infidel/wg-backend-django
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Added login api

Browse Source
This commit is contained in:
infidel 2022-11-30 15:58:16 +07:00
parent 263218ed9e
commit d5d3401265
7319 changed files with 912655 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

247
acer-env/bin/Activate.ps1 Normal file
View File

@ -0,0 +1,247 @@
<#
.Synopsis
Activate a Python virtual environment for the current PowerShell session.
.Description
Pushes the python executable for a virtual environment to the front of the
$Env:PATH environment variable and sets the prompt to signify that you are
in a Python virtual environment. Makes use of the command line switches as
well as the `pyvenv.cfg` file values present in the virtual environment.
.Parameter VenvDir
Path to the directory that contains the virtual environment to activate. The
default value for this is the parent of the directory that the Activate.ps1
script is located within.
.Parameter Prompt
The prompt prefix to display when this virtual environment is activated. By
default, this prompt is the name of the virtual environment folder (VenvDir)
surrounded by parentheses and followed by a single space (ie. '(.venv) ').
.Example
Activate.ps1
Activates the Python virtual environment that contains the Activate.ps1 script.
.Example
Activate.ps1 -Verbose
Activates the Python virtual environment that contains the Activate.ps1 script,
and shows extra information about the activation as it executes.
.Example
Activate.ps1 -VenvDir C:\Users\MyUser\Common\.venv
Activates the Python virtual environment located in the specified location.
.Example
Activate.ps1 -Prompt "MyPython"
Activates the Python virtual environment that contains the Activate.ps1 script,
and prefixes the current prompt with the specified string (surrounded in
parentheses) while the virtual environment is active.
.Notes
On Windows, it may be required to enable this Activate.ps1 script by setting the
execution policy for the user. You can do this by issuing the following PowerShell
command:
PS C:\> Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser
For more information on Execution Policies:
https://go.microsoft.com/fwlink/?LinkID=135170
#>
Param(
[Parameter(Mandatory = $false)]
[String]
$VenvDir,
[Parameter(Mandatory = $false)]
[String]
$Prompt
)
<# Function declarations --------------------------------------------------- #>
<#
.Synopsis
Remove all shell session elements added by the Activate script, including the
addition of the virtual environment's Python executable from the beginning of
the PATH variable.
.Parameter NonDestructive
If present, do not remove this function from the global namespace for the
session.
#>
function global:deactivate ([switch]$NonDestructive) {
# Revert to original values
# The prior prompt:
if (Test-Path -Path Function:_OLD_VIRTUAL_PROMPT) {
Copy-Item -Path Function:_OLD_VIRTUAL_PROMPT -Destination Function:prompt
Remove-Item -Path Function:_OLD_VIRTUAL_PROMPT
}
# The prior PYTHONHOME:
if (Test-Path -Path Env:_OLD_VIRTUAL_PYTHONHOME) {
Copy-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME -Destination Env:PYTHONHOME
Remove-Item -Path Env:_OLD_VIRTUAL_PYTHONHOME
}
# The prior PATH:
if (Test-Path -Path Env:_OLD_VIRTUAL_PATH) {
Copy-Item -Path Env:_OLD_VIRTUAL_PATH -Destination Env:PATH
Remove-Item -Path Env:_OLD_VIRTUAL_PATH
}
# Just remove the VIRTUAL_ENV altogether:
if (Test-Path -Path Env:VIRTUAL_ENV) {
Remove-Item -Path env:VIRTUAL_ENV
}
# Just remove VIRTUAL_ENV_PROMPT altogether.
if (Test-Path -Path Env:VIRTUAL_ENV_PROMPT) {
Remove-Item -Path env:VIRTUAL_ENV_PROMPT
}
# Just remove the _PYTHON_VENV_PROMPT_PREFIX altogether:
if (Get-Variable -Name "_PYTHON_VENV_PROMPT_PREFIX" -ErrorAction SilentlyContinue) {
Remove-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Scope Global -Force
}
# Leave deactivate function in the global namespace if requested:
if (-not $NonDestructive) {
Remove-Item -Path function:deactivate
}
}
<#
.Description
Get-PyVenvConfig parses the values from the pyvenv.cfg file located in the
given folder, and returns them in a map.
For each line in the pyvenv.cfg file, if that line can be parsed into exactly
two strings separated by `=` (with any amount of whitespace surrounding the =)
then it is considered a `key = value` line. The left hand string is the key,
the right hand is the value.
If the value starts with a `'` or a `"` then the first and last character is
stripped from the value before being captured.
.Parameter ConfigDir
Path to the directory that contains the `pyvenv.cfg` file.
#>
function Get-PyVenvConfig(
[String]
$ConfigDir
) {
Write-Verbose "Given ConfigDir=$ConfigDir, obtain values in pyvenv.cfg"
# Ensure the file exists, and issue a warning if it doesn't (but still allow the function to continue).
$pyvenvConfigPath = Join-Path -Resolve -Path $ConfigDir -ChildPath 'pyvenv.cfg' -ErrorAction Continue
# An empty map will be returned if no config file is found.
$pyvenvConfig = @{ }
if ($pyvenvConfigPath) {
Write-Verbose "File exists, parse `key = value` lines"
$pyvenvConfigContent = Get-Content -Path $pyvenvConfigPath
$pyvenvConfigContent | ForEach-Object {
$keyval = $PSItem -split "\s*=\s*", 2
if ($keyval[0] -and $keyval[1]) {
$val = $keyval[1]
# Remove extraneous quotations around a string value.
if ("'""".Contains($val.Substring(0, 1))) {
$val = $val.Substring(1, $val.Length - 2)
}
$pyvenvConfig[$keyval[0]] = $val
Write-Verbose "Adding Key: '$($keyval[0])'='$val'"
}
}
}
return $pyvenvConfig
}
<# Begin Activate script --------------------------------------------------- #>
# Determine the containing directory of this script
$VenvExecPath = Split-Path -Parent $MyInvocation.MyCommand.Definition
$VenvExecDir = Get-Item -Path $VenvExecPath
Write-Verbose "Activation script is located in path: '$VenvExecPath'"
Write-Verbose "VenvExecDir Fullname: '$($VenvExecDir.FullName)"
Write-Verbose "VenvExecDir Name: '$($VenvExecDir.Name)"
# Set values required in priority: CmdLine, ConfigFile, Default
# First, get the location of the virtual environment, it might not be
# VenvExecDir if specified on the command line.
if ($VenvDir) {
Write-Verbose "VenvDir given as parameter, using '$VenvDir' to determine values"
}
else {
Write-Verbose "VenvDir not given as a parameter, using parent directory name as VenvDir."
$VenvDir = $VenvExecDir.Parent.FullName.TrimEnd("\\/")
Write-Verbose "VenvDir=$VenvDir"
}
# Next, read the `pyvenv.cfg` file to determine any required value such
# as `prompt`.
$pyvenvCfg = Get-PyVenvConfig -ConfigDir $VenvDir
# Next, set the prompt from the command line, or the config file, or
# just use the name of the virtual environment folder.
if ($Prompt) {
Write-Verbose "Prompt specified as argument, using '$Prompt'"
}
else {
Write-Verbose "Prompt not specified as argument to script, checking pyvenv.cfg value"
if ($pyvenvCfg -and $pyvenvCfg['prompt']) {
Write-Verbose " Setting based on value in pyvenv.cfg='$($pyvenvCfg['prompt'])'"
$Prompt = $pyvenvCfg['prompt'];
}
else {
Write-Verbose " Setting prompt based on parent's directory's name. (Is the directory name passed to venv module when creating the virtual environment)"
Write-Verbose " Got leaf-name of $VenvDir='$(Split-Path -Path $venvDir -Leaf)'"
$Prompt = Split-Path -Path $venvDir -Leaf
}
}
Write-Verbose "Prompt = '$Prompt'"
Write-Verbose "VenvDir='$VenvDir'"
# Deactivate any currently active virtual environment, but leave the
# deactivate function in place.
deactivate -nondestructive
# Now set the environment variable VIRTUAL_ENV, used by many tools to determine
# that there is an activated venv.
$env:VIRTUAL_ENV = $VenvDir
if (-not $Env:VIRTUAL_ENV_DISABLE_PROMPT) {
Write-Verbose "Setting prompt to '$Prompt'"
# Set the prompt to include the env name
# Make sure _OLD_VIRTUAL_PROMPT is global
function global:_OLD_VIRTUAL_PROMPT { "" }
Copy-Item -Path function:prompt -Destination function:_OLD_VIRTUAL_PROMPT
New-Variable -Name _PYTHON_VENV_PROMPT_PREFIX -Description "Python virtual environment prompt prefix" -Scope Global -Option ReadOnly -Visibility Public -Value $Prompt
function global:prompt {
Write-Host -NoNewline -ForegroundColor Green "($_PYTHON_VENV_PROMPT_PREFIX) "
_OLD_VIRTUAL_PROMPT
}
$env:VIRTUAL_ENV_PROMPT = $Prompt
}
# Clear PYTHONHOME
if (Test-Path -Path Env:PYTHONHOME) {
Copy-Item -Path Env:PYTHONHOME -Destination Env:_OLD_VIRTUAL_PYTHONHOME
Remove-Item -Path Env:PYTHONHOME
}
# Add the venv to the PATH
Copy-Item -Path Env:PATH -Destination Env:_OLD_VIRTUAL_PATH
$Env:PATH = "$VenvExecDir$([System.IO.Path]::PathSeparator)$Env:PATH"

69
acer-env/bin/activate Normal file
View File

@ -0,0 +1,69 @@
# This file must be used with "source bin/activate" *from bash*
# you cannot run it directly
deactivate () {
# reset old environment variables
if [ -n "${_OLD_VIRTUAL_PATH:-}" ] ; then
PATH="${_OLD_VIRTUAL_PATH:-}"
export PATH
unset _OLD_VIRTUAL_PATH
fi
if [ -n "${_OLD_VIRTUAL_PYTHONHOME:-}" ] ; then
PYTHONHOME="${_OLD_VIRTUAL_PYTHONHOME:-}"
export PYTHONHOME
unset _OLD_VIRTUAL_PYTHONHOME
fi
# This should detect bash and zsh, which have a hash command that must
# be called to get it to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
hash -r 2> /dev/null
fi
if [ -n "${_OLD_VIRTUAL_PS1:-}" ] ; then
PS1="${_OLD_VIRTUAL_PS1:-}"
export PS1
unset _OLD_VIRTUAL_PS1
fi
unset VIRTUAL_ENV
unset VIRTUAL_ENV_PROMPT
if [ ! "${1:-}" = "nondestructive" ] ; then
# Self destruct!
unset -f deactivate
fi
}
# unset irrelevant variables
deactivate nondestructive
VIRTUAL_ENV="/home/infidel/Sync/Project/ocp-wg-backend/acer-env"
export VIRTUAL_ENV
_OLD_VIRTUAL_PATH="$PATH"
PATH="$VIRTUAL_ENV/bin:$PATH"
export PATH
# unset PYTHONHOME if set
# this will fail if PYTHONHOME is set to the empty string (which is bad anyway)
# could use `if (set -u; : $PYTHONHOME) ;` in bash
if [ -n "${PYTHONHOME:-}" ] ; then
_OLD_VIRTUAL_PYTHONHOME="${PYTHONHOME:-}"
unset PYTHONHOME
fi
if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT:-}" ] ; then
_OLD_VIRTUAL_PS1="${PS1:-}"
PS1="(acer-env) ${PS1:-}"
export PS1
VIRTUAL_ENV_PROMPT="(acer-env) "
export VIRTUAL_ENV_PROMPT
fi
# This should detect bash and zsh, which have a hash command that must
# be called to get it to forget past commands. Without forgetting
# past commands the $PATH changes we made may not be respected
if [ -n "${BASH:-}" -o -n "${ZSH_VERSION:-}" ] ; then
hash -r 2> /dev/null
fi

26
acer-env/bin/activate.csh Normal file
View File

@ -0,0 +1,26 @@
# This file must be used with "source bin/activate.csh" *from csh*.
# You cannot run it directly.
# Created by Davide Di Blasi <davidedb@gmail.com>.
# Ported to Python 3.3 venv by Andrew Svetlov <andrew.svetlov@gmail.com>
alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; unsetenv VIRTUAL_ENV_PROMPT; test "\!:*" != "nondestructive" && unalias deactivate'
# Unset irrelevant variables.
deactivate nondestructive
setenv VIRTUAL_ENV "/home/infidel/Sync/Project/ocp-wg-backend/acer-env"
set _OLD_VIRTUAL_PATH="$PATH"
setenv PATH "$VIRTUAL_ENV/bin:$PATH"
set _OLD_VIRTUAL_PROMPT="$prompt"
if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then
set prompt = "(acer-env) $prompt"
setenv VIRTUAL_ENV_PROMPT "(acer-env) "
endif
alias pydoc python -m pydoc
rehash

66
acer-env/bin/activate.fish Normal file
View File

@ -0,0 +1,66 @@
# This file must be used with "source <venv>/bin/activate.fish" *from fish*
# (https://fishshell.com/); you cannot run it directly.
function deactivate -d "Exit virtual environment and return to normal shell environment"
# reset old environment variables
if test -n "$_OLD_VIRTUAL_PATH"
set -gx PATH $_OLD_VIRTUAL_PATH
set -e _OLD_VIRTUAL_PATH
end
if test -n "$_OLD_VIRTUAL_PYTHONHOME"
set -gx PYTHONHOME $_OLD_VIRTUAL_PYTHONHOME
set -e _OLD_VIRTUAL_PYTHONHOME
end
if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
functions -e fish_prompt
set -e _OLD_FISH_PROMPT_OVERRIDE
functions -c _old_fish_prompt fish_prompt
functions -e _old_fish_prompt
end
set -e VIRTUAL_ENV
set -e VIRTUAL_ENV_PROMPT
if test "$argv[1]" != "nondestructive"
# Self-destruct!
functions -e deactivate
end
end
# Unset irrelevant variables.
deactivate nondestructive
set -gx VIRTUAL_ENV "/home/infidel/Sync/Project/ocp-wg-backend/acer-env"
set -gx _OLD_VIRTUAL_PATH $PATH
set -gx PATH "$VIRTUAL_ENV/bin" $PATH
# Unset PYTHONHOME if set.
if set -q PYTHONHOME
set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
set -e PYTHONHOME
end
if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
# fish uses a function instead of an env var to generate the prompt.
# Save the current fish_prompt function as the function _old_fish_prompt.
functions -c fish_prompt _old_fish_prompt
# With the original prompt function renamed, we can override with our own.
function fish_prompt
# Save the return status of the last command.
set -l old_status $status
# Output the venv prompt; color taken from the blue of the Python logo.
printf "%s%s%s" (set_color 4B8BBE) "(acer-env) " (set_color normal)
# Restore the return status of the previous command.
echo "exit $old_status" | .
# Output the original/"old" prompt.
_old_fish_prompt
end
set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
set -gx VIRTUAL_ENV_PROMPT "(acer-env) "
end

8
acer-env/bin/django-admin Executable file
View File

@ -0,0 +1,8 @@
#!/home/infidel/Sync/Project/ocp-wg-backend/acer-env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from django.core.management import execute_from_command_line
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(execute_from_command_line())

8
acer-env/bin/normalizer Executable file
View File

@ -0,0 +1,8 @@
#!/home/infidel/Sync/Project/ocp-wg-backend/acer-env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from charset_normalizer.cli.normalizer import cli_detect
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(cli_detect())

8
acer-env/bin/pip Executable file
View File

@ -0,0 +1,8 @@
#!/home/infidel/Sync/Project/ocp-wg-backend/acer-env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
acer-env/bin/pip3 Executable file
View File

@ -0,0 +1,8 @@
#!/home/infidel/Sync/Project/ocp-wg-backend/acer-env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
acer-env/bin/pip3.10 Executable file
View File

@ -0,0 +1,8 @@
#!/home/infidel/Sync/Project/ocp-wg-backend/acer-env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

1
acer-env/bin/python Symbolic link
View File

@ -0,0 +1 @@
python3

1
acer-env/bin/python3 Symbolic link
View File

@ -0,0 +1 @@
/usr/bin/python3

1
acer-env/bin/python3.10 Symbolic link
View File

@ -0,0 +1 @@
python3

8
acer-env/bin/sqlformat Executable file
View File

@ -0,0 +1,8 @@
#!/home/infidel/Sync/Project/ocp-wg-backend/acer-env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from sqlparse.__main__ import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
acer-env/bin/tabulate Executable file
View File

@ -0,0 +1,8 @@
#!/home/infidel/Sync/Project/ocp-wg-backend/acer-env/bin/python3
# -*- coding: utf-8 -*-
import re
import sys
from tabulate import _main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(_main())

1046
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/AUTHORS Normal file
View File

File diff suppressed because it is too large Load Diff

1
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/INSTALLER Normal file
View File

@ -0,0 +1 @@
pip

27
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/LICENSE Normal file
View File

@ -0,0 +1,27 @@
Copyright (c) Django Software Foundation and individual contributors.
All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
3. Neither the name of Django nor the names of its contributors may be used
to endorse or promote products derived from this software without
specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

290
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/LICENSE.python Normal file
View File

