senaduka/old-nlp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Senad Uka
2019-10-20 13:16:49 +02:00
commit 233066caf4
2099 changed files with 360824 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
venv/lib/python3.7/site-packages/__pycache__/easy_install.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/__pycache__/six.cpython-37.pyc Normal file
View File

Binary file not shown.

104
venv/lib/python3.7/site-packages/beautifulsoup4-4.8.1.dist-info/DESCRIPTION.rst Normal file
View File

@@ -0,0 +1,104 @@
Beautiful Soup is a library that makes it easy to scrape information
from web pages. It sits atop an HTML or XML parser, providing Pythonic
idioms for iterating, searching, and modifying the parse tree.
# Quick start
```
>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
>>> print soup.prettify()
<html>
<body>
<p>
Some
<b>
bad
<i>
HTML
</i>
</b>
</p>
</body>
</html>
>>> soup.find(text="bad")
u'bad'
>>> soup.i
<i>HTML</i>
#
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
#
>>> print soup.prettify()
<?xml version="1.0" encoding="utf-8">
<tag1>
Some
<tag2 />
bad
<tag3>
XML
</tag3>
</tag1>
```
To go beyond the basics, [comprehensive documentation is available](http://www.crummy.com/software/BeautifulSoup/bs4/doc/).
# Links
* [Homepage](http://www.crummy.com/software/BeautifulSoup/bs4/)
* [Documentation](http://www.crummy.com/software/BeautifulSoup/bs4/doc/)
* [Discussion group](http://groups.google.com/group/beautifulsoup/)
* [Development](https://code.launchpad.net/beautifulsoup/)
* [Bug tracker](https://bugs.launchpad.net/beautifulsoup/)
* [Complete changelog](https://bazaar.launchpad.net/~leonardr/beautifulsoup/bs4/view/head:/CHANGELOG)
# Note on Python 2 sunsetting
Since 2012, Beautiful Soup has been developed as a Python 2 library
which is automatically converted to Python 3 code as necessary. This
makes it impossible to take advantages of some features of Python
3.
For this reason, I plan to discontinue Beautiful Soup's Python 2
support at some point after January 1, 2021: one year after the sunset
date for Python 2 itself. Beyond that point, new Beautiful Soup
development will exclusively target Python 3. Of course, older
releases of Beautiful Soup, which support both versions, will continue
to be available.
# Supporting the project
If you use Beautiful Soup as part of your professional work, please consider a
[Tidelift subscription](https://tidelift.com/subscription/pkg/pypi-beautifulsoup4?utm_source=pypi-beautifulsoup4&utm_medium=referral&utm_campaign=readme).
This will support many of the free software projects your organization
depends on, not just Beautiful Soup.
If you use Beautiful Soup for personal projects, the best way to say
thank you is to read
[Tool Safety](https://www.crummy.com/software/BeautifulSoup/zine/), a zine I
wrote about what Beautiful Soup has taught me about software
development.
# Building the documentation
The bs4/doc/ directory contains full documentation in Sphinx
format. Run `make html` in that directory to create HTML
documentation.
# Running the unit tests
Beautiful Soup supports unit test discovery from the project root directory:
```
$ nosetests
```
```
$ python -m unittest discover -s bs4
```
If you checked out the source tree, you should see a script in the
home directory called test-all-versions. This script will run the unit
tests under Python 2, then create a temporary Python 3 conversion of
the source and run the unit tests again under Python 3.

1
venv/lib/python3.7/site-packages/beautifulsoup4-4.8.1.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

130
venv/lib/python3.7/site-packages/beautifulsoup4-4.8.1.dist-info/METADATA Normal file
View File

@@ -0,0 +1,130 @@
Metadata-Version: 2.0
Name: beautifulsoup4
Version: 4.8.1
Summary: Screen-scraping library
Home-page: http://www.crummy.com/software/BeautifulSoup/bs4/
Author: Leonard Richardson
Author-email: leonardr@segfault.org
License: MIT
Download-URL: http://www.crummy.com/software/BeautifulSoup/bs4/download/
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Text Processing :: Markup :: HTML
Classifier: Topic :: Text Processing :: Markup :: XML
Classifier: Topic :: Text Processing :: Markup :: SGML
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Dist: soupsieve (>=1.2)
Provides-Extra: html5lib
Requires-Dist: html5lib; extra == 'html5lib'
Provides-Extra: lxml
Requires-Dist: lxml; extra == 'lxml'
Beautiful Soup is a library that makes it easy to scrape information
from web pages. It sits atop an HTML or XML parser, providing Pythonic
idioms for iterating, searching, and modifying the parse tree.
# Quick start
```
>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
>>> print soup.prettify()
<html>
<body>
<p>
Some
<b>
bad
<i>
HTML
</i>
</b>
</p>
</body>
</html>
>>> soup.find(text="bad")
u'bad'
>>> soup.i
<i>HTML</i>
#
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
#
>>> print soup.prettify()
<?xml version="1.0" encoding="utf-8">
<tag1>
Some
<tag2 />
bad
<tag3>
XML
</tag3>
</tag1>
```
To go beyond the basics, [comprehensive documentation is available](http://www.crummy.com/software/BeautifulSoup/bs4/doc/).
# Links
* [Homepage](http://www.crummy.com/software/BeautifulSoup/bs4/)
* [Documentation](http://www.crummy.com/software/BeautifulSoup/bs4/doc/)
* [Discussion group](http://groups.google.com/group/beautifulsoup/)
* [Development](https://code.launchpad.net/beautifulsoup/)
* [Bug tracker](https://bugs.launchpad.net/beautifulsoup/)
* [Complete changelog](https://bazaar.launchpad.net/~leonardr/beautifulsoup/bs4/view/head:/CHANGELOG)
# Note on Python 2 sunsetting
Since 2012, Beautiful Soup has been developed as a Python 2 library
which is automatically converted to Python 3 code as necessary. This
makes it impossible to take advantages of some features of Python
3.
For this reason, I plan to discontinue Beautiful Soup's Python 2
support at some point after January 1, 2021: one year after the sunset
date for Python 2 itself. Beyond that point, new Beautiful Soup
development will exclusively target Python 3. Of course, older
releases of Beautiful Soup, which support both versions, will continue
to be available.
# Supporting the project
If you use Beautiful Soup as part of your professional work, please consider a
[Tidelift subscription](https://tidelift.com/subscription/pkg/pypi-beautifulsoup4?utm_source=pypi-beautifulsoup4&utm_medium=referral&utm_campaign=readme).
This will support many of the free software projects your organization
depends on, not just Beautiful Soup.
If you use Beautiful Soup for personal projects, the best way to say
thank you is to read
[Tool Safety](https://www.crummy.com/software/BeautifulSoup/zine/), a zine I
wrote about what Beautiful Soup has taught me about software
development.
# Building the documentation
The bs4/doc/ directory contains full documentation in Sphinx
format. Run `make html` in that directory to create HTML
documentation.
# Running the unit tests
Beautiful Soup supports unit test discovery from the project root directory:
```
$ nosetests
```
```
$ python -m unittest discover -s bs4
```
If you checked out the source tree, you should see a script in the
home directory called test-all-versions. This script will run the unit
tests under Python 2, then create a temporary Python 3 conversion of
the source and run the unit tests again under Python 3.

45
venv/lib/python3.7/site-packages/beautifulsoup4-4.8.1.dist-info/RECORD Normal file
View File

@@ -0,0 +1,45 @@
beautifulsoup4-4.8.1.dist-info/DESCRIPTION.rst,sha256=TUEndO1FnBoCMGIeuX9tkAhKSylXB1t_NUSYxDo6ce4,3010
beautifulsoup4-4.8.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
beautifulsoup4-4.8.1.dist-info/METADATA,sha256=ZQSTtI3Y6TP3LVrckhEel5QhfhqT8pwwvBuronGBz34,4020
beautifulsoup4-4.8.1.dist-info/RECORD,,
beautifulsoup4-4.8.1.dist-info/WHEEL,sha256=rNo05PbNqwnXiIHFsYm0m22u4Zm6YJtugFG2THx4w3g,92
beautifulsoup4-4.8.1.dist-info/metadata.json,sha256=RNf83TEq3M65TUoCk_oElvbCdiLyo_AQuj0f7SNVEGc,1144
beautifulsoup4-4.8.1.dist-info/top_level.txt,sha256=H8VT-IuPWLzQqwG9_eChjXDJ1z0H9RRebdSR90Bjnkw,4
bs4/__init__.py,sha256=VF0X3wc9hsmeJiMt630mwChrwIc58DYt4c9vP2ky-w4,25903
bs4/__pycache__/__init__.cpython-37.pyc,,
bs4/__pycache__/check_block.cpython-37.pyc,,
bs4/__pycache__/dammit.cpython-37.pyc,,
bs4/__pycache__/diagnose.cpython-37.pyc,,
bs4/__pycache__/element.cpython-37.pyc,,
bs4/__pycache__/formatter.cpython-37.pyc,,
bs4/__pycache__/testing.cpython-37.pyc,,
bs4/builder/__init__.py,sha256=e_vTLD3AkgUTjUXkc04b0FZHJBRaVM8SDxvVNMnLXtE,14749
bs4/builder/__pycache__/__init__.cpython-37.pyc,,
bs4/builder/__pycache__/_html5lib.cpython-37.pyc,,
bs4/builder/__pycache__/_htmlparser.cpython-37.pyc,,
bs4/builder/__pycache__/_lxml.cpython-37.pyc,,
bs4/builder/_html5lib.py,sha256=105ocel2oFeApKaPem5XtjL67kO5rKJxM5_6B2gxBw0,18088
bs4/builder/_htmlparser.py,sha256=AKpOnUAoPBYi7x0Y1fTb1Uxrxb2EFroWIdCWgwShcF4,13653
bs4/builder/_lxml.py,sha256=BsJBgIoyIZYY001TSHLtEsJtYD5hCXhldwpUEaYaJkg,11114
bs4/check_block.py,sha256=ltAO73VRGrGcO0bVPMd0GdTlIg9eVTCGnnZiPbKzFI0,132
bs4/dammit.py,sha256=VcHa3eSGP6bL3UuCrjMy_auYO7tTH42I-lhNDbrMsy8,31028
bs4/diagnose.py,sha256=wvGDZf6VNj6rwDjU3xOsz90z2KZiBWgpu-GRqWfR6is,6966
bs4/element.py,sha256=ebosrK3jVgnZ4Dr7kmrJdfRUu8JkENXKQHwNKPcA2QE,59447
bs4/formatter.py,sha256=G2AYBRjeX404vLNwIPbjiG8KDjuoCqrgi9NHua6o34M,3199
bs4/testing.py,sha256=MBsN77WRpB1Z78Y0pV7RlwbMWGfEU1iPySFKE-JJIgc,41306
bs4/tests/__init__.py,sha256=bdUBDE750n7qNEfue7-3a1fBaUxJlvZMkvJvZa-lbYs,27
bs4/tests/__pycache__/__init__.cpython-37.pyc,,
bs4/tests/__pycache__/test_builder_registry.cpython-37.pyc,,
bs4/tests/__pycache__/test_docs.cpython-37.pyc,,
bs4/tests/__pycache__/test_html5lib.cpython-37.pyc,,
bs4/tests/__pycache__/test_htmlparser.cpython-37.pyc,,
bs4/tests/__pycache__/test_lxml.cpython-37.pyc,,
bs4/tests/__pycache__/test_soup.cpython-37.pyc,,
bs4/tests/__pycache__/test_tree.cpython-37.pyc,,
bs4/tests/test_builder_registry.py,sha256=pllfRpArh9TYhjjRUiu1wITr9Ryyv4hiaAtRjij-k4E,5582
bs4/tests/test_docs.py,sha256=FXfz2bGL4Xe0q6duwpmg9hmFiZuU4DVJPNZ0hTb6aH4,1067
bs4/tests/test_html5lib.py,sha256=R2zNUUbUa3WnSqGGOiARKDWH1TLguogluqQDr10Gick,6493
bs4/tests/test_htmlparser.py,sha256=N-wPX5jDOy7b8xUv9pHEIEfEFjOitLuD9V1blKcbscM,2354
bs4/tests/test_lxml.py,sha256=xJr8eDrtHSb_vQw88lYEKyfdM1Hel4-dBaz14vQq78M,4105
bs4/tests/test_soup.py,sha256=JbjlyIKCmUnVNfEHq3aPjyj-w7WZEgE9cAV-LOx6xwo,27613
bs4/tests/test_tree.py,sha256=XBRpEOpAEvDhOeSSN857U5OcjdvfqmYT3bDNN8Qbabw,86259

5
venv/lib/python3.7/site-packages/beautifulsoup4-4.8.1.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.29.0)
Root-Is-Purelib: true
Tag: py3-none-any

1
venv/lib/python3.7/site-packages/beautifulsoup4-4.8.1.dist-info/metadata.json Normal file
View File

@@ -0,0 +1 @@
{"classifiers": ["Development Status :: 5 - Production/Stable", "Intended Audience :: Developers", "License :: OSI Approved :: MIT License", "Programming Language :: Python", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3", "Topic :: Text Processing :: Markup :: HTML", "Topic :: Text Processing :: Markup :: XML", "Topic :: Text Processing :: Markup :: SGML", "Topic :: Software Development :: Libraries :: Python Modules"], "download_url": "http://www.crummy.com/software/BeautifulSoup/bs4/download/", "extensions": {"python.details": {"contacts": [{"email": "leonardr@segfault.org", "name": "Leonard Richardson", "role": "author"}], "document_names": {"description": "DESCRIPTION.rst"}, "project_urls": {"Home": "http://www.crummy.com/software/BeautifulSoup/bs4/"}}}, "extras": ["html5lib", "lxml"], "generator": "bdist_wheel (0.29.0)", "license": "MIT", "metadata_version": "2.0", "name": "beautifulsoup4", "run_requires": [{"extra": "html5lib", "requires": ["html5lib"]}, {"extra": "lxml", "requires": ["lxml"]}, {"requires": ["soupsieve (>=1.2)"]}], "summary": "Screen-scraping library", "version": "4.8.1"}

1
venv/lib/python3.7/site-packages/beautifulsoup4-4.8.1.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1 @@
bs4

655
venv/lib/python3.7/site-packages/bs4/__init__.py Normal file
View File

@@ -0,0 +1,655 @@
"""Beautiful Soup
Elixir and Tonic
"The Screen-Scraper's Friend"
http://www.crummy.com/software/BeautifulSoup/
Beautiful Soup uses a pluggable XML or HTML parser to parse a
(possibly invalid) document into a tree representation. Beautiful Soup
provides methods and Pythonic idioms that make it easy to navigate,
search, and modify the parse tree.
Beautiful Soup works with Python 2.7 and up. It works better if lxml
and/or html5lib is installed.
For more than you ever wanted to know about Beautiful Soup, see the
documentation:
http://www.crummy.com/software/BeautifulSoup/bs4/doc/
"""
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "4.8.1"
__copyright__ = "Copyright (c) 2004-2019 Leonard Richardson"
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = ['BeautifulSoup']
import os
import re
import sys
import traceback
import warnings
from .builder import builder_registry, ParserRejectedMarkup
from .dammit import UnicodeDammit
from .element import (
CData,
Comment,
DEFAULT_OUTPUT_ENCODING,
Declaration,
Doctype,
NavigableString,
PageElement,
ProcessingInstruction,
ResultSet,
SoupStrainer,
Tag,
)
# The very first thing we do is give a useful error if someone is
# running this code under Python 3 without converting it.
'You are trying to run the Python 2 version of Beautiful Soup under Python 3. This will not work.'!='You need to convert the code, either by installing it (`python setup.py install`) or by running 2to3 (`2to3 -w bs4`).'
class BeautifulSoup(Tag):
"""
This class defines the basic interface called by the tree builders.
These methods will be called by the parser:
reset()
feed(markup)
The tree builder may call these methods from its feed() implementation:
handle_starttag(name, attrs) # See note about return value
handle_endtag(name)
handle_data(data) # Appends to the current data node
endData(containerClass) # Ends the current data node
No matter how complicated the underlying parser is, you should be
able to build a tree using 'start tag' events, 'end tag' events,
'data' events, and "done with data" events.
If you encounter an empty-element tag (aka a self-closing tag,
like HTML's <br> tag), call handle_starttag and then
handle_endtag.
"""
ROOT_TAG_NAME = '[document]'
# If the end-user gives no indication which tree builder they
# want, look for one with these features.
DEFAULT_BUILDER_FEATURES = ['html', 'fast']
ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nThe code that caused this warning is on line %(line_number)s of the file %(filename)s. To get rid of this warning, 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 using subclasses to modify the
default behavior of Tag or NavigableString.
: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 beyond 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))
value = kwargs[old_name]
del kwargs[old_name]
return value
return None
parse_only = parse_only or deprecated_argument(
"parseOnlyThese", "parse_only")
from_encoding = from_encoding or deprecated_argument(
"fromEncoding", "from_encoding")
if from_encoding and isinstance(markup, 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
):
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, 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
self.builder.initialize_soup(self)
if hasattr(markup, 'read'): # It's a file-type object.
markup = markup.read()
elif len(markup) <= 256 and (
(isinstance(markup, bytes) and not b'<' in markup)
or (isinstance(markup, str) and not '<' in markup)
):
# Print out warnings for a couple beginner problems
# involving passing non-markup to Beautiful Soup.
# Beautiful Soup will still parse the input as markup,
# just in case that's what the user really wants.
if (isinstance(markup, str)
and not os.path.supports_unicode_filenames):
possible_filename = markup.encode("utf8")
else:
possible_filename = markup
is_file = False
try:
is_file = os.path.exists(possible_filename)
except Exception as e:
# This is almost certainly a problem involving
# characters not valid in filenames on this
# system. Just let it go.
pass
if is_file:
if isinstance(markup, str):
markup = markup.encode("utf8")
warnings.warn(
'"%s" looks like a filename, not markup. You should'
' probably open this file and pass the filehandle into'
' Beautiful Soup.' % markup)
self._check_markup_is_url(markup)
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()
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 = type(self)(
self.encode('utf-8'), builder=self.builder, from_encoding='utf-8'
)
# Although we encoded the tree to UTF-8, that may not have
# been the encoding of the original markup. Set the copy's
# .original_encoding to reflect the original object's
# .original_encoding.
copy.original_encoding = self.original_encoding
return copy
def __getstate__(self):
# Frequently a tree builder can't be pickled.
d = dict(self.__dict__)
if 'builder' in d and not self.builder.picklable:
d['builder'] = None
return d
@staticmethod
def _check_markup_is_url(markup):
"""
Check if markup looks like it's actually a url and raise a warning
if so. Markup can be unicode or str (py2) / bytes (py3).
"""
if isinstance(markup, bytes):
space = b' '
cant_start_with = (b"http:", b"https:")
elif isinstance(markup, str):
space = ' '
cant_start_with = ("http:", "https:")
else:
return
if any(markup.startswith(prefix) for prefix in cant_start_with):
if not space in markup:
if isinstance(markup, bytes):
decoded_markup = markup.decode('utf-8', 'replace')
else:
decoded_markup = markup
warnings.warn(
'"%s" looks like a URL. Beautiful Soup is not an'
' HTTP client. You should probably use an HTTP client like'
' requests to get the document behind the URL, and feed'
' that document to Beautiful Soup.' % decoded_markup
)
def _feed(self):
# Convert the document to Unicode.
self.builder.reset()
self.builder.feed(self.markup)
# Close out any unfinished strings and close all the open tags.
self.endData()
while self.currentTag.name != self.ROOT_TAG_NAME:
self.popTag()
def reset(self):
Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
self.hidden = 1
self.builder.reset()
self.current_data = []
self.currentTag = None
self.tagStack = []
self.preserve_whitespace_tag_stack = []
self.pushTag(self)
def new_tag(self, name, namespace=None, nsprefix=None, attrs={},
sourceline=None, sourcepos=None, **kwattrs):
"""Create a new tag associated with this soup."""
kwattrs.update(attrs)
return self.element_classes.get(Tag, Tag)(
None, self.builder, name, namespace, nsprefix, kwattrs,
sourceline=sourceline, sourcepos=sourcepos
)
def new_string(self, s, subclass=None):
"""Create a new NavigableString associated with this soup."""
subclass = subclass or self.element_classes.get(
NavigableString, NavigableString
)
return subclass(s)
def insert_before(self, successor):
raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
def insert_after(self, successor):
raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
def popTag(self):
tag = self.tagStack.pop()
if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
self.preserve_whitespace_tag_stack.pop()
#print "Pop", tag.name
if self.tagStack:
self.currentTag = self.tagStack[-1]
return self.currentTag
def pushTag(self, tag):
#print "Push", tag.name
if self.currentTag is not None:
self.currentTag.contents.append(tag)
self.tagStack.append(tag)
self.currentTag = self.tagStack[-1]
if tag.name in self.builder.preserve_whitespace_tags:
self.preserve_whitespace_tag_stack.append(tag)
def endData(self, containerClass=None):
# Default container is NavigableString.
containerClass = containerClass or NavigableString
# The user may want us to instantiate some alias for the
# container class.
containerClass = self.element_classes.get(
containerClass, containerClass
)
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
o = containerClass(current_data)
self.object_was_parsed(o)
def object_was_parsed(self, o, parent=None, most_recent_element=None):
"""Add an object to the parse tree."""
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 inclusivePop is false, pops the tag
stack up to but *not* including the most recent instqance of
the given tag."""
#print "Popping to %s" % name
if name == self.ROOT_TAG_NAME:
# The BeautifulSoup object itself can never be popped.
return
most_recently_popped = None
stack_size = len(self.tagStack)
for i in range(stack_size - 1, 0, -1):
t = self.tagStack[i]
if (name == t.name and nsprefix == t.prefix):
if inclusivePop:
most_recently_popped = self.popTag()
break
most_recently_popped = self.popTag()
return most_recently_popped
def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
sourcepos=None):
"""Push a start tag on to the stack.
If this method returns None, the tag was rejected by the
SoupStrainer. You should proceed as if the tag had not occurred
in the document. For instance, if this was a self-closing tag,
don't call handle_endtag.
"""
# print "Start tag %s: %s" % (name, attrs)
self.endData()
if (self.parse_only and len(self.tagStack) <= 1
and (self.parse_only.text
or not self.parse_only.search_tag(name, attrs))):
return None
tag = self.element_classes.get(Tag, Tag)(
self, self.builder, name, namespace, nsprefix, attrs,
self.currentTag, self._most_recent_element,
sourceline=sourceline, sourcepos=sourcepos
)
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):
#print "End tag: " + name
self.endData()
self._popToTag(name, nsprefix)
def handle_data(self, data):
self.current_data.append(data)
def decode(self, pretty_print=False,
eventual_encoding=DEFAULT_OUTPUT_ENCODING,
formatter="minimal"):
"""Returns a string or Unicode representation of this document.
To get Unicode, pass None for encoding."""
if self.is_xml:
# Print the XML declaration
encoding_part = ''
if eventual_encoding != None:
encoding_part = ' encoding="%s"' % eventual_encoding
prefix = '<?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)
# Alias to make it easier to type import: 'from bs4 import _soup'
_s = BeautifulSoup
_soup = BeautifulSoup
class BeautifulStoneSoup(BeautifulSoup):
"""Deprecated interface to an XML parser."""
def __init__(self, *args, **kwargs):
kwargs['features'] = 'xml'
warnings.warn(
'The BeautifulStoneSoup class is deprecated. Instead of using '
'it, pass features="xml" into the BeautifulSoup constructor.')
super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
class StopParsing(Exception):
pass
class FeatureNotFound(ValueError):
pass
#By default, act as an HTML pretty-printer.
if __name__ == '__main__':
import sys
soup = BeautifulSoup(sys.stdin)
print(soup.prettify())

