warning.message)
assert url not in str(warning.message)
def test_url_warning_with_bytes_and_space(self):
# Here the markup contains something besides a URL, so no warning
# is issued.
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(b"http://www.crummybytes.com/ is great")
assert not any("looks more like a URL" in str(w.message)
for w in warning_list)
def test_url_warning_with_unicode_and_space(self):
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup("http://www.crummyunicode.com/ is great")
assert not any("looks more like a URL" in str(w.message)
for w in warning_list)
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)
assert soup.encode() == b"<b>Yes</b><b>Yes <c>Yes</c></b>"
class TestNewTag(SoupTest):
"""Test the BeautifulSoup.new_tag() method."""
def test_new_tag(self):
soup = self.soup("")
new_tag = soup.new_tag("foo", bar="baz", attrs={"name": "a name"})
assert isinstance(new_tag, Tag)
assert "foo" == new_tag.name
assert dict(bar="baz", name="a name") == new_tag.attrs
assert None == new_tag.parent
def test_tag_inherits_self_closing_rules_from_builder(self):
if LXML_PRESENT:
xml_soup = BeautifulSoup("", "lxml-xml")
xml_br = xml_soup.new_tag("br")
xml_p = xml_soup.new_tag("p")
# Both the <br> and <p> tag are empty-element, just because
# they have no contents.
assert b"<br/>" == xml_br.encode()
assert b"<p/>" == xml_p.encode()
html_soup = BeautifulSoup("", "html.parser")
html_br = html_soup.new_tag("br")
html_p = html_soup.new_tag("p")
# The HTML builder users HTML's rules about which tags are
# empty-element tags, and the new tags reflect these rules.
assert b"<br/>" == html_br.encode()
assert b"<p></p>" == html_p.encode()
class TestNewString(SoupTest):
"""Test the BeautifulSoup.new_string() method."""
def test_new_string_creates_navigablestring(self):
soup = self.soup("")
s = soup.new_string("foo")
assert "foo" == s
assert isinstance(s, NavigableString)
def test_new_string_can_create_navigablestring_subclass(self):
soup = self.soup("")
s = soup.new_string("foo", Comment)
assert "foo" == s
assert isinstance(s, Comment)
class TestPickle(SoupTest):
# Test our ability to pickle the BeautifulSoup object itself.
def test_normal_pickle(self):
soup = self.soup("<a>some markup</a>")
pickled = pickle.dumps(soup)
unpickled = pickle.loads(pickled)
assert "some markup" == unpickled.a.string
def test_pickle_with_no_builder(self):
# We had a bug that prevented pickling from working if
# the builder wasn't set.
soup = self.soup("some markup")
soup.builder = None
pickled = pickle.dumps(soup)
unpickled = pickle.loads(pickled)
assert "some markup" == unpickled.string
class TestEncodingConversion(SoupTest):
# Test Beautiful Soup's ability to decode and encode from various
# encodings.
def setup_method(self):
self.unicode_data = '<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.
assert 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 = dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
# Disable chardet, which will realize that the ASCII is ASCII.
dammit.chardet_dammit = noop
ascii = b"<foo>a</foo>"
soup_from_ascii = self.soup(ascii)
unicode_output = soup_from_ascii.decode()
assert isinstance(unicode_output, str)
assert unicode_output == self.document_for(ascii.decode())
assert soup_from_ascii.original_encoding.lower() == "utf-8"
finally:
logging.disable(logging.NOTSET)
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)
assert soup_from_unicode.decode() == self.unicode_data
assert soup_from_unicode.foo.string == 'Sacr\xe9 bleu!'
assert 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)
assert soup_from_utf8.decode() == self.unicode_data
assert soup_from_utf8.foo.string == '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)
assert soup_from_unicode.encode('utf-8') == self.utf8_data
@skipIf(
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 = '<div><a \N{SNOWMAN}="snowman"></a></div>'
assert self.soup(markup).div.encode("utf8") == markup.encode("utf8")

221
Source/Libs/bs4/tests/test_tag.py Normal file
View File

@ -0,0 +1,221 @@
import warnings
from bs4.element import (
Comment,
NavigableString,
)
from . import SoupTest
class TestTag(SoupTest):
"""Test various methods of Tag which aren't so complicated they
need their own classes.