@ -0,0 +1,290 @@
Django is licensed under the three-clause BSD license; see the file
LICENSE for details.
Django includes code from the Python standard library, which is licensed under
the Python license, a permissive open source license. The copyright and license
is included below for compliance with Python's terms.
----------------------------------------------------------------------
Copyright (c) 2001-present Python Software Foundation; All Rights Reserved
A. HISTORY OF THE SOFTWARE
==========================
Python was created in the early 1990s by Guido van Rossum at Stichting
Mathematisch Centrum (CWI, see http://www.cwi.nl) in the Netherlands
as a successor of a language called ABC. Guido remains Python's
principal author, although it includes many contributions from others.
In 1995, Guido continued his work on Python at the Corporation for
National Research Initiatives (CNRI, see http://www.cnri.reston.va.us)
in Reston, Virginia where he released several versions of the
software.
In May 2000, Guido and the Python core development team moved to
BeOpen.com to form the BeOpen PythonLabs team. In October of the same
year, the PythonLabs team moved to Digital Creations, which became
Zope Corporation. In 2001, the Python Software Foundation (PSF, see
https://www.python.org/psf/) was formed, a non-profit organization
created specifically to own Python-related Intellectual Property.
Zope Corporation was a sponsoring member of the PSF.
All Python releases are Open Source (see http://www.opensource.org for
the Open Source Definition). Historically, most, but not all, Python
releases have also been GPL-compatible; the table below summarizes
the various releases.
Release Derived Year Owner GPL-
from compatible? (1)
0.9.0 thru 1.2 1991-1995 CWI yes
1.3 thru 1.5.2 1.2 1995-1999 CNRI yes
1.6 1.5.2 2000 CNRI no
2.0 1.6 2000 BeOpen.com no
1.6.1 1.6 2001 CNRI yes (2)
2.1 2.0+1.6.1 2001 PSF no
2.0.1 2.0+1.6.1 2001 PSF yes
2.1.1 2.1+2.0.1 2001 PSF yes
2.1.2 2.1.1 2002 PSF yes
2.1.3 2.1.2 2002 PSF yes
2.2 and above 2.1.1 2001-now PSF yes
Footnotes:
(1) GPL-compatible doesn't mean that we're distributing Python under
the GPL. All Python licenses, unlike the GPL, let you distribute
a modified version without making your changes open source. The
GPL-compatible licenses make it possible to combine Python with
other software that is released under the GPL; the others don't.
(2) According to Richard Stallman, 1.6.1 is not GPL-compatible,
because its license has a choice of law clause. According to
CNRI, however, Stallman's lawyer has told CNRI's lawyer that 1.6.1
is "not incompatible" with the GPL.
Thanks to the many outside volunteers who have worked under Guido's
direction to make these releases possible.
B. TERMS AND CONDITIONS FOR ACCESSING OR OTHERWISE USING PYTHON
===============================================================
Python software and documentation are licensed under the
Python Software Foundation License Version 2.
Starting with Python 3.8.6, examples, recipes, and other code in
the documentation are dual licensed under the PSF License Version 2
and the Zero-Clause BSD license.
Some software incorporated into Python is under different licenses.
The licenses are listed with code falling under that license.
PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
--------------------------------------------
1. This LICENSE AGREEMENT is between the Python Software Foundation
("PSF"), and the Individual or Organization ("Licensee") accessing and
otherwise using this software ("Python") in source or binary form and
its associated documentation.
2. Subject to the terms and conditions of this License Agreement, PSF hereby
grants Licensee a nonexclusive, royalty-free, world-wide license to reproduce,
analyze, test, perform and/or display publicly, prepare derivative works,
distribute, and otherwise use Python alone or in any derivative version,
provided, however, that PSF's License Agreement and PSF's notice of copyright,
i.e., "Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010,
2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022 Python Software Foundation;
All Rights Reserved" are retained in Python alone or in any derivative version
prepared by Licensee.
3. In the event Licensee prepares a derivative work that is based on
or incorporates Python or any part thereof, and wants to make
the derivative work available to others as provided herein, then
Licensee hereby agrees to include in any such work a brief summary of
the changes made to Python.
4. PSF is making Python available to Licensee on an "AS IS"
basis. PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON,
OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
6. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
7. Nothing in this License Agreement shall be deemed to create any
relationship of agency, partnership, or joint venture between PSF and
Licensee. This License Agreement does not grant permission to use PSF
trademarks or trade name in a trademark sense to endorse or promote
products or services of Licensee, or any third party.
8. By copying, installing or otherwise using Python, Licensee
agrees to be bound by the terms and conditions of this License
Agreement.
BEOPEN.COM LICENSE AGREEMENT FOR PYTHON 2.0
-------------------------------------------
BEOPEN PYTHON OPEN SOURCE LICENSE AGREEMENT VERSION 1
1. This LICENSE AGREEMENT is between BeOpen.com ("BeOpen"), having an
office at 160 Saratoga Avenue, Santa Clara, CA 95051, and the
Individual or Organization ("Licensee") accessing and otherwise using
this software in source or binary form and its associated
documentation ("the Software").
2. Subject to the terms and conditions of this BeOpen Python License
Agreement, BeOpen hereby grants Licensee a non-exclusive,
royalty-free, world-wide license to reproduce, analyze, test, perform
and/or display publicly, prepare derivative works, distribute, and
otherwise use the Software alone or in any derivative version,
provided, however, that the BeOpen Python License is retained in the
Software, alone or in any derivative version prepared by Licensee.
3. BeOpen is making the Software available to Licensee on an "AS IS"
basis. BEOPEN MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, BEOPEN MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
4. BEOPEN SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF THE
SOFTWARE FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS
AS A RESULT OF USING, MODIFYING OR DISTRIBUTING THE SOFTWARE, OR ANY
DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
5. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
6. This License Agreement shall be governed by and interpreted in all
respects by the law of the State of California, excluding conflict of
law provisions. Nothing in this License Agreement shall be deemed to
create any relationship of agency, partnership, or joint venture
between BeOpen and Licensee. This License Agreement does not grant
permission to use BeOpen trademarks or trade names in a trademark
sense to endorse or promote products or services of Licensee, or any
third party. As an exception, the "BeOpen Python" logos available at
http://www.pythonlabs.com/logos.html may be used according to the
permissions granted on that web page.
7. By copying, installing or otherwise using the software, Licensee
agrees to be bound by the terms and conditions of this License
Agreement.
CNRI LICENSE AGREEMENT FOR PYTHON 1.6.1
---------------------------------------
1. This LICENSE AGREEMENT is between the Corporation for National
Research Initiatives, having an office at 1895 Preston White Drive,
Reston, VA 20191 ("CNRI"), and the Individual or Organization
("Licensee") accessing and otherwise using Python 1.6.1 software in
source or binary form and its associated documentation.
2. Subject to the terms and conditions of this License Agreement, CNRI
hereby grants Licensee a nonexclusive, royalty-free, world-wide
license to reproduce, analyze, test, perform and/or display publicly,
prepare derivative works, distribute, and otherwise use Python 1.6.1
alone or in any derivative version, provided, however, that CNRI's
License Agreement and CNRI's notice of copyright, i.e., "Copyright (c)
1995-2001 Corporation for National Research Initiatives; All Rights
Reserved" are retained in Python 1.6.1 alone or in any derivative
version prepared by Licensee. Alternately, in lieu of CNRI's License
Agreement, Licensee may substitute the following text (omitting the
quotes): "Python 1.6.1 is made available subject to the terms and
conditions in CNRI's License Agreement. This Agreement together with
Python 1.6.1 may be located on the internet using the following
unique, persistent identifier (known as a handle): 1895.22/1013. This
Agreement may also be obtained from a proxy server on the internet
using the following URL: http://hdl.handle.net/1895.22/1013".
3. In the event Licensee prepares a derivative work that is based on
or incorporates Python 1.6.1 or any part thereof, and wants to make
the derivative work available to others as provided herein, then
Licensee hereby agrees to include in any such work a brief summary of
the changes made to Python 1.6.1.
4. CNRI is making Python 1.6.1 available to Licensee on an "AS IS"
basis. CNRI MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, CNRI MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 1.6.1 WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
5. CNRI SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
1.6.1 FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 1.6.1,
OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
6. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
7. This License Agreement shall be governed by the federal
intellectual property law of the United States, including without
limitation the federal copyright law, and, to the extent such
U.S. federal law does not apply, by the law of the Commonwealth of
Virginia, excluding Virginia's conflict of law provisions.
Notwithstanding the foregoing, with regard to derivative works based
on Python 1.6.1 that incorporate non-separable material that was
previously distributed under the GNU General Public License (GPL), the
law of the Commonwealth of Virginia shall govern this License
Agreement only as to issues arising under or with respect to
Paragraphs 4, 5, and 7 of this License Agreement. Nothing in this
License Agreement shall be deemed to create any relationship of
agency, partnership, or joint venture between CNRI and Licensee. This
License Agreement does not grant permission to use CNRI trademarks or
trade name in a trademark sense to endorse or promote products or
services of Licensee, or any third party.
8. By clicking on the "ACCEPT" button where indicated, or by copying,
installing or otherwise using Python 1.6.1, Licensee agrees to be
bound by the terms and conditions of this License Agreement.
ACCEPT
CWI LICENSE AGREEMENT FOR PYTHON 0.9.0 THROUGH 1.2
--------------------------------------------------
Copyright (c) 1991 - 1995, Stichting Mathematisch Centrum Amsterdam,
The Netherlands. All rights reserved.
Permission to use, copy, modify, and distribute this software and its
documentation for any purpose and without fee is hereby granted,
provided that the above copyright notice appear in all copies and that
both that copyright notice and this permission notice appear in
supporting documentation, and that the name of Stichting Mathematisch
Centrum or CWI not be used in advertising or publicity pertaining to
distribution of the software without specific, written prior
permission.
STICHTING MATHEMATISCH CENTRUM DISCLAIMS ALL WARRANTIES WITH REGARD TO
THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH CENTRUM BE LIABLE
FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
ZERO-CLAUSE BSD LICENSE FOR CODE IN THE PYTHON DOCUMENTATION
----------------------------------------------------------------------
Permission to use, copy, modify, and/or distribute this software for any
purpose with or without fee is hereby granted.
THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.

100
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/METADATA Normal file
View File

@ -0,0 +1,100 @@
Metadata-Version: 2.1
Name: Django
Version: 4.1.2
Summary: A high-level Python web framework that encourages rapid development and clean, pragmatic design.
Home-page: https://www.djangoproject.com/
Author: Django Software Foundation
Author-email: foundation@djangoproject.com
License: BSD-3-Clause
Project-URL: Documentation, https://docs.djangoproject.com/
Project-URL: Release notes, https://docs.djangoproject.com/en/stable/releases/
Project-URL: Funding, https://www.djangoproject.com/fundraising/
Project-URL: Source, https://github.com/django/django
Project-URL: Tracker, https://code.djangoproject.com/
Platform: UNKNOWN
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Web Environment
Classifier: Framework :: Django
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Internet :: WWW/HTTP
Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
Classifier: Topic :: Internet :: WWW/HTTP :: WSGI
Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.8
License-File: LICENSE
License-File: LICENSE.python
License-File: AUTHORS
Requires-Dist: asgiref (<4,>=3.5.2)
Requires-Dist: sqlparse (>=0.2.2)
Requires-Dist: backports.zoneinfo ; python_version < "3.9"
Requires-Dist: tzdata ; sys_platform == "win32"
Provides-Extra: argon2
Requires-Dist: argon2-cffi (>=19.1.0) ; extra == 'argon2'
Provides-Extra: bcrypt
Requires-Dist: bcrypt ; extra == 'bcrypt'
======
Django
======
Django is a high-level Python web framework that encourages rapid development
and clean, pragmatic design. Thanks for checking it out.
All documentation is in the "``docs``" directory and online at
https://docs.djangoproject.com/en/stable/. If you're just getting started,
here's how we recommend you read the docs:
* First, read ``docs/intro/install.txt`` for instructions on installing Django.
* Next, work through the tutorials in order (``docs/intro/tutorial01.txt``,
``docs/intro/tutorial02.txt``, etc.).
* If you want to set up an actual deployment server, read
``docs/howto/deployment/index.txt`` for instructions.
* You'll probably want to read through the topical guides (in ``docs/topics``)
next; from there you can jump to the HOWTOs (in ``docs/howto``) for specific
problems, and check out the reference (``docs/ref``) for gory details.
* See ``docs/README`` for instructions on building an HTML version of the docs.
Docs are updated rigorously. If you find any problems in the docs, or think
they should be clarified in any way, please take 30 seconds to fill out a
ticket here: https://code.djangoproject.com/newticket
To get more help:
* Join the ``#django`` channel on ``irc.libera.chat``. Lots of helpful people
hang out there. See https://web.libera.chat if you're new to IRC.
* Join the django-users mailing list, or read the archives, at
https://groups.google.com/group/django-users.
To contribute to Django:
* Check out https://docs.djangoproject.com/en/dev/internals/contributing/ for
information about getting involved.
To run Django's test suite:
* Follow the instructions in the "Unit tests" section of
``docs/internals/contributing/writing-code/unit-tests.txt``, published online at
https://docs.djangoproject.com/en/dev/internals/contributing/writing-code/unit-tests/#running-the-unit-tests
Supporting the Development of Django
====================================
Django's development depends on your contributions.
If you depend on Django, remember to support the Django Software Foundation: https://www.djangoproject.com/fundraising/

4451
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/RECORD Normal file
View File

File diff suppressed because it is too large Load Diff

0
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/REQUESTED Normal file
View File

5
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/WHEEL Normal file
View File

@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.0)
Root-Is-Purelib: true
Tag: py3-none-any

3
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/entry_points.txt Normal file
View File

@ -0,0 +1,3 @@
[console_scripts]
django-admin = django.core.management:execute_from_command_line

1
acer-env/lib/python3.10/site-packages/Django-4.1.2.dist-info/top_level.txt Normal file
View File

@ -0,0 +1 @@
django

132
acer-env/lib/python3.10/site-packages/_distutils_hack/__init__.py Normal file
View File

@ -0,0 +1,132 @@
import sys
import os
import re
import importlib
import warnings
is_pypy = '__pypy__' in sys.builtin_module_names
warnings.filterwarnings('ignore',
r'.+ distutils\b.+ deprecated',
DeprecationWarning)
def warn_distutils_present():
if 'distutils' not in sys.modules:
return
if is_pypy and sys.version_info < (3, 7):
# PyPy for 3.6 unconditionally imports distutils, so bypass the warning
# https://foss.heptapod.net/pypy/pypy/-/blob/be829135bc0d758997b3566062999ee8b23872b4/lib-python/3/site.py#L250
return
warnings.warn(
"Distutils was imported before Setuptools, but importing Setuptools "
"also replaces the `distutils` module in `sys.modules`. This may lead "
"to undesirable behaviors or errors. To avoid these issues, avoid "
"using distutils directly, ensure that setuptools is installed in the "
"traditional way (e.g. not an editable install), and/or make sure "
"that setuptools is always imported before distutils.")
def clear_distutils():
if 'distutils' not in sys.modules:
return
warnings.warn("Setuptools is replacing distutils.")
mods = [name for name in sys.modules if re.match(r'distutils\b', name)]
for name in mods:
del sys.modules[name]
def enabled():
"""
Allow selection of distutils by environment variable.
"""
which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'stdlib')
return which == 'local'
def ensure_local_distutils():
clear_distutils()
# With the DistutilsMetaFinder in place,
# perform an import to cause distutils to be
# loaded from setuptools._distutils. Ref #2906.
add_shim()
importlib.import_module('distutils')
remove_shim()
# check that submodules load as expected
core = importlib.import_module('distutils.core')
assert '_distutils' in core.__file__, core.__file__
def do_override():
"""
Ensure that the local copy of distutils is preferred over stdlib.
See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401
for more motivation.
"""
if enabled():
warn_distutils_present()
ensure_local_distutils()
class DistutilsMetaFinder:
def find_spec(self, fullname, path, target=None):
if path is not None:
return
method_name = 'spec_for_{fullname}'.format(**locals())
method = getattr(self, method_name, lambda: None)
return method()
def spec_for_distutils(self):
import importlib.abc
import importlib.util
class DistutilsLoader(importlib.abc.Loader):
def create_module(self, spec):
return importlib.import_module('setuptools._distutils')
def exec_module(self, module):
pass
return importlib.util.spec_from_loader('distutils', DistutilsLoader())
def spec_for_pip(self):
"""
Ensure stdlib distutils when running under pip.
See pypa/pip#8761 for rationale.
"""
if self.pip_imported_during_build():
return
clear_distutils()
self.spec_for_distutils = lambda: None
@staticmethod
def pip_imported_during_build():
"""
Detect if pip is being imported in a build script. Ref #2355.
"""
import traceback
return any(
frame.f_globals['__file__'].endswith('setup.py')
for frame, line in traceback.walk_stack(None)
)
DISTUTILS_FINDER = DistutilsMetaFinder()
def add_shim():
sys.meta_path.insert(0, DISTUTILS_FINDER)
def remove_shim():
try:
sys.meta_path.remove(DISTUTILS_FINDER)
except ValueError:
pass

BIN
acer-env/lib/python3.10/site-packages/_distutils_hack/__pycache__/__init__.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/_distutils_hack/__pycache__/override.cpython-310.pyc Normal file
View File

Binary file not shown.

1
acer-env/lib/python3.10/site-packages/_distutils_hack/override.py Normal file
View File

@ -0,0 +1 @@
__import__('_distutils_hack').do_override()

1
acer-env/lib/python3.10/site-packages/asgiref-3.5.2.dist-info/INSTALLER Normal file
View File

@ -0,0 +1 @@
pip

27
acer-env/lib/python3.10/site-packages/asgiref-3.5.2.dist-info/LICENSE Normal file
View File

@ -0,0 +1,27 @@
Copyright (c) Django Software Foundation and individual contributors.
All rights reserved.
Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
3. Neither the name of Django nor the names of its contributors may be used
to endorse or promote products derived from this software without
specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

245
acer-env/lib/python3.10/site-packages/asgiref-3.5.2.dist-info/METADATA Normal file
View File