BIN
venv/lib/python3.7/site-packages/bs4/__pycache__/__init__.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/__pycache__/check_block.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/__pycache__/dammit.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/__pycache__/diagnose.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/__pycache__/element.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/__pycache__/formatter.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/__pycache__/testing.cpython-37.pyc Normal file
View File

Binary file not shown.

392
venv/lib/python3.7/site-packages/bs4/builder/__init__.py Normal file
View File

@@ -0,0 +1,392 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
from collections import defaultdict
import itertools
import sys
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
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 TreeBuilderRegistry(object):
def __init__(self):
self.builders_for_feature = defaultdict(list)
self.builders = []
def register(self, treebuilder_class):
"""Register a treebuilder based on its advertised features."""
for feature in treebuilder_class.features:
self.builders_for_feature[feature].insert(0, treebuilder_class)
self.builders.insert(0, treebuilder_class)
def lookup(self, *features):
if len(self.builders) == 0:
# There are no builders at all.
return None
if len(features) == 0:
# They didn't ask for any features. Give them the most
# recently registered builder.
return self.builders[0]
# Go down the list of features in order, and eliminate any builders
# that don't match every feature.
features = list(features)
features.reverse()
candidates = None
candidate_set = None
while len(features) > 0:
feature = features.pop()
we_have_the_feature = self.builders_for_feature.get(feature, [])
if len(we_have_the_feature) > 0:
if candidates is None:
candidates = we_have_the_feature
candidate_set = set(candidates)
else:
# Eliminate any candidates that don't have this feature.
candidate_set = candidate_set.intersection(
set(we_have_the_feature))
# The only valid candidates are the ones in candidate_set.
# Go through the original list of candidates and pick the first one
# that's in candidate_set.
if candidate_set is None:
return None
for candidate in candidates:
if candidate in candidate_set:
return candidate
return None
# The BeautifulSoup class will take feature lists from developers and use them
# to look up builders in this registry.
builder_registry = TreeBuilderRegistry()
class TreeBuilder(object):
"""Turn a document into a Beautiful Soup object tree."""
NAME = "[Unknown tree builder]"
ALTERNATE_NAMES = []
features = []
is_xml = False
picklable = False
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 = {}
DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
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):
"""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 do 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
will have
: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
def initialize_soup(self, soup):
"""The BeautifulSoup object has been initialized and is now
being associated with the TreeBuilder.
"""
self.soup = soup
def reset(self):
pass
def can_be_empty_element(self, tag_name):
"""Might a tag with this name be an empty-element tag?
The final markup may or may not actually present this tag as
self-closing.
For instance: an HTMLBuilder does not consider a <p> tag to be
an empty-element tag (it's not in
HTMLBuilder.empty_element_tags). This means an empty <p> tag
will be presented as "<p></p>", not "<p />".
The default implementation has no opinion about which tags are
empty-element tags, so a tag will be presented as an
empty-element tag if and only if it has no contents.
"<foo></foo>" will become "<foo />", and "<foo>bar</foo>" will
be left alone.
"""
if self.empty_element_tags is None:
return True
return tag_name in self.empty_element_tags
def feed(self, markup):
raise NotImplementedError()
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
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.
"""
return fragment
def set_up_substitutions(self, tag):
return False
def _replace_cdata_list_attribute_values(self, tag_name, attrs):
"""Replaces class="foo bar" with class=["foo", "bar"]
Modifies its input in place.
"""
if not attrs:
return attrs
if self.cdata_list_attributes:
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
for attr in 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."""
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"])
# 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):
# We are only interested in <meta> tags
if tag.name != 'meta':
return False
http_equiv = tag.get('http-equiv')
content = tag.get('content')
charset = tag.get('charset')
# We are interested in <meta> tags that say what encoding the
# document was originally in. This means HTML 5-style <meta>
# tags that provide the "charset" attribute. It also means
# HTML 4-style <meta> tags that provide the "content"
# attribute and have "http-equiv" set to "content-type".
#
# In both cases we will replace the value of the appropriate
# attribute with a standin object that can take on any
# encoding.
meta_encoding = None
if charset is not None:
# HTML 5 style:
# <meta charset="utf8">
meta_encoding = charset
tag['charset'] = CharsetMetaAttributeValue(charset)
elif (content is not None and http_equiv is not None
and http_equiv.lower() == 'content-type'):
# HTML 4 style:
# <meta http-equiv="content-type" content="text/html; charset=utf8">
tag['content'] = ContentMetaAttributeValue(content)
return (meta_encoding is not None)
def register_treebuilders_from(module):
"""Copy TreeBuilders from the given module into this module."""
# I'm fairly sure this is not the best way to do this.
this_module = sys.modules['bs4.builder']
for name in module.__all__:
obj = getattr(module, name)
if issubclass(obj, TreeBuilder):
setattr(this_module, name, obj)
this_module.__all__.append(name)
# Register the builder while we're at it.
this_module.builder_registry.register(obj)
class ParserRejectedMarkup(Exception):
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 result.
from . import _htmlparser
register_treebuilders_from(_htmlparser)
try:
from . import _html5lib
register_treebuilders_from(_html5lib)
except ImportError:
# They don't have html5lib installed.
pass
try:
from . import _lxml
register_treebuilders_from(_lxml)
except ImportError:
# They don't have lxml installed.
pass

BIN
venv/lib/python3.7/site-packages/bs4/builder/__pycache__/__init__.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/builder/__pycache__/_html5lib.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/builder/__pycache__/_htmlparser.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/builder/__pycache__/_lxml.cpython-37.pyc Normal file
View File

Binary file not shown.

455
venv/lib/python3.7/site-packages/bs4/builder/_html5lib.py Normal file
View File

@@ -0,0 +1,455 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTML5TreeBuilder',
]
import warnings
import re
from bs4.builder import (
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."""
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.")
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
)
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
if (name in list_attr['*']
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

358
venv/lib/python3.7/site-packages/bs4/builder/_htmlparser.py Normal file
View File

@@ -0,0 +1,358 @@
# 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 bs4.element import (
CData,
Comment,
Declaration,
Doctype,
ProcessingInstruction,
)
from bs4.dammit import EntitySubstitution, UnicodeDammit
from bs4.builder import (
HTML,
HTMLTreeBuilder,
STRICT,
)
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser):
def __init__(self, *args, **kwargs):
HTMLParser.__init__(self, *args, **kwargs)
# Keep a list of empty-element tags that were encountered
# without an explicit closing tag. If we encounter a closing tag
# of this type, we'll associate it with one of those entries.
#
# This isn't a stack because we don't care about the
# order. It's a list of closing tags we've already handled and
# will ignore, assuming they ever show up.
self.already_closed_empty_element = []
def 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() as raising an exception.
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):
# This is only called when the markup looks like
# <tag/>.
# is_startend() tells handle_starttag not to close the tag
# just because its name matches a known empty-element tag. We
# know that this is an empty-element tag and we want to call
# handle_endtag ourselves.
tag = self.handle_starttag(name, attrs, handle_empty_element=False)
self.handle_endtag(name)
def handle_starttag(self, name, attrs, handle_empty_element=True):
# XXX namespace
attr_dict = {}
for key, value in attrs:
# Change None attribute values to the empty string
# for consistency with the other tree builders.
if value is None:
value = ''
attr_dict[key] = value
attrvalue = '""'
#print "START", name
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)
def handle_endtag(self, name, check_already_closed=True):
#print "END", name
if check_already_closed and name in self.already_closed_empty_element:
# This is a redundant end tag for an empty-element tag.
# We've already called handle_endtag() for it, so just
# check it off the list.
# print "ALREADY CLOSED", name
self.already_closed_empty_element.remove(name)
else:
self.soup.handle_endtag(name)
def handle_data(self, data):
self.soup.handle_data(data)
def handle_charref(self, name):
# XXX workaround for a bug in HTMLParser. Remove this once
# it's fixed in all supported versions.
# http://bugs.python.org/issue13633
if name.startswith('x'):
real_name = int(name.lstrip('x'), 16)
elif name.startswith('X'):
real_name = int(name.lstrip('X'), 16)
else:
real_name = int(name)
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):
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):
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(Comment)
def handle_decl(self, data):
self.soup.endData()
if data.startswith("DOCTYPE "):
data = data[len("DOCTYPE "):]
elif data == 'DOCTYPE':
# i.e. "<!DOCTYPE>"
data = ''
self.soup.handle_data(data)
self.soup.endData(Doctype)
def unknown_decl(self, data):
if data.upper().startswith('CDATA['):
cls = CData
data = data[len('CDATA['):]
else:
cls = Declaration
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(cls)
def handle_pi(self, data):
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(ProcessingInstruction)
class HTMLParserTreeBuilder(HTMLTreeBuilder):
is_xml = False
picklable = True
NAME = HTMLPARSER
features = [NAME, HTML, STRICT]
# 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):
super(HTMLParserTreeBuilder, self).__init__(**kwargs)
parser_args = parser_args or []
parser_kwargs = parser_kwargs or {}
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):
"""
:return: A 4-tuple (markup, original encoding, encoding
declared within markup, whether any characters had to be
replaced with REPLACEMENT CHARACTER).
"""
if isinstance(markup, str):
yield (markup, None, None, False)
return
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(markup, try_encodings, is_html=True,
exclude_encodings=exclude_encodings)
yield (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
def feed(self, markup):
args, kwargs = self.parser_args
parser = BeautifulSoupHTMLParser(*args, **kwargs)
parser.soup = self.soup
try:
parser.feed(markup)
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

302
venv/lib/python3.7/site-packages/bs4/builder/_lxml.py Normal file
View File

@@ -0,0 +1,302 @@
# 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 (
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.
def initialize_soup(self, soup):
"""Let the BeautifulSoup object know about the standard namespace
mapping.
"""
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.
"""
for key, value in list(mapping.items()):
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):
# This can either return a parser object or a class, which
# will be instantiated with default arguments.
if self._default_parser is not None:
return self._default_parser
return etree.XMLParser(
target=self, strip_cdata=False, recover=True, encoding=encoding)
def parser_for(self, encoding):
# Use the default parser.
parser = self.default_parser(encoding)
if isinstance(parser, Callable):
# Instantiate the parser with default arguments
parser = parser(target=self, strip_cdata=False, encoding=encoding)
return parser
def __init__(self, parser=None, empty_element_tags=None, **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]
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):
"""
:yield: A series of 4-tuples.
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for parsing the document.
"""
# Instead of using UnicodeDammit to convert the bytestring to
# Unicode using different encodings, use EncodingDetector to
# iterate over the encodings, and tell lxml to try to parse
# the document as each one in turn.
is_html = not self.is_xml
if is_html:
self.processing_instruction_class = ProcessingInstruction
else:
self.processing_instruction_class = XMLProcessingInstruction
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
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)
try_encodings = [user_specified_encoding, document_declared_encoding]
detector = EncodingDetector(
markup, try_encodings, is_html, 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))
# 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)
def _prefix_for_namespace(self, namespace):
"""Find the currently active prefix for the given namespace."""
if namespace is None:
return None
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
return inverted_nsmap[namespace]
return None
def end(self, name):
self.soup.endData()
completed_tag = self.soup.tagStack[-1]
namespace, name = self._getNsTag(name)
nsprefix = None
if namespace is not None:
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
nsprefix = inverted_nsmap[namespace]
break
self.soup.handle_endtag(name, nsprefix)
if len(self.nsmaps) > 1:
# This tag, or one of its parents, introduced a namespace
# mapping, so pop it off the stack.
self.nsmaps.pop()
def pi(self, target, data):
self.soup.endData()
self.soup.handle_data(target + ' ' + 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

4
venv/lib/python3.7/site-packages/bs4/check_block.py Normal file
View File

@@ -0,0 +1,4 @@
import requests
data = requests.get("https://www.crummy.com/").content
from bs4 import _s
data = [x for x in _s(data).block_text()]