"""
def test__should_pretty_print(self):
# Test the rules about when a tag should be pretty-printed.
tag = self.soup("").new_tag("a_tag")
# No list of whitespace-preserving tags -> pretty-print
tag._preserve_whitespace_tags = None
assert True == tag._should_pretty_print(0)
# List exists but tag is not on the list -> pretty-print
tag.preserve_whitespace_tags = ["some_other_tag"]
assert True == tag._should_pretty_print(1)
# Indent level is None -> don't pretty-print
assert False == tag._should_pretty_print(None)
# Tag is on the whitespace-preserving list -> don't pretty-print
tag.preserve_whitespace_tags = ["some_other_tag", "a_tag"]
assert False == tag._should_pretty_print(1)
def test_len(self):
"""The length of a Tag is its number of children."""
soup = self.soup("<top>1<b>2</b>3</top>")
# The BeautifulSoup object itself contains one element: the
# <top> tag.
assert len(soup.contents) == 1
assert len(soup) == 1
# The <top> tag contains three elements: the text node "1", the
# <b> tag, and the text node "3".
assert len(soup.top) == 3
assert len(soup.top.contents) == 3
def test_member_access_invokes_find(self):
"""Accessing a Python member .foo invokes find('foo')"""
soup = self.soup('<b><i></i></b>')
assert soup.b == soup.find('b')
assert soup.b.i == soup.find('b').find('i')
assert soup.a == None
def test_deprecated_member_access(self):
soup = self.soup('<b><i></i></b>')
with warnings.catch_warnings(record=True) as w:
tag = soup.bTag
assert soup.b == tag
assert '.bTag is deprecated, use .find("b") instead. If you really were looking for a tag called bTag, use .find("bTag")' == str(w[0].message)
def test_has_attr(self):
"""has_attr() checks for the presence of an attribute.
Please note note: has_attr() is different from
__in__. has_attr() checks the tag's attributes and __in__
checks the tag's chidlren.
"""
soup = self.soup("<foo attr='bar'>")
assert soup.foo.has_attr('attr')
assert not soup.foo.has_attr('attr2')
def test_attributes_come_out_in_alphabetical_order(self):
markup = '<b a="1" z="5" m="3" f="2" y="4"></b>'
self.assertSoupEquals(markup, '<b a="1" f="2" m="3" y="4" z="5"></b>')
def test_string(self):
# A Tag that contains only a text node makes that node
# available as .string.
soup = self.soup("<b>foo</b>")
assert soup.b.string == 'foo'
def test_empty_tag_has_no_string(self):
# A Tag with no children has no .stirng.
soup = self.soup("<b></b>")
assert soup.b.string == None
def test_tag_with_multiple_children_has_no_string(self):
# A Tag with no children has no .string.
soup = self.soup("<a>foo<b></b><b></b></b>")
assert soup.b.string == None
soup = self.soup("<a>foo<b></b>bar</b>")
assert soup.b.string == None
# Even if all the children are strings, due to trickery,
# it won't work--but this would be a good optimization.
soup = self.soup("<a>foo</b>")
soup.a.insert(1, "bar")
assert soup.a.string == None
def test_tag_with_recursive_string_has_string(self):
# A Tag with a single child which has a .string inherits that
# .string.
soup = self.soup("<a><b>foo</b></a>")
assert soup.a.string == "foo"
assert soup.string == "foo"
def test_lack_of_string(self):
"""Only a Tag containing a single text node has a .string."""