@ -0,0 +1,245 @@
Metadata-Version: 2.1
Name: asgiref
Version: 3.5.2
Summary: ASGI specs, helper code, and adapters
Home-page: https://github.com/django/asgiref/
Author: Django Software Foundation
Author-email: foundation@djangoproject.com
License: BSD
Project-URL: Documentation, https://asgi.readthedocs.io/
Project-URL: Further Documentation, https://docs.djangoproject.com/en/stable/topics/async/#async-adapter-functions
Project-URL: Changelog, https://github.com/django/asgiref/blob/master/CHANGELOG.txt
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Web Environment
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Internet :: WWW/HTTP
Requires-Python: >=3.7
License-File: LICENSE
Requires-Dist: typing-extensions ; python_version < "3.8"
Provides-Extra: tests
Requires-Dist: pytest ; extra == 'tests'
Requires-Dist: pytest-asyncio ; extra == 'tests'
Requires-Dist: mypy (>=0.800) ; extra == 'tests'
asgiref
=======
.. image:: https://api.travis-ci.org/django/asgiref.svg
:target: https://travis-ci.org/django/asgiref
.. image:: https://img.shields.io/pypi/v/asgiref.svg
:target: https://pypi.python.org/pypi/asgiref
ASGI is a standard for Python asynchronous web apps and servers to communicate
with each other, and positioned as an asynchronous successor to WSGI. You can
read more at https://asgi.readthedocs.io/en/latest/
This package includes ASGI base libraries, such as:
* Sync-to-async and async-to-sync function wrappers, ``asgiref.sync``
* Server base classes, ``asgiref.server``
* A WSGI-to-ASGI adapter, in ``asgiref.wsgi``
Function wrappers
-----------------
These allow you to wrap or decorate async or sync functions to call them from
the other style (so you can call async functions from a synchronous thread,
or vice-versa).
In particular:
* AsyncToSync lets a synchronous subthread stop and wait while the async
function is called on the main thread's event loop, and then control is
returned to the thread when the async function is finished.
* SyncToAsync lets async code call a synchronous function, which is run in
a threadpool and control returned to the async coroutine when the synchronous
function completes.
The idea is to make it easier to call synchronous APIs from async code and
asynchronous APIs from synchronous code so it's easier to transition code from
one style to the other. In the case of Channels, we wrap the (synchronous)
Django view system with SyncToAsync to allow it to run inside the (asynchronous)
ASGI server.
Note that exactly what threads things run in is very specific, and aimed to
keep maximum compatibility with old synchronous code. See
"Synchronous code & Threads" below for a full explanation. By default,
``sync_to_async`` will run all synchronous code in the program in the same
thread for safety reasons; you can disable this for more performance with
``@sync_to_async(thread_sensitive=False)``, but make sure that your code does
not rely on anything bound to threads (like database connections) when you do.
Threadlocal replacement
-----------------------
This is a drop-in replacement for ``threading.local`` that works with both
threads and asyncio Tasks. Even better, it will proxy values through from a
task-local context to a thread-local context when you use ``sync_to_async``
to run things in a threadpool, and vice-versa for ``async_to_sync``.
If you instead want true thread- and task-safety, you can set
``thread_critical`` on the Local object to ensure this instead.
Server base classes
-------------------
Includes a ``StatelessServer`` class which provides all the hard work of
writing a stateless server (as in, does not handle direct incoming sockets
but instead consumes external streams or sockets to work out what is happening).
An example of such a server would be a chatbot server that connects out to
a central chat server and provides a "connection scope" per user chatting to
it. There's only one actual connection, but the server has to separate things
into several scopes for easier writing of the code.
You can see an example of this being used in `frequensgi <https://github.com/andrewgodwin/frequensgi>`_.
WSGI-to-ASGI adapter
--------------------
Allows you to wrap a WSGI application so it appears as a valid ASGI application.
Simply wrap it around your WSGI application like so::
asgi_application = WsgiToAsgi(wsgi_application)
The WSGI application will be run in a synchronous threadpool, and the wrapped
ASGI application will be one that accepts ``http`` class messages.
Please note that not all extended features of WSGI may be supported (such as
file handles for incoming POST bodies).
Dependencies
------------
``asgiref`` requires Python 3.7 or higher.
Contributing
------------
Please refer to the
`main Channels contributing docs <https://github.com/django/channels/blob/master/CONTRIBUTING.rst>`_.
Testing
'''''''
To run tests, make sure you have installed the ``tests`` extra with the package::
cd asgiref/
pip install -e .[tests]
pytest
Building the documentation
''''''''''''''''''''''''''
The documentation uses `Sphinx <http://www.sphinx-doc.org>`_::
cd asgiref/docs/
pip install sphinx
To build the docs, you can use the default tools::
sphinx-build -b html . _build/html # or `make html`, if you've got make set up
cd _build/html
python -m http.server
...or you can use ``sphinx-autobuild`` to run a server and rebuild/reload
your documentation changes automatically::
pip install sphinx-autobuild
sphinx-autobuild . _build/html
Releasing
'''''''''
To release, first add details to CHANGELOG.txt and update the version number in ``asgiref/__init__.py``.
Then, build and push the packages::
python -m build
twine upload dist/*
rm -r build/ dist/
Implementation Details
----------------------
Synchronous code & threads
''''''''''''''''''''''''''
The ``asgiref.sync`` module provides two wrappers that let you go between
asynchronous and synchronous code at will, while taking care of the rough edges
for you.
Unfortunately, the rough edges are numerous, and the code has to work especially
hard to keep things in the same thread as much as possible. Notably, the
restrictions we are working with are:
* All synchronous code called through ``SyncToAsync`` and marked with
``thread_sensitive`` should run in the same thread as each other (and if the
outer layer of the program is synchronous, the main thread)
* If a thread already has a running async loop, ``AsyncToSync`` can't run things
on that loop if it's blocked on synchronous code that is above you in the
call stack.
The first compromise you get to might be that ``thread_sensitive`` code should
just run in the same thread and not spawn in a sub-thread, fulfilling the first
restriction, but that immediately runs you into the second restriction.
The only real solution is to essentially have a variant of ThreadPoolExecutor
that executes any ``thread_sensitive`` code on the outermost synchronous
thread - either the main thread, or a single spawned subthread.
This means you now have two basic states:
* If the outermost layer of your program is synchronous, then all async code
run through ``AsyncToSync`` will run in a per-call event loop in arbitrary
sub-threads, while all ``thread_sensitive`` code will run in the main thread.
* If the outermost layer of your program is asynchronous, then all async code
runs on the main thread's event loop, and all ``thread_sensitive`` synchronous
code will run in a single shared sub-thread.
Crucially, this means that in both cases there is a thread which is a shared
resource that all ``thread_sensitive`` code must run on, and there is a chance
that this thread is currently blocked on its own ``AsyncToSync`` call. Thus,
``AsyncToSync`` needs to act as an executor for thread code while it's blocking.
The ``CurrentThreadExecutor`` class provides this functionality; rather than
simply waiting on a Future, you can call its ``run_until_future`` method and
it will run submitted code until that Future is done. This means that code
inside the call can then run code on your thread.
Maintenance and Security
------------------------
To report security issues, please contact security@djangoproject.com. For GPG
signatures and more security process information, see
https://docs.djangoproject.com/en/dev/internals/security/.
To report bugs or request new features, please open a new GitHub issue.
This repository is part of the Channels project. For the shepherd and maintenance team, please see the
`main Channels readme <https://github.com/django/channels/blob/master/README.rst>`_.

28
acer-env/lib/python3.10/site-packages/asgiref-3.5.2.dist-info/RECORD Normal file
View File

@ -0,0 +1,28 @@
asgiref-3.5.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
asgiref-3.5.2.dist-info/LICENSE,sha256=uEZBXRtRTpwd_xSiLeuQbXlLxUbKYSn5UKGM0JHipmk,1552
asgiref-3.5.2.dist-info/METADATA,sha256=3JU5Zw-j9qCKPcuf3cJZ5dVispB_b7UXU0fnQVp9DDA,9143
asgiref-3.5.2.dist-info/RECORD,,
asgiref-3.5.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
asgiref-3.5.2.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
asgiref-3.5.2.dist-info/top_level.txt,sha256=bokQjCzwwERhdBiPdvYEZa4cHxT4NCeAffQNUqJ8ssg,8
asgiref/__init__.py,sha256=LtYJ5AVwuiAlsrJUQwzHZMrGMIRn7cuIoIt4OznYy6c,22
asgiref/__pycache__/__init__.cpython-310.pyc,,
asgiref/__pycache__/compatibility.cpython-310.pyc,,
asgiref/__pycache__/current_thread_executor.cpython-310.pyc,,
asgiref/__pycache__/local.cpython-310.pyc,,
asgiref/__pycache__/server.cpython-310.pyc,,
asgiref/__pycache__/sync.cpython-310.pyc,,
asgiref/__pycache__/testing.cpython-310.pyc,,
asgiref/__pycache__/timeout.cpython-310.pyc,,
asgiref/__pycache__/typing.cpython-310.pyc,,
asgiref/__pycache__/wsgi.cpython-310.pyc,,
asgiref/compatibility.py,sha256=MVH2bEdiCMMVTLbE-1V6KiU7q4LwqzP7PIufeXa-njM,1598
asgiref/current_thread_executor.py,sha256=oeH8zv2tTmcbpxdUmOSMzbEXzeY5nJzIMFvzprE95gA,2801
asgiref/local.py,sha256=nx5RqVFLYgUJVaxzApuQUW7dd9y21sruMYdgISoRs1k,4854
asgiref/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
asgiref/server.py,sha256=egTQhZo1k4G0F7SSBQNp_VOekpGcjBJZU2kkCoiGC_M,6005
asgiref/sync.py,sha256=3P813NHl3EHPMtzPEjaBelmjV_JUw97zYbtx-MmLUiw,20185
asgiref/testing.py,sha256=3byNRV7Oto_Fg8Z-fErQJ3yGf7OQlcUexbN_cDQugzQ,3119
asgiref/timeout.py,sha256=5Ekbmn3X1HPR55qgx-hPJMPEu_-YoivHqNhFEitiSYE,3440
asgiref/typing.py,sha256=MZ7vbJY1F7EQqo9gL9pMSFRMw9b_SQrQQsnvlJQ2iP4,5603
asgiref/wsgi.py,sha256=-L0eo_uK_dq7EPjv1meW1BRGytURaO9NPESxnJc9CtA,6575

0
acer-env/lib/python3.10/site-packages/asgiref-3.5.2.dist-info/REQUESTED Normal file
View File

5
acer-env/lib/python3.10/site-packages/asgiref-3.5.2.dist-info/WHEEL Normal file
View File

@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.1)
Root-Is-Purelib: true
Tag: py3-none-any

1
acer-env/lib/python3.10/site-packages/asgiref-3.5.2.dist-info/top_level.txt Normal file
View File

@ -0,0 +1 @@
asgiref

1
acer-env/lib/python3.10/site-packages/asgiref/__init__.py Normal file
View File

@ -0,0 +1 @@
__version__ = "3.5.2"

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/__init__.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/compatibility.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/current_thread_executor.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/local.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/server.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/sync.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/testing.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/timeout.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/typing.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/asgiref/__pycache__/wsgi.cpython-310.pyc Normal file
View File

Binary file not shown.

47
acer-env/lib/python3.10/site-packages/asgiref/compatibility.py Normal file
View File

@ -0,0 +1,47 @@
import asyncio
import inspect
def is_double_callable(application):
"""
Tests to see if an application is a legacy-style (double-callable) application.
"""
# Look for a hint on the object first
if getattr(application, "_asgi_single_callable", False):
return False
if getattr(application, "_asgi_double_callable", False):
return True
# Uninstanted classes are double-callable
if inspect.isclass(application):
return True
# Instanted classes depend on their __call__
if hasattr(application, "__call__"):
# We only check to see if its __call__ is a coroutine function -
# if it's not, it still might be a coroutine function itself.
if asyncio.iscoroutinefunction(application.__call__):
return False
# Non-classes we just check directly
return not asyncio.iscoroutinefunction(application)
def double_to_single_callable(application):
"""
Transforms a double-callable ASGI application into a single-callable one.
"""
async def new_application(scope, receive, send):
instance = application(scope)
return await instance(receive, send)
return new_application
def guarantee_single_callable(application):
"""
Takes either a single- or double-callable application and always returns it
in single-callable style. Use this to add backwards compatibility for ASGI
2.0 applications to your server/test harness/etc.
"""
if is_double_callable(application):
application = double_to_single_callable(application)
return application

81
acer-env/lib/python3.10/site-packages/asgiref/current_thread_executor.py Normal file
View File

@ -0,0 +1,81 @@
import queue
import threading
from concurrent.futures import Executor, Future
class _WorkItem:
"""
Represents an item needing to be run in the executor.
Copied from ThreadPoolExecutor (but it's private, so we're not going to rely on importing it)
"""
def __init__(self, future, fn, args, kwargs):
self.future = future
self.fn = fn
self.args = args
self.kwargs = kwargs
def run(self):
if not self.future.set_running_or_notify_cancel():
return
try:
result = self.fn(*self.args, **self.kwargs)
except BaseException as exc:
self.future.set_exception(exc)
# Break a reference cycle with the exception 'exc'
self = None
else:
self.future.set_result(result)
class CurrentThreadExecutor(Executor):
"""
An Executor that actually runs code in the thread it is instantiated in.
Passed to other threads running async code, so they can run sync code in
the thread they came from.
"""
def __init__(self):
self._work_thread = threading.current_thread()
self._work_queue = queue.Queue()
self._broken = False
def run_until_future(self, future):
"""
Runs the code in the work queue until a result is available from the future.
Should be run from the thread the executor is initialised in.
"""
# Check we're in the right thread
if threading.current_thread() != self._work_thread:
raise RuntimeError(
"You cannot run CurrentThreadExecutor from a different thread"
)
future.add_done_callback(self._work_queue.put)
# Keep getting and running work items until we get the future we're waiting for
# back via the future's done callback.
try:
while True:
# Get a work item and run it
work_item = self._work_queue.get()
if work_item is future:
return
work_item.run()
del work_item
finally:
self._broken = True
def submit(self, fn, *args, **kwargs):
# Check they're not submitting from the same thread
if threading.current_thread() == self._work_thread:
raise RuntimeError(
"You cannot submit onto CurrentThreadExecutor from its own thread"
)
# Check they're not too late or the executor errored
if self._broken:
raise RuntimeError("CurrentThreadExecutor already quit or is broken")
# Add to work queue
f = Future()
work_item = _WorkItem(f, fn, args, kwargs)
self._work_queue.put(work_item)
# Return the future
return f

120
acer-env/lib/python3.10/site-packages/asgiref/local.py Normal file
View File

@ -0,0 +1,120 @@
import random
import string
import sys
import threading
import weakref
class Local:
"""
A drop-in replacement for threading.locals that also works with asyncio
Tasks (via the current_task asyncio method), and passes locals through
sync_to_async and async_to_sync.
Specifically:
- Locals work per-coroutine on any thread not spawned using asgiref
- Locals work per-thread on any thread not spawned using asgiref
- Locals are shared with the parent coroutine when using sync_to_async
- Locals are shared with the parent thread when using async_to_sync
(and if that thread was launched using sync_to_async, with its parent
coroutine as well, with this working for indefinite levels of nesting)
Set thread_critical to True to not allow locals to pass from an async Task
to a thread it spawns. This is needed for code that truly needs
thread-safety, as opposed to things used for helpful context (e.g. sqlite
does not like being called from a different thread to the one it is from).
Thread-critical code will still be differentiated per-Task within a thread
as it is expected it does not like concurrent access.
This doesn't use contextvars as it needs to support 3.6. Once it can support
3.7 only, we can then reimplement the storage more nicely.
"""
def __init__(self, thread_critical: bool = False) -> None:
self._thread_critical = thread_critical
self._thread_lock = threading.RLock()
self._context_refs: "weakref.WeakSet[object]" = weakref.WeakSet()
# Random suffixes stop accidental reuse between different Locals,
# though we try to force deletion as well.
self._attr_name = "_asgiref_local_impl_{}_{}".format(
id(self),
"".join(random.choice(string.ascii_letters) for i in range(8)),
)
def _get_context_id(self):
"""
Get the ID we should use for looking up variables
"""
# Prevent a circular reference
from .sync import AsyncToSync, SyncToAsync
# First, pull the current task if we can
context_id = SyncToAsync.get_current_task()
context_is_async = True
# OK, let's try for a thread ID
if context_id is None:
context_id = threading.current_thread()
context_is_async = False
# If we're thread-critical, we stop here, as we can't share contexts.
if self._thread_critical:
return context_id
# Now, take those and see if we can resolve them through the launch maps
for i in range(sys.getrecursionlimit()):
try:
if context_is_async:
# Tasks have a source thread in AsyncToSync
context_id = AsyncToSync.launch_map[context_id]
context_is_async = False
else:
# Threads have a source task in SyncToAsync
context_id = SyncToAsync.launch_map[context_id]
context_is_async = True
except KeyError:
break
else:
# Catch infinite loops (they happen if you are screwing around
# with AsyncToSync implementations)
raise RuntimeError("Infinite launch_map loops")
return context_id
def _get_storage(self):
context_obj = self._get_context_id()
if not hasattr(context_obj, self._attr_name):
setattr(context_obj, self._attr_name, {})
self._context_refs.add(context_obj)
return getattr(context_obj, self._attr_name)
def __del__(self):
try:
for context_obj in self._context_refs:
try:
delattr(context_obj, self._attr_name)
except AttributeError:
pass
except TypeError:
# WeakSet.__iter__ can crash when interpreter is shutting down due
# to _IterationGuard being None.
pass
def __getattr__(self, key):
with self._thread_lock:
storage = self._get_storage()
if key in storage:
return storage[key]
else:
raise AttributeError(f"{self!r} object has no attribute {key!r}")
def __setattr__(self, key, value):
if key in ("_context_refs", "_thread_critical", "_thread_lock", "_attr_name"):
return super().__setattr__(key, value)
with self._thread_lock:
storage = self._get_storage()
storage[key] = value
def __delattr__(self, key):
with self._thread_lock:
storage = self._get_storage()
if key in storage:
del storage[key]
else:
raise AttributeError(f"{self!r} object has no attribute {key!r}")

0
acer-env/lib/python3.10/site-packages/asgiref/py.typed Normal file
View File

157
acer-env/lib/python3.10/site-packages/asgiref/server.py Normal file
View File

@ -0,0 +1,157 @@
import asyncio
import logging
import time
import traceback
from .compatibility import guarantee_single_callable
logger = logging.getLogger(__name__)
class StatelessServer:
"""
Base server class that handles basic concepts like application instance
creation/pooling, exception handling, and similar, for stateless protocols
(i.e. ones without actual incoming connections to the process)
Your code should override the handle() method, doing whatever it needs to,
and calling get_or_create_application_instance with a unique `scope_id`
and `scope` for the scope it wants to get.
If an application instance is found with the same `scope_id`, you are
given its input queue, otherwise one is made for you with the scope provided
and you are given that fresh new input queue. Either way, you should do
something like:
input_queue = self.get_or_create_application_instance(
"user-123456",
{"type": "testprotocol", "user_id": "123456", "username": "andrew"},
)
input_queue.put_nowait(message)
If you try and create an application instance and there are already
`max_application` instances, the oldest/least recently used one will be
reclaimed and shut down to make space.
Application coroutines that error will be found periodically (every 100ms
by default) and have their exceptions printed to the console. Override
application_exception() if you want to do more when this happens.
If you override run(), make sure you handle things like launching the
application checker.
"""
application_checker_interval = 0.1
def __init__(self, application, max_applications=1000):
# Parameters
self.application = application
self.max_applications = max_applications
# Initialisation
self.application_instances = {}
### Mainloop and handling
def run(self):
"""
Runs the asyncio event loop with our handler loop.
"""
event_loop = asyncio.get_event_loop()
asyncio.ensure_future(self.application_checker())
try:
event_loop.run_until_complete(self.handle())
except KeyboardInterrupt:
logger.info("Exiting due to Ctrl-C/interrupt")
async def handle(self):
raise NotImplementedError("You must implement handle()")
async def application_send(self, scope, message):
"""
Receives outbound sends from applications and handles them.
"""
raise NotImplementedError("You must implement application_send()")
### Application instance management
def get_or_create_application_instance(self, scope_id, scope):
"""
Creates an application instance and returns its queue.
"""
if scope_id in self.application_instances:
self.application_instances[scope_id]["last_used"] = time.time()
return self.application_instances[scope_id]["input_queue"]
# See if we need to delete an old one
while len(self.application_instances) > self.max_applications:
self.delete_oldest_application_instance()
# Make an instance of the application
input_queue = asyncio.Queue()
application_instance = guarantee_single_callable(self.application)
# Run it, and stash the future for later checking
future = asyncio.ensure_future(
application_instance(
scope=scope,
receive=input_queue.get,
send=lambda message: self.application_send(scope, message),
),
)
self.application_instances[scope_id] = {
"input_queue": input_queue,
"future": future,
"scope": scope,
"last_used": time.time(),
}
return input_queue
def delete_oldest_application_instance(self):
"""
Finds and deletes the oldest application instance
"""
oldest_time = min(
details["last_used"] for details in self.application_instances.values()
)
for scope_id, details in self.application_instances.items():
if details["last_used"] == oldest_time:
self.delete_application_instance(scope_id)
# Return to make sure we only delete one in case two have
# the same oldest time
return
def delete_application_instance(self, scope_id):
"""
Removes an application instance (makes sure its task is stopped,
then removes it from the current set)
"""
details = self.application_instances[scope_id]
del self.application_instances[scope_id]
if not details["future"].done():
details["future"].cancel()
async def application_checker(self):
"""
Goes through the set of current application instance Futures and cleans up
any that are done/prints exceptions for any that errored.
"""
while True:
await asyncio.sleep(self.application_checker_interval)
for scope_id, details in list(self.application_instances.items()):
if details["future"].done():
exception = details["future"].exception()
if exception:
await self.application_exception(exception, details)
try:
del self.application_instances[scope_id]
except KeyError:
# Exception handling might have already got here before us. That's fine.
pass
async def application_exception(self, exception, application_details):
"""
Called whenever an application coroutine has an exception.
"""
logging.error(
"Exception inside application: %s\n%s%s",
exception,
"".join(traceback.format_tb(exception.__traceback__)),
f" {exception}",
)