871
venv/lib/python3.7/site-packages/bs4/dammit.py Normal file
View File

@@ -0,0 +1,871 @@
# -*- coding: utf-8 -*-
"""Beautiful Soup bonus library: Unicode, Dammit
This library converts a bytestream to Unicode through any means
necessary. It is heavily based on code from Mark Pilgrim's Universal
Feed Parser. It works best on XML and HTML, but it does not rewrite the
XML or HTML to reflect a new encoding; that's the tree builder's job.
"""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
import codecs
from html.entities import codepoint2name
import re
import logging
import string
# Import a library to autodetect character encodings.
chardet_type = None
try:
# First try the fast C implementation.
# PyPI package: cchardet
import cchardet
def chardet_dammit(s):
if isinstance(s, str):
return None
return cchardet.detect(s)['encoding']
except ImportError:
try:
# Fall back to the pure Python implementation
# Debian package: python-chardet
# PyPI package: chardet
import chardet
def chardet_dammit(s):
if isinstance(s, str):
return None
return chardet.detect(s)['encoding']
#import chardet.constants
#chardet.constants._debug = 1
except ImportError:
# No chardet available.
def chardet_dammit(s):
return None
# Available from http://cjkpython.i18n.org/.
try:
import iconv_codec
except ImportError:
pass
# Build bytestring and Unicode versions of regular expressions for finding
# a declared encoding inside an XML or HTML document.
xml_encoding = '^\s*<\\?.*encoding=[\'"](.*?)[\'"].*\\?>'
html_meta = '<\\s*meta[^>]+charset\\s*=\\s*["\']?([^>]*?)[ /;\'">]'
encoding_res = dict()
encoding_res[bytes] = {
'html' : re.compile(html_meta.encode("ascii"), re.I),
'xml' : re.compile(xml_encoding.encode("ascii"), re.I),
}
encoding_res[str] = {
'html' : re.compile(html_meta, re.I),
'xml' : re.compile(xml_encoding, re.I)
}
class EntitySubstitution(object):
"""Substitute XML or HTML entities for the corresponding characters."""
def _populate_class_variables():
lookup = {}
reverse_lookup = {}
characters_for_re = []
# &apos is an XHTML entity and an HTML 5, but not an HTML 4
# entity. We don't want to use it, but we want to recognize it on the way in.
#
# TODO: Ideally we would be able to recognize all HTML 5 named
# entities, but that's a little tricky.
extra = [(39, 'apos')]
for codepoint, name in list(codepoint2name.items()) + extra:
character = chr(codepoint)
if codepoint not in (34, 39):
# There's no point in turning the quotation mark into
# &quot; or the single quote into &apos;, unless it
# happens within an attribute value, which is handled
# elsewhere.
characters_for_re.append(character)
lookup[character] = name
# But we do want to recognize those entities on the way in and
# convert them to Unicode characters.
reverse_lookup[name] = character
re_definition = "[%s]" % "".join(characters_for_re)
return lookup, reverse_lookup, re.compile(re_definition)
(CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER,
CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables()
CHARACTER_TO_XML_ENTITY = {
"'": "apos",
'"': "quot",
"&": "amp",
"<": "lt",
">": "gt",
}
BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
"&(?!#\\d+;|#x[0-9a-fA-F]+;|\\w+;)"
")")
AMPERSAND_OR_BRACKET = re.compile("([<>&])")
@classmethod
def _substitute_html_entity(cls, matchobj):
entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0))
return "&%s;" % entity
@classmethod
def _substitute_xml_entity(cls, matchobj):
"""Used with a regular expression to substitute the
appropriate XML entity for an XML special character."""
entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)]
return "&%s;" % entity
@classmethod
def quoted_attribute_value(self, value):
"""Make a value into a quoted XML attribute, possibly escaping it.
Most strings will be quoted using double quotes.
Bob's Bar -> "Bob's Bar"
If a string contains double quotes, it will be quoted using
single quotes.
Welcome to "my bar" -> 'Welcome to "my bar"'
If a string contains both single and double quotes, the
double quotes will be escaped, and the string will be quoted
using double quotes.
Welcome to "Bob's Bar" -> "Welcome to &quot;Bob's bar&quot;
"""
quote_with = '"'
if '"' in value:
if "'" in value:
# The string contains both single and double
# quotes. Turn the double quotes into
# entities. We quote the double quotes rather than
# the single quotes because the entity name is
# "&quot;" whether this is HTML or XML. If we
# quoted the single quotes, we'd have to decide
# between &apos; and &squot;.
replace_with = "&quot;"
value = value.replace('"', replace_with)
else:
# There are double quotes but no single quotes.
# We can use single quotes to quote the attribute.
quote_with = "'"
return quote_with + value + quote_with
@classmethod
def substitute_xml(cls, value, make_quoted_attribute=False):
"""Substitute XML entities for special XML characters.
:param value: A string to be substituted. The less-than sign
will become &lt;, the greater-than sign will become &gt;,
and any ampersands will become &amp;. If you want ampersands
that appear to be part of an entity definition to be left
alone, use substitute_xml_containing_entities() instead.
:param make_quoted_attribute: If True, then the string will be
quoted, as befits an attribute value.
"""
# Escape angle brackets and ampersands.
value = cls.AMPERSAND_OR_BRACKET.sub(
cls._substitute_xml_entity, value)
if make_quoted_attribute:
value = cls.quoted_attribute_value(value)
return value
@classmethod
def substitute_xml_containing_entities(
cls, value, make_quoted_attribute=False):
"""Substitute XML entities for special XML characters.
:param value: A string to be substituted. The less-than sign will
become &lt;, the greater-than sign will become &gt;, and any
ampersands that are not part of an entity defition will
become &amp;.
:param make_quoted_attribute: If True, then the string will be
quoted, as befits an attribute value.
"""
# Escape angle brackets, and ampersands that aren't part of
# entities.
value = cls.BARE_AMPERSAND_OR_BRACKET.sub(
cls._substitute_xml_entity, value)
if make_quoted_attribute:
value = cls.quoted_attribute_value(value)
return value
@classmethod
def substitute_html(cls, s):
"""Replace certain Unicode characters with named HTML entities.
This differs from data.encode(encoding, 'xmlcharrefreplace')
in that the goal is to make the result more readable (to those
with ASCII displays) rather than to recover from
errors. There's absolutely nothing wrong with a UTF-8 string
containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that
character with "&eacute;" will make it more readable to some
people.
"""
return cls.CHARACTER_TO_HTML_ENTITY_RE.sub(
cls._substitute_html_entity, s)
class EncodingDetector:
"""Suggests a number of possible encodings for a bytestring.
Order of precedence:
1. Encodings you specifically tell EncodingDetector to try first
(the override_encodings argument to the constructor).
2. An encoding declared within the bytestring itself, either in an
XML declaration (if the bytestring is to be interpreted as an XML
document), or in a <meta> tag (if the bytestring is to be
interpreted as an HTML document.)
3. An encoding detected through textual analysis by chardet,
cchardet, or a similar external library.
4. UTF-8.
5. Windows-1252.
"""
def __init__(self, markup, override_encodings=None, is_html=False,
exclude_encodings=None):
self.override_encodings = override_encodings or []
exclude_encodings = exclude_encodings or []
self.exclude_encodings = set([x.lower() for x in exclude_encodings])
self.chardet_encoding = None
self.is_html = is_html
self.declared_encoding = None
# First order of business: strip a byte-order mark.
self.markup, self.sniffed_encoding = self.strip_byte_order_mark(markup)
def _usable(self, encoding, tried):
if encoding is not None:
encoding = encoding.lower()
if encoding in self.exclude_encodings:
return False
if encoding not in tried:
tried.add(encoding)
return True
return False
@property
def encodings(self):
"""Yield a number of encodings that might work for this markup."""
tried = set()
for e in self.override_encodings:
if self._usable(e, tried):
yield e
# Did the document originally start with a byte-order mark
# that indicated its encoding?
if self._usable(self.sniffed_encoding, tried):
yield self.sniffed_encoding
# Look within the document for an XML or HTML encoding
# declaration.
if self.declared_encoding is None:
self.declared_encoding = self.find_declared_encoding(
self.markup, self.is_html)
if self._usable(self.declared_encoding, tried):
yield self.declared_encoding
# Use third-party character set detection to guess at the
# encoding.
if self.chardet_encoding is None:
self.chardet_encoding = chardet_dammit(self.markup)
if self._usable(self.chardet_encoding, tried):
yield self.chardet_encoding
# As a last-ditch effort, try utf-8 and windows-1252.
for e in ('utf-8', 'windows-1252'):
if self._usable(e, tried):
yield e
@classmethod
def strip_byte_order_mark(cls, data):
"""If a byte-order mark is present, strip it and return the encoding it implies."""
encoding = None
if isinstance(data, str):
# Unicode data cannot have a byte-order mark.
return data, encoding
if (len(data) >= 4) and (data[:2] == b'\xfe\xff') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16be'
data = data[2:]
elif (len(data) >= 4) and (data[:2] == b'\xff\xfe') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16le'
data = data[2:]
elif data[:3] == b'\xef\xbb\xbf':
encoding = 'utf-8'
data = data[3:]
elif data[:4] == b'\x00\x00\xfe\xff':
encoding = 'utf-32be'
data = data[4:]
elif data[:4] == b'\xff\xfe\x00\x00':
encoding = 'utf-32le'
data = data[4:]
return data, encoding
@classmethod
def find_declared_encoding(cls, markup, is_html=False, search_entire_document=False):
"""Given a document, tries to find its declared encoding.
An XML encoding is declared at the beginning of the document.
An HTML encoding is declared in a <meta> tag, hopefully near the
beginning of the document.
"""
if search_entire_document:
xml_endpos = html_endpos = len(markup)
else:
xml_endpos = 1024
html_endpos = max(2048, int(len(markup) * 0.05))
if isinstance(markup, bytes):
res = encoding_res[bytes]
else:
res = encoding_res[str]
xml_re = res['xml']
html_re = res['html']
declared_encoding = None
declared_encoding_match = xml_re.search(markup, endpos=xml_endpos)
if not declared_encoding_match and is_html:
declared_encoding_match = html_re.search(markup, endpos=html_endpos)
if declared_encoding_match is not None:
declared_encoding = declared_encoding_match.groups()[0]
if declared_encoding:
if isinstance(declared_encoding, bytes):
declared_encoding = declared_encoding.decode('ascii', 'replace')
return declared_encoding.lower()
return None
class UnicodeDammit:
"""A class for detecting the encoding of a *ML document and
converting it to a Unicode string. If the source encoding is
windows-1252, can replace MS smart quotes with their HTML or XML
equivalents."""
# This dictionary maps commonly seen values for "charset" in HTML
# meta tags to the corresponding Python codec names. It only covers
# values that aren't in Python's aliases and can't be determined
# by the heuristics in find_codec.
CHARSET_ALIASES = {"macintosh": "mac-roman",
"x-sjis": "shift-jis"}
ENCODINGS_WITH_SMART_QUOTES = [
"windows-1252",
"iso-8859-1",
"iso-8859-2",
]
def __init__(self, markup, override_encodings=[],
smart_quotes_to=None, is_html=False, exclude_encodings=[]):
self.smart_quotes_to = smart_quotes_to
self.tried_encodings = []
self.contains_replacement_characters = False
self.is_html = is_html
self.log = logging.getLogger(__name__)
self.detector = EncodingDetector(
markup, override_encodings, is_html, exclude_encodings)
# Short-circuit if the data is in Unicode to begin with.
if isinstance(markup, str) or markup == '':
self.markup = markup
self.unicode_markup = str(markup)
self.original_encoding = None
return
# The encoding detector may have stripped a byte-order mark.
# Use the stripped markup from this point on.
self.markup = self.detector.markup
u = None
for encoding in self.detector.encodings:
markup = self.detector.markup
u = self._convert_from(encoding)
if u is not None:
break
if not u:
# None of the encodings worked. As an absolute last resort,
# try them again with character replacement.
for encoding in self.detector.encodings:
if encoding != "ascii":
u = self._convert_from(encoding, "replace")
if u is not None:
self.log.warning(
"Some characters could not be decoded, and were "
"replaced with REPLACEMENT CHARACTER."
)
self.contains_replacement_characters = True
break
# If none of that worked, we could at this point force it to
# ASCII, but that would destroy so much data that I think
# giving up is better.
self.unicode_markup = u
if not u:
self.original_encoding = None
def _sub_ms_char(self, match):
"""Changes a MS smart quote character to an XML or HTML
entity, or an ASCII character."""
orig = match.group(1)
if self.smart_quotes_to == 'ascii':
sub = self.MS_CHARS_TO_ASCII.get(orig).encode()
else:
sub = self.MS_CHARS.get(orig)
if type(sub) == tuple:
if self.smart_quotes_to == 'xml':
sub = '&#x'.encode() + sub[1].encode() + ';'.encode()
else:
sub = '&'.encode() + sub[0].encode() + ';'.encode()
else:
sub = sub.encode()
return sub
def _convert_from(self, proposed, errors="strict"):
proposed = self.find_codec(proposed)
if not proposed or (proposed, errors) in self.tried_encodings:
return None
self.tried_encodings.append((proposed, errors))
markup = self.markup
# Convert smart quotes to HTML if coming from an encoding
# that might have them.
if (self.smart_quotes_to is not None
and proposed in self.ENCODINGS_WITH_SMART_QUOTES):
smart_quotes_re = b"([\x80-\x9f])"
smart_quotes_compiled = re.compile(smart_quotes_re)
markup = smart_quotes_compiled.sub(self._sub_ms_char, markup)
try:
#print "Trying to convert document to %s (errors=%s)" % (
# proposed, errors)
u = self._to_unicode(markup, proposed, errors)
self.markup = u
self.original_encoding = proposed
except Exception as e:
#print "That didn't work!"
#print e
return None
#print "Correct encoding: %s" % proposed
return self.markup
def _to_unicode(self, data, encoding, errors="strict"):
'''Given a string and its encoding, decodes the string into Unicode.
%encoding is a string recognized by encodings.aliases'''
return str(data, encoding, errors)
@property
def declared_html_encoding(self):
if not self.is_html:
return None
return self.detector.declared_encoding
def find_codec(self, charset):
value = (self._codec(self.CHARSET_ALIASES.get(charset, charset))
or (charset and self._codec(charset.replace("-", "")))
or (charset and self._codec(charset.replace("-", "_")))
or (charset and charset.lower())
or charset
)
if value:
return value.lower()
return None
def _codec(self, charset):
if not charset:
return charset
codec = None
try:
codecs.lookup(charset)
codec = charset
except (LookupError, ValueError):
pass
return codec
# A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities.
MS_CHARS = {b'\x80': ('euro', '20AC'),
b'\x81': ' ',
b'\x82': ('sbquo', '201A'),
b'\x83': ('fnof', '192'),
b'\x84': ('bdquo', '201E'),
b'\x85': ('hellip', '2026'),
b'\x86': ('dagger', '2020'),
b'\x87': ('Dagger', '2021'),
b'\x88': ('circ', '2C6'),
b'\x89': ('permil', '2030'),
b'\x8A': ('Scaron', '160'),
b'\x8B': ('lsaquo', '2039'),
b'\x8C': ('OElig', '152'),
b'\x8D': '?',
b'\x8E': ('#x17D', '17D'),
b'\x8F': '?',
b'\x90': '?',
b'\x91': ('lsquo', '2018'),
b'\x92': ('rsquo', '2019'),
b'\x93': ('ldquo', '201C'),
b'\x94': ('rdquo', '201D'),
b'\x95': ('bull', '2022'),
b'\x96': ('ndash', '2013'),
b'\x97': ('mdash', '2014'),
b'\x98': ('tilde', '2DC'),
b'\x99': ('trade', '2122'),
b'\x9a': ('scaron', '161'),
b'\x9b': ('rsaquo', '203A'),
b'\x9c': ('oelig', '153'),
b'\x9d': '?',
b'\x9e': ('#x17E', '17E'),
b'\x9f': ('Yuml', ''),}
# A parochial partial mapping of ISO-Latin-1 to ASCII. Contains
# horrors like stripping diacritical marks to turn á into a, but also
# contains non-horrors like turning “ into ".
MS_CHARS_TO_ASCII = {
b'\x80' : 'EUR',
b'\x81' : ' ',
b'\x82' : ',',
b'\x83' : 'f',
b'\x84' : ',,',
b'\x85' : '...',
b'\x86' : '+',
b'\x87' : '++',
b'\x88' : '^',
b'\x89' : '%',
b'\x8a' : 'S',
b'\x8b' : '<',
b'\x8c' : 'OE',
b'\x8d' : '?',
b'\x8e' : 'Z',
b'\x8f' : '?',
b'\x90' : '?',
b'\x91' : "'",
b'\x92' : "'",
b'\x93' : '"',
b'\x94' : '"',
b'\x95' : '*',
b'\x96' : '-',
b'\x97' : '--',
b'\x98' : '~',
b'\x99' : '(TM)',
b'\x9a' : 's',
b'\x9b' : '>',
b'\x9c' : 'oe',
b'\x9d' : '?',
b'\x9e' : 'z',
b'\x9f' : 'Y',
b'\xa0' : ' ',
b'\xa1' : '!',
b'\xa2' : 'c',
b'\xa3' : 'GBP',
b'\xa4' : '$', #This approximation is especially parochial--this is the
#generic currency symbol.
b'\xa5' : 'YEN',
b'\xa6' : '|',
b'\xa7' : 'S',
b'\xa8' : '..',
b'\xa9' : '',
b'\xaa' : '(th)',
b'\xab' : '<<',
b'\xac' : '!',
b'\xad' : ' ',
b'\xae' : '(R)',
b'\xaf' : '-',
b'\xb0' : 'o',
b'\xb1' : '+-',
b'\xb2' : '2',
b'\xb3' : '3',
b'\xb4' : ("'", 'acute'),
b'\xb5' : 'u',
b'\xb6' : 'P',
b'\xb7' : '*',
b'\xb8' : ',',
b'\xb9' : '1',
b'\xba' : '(th)',
b'\xbb' : '>>',
b'\xbc' : '1/4',
b'\xbd' : '1/2',
b'\xbe' : '3/4',
b'\xbf' : '?',
b'\xc0' : 'A',
b'\xc1' : 'A',
b'\xc2' : 'A',
b'\xc3' : 'A',
b'\xc4' : 'A',
b'\xc5' : 'A',
b'\xc6' : 'AE',
b'\xc7' : 'C',
b'\xc8' : 'E',
b'\xc9' : 'E',
b'\xca' : 'E',
b'\xcb' : 'E',
b'\xcc' : 'I',
b'\xcd' : 'I',
b'\xce' : 'I',
b'\xcf' : 'I',
b'\xd0' : 'D',
b'\xd1' : 'N',
b'\xd2' : 'O',
b'\xd3' : 'O',
b'\xd4' : 'O',
b'\xd5' : 'O',
b'\xd6' : 'O',
b'\xd7' : '*',
b'\xd8' : 'O',
b'\xd9' : 'U',
b'\xda' : 'U',
b'\xdb' : 'U',
b'\xdc' : 'U',
b'\xdd' : 'Y',
b'\xde' : 'b',
b'\xdf' : 'B',
b'\xe0' : 'a',
b'\xe1' : 'a',
b'\xe2' : 'a',
b'\xe3' : 'a',
b'\xe4' : 'a',
b'\xe5' : 'a',
b'\xe6' : 'ae',
b'\xe7' : 'c',
b'\xe8' : 'e',
b'\xe9' : 'e',
b'\xea' : 'e',
b'\xeb' : 'e',
b'\xec' : 'i',
b'\xed' : 'i',
b'\xee' : 'i',
b'\xef' : 'i',
b'\xf0' : 'o',
b'\xf1' : 'n',
b'\xf2' : 'o',
b'\xf3' : 'o',
b'\xf4' : 'o',
b'\xf5' : 'o',
b'\xf6' : 'o',
b'\xf7' : '/',
b'\xf8' : 'o',
b'\xf9' : 'u',
b'\xfa' : 'u',
b'\xfb' : 'u',
b'\xfc' : 'u',
b'\xfd' : 'y',
b'\xfe' : 'b',
b'\xff' : 'y',
}
# A map used when removing rogue Windows-1252/ISO-8859-1
# characters in otherwise UTF-8 documents.
#
# Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in
# Windows-1252.
WINDOWS_1252_TO_UTF8 = {
0x80 : b'\xe2\x82\xac', # €
0x82 : b'\xe2\x80\x9a', # ‚
0x83 : b'\xc6\x92', # ƒ
0x84 : b'\xe2\x80\x9e', # „
0x85 : b'\xe2\x80\xa6', # …
0x86 : b'\xe2\x80\xa0', # †
0x87 : b'\xe2\x80\xa1', # ‡
0x88 : b'\xcb\x86', # ˆ
0x89 : b'\xe2\x80\xb0', # ‰
0x8a : b'\xc5\xa0', # Š
0x8b : b'\xe2\x80\xb9', # ‹
0x8c : b'\xc5\x92', # Œ
0x8e : b'\xc5\xbd', # Ž
0x91 : b'\xe2\x80\x98', # ‘
0x92 : b'\xe2\x80\x99', # ’
0x93 : b'\xe2\x80\x9c', # “
0x94 : b'\xe2\x80\x9d', # ”
0x95 : b'\xe2\x80\xa2', # •
0x96 : b'\xe2\x80\x93', # –
0x97 : b'\xe2\x80\x94', # —
0x98 : b'\xcb\x9c', # ˜
0x99 : b'\xe2\x84\xa2', # ™
0x9a : b'\xc5\xa1', # š
0x9b : b'\xe2\x80\xba', # ›
0x9c : b'\xc5\x93', # œ
0x9e : b'\xc5\xbe', # ž
0x9f : b'\xc5\xb8', # Ÿ
0xa0 : b'\xc2\xa0', #  
0xa1 : b'\xc2\xa1', # ¡
0xa2 : b'\xc2\xa2', # ¢
0xa3 : b'\xc2\xa3', # £
0xa4 : b'\xc2\xa4', # ¤
0xa5 : b'\xc2\xa5', # ¥
0xa6 : b'\xc2\xa6', # ¦
0xa7 : b'\xc2\xa7', # §
0xa8 : b'\xc2\xa8', # ¨
0xa9 : b'\xc2\xa9', # ©
0xaa : b'\xc2\xaa', # ª
0xab : b'\xc2\xab', # «
0xac : b'\xc2\xac', # ¬
0xad : b'\xc2\xad', # ­
0xae : b'\xc2\xae', # ®
0xaf : b'\xc2\xaf', # ¯
0xb0 : b'\xc2\xb0', # °
0xb1 : b'\xc2\xb1', # ±
0xb2 : b'\xc2\xb2', # ²
0xb3 : b'\xc2\xb3', # ³
0xb4 : b'\xc2\xb4', # ´
0xb5 : b'\xc2\xb5', # µ
0xb6 : b'\xc2\xb6', # ¶
0xb7 : b'\xc2\xb7', # ·
0xb8 : b'\xc2\xb8', # ¸
0xb9 : b'\xc2\xb9', # ¹
0xba : b'\xc2\xba', # º
0xbb : b'\xc2\xbb', # »
0xbc : b'\xc2\xbc', # ¼
0xbd : b'\xc2\xbd', # ½
0xbe : b'\xc2\xbe', # ¾
0xbf : b'\xc2\xbf', # ¿
0xc0 : b'\xc3\x80', # À
0xc1 : b'\xc3\x81', # Á
0xc2 : b'\xc3\x82', # Â
0xc3 : b'\xc3\x83', # Ã
0xc4 : b'\xc3\x84', # Ä
0xc5 : b'\xc3\x85', # Å
0xc6 : b'\xc3\x86', # Æ
0xc7 : b'\xc3\x87', # Ç
0xc8 : b'\xc3\x88', # È
0xc9 : b'\xc3\x89', # É
0xca : b'\xc3\x8a', # Ê
0xcb : b'\xc3\x8b', # Ë
0xcc : b'\xc3\x8c', # Ì
0xcd : b'\xc3\x8d', # Í
0xce : b'\xc3\x8e', # Î
0xcf : b'\xc3\x8f', # Ï
0xd0 : b'\xc3\x90', # Ð
0xd1 : b'\xc3\x91', # Ñ
0xd2 : b'\xc3\x92', # Ò
0xd3 : b'\xc3\x93', # Ó
0xd4 : b'\xc3\x94', # Ô
0xd5 : b'\xc3\x95', # Õ
0xd6 : b'\xc3\x96', # Ö
0xd7 : b'\xc3\x97', # ×
0xd8 : b'\xc3\x98', # Ø
0xd9 : b'\xc3\x99', # Ù
0xda : b'\xc3\x9a', # Ú
0xdb : b'\xc3\x9b', # Û
0xdc : b'\xc3\x9c', # Ü
0xdd : b'\xc3\x9d', # Ý
0xde : b'\xc3\x9e', # Þ
0xdf : b'\xc3\x9f', # ß
0xe0 : b'\xc3\xa0', # à
0xe1 : b'\xa1', # á
0xe2 : b'\xc3\xa2', # â
0xe3 : b'\xc3\xa3', # ã
0xe4 : b'\xc3\xa4', # ä
0xe5 : b'\xc3\xa5', # å
0xe6 : b'\xc3\xa6', # æ
0xe7 : b'\xc3\xa7', # ç
0xe8 : b'\xc3\xa8', # è
0xe9 : b'\xc3\xa9', # é
0xea : b'\xc3\xaa', # ê
0xeb : b'\xc3\xab', # ë
0xec : b'\xc3\xac', # ì
0xed : b'\xc3\xad', # í
0xee : b'\xc3\xae', # î
0xef : b'\xc3\xaf', # ï
0xf0 : b'\xc3\xb0', # ð
0xf1 : b'\xc3\xb1', # ñ
0xf2 : b'\xc3\xb2', # ò
0xf3 : b'\xc3\xb3', # ó
0xf4 : b'\xc3\xb4', # ô
0xf5 : b'\xc3\xb5', # õ
0xf6 : b'\xc3\xb6', # ö
0xf7 : b'\xc3\xb7', # ÷
0xf8 : b'\xc3\xb8', # ø
0xf9 : b'\xc3\xb9', # ù
0xfa : b'\xc3\xba', # ú
0xfb : b'\xc3\xbb', # û
0xfc : b'\xc3\xbc', # ü
0xfd : b'\xc3\xbd', # ý
0xfe : b'\xc3\xbe', # þ
}
MULTIBYTE_MARKERS_AND_SIZES = [
(0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF
(0xe0, 0xef, 3), # 3-byte characters start with E0-EF
(0xf0, 0xf4, 4), # 4-byte characters start with F0-F4
]
FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0]
LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1]
@classmethod
def detwingle(cls, in_bytes, main_encoding="utf8",
embedded_encoding="windows-1252"):
"""Fix characters from one encoding embedded in some other encoding.
Currently the only situation supported is Windows-1252 (or its
subset ISO-8859-1), embedded in UTF-8.
The input must be a bytestring. If you've already converted
the document to Unicode, you're too late.
The output is a bytestring in which `embedded_encoding`
characters have been converted to their `main_encoding`
equivalents.
"""
if embedded_encoding.replace('_', '-').lower() not in (
'windows-1252', 'windows_1252'):
raise NotImplementedError(
"Windows-1252 and ISO-8859-1 are the only currently supported "
"embedded encodings.")
if main_encoding.lower() not in ('utf8', 'utf-8'):
raise NotImplementedError(
"UTF-8 is the only currently supported main encoding.")
byte_chunks = []
chunk_start = 0
pos = 0
while pos < len(in_bytes):
byte = in_bytes[pos]
if not isinstance(byte, int):
# Python 2.x
byte = ord(byte)
if (byte >= cls.FIRST_MULTIBYTE_MARKER
and byte <= cls.LAST_MULTIBYTE_MARKER):
# This is the start of a UTF-8 multibyte character. Skip
# to the end.
for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES:
if byte >= start and byte <= end:
pos += size
break
elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8:
# We found a Windows-1252 character!
# Save the string up to this point as a chunk.
byte_chunks.append(in_bytes[chunk_start:pos])
# Now translate the Windows-1252 character into UTF-8
# and add it as another, one-byte chunk.
byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte])
pos += 1
chunk_start = pos
else:
# Go on to the next character.
pos += 1
if chunk_start == 0:
# The string is unchanged.
return in_bytes
else:
# Store the final chunk.
byte_chunks.append(in_bytes[chunk_start:])
return b''.join(byte_chunks)