soup = self.soup("<b>f<i>e</i>o</b>")
assert soup.b.string is None
soup = self.soup("<b></b>")
assert soup.b.string is None
def test_all_text(self):
"""Tag.text and Tag.get_text(sep=u"") -> all child text, concatenated"""
soup = self.soup("<a>a<b>r</b> <r> t </r></a>")
assert soup.a.text == "ar t "
assert soup.a.get_text(strip=True) == "art"
assert soup.a.get_text(",") == "a,r, , t "
assert soup.a.get_text(",", strip=True) == "a,r,t"
def test_get_text_ignores_special_string_containers(self):
soup = self.soup("foo<!--IGNORE-->bar")
assert soup.get_text() == "foobar"
assert soup.get_text(types=(NavigableString, Comment)) == "fooIGNOREbar"
assert soup.get_text(types=None) == "fooIGNOREbar"
soup = self.soup("foo<style>CSS</style><script>Javascript</script>bar")
assert soup.get_text() == "foobar"
def test_all_strings_ignores_special_string_containers(self):
soup = self.soup("foo<!--IGNORE-->bar")
assert ['foo', 'bar'] == list(soup.strings)
soup = self.soup("foo<style>CSS</style><script>Javascript</script>bar")
assert ['foo', 'bar'] == list(soup.strings)
def test_string_methods_inside_special_string_container_tags(self):
# Strings inside tags like <script> are generally ignored by
# methods like get_text, because they're not what humans
# consider 'text'. But if you call get_text on the <script>
# tag itself, those strings _are_ considered to be 'text',
# because there's nothing else you might be looking for.
style = self.soup("<div>a<style>Some CSS</style></div>")
template = self.soup("<div>a<template><p>Templated <b>text</b>.</p><!--With a comment.--></template></div>")
script = self.soup("<div>a<script><!--a comment-->Some text</script></div>")
assert style.div.get_text() == "a"
assert list(style.div.strings) == ["a"]
assert style.div.style.get_text() == "Some CSS"
assert list(style.div.style.strings) == ['Some CSS']
# The comment is not picked up here. That's because it was
# parsed into a Comment object, which is not considered
# interesting by template.strings.
assert template.div.get_text() == "a"
assert list(template.div.strings) == ["a"]
assert template.div.template.get_text() == "Templated text."
assert list(template.div.template.strings) == ["Templated ", "text", "."]
# The comment is included here, because it didn't get parsed
# into a Comment object--it's part of the Script string.
assert script.div.get_text() == "a"
assert list(script.div.strings) == ["a"]
assert script.div.script.get_text() == "<!--a comment-->Some text"
assert list(script.div.script.strings) == ['<!--a comment-->Some text']
class TestMultiValuedAttributes(SoupTest):
"""Test the behavior of multi-valued attributes like 'class'.
The values of such attributes are always presented as lists.
"""
def test_single_value_becomes_list(self):
soup = self.soup("<a class='foo'>")
assert ["foo"] ==soup.a['class']
def test_multiple_values_becomes_list(self):
soup = self.soup("<a class='foo bar'>")
assert ["foo", "bar"] == soup.a['class']
def test_multiple_values_separated_by_weird_whitespace(self):
soup = self.soup("<a class='foo\tbar\nbaz'>")
assert ["foo", "bar", "baz"] ==soup.a['class']
def test_attributes_joined_into_string_on_output(self):
soup = self.soup("<a class='foo\tbar'>")
assert b'<a class="foo bar"></a>' == soup.a.encode()
def test_get_attribute_list(self):
soup = self.soup("<a id='abc def'>")
assert ['abc def'] == soup.a.get_attribute_list('id')
def test_accept_charset(self):
soup = self.soup('<form accept-charset="ISO-8859-1 UTF-8">')
assert ['ISO-8859-1', 'UTF-8'] == soup.form['accept-charset']
def test_cdata_attribute_applying_only_to_one_tag(self):
data = '<a accept-charset="ISO-8859-1 UTF-8"></a>'
soup = self.soup(data)
# We saw in another test that accept-charset is a cdata-list
# attribute for the <form> tag. But it's not a cdata-list
# attribute for any other tag.
assert 'ISO-8859-1 UTF-8' == soup.a['accept-charset']
def test_customization(self):
# It's possible to change which attributes of which tags
# are treated as multi-valued attributes.
#
# Here, 'id' is a multi-valued attribute and 'class' is not.
#
# TODO: This code is in the builder and should be tested there.
soup = self.soup(
'<a class="foo" id="bar">', multi_valued_attributes={ '*' : 'id' }
)
assert soup.a['class'] == 'foo'
assert soup.a['id'] == ['bar']

1290
Source/Libs/bs4/tests/test_tree.py Normal file
View File

File diff suppressed because it is too large Load Diff