532
acer-env/lib/python3.10/site-packages/asgiref/sync.py Normal file
View File

@ -0,0 +1,532 @@
import asyncio
import asyncio.coroutines
import contextvars
import functools
import inspect
import os
import sys
import threading
import warnings
import weakref
from concurrent.futures import Future, ThreadPoolExecutor
from typing import Any, Callable, Dict, Optional, overload
from .current_thread_executor import CurrentThreadExecutor
from .local import Local
def _restore_context(context):
# Check for changes in contextvars, and set them to the current
# context for downstream consumers
for cvar in context:
try:
if cvar.get() != context.get(cvar):
cvar.set(context.get(cvar))
except LookupError:
cvar.set(context.get(cvar))
def _iscoroutinefunction_or_partial(func: Any) -> bool:
# Python < 3.8 does not correctly determine partially wrapped
# coroutine functions are coroutine functions, hence the need for
# this to exist. Code taken from CPython.
if sys.version_info >= (3, 8):
return asyncio.iscoroutinefunction(func)
else:
while inspect.ismethod(func):
func = func.__func__
while isinstance(func, functools.partial):
func = func.func
return asyncio.iscoroutinefunction(func)
class ThreadSensitiveContext:
"""Async context manager to manage context for thread sensitive mode
This context manager controls which thread pool executor is used when in
thread sensitive mode. By default, a single thread pool executor is shared
within a process.
In Python 3.7+, the ThreadSensitiveContext() context manager may be used to
specify a thread pool per context.
This context manager is re-entrant, so only the outer-most call to
ThreadSensitiveContext will set the context.
Usage:
>>> import time
>>> async with ThreadSensitiveContext():
... await sync_to_async(time.sleep, 1)()
"""
def __init__(self):
self.token = None
async def __aenter__(self):
try:
SyncToAsync.thread_sensitive_context.get()
except LookupError:
self.token = SyncToAsync.thread_sensitive_context.set(self)
return self
async def __aexit__(self, exc, value, tb):
if not self.token:
return
executor = SyncToAsync.context_to_thread_executor.pop(self, None)
if executor:
executor.shutdown()
SyncToAsync.thread_sensitive_context.reset(self.token)
class AsyncToSync:
"""
Utility class which turns an awaitable that only works on the thread with
the event loop into a synchronous callable that works in a subthread.
If the call stack contains an async loop, the code runs there.
Otherwise, the code runs in a new loop in a new thread.
Either way, this thread then pauses and waits to run any thread_sensitive
code called from further down the call stack using SyncToAsync, before
finally exiting once the async task returns.
"""
# Maps launched Tasks to the threads that launched them (for locals impl)
launch_map: "Dict[asyncio.Task[object], threading.Thread]" = {}
# Keeps track of which CurrentThreadExecutor to use. This uses an asgiref
# Local, not a threadlocal, so that tasks can work out what their parent used.
executors = Local()
# When we can't find a CurrentThreadExecutor from the context, such as
# inside create_task, we'll look it up here from the running event loop.
loop_thread_executors: "Dict[asyncio.AbstractEventLoop, CurrentThreadExecutor]" = {}
def __init__(self, awaitable, force_new_loop=False):
if not callable(awaitable) or (
not _iscoroutinefunction_or_partial(awaitable)
and not _iscoroutinefunction_or_partial(
getattr(awaitable, "__call__", awaitable)
)
):
# Python does not have very reliable detection of async functions
# (lots of false negatives) so this is just a warning.
warnings.warn(
"async_to_sync was passed a non-async-marked callable", stacklevel=2
)
self.awaitable = awaitable
try:
self.__self__ = self.awaitable.__self__
except AttributeError:
pass
if force_new_loop:
# They have asked that we always run in a new sub-loop.
self.main_event_loop = None
else:
try:
self.main_event_loop = asyncio.get_running_loop()
except RuntimeError:
# There's no event loop in this thread. Look for the threadlocal if
# we're inside SyncToAsync
main_event_loop_pid = getattr(
SyncToAsync.threadlocal, "main_event_loop_pid", None
)
# We make sure the parent loop is from the same process - if
# they've forked, this is not going to be valid any more (#194)
if main_event_loop_pid and main_event_loop_pid == os.getpid():
self.main_event_loop = getattr(
SyncToAsync.threadlocal, "main_event_loop", None
)
else:
self.main_event_loop = None
def __call__(self, *args, **kwargs):
# You can't call AsyncToSync from a thread with a running event loop
try:
event_loop = asyncio.get_running_loop()
except RuntimeError:
pass
else:
if event_loop.is_running():
raise RuntimeError(
"You cannot use AsyncToSync in the same thread as an async event loop - "
"just await the async function directly."
)
# Wrapping context in list so it can be reassigned from within
# `main_wrap`.
context = [contextvars.copy_context()]
# Make a future for the return information
call_result = Future()
# Get the source thread
source_thread = threading.current_thread()
# Make a CurrentThreadExecutor we'll use to idle in this thread - we
# need one for every sync frame, even if there's one above us in the
# same thread.
if hasattr(self.executors, "current"):
old_current_executor = self.executors.current
else:
old_current_executor = None
current_executor = CurrentThreadExecutor()
self.executors.current = current_executor
loop = None
# Use call_soon_threadsafe to schedule a synchronous callback on the
# main event loop's thread if it's there, otherwise make a new loop
# in this thread.
try:
awaitable = self.main_wrap(
args, kwargs, call_result, source_thread, sys.exc_info(), context
)
if not (self.main_event_loop and self.main_event_loop.is_running()):
# Make our own event loop - in a new thread - and run inside that.
loop = asyncio.new_event_loop()
self.loop_thread_executors[loop] = current_executor
loop_executor = ThreadPoolExecutor(max_workers=1)
loop_future = loop_executor.submit(
self._run_event_loop, loop, awaitable
)
if current_executor:
# Run the CurrentThreadExecutor until the future is done
current_executor.run_until_future(loop_future)
# Wait for future and/or allow for exception propagation
loop_future.result()
else:
# Call it inside the existing loop
self.main_event_loop.call_soon_threadsafe(
self.main_event_loop.create_task, awaitable
)
if current_executor:
# Run the CurrentThreadExecutor until the future is done
current_executor.run_until_future(call_result)
finally:
# Clean up any executor we were running
if loop is not None:
del self.loop_thread_executors[loop]
if hasattr(self.executors, "current"):
del self.executors.current
if old_current_executor:
self.executors.current = old_current_executor
_restore_context(context[0])
# Wait for results from the future.
return call_result.result()
def _run_event_loop(self, loop, coro):
"""
Runs the given event loop (designed to be called in a thread).
"""
asyncio.set_event_loop(loop)
try:
loop.run_until_complete(coro)
finally:
try:
# mimic asyncio.run() behavior
# cancel unexhausted async generators
tasks = asyncio.all_tasks(loop)
for task in tasks:
task.cancel()
async def gather():
await asyncio.gather(*tasks, return_exceptions=True)
loop.run_until_complete(gather())
for task in tasks:
if task.cancelled():
continue
if task.exception() is not None:
loop.call_exception_handler(
{
"message": "unhandled exception during loop shutdown",
"exception": task.exception(),
"task": task,
}
)
if hasattr(loop, "shutdown_asyncgens"):
loop.run_until_complete(loop.shutdown_asyncgens())
finally:
loop.close()
asyncio.set_event_loop(self.main_event_loop)
def __get__(self, parent, objtype):
"""
Include self for methods
"""
func = functools.partial(self.__call__, parent)
return functools.update_wrapper(func, self.awaitable)
async def main_wrap(
self, args, kwargs, call_result, source_thread, exc_info, context
):
"""
Wraps the awaitable with something that puts the result into the
result/exception future.
"""
if context is not None:
_restore_context(context[0])
current_task = SyncToAsync.get_current_task()
self.launch_map[current_task] = source_thread
try:
# If we have an exception, run the function inside the except block
# after raising it so exc_info is correctly populated.
if exc_info[1]:
try:
raise exc_info[1]
except BaseException:
result = await self.awaitable(*args, **kwargs)
else:
result = await self.awaitable(*args, **kwargs)
except BaseException as e:
call_result.set_exception(e)
else:
call_result.set_result(result)
finally:
del self.launch_map[current_task]
context[0] = contextvars.copy_context()
class SyncToAsync:
"""
Utility class which turns a synchronous callable into an awaitable that
runs in a threadpool. It also sets a threadlocal inside the thread so
calls to AsyncToSync can escape it.
If thread_sensitive is passed, the code will run in the same thread as any
outer code. This is needed for underlying Python code that is not
threadsafe (for example, code which handles SQLite database connections).
If the outermost program is async (i.e. SyncToAsync is outermost), then
this will be a dedicated single sub-thread that all sync code runs in,
one after the other. If the outermost program is sync (i.e. AsyncToSync is
outermost), this will just be the main thread. This is achieved by idling
with a CurrentThreadExecutor while AsyncToSync is blocking its sync parent,
rather than just blocking.
If executor is passed in, that will be used instead of the loop's default executor.
In order to pass in an executor, thread_sensitive must be set to False, otherwise
a TypeError will be raised.
"""
# If they've set ASGI_THREADS, update the default asyncio executor for now
if "ASGI_THREADS" in os.environ:
# We use get_event_loop here - not get_running_loop - as this will
# be run at import time, and we want to update the main thread's loop.
loop = asyncio.get_event_loop()
loop.set_default_executor(
ThreadPoolExecutor(max_workers=int(os.environ["ASGI_THREADS"]))
)
# Maps launched threads to the coroutines that spawned them
launch_map: "Dict[threading.Thread, asyncio.Task[object]]" = {}
# Storage for main event loop references
threadlocal = threading.local()
# Single-thread executor for thread-sensitive code
single_thread_executor = ThreadPoolExecutor(max_workers=1)
# Maintain a contextvar for the current execution context. Optionally used
# for thread sensitive mode.
thread_sensitive_context: "contextvars.ContextVar[str]" = contextvars.ContextVar(
"thread_sensitive_context"
)
# Contextvar that is used to detect if the single thread executor
# would be awaited on while already being used in the same context
deadlock_context: "contextvars.ContextVar[bool]" = contextvars.ContextVar(
"deadlock_context"
)
# Maintaining a weak reference to the context ensures that thread pools are
# erased once the context goes out of scope. This terminates the thread pool.
context_to_thread_executor: "weakref.WeakKeyDictionary[object, ThreadPoolExecutor]" = (
weakref.WeakKeyDictionary()
)
def __init__(
self,
func: Callable[..., Any],
thread_sensitive: bool = True,
executor: Optional["ThreadPoolExecutor"] = None,
) -> None:
if (
not callable(func)
or _iscoroutinefunction_or_partial(func)
or _iscoroutinefunction_or_partial(getattr(func, "__call__", func))
):
raise TypeError("sync_to_async can only be applied to sync functions.")
self.func = func
functools.update_wrapper(self, func)
self._thread_sensitive = thread_sensitive
self._is_coroutine = asyncio.coroutines._is_coroutine # type: ignore
if thread_sensitive and executor is not None:
raise TypeError("executor must not be set when thread_sensitive is True")
self._executor = executor
try:
self.__self__ = func.__self__ # type: ignore
except AttributeError:
pass
async def __call__(self, *args, **kwargs):
loop = asyncio.get_running_loop()
# Work out what thread to run the code in
if self._thread_sensitive:
if hasattr(AsyncToSync.executors, "current"):
# If we have a parent sync thread above somewhere, use that
executor = AsyncToSync.executors.current
elif self.thread_sensitive_context and self.thread_sensitive_context.get(
None
):
# If we have a way of retrieving the current context, attempt
# to use a per-context thread pool executor
thread_sensitive_context = self.thread_sensitive_context.get()
if thread_sensitive_context in self.context_to_thread_executor:
# Re-use thread executor in current context
executor = self.context_to_thread_executor[thread_sensitive_context]
else:
# Create new thread executor in current context
executor = ThreadPoolExecutor(max_workers=1)
self.context_to_thread_executor[thread_sensitive_context] = executor
elif loop in AsyncToSync.loop_thread_executors:
# Re-use thread executor for running loop
executor = AsyncToSync.loop_thread_executors[loop]
elif self.deadlock_context and self.deadlock_context.get(False):
raise RuntimeError(
"Single thread executor already being used, would deadlock"
)
else:
# Otherwise, we run it in a fixed single thread
executor = self.single_thread_executor
if self.deadlock_context:
self.deadlock_context.set(True)
else:
# Use the passed in executor, or the loop's default if it is None
executor = self._executor
context = contextvars.copy_context()
child = functools.partial(self.func, *args, **kwargs)
func = context.run
args = (child,)
kwargs = {}
try:
# Run the code in the right thread
future = loop.run_in_executor(
executor,
functools.partial(
self.thread_handler,
loop,
self.get_current_task(),
sys.exc_info(),
func,
*args,
**kwargs,
),
)
ret = await asyncio.wait_for(future, timeout=None)
finally:
_restore_context(context)
if self.deadlock_context:
self.deadlock_context.set(False)
return ret
def __get__(self, parent, objtype):
"""
Include self for methods
"""
return functools.partial(self.__call__, parent)
def thread_handler(self, loop, source_task, exc_info, func, *args, **kwargs):
"""
Wraps the sync application with exception handling.
"""
# Set the threadlocal for AsyncToSync
self.threadlocal.main_event_loop = loop
self.threadlocal.main_event_loop_pid = os.getpid()
# Set the task mapping (used for the locals module)
current_thread = threading.current_thread()
if AsyncToSync.launch_map.get(source_task) == current_thread:
# Our parent task was launched from this same thread, so don't make
# a launch map entry - let it shortcut over us! (and stop infinite loops)
parent_set = False
else:
self.launch_map[current_thread] = source_task
parent_set = True
# Run the function
try:
# If we have an exception, run the function inside the except block
# after raising it so exc_info is correctly populated.
if exc_info[1]:
try:
raise exc_info[1]
except BaseException:
return func(*args, **kwargs)
else:
return func(*args, **kwargs)
finally:
# Only delete the launch_map parent if we set it, otherwise it is
# from someone else.
if parent_set:
del self.launch_map[current_thread]
@staticmethod
def get_current_task():
"""
Implementation of asyncio.current_task()
that returns None if there is no task.
"""
try:
return asyncio.current_task()
except RuntimeError:
return None
# Lowercase aliases (and decorator friendliness)
async_to_sync = AsyncToSync
@overload
def sync_to_async(
func: None = None,
thread_sensitive: bool = True,
executor: Optional["ThreadPoolExecutor"] = None,
) -> Callable[[Callable[..., Any]], SyncToAsync]:
...
@overload
def sync_to_async(
func: Callable[..., Any],
thread_sensitive: bool = True,
executor: Optional["ThreadPoolExecutor"] = None,
) -> SyncToAsync:
...
def sync_to_async(
func=None,
thread_sensitive=True,
executor=None,
):
if func is None:
return lambda f: SyncToAsync(
f,
thread_sensitive=thread_sensitive,
executor=executor,
)
return SyncToAsync(
func,
thread_sensitive=thread_sensitive,
executor=executor,
)

97
acer-env/lib/python3.10/site-packages/asgiref/testing.py Normal file
View File

@ -0,0 +1,97 @@
import asyncio
import time
from .compatibility import guarantee_single_callable
from .timeout import timeout as async_timeout
class ApplicationCommunicator:
"""
Runs an ASGI application in a test mode, allowing sending of
messages to it and retrieval of messages it sends.
"""
def __init__(self, application, scope):
self.application = guarantee_single_callable(application)
self.scope = scope
self.input_queue = asyncio.Queue()
self.output_queue = asyncio.Queue()
self.future = asyncio.ensure_future(
self.application(scope, self.input_queue.get, self.output_queue.put)
)
async def wait(self, timeout=1):
"""
Waits for the application to stop itself and returns any exceptions.
"""
try:
async with async_timeout(timeout):
try:
await self.future
self.future.result()
except asyncio.CancelledError:
pass
finally:
if not self.future.done():
self.future.cancel()
try:
await self.future
except asyncio.CancelledError:
pass
def stop(self, exceptions=True):
if not self.future.done():
self.future.cancel()
elif exceptions:
# Give a chance to raise any exceptions
self.future.result()
def __del__(self):
# Clean up on deletion
try:
self.stop(exceptions=False)
except RuntimeError:
# Event loop already stopped
pass
async def send_input(self, message):
"""
Sends a single message to the application
"""
# Give it the message
await self.input_queue.put(message)
async def receive_output(self, timeout=1):
"""
Receives a single message from the application, with optional timeout.
"""
# Make sure there's not an exception to raise from the task
if self.future.done():
self.future.result()
# Wait and receive the message
try:
async with async_timeout(timeout):
return await self.output_queue.get()
except asyncio.TimeoutError as e:
# See if we have another error to raise inside
if self.future.done():
self.future.result()
else:
self.future.cancel()
try:
await self.future
except asyncio.CancelledError:
pass
raise e
async def receive_nothing(self, timeout=0.1, interval=0.01):
"""
Checks that there is no message to receive in the given time.
"""
# `interval` has precedence over `timeout`
start = time.monotonic()
while time.monotonic() - start < timeout:
if not self.output_queue.empty():
return False
await asyncio.sleep(interval)
return self.output_queue.empty()

112
acer-env/lib/python3.10/site-packages/asgiref/timeout.py Normal file
View File