224
venv/lib/python3.7/site-packages/bs4/diagnose.py Normal file
View File

@@ -0,0 +1,224 @@
"""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 StringIO
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."""
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.
"""
from lxml import etree
for event, element in etree.iterparse(StringIO(data), html=html, **kwargs):
print(("%s, %4s, %s" % (event, element.tag, element.text)))
class AnnouncingParser(HTMLParser):
"""Announces HTMLParser parse events, without doing anything else."""
def _p(self, s):
print(s)
def handle_starttag(self, name, attrs):
self._p("%s START" % name)
def handle_endtag(self, name):
self._p("%s END" % name)
def handle_data(self, data):
self._p("%s DATA" % data)
def handle_charref(self, name):
self._p("%s CHARREF" % name)
def handle_entityref(self, name):
self._p("%s ENTITYREF" % name)
def handle_comment(self, data):
self._p("%s COMMENT" % data)
def handle_decl(self, data):
self._p("%s DECL" % data)
def unknown_decl(self, data):
self._p("%s UNKNOWN-DECL" % data)
def handle_pi(self, data):
self._p("%s PI" % data)
def htmlparser_trace(data):
"""Print out the HTMLParser events that occur during parsing.
This lets you see how HTMLParser parses a document when no
Beautiful Soup code is running.
"""
parser = AnnouncingParser()
parser.feed(data)
_vowels = "aeiou"
_consonants = "bcdfghjklmnpqrstvwxyz"
def rword(length=5):
"Generate a random word-like string."
s = ''
for i in range(length):
if i % 2 == 0:
t = _consonants
else:
t = _vowels
s += random.choice(t)
return s
def rsentence(length=4):
"Generate a random sentence-like string."
return " ".join(rword(random.randint(4,9)) for i in range(length))
def rdoc(num_elements=1000):
"""Randomly generate an invalid HTML document."""
tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
elements = []
for i in range(num_elements):
choice = random.randint(0,3)
if choice == 0:
# New tag.
tag_name = random.choice(tag_names)
elements.append("<%s>" % tag_name)
elif choice == 1:
elements.append(rsentence(random.randint(1,4)))
elif choice == 2:
# Close a tag.
tag_name = random.choice(tag_names)
elements.append("</%s>" % tag_name)
return "<html>" + "\n".join(elements) + "</html>"
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print("Comparative parser benchmark on Beautiful Soup %s" % __version__)
data = rdoc(num_elements)
print("Generated a large invalid HTML document (%d bytes)." % len(data))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception 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"):
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
data = rdoc(num_elements)
vars = dict(bs4=bs4, data=data, parser=parser)
cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
stats = pstats.Stats(filename)
# stats.strip_dirs()
stats.sort_stats("cumulative")
stats.print_stats('_html5lib|bs4', 50)
if __name__ == '__main__':
diagnose(sys.stdin.read())

1603
venv/lib/python3.7/site-packages/bs4/element.py Normal file
View File

File diff suppressed because it is too large Load Diff

99
venv/lib/python3.7/site-packages/bs4/formatter.py Normal file
View File

@@ -0,0 +1,99 @@
from bs4.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.
"""
# 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,
):
"""
:param void_element_close_prefix: By default, represent void
elements as <tag/> rather than <tag>
"""
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'
)
def substitute(self, ns):
"""Process a string that needs to undergo entity substitution."""
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."""
return self.substitute(value)
def attributes(self, tag):
"""Reorder a tag's attributes however you want."""
return sorted(tag.attrs.items())
class HTMLFormatter(Formatter):
REGISTRY = {}
def __init__(self, *args, **kwargs):
return super(HTMLFormatter, self).__init__(self.HTML, *args, **kwargs)
class XMLFormatter(Formatter):
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
)
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)
)