@ -0,0 +1,112 @@
# This code is originally sourced from the aio-libs project "async_timeout",
# under the Apache 2.0 license. You may see the original project at
# https://github.com/aio-libs/async-timeout
# It is vendored here to reduce chain-dependencies on this library, and
# modified slightly to remove some features we don't use.
import asyncio
from types import TracebackType
from typing import Any, Optional, Type
class timeout:
"""timeout context manager.
Useful in cases when you want to apply timeout logic around block
of code or in cases when asyncio.wait_for is not suitable. For example:
>>> with timeout(0.001):
... async with aiohttp.get('https://github.com') as r:
... await r.text()
timeout - value in seconds or None to disable timeout logic
loop - asyncio compatible event loop
"""
def __init__(
self,
timeout: Optional[float],
*,
loop: Optional[asyncio.AbstractEventLoop] = None,
) -> None:
self._timeout = timeout
if loop is None:
loop = asyncio.get_event_loop()
self._loop = loop
self._task = None # type: Optional[asyncio.Task[Any]]
self._cancelled = False
self._cancel_handler = None # type: Optional[asyncio.Handle]
self._cancel_at = None # type: Optional[float]
def __enter__(self) -> "timeout":
return self._do_enter()
def __exit__(
self,
exc_type: Type[BaseException],
exc_val: BaseException,
exc_tb: TracebackType,
) -> Optional[bool]:
self._do_exit(exc_type)
return None
async def __aenter__(self) -> "timeout":
return self._do_enter()
async def __aexit__(
self,
exc_type: Type[BaseException],
exc_val: BaseException,
exc_tb: TracebackType,
) -> None:
self._do_exit(exc_type)
@property
def expired(self) -> bool:
return self._cancelled
@property
def remaining(self) -> Optional[float]:
if self._cancel_at is not None:
return max(self._cancel_at - self._loop.time(), 0.0)
else:
return None
def _do_enter(self) -> "timeout":
# Support Tornado 5- without timeout
# Details: https://github.com/python/asyncio/issues/392
if self._timeout is None:
return self
self._task = asyncio.current_task(self._loop)
if self._task is None:
raise RuntimeError(
"Timeout context manager should be used " "inside a task"
)
if self._timeout <= 0:
self._loop.call_soon(self._cancel_task)
return self
self._cancel_at = self._loop.time() + self._timeout
self._cancel_handler = self._loop.call_at(self._cancel_at, self._cancel_task)
return self
def _do_exit(self, exc_type: Type[BaseException]) -> None:
if exc_type is asyncio.CancelledError and self._cancelled:
self._cancel_handler = None
self._task = None
raise asyncio.TimeoutError
if self._timeout is not None and self._cancel_handler is not None:
self._cancel_handler.cancel()
self._cancel_handler = None
self._task = None
return None
def _cancel_task(self) -> None:
if self._task is not None:
self._task.cancel()
self._cancelled = True

242
acer-env/lib/python3.10/site-packages/asgiref/typing.py Normal file
View File

@ -0,0 +1,242 @@
import sys
from typing import Awaitable, Callable, Dict, Iterable, Optional, Tuple, Type, Union
if sys.version_info >= (3, 8):
from typing import Literal, Protocol, TypedDict
else:
from typing_extensions import Literal, Protocol, TypedDict
__all__ = (
"ASGIVersions",
"HTTPScope",
"WebSocketScope",
"LifespanScope",
"WWWScope",
"Scope",
"HTTPRequestEvent",
"HTTPResponseStartEvent",
"HTTPResponseBodyEvent",
"HTTPServerPushEvent",
"HTTPDisconnectEvent",
"WebSocketConnectEvent",
"WebSocketAcceptEvent",
"WebSocketReceiveEvent",
"WebSocketSendEvent",
"WebSocketResponseStartEvent",
"WebSocketResponseBodyEvent",
"WebSocketDisconnectEvent",
"WebSocketCloseEvent",
"LifespanStartupEvent",
"LifespanShutdownEvent",
"LifespanStartupCompleteEvent",
"LifespanStartupFailedEvent",
"LifespanShutdownCompleteEvent",
"LifespanShutdownFailedEvent",
"ASGIReceiveEvent",
"ASGISendEvent",
"ASGIReceiveCallable",
"ASGISendCallable",
"ASGI2Protocol",
"ASGI2Application",
"ASGI3Application",
"ASGIApplication",
)
class ASGIVersions(TypedDict):
spec_version: str
version: Union[Literal["2.0"], Literal["3.0"]]
class HTTPScope(TypedDict):
type: Literal["http"]
asgi: ASGIVersions
http_version: str
method: str
scheme: str
path: str
raw_path: bytes
query_string: bytes
root_path: str
headers: Iterable[Tuple[bytes, bytes]]
client: Optional[Tuple[str, int]]
server: Optional[Tuple[str, Optional[int]]]
extensions: Optional[Dict[str, Dict[object, object]]]
class WebSocketScope(TypedDict):
type: Literal["websocket"]
asgi: ASGIVersions
http_version: str
scheme: str
path: str
raw_path: bytes
query_string: bytes
root_path: str
headers: Iterable[Tuple[bytes, bytes]]
client: Optional[Tuple[str, int]]
server: Optional[Tuple[str, Optional[int]]]
subprotocols: Iterable[str]
extensions: Optional[Dict[str, Dict[object, object]]]
class LifespanScope(TypedDict):
type: Literal["lifespan"]
asgi: ASGIVersions
WWWScope = Union[HTTPScope, WebSocketScope]
Scope = Union[HTTPScope, WebSocketScope, LifespanScope]
class HTTPRequestEvent(TypedDict):
type: Literal["http.request"]
body: bytes
more_body: bool
class HTTPResponseStartEvent(TypedDict):
type: Literal["http.response.start"]
status: int
headers: Iterable[Tuple[bytes, bytes]]
class HTTPResponseBodyEvent(TypedDict):
type: Literal["http.response.body"]
body: bytes
more_body: bool
class HTTPServerPushEvent(TypedDict):
type: Literal["http.response.push"]
path: str
headers: Iterable[Tuple[bytes, bytes]]
class HTTPDisconnectEvent(TypedDict):
type: Literal["http.disconnect"]
class WebSocketConnectEvent(TypedDict):
type: Literal["websocket.connect"]
class WebSocketAcceptEvent(TypedDict):
type: Literal["websocket.accept"]
subprotocol: Optional[str]
headers: Iterable[Tuple[bytes, bytes]]
class WebSocketReceiveEvent(TypedDict):
type: Literal["websocket.receive"]
bytes: Optional[bytes]
text: Optional[str]
class WebSocketSendEvent(TypedDict):
type: Literal["websocket.send"]
bytes: Optional[bytes]
text: Optional[str]
class WebSocketResponseStartEvent(TypedDict):
type: Literal["websocket.http.response.start"]
status: int
headers: Iterable[Tuple[bytes, bytes]]
class WebSocketResponseBodyEvent(TypedDict):
type: Literal["websocket.http.response.body"]
body: bytes
more_body: bool
class WebSocketDisconnectEvent(TypedDict):
type: Literal["websocket.disconnect"]
code: int
class WebSocketCloseEvent(TypedDict):
type: Literal["websocket.close"]
code: int
reason: Optional[str]
class LifespanStartupEvent(TypedDict):
type: Literal["lifespan.startup"]
class LifespanShutdownEvent(TypedDict):
type: Literal["lifespan.shutdown"]
class LifespanStartupCompleteEvent(TypedDict):
type: Literal["lifespan.startup.complete"]
class LifespanStartupFailedEvent(TypedDict):
type: Literal["lifespan.startup.failed"]
message: str
class LifespanShutdownCompleteEvent(TypedDict):
type: Literal["lifespan.shutdown.complete"]
class LifespanShutdownFailedEvent(TypedDict):
type: Literal["lifespan.shutdown.failed"]
message: str
ASGIReceiveEvent = Union[
HTTPRequestEvent,
HTTPDisconnectEvent,
WebSocketConnectEvent,
WebSocketReceiveEvent,
WebSocketDisconnectEvent,
LifespanStartupEvent,
LifespanShutdownEvent,
]
ASGISendEvent = Union[
HTTPResponseStartEvent,
HTTPResponseBodyEvent,
HTTPServerPushEvent,
HTTPDisconnectEvent,
WebSocketAcceptEvent,
WebSocketSendEvent,
WebSocketResponseStartEvent,
WebSocketResponseBodyEvent,
WebSocketCloseEvent,
LifespanStartupCompleteEvent,
LifespanStartupFailedEvent,
LifespanShutdownCompleteEvent,
LifespanShutdownFailedEvent,
]
ASGIReceiveCallable = Callable[[], Awaitable[ASGIReceiveEvent]]
ASGISendCallable = Callable[[ASGISendEvent], Awaitable[None]]
class ASGI2Protocol(Protocol):
def __init__(self, scope: Scope) -> None:
...
async def __call__(
self, receive: ASGIReceiveCallable, send: ASGISendCallable
) -> None:
...
ASGI2Application = Type[ASGI2Protocol]
ASGI3Application = Callable[
[
Scope,
ASGIReceiveCallable,
ASGISendCallable,
],
Awaitable[None],
]
ASGIApplication = Union[ASGI2Application, ASGI3Application]

162
acer-env/lib/python3.10/site-packages/asgiref/wsgi.py Normal file
View File

@ -0,0 +1,162 @@
from io import BytesIO
from tempfile import SpooledTemporaryFile
from asgiref.sync import AsyncToSync, sync_to_async
class WsgiToAsgi:
"""
Wraps a WSGI application to make it into an ASGI application.
"""
def __init__(self, wsgi_application):
self.wsgi_application = wsgi_application
async def __call__(self, scope, receive, send):
"""
ASGI application instantiation point.
We return a new WsgiToAsgiInstance here with the WSGI app
and the scope, ready to respond when it is __call__ed.
"""
await WsgiToAsgiInstance(self.wsgi_application)(scope, receive, send)
class WsgiToAsgiInstance:
"""
Per-socket instance of a wrapped WSGI application
"""
def __init__(self, wsgi_application):
self.wsgi_application = wsgi_application
self.response_started = False
self.response_content_length = None
async def __call__(self, scope, receive, send):
if scope["type"] != "http":
raise ValueError("WSGI wrapper received a non-HTTP scope")
self.scope = scope
with SpooledTemporaryFile(max_size=65536) as body:
# Alright, wait for the http.request messages
while True:
message = await receive()
if message["type"] != "http.request":
raise ValueError("WSGI wrapper received a non-HTTP-request message")
body.write(message.get("body", b""))
if not message.get("more_body"):
break
body.seek(0)
# Wrap send so it can be called from the subthread
self.sync_send = AsyncToSync(send)
# Call the WSGI app
await self.run_wsgi_app(body)
def build_environ(self, scope, body):
"""
Builds a scope and request body into a WSGI environ object.
"""
environ = {
"REQUEST_METHOD": scope["method"],
"SCRIPT_NAME": scope.get("root_path", "").encode("utf8").decode("latin1"),
"PATH_INFO": scope["path"].encode("utf8").decode("latin1"),
"QUERY_STRING": scope["query_string"].decode("ascii"),
"SERVER_PROTOCOL": "HTTP/%s" % scope["http_version"],
"wsgi.version": (1, 0),
"wsgi.url_scheme": scope.get("scheme", "http"),
"wsgi.input": body,
"wsgi.errors": BytesIO(),
"wsgi.multithread": True,
"wsgi.multiprocess": True,
"wsgi.run_once": False,
}
# Get server name and port - required in WSGI, not in ASGI
if "server" in scope:
environ["SERVER_NAME"] = scope["server"][0]
environ["SERVER_PORT"] = str(scope["server"][1])
else:
environ["SERVER_NAME"] = "localhost"
environ["SERVER_PORT"] = "80"
if "client" in scope:
environ["REMOTE_ADDR"] = scope["client"][0]
# Go through headers and make them into environ entries
for name, value in self.scope.get("headers", []):
name = name.decode("latin1")
if name == "content-length":
corrected_name = "CONTENT_LENGTH"
elif name == "content-type":
corrected_name = "CONTENT_TYPE"
else:
corrected_name = "HTTP_%s" % name.upper().replace("-", "_")
# HTTPbis say only ASCII chars are allowed in headers, but we latin1 just in case
value = value.decode("latin1")
if corrected_name in environ:
value = environ[corrected_name] + "," + value
environ[corrected_name] = value
return environ
def start_response(self, status, response_headers, exc_info=None):
"""
WSGI start_response callable.
"""
# Don't allow re-calling once response has begun
if self.response_started:
raise exc_info[1].with_traceback(exc_info[2])
# Don't allow re-calling without exc_info
if hasattr(self, "response_start") and exc_info is None:
raise ValueError(
"You cannot call start_response a second time without exc_info"
)
# Extract status code
status_code, _ = status.split(" ", 1)
status_code = int(status_code)
# Extract headers
headers = [
(name.lower().encode("ascii"), value.encode("ascii"))
for name, value in response_headers
]
# Extract content-length
self.response_content_length = None
for name, value in response_headers:
if name.lower() == "content-length":
self.response_content_length = int(value)
# Build and send response start message.
self.response_start = {
"type": "http.response.start",
"status": status_code,
"headers": headers,
}
@sync_to_async
def run_wsgi_app(self, body):
"""
Called in a subthread to run the WSGI app. We encapsulate like
this so that the start_response callable is called in the same thread.
"""
# Translate the scope and incoming request body into a WSGI environ
environ = self.build_environ(self.scope, body)
# Run the WSGI app
bytes_sent = 0
for output in self.wsgi_application(environ, self.start_response):
# If this is the first response, include the response headers
if not self.response_started:
self.response_started = True
self.sync_send(self.response_start)
# If the application supplies a Content-Length header
if self.response_content_length is not None:
# The server should not transmit more bytes to the client than the header allows
bytes_allowed = self.response_content_length - bytes_sent
if len(output) > bytes_allowed:
output = output[:bytes_allowed]
self.sync_send(
{"type": "http.response.body", "body": output, "more_body": True}
)
bytes_sent += len(output)
# The server should stop iterating over the response when enough data has been sent
if bytes_sent == self.response_content_length:
break
# Close connection
if not self.response_started:
self.response_started = True
self.sync_send(self.response_start)
self.sync_send({"type": "http.response.body"})

1
acer-env/lib/python3.10/site-packages/beautifulsoup4-4.11.1.dist-info/INSTALLER Normal file
View File

@ -0,0 +1 @@
pip

119
acer-env/lib/python3.10/site-packages/beautifulsoup4-4.11.1.dist-info/METADATA Normal file
View File

@ -0,0 +1,119 @@
Metadata-Version: 2.1
Name: beautifulsoup4
Version: 4.11.1
Summary: Screen-scraping library
Home-page: https://www.crummy.com/software/BeautifulSoup/bs4/
Author: Leonard Richardson
Author-email: leonardr@segfault.org
License: MIT
Download-URL: https://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 :: 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-Python: >=3.6.0
Description-Content-Type: text/markdown
Provides-Extra: lxml
Provides-Extra: html5lib
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")
'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](https://www.crummy.com/software/BeautifulSoup/bs4/doc/).
# Links
* [Homepage](https://www.crummy.com/software/BeautifulSoup/bs4/)
* [Documentation](https://www.crummy.com/software/BeautifulSoup/bs4/doc/)
* [Discussion group](https://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
Beautiful Soup's support for Python 2 was discontinued on December 31,
2020: one year after the sunset date for Python 2 itself. From this
point onward, new Beautiful Soup development will exclusively target
Python 3. The final release of Beautiful Soup 4 to support Python 2
was 4.9.3.
# 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 using Pytest:
```
$ pytest
```

54
acer-env/lib/python3.10/site-packages/beautifulsoup4-4.11.1.dist-info/RECORD Normal file
View File

@ -0,0 +1,54 @@
beautifulsoup4-4.11.1.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
beautifulsoup4-4.11.1.dist-info/METADATA,sha256=zefuevXradYVap7gKfvpSwLzvs8FSBONKfY8j5HIj-k,3525
beautifulsoup4-4.11.1.dist-info/RECORD,,
beautifulsoup4-4.11.1.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
beautifulsoup4-4.11.1.dist-info/WHEEL,sha256=NzFAKnL7g-U64xnS1s5e3mJnxKpOTeOtlXdFwS9yNXI,92
beautifulsoup4-4.11.1.dist-info/top_level.txt,sha256=gpUVJcTwW3q7-QGp6tAEomZsskknmgSqVe6xn1C0jJI,26
bs4/__init__.py,sha256=v5VuQqegAzN3bo4kjs6fT0391zvKQGhvBlV841aJ86A,32832
bs4/__pycache__/__init__.cpython-310.pyc,,
bs4/__pycache__/dammit.cpython-310.pyc,,
bs4/__pycache__/diagnose.cpython-310.pyc,,
bs4/__pycache__/element.cpython-310.pyc,,
bs4/__pycache__/formatter.cpython-310.pyc,,
bs4/builder/__init__.py,sha256=Ny7NmZu3XDndp_elCrz2W8K9OUjrAjHQuYianJR6RDM,24378
bs4/builder/__pycache__/__init__.cpython-310.pyc,,
bs4/builder/__pycache__/_html5lib.cpython-310.pyc,,
bs4/builder/__pycache__/_htmlparser.cpython-310.pyc,,
bs4/builder/__pycache__/_lxml.cpython-310.pyc,,
bs4/builder/_html5lib.py,sha256=YFOKZf3E22AEp_V2k49U5LmF26bpSZixZrZGSwM_iCU,18946
bs4/builder/_htmlparser.py,sha256=6RYsAXWb_ppMZGB-7lpEmJQ73tpzSu_CJ5QPaFcJu-Y,19169
bs4/builder/_lxml.py,sha256=ik6BFGnxAzV2-21S_Wc-7ZeA174muSA_ZhmpnAe3g0E,14904
bs4/dammit.py,sha256=G0cQfsEqfwJ-FIQMkXgCJwSHMn7t9vPepCrud6fZEKk,41158
bs4/diagnose.py,sha256=MRbN2bJSpa8VFt8HemqP8BK9hL5ronCxZmrfGRZYwBg,7911
bs4/element.py,sha256=jjP-cIA3oWJrAhky61wayot92SQFKzJMEE8My6uTPDM,86753
bs4/formatter.py,sha256=f5UBtvW9twrrQeLjBeLaKp4ntZpUDmUBY8jF3BiLraM,7206
bs4/tests/__init__.py,sha256=yFvfhDv5vOeho6NEZcI0AIpmuEe9bvC7TsqNp3hDGxQ,49185
bs4/tests/__pycache__/__init__.cpython-310.pyc,,
bs4/tests/__pycache__/test_builder.cpython-310.pyc,,
bs4/tests/__pycache__/test_builder_registry.cpython-310.pyc,,
bs4/tests/__pycache__/test_dammit.cpython-310.pyc,,
bs4/tests/__pycache__/test_docs.cpython-310.pyc,,
bs4/tests/__pycache__/test_element.cpython-310.pyc,,
bs4/tests/__pycache__/test_formatter.cpython-310.pyc,,
bs4/tests/__pycache__/test_html5lib.cpython-310.pyc,,
bs4/tests/__pycache__/test_htmlparser.cpython-310.pyc,,
bs4/tests/__pycache__/test_lxml.cpython-310.pyc,,
bs4/tests/__pycache__/test_navigablestring.cpython-310.pyc,,
bs4/tests/__pycache__/test_pageelement.cpython-310.pyc,,
bs4/tests/__pycache__/test_soup.cpython-310.pyc,,
bs4/tests/__pycache__/test_tag.cpython-310.pyc,,
bs4/tests/__pycache__/test_tree.cpython-310.pyc,,
bs4/tests/test_builder.py,sha256=nc2JE5EMrEf-p24qhf2R8qAV5PpFiOuNpYCmtmCjlTI,1115
bs4/tests/test_builder_registry.py,sha256=_Vh2CyYzv4BKoJdCa7s4lsBLUQptskfgiSn3U3810CQ,5068
bs4/tests/test_dammit.py,sha256=lS3EWCYCtxVE4fC_J2eTcXiChhuaL4Vcbo94B5geIL4,15680
bs4/tests/test_docs.py,sha256=xoAxnUfoQ7aRqGImwW_9BJDU8WNMZHIuvWqVepvWXt8,1127
bs4/tests/test_element.py,sha256=92oRSRoGk8gIXAbAGHErKzocx2MK32TqcQdUJ-dGQMo,2377
bs4/tests/test_formatter.py,sha256=0qV9H7mMDBcnFFH-dwNCrSm2zNi_40WMB2GMcV35PoY,4128
bs4/tests/test_html5lib.py,sha256=X6r13jfJ-OmG6SL_hyfFNXWs7sEEq_1TmCzCJclxvbA,8246
bs4/tests/test_htmlparser.py,sha256=BFCspIdhkr8Bss-kHufeNcwa_lvJpVWKgJskPoZgZ7E,5532
bs4/tests/test_lxml.py,sha256=deaf1YOrR8I0T5yZAV4TDxcAXHzVhdlnsSajGpBoxs0,7376
bs4/tests/test_navigablestring.py,sha256=RGSgziNf7cZnYdEPsoqL1B2I68TUJp1JmEQVxbh_ryA,5081
bs4/tests/test_pageelement.py,sha256=fpOU3W5IAz92b0A2VxWKkI5pApObMB17cNzXNF85FfA,27792
bs4/tests/test_soup.py,sha256=CUnK-rDccIlKMLBP4AweCqRDbPt3Lqzln_BpnBgKm4M,17810
bs4/tests/test_tag.py,sha256=f19uie7QehvgvhIqNWfjDRR4TKa-ftm_RRoo6LXZyqk,9016
bs4/tests/test_tree.py,sha256=y9Qvs8nnYj6RnGRSxtoYQQwSja-DlbtukCVs0neVwyU,47557

0
acer-env/lib/python3.10/site-packages/beautifulsoup4-4.11.1.dist-info/REQUESTED Normal file
View File

5
acer-env/lib/python3.10/site-packages/beautifulsoup4-4.11.1.dist-info/WHEEL Normal file
View File

@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.31.1)
Root-Is-Purelib: true
Tag: py3-none-any

3
acer-env/lib/python3.10/site-packages/beautifulsoup4-4.11.1.dist-info/top_level.txt Normal file
View File

@ -0,0 +1,3 @@
bs4
bs4/builder
bs4/tests

812
acer-env/lib/python3.10/site-packages/bs4/__init__.py Normal file
View File

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

BIN
acer-env/lib/python3.10/site-packages/bs4/__pycache__/__init__.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/__pycache__/dammit.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/__pycache__/diagnose.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/__pycache__/element.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/__pycache__/formatter.cpython-310.pyc Normal file
View File

Binary file not shown.