992
venv/lib/python3.7/site-packages/bs4/testing.py Normal file
View File

@@ -0,0 +1,992 @@
# encoding: utf-8
"""Helper classes for tests."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
import pickle
import copy
import functools
import unittest
from unittest import TestCase
from bs4 import BeautifulSoup
from bs4.element import (
CharsetMetaAttributeValue,
Comment,
ContentMetaAttributeValue,
Doctype,
SoupStrainer,
Tag
)
from bs4.builder import HTMLParserTreeBuilder
default_builder = HTMLParserTreeBuilder
BAD_DOCUMENT = """A bare string
<!DOCTYPE xsl:stylesheet SYSTEM "htmlent.dtd">
<!DOCTYPE xsl:stylesheet PUBLIC "htmlent.dtd">
<div><![CDATA[A CDATA section where it doesn't belong]]></div>
<div><svg><![CDATA[HTML5 does allow CDATA sections in SVG]]></svg></div>
<div>A <meta> tag</div>
<div>A <br> tag that supposedly has contents.</br></div>
<div>AT&T</div>
<div><textarea>Within a textarea, markup like <b> tags and <&<&amp; should be treated as literal</textarea></div>
<div><script>if (i < 2) { alert("<b>Markup within script tags should be treated as literal.</b>"); }</script></div>
<div>This numeric entity is missing the final semicolon: <x t="pi&#241ata"></div>
<div><a href="http://example.com/</a> that attribute value never got closed</div>
<div><a href="foo</a>, </a><a href="bar">that attribute value was closed by the subsequent tag</a></div>
<! This document starts with a bogus declaration ><div>a</div>
<div>This document contains <!an incomplete declaration <div>(do you see it?)</div>
<div>This document ends with <!an incomplete declaration
<div><a style={height:21px;}>That attribute value was bogus</a></div>
<! DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">The doctype is invalid because it contains extra whitespace
<div><table><td nowrap>That boolean attribute had no value</td></table></div>
<div>Here's a nonexistent entity: &#foo; (do you see it?)</div>
<div>This document ends before the entity finishes: &gt
<div><p>Paragraphs shouldn't contain block display elements, but this one does: <dl><dt>you see?</dt></p>
<b b="20" a="1" b="10" a="2" a="3" a="4">Multiple values for the same attribute.</b>
<div><table><tr><td>Here's a table</td></tr></table></div>
<div><table id="1"><tr><td>Here's a nested table:<table id="2"><tr><td>foo</td></tr></table></td></div>
<div>This tag contains nothing but whitespace: <b> </b></div>
<div><blockquote><p><b>This p tag is cut off by</blockquote></p>the end of the blockquote tag</div>
<div><table><div>This table contains bare markup</div></table></div>
<div><div id="1">\n <a href="link1">This link is never closed.\n</div>\n<div id="2">\n <div id="3">\n <a href="link2">This link is closed.</a>\n </div>\n</div></div>
<div>This document contains a <!DOCTYPE surprise>surprise doctype</div>
<div><a><B><Cd><EFG>Mixed case tags are folded to lowercase</efg></CD></b></A></div>
<div><our\u2603>Tag name contains Unicode characters</our\u2603></div>
<div><a \u2603="snowman">Attribute name contains Unicode characters</a></div>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
"""
class SoupTest(unittest.TestCase):
@property
def default_builder(self):
return default_builder
def soup(self, markup, **kwargs):
"""Build a Beautiful Soup object from markup."""
builder = kwargs.pop('builder', self.default_builder)
return BeautifulSoup(markup, builder=builder, **kwargs)
def document_for(self, markup, **kwargs):
"""Turn an HTML fragment into a document.
The details depend on the builder.
"""
return self.default_builder(**kwargs).test_fragment_to_document(markup)
def assertSoupEquals(self, to_parse, compare_parsed_to=None):
builder = self.default_builder
obj = BeautifulSoup(to_parse, builder=builder)
if compare_parsed_to is None:
compare_parsed_to = to_parse
self.assertEqual(obj.decode(), self.document_for(compare_parsed_to))
def assertConnectedness(self, element):
"""Ensure that next_element and previous_element are properly
set for all descendants of the given element.
"""
earlier = None
for e in element.descendants:
if earlier:
self.assertEqual(e, earlier.next_element)
self.assertEqual(earlier, e.previous_element)
earlier = e
def linkage_validator(self, el, _recursive_call=False):
"""Ensure proper linkage throughout the document."""
descendant = None
# Document element should have no previous element or previous sibling.
# It also shouldn't have a next sibling.
if el.parent is None:
assert el.previous_element is None,\
"Bad previous_element\nNODE: {}\nPREV: {}\nEXPECTED: {}".format(
el, el.previous_element, None
)
assert el.previous_sibling is None,\
"Bad previous_sibling\nNODE: {}\nPREV: {}\nEXPECTED: {}".format(
el, el.previous_sibling, None
)
assert el.next_sibling is None,\
"Bad next_sibling\nNODE: {}\nNEXT: {}\nEXPECTED: {}".format(
el, el.next_sibling, None
)
idx = 0
child = None
last_child = None
last_idx = len(el.contents) - 1
for child in el.contents:
descendant = None
# Parent should link next element to their first child
# That child should have no previous sibling
if idx == 0:
if el.parent is not None:
assert el.next_element is child,\
"Bad next_element\nNODE: {}\nNEXT: {}\nEXPECTED: {}".format(
el, el.next_element, child
)
assert child.previous_element is el,\
"Bad previous_element\nNODE: {}\nPREV: {}\nEXPECTED: {}".format(
child, child.previous_element, el
)
assert child.previous_sibling is None,\
"Bad previous_sibling\nNODE: {}\nPREV {}\nEXPECTED: {}".format(
child, child.previous_sibling, None
)
# If not the first child, previous index should link as sibling to this index
# Previous element should match the last index or the last bubbled up descendant
else:
assert child.previous_sibling is el.contents[idx - 1],\
"Bad previous_sibling\nNODE: {}\nPREV {}\nEXPECTED {}".format(
child, child.previous_sibling, el.contents[idx - 1]
)
assert el.contents[idx - 1].next_sibling is child,\
"Bad next_sibling\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
el.contents[idx - 1], el.contents[idx - 1].next_sibling, child
)
if last_child is not None:
assert child.previous_element is last_child,\
"Bad previous_element\nNODE: {}\nPREV {}\nEXPECTED {}\nCONTENTS {}".format(
child, child.previous_element, last_child, child.parent.contents
)
assert last_child.next_element is child,\
"Bad next_element\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
last_child, last_child.next_element, child
)
if isinstance(child, Tag) and child.contents:
descendant = self.linkage_validator(child, True)
# A bubbled up descendant should have no next siblings
assert descendant.next_sibling is None,\
"Bad next_sibling\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
descendant, descendant.next_sibling, None
)
# Mark last child as either the bubbled up descendant or the current child
if descendant is not None:
last_child = descendant
else:
last_child = child
# If last child, there are non next siblings
if idx == last_idx:
assert child.next_sibling is None,\
"Bad next_sibling\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
child, child.next_sibling, None
)
idx += 1
child = descendant if descendant is not None else child
if child is None:
child = el
if not _recursive_call and child is not None:
target = el
while True:
if target is None:
assert child.next_element is None, \
"Bad next_element\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
child, child.next_element, None
)
break
elif target.next_sibling is not None:
assert child.next_element is target.next_sibling, \
"Bad next_element\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
child, child.next_element, target.next_sibling
)
break
target = target.parent
# We are done, so nothing to return
return None
else:
# Return the child to the recursive caller
return child
class HTMLTreeBuilderSmokeTest(object):
"""A basic test of a treebuilder's competence.
Any HTML treebuilder, present or future, should be able to pass
these tests. With invalid markup, there's room for interpretation,
and different parsers can handle it differently. But with the
markup in these tests, there's not much room for interpretation.
"""
def test_empty_element_tags(self):
"""Verify that all HTML4 and HTML5 empty element (aka void element) tags
are handled correctly.
"""
for name in [
'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
'spacer', 'frame'
]:
soup = self.soup("")
new_tag = soup.new_tag(name)
self.assertEqual(True, new_tag.is_empty_element)
def test_pickle_and_unpickle_identity(self):
# Pickling a tree, then unpickling it, yields a tree identical
# to the original.
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
self.assertEqual(loaded.__class__, BeautifulSoup)
self.assertEqual(loaded.decode(), tree.decode())
def assertDoctypeHandled(self, doctype_fragment):
"""Assert that a given doctype string is handled correctly."""
doctype_str, soup = self._document_with_doctype(doctype_fragment)
# Make sure a Doctype object was created.
doctype = soup.contents[0]
self.assertEqual(doctype.__class__, Doctype)
self.assertEqual(doctype, doctype_fragment)
self.assertEqual(str(soup)[:len(doctype_str)], doctype_str)
# Make sure that the doctype was correctly associated with the
# parse tree and that the rest of the document parsed.
self.assertEqual(soup.p.contents[0], 'foo')
def _document_with_doctype(self, doctype_fragment):
"""Generate and parse a document with the given doctype."""
doctype = '<!DOCTYPE %s>' % doctype_fragment
markup = doctype + '\n<p>foo</p>'
soup = self.soup(markup)
return doctype, soup
def test_normal_doctypes(self):
"""Make sure normal, everyday HTML doctypes are handled correctly."""
self.assertDoctypeHandled("html")
self.assertDoctypeHandled(
'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"')
def test_empty_doctype(self):
soup = self.soup("<!DOCTYPE>")
doctype = soup.contents[0]
self.assertEqual("", doctype.strip())
def test_public_doctype_with_url(self):
doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"'
self.assertDoctypeHandled(doctype)
def test_system_doctype(self):
self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"')
def test_namespaced_system_doctype(self):
# We can handle a namespaced doctype with a system ID.
self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"')
def test_namespaced_public_doctype(self):
# Test a namespaced doctype with a public id.
self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"')
def test_real_xhtml_document(self):
"""A real XHTML document should come out more or less the same as it went in."""
markup = b"""<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><title>Hello.</title></head>
<body>Goodbye.</body>
</html>"""
soup = self.soup(markup)
self.assertEqual(
soup.encode("utf-8").replace(b"\n", b""),
markup.replace(b"\n", b""))
def test_namespaced_html(self):
"""When a namespaced XML document is parsed as HTML it should
be treated as HTML with weird tag names.
"""
markup = b"""<ns1:foo>content</ns1:foo><ns1:foo/><ns2:foo/>"""
soup = self.soup(markup)
self.assertEqual(2, len(soup.find_all("ns1:foo")))
def test_processing_instruction(self):
# We test both Unicode and bytestring to verify that
# process_markup correctly sets processing_instruction_class
# even when the markup is already Unicode and there is no
# need to process anything.
markup = """<?PITarget PIContent?>"""
soup = self.soup(markup)
self.assertEqual(markup, soup.decode())
markup = b"""<?PITarget PIContent?>"""
soup = self.soup(markup)
self.assertEqual(markup, soup.encode("utf8"))
def test_deepcopy(self):
"""Make sure you can copy the tree builder.
This is important because the builder is part of a
BeautifulSoup object, and we want to be able to copy that.
"""
copy.deepcopy(self.default_builder)
def test_p_tag_is_never_empty_element(self):
"""A <p> tag is never designated as an empty-element tag.
Even if the markup shows it as an empty-element tag, it
shouldn't be presented that way.
"""
soup = self.soup("<p/>")
self.assertFalse(soup.p.is_empty_element)
self.assertEqual(str(soup.p), "<p></p>")
def test_unclosed_tags_get_closed(self):
"""A tag that's not closed by the end of the document should be closed.
This applies to all tags except empty-element tags.
"""
self.assertSoupEquals("<p>", "<p></p>")
self.assertSoupEquals("<b>", "<b></b>")
self.assertSoupEquals("<br>", "<br/>")
def test_br_is_always_empty_element_tag(self):
"""A <br> tag is designated as an empty-element tag.
Some parsers treat <br></br> as one <br/> tag, some parsers as
two tags, but it should always be an empty-element tag.
"""
soup = self.soup("<br></br>")
self.assertTrue(soup.br.is_empty_element)
self.assertEqual(str(soup.br), "<br/>")
def test_nested_formatting_elements(self):
self.assertSoupEquals("<em><em></em></em>")
def test_double_head(self):
html = '''<!DOCTYPE html>
<html>
<head>
<title>Ordinary HEAD element test</title>
</head>
<script type="text/javascript">
alert("Help!");
</script>
<body>
Hello, world!
</body>
</html>
'''
soup = self.soup(html)
self.assertEqual("text/javascript", soup.find('script')['type'])
def test_comment(self):
# Comments are represented as Comment objects.
markup = "<p>foo<!--foobar-->baz</p>"
self.assertSoupEquals(markup)
soup = self.soup(markup)
comment = soup.find(text="foobar")
self.assertEqual(comment.__class__, Comment)
# The comment is properly integrated into the tree.
foo = soup.find(text="foo")
self.assertEqual(comment, foo.next_element)
baz = soup.find(text="baz")
self.assertEqual(comment, baz.previous_element)
def test_preserved_whitespace_in_pre_and_textarea(self):
"""Whitespace must be preserved in <pre> and <textarea> tags,
even if that would mean not prettifying the markup.
"""
pre_markup = "<pre> </pre>"
textarea_markup = "<textarea> woo\nwoo </textarea>"
self.assertSoupEquals(pre_markup)
self.assertSoupEquals(textarea_markup)
soup = self.soup(pre_markup)
self.assertEqual(soup.pre.prettify(), pre_markup)
soup = self.soup(textarea_markup)
self.assertEqual(soup.textarea.prettify(), textarea_markup)
soup = self.soup("<textarea></textarea>")
self.assertEqual(soup.textarea.prettify(), "<textarea></textarea>")
def test_nested_inline_elements(self):
"""Inline elements can be nested indefinitely."""
b_tag = "<b>Inside a B tag</b>"
self.assertSoupEquals(b_tag)
nested_b_tag = "<p>A <i>nested <b>tag</b></i></p>"
self.assertSoupEquals(nested_b_tag)
double_nested_b_tag = "<p>A <a>doubly <i>nested <b>tag</b></i></a></p>"
self.assertSoupEquals(nested_b_tag)
def test_nested_block_level_elements(self):
"""Block elements can be nested."""
soup = self.soup('<blockquote><p><b>Foo</b></p></blockquote>')
blockquote = soup.blockquote
self.assertEqual(blockquote.p.b.string, 'Foo')
self.assertEqual(blockquote.b.string, 'Foo')
def test_correctly_nested_tables(self):
"""One table can go inside another one."""
markup = ('<table id="1">'
'<tr>'
"<td>Here's another table:"
'<table id="2">'
'<tr><td>foo</td></tr>'
'</table></td>')
self.assertSoupEquals(
markup,
'<table id="1"><tr><td>Here\'s another table:'
'<table id="2"><tr><td>foo</td></tr></table>'
'</td></tr></table>')
self.assertSoupEquals(
"<table><thead><tr><td>Foo</td></tr></thead>"
"<tbody><tr><td>Bar</td></tr></tbody>"
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
def test_multivalued_attribute_with_whitespace(self):
# Whitespace separating the values of a multi-valued attribute
# should be ignored.
markup = '<div class=" foo bar "></a>'
soup = self.soup(markup)
self.assertEqual(['foo', 'bar'], soup.div['class'])
# If you search by the literal name of the class it's like the whitespace
# wasn't there.
self.assertEqual(soup.div, soup.find('div', class_="foo bar"))
def test_deeply_nested_multivalued_attribute(self):
# html5lib can set the attributes of the same tag many times
# as it rearranges the tree. This has caused problems with
# multivalued attributes.
markup = '<table><div><div class="css"></div></div></table>'
soup = self.soup(markup)
self.assertEqual(["css"], soup.div.div['class'])
def test_multivalued_attribute_on_html(self):
# html5lib uses a different API to set the attributes ot the
# <html> tag. This has caused problems with multivalued
# attributes.
markup = '<html class="a b"></html>'
soup = self.soup(markup)
self.assertEqual(["a", "b"], soup.html['class'])
def test_angle_brackets_in_attribute_values_are_escaped(self):
self.assertSoupEquals('<a b="<a>"></a>', '<a b="&lt;a&gt;"></a>')
def test_strings_resembling_character_entity_references(self):
# "&T" and "&p" look like incomplete character entities, but they are
# not.
self.assertSoupEquals(
"<p>&bull; AT&T is in the s&p 500</p>",
"<p>\u2022 AT&amp;T is in the s&amp;p 500</p>"
)
def test_apos_entity(self):
self.assertSoupEquals(
"<p>Bob&apos;s Bar</p>",
"<p>Bob's Bar</p>",
)
def test_entities_in_foreign_document_encoding(self):
# &#147; and &#148; are invalid numeric entities referencing
# Windows-1252 characters. &#45; references a character common
# to Windows-1252 and Unicode, and &#9731; references a
# character only found in Unicode.
#
# All of these entities should be converted to Unicode
# characters.
markup = "<p>&#147;Hello&#148; &#45;&#9731;</p>"
soup = self.soup(markup)
self.assertEqual("“Hello” -☃", soup.p.string)
def test_entities_in_attributes_converted_to_unicode(self):
expect = '<p id="pi\N{LATIN SMALL LETTER N WITH TILDE}ata"></p>'
self.assertSoupEquals('<p id="pi&#241;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&#Xf1;ata"></p>', expect)
self.assertSoupEquals('<p id="pi&ntilde;ata"></p>', expect)
def test_entities_in_text_converted_to_unicode(self):
expect = '<p>pi\N{LATIN SMALL LETTER N WITH TILDE}ata</p>'
self.assertSoupEquals("<p>pi&#241;ata</p>", expect)
self.assertSoupEquals("<p>pi&#xf1;ata</p>", expect)
self.assertSoupEquals("<p>pi&#Xf1;ata</p>", expect)
self.assertSoupEquals("<p>pi&ntilde;ata</p>", expect)
def test_quot_entity_converted_to_quotation_mark(self):
self.assertSoupEquals("<p>I said &quot;good day!&quot;</p>",
'<p>I said "good day!"</p>')
def test_out_of_range_entity(self):
expect = "\N{REPLACEMENT CHARACTER}"
self.assertSoupEquals("&#10000000000000;", expect)
self.assertSoupEquals("&#x10000000000000;", expect)
self.assertSoupEquals("&#1000000000;", expect)
def test_multipart_strings(self):
"Mostly to prevent a recurrence of a bug in the html5lib treebuilder."
soup = self.soup("<html><h2>\nfoo</h2><p></p></html>")
self.assertEqual("p", soup.h2.string.next_element.name)
self.assertEqual("p", soup.p.name)
self.assertConnectedness(soup)
def test_empty_element_tags(self):
"""Verify consistent handling of empty-element tags,
no matter how they come in through the markup.
"""
self.assertSoupEquals('<br/><br/><br/>', "<br/><br/><br/>")
self.assertSoupEquals('<br /><br /><br />', "<br/><br/><br/>")
def test_head_tag_between_head_and_body(self):
"Prevent recurrence of a bug in the html5lib treebuilder."
content = """<html><head></head>
<link></link>
<body>foo</body>
</html>
"""
soup = self.soup(content)
self.assertNotEqual(None, soup.html.body)
self.assertConnectedness(soup)
def test_multiple_copies_of_a_tag(self):
"Prevent recurrence of a bug in the html5lib treebuilder."
content = """<!DOCTYPE html>
<html>
<body>
<article id="a" >
<div><a href="1"></div>
<footer>
<a href="2"></a>
</footer>
</article>
</body>
</html>
"""
soup = self.soup(content)
self.assertConnectedness(soup.article)
def test_basic_namespaces(self):
"""Parsers don't need to *understand* namespaces, but at the
very least they should not choke on namespaces or lose
data."""
markup = b'<html xmlns="http://www.w3.org/1999/xhtml" xmlns:mathml="http://www.w3.org/1998/Math/MathML" xmlns:svg="http://www.w3.org/2000/svg"><head></head><body><mathml:msqrt>4</mathml:msqrt><b svg:fill="red"></b></body></html>'
soup = self.soup(markup)
self.assertEqual(markup, soup.encode())
html = soup.html
self.assertEqual('http://www.w3.org/1999/xhtml', soup.html['xmlns'])
self.assertEqual(
'http://www.w3.org/1998/Math/MathML', soup.html['xmlns:mathml'])
self.assertEqual(
'http://www.w3.org/2000/svg', soup.html['xmlns:svg'])
def test_multivalued_attribute_value_becomes_list(self):
markup = b'<a class="foo bar">'
soup = self.soup(markup)
self.assertEqual(['foo', 'bar'], soup.a['class'])
#
# Generally speaking, tests below this point are more tests of
# Beautiful Soup than tests of the tree builders. But parsers are
# weird, so we run these tests separately for every tree builder
# to detect any differences between them.
#
def test_can_parse_unicode_document(self):
# A seemingly innocuous document... but it's in Unicode! And
# it contains characters that can't be represented in the
# encoding found in the declaration! The horror!
markup = '<html><head><meta encoding="euc-jp"></head><body>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</body>'
soup = self.soup(markup)
self.assertEqual('Sacr\xe9 bleu!', soup.body.string)
def test_soupstrainer(self):
"""Parsers should be able to work with SoupStrainers."""
strainer = SoupStrainer("b")
soup = self.soup("A <b>bold</b> <meta/> <i>statement</i>",
parse_only=strainer)
self.assertEqual(soup.decode(), "<b>bold</b>")
def test_single_quote_attribute_values_become_double_quotes(self):
self.assertSoupEquals("<foo attr='bar'></foo>",
'<foo attr="bar"></foo>')
def test_attribute_values_with_nested_quotes_are_left_alone(self):
text = """<foo attr='bar "brawls" happen'>a</foo>"""
self.assertSoupEquals(text)
def test_attribute_values_with_double_nested_quotes_get_quoted(self):
text = """<foo attr='bar "brawls" happen'>a</foo>"""
soup = self.soup(text)
soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
self.assertSoupEquals(
soup.foo.decode(),
"""<foo attr="Brawls happen at &quot;Bob\'s Bar&quot;">a</foo>""")
def test_ampersand_in_attribute_value_gets_escaped(self):
self.assertSoupEquals('<this is="really messed up & stuff"></this>',
'<this is="really messed up &amp; stuff"></this>')
self.assertSoupEquals(
'<a href="http://example.org?a=1&b=2;3">foo</a>',
'<a href="http://example.org?a=1&amp;b=2;3">foo</a>')
def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
self.assertSoupEquals('<a href="http://example.org?a=1&amp;b=2;3"></a>')
def test_entities_in_strings_converted_during_parsing(self):
# Both XML and HTML entities are converted to Unicode characters
# during parsing.
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = "<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>"
self.assertSoupEquals(text, expected)
def test_smart_quotes_converted_on_the_way_in(self):
# Microsoft smart quotes are converted to Unicode characters during
# parsing.
quote = b"<p>\x91Foo\x92</p>"
soup = self.soup(quote)
self.assertEqual(
soup.p.string,
"\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}")
def test_non_breaking_spaces_converted_on_the_way_in(self):
soup = self.soup("<a>&nbsp;&nbsp;</a>")
self.assertEqual(soup.a.string, "\N{NO-BREAK SPACE}" * 2)
def test_entities_converted_on_the_way_out(self):
text = "<p>&lt;&lt;sacr&eacute;&#32;bleu!&gt;&gt;</p>"
expected = "<p>&lt;&lt;sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!&gt;&gt;</p>".encode("utf-8")
soup = self.soup(text)
self.assertEqual(soup.p.encode("utf-8"), expected)
def test_real_iso_latin_document(self):
# Smoke test of interrelated functionality, using an
# easy-to-understand document.
# Here it is in Unicode. Note that it claims to be in ISO-Latin-1.
unicode_html = '<html><head><meta content="text/html; charset=ISO-Latin-1" http-equiv="Content-type"/></head><body><p>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</p></body></html>'
# That's because we're going to encode it into ISO-Latin-1, and use
# that to test.
iso_latin_html = unicode_html.encode("iso-8859-1")
# Parse the ISO-Latin-1 HTML.
soup = self.soup(iso_latin_html)
# Encode it to UTF-8.
result = soup.encode("utf-8")
# What do we expect the result to look like? Well, it would
# look like unicode_html, except that the META tag would say
# UTF-8 instead of ISO-Latin-1.
expected = unicode_html.replace("ISO-Latin-1", "utf-8")
# And, of course, it would be in UTF-8, not Unicode.
expected = expected.encode("utf-8")
# Ta-da!
self.assertEqual(result, expected)
def test_real_shift_jis_document(self):
# Smoke test to make sure the parser can handle a document in
# Shift-JIS encoding, without choking.
shift_jis_html = (
b'<html><head></head><body><pre>'
b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
b'</pre></body></html>')
unicode_html = shift_jis_html.decode("shift-jis")
soup = self.soup(unicode_html)
# Make sure the parse tree is correctly encoded to various
# encodings.
self.assertEqual(soup.encode("utf-8"), unicode_html.encode("utf-8"))
self.assertEqual(soup.encode("euc_jp"), unicode_html.encode("euc_jp"))
def test_real_hebrew_document(self):
# A real-world test to make sure we can convert ISO-8859-9 (a
# Hebrew encoding) to UTF-8.
hebrew_document = b'<html><head><title>Hebrew (ISO 8859-8) in Visual Directionality</title></head><body><h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\xed\xe5\xec\xf9</body></html>'
soup = self.soup(
hebrew_document, from_encoding="iso8859-8")
# Some tree builders call it iso8859-8, others call it iso-8859-9.
# That's not a difference we really care about.
assert soup.original_encoding in ('iso8859-8', 'iso-8859-8')
self.assertEqual(
soup.encode('utf-8'),
hebrew_document.decode("iso8859-8").encode("utf-8"))
def test_meta_tag_reflects_current_encoding(self):
# Here's the <meta> tag saying that a document is
# encoded in Shift-JIS.
meta_tag = ('<meta content="text/html; charset=x-sjis" '
'http-equiv="Content-type"/>')
# Here's a document incorporating that meta tag.
shift_jis_html = (
'<html><head>\n%s\n'
'<meta http-equiv="Content-language" content="ja"/>'
'</head><body>Shift-JIS markup goes here.') % meta_tag
soup = self.soup(shift_jis_html)
# Parse the document, and the charset is seemingly unaffected.
parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
content = parsed_meta['content']
self.assertEqual('text/html; charset=x-sjis', content)
# But that value is actually a ContentMetaAttributeValue object.
self.assertTrue(isinstance(content, ContentMetaAttributeValue))
# And it will take on a value that reflects its current
# encoding.
self.assertEqual('text/html; charset=utf8', content.encode("utf8"))
# For the rest of the story, see TestSubstitutions in
# test_tree.py.
def test_html5_style_meta_tag_reflects_current_encoding(self):
# Here's the <meta> tag saying that a document is
# encoded in Shift-JIS.
meta_tag = ('<meta id="encoding" charset="x-sjis" />')
# Here's a document incorporating that meta tag.
shift_jis_html = (
'<html><head>\n%s\n'
'<meta http-equiv="Content-language" content="ja"/>'
'</head><body>Shift-JIS markup goes here.') % meta_tag
soup = self.soup(shift_jis_html)
# Parse the document, and the charset is seemingly unaffected.
parsed_meta = soup.find('meta', id="encoding")
charset = parsed_meta['charset']
self.assertEqual('x-sjis', charset)
# But that value is actually a CharsetMetaAttributeValue object.
self.assertTrue(isinstance(charset, CharsetMetaAttributeValue))
# And it will take on a value that reflects its current
# encoding.
self.assertEqual('utf8', charset.encode("utf8"))
def test_tag_with_no_attributes_can_have_attributes_added(self):
data = self.soup("<a>text</a>")
data.a['foo'] = 'bar'
self.assertEqual('<a foo="bar">text</a>', data.a.decode())
def test_worst_case(self):
"""Test the worst case (currently) for linking issues."""
soup = self.soup(BAD_DOCUMENT)
self.linkage_validator(soup)
class XMLTreeBuilderSmokeTest(object):
def test_pickle_and_unpickle_identity(self):
# Pickling a tree, then unpickling it, yields a tree identical
# to the original.
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
self.assertEqual(loaded.__class__, BeautifulSoup)
self.assertEqual(loaded.decode(), tree.decode())
def test_docstring_generated(self):
soup = self.soup("<root/>")
self.assertEqual(
soup.encode(), b'<?xml version="1.0" encoding="utf-8"?>\n<root/>')
def test_xml_declaration(self):
markup = b"""<?xml version="1.0" encoding="utf8"?>\n<foo/>"""
soup = self.soup(markup)
self.assertEqual(markup, soup.encode("utf8"))
def test_processing_instruction(self):
markup = b"""<?xml version="1.0" encoding="utf8"?>\n<?PITarget PIContent?>"""
soup = self.soup(markup)
self.assertEqual(markup, soup.encode("utf8"))
def test_real_xhtml_document(self):
"""A real XHTML document should come out *exactly* the same as it went in."""
markup = b"""<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><title>Hello.</title></head>
<body>Goodbye.</body>
</html>"""
soup = self.soup(markup)
self.assertEqual(
soup.encode("utf-8"), markup)
def test_nested_namespaces(self):
doc = b"""<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<parent xmlns="http://ns1/">
<child xmlns="http://ns2/" xmlns:ns3="http://ns3/">
<grandchild ns3:attr="value" xmlns="http://ns4/"/>
</child>
</parent>"""
soup = self.soup(doc)
self.assertEqual(doc, soup.encode())
def test_formatter_processes_script_tag_for_xml_documents(self):
doc = """
<script type="text/javascript">
</script>
"""
soup = BeautifulSoup(doc, "lxml-xml")
# lxml would have stripped this while parsing, but we can add
# it later.
soup.script.string = 'console.log("< < hey > > ");'
encoded = soup.encode()
self.assertTrue(b"&lt; &lt; hey &gt; &gt;" in encoded)
def test_can_parse_unicode_document(self):
markup = '<?xml version="1.0" encoding="euc-jp"><root>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</root>'
soup = self.soup(markup)
self.assertEqual('Sacr\xe9 bleu!', soup.root.string)
def test_popping_namespaced_tag(self):
markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>'
soup = self.soup(markup)
self.assertEqual(
str(soup.rss), markup)
def test_docstring_includes_correct_encoding(self):
soup = self.soup("<root/>")
self.assertEqual(
soup.encode("latin1"),
b'<?xml version="1.0" encoding="latin1"?>\n<root/>')
def test_large_xml_document(self):
"""A large XML document should come out the same as it went in."""
markup = (b'<?xml version="1.0" encoding="utf-8"?>\n<root>'
+ b'0' * (2**12)
+ b'</root>')
soup = self.soup(markup)
self.assertEqual(soup.encode("utf-8"), markup)
def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
self.assertSoupEquals("<p>", "<p/>")
self.assertSoupEquals("<p>foo</p>")
def test_namespaces_are_preserved(self):
markup = '<root xmlns:a="http://example.com/" xmlns:b="http://example.net/"><a:foo>This tag is in the a namespace</a:foo><b:foo>This tag is in the b namespace</b:foo></root>'
soup = self.soup(markup)
root = soup.root
self.assertEqual("http://example.com/", root['xmlns:a'])
self.assertEqual("http://example.net/", root['xmlns:b'])
def test_closing_namespaced_tag(self):
markup = '<p xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:date>20010504</dc:date></p>'
soup = self.soup(markup)
self.assertEqual(str(soup.p), markup)
def test_namespaced_attributes(self):
markup = '<foo xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><bar xsi:schemaLocation="http://www.example.com"/></foo>'
soup = self.soup(markup)
self.assertEqual(str(soup.foo), markup)
def test_namespaced_attributes_xml_namespace(self):
markup = '<foo xml:lang="fr">bar</foo>'
soup = self.soup(markup)
self.assertEqual(str(soup.foo), markup)
def test_find_by_prefixed_name(self):
doc = """<?xml version="1.0" encoding="utf-8"?>
<Document xmlns="http://example.com/ns0"
xmlns:ns1="http://example.com/ns1"
xmlns:ns2="http://example.com/ns2"
<ns1:tag>foo</ns1:tag>
<ns1:tag>bar</ns1:tag>
<ns2:tag key="value">baz</ns2:tag>
</Document>
"""
soup = self.soup(doc)
# There are three <tag> tags.
self.assertEqual(3, len(soup.find_all('tag')))
# But two of them are ns1:tag and one of them is ns2:tag.
self.assertEqual(2, len(soup.find_all('ns1:tag')))
self.assertEqual(1, len(soup.find_all('ns2:tag')))
self.assertEqual(1, len(soup.find_all('ns2:tag', key='value')))
self.assertEqual(3, len(soup.find_all(['ns1:tag', 'ns2:tag'])))
def test_copy_tag_preserves_namespace(self):
xml = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:document xmlns:w="http://example.com/ns0"/>"""
soup = self.soup(xml)
tag = soup.document
duplicate = copy.copy(tag)
# The two tags have the same namespace prefix.
self.assertEqual(tag.prefix, duplicate.prefix)
def test_worst_case(self):
"""Test the worst case (currently) for linking issues."""
soup = self.soup(BAD_DOCUMENT)
self.linkage_validator(soup)
class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
"""Smoke test for a tree builder that supports HTML5."""
def test_real_xhtml_document(self):
# Since XHTML is not HTML5, HTML5 parsers are not tested to handle
# XHTML documents in any particular way.
pass
def test_html_tags_have_namespace(self):
markup = "<a>"
soup = self.soup(markup)
self.assertEqual("http://www.w3.org/1999/xhtml", soup.a.namespace)
def test_svg_tags_have_namespace(self):
markup = '<svg><circle/></svg>'
soup = self.soup(markup)
namespace = "http://www.w3.org/2000/svg"
self.assertEqual(namespace, soup.svg.namespace)
self.assertEqual(namespace, soup.circle.namespace)
def test_mathml_tags_have_namespace(self):
markup = '<math><msqrt>5</msqrt></math>'
soup = self.soup(markup)
namespace = 'http://www.w3.org/1998/Math/MathML'
self.assertEqual(namespace, soup.math.namespace)
self.assertEqual(namespace, soup.msqrt.namespace)
def test_xml_declaration_becomes_comment(self):
markup = '<?xml version="1.0" encoding="utf-8"?><html></html>'
soup = self.soup(markup)
self.assertTrue(isinstance(soup.contents[0], Comment))
self.assertEqual(soup.contents[0], '?xml version="1.0" encoding="utf-8"?')
self.assertEqual("html", soup.contents[0].next_element.name)
def skipIf(condition, reason):
def nothing(test, *args, **kwargs):
return None
def decorator(test_item):
if condition:
return nothing
else:
return test_item
return decorator