631
acer-env/lib/python3.10/site-packages/bs4/builder/__init__.py Normal file
View File

@ -0,0 +1,631 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
from collections import defaultdict
import itertools
import re
import warnings
import sys
from bs4.element import (
CharsetMetaAttributeValue,
ContentMetaAttributeValue,
RubyParenthesisString,
RubyTextString,
Stylesheet,
Script,
TemplateString,
nonwhitespace_re
)
__all__ = [
'HTMLTreeBuilder',
'SAXTreeBuilder',
'TreeBuilder',
'TreeBuilderRegistry',
]
# Some useful features for a TreeBuilder to have.
FAST = 'fast'
PERMISSIVE = 'permissive'
STRICT = 'strict'
XML = 'xml'
HTML = 'html'
HTML_5 = 'html5'
class XMLParsedAsHTMLWarning(UserWarning):
"""The warning issued when an HTML parser is used to parse
XML that is not XHTML.
"""
MESSAGE = """It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor."""
class TreeBuilderRegistry(object):
"""A way of looking up TreeBuilder subclasses by their name or by desired
features.
"""
def __init__(self):
self.builders_for_feature = defaultdict(list)
self.builders = []
def register(self, treebuilder_class):
"""Register a treebuilder based on its advertised features.
:param treebuilder_class: A subclass of Treebuilder. its .features
attribute should list its features.
"""
for feature in treebuilder_class.features:
self.builders_for_feature[feature].insert(0, treebuilder_class)
self.builders.insert(0, treebuilder_class)
def lookup(self, *features):
"""Look up a TreeBuilder subclass with the desired features.
:param features: A list of features to look for. If none are
provided, the most recently registered TreeBuilder subclass
will be used.
:return: A TreeBuilder subclass, or None if there's no
registered subclass with all the requested features.
"""
if len(self.builders) == 0:
# There are no builders at all.
return None
if len(features) == 0:
# They didn't ask for any features. Give them the most
# recently registered builder.
return self.builders[0]
# Go down the list of features in order, and eliminate any builders
# that don't match every feature.
features = list(features)
features.reverse()
candidates = None
candidate_set = None
while len(features) > 0:
feature = features.pop()
we_have_the_feature = self.builders_for_feature.get(feature, [])
if len(we_have_the_feature) > 0:
if candidates is None:
candidates = we_have_the_feature
candidate_set = set(candidates)
else:
# Eliminate any candidates that don't have this feature.
candidate_set = candidate_set.intersection(
set(we_have_the_feature))
# The only valid candidates are the ones in candidate_set.
# Go through the original list of candidates and pick the first one
# that's in candidate_set.
if candidate_set is None:
return None
for candidate in candidates:
if candidate in candidate_set:
return candidate
return None
# The BeautifulSoup class will take feature lists from developers and use them
# to look up builders in this registry.
builder_registry = TreeBuilderRegistry()
class TreeBuilder(object):
"""Turn a textual document into a Beautiful Soup object tree."""
NAME = "[Unknown tree builder]"
ALTERNATE_NAMES = []
features = []
is_xml = False
picklable = False
empty_element_tags = None # A tag will be considered an empty-element
# tag when and only when it has no contents.
# A value for these tag/attribute combinations is a space- or
# comma-separated list of CDATA, rather than a single CDATA.
DEFAULT_CDATA_LIST_ATTRIBUTES = {}
# Whitespace should be preserved inside these tags.
DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
# The textual contents of tags with these names should be
# instantiated with some class other than NavigableString.
DEFAULT_STRING_CONTAINERS = {}
USE_DEFAULT = object()
# Most parsers don't keep track of line numbers.
TRACKS_LINE_NUMBERS = False
def __init__(self, multi_valued_attributes=USE_DEFAULT,
preserve_whitespace_tags=USE_DEFAULT,
store_line_numbers=USE_DEFAULT,
string_containers=USE_DEFAULT,
):
"""Constructor.
:param multi_valued_attributes: If this is set to None, the
TreeBuilder will not turn any values for attributes like
'class' into lists. Setting this to a dictionary will
customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES
for an example.
Internally, these are called "CDATA list attributes", but that
probably doesn't make sense to an end-user, so the argument name
is `multi_valued_attributes`.
:param preserve_whitespace_tags: A list of tags to treat
the way <pre> tags are treated in HTML. Tags in this list
are immune from pretty-printing; their contents will always be
output as-is.
:param string_containers: A dictionary mapping tag names to
the classes that should be instantiated to contain the textual
contents of those tags. The default is to use NavigableString
for every tag, no matter what the name. You can override the
default by changing DEFAULT_STRING_CONTAINERS.
:param store_line_numbers: If the parser keeps track of the
line numbers and positions of the original markup, that
information will, by default, be stored in each corresponding
`Tag` object. You can turn this off by passing
store_line_numbers=False. If the parser you're using doesn't
keep track of this information, then setting store_line_numbers=True
will do nothing.
"""
self.soup = None
if multi_valued_attributes is self.USE_DEFAULT:
multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
self.cdata_list_attributes = multi_valued_attributes
if preserve_whitespace_tags is self.USE_DEFAULT:
preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
self.preserve_whitespace_tags = preserve_whitespace_tags
if store_line_numbers == self.USE_DEFAULT:
store_line_numbers = self.TRACKS_LINE_NUMBERS
self.store_line_numbers = store_line_numbers
if string_containers == self.USE_DEFAULT:
string_containers = self.DEFAULT_STRING_CONTAINERS
self.string_containers = string_containers
def initialize_soup(self, soup):
"""The BeautifulSoup object has been initialized and is now
being associated with the TreeBuilder.
:param soup: A BeautifulSoup object.
"""
self.soup = soup
def reset(self):
"""Do any work necessary to reset the underlying parser
for a new document.
By default, this does nothing.
"""
pass
def can_be_empty_element(self, tag_name):
"""Might a tag with this name be an empty-element tag?
The final markup may or may not actually present this tag as
self-closing.
For instance: an HTMLBuilder does not consider a <p> tag to be
an empty-element tag (it's not in
HTMLBuilder.empty_element_tags). This means an empty <p> tag
will be presented as "<p></p>", not "<p/>" or "<p>".
The default implementation has no opinion about which tags are
empty-element tags, so a tag will be presented as an
empty-element tag if and only if it has no children.
"<foo></foo>" will become "<foo/>", and "<foo>bar</foo>" will
be left alone.
:param tag_name: The name of a markup tag.
"""
if self.empty_element_tags is None:
return True
return tag_name in self.empty_element_tags
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
This method is not implemented in TreeBuilder; it must be
implemented in subclasses.
:return: None.
"""
raise NotImplementedError()
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding. NOTE: This argument is not used by the
calling code and can probably be removed.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
By default, the only strategy is to parse the markup
as-is. See `LXMLTreeBuilderForXML` and
`HTMLParserTreeBuilder` for implementations that take into
account the quirks of particular parsers.
"""
yield markup, None, None, False
def test_fragment_to_document(self, fragment):
"""Wrap an HTML fragment to make it look like a document.
Different parsers do this differently. For instance, lxml
introduces an empty <head> tag, and html5lib
doesn't. Abstracting this away lets us write simple tests
which run HTML fragments through the parser and compare the
results against other HTML fragments.
This method should not be used outside of tests.
:param fragment: A string -- fragment of HTML.
:return: A string -- a full HTML document.
"""
return fragment
def set_up_substitutions(self, tag):
"""Set up any substitutions that will need to be performed on
a `Tag` when it's output as a string.
By default, this does nothing. See `HTMLTreeBuilder` for a
case where this is used.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
return False
def _replace_cdata_list_attribute_values(self, tag_name, attrs):
"""When an attribute value is associated with a tag that can
have multiple values for that attribute, convert the string
value to a list of strings.
Basically, replaces class="foo bar" with class=["foo", "bar"]
NOTE: This method modifies its input in place.
:param tag_name: The name of a tag.
:param attrs: A dictionary containing the tag's attributes.
Any appropriate attribute values will be modified in place.
"""
if not attrs:
return attrs
if self.cdata_list_attributes:
universal = self.cdata_list_attributes.get('*', [])
tag_specific = self.cdata_list_attributes.get(
tag_name.lower(), None)
for attr in list(attrs.keys()):
if attr in universal or (tag_specific and attr in tag_specific):
# We have a "class"-type attribute whose string
# value is a whitespace-separated list of
# values. Split it into a list.
value = attrs[attr]
if isinstance(value, str):
values = nonwhitespace_re.findall(value)
else:
# html5lib sometimes calls setAttributes twice
# for the same tag when rearranging the parse
# tree. On the second call the attribute value
# here is already a list. If this happens,
# leave the value alone rather than trying to
# split it again.
values = value
attrs[attr] = values
return attrs
class SAXTreeBuilder(TreeBuilder):
"""A Beautiful Soup treebuilder that listens for SAX events.
This is not currently used for anything, but it demonstrates
how a simple TreeBuilder would work.
"""
def feed(self, markup):
raise NotImplementedError()
def close(self):
pass
def startElement(self, name, attrs):
attrs = dict((key[1], value) for key, value in list(attrs.items()))
#print("Start %s, %r" % (name, attrs))
self.soup.handle_starttag(name, attrs)
def endElement(self, name):
#print("End %s" % name)
self.soup.handle_endtag(name)
def startElementNS(self, nsTuple, nodeName, attrs):
# Throw away (ns, nodeName) for now.
self.startElement(nodeName, attrs)
def endElementNS(self, nsTuple, nodeName):
# Throw away (ns, nodeName) for now.
self.endElement(nodeName)
#handler.endElementNS((ns, node.nodeName), node.nodeName)
def startPrefixMapping(self, prefix, nodeValue):
# Ignore the prefix for now.
pass
def endPrefixMapping(self, prefix):
# Ignore the prefix for now.
# handler.endPrefixMapping(prefix)
pass
def characters(self, content):
self.soup.handle_data(content)
def startDocument(self):
pass
def endDocument(self):
pass
class HTMLTreeBuilder(TreeBuilder):
"""This TreeBuilder knows facts about HTML.
Such as which tags are empty-element tags.
"""
empty_element_tags = set([
# These are from HTML5.
'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
# These are from earlier versions of HTML and are removed in HTML5.
'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
])
# The HTML standard defines these as block-level elements. Beautiful
# Soup does not treat these elements differently from other elements,
# but it may do so eventually, and this information is available if
# you need to use it.
block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
# These HTML tags need special treatment so they can be
# represented by a string class other than NavigableString.
#
# For some of these tags, it's because the HTML standard defines
# an unusual content model for them. I made this list by going
# through the HTML spec
# (https://html.spec.whatwg.org/#metadata-content) and looking for
# "metadata content" elements that can contain strings.
#
# The Ruby tags (<rt> and <rp>) are here despite being normal
# "phrasing content" tags, because the content they contain is
# qualitatively different from other text in the document, and it
# can be useful to be able to distinguish it.
#
# TODO: Arguably <noscript> could go here but it seems
# qualitatively different from the other tags.
DEFAULT_STRING_CONTAINERS = {
'rt' : RubyTextString,
'rp' : RubyParenthesisString,
'style': Stylesheet,
'script': Script,
'template': TemplateString,
}
# The HTML standard defines these attributes as containing a
# space-separated list of values, not a single value. That is,
# class="foo bar" means that the 'class' attribute has two values,
# 'foo' and 'bar', not the single value 'foo bar'. When we
# encounter one of these attributes, we will parse its value into
# a list of values if possible. Upon output, the list will be
# converted back into a string.
DEFAULT_CDATA_LIST_ATTRIBUTES = {
"*" : ['class', 'accesskey', 'dropzone'],
"a" : ['rel', 'rev'],
"link" : ['rel', 'rev'],
"td" : ["headers"],
"th" : ["headers"],
"td" : ["headers"],
"form" : ["accept-charset"],
"object" : ["archive"],
# These are HTML5 specific, as are *.accesskey and *.dropzone above.
"area" : ["rel"],
"icon" : ["sizes"],
"iframe" : ["sandbox"],
"output" : ["for"],
}
DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
def set_up_substitutions(self, tag):
"""Replace the declared encoding in a <meta> tag with a placeholder,
to be substituted when the tag is output to a string.
An HTML document may come in to Beautiful Soup as one
encoding, but exit in a different encoding, and the <meta> tag
needs to be changed to reflect this.
:param tag: A `Tag`
:return: Whether or not a substitution was performed.
"""
# We are only interested in <meta> tags
if tag.name != 'meta':
return False
http_equiv = tag.get('http-equiv')
content = tag.get('content')
charset = tag.get('charset')
# We are interested in <meta> tags that say what encoding the
# document was originally in. This means HTML 5-style <meta>
# tags that provide the "charset" attribute. It also means
# HTML 4-style <meta> tags that provide the "content"
# attribute and have "http-equiv" set to "content-type".
#
# In both cases we will replace the value of the appropriate
# attribute with a standin object that can take on any
# encoding.
meta_encoding = None
if charset is not None:
# HTML 5 style:
# <meta charset="utf8">
meta_encoding = charset
tag['charset'] = CharsetMetaAttributeValue(charset)
elif (content is not None and http_equiv is not None
and http_equiv.lower() == 'content-type'):
# HTML 4 style:
# <meta http-equiv="content-type" content="text/html; charset=utf8">
tag['content'] = ContentMetaAttributeValue(content)
return (meta_encoding is not None)
class DetectsXMLParsedAsHTML(object):
"""A mixin class for any class (a TreeBuilder, or some class used by a
TreeBuilder) that's in a position to detect whether an XML
document is being incorrectly parsed as HTML, and issue an
appropriate warning.
This requires being able to observe an incoming processing
instruction that might be an XML declaration, and also able to
observe tags as they're opened. If you can't do that for a given
TreeBuilder, there's a less reliable implementation based on
examining the raw markup.
"""
# Regular expression for seeing if markup has an <html> tag.
LOOKS_LIKE_HTML = re.compile("<[^ +]html", re.I)
LOOKS_LIKE_HTML_B = re.compile(b"<[^ +]html", re.I)
XML_PREFIX = '<?xml'
XML_PREFIX_B = b'<?xml'
@classmethod
def warn_if_markup_looks_like_xml(cls, markup):
"""Perform a check on some markup to see if it looks like XML
that's not XHTML. If so, issue a warning.
This is much less reliable than doing the check while parsing,
but some of the tree builders can't do that.
:return: True if the markup looks like non-XHTML XML, False
otherwise.
"""
if isinstance(markup, bytes):
prefix = cls.XML_PREFIX_B
looks_like_html = cls.LOOKS_LIKE_HTML_B
else:
prefix = cls.XML_PREFIX
looks_like_html = cls.LOOKS_LIKE_HTML
if (markup is not None
and markup.startswith(prefix)
and not looks_like_html.search(markup[:500])
):
cls._warn()
return True
return False
@classmethod
def _warn(cls):
"""Issue a warning about XML being parsed as HTML."""
warnings.warn(
XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning
)
def _initialize_xml_detector(self):
"""Call this method before parsing a document."""
self._first_processing_instruction = None
self._root_tag = None
def _document_might_be_xml(self, processing_instruction):
"""Call this method when encountering an XML declaration, or a
"processing instruction" that might be an XML declaration.
"""
if (self._first_processing_instruction is not None
or self._root_tag is not None):
# The document has already started. Don't bother checking
# anymore.
return
self._first_processing_instruction = processing_instruction
# We won't know until we encounter the first tag whether or
# not this is actually a problem.
def _root_tag_encountered(self, name):
"""Call this when you encounter the document's root tag.
This is where we actually check whether an XML document is
being incorrectly parsed as HTML, and issue the warning.
"""
if self._root_tag is not None:
# This method was incorrectly called multiple times. Do
# nothing.
return
self._root_tag = name
if (name != 'html' and self._first_processing_instruction is not None
and self._first_processing_instruction.lower().startswith('xml ')):
# We encountered an XML declaration and then a tag other
# than 'html'. This is a reliable indicator that a
# non-XHTML document is being parsed as XML.
self._warn()
def register_treebuilders_from(module):
"""Copy TreeBuilders from the given module into this module."""
this_module = sys.modules[__name__]
for name in module.__all__:
obj = getattr(module, name)
if issubclass(obj, TreeBuilder):
setattr(this_module, name, obj)
this_module.__all__.append(name)
# Register the builder while we're at it.
this_module.builder_registry.register(obj)
class ParserRejectedMarkup(Exception):
"""An Exception to be raised when the underlying parser simply
refuses to parse the given markup.
"""
def __init__(self, message_or_exception):
"""Explain why the parser rejected the given markup, either
with a textual explanation or another exception.
"""
if isinstance(message_or_exception, Exception):
e = message_or_exception
message_or_exception = "%s: %s" % (e.__class__.__name__, str(e))
super(ParserRejectedMarkup, self).__init__(message_or_exception)
# Builders are registered in reverse order of priority, so that custom
# builder registrations will take precedence. In general, we want lxml
# to take precedence over html5lib, because it's faster. And we only
# want to use HTMLParser as a last resort.
from . import _htmlparser
register_treebuilders_from(_htmlparser)
try:
from . import _html5lib
register_treebuilders_from(_html5lib)
except ImportError:
# They don't have html5lib installed.
pass
try:
from . import _lxml
register_treebuilders_from(_lxml)
except ImportError:
# They don't have lxml installed.
pass

BIN
acer-env/lib/python3.10/site-packages/bs4/builder/__pycache__/__init__.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/builder/__pycache__/_html5lib.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/builder/__pycache__/_htmlparser.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/builder/__pycache__/_lxml.cpython-310.pyc Normal file
View File

Binary file not shown.

473
acer-env/lib/python3.10/site-packages/bs4/builder/_html5lib.py Normal file
View File

@ -0,0 +1,473 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTML5TreeBuilder',
]
import warnings
import re
from bs4.builder import (
DetectsXMLParsedAsHTML,
PERMISSIVE,
HTML,
HTML_5,
HTMLTreeBuilder,
)
from bs4.element import (
NamespacedAttribute,
nonwhitespace_re,
)
import html5lib
from html5lib.constants import (
namespaces,
prefixes,
)
from bs4.element import (
Comment,
Doctype,
NavigableString,
Tag,
)
try:
# Pre-0.99999999
from html5lib.treebuilders import _base as treebuilder_base
new_html5lib = False
except ImportError as e:
# 0.99999999 and up
from html5lib.treebuilders import base as treebuilder_base
new_html5lib = True
class HTML5TreeBuilder(HTMLTreeBuilder):
"""Use html5lib to build a tree.
Note that this TreeBuilder does not support some features common
to HTML TreeBuilders. Some of these features could theoretically
be implemented, but at the very least it's quite difficult,
because html5lib moves the parse tree around as it's being built.
* This TreeBuilder doesn't use different subclasses of NavigableString
based on the name of the tag in which the string was found.
* You can't use a SoupStrainer to parse only part of a document.
"""
NAME = "html5lib"
features = [NAME, PERMISSIVE, HTML_5, HTML]
# html5lib can tell us which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def prepare_markup(self, markup, user_specified_encoding,
document_declared_encoding=None, exclude_encodings=None):
# Store the user-specified encoding for use later on.
self.user_specified_encoding = user_specified_encoding
# document_declared_encoding and exclude_encodings aren't used
# ATM because the html5lib TreeBuilder doesn't use
# UnicodeDammit.
if exclude_encodings:
warnings.warn("You provided a value for exclude_encoding, but the html5lib tree builder doesn't support exclude_encoding.")
# html5lib only parses HTML, so if it's given XML that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
yield (markup, None, None, False)
# These methods are defined by Beautiful Soup.
def feed(self, markup):
if self.soup.parse_only is not None:
warnings.warn("You provided a value for parse_only, but the html5lib tree builder doesn't support parse_only. The entire document will be parsed.")
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
self.underlying_builder.parser = parser
extra_kwargs = dict()
if not isinstance(markup, str):
if new_html5lib:
extra_kwargs['override_encoding'] = self.user_specified_encoding
else:
extra_kwargs['encoding'] = self.user_specified_encoding
doc = parser.parse(markup, **extra_kwargs)
# Set the character encoding detected by the tokenizer.
if isinstance(markup, str):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
else:
original_encoding = parser.tokenizer.stream.charEncoding[0]
if not isinstance(original_encoding, str):
# In 0.99999999 and up, the encoding is an html5lib
# Encoding object. We want to use a string for compatibility
# with other tree builders.
original_encoding = original_encoding.name
doc.original_encoding = original_encoding
self.underlying_builder.parser = None
def create_treebuilder(self, namespaceHTMLElements):
self.underlying_builder = TreeBuilderForHtml5lib(
namespaceHTMLElements, self.soup,
store_line_numbers=self.store_line_numbers
)
return self.underlying_builder
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
def __init__(self, namespaceHTMLElements, soup=None,
store_line_numbers=True, **kwargs):
if soup:
self.soup = soup
else:
from bs4 import BeautifulSoup
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup(
"", "html.parser", store_line_numbers=store_line_numbers,
**kwargs
)
# TODO: What are **kwargs exactly? Should they be passed in
# here in addition to/instead of being passed to the BeautifulSoup
# constructor?
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
# This will be set later to an html5lib.html5parser.HTMLParser
# object, which we can use to track the current line number.
self.parser = None
self.store_line_numbers = store_line_numbers
def documentClass(self):
self.soup.reset()
return Element(self.soup, self.soup, None)
def insertDoctype(self, token):
name = token["name"]
publicId = token["publicId"]
systemId = token["systemId"]
doctype = Doctype.for_name_and_ids(name, publicId, systemId)
self.soup.object_was_parsed(doctype)
def elementClass(self, name, namespace):
kwargs = {}
if self.parser and self.store_line_numbers:
# This represents the point immediately after the end of the
# tag. We don't know when the tag started, but we do know
# where it ended -- the character just before this one.
sourceline, sourcepos = self.parser.tokenizer.stream.position()
kwargs['sourceline'] = sourceline
kwargs['sourcepos'] = sourcepos-1
tag = self.soup.new_tag(name, namespace, **kwargs)
return Element(tag, self.soup, namespace)
def commentClass(self, data):
return TextNode(Comment(data), self.soup)
def fragmentClass(self):
from bs4 import BeautifulSoup
# TODO: Why is the parser 'html.parser' here? To avoid an
# infinite loop?
self.soup = BeautifulSoup("", "html.parser")
self.soup.name = "[document_fragment]"
return Element(self.soup, self.soup, None)
def appendChild(self, node):
# XXX This code is not covered by the BS4 tests.
self.soup.append(node.element)
def getDocument(self):
return self.soup
def getFragment(self):
return treebuilder_base.TreeBuilder.getFragment(self).element
def testSerializer(self, element):
from bs4 import BeautifulSoup
rv = []
doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
def serializeElement(element, indent=0):
if isinstance(element, BeautifulSoup):
pass
if isinstance(element, Doctype):
m = doctype_re.match(element)
if m:
name = m.group(1)
if m.lastindex > 1:
publicId = m.group(2) or ""
systemId = m.group(3) or m.group(4) or ""
rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
(' ' * indent, name, publicId, systemId))
else:
rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, name))
else:
rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
elif isinstance(element, Comment):
rv.append("|%s<!-- %s -->" % (' ' * indent, element))
elif isinstance(element, NavigableString):
rv.append("|%s\"%s\"" % (' ' * indent, element))
else:
if element.namespace:
name = "%s %s" % (prefixes[element.namespace],
element.name)
else:
name = element.name
rv.append("|%s<%s>" % (' ' * indent, name))
if element.attrs:
attributes = []
for name, value in list(element.attrs.items()):
if isinstance(name, NamespacedAttribute):
name = "%s %s" % (prefixes[name.namespace], name.name)
if isinstance(value, list):
value = " ".join(value)
attributes.append((name, value))
for name, value in sorted(attributes):
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
indent += 2
for child in element.children:
serializeElement(child, indent)
serializeElement(element, 0)
return "\n".join(rv)
class AttrList(object):
def __init__(self, element):
self.element = element
self.attrs = dict(self.element.attrs)
def __iter__(self):
return list(self.attrs.items()).__iter__()
def __setitem__(self, name, value):
# If this attribute is a multi-valued attribute for this element,
# turn its value into a list.
list_attr = self.element.cdata_list_attributes or {}
if (name in list_attr.get('*')
or (self.element.name in list_attr
and name in list_attr[self.element.name])):
# A node that is being cloned may have already undergone
# this procedure.
if not isinstance(value, list):
value = nonwhitespace_re.findall(value)
self.element[name] = value
def items(self):
return list(self.attrs.items())
def keys(self):
return list(self.attrs.keys())
def __len__(self):
return len(self.attrs)
def __getitem__(self, name):
return self.attrs[name]
def __contains__(self, name):
return name in list(self.attrs.keys())
class Element(treebuilder_base.Node):
def __init__(self, element, soup, namespace):
treebuilder_base.Node.__init__(self, element.name)
self.element = element
self.soup = soup
self.namespace = namespace
def appendChild(self, node):
string_child = child = None
if isinstance(node, str):
# Some other piece of code decided to pass in a string
# instead of creating a TextElement object to contain the
# string.
string_child = child = node
elif isinstance(node, Tag):
# Some other piece of code decided to pass in a Tag
# instead of creating an Element object to contain the
# Tag.
child = node
elif node.element.__class__ == NavigableString:
string_child = child = node.element
node.parent = self
else:
child = node.element
node.parent = self
if not isinstance(child, str) and child.parent is not None:
node.element.extract()
if (string_child is not None and self.element.contents
and self.element.contents[-1].__class__ == NavigableString):
# We are appending a string onto another string.
# TODO This has O(n^2) performance, for input like
# "a</a>a</a>a</a>..."
old_element = self.element.contents[-1]
new_element = self.soup.new_string(old_element + string_child)
old_element.replace_with(new_element)
self.soup._most_recent_element = new_element
else:
if isinstance(node, str):
# Create a brand new NavigableString from this string.
child = self.soup.new_string(node)
# Tell Beautiful Soup to act as if it parsed this element
# immediately after the parent's last descendant. (Or
# immediately after the parent, if it has no children.)
if self.element.contents:
most_recent_element = self.element._last_descendant(False)
elif self.element.next_element is not None:
# Something from further ahead in the parse tree is
# being inserted into this earlier element. This is
# very annoying because it means an expensive search
# for the last element in the tree.
most_recent_element = self.soup._last_descendant()
else:
most_recent_element = self.element
self.soup.object_was_parsed(
child, parent=self.element,
most_recent_element=most_recent_element)
def getAttributes(self):
if isinstance(self.element, Comment):
return {}
return AttrList(self.element)
def setAttributes(self, attributes):
if attributes is not None and len(attributes) > 0:
converted_attributes = []
for name, value in list(attributes.items()):
if isinstance(name, tuple):
new_name = NamespacedAttribute(*name)
del attributes[name]
attributes[new_name] = value
self.soup.builder._replace_cdata_list_attribute_values(
self.name, attributes)
for name, value in list(attributes.items()):
self.element[name] = value
# The attributes may contain variables that need substitution.
# Call set_up_substitutions manually.
#
# The Tag constructor called this method when the Tag was created,
# but we just set/changed the attributes, so call it again.
self.soup.builder.set_up_substitutions(self.element)
attributes = property(getAttributes, setAttributes)
def insertText(self, data, insertBefore=None):
text = TextNode(self.soup.new_string(data), self.soup)
if insertBefore:
self.insertBefore(text, insertBefore)
else:
self.appendChild(text)
def insertBefore(self, node, refNode):
index = self.element.index(refNode.element)
if (node.element.__class__ == NavigableString and self.element.contents
and self.element.contents[index-1].__class__ == NavigableString):
# (See comments in appendChild)
old_node = self.element.contents[index-1]
new_str = self.soup.new_string(old_node + node.element)
old_node.replace_with(new_str)
else:
self.element.insert(index, node.element)
node.parent = self
def removeChild(self, node):
node.element.extract()
def reparentChildren(self, new_parent):
"""Move all of this tag's children into another tag."""
# print("MOVE", self.element.contents)
# print("FROM", self.element)
# print("TO", new_parent.element)
element = self.element
new_parent_element = new_parent.element
# Determine what this tag's next_element will be once all the children
# are removed.
final_next_element = element.next_sibling
new_parents_last_descendant = new_parent_element._last_descendant(False, False)
if len(new_parent_element.contents) > 0:
# The new parent already contains children. We will be
# appending this tag's children to the end.
new_parents_last_child = new_parent_element.contents[-1]
new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
else:
# The new parent contains no children.
new_parents_last_child = None
new_parents_last_descendant_next_element = new_parent_element.next_element
to_append = element.contents
if len(to_append) > 0:
# Set the first child's previous_element and previous_sibling
# to elements within the new parent
first_child = to_append[0]
if new_parents_last_descendant is not None:
first_child.previous_element = new_parents_last_descendant
else:
first_child.previous_element = new_parent_element
first_child.previous_sibling = new_parents_last_child
if new_parents_last_descendant is not None:
new_parents_last_descendant.next_element = first_child
else:
new_parent_element.next_element = first_child
if new_parents_last_child is not None:
new_parents_last_child.next_sibling = first_child
# Find the very last element being moved. It is now the
# parent's last descendant. It has no .next_sibling and
# its .next_element is whatever the previous last
# descendant had.
last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
if new_parents_last_descendant_next_element is not None:
# TODO: This code has no test coverage and I'm not sure
# how to get html5lib to go through this path, but it's
# just the other side of the previous line.
new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
last_childs_last_descendant.next_sibling = None
for child in to_append:
child.parent = new_parent_element
new_parent_element.contents.append(child)
# Now that this element has no children, change its .next_element.
element.contents = []
element.next_element = final_next_element
# print("DONE WITH MOVE")
# print("FROM", self.element)
# print("TO", new_parent_element)
def cloneNode(self):
tag = self.soup.new_tag(self.element.name, self.namespace)
node = Element(tag, self.soup, self.namespace)
for key,value in self.attributes:
node.attributes[key] = value
return node
def hasContent(self):
return self.element.contents
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
nameTuple = property(getNameTuple)
class TextNode(Element):
def __init__(self, element, soup):
treebuilder_base.Node.__init__(self, None)
self.element = element
self.soup = soup
def cloneNode(self):
raise NotImplementedError

499
acer-env/lib/python3.10/site-packages/bs4/builder/_htmlparser.py Normal file
View File