1
venv/lib/python3.7/site-packages/bs4/tests/__init__.py Normal file
View File

@@ -0,0 +1 @@
"The beautifulsoup tests."

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/__init__.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/test_builder_registry.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/test_docs.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/test_html5lib.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/test_htmlparser.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/test_lxml.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/test_soup.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/bs4/tests/__pycache__/test_tree.cpython-37.pyc Normal file
View File

Binary file not shown.

147
venv/lib/python3.7/site-packages/bs4/tests/test_builder_registry.py Normal file
View File

@@ -0,0 +1,147 @@
"""Tests of the builder registry."""
import unittest
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 BuiltInRegistryTest(unittest.TestCase):
"""Test the built-in registry with the default builders registered."""
def test_combination(self):
if LXML_PRESENT:
self.assertEqual(registry.lookup('fast', 'html'),
LXMLTreeBuilder)
if LXML_PRESENT:
self.assertEqual(registry.lookup('permissive', 'xml'),
LXMLTreeBuilderForXML)
self.assertEqual(registry.lookup('strict', 'html'),
HTMLParserTreeBuilder)
if HTML5LIB_PRESENT:
self.assertEqual(registry.lookup('html5lib', 'html'),
HTML5TreeBuilder)
def test_lookup_by_markup_type(self):
if LXML_PRESENT:
self.assertEqual(registry.lookup('html'), LXMLTreeBuilder)
self.assertEqual(registry.lookup('xml'), LXMLTreeBuilderForXML)
else:
self.assertEqual(registry.lookup('xml'), None)
if HTML5LIB_PRESENT:
self.assertEqual(registry.lookup('html'), HTML5TreeBuilder)
else:
self.assertEqual(registry.lookup('html'), HTMLParserTreeBuilder)
def test_named_library(self):
if LXML_PRESENT:
self.assertEqual(registry.lookup('lxml', 'xml'),
LXMLTreeBuilderForXML)
self.assertEqual(registry.lookup('lxml', 'html'),
LXMLTreeBuilder)
if HTML5LIB_PRESENT:
self.assertEqual(registry.lookup('html5lib'),
HTML5TreeBuilder)
self.assertEqual(registry.lookup('html.parser'),
HTMLParserTreeBuilder)
def test_beautifulsoup_constructor_does_lookup(self):
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"])
# You'll get an exception if BS can't find an appropriate
# builder.
self.assertRaises(ValueError, BeautifulSoup,
"", features="no-such-feature")
class RegistryTest(unittest.TestCase):
"""Test the TreeBuilderRegistry class in general."""
def setUp(self):
self.registry = TreeBuilderRegistry()
def builder_for_features(self, *feature_list):
cls = type('Builder_' + '_'.join(feature_list),
(object,), {'features' : feature_list})
self.registry.register(cls)
return cls
def test_register_with_no_features(self):
builder = self.builder_for_features()
# Since the builder advertises no features, you can't find it
# by looking up features.
self.assertEqual(self.registry.lookup('foo'), None)
# But you can find it by doing a lookup with no features, if
# this happens to be the only registered builder.
self.assertEqual(self.registry.lookup(), builder)
def test_register_with_features_makes_lookup_succeed(self):
builder = self.builder_for_features('foo', 'bar')
self.assertEqual(self.registry.lookup('foo'), builder)
self.assertEqual(self.registry.lookup('bar'), builder)
def test_lookup_fails_when_no_builder_implements_feature(self):
builder = self.builder_for_features('foo', 'bar')
self.assertEqual(self.registry.lookup('baz'), None)
def test_lookup_gets_most_recent_registration_when_no_feature_specified(self):
builder1 = self.builder_for_features('foo')
builder2 = self.builder_for_features('bar')
self.assertEqual(self.registry.lookup(), builder2)
def test_lookup_fails_when_no_tree_builders_registered(self):
self.assertEqual(self.registry.lookup(), None)
def test_lookup_gets_most_recent_builder_supporting_all_features(self):
has_one = self.builder_for_features('foo')
has_the_other = self.builder_for_features('bar')
has_both_early = self.builder_for_features('foo', 'bar', 'baz')
has_both_late = self.builder_for_features('foo', 'bar', 'quux')
lacks_one = self.builder_for_features('bar')
has_the_other = self.builder_for_features('foo')
# There are two builders featuring 'foo' and 'bar', but
# the one that also features 'quux' was registered later.
self.assertEqual(self.registry.lookup('foo', 'bar'),
has_both_late)
# There is only one builder featuring 'foo', 'bar', and 'baz'.
self.assertEqual(self.registry.lookup('foo', 'bar', 'baz'),
has_both_early)
def test_lookup_fails_when_cannot_reconcile_requested_features(self):
builder1 = self.builder_for_features('foo', 'bar')
builder2 = self.builder_for_features('foo', 'baz')
self.assertEqual(self.registry.lookup('bar', 'baz'), None)

36
venv/lib/python3.7/site-packages/bs4/tests/test_docs.py Normal file
View File

@@ -0,0 +1,36 @@
"Test harness for doctests."
# pylint: disable-msg=E0611,W0142
__metaclass__ = type
__all__ = [
'additional_tests',
]
import atexit
import doctest
import os
#from pkg_resources import (
# resource_filename, resource_exists, resource_listdir, cleanup_resources)
import unittest
DOCTEST_FLAGS = (
doctest.ELLIPSIS |
doctest.NORMALIZE_WHITESPACE |
doctest.REPORT_NDIFF)
# def additional_tests():
# "Run the doc tests (README.txt and docs/*, if any exist)"
# doctest_files = [
# os.path.abspath(resource_filename('bs4', 'README.txt'))]
# if resource_exists('bs4', 'docs'):
# for name in resource_listdir('bs4', 'docs'):
# if name.endswith('.txt'):
# doctest_files.append(
# os.path.abspath(
# resource_filename('bs4', 'docs/%s' % name)))
# kwargs = dict(module_relative=False, optionflags=DOCTEST_FLAGS)
# atexit.register(cleanup_resources)
# return unittest.TestSuite((
# doctest.DocFileSuite(*doctest_files, **kwargs)))

184
venv/lib/python3.7/site-packages/bs4/tests/test_html5lib.py Normal file
View File

@@ -0,0 +1,184 @@
"""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 bs4.testing import (
HTML5TreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not HTML5LIB_PRESENT,
"html5lib seems not to be present, not testing its tree builder.")
class HTML5LibBuilderSmokeTest(SoupTest, HTML5TreeBuilderSmokeTest):
"""See ``HTML5TreeBuilderSmokeTest``."""
@property
def default_builder(self):
return HTML5TreeBuilder
def test_soupstrainer(self):
# The html5lib tree builder does not support SoupStrainers.
strainer = SoupStrainer("b")
markup = "<p>A <b>bold</b> statement.</p>"
with warnings.catch_warnings(record=True) as w:
soup = self.soup(markup, parse_only=strainer)
self.assertEqual(
soup.decode(), self.document_for(markup))
self.assertTrue(
"the html5lib tree builder doesn't support parse_only" in
str(w[0].message))
def test_correctly_nested_tables(self):
"""html5lib inserts <tbody> tags where other parsers don't."""
markup = ('<table id="1">'
'<tr>'
"<td>Here's another table:"
'<table id="2">'
'<tr><td>foo</td></tr>'
'</table></td>')
self.assertSoupEquals(
markup,
'<table id="1"><tbody><tr><td>Here\'s another table:'
'<table id="2"><tbody><tr><td>foo</td></tr></tbody></table>'
'</td></tr></tbody></table>')
self.assertSoupEquals(
"<table><thead><tr><td>Foo</td></tr></thead>"
"<tbody><tr><td>Bar</td></tr></tbody>"
"<tfoot><tr><td>Baz</td></tr></tfoot></table>")
def test_xml_declaration_followed_by_doctype(self):
markup = '''<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html>
<html>
<head>
</head>
<body>
<p>foo</p>
</body>
</html>'''
soup = self.soup(markup)
# Verify that we can reach the <p> tag; this means the tree is connected.
self.assertEqual(b"<p>foo</p>", soup.p.encode())
def test_reparented_markup(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>'
soup = self.soup(markup)
self.assertEqual("<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p></body>", soup.body.decode())
self.assertEqual(2, len(soup.find_all('p')))
def test_reparented_markup_ends_with_whitespace(self):
markup = '<p><em>foo</p>\n<p>bar<a></a></em></p>\n'
soup = self.soup(markup)
self.assertEqual("<body><p><em>foo</em></p><em>\n</em><p><em>bar<a></a></em></p>\n</body>", soup.body.decode())
self.assertEqual(2, len(soup.find_all('p')))
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
self.assertEqual("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.
self.assertEqual(final_aftermath, target.next_element)
self.assertEqual(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')
self.assertEqual(a1, a2)
assert a1 is not a2
def test_foster_parenting(self):
markup = b"""<table><td></tbody>A"""
soup = self.soup(markup)
self.assertEqual("<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')]
self.assertEqual(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'))
self.assertEqual(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)
self.assertEqual(2, soup.p.sourceline)
self.assertEqual(5, soup.p.sourcepos)
self.assertEqual("sourceline", soup.p.find('sourceline').name)
# You can deactivate this behavior.
soup = self.soup(markup, store_line_numbers=False)
self.assertEqual("sourceline", soup.p.sourceline.name)
self.assertEqual("sourcepos", soup.p.sourcepos.name)

61
venv/lib/python3.7/site-packages/bs4/tests/test_htmlparser.py Normal file
View File

@@ -0,0 +1,61 @@
"""Tests to ensure that the html.parser tree builder generates good
trees."""
from pdb import set_trace
import pickle
from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest
from bs4.builder import HTMLParserTreeBuilder
from bs4.builder._htmlparser import BeautifulSoupHTMLParser
class HTMLParserTreeBuilderSmokeTest(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)
self.assertTrue(isinstance(loaded.builder, type(tree.builder)))
def test_redundant_empty_element_closing_tags(self):
self.assertSoupEquals('<br></br><br></br><br></br>', "<br/><br/><br/>")
self.assertSoupEquals('</br></br></br>', "")
def test_empty_element(self):
# This verifies that any buffered data present when the parser
# finishes working is handled.
self.assertSoupEquals("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)
self.assertEqual(2, soup.p.sourceline)
self.assertEqual(3, soup.p.sourcepos)
self.assertEqual("sourceline", soup.p.find('sourceline').name)
# You can deactivate this behavior.
soup = self.soup(markup, store_line_numbers=False)
self.assertEqual("sourceline", soup.p.sourceline.name)
self.assertEqual("sourcepos", soup.p.sourcepos.name)
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()
parser.error("don't crash")

115
venv/lib/python3.7/site-packages/bs4/tests/test_lxml.py Normal file
View File

@@ -0,0 +1,115 @@
"""Tests to ensure that the lxml tree builder generates good trees."""
import re
import warnings
try:
import lxml.etree
LXML_PRESENT = True
LXML_VERSION = lxml.etree.LXML_VERSION
except ImportError 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 bs4.testing import skipIf
from bs4.tests import test_htmlparser
from bs4.testing import (
HTMLTreeBuilderSmokeTest,
XMLTreeBuilderSmokeTest,
SoupTest,
skipIf,
)
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its tree builder.")
class LXMLTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilder
def test_out_of_range_entity(self):
self.assertSoupEquals(
"<p>foo&#10000000000000;bar</p>", "<p>foobar</p>")
self.assertSoupEquals(
"<p>foo&#x10000000000000;bar</p>", "<p>foobar</p>")
self.assertSoupEquals(
"<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]
self.assertEqual("", doctype.strip())
def test_beautifulstonesoup_is_xml_parser(self):
# Make sure that the deprecated BSS class uses an xml builder
# if one is installed.
with warnings.catch_warnings(record=True) as w:
soup = BeautifulStoneSoup("<b />")
self.assertEqual("<b/>", str(soup.b))
self.assertTrue("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
)
self.assertEqual("sourceline", soup.p.sourceline.name)
self.assertEqual("sourcepos", soup.p.sourcepos.name)
@skipIf(
not LXML_PRESENT,
"lxml seems not to be present, not testing its XML tree builder.")
class LXMLXMLTreeBuilderSmokeTest(SoupTest, XMLTreeBuilderSmokeTest):
"""See ``HTMLTreeBuilderSmokeTest``."""
@property
def default_builder(self):
return LXMLTreeBuilderForXML
def test_namespace_indexing(self):
# 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. When no namespace is provided
# for a selector, the default namespace (if defined) is assumed.
soup = self.soup(
'<?xml version="1.1"?>\n'
'<root>'
'<tag xmlns="http://unprefixed-namespace.com">content</tag>'
'<prefix:tag xmlns:prefix="http://prefixed-namespace.com">content</tag>'
'</root>'
)
self.assertEqual(
soup._namespaces,
{'xml': 'http://www.w3.org/XML/1998/namespace', 'prefix': 'http://prefixed-namespace.com'}
)

682
venv/lib/python3.7/site-packages/bs4/tests/test_soup.py Normal file
View File

@@ -0,0 +1,682 @@
# -*- coding: utf-8 -*-
"""Tests of Beautiful Soup as a whole."""
from pdb import set_trace
import logging
import unittest
import sys
import tempfile
from bs4 import (
BeautifulSoup,
BeautifulStoneSoup,
)
from bs4.builder import (
TreeBuilder,
ParserRejectedMarkup,
)
from bs4.element import (
CharsetMetaAttributeValue,
Comment,
ContentMetaAttributeValue,
SoupStrainer,
NamespacedAttribute,
Tag,
NavigableString,
)
import bs4.dammit
from bs4.dammit import (
EntitySubstitution,
UnicodeDammit,
EncodingDetector,
)
from bs4.testing 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)
self.assertEqual("éé", soup.h1.string)
def test_embedded_null(self):
data = "<h1>foo\0bar</h1>"
soup = self.soup(data)
self.assertEqual("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"])
self.assertEqual("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 = []
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)
self.assertEqual(dict(var="value"), soup.builder.called_with)
self.assertEqual("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.")
self.assertEqual(builder, soup.builder)
self.assertEqual(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
self.assertRaisesRegex(
ParserRejectedMarkup,
"The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help.",
BeautifulSoup, '', builder=Mock,
)
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
self.assertEqual(" an id ", a['id'])
self.assertEqual(["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)
self.assertEqual(" 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
self.assertEqual(["an", "id"], a['id'])
self.assertEqual(" 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()
)
class TestWarnings(SoupTest):
def _no_parser_specified(self, s, is_there=True):
v = s.startswith(BeautifulSoup.NO_PARSER_SPECIFIED_WARNING[:80])
self.assertTrue(v)
def test_warning_if_no_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>")
msg = str(w[0].message)
self._assert_no_parser_specified(msg)
def test_warning_if_parser_specified_too_vague(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>", "html")
msg = str(w[0].message)
self._assert_no_parser_specified(msg)
def test_no_warning_if_explicit_parser_specified(self):
with warnings.catch_warnings(record=True) as w:
soup = self.soup("<a><b></b></a>", "html.parser")
self.assertEqual([], 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)
self.assertTrue("parseOnlyThese" in msg)
self.assertTrue("parse_only" in msg)
self.assertEqual(b"<b></b>", soup.encode())
def test_fromEncoding_renamed_to_from_encoding(self):
with warnings.catch_warnings(record=True) as w:
utf8 = b"\xc3\xa9"
soup = self.soup(utf8, fromEncoding="utf8")
msg = str(w[0].message)
self.assertTrue("fromEncoding" in msg)
self.assertTrue("from_encoding" in msg)
self.assertEqual("utf8", soup.original_encoding)
def test_unrecognized_keyword_argument(self):
self.assertRaises(
TypeError, self.soup, "<a>", no_such_argument=True)
class TestWarnings(SoupTest):
def test_disk_file_warning(self):
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
try:
with warnings.catch_warnings(record=True) as w:
soup = self.soup(filename)
msg = str(w[0].message)
self.assertTrue("looks like a filename" in msg)
finally:
filehandle.close()
# The file no longer exists, so Beautiful Soup will no longer issue the warning.
with warnings.catch_warnings(record=True) as w:
soup = self.soup(filename)
self.assertEqual(0, len(w))
def test_url_warning_with_bytes_url(self):
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(b"http://www.crummybytes.com/")
# Be aware this isn't the only warning that can be raised during
# execution..
self.assertTrue(any("looks like a URL" in str(w.message)
for w in warning_list))
def test_url_warning_with_unicode_url(self):
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("http://www.crummyunicode.com/")
self.assertTrue(any("looks like a URL" in str(w.message)
for w in warning_list))
def test_url_warning_with_bytes_and_space(self):
with warnings.catch_warnings(record=True) as warning_list:
soup = self.soup(b"http://www.crummybytes.com/ is great")
self.assertFalse(any("looks 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.crummyuncode.com/ is great")
self.assertFalse(any("looks 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)
self.assertEqual(soup.encode(), b"<b>Yes</b><b>Yes <c>Yes</c></b>")
class TestEntitySubstitution(unittest.TestCase):
"""Standalone tests of the EntitySubstitution class."""
def setUp(self):
self.sub = EntitySubstitution
def test_simple_html_substitution(self):
# Unicode characters corresponding to named HTML entites
# are substituted, and no others.
s = "foo\u2200\N{SNOWMAN}\u00f5bar"
self.assertEqual(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)
self.assertEqual(self.sub.substitute_html(dammit.markup),
"&lsquo;&rsquo;foo&ldquo;&rdquo;")
def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
s = 'Welcome to "my bar"'
self.assertEqual(self.sub.substitute_xml(s, False), s)
def test_xml_attribute_quoting_normally_uses_double_quotes(self):
self.assertEqual(self.sub.substitute_xml("Welcome", True),
'"Welcome"')
self.assertEqual(self.sub.substitute_xml("Bob's Bar", True),
'"Bob\'s Bar"')
def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
s = 'Welcome to "my bar"'
self.assertEqual(self.sub.substitute_xml(s, True),
"'Welcome to \"my bar\"'")
def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
s = 'Welcome to "Bob\'s Bar"'
self.assertEqual(
self.sub.substitute_xml(s, True),
'"Welcome to &quot;Bob\'s Bar&quot;"')
def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
quoted = 'Welcome to "Bob\'s Bar"'
self.assertEqual(self.sub.substitute_xml(quoted), quoted)
def test_xml_quoting_handles_angle_brackets(self):
self.assertEqual(
self.sub.substitute_xml("foo<bar>"),
"foo&lt;bar&gt;")
def test_xml_quoting_handles_ampersands(self):
self.assertEqual(self.sub.substitute_xml("AT&T"), "AT&amp;T")
def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
self.assertEqual(
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):
self.assertEqual(
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"'
self.assertEqual(self.sub.substitute_html(text), text)
class TestEncodingConversion(SoupTest):
# Test Beautiful Soup's ability to decode and encode from various
# encodings.
def setUp(self):
super(TestEncodingConversion, self).setUp()
self.unicode_data = '<html><head><meta charset="utf-8"/></head><body><foo>Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!</foo></body></html>'
self.utf8_data = self.unicode_data.encode("utf-8")
# Just so you know what it looks like.
self.assertEqual(
self.utf8_data,
b'<html><head><meta charset="utf-8"/></head><body><foo>Sacr\xc3\xa9 bleu!</foo></body></html>')
def test_ascii_in_unicode_out(self):
# ASCII input is converted to Unicode. The original_encoding
# attribute is set to 'utf-8', a superset of ASCII.
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
# Disable chardet, which will realize that the ASCII is ASCII.
bs4.dammit.chardet_dammit = noop
ascii = b"<foo>a</foo>"
soup_from_ascii = self.soup(ascii)
unicode_output = soup_from_ascii.decode()
self.assertTrue(isinstance(unicode_output, str))
self.assertEqual(unicode_output, self.document_for(ascii.decode()))
self.assertEqual(soup_from_ascii.original_encoding.lower(), "utf-8")
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet
def test_unicode_in_unicode_out(self):
# Unicode input is left alone. The original_encoding attribute
# is not set.
soup_from_unicode = self.soup(self.unicode_data)
self.assertEqual(soup_from_unicode.decode(), self.unicode_data)
self.assertEqual(soup_from_unicode.foo.string, 'Sacr\xe9 bleu!')
self.assertEqual(soup_from_unicode.original_encoding, None)
def test_utf8_in_unicode_out(self):
# UTF-8 input is converted to Unicode. The original_encoding
# attribute is set.
soup_from_utf8 = self.soup(self.utf8_data)
self.assertEqual(soup_from_utf8.decode(), self.unicode_data)
self.assertEqual(soup_from_utf8.foo.string, 'Sacr\xe9 bleu!')
def test_utf8_out(self):
# The internal data structures can be encoded as UTF-8.
soup_from_unicode = self.soup(self.unicode_data)
self.assertEqual(soup_from_unicode.encode('utf-8'), self.utf8_data)
@skipIf(
PYTHON_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>'
self.assertEqual(self.soup(markup).div.encode("utf8"), markup.encode("utf8"))
class TestUnicodeDammit(unittest.TestCase):
"""Standalone tests of UnicodeDammit."""
def test_unicode_input(self):
markup = "I'm already Unicode! \N{SNOWMAN}"
dammit = UnicodeDammit(markup)
self.assertEqual(dammit.unicode_markup, markup)
def test_smart_quotes_to_unicode(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup)
self.assertEqual(
dammit.unicode_markup, "<foo>\u2018\u2019\u201c\u201d</foo>")
def test_smart_quotes_to_xml_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="xml")
self.assertEqual(
dammit.unicode_markup, "<foo>&#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")
self.assertEqual(
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")
self.assertEqual(
dammit.unicode_markup, """<foo>''""</foo>""")
def test_detect_utf8(self):
utf8 = b"Sacr\xc3\xa9 bleu! \xe2\x98\x83"
dammit = UnicodeDammit(utf8)
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
self.assertEqual(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"])
self.assertEqual(dammit.original_encoding.lower(), 'iso-8859-8')
self.assertEqual(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)
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
self.assertEqual(dammit.unicode_markup.encode("utf-8"), utf_8)
def test_ignore_inappropriate_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
def test_ignore_invalid_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
for bad_encoding in ['.utf8', '...', 'utF---16.!']:
dammit = UnicodeDammit(utf8_data, [bad_encoding])
self.assertEqual(dammit.original_encoding.lower(), 'utf-8')
def test_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"])
self.assertEqual(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"])
self.assertEqual(dammit.original_encoding, None)
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)
self.assertEqual(
"euc-jp", dammit.original_encoding)
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
bs4.dammit.chardet_dammit = noop
dammit = UnicodeDammit(doc)
self.assertEqual(True, dammit.contains_replacement_characters)
self.assertTrue("\ufffd" in dammit.unicode_markup)
soup = BeautifulSoup(doc, "html.parser")
self.assertTrue(soup.contains_replacement_characters)
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet
def test_byte_order_mark_removed(self):
# A document written in UTF-16LE will have its byte order marker stripped.
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
dammit = UnicodeDammit(data)
self.assertEqual("<a>áé</a>", dammit.unicode_markup)
self.assertEqual("utf-16le", dammit.original_encoding)
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:
self.assertRaises(UnicodeDecodeError, doc.decode, "utf8")
# Unicode, Dammit thinks the whole document is Windows-1252,
# and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
# But if we run it through fix_embedded_windows_1252, it's fixed:
fixed = UnicodeDammit.detwingle(doc)
self.assertEqual(
"☃☃☃“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")
self.assertTrue(input.endswith(b'\x93'))
output = UnicodeDammit.detwingle(input)
self.assertEqual(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
self.assertEqual(None, m(html_unicode, is_html=False))
self.assertEqual("utf-8", m(html_unicode, is_html=True))
self.assertEqual("utf-8", m(html_bytes, is_html=True))
self.assertEqual("iso-8859-1", m(xml_unicode))
self.assertEqual("iso-8859-1", m(xml_bytes))
# Normally, only the first few kilobytes of a document are checked for
# an encoding.
spacer = b' ' * 5000
self.assertEqual(None, m(spacer + html_bytes))
self.assertEqual(None, m(spacer + xml_bytes))
# But you can tell find_declared_encoding to search an entire
# HTML document.
self.assertEqual(
"utf-8",
m(spacer + html_bytes, is_html=True, search_entire_document=True)
)
# 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.
self.assertEqual(
"iso-8859-1",
m(xml_bytes, search_entire_document=True)
)
self.assertEqual(
None, m(b'a' + xml_bytes, search_entire_document=True)
)
class TestNamedspacedAttribute(SoupTest):
def test_name_may_be_none_or_missing(self):
a = NamespacedAttribute("xmlns", None)
self.assertEqual(a, "xmlns")
a = NamespacedAttribute("xmlns")
self.assertEqual(a, "xmlns")
def test_attribute_is_equivalent_to_colon_separated_string(self):
a = NamespacedAttribute("a", "b")
self.assertEqual("a:b", a)
def test_attributes_are_equivalent_if_prefix_and_name_identical(self):
a = NamespacedAttribute("a", "b", "c")
b = NamespacedAttribute("a", "b", "c")
self.assertEqual(a, b)
# The actual namespace is not considered.
c = NamespacedAttribute("a", "b", None)
self.assertEqual(a, c)
# But name and prefix are important.
d = NamespacedAttribute("a", "z", "c")
self.assertNotEqual(a, d)
e = NamespacedAttribute("z", "b", "c")
self.assertNotEqual(a, e)
class TestAttributeValueWithCharsetSubstitution(unittest.TestCase):
def test_content_meta_attribute_value(self):
value = CharsetMetaAttributeValue("euc-jp")
self.assertEqual("euc-jp", value)
self.assertEqual("euc-jp", value.original_value)
self.assertEqual("utf8", value.encode("utf8"))
def test_content_meta_attribute_value(self):
value = ContentMetaAttributeValue("text/html; charset=euc-jp")
self.assertEqual("text/html; charset=euc-jp", value)
self.assertEqual("text/html; charset=euc-jp", value.original_value)
self.assertEqual("text/html; charset=utf8", value.encode("utf8"))

2254
venv/lib/python3.7/site-packages/bs4/tests/test_tree.py Normal file
View File

File diff suppressed because it is too large Load Diff

50
venv/lib/python3.7/site-packages/certifi-2019.9.11.dist-info/DESCRIPTION.rst Normal file
View File

@@ -0,0 +1,50 @@
Certifi: Python SSL Certificates
================================
`Certifi`_ is a carefully curated collection of Root Certificates for
validating the trustworthiness of SSL certificates while verifying the identity
of TLS hosts. It has been extracted from the `Requests`_ project.
Installation
------------
``certifi`` is available on PyPI. Simply install it with ``pip``::
$ pip install certifi
Usage
-----
To reference the installed certificate authority (CA) bundle, you can use the
built-in function::
>>> import certifi
>>> certifi.where()
'/usr/local/lib/python2.7/site-packages/certifi/cacert.pem'
Or from the command line::
$ python -m certifi
/usr/local/lib/python2.7/site-packages/certifi/cacert.pem
Enjoy!
1024-bit Root Certificates
~~~~~~~~~~~~~~~~~~~~~~~~~~
Browsers and certificate authorities have concluded that 1024-bit keys are
unacceptably weak for certificates, particularly root certificates. For this
reason, Mozilla has removed any weak (i.e. 1024-bit key) certificate from its
bundle, replacing it with an equivalent strong (i.e. 2048-bit or greater key)
certificate from the same CA. Because Mozilla removed these certificates from
its bundle, ``certifi`` removed them as well.
In previous versions, ``certifi`` provided the ``certifi.old_where()`` function
to intentionally re-add the 1024-bit roots back into your bundle. This was not
recommended in production and therefore was removed at the end of 2018.
.. _`Certifi`: https://certifi.io/en/latest/
.. _`Requests`: http://docs.python-requests.org/en/latest/

1
venv/lib/python3.7/site-packages/certifi-2019.9.11.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

74
venv/lib/python3.7/site-packages/certifi-2019.9.11.dist-info/METADATA Normal file
View File

@@ -0,0 +1,74 @@
Metadata-Version: 2.0
Name: certifi
Version: 2019.9.11
Summary: Python package for providing Mozilla's CA Bundle.
Home-page: https://certifi.io/
Author: Kenneth Reitz
Author-email: me@kennethreitz.com
License: MPL-2.0
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
Classifier: Natural Language :: English
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.6
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.3
Classifier: Programming Language :: Python :: 3.4
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Certifi: Python SSL Certificates
================================
`Certifi`_ is a carefully curated collection of Root Certificates for
validating the trustworthiness of SSL certificates while verifying the identity
of TLS hosts. It has been extracted from the `Requests`_ project.
Installation
------------
``certifi`` is available on PyPI. Simply install it with ``pip``::
$ pip install certifi
Usage
-----
To reference the installed certificate authority (CA) bundle, you can use the
built-in function::
>>> import certifi
>>> certifi.where()
'/usr/local/lib/python2.7/site-packages/certifi/cacert.pem'
Or from the command line::
$ python -m certifi
/usr/local/lib/python2.7/site-packages/certifi/cacert.pem
Enjoy!
1024-bit Root Certificates
~~~~~~~~~~~~~~~~~~~~~~~~~~
Browsers and certificate authorities have concluded that 1024-bit keys are
unacceptably weak for certificates, particularly root certificates. For this
reason, Mozilla has removed any weak (i.e. 1024-bit key) certificate from its
bundle, replacing it with an equivalent strong (i.e. 2048-bit or greater key)
certificate from the same CA. Because Mozilla removed these certificates from
its bundle, ``certifi`` removed them as well.
In previous versions, ``certifi`` provided the ``certifi.old_where()`` function
to intentionally re-add the 1024-bit roots back into your bundle. This was not
recommended in production and therefore was removed at the end of 2018.
.. _`Certifi`: https://certifi.io/en/latest/
.. _`Requests`: http://docs.python-requests.org/en/latest/

14
venv/lib/python3.7/site-packages/certifi-2019.9.11.dist-info/RECORD Normal file
View File

@@ -0,0 +1,14 @@
certifi-2019.9.11.dist-info/DESCRIPTION.rst,sha256=aLNHONztn2ZiBpSTivVFy6EDIWmuNYSsEQwx4NWbvB4,1580
certifi-2019.9.11.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
certifi-2019.9.11.dist-info/METADATA,sha256=M0Gen7rhgJKIvggZuENXqcZexg74gXdjGC679bMeoDw,2522
certifi-2019.9.11.dist-info/RECORD,,
certifi-2019.9.11.dist-info/WHEEL,sha256=5wvfB7GvgZAbKBSE9uX9Zbi6LCL-_KgezgHblXhCRnM,113
certifi-2019.9.11.dist-info/metadata.json,sha256=NppG2TtVr6va5nwyG9pxGhktdvudS-IfpTkaQaWKlBE,1022
certifi-2019.9.11.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
certifi/__init__.py,sha256=WFoavXHhpX-BZ5kbvyinZTbhLsqPJypLKIZu29nUsQg,52
certifi/__main__.py,sha256=FiOYt1Fltst7wk9DRa6GCoBr8qBUxlNQu_MKJf04E6s,41
certifi/__pycache__/__init__.cpython-37.pyc,,
certifi/__pycache__/__main__.cpython-37.pyc,,
certifi/__pycache__/core.cpython-37.pyc,,
certifi/cacert.pem,sha256=cVC1b0T-OcQzgdcRql2yMxT7O08O6pcJHnuO9nbLLn0,278533
certifi/core.py,sha256=EuFc2BsToG5O1-qsx4BSjQ1r1-7WRtH87b1WflZOWhI,218

6
venv/lib/python3.7/site-packages/certifi-2019.9.11.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,6 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.30.0.a0)
Root-Is-Purelib: true
Tag: py2-none-any
Tag: py3-none-any

1
venv/lib/python3.7/site-packages/certifi-2019.9.11.dist-info/metadata.json Normal file
View File

@@ -0,0 +1 @@
{"classifiers": ["Development Status :: 5 - Production/Stable", "Intended Audience :: Developers", "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)", "Natural Language :: English", "Programming Language :: Python", "Programming Language :: Python :: 2", "Programming Language :: Python :: 2.6", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.3", "Programming Language :: Python :: 3.4", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Programming Language :: Python :: 3.7"], "extensions": {"python.details": {"contacts": [{"email": "me@kennethreitz.com", "name": "Kenneth Reitz", "role": "author"}], "document_names": {"description": "DESCRIPTION.rst"}, "project_urls": {"Home": "https://certifi.io/"}}}, "generator": "bdist_wheel (0.30.0.a0)", "license": "MPL-2.0", "metadata_version": "2.0", "name": "certifi", "summary": "Python package for providing Mozilla's CA Bundle.", "version": "2019.9.11"}

1
venv/lib/python3.7/site-packages/certifi-2019.9.11.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1 @@
certifi

3
venv/lib/python3.7/site-packages/certifi/__init__.py Normal file
View File

@@ -0,0 +1,3 @@
from .core import where
__version__ = "2019.09.11"

2
venv/lib/python3.7/site-packages/certifi/__main__.py Normal file
View File

@@ -0,0 +1,2 @@
from certifi import where
print(where())

BIN
venv/lib/python3.7/site-packages/certifi/__pycache__/__init__.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/certifi/__pycache__/__main__.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/certifi/__pycache__/core.cpython-37.pyc Normal file
View File

Binary file not shown.

4558
venv/lib/python3.7/site-packages/certifi/cacert.pem Normal file
View File

File diff suppressed because it is too large Load Diff

15
venv/lib/python3.7/site-packages/certifi/core.py Normal file
View File

@@ -0,0 +1,15 @@
# -*- coding: utf-8 -*-
"""
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem.
"""
import os
def where():
f = os.path.dirname(__file__)
return os.path.join(f, 'cacert.pem')

70
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/DESCRIPTION.rst Normal file
View File

@@ -0,0 +1,70 @@
Chardet: The Universal Character Encoding Detector
--------------------------------------------------
.. image:: https://img.shields.io/travis/chardet/chardet/stable.svg
:alt: Build status
:target: https://travis-ci.org/chardet/chardet
.. image:: https://img.shields.io/coveralls/chardet/chardet/stable.svg
:target: https://coveralls.io/r/chardet/chardet
.. image:: https://img.shields.io/pypi/v/chardet.svg
:target: https://warehouse.python.org/project/chardet/
:alt: Latest version on PyPI
.. image:: https://img.shields.io/pypi/l/chardet.svg
:alt: License
Detects
- ASCII, UTF-8, UTF-16 (2 variants), UTF-32 (4 variants)
- Big5, GB2312, EUC-TW, HZ-GB-2312, ISO-2022-CN (Traditional and Simplified Chinese)
- EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP (Japanese)
- EUC-KR, ISO-2022-KR (Korean)
- KOI8-R, MacCyrillic, IBM855, IBM866, ISO-8859-5, windows-1251 (Cyrillic)
- ISO-8859-5, windows-1251 (Bulgarian)
- ISO-8859-1, windows-1252 (Western European languages)
- ISO-8859-7, windows-1253 (Greek)
- ISO-8859-8, windows-1255 (Visual and Logical Hebrew)
- TIS-620 (Thai)
.. note::
Our ISO-8859-2 and windows-1250 (Hungarian) probers have been temporarily
disabled until we can retrain the models.
Requires Python 2.6, 2.7, or 3.3+.
Installation
------------
Install from `PyPI <https://pypi.python.org/pypi/chardet>`_::
pip install chardet
Documentation
-------------
For users, docs are now available at https://chardet.readthedocs.io/.
Command-line Tool
-----------------
chardet comes with a command-line script which reports on the encodings of one
or more files::
% chardetect somefile someotherfile
somefile: windows-1252 with confidence 0.5
someotherfile: ascii with confidence 1.0
About
-----
This is a continuation of Mark Pilgrim's excellent chardet. Previously, two
versions needed to be maintained: one that supported python 2.x and one that
supported python 3.x. We've recently merged with `Ian Cordasco <https://github.com/sigmavirus24>`_'s
`charade <https://github.com/sigmavirus24/charade>`_ fork, so now we have one
coherent version that works for Python 2.6+.
:maintainer: Dan Blanchard

1
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

96
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/METADATA Normal file
View File

@@ -0,0 +1,96 @@
Metadata-Version: 2.0
Name: chardet
Version: 3.0.4
Summary: Universal encoding detector for Python 2 and 3
Home-page: https://github.com/chardet/chardet
Author: Daniel Blanchard
Author-email: dan.blanchard@gmail.com
License: LGPL
Keywords: encoding,i18n,xml
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.6
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.3
Classifier: Programming Language :: Python :: 3.4
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Linguistic
Chardet: The Universal Character Encoding Detector
--------------------------------------------------
.. image:: https://img.shields.io/travis/chardet/chardet/stable.svg
:alt: Build status
:target: https://travis-ci.org/chardet/chardet
.. image:: https://img.shields.io/coveralls/chardet/chardet/stable.svg
:target: https://coveralls.io/r/chardet/chardet
.. image:: https://img.shields.io/pypi/v/chardet.svg
:target: https://warehouse.python.org/project/chardet/
:alt: Latest version on PyPI
.. image:: https://img.shields.io/pypi/l/chardet.svg
:alt: License
Detects
- ASCII, UTF-8, UTF-16 (2 variants), UTF-32 (4 variants)
- Big5, GB2312, EUC-TW, HZ-GB-2312, ISO-2022-CN (Traditional and Simplified Chinese)
- EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP (Japanese)
- EUC-KR, ISO-2022-KR (Korean)
- KOI8-R, MacCyrillic, IBM855, IBM866, ISO-8859-5, windows-1251 (Cyrillic)
- ISO-8859-5, windows-1251 (Bulgarian)
- ISO-8859-1, windows-1252 (Western European languages)
- ISO-8859-7, windows-1253 (Greek)
- ISO-8859-8, windows-1255 (Visual and Logical Hebrew)
- TIS-620 (Thai)
.. note::
Our ISO-8859-2 and windows-1250 (Hungarian) probers have been temporarily
disabled until we can retrain the models.
Requires Python 2.6, 2.7, or 3.3+.
Installation
------------
Install from `PyPI <https://pypi.python.org/pypi/chardet>`_::
pip install chardet
Documentation
-------------
For users, docs are now available at https://chardet.readthedocs.io/.
Command-line Tool
-----------------
chardet comes with a command-line script which reports on the encodings of one
or more files::
% chardetect somefile someotherfile
somefile: windows-1252 with confidence 0.5
someotherfile: ascii with confidence 1.0
About
-----
This is a continuation of Mark Pilgrim's excellent chardet. Previously, two
versions needed to be maintained: one that supported python 2.x and one that
supported python 3.x. We've recently merged with `Ian Cordasco <https://github.com/sigmavirus24>`_'s
`charade <https://github.com/sigmavirus24/charade>`_ fork, so now we have one
coherent version that works for Python 2.6+.
:maintainer: Dan Blanchard

91
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/RECORD Normal file
View File

@@ -0,0 +1,91 @@
../../../bin/chardetect,sha256=1K9Rp_7Hp91DfV89iLMNJ9JM533HfOdLHlpYN6RWwTA,257
chardet-3.0.4.dist-info/DESCRIPTION.rst,sha256=PQ4sBsMyKFZkjC6QpmbpLn0UtCNyeb-ZqvCGEgyZMGk,2174
chardet-3.0.4.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
chardet-3.0.4.dist-info/METADATA,sha256=RV_2I4B1Z586DL8oVO5Kp7X5bUdQ5EuKAvNoAEF8wSw,3239
chardet-3.0.4.dist-info/RECORD,,
chardet-3.0.4.dist-info/WHEEL,sha256=o2k-Qa-RMNIJmUdIc7KU6VWR_ErNRbWNlxDIpl7lm34,110
chardet-3.0.4.dist-info/entry_points.txt,sha256=fAMmhu5eJ-zAJ-smfqQwRClQ3-nozOCmvJ6-E8lgGJo,60
chardet-3.0.4.dist-info/metadata.json,sha256=0htbRM18ujyGZDdfowgAqj6Hq2eQtwzwyhaEveKntgo,1375
chardet-3.0.4.dist-info/top_level.txt,sha256=AowzBbZy4x8EirABDdJSLJZMkJ_53iIag8xfKR6D7kI,8
chardet/__init__.py,sha256=YsP5wQlsHJ2auF1RZJfypiSrCA7_bQiRm3ES_NI76-Y,1559
chardet/__pycache__/__init__.cpython-37.pyc,,
chardet/__pycache__/big5freq.cpython-37.pyc,,
chardet/__pycache__/big5prober.cpython-37.pyc,,
chardet/__pycache__/chardistribution.cpython-37.pyc,,
chardet/__pycache__/charsetgroupprober.cpython-37.pyc,,
chardet/__pycache__/charsetprober.cpython-37.pyc,,
chardet/__pycache__/codingstatemachine.cpython-37.pyc,,
chardet/__pycache__/compat.cpython-37.pyc,,
chardet/__pycache__/cp949prober.cpython-37.pyc,,
chardet/__pycache__/enums.cpython-37.pyc,,
chardet/__pycache__/escprober.cpython-37.pyc,,
chardet/__pycache__/escsm.cpython-37.pyc,,
chardet/__pycache__/eucjpprober.cpython-37.pyc,,
chardet/__pycache__/euckrfreq.cpython-37.pyc,,
chardet/__pycache__/euckrprober.cpython-37.pyc,,
chardet/__pycache__/euctwfreq.cpython-37.pyc,,
chardet/__pycache__/euctwprober.cpython-37.pyc,,
chardet/__pycache__/gb2312freq.cpython-37.pyc,,
chardet/__pycache__/gb2312prober.cpython-37.pyc,,
chardet/__pycache__/hebrewprober.cpython-37.pyc,,
chardet/__pycache__/jisfreq.cpython-37.pyc,,
chardet/__pycache__/jpcntx.cpython-37.pyc,,
chardet/__pycache__/langbulgarianmodel.cpython-37.pyc,,
chardet/__pycache__/langcyrillicmodel.cpython-37.pyc,,
chardet/__pycache__/langgreekmodel.cpython-37.pyc,,
chardet/__pycache__/langhebrewmodel.cpython-37.pyc,,
chardet/__pycache__/langhungarianmodel.cpython-37.pyc,,
chardet/__pycache__/langthaimodel.cpython-37.pyc,,
chardet/__pycache__/langturkishmodel.cpython-37.pyc,,
chardet/__pycache__/latin1prober.cpython-37.pyc,,
chardet/__pycache__/mbcharsetprober.cpython-37.pyc,,
chardet/__pycache__/mbcsgroupprober.cpython-37.pyc,,
chardet/__pycache__/mbcssm.cpython-37.pyc,,
chardet/__pycache__/sbcharsetprober.cpython-37.pyc,,
chardet/__pycache__/sbcsgroupprober.cpython-37.pyc,,
chardet/__pycache__/sjisprober.cpython-37.pyc,,
chardet/__pycache__/universaldetector.cpython-37.pyc,,
chardet/__pycache__/utf8prober.cpython-37.pyc,,
chardet/__pycache__/version.cpython-37.pyc,,
chardet/big5freq.py,sha256=D_zK5GyzoVsRes0HkLJziltFQX0bKCLOrFe9_xDvO_8,31254
chardet/big5prober.py,sha256=kBxHbdetBpPe7xrlb-e990iot64g_eGSLd32lB7_h3M,1757
chardet/chardistribution.py,sha256=3woWS62KrGooKyqz4zQSnjFbJpa6V7g02daAibTwcl8,9411
chardet/charsetgroupprober.py,sha256=6bDu8YIiRuScX4ca9Igb0U69TA2PGXXDej6Cc4_9kO4,3787
chardet/charsetprober.py,sha256=KSmwJErjypyj0bRZmC5F5eM7c8YQgLYIjZXintZNstg,5110
chardet/cli/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
chardet/cli/__pycache__/__init__.cpython-37.pyc,,
chardet/cli/__pycache__/chardetect.cpython-37.pyc,,
chardet/cli/chardetect.py,sha256=YBO8L4mXo0WR6_-Fjh_8QxPBoEBNqB9oNxNrdc54AQs,2738
chardet/codingstatemachine.py,sha256=VYp_6cyyki5sHgXDSZnXW4q1oelHc3cu9AyQTX7uug8,3590
chardet/compat.py,sha256=PKTzHkSbtbHDqS9PyujMbX74q1a8mMpeQTDVsQhZMRw,1134
chardet/cp949prober.py,sha256=TZ434QX8zzBsnUvL_8wm4AQVTZ2ZkqEEQL_lNw9f9ow,1855
chardet/enums.py,sha256=Aimwdb9as1dJKZaFNUH2OhWIVBVd6ZkJJ_WK5sNY8cU,1661
chardet/escprober.py,sha256=kkyqVg1Yw3DIOAMJ2bdlyQgUFQhuHAW8dUGskToNWSc,3950
chardet/escsm.py,sha256=RuXlgNvTIDarndvllNCk5WZBIpdCxQ0kcd9EAuxUh84,10510
chardet/eucjpprober.py,sha256=iD8Jdp0ISRjgjiVN7f0e8xGeQJ5GM2oeZ1dA8nbSeUw,3749
chardet/euckrfreq.py,sha256=-7GdmvgWez4-eO4SuXpa7tBiDi5vRXQ8WvdFAzVaSfo,13546
chardet/euckrprober.py,sha256=MqFMTQXxW4HbzIpZ9lKDHB3GN8SP4yiHenTmf8g_PxY,1748
chardet/euctwfreq.py,sha256=No1WyduFOgB5VITUA7PLyC5oJRNzRyMbBxaKI1l16MA,31621
chardet/euctwprober.py,sha256=13p6EP4yRaxqnP4iHtxHOJ6R2zxHq1_m8hTRjzVZ95c,1747
chardet/gb2312freq.py,sha256=JX8lsweKLmnCwmk8UHEQsLgkr_rP_kEbvivC4qPOrlc,20715
chardet/gb2312prober.py,sha256=gGvIWi9WhDjE-xQXHvNIyrnLvEbMAYgyUSZ65HUfylw,1754
chardet/hebrewprober.py,sha256=c3SZ-K7hvyzGY6JRAZxJgwJ_sUS9k0WYkvMY00YBYFo,13838
chardet/jisfreq.py,sha256=vpmJv2Bu0J8gnMVRPHMFefTRvo_ha1mryLig8CBwgOg,25777
chardet/jpcntx.py,sha256=PYlNqRUQT8LM3cT5FmHGP0iiscFlTWED92MALvBungo,19643
chardet/langbulgarianmodel.py,sha256=1HqQS9Pbtnj1xQgxitJMvw8X6kKr5OockNCZWfEQrPE,12839
chardet/langcyrillicmodel.py,sha256=LODajvsetH87yYDDQKA2CULXUH87tI223dhfjh9Zx9c,17948
chardet/langgreekmodel.py,sha256=8YAW7bU8YwSJap0kIJSbPMw1BEqzGjWzqcqf0WgUKAA,12688
chardet/langhebrewmodel.py,sha256=JSnqmE5E62tDLTPTvLpQsg5gOMO4PbdWRvV7Avkc0HA,11345
chardet/langhungarianmodel.py,sha256=RhapYSG5l0ZaO-VV4Fan5sW0WRGQqhwBM61yx3yxyOA,12592
chardet/langthaimodel.py,sha256=8l0173Gu_W6G8mxmQOTEF4ls2YdE7FxWf3QkSxEGXJQ,11290
chardet/langturkishmodel.py,sha256=W22eRNJsqI6uWAfwXSKVWWnCerYqrI8dZQTm_M0lRFk,11102
chardet/latin1prober.py,sha256=S2IoORhFk39FEFOlSFWtgVybRiP6h7BlLldHVclNkU8,5370
chardet/mbcharsetprober.py,sha256=AR95eFH9vuqSfvLQZN-L5ijea25NOBCoXqw8s5O9xLQ,3413
chardet/mbcsgroupprober.py,sha256=h6TRnnYq2OxG1WdD5JOyxcdVpn7dG0q-vB8nWr5mbh4,2012
chardet/mbcssm.py,sha256=SY32wVIF3HzcjY3BaEspy9metbNSKxIIB0RKPn7tjpI,25481
chardet/sbcharsetprober.py,sha256=LDSpCldDCFlYwUkGkwD2oFxLlPWIWXT09akH_2PiY74,5657
chardet/sbcsgroupprober.py,sha256=1IprcCB_k1qfmnxGC6MBbxELlKqD3scW6S8YIwdeyXA,3546
chardet/sjisprober.py,sha256=IIt-lZj0WJqK4rmUZzKZP4GJlE8KUEtFYVuY96ek5MQ,3774
chardet/universaldetector.py,sha256=qL0174lSZE442eB21nnktT9_VcAye07laFWUeUrjttY,12485
chardet/utf8prober.py,sha256=IdD8v3zWOsB8OLiyPi-y_fqwipRFxV9Nc1eKBLSuIEw,2766
chardet/version.py,sha256=sp3B08mrDXB-pf3K9fqJ_zeDHOCLC8RrngQyDFap_7g,242

6
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,6 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.29.0)
Root-Is-Purelib: true
Tag: py2-none-any
Tag: py3-none-any

3
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/entry_points.txt Normal file
View File

@@ -0,0 +1,3 @@
[console_scripts]
chardetect = chardet.cli.chardetect:main

1
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/metadata.json Normal file
View File

@@ -0,0 +1 @@
{"classifiers": ["Development Status :: 4 - Beta", "Intended Audience :: Developers", "License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)", "Operating System :: OS Independent", "Programming Language :: Python", "Programming Language :: Python :: 2", "Programming Language :: Python :: 2.6", "Programming Language :: Python :: 2.7", "Programming Language :: Python :: 3", "Programming Language :: Python :: 3.3", "Programming Language :: Python :: 3.4", "Programming Language :: Python :: 3.5", "Programming Language :: Python :: 3.6", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Text Processing :: Linguistic"], "extensions": {"python.commands": {"wrap_console": {"chardetect": "chardet.cli.chardetect:main"}}, "python.details": {"contacts": [{"email": "dan.blanchard@gmail.com", "name": "Daniel Blanchard", "role": "author"}], "document_names": {"description": "DESCRIPTION.rst"}, "project_urls": {"Home": "https://github.com/chardet/chardet"}}, "python.exports": {"console_scripts": {"chardetect": "chardet.cli.chardetect:main"}}}, "generator": "bdist_wheel (0.29.0)", "keywords": ["encoding", "i18n", "xml"], "license": "LGPL", "metadata_version": "2.0", "name": "chardet", "summary": "Universal encoding detector for Python 2 and 3", "test_requires": [{"requires": ["hypothesis", "pytest"]}], "version": "3.0.4"}

1
venv/lib/python3.7/site-packages/chardet-3.0.4.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1 @@
chardet

39
venv/lib/python3.7/site-packages/chardet/__init__.py Normal file
View File

@@ -0,0 +1,39 @@
######################## BEGIN LICENSE BLOCK ########################
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
# 02110-1301 USA
######################### END LICENSE BLOCK #########################
from .compat import PY2, PY3
from .universaldetector import UniversalDetector
from .version import __version__, VERSION
def detect(byte_str):
"""
Detect the encoding of the given byte string.
:param byte_str: The byte sequence to examine.
:type byte_str: ``bytes`` or ``bytearray``
"""
if not isinstance(byte_str, bytearray):
if not isinstance(byte_str, bytes):
raise TypeError('Expected object of type bytes or bytearray, got: '
'{0}'.format(type(byte_str)))
else:
byte_str = bytearray(byte_str)
detector = UniversalDetector()
detector.feed(byte_str)
return detector.close()

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/__init__.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/big5freq.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/big5prober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/chardistribution.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/charsetgroupprober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/charsetprober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/codingstatemachine.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/compat.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/cp949prober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/enums.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/escprober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/escsm.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/eucjpprober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/euckrfreq.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/euckrprober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/euctwfreq.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/euctwprober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/gb2312freq.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/gb2312prober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/hebrewprober.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/jisfreq.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/jpcntx.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/langbulgarianmodel.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/langcyrillicmodel.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/langgreekmodel.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/langhebrewmodel.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/langhungarianmodel.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/langthaimodel.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/langturkishmodel.cpython-37.pyc Normal file
View File

Binary file not shown.

BIN
venv/lib/python3.7/site-packages/chardet/__pycache__/latin1prober.cpython-37.pyc Normal file
View File

Binary file not shown.

Some files were not shown because too many files have changed in this diff Show More