@ -0,0 +1,499 @@
# encoding: utf-8
"""Use the HTMLParser library to parse HTML files that aren't too bad."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'HTMLParserTreeBuilder',
]
from html.parser import HTMLParser
try:
from html.parser import HTMLParseError
except ImportError as e:
# HTMLParseError is removed in Python 3.5. Since it can never be
# thrown in 3.5, we can just define our own class as a placeholder.
class HTMLParseError(Exception):
pass
import sys
import warnings
# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
# argument, which we'd like to set to False. Unfortunately,
# http://bugs.python.org/issue13273 makes strict=True a better bet
# before Python 3.2.3.
#
# At the end of this file, we monkeypatch HTMLParser so that
# strict=True works well on Python 3.2.2.
major, minor, release = sys.version_info[:3]
CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
from bs4.element import (
CData,
Comment,
Declaration,
Doctype,
ProcessingInstruction,
)
from bs4.dammit import EntitySubstitution, UnicodeDammit
from bs4.builder import (
DetectsXMLParsedAsHTML,
HTML,
HTMLTreeBuilder,
STRICT,
)
HTMLPARSER = 'html.parser'
class BeautifulSoupHTMLParser(HTMLParser, DetectsXMLParsedAsHTML):
"""A subclass of the Python standard library's HTMLParser class, which
listens for HTMLParser events and translates them into calls
to Beautiful Soup's tree construction API.
"""
# Strategies for handling duplicate attributes
IGNORE = 'ignore'
REPLACE = 'replace'
def __init__(self, *args, **kwargs):
"""Constructor.
:param on_duplicate_attribute: A strategy for what to do if a
tag includes the same attribute more than once. Accepted
values are: REPLACE (replace earlier values with later
ones, the default), IGNORE (keep the earliest value
encountered), or a callable. A callable must take three
arguments: the dictionary of attributes already processed,
the name of the duplicate attribute, and the most recent value
encountered.
"""
self.on_duplicate_attribute = kwargs.pop(
'on_duplicate_attribute', self.REPLACE
)
HTMLParser.__init__(self, *args, **kwargs)
# Keep a list of empty-element tags that were encountered
# without an explicit closing tag. If we encounter a closing tag
# of this type, we'll associate it with one of those entries.
#
# This isn't a stack because we don't care about the
# order. It's a list of closing tags we've already handled and
# will ignore, assuming they ever show up.
self.already_closed_empty_element = []
self._initialize_xml_detector()
def error(self, msg):
"""In Python 3, HTMLParser subclasses must implement error(), although
this requirement doesn't appear to be documented.
In Python 2, HTMLParser implements error() by raising an exception,
which we don't want to do.
In any event, this method is called only on very strange
markup and our best strategy is to pretend it didn't happen
and keep going.
"""
warnings.warn(msg)
def handle_startendtag(self, name, attrs):
"""Handle an incoming empty-element tag.
This is only called when the markup looks like <tag/>.
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
"""
# is_startend() tells handle_starttag not to close the tag
# just because its name matches a known empty-element tag. We
# know that this is an empty-element tag and we want to call
# handle_endtag ourselves.
tag = self.handle_starttag(name, attrs, handle_empty_element=False)
self.handle_endtag(name)
def handle_starttag(self, name, attrs, handle_empty_element=True):
"""Handle an opening tag, e.g. '<tag>'
:param name: Name of the tag.
:param attrs: Dictionary of the tag's attributes.
:param handle_empty_element: True if this tag is known to be
an empty-element tag (i.e. there is not expected to be any
closing tag).
"""
# XXX namespace
attr_dict = {}
for key, value in attrs:
# Change None attribute values to the empty string
# for consistency with the other tree builders.
if value is None:
value = ''
if key in attr_dict:
# A single attribute shows up multiple times in this
# tag. How to handle it depends on the
# on_duplicate_attribute setting.
on_dupe = self.on_duplicate_attribute
if on_dupe == self.IGNORE:
pass
elif on_dupe in (None, self.REPLACE):
attr_dict[key] = value
else:
on_dupe(attr_dict, key, value)
else:
attr_dict[key] = value
attrvalue = '""'
#print("START", name)
sourceline, sourcepos = self.getpos()
tag = self.soup.handle_starttag(
name, None, None, attr_dict, sourceline=sourceline,
sourcepos=sourcepos
)
if tag and tag.is_empty_element and handle_empty_element:
# Unlike other parsers, html.parser doesn't send separate end tag
# events for empty-element tags. (It's handled in
# handle_startendtag, but only if the original markup looked like
# <tag/>.)
#
# So we need to call handle_endtag() ourselves. Since we
# know the start event is identical to the end event, we
# don't want handle_endtag() to cross off any previous end
# events for tags of this name.
self.handle_endtag(name, check_already_closed=False)
# But we might encounter an explicit closing tag for this tag
# later on. If so, we want to ignore it.
self.already_closed_empty_element.append(name)
if self._root_tag is None:
self._root_tag_encountered(name)
def handle_endtag(self, name, check_already_closed=True):
"""Handle a closing tag, e.g. '</tag>'
:param name: A tag name.
:param check_already_closed: True if this tag is expected to
be the closing portion of an empty-element tag,
e.g. '<tag></tag>'.
"""
#print("END", name)
if check_already_closed and name in self.already_closed_empty_element:
# This is a redundant end tag for an empty-element tag.
# We've already called handle_endtag() for it, so just
# check it off the list.
#print("ALREADY CLOSED", name)
self.already_closed_empty_element.remove(name)
else:
self.soup.handle_endtag(name)
def handle_data(self, data):
"""Handle some textual data that shows up between tags."""
self.soup.handle_data(data)
def handle_charref(self, name):
"""Handle a numeric character reference by converting it to the
corresponding Unicode character and treating it as textual
data.
:param name: Character number, possibly in hexadecimal.
"""
# XXX workaround for a bug in HTMLParser. Remove this once
# it's fixed in all supported versions.
# http://bugs.python.org/issue13633
if name.startswith('x'):
real_name = int(name.lstrip('x'), 16)
elif name.startswith('X'):
real_name = int(name.lstrip('X'), 16)
else:
real_name = int(name)
data = None
if real_name < 256:
# HTML numeric entities are supposed to reference Unicode
# code points, but sometimes they reference code points in
# some other encoding (ahem, Windows-1252). E.g. &#147;
# instead of &#201; for LEFT DOUBLE QUOTATION MARK. This
# code tries to detect this situation and compensate.
for encoding in (self.soup.original_encoding, 'windows-1252'):
if not encoding:
continue
try:
data = bytearray([real_name]).decode(encoding)
except UnicodeDecodeError as e:
pass
if not data:
try:
data = chr(real_name)
except (ValueError, OverflowError) as e:
pass
data = data or "\N{REPLACEMENT CHARACTER}"
self.handle_data(data)
def handle_entityref(self, name):
"""Handle a named entity reference by converting it to the
corresponding Unicode character(s) and treating it as textual
data.
:param name: Name of the entity reference.
"""
character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
if character is not None:
data = character
else:
# If this were XML, it would be ambiguous whether "&foo"
# was an character entity reference with a missing
# semicolon or the literal string "&foo". Since this is
# HTML, we have a complete list of all character entity references,
# and this one wasn't found, so assume it's the literal string "&foo".
data = "&%s" % name
self.handle_data(data)
def handle_comment(self, data):
"""Handle an HTML comment.
:param data: The text of the comment.
"""
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(Comment)
def handle_decl(self, data):
"""Handle a DOCTYPE declaration.
:param data: The text of the declaration.
"""
self.soup.endData()
data = data[len("DOCTYPE "):]
self.soup.handle_data(data)
self.soup.endData(Doctype)
def unknown_decl(self, data):
"""Handle a declaration of unknown type -- probably a CDATA block.
:param data: The text of the declaration.
"""
if data.upper().startswith('CDATA['):
cls = CData
data = data[len('CDATA['):]
else:
cls = Declaration
self.soup.endData()
self.soup.handle_data(data)
self.soup.endData(cls)
def handle_pi(self, data):
"""Handle a processing instruction.
:param data: The text of the instruction.
"""
self.soup.endData()
self.soup.handle_data(data)
self._document_might_be_xml(data)
self.soup.endData(ProcessingInstruction)
class HTMLParserTreeBuilder(HTMLTreeBuilder):
"""A Beautiful soup `TreeBuilder` that uses the `HTMLParser` parser,
found in the Python standard library.
"""
is_xml = False
picklable = True
NAME = HTMLPARSER
features = [NAME, HTML, STRICT]
# The html.parser knows which line number and position in the
# original file is the source of an element.
TRACKS_LINE_NUMBERS = True
def __init__(self, parser_args=None, parser_kwargs=None, **kwargs):
"""Constructor.
:param parser_args: Positional arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param parser_kwargs: Keyword arguments to pass into
the BeautifulSoupHTMLParser constructor, once it's
invoked.
:param kwargs: Keyword arguments for the superclass constructor.
"""
# Some keyword arguments will be pulled out of kwargs and placed
# into parser_kwargs.
extra_parser_kwargs = dict()
for arg in ('on_duplicate_attribute',):
if arg in kwargs:
value = kwargs.pop(arg)
extra_parser_kwargs[arg] = value
super(HTMLParserTreeBuilder, self).__init__(**kwargs)
parser_args = parser_args or []
parser_kwargs = parser_kwargs or {}
parser_kwargs.update(extra_parser_kwargs)
if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
parser_kwargs['strict'] = False
if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
parser_kwargs['convert_charrefs'] = False
self.parser_args = (parser_args, parser_kwargs)
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None, exclude_encodings=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
:param markup: Some markup -- probably a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
if isinstance(markup, str):
# Parse Unicode as-is.
yield (markup, None, None, False)
return
# Ask UnicodeDammit to sniff the most likely encoding.
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(
markup,
known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings,
is_html=True,
exclude_encodings=exclude_encodings
)
yield (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
def feed(self, markup):
"""Run some incoming markup through some parsing process,
populating the `BeautifulSoup` object in self.soup.
"""
args, kwargs = self.parser_args
parser = BeautifulSoupHTMLParser(*args, **kwargs)
parser.soup = self.soup
try:
parser.feed(markup)
parser.close()
except HTMLParseError as e:
warnings.warn(RuntimeWarning(
"Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
raise e
parser.already_closed_empty_element = []
# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
# 3.2.3 code. This ensures they don't treat markup like <p></p> as a
# string.
#
# XXX This code can be removed once most Python 3 users are on 3.2.3.
if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
import re
attrfind_tolerant = re.compile(
r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
|[^'\">\s]+ # bare value
)
)?
)
)*
\s* # trailing whitespace
""", re.VERBOSE)
BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
from html.parser import tagfind, attrfind
def parse_starttag(self, i):
self.__starttag_text = None
endpos = self.check_for_whole_start_tag(i)
if endpos < 0:
return endpos
rawdata = self.rawdata
self.__starttag_text = rawdata[i:endpos]
# Now parse the data between i+1 and j into a tag and attrs
attrs = []
match = tagfind.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
self.lasttag = tag = rawdata[i+1:k].lower()
while k < endpos:
if self.strict:
m = attrfind.match(rawdata, k)
else:
m = attrfind_tolerant.match(rawdata, k)
if not m:
break
attrname, rest, attrvalue = m.group(1, 2, 3)
if not rest:
attrvalue = None
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
attrvalue[:1] == '"' == attrvalue[-1:]:
attrvalue = attrvalue[1:-1]
if attrvalue:
attrvalue = self.unescape(attrvalue)
attrs.append((attrname.lower(), attrvalue))
k = m.end()
end = rawdata[k:endpos].strip()
if end not in (">", "/>"):
lineno, offset = self.getpos()
if "\n" in self.__starttag_text:
lineno = lineno + self.__starttag_text.count("\n")
offset = len(self.__starttag_text) \
- self.__starttag_text.rfind("\n")
else:
offset = offset + len(self.__starttag_text)
if self.strict:
self.error("junk characters in start tag: %r"
% (rawdata[k:endpos][:20],))
self.handle_data(rawdata[i:endpos])
return endpos
if end.endswith('/>'):
# XHTML-style empty tag: <span attr="value" />
self.handle_startendtag(tag, attrs)
else:
self.handle_starttag(tag, attrs)
if tag in self.CDATA_CONTENT_ELEMENTS:
self.set_cdata_mode(tag)
return endpos
def set_cdata_mode(self, elem):
self.cdata_elem = elem.lower()
self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
BeautifulSoupHTMLParser.parse_starttag = parse_starttag
BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
CONSTRUCTOR_TAKES_STRICT = True

386
acer-env/lib/python3.10/site-packages/bs4/builder/_lxml.py Normal file
View File

@ -0,0 +1,386 @@
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
]
try:
from collections.abc import Callable # Python 3.6
except ImportError as e:
from collections import Callable
from io import BytesIO
from io import StringIO
from lxml import etree
from bs4.element import (
Comment,
Doctype,
NamespacedAttribute,
ProcessingInstruction,
XMLProcessingInstruction,
)
from bs4.builder import (
DetectsXMLParsedAsHTML,
FAST,
HTML,
HTMLTreeBuilder,
PERMISSIVE,
ParserRejectedMarkup,
TreeBuilder,
XML)
from bs4.dammit import EncodingDetector
LXML = 'lxml'
def _invert(d):
"Invert a dictionary."
return dict((v,k) for k, v in list(d.items()))
class LXMLTreeBuilderForXML(TreeBuilder):
DEFAULT_PARSER_CLASS = etree.XMLParser
is_xml = True
processing_instruction_class = XMLProcessingInstruction
NAME = "lxml-xml"
ALTERNATE_NAMES = ["xml"]
# Well, it's permissive by XML parser standards.
features = [NAME, LXML, XML, FAST, PERMISSIVE]
CHUNK_SIZE = 512
# This namespace mapping is specified in the XML Namespace
# standard.
DEFAULT_NSMAPS = dict(xml='http://www.w3.org/XML/1998/namespace')
DEFAULT_NSMAPS_INVERTED = _invert(DEFAULT_NSMAPS)
# NOTE: If we parsed Element objects and looked at .sourceline,
# we'd be able to see the line numbers from the original document.
# But instead we build an XMLParser or HTMLParser object to serve
# as the target of parse messages, and those messages don't include
# line numbers.
# See: https://bugs.launchpad.net/lxml/+bug/1846906
def initialize_soup(self, soup):
"""Let the BeautifulSoup object know about the standard namespace
mapping.
:param soup: A `BeautifulSoup`.
"""
super(LXMLTreeBuilderForXML, self).initialize_soup(soup)
self._register_namespaces(self.DEFAULT_NSMAPS)
def _register_namespaces(self, mapping):
"""Let the BeautifulSoup object know about namespaces encountered
while parsing the document.
This might be useful later on when creating CSS selectors.
This will track (almost) all namespaces, even ones that were
only in scope for part of the document. If two namespaces have
the same prefix, only the first one encountered will be
tracked. Un-prefixed namespaces are not tracked.
:param mapping: A dictionary mapping namespace prefixes to URIs.
"""
for key, value in list(mapping.items()):
# This is 'if key' and not 'if key is not None' because we
# don't track un-prefixed namespaces. Soupselect will
# treat an un-prefixed namespace as the default, which
# causes confusion in some cases.
if key and key not in self.soup._namespaces:
# Let the BeautifulSoup object know about a new namespace.
# If there are multiple namespaces defined with the same
# prefix, the first one in the document takes precedence.
self.soup._namespaces[key] = value
def default_parser(self, encoding):
"""Find the default parser for the given encoding.
:param encoding: A string.
:return: Either a parser object or a class, which
will be instantiated with default arguments.
"""
if self._default_parser is not None:
return self._default_parser
return etree.XMLParser(
target=self, strip_cdata=False, recover=True, encoding=encoding)
def parser_for(self, encoding):
"""Instantiate an appropriate parser for the given encoding.
:param encoding: A string.
:return: A parser object such as an `etree.XMLParser`.
"""
# Use the default parser.
parser = self.default_parser(encoding)
if isinstance(parser, Callable):
# Instantiate the parser with default arguments
parser = parser(
target=self, strip_cdata=False, recover=True, encoding=encoding
)
return parser
def __init__(self, parser=None, empty_element_tags=None, **kwargs):
# TODO: Issue a warning if parser is present but not a
# callable, since that means there's no way to create new
# parsers for different encodings.
self._default_parser = parser
if empty_element_tags is not None:
self.empty_element_tags = set(empty_element_tags)
self.soup = None
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
self.active_namespace_prefixes = [dict(self.DEFAULT_NSMAPS)]
super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
def _getNsTag(self, tag):
# Split the namespace URL out of a fully-qualified lxml tag
# name. Copied from lxml's src/lxml/sax.py.
if tag[0] == '{':
return tuple(tag[1:].split('}', 1))
else:
return (None, tag)
def prepare_markup(self, markup, user_specified_encoding=None,
exclude_encodings=None,
document_declared_encoding=None):
"""Run any preliminary steps necessary to make incoming markup
acceptable to the parser.
lxml really wants to get a bytestring and convert it to
Unicode itself. So instead of using UnicodeDammit to convert
the bytestring to Unicode using different encodings, this
implementation uses EncodingDetector to iterate over the
encodings, and tell lxml to try to parse the document as each
one in turn.
:param markup: Some markup -- hopefully a bytestring.
:param user_specified_encoding: The user asked to try this encoding.
:param document_declared_encoding: The markup itself claims to be
in this encoding.
:param exclude_encodings: The user asked _not_ to try any of
these encodings.
:yield: A series of 4-tuples:
(markup, encoding, declared encoding,
has undergone character replacement)
Each 4-tuple represents a strategy for converting the
document to Unicode and parsing it. Each strategy will be tried
in turn.
"""
is_html = not self.is_xml
if is_html:
self.processing_instruction_class = ProcessingInstruction
# We're in HTML mode, so if we're given XML, that's worth
# noting.
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
else:
self.processing_instruction_class = XMLProcessingInstruction
if isinstance(markup, str):
# We were given Unicode. Maybe lxml can parse Unicode on
# this system?
# TODO: This is a workaround for
# https://bugs.launchpad.net/lxml/+bug/1948551.
# We can remove it once the upstream issue is fixed.
if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}':
markup = markup[1:]
yield markup, None, document_declared_encoding, False
if isinstance(markup, str):
# No, apparently not. Convert the Unicode to UTF-8 and
# tell lxml to parse it as UTF-8.
yield (markup.encode("utf8"), "utf8",
document_declared_encoding, False)
# This was provided by the end-user; treat it as a known
# definite encoding per the algorithm laid out in the HTML5
# spec. (See the EncodingDetector class for details.)
known_definite_encodings = [user_specified_encoding]
# This was found in the document; treat it as a slightly lower-priority
# user encoding.
user_encodings = [document_declared_encoding]
detector = EncodingDetector(
markup, known_definite_encodings=known_definite_encodings,
user_encodings=user_encodings, is_html=is_html,
exclude_encodings=exclude_encodings
)
for encoding in detector.encodings:
yield (detector.markup, encoding, document_declared_encoding, False)
def feed(self, markup):
if isinstance(markup, bytes):
markup = BytesIO(markup)
elif isinstance(markup, str):
markup = StringIO(markup)
# Call feed() at least once, even if the markup is empty,
# or the parser won't be initialized.
data = markup.read(self.CHUNK_SIZE)
try:
self.parser = self.parser_for(self.soup.original_encoding)
self.parser.feed(data)
while len(data) != 0:
# Now call feed() on the rest of the data, chunk by chunk.
data = markup.read(self.CHUNK_SIZE)
if len(data) != 0:
self.parser.feed(data)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(e)
def close(self):
self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
def start(self, name, attrs, nsmap={}):
# Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
attrs = dict(attrs)
nsprefix = None
# Invert each namespace map as it comes in.
if len(nsmap) == 0 and len(self.nsmaps) > 1:
# There are no new namespaces for this tag, but
# non-default namespaces are in play, so we need a
# separate tag stack to know when they end.
self.nsmaps.append(None)
elif len(nsmap) > 0:
# A new namespace mapping has come into play.
# First, Let the BeautifulSoup object know about it.
self._register_namespaces(nsmap)
# Then, add it to our running list of inverted namespace
# mappings.
self.nsmaps.append(_invert(nsmap))
# The currently active namespace prefixes have
# changed. Calculate the new mapping so it can be stored
# with all Tag objects created while these prefixes are in
# scope.
current_mapping = dict(self.active_namespace_prefixes[-1])
current_mapping.update(nsmap)
# We should not track un-prefixed namespaces as we can only hold one
# and it will be recognized as the default namespace by soupsieve,
# which may be confusing in some situations.
if '' in current_mapping:
del current_mapping['']
self.active_namespace_prefixes.append(current_mapping)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
for prefix, namespace in list(nsmap.items()):
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
# Namespaces are in play. Find any attributes that came in
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
for attr, value in list(attrs.items()):
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
else:
nsprefix = self._prefix_for_namespace(namespace)
attr = NamespacedAttribute(nsprefix, attr, namespace)
new_attrs[attr] = value
attrs = new_attrs
namespace, name = self._getNsTag(name)
nsprefix = self._prefix_for_namespace(namespace)
self.soup.handle_starttag(
name, namespace, nsprefix, attrs,
namespaces=self.active_namespace_prefixes[-1]
)
def _prefix_for_namespace(self, namespace):
"""Find the currently active prefix for the given namespace."""
if namespace is None:
return None
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
return inverted_nsmap[namespace]
return None
def end(self, name):
self.soup.endData()
completed_tag = self.soup.tagStack[-1]
namespace, name = self._getNsTag(name)
nsprefix = None
if namespace is not None:
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
nsprefix = inverted_nsmap[namespace]
break
self.soup.handle_endtag(name, nsprefix)
if len(self.nsmaps) > 1:
# This tag, or one of its parents, introduced a namespace
# mapping, so pop it off the stack.
out_of_scope_nsmap = self.nsmaps.pop()
if out_of_scope_nsmap is not None:
# This tag introduced a namespace mapping which is no
# longer in scope. Recalculate the currently active
# namespace prefixes.
self.active_namespace_prefixes.pop()
def pi(self, target, data):
self.soup.endData()
data = target + ' ' + data
self.soup.handle_data(data)
self.soup.endData(self.processing_instruction_class)
def data(self, content):
self.soup.handle_data(content)
def doctype(self, name, pubid, system):
self.soup.endData()
doctype = Doctype.for_name_and_ids(name, pubid, system)
self.soup.object_was_parsed(doctype)
def comment(self, content):
"Handle comments as Comment objects."
self.soup.endData()
self.soup.handle_data(content)
self.soup.endData(Comment)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
NAME = LXML
ALTERNATE_NAMES = ["lxml-html"]
features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
is_xml = False
processing_instruction_class = ProcessingInstruction
def default_parser(self, encoding):
return etree.HTMLParser
def feed(self, markup):
encoding = self.soup.original_encoding
try:
self.parser = self.parser_for(encoding)
self.parser.feed(markup)
self.parser.close()
except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
raise ParserRejectedMarkup(e)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return '<html><body>%s</body></html>' % fragment

1095
acer-env/lib/python3.10/site-packages/bs4/dammit.py Normal file
View File

File diff suppressed because it is too large Load Diff

248
acer-env/lib/python3.10/site-packages/bs4/diagnose.py Normal file
View File

@ -0,0 +1,248 @@
"""Diagnostic functions, mainly for use when doing tech support."""
# Use of this source code is governed by the MIT license.
__license__ = "MIT"
import cProfile
from io import BytesIO
from html.parser import HTMLParser
import bs4
from bs4 import BeautifulSoup, __version__
from bs4.builder import builder_registry
import os
import pstats
import random
import tempfile
import time
import traceback
import sys
import cProfile
def diagnose(data):
"""Diagnostic suite for isolating common problems.
:param data: A string containing markup that needs to be explained.
:return: None; diagnostics are printed to standard output.
"""
print(("Diagnostic running on Beautiful Soup %s" % __version__))
print(("Python version %s" % sys.version))
basic_parsers = ["html.parser", "html5lib", "lxml"]
for name in basic_parsers:
for builder in builder_registry.builders:
if name in builder.features:
break
else:
basic_parsers.remove(name)
print((
"I noticed that %s is not installed. Installing it may help." %
name))
if 'lxml' in basic_parsers:
basic_parsers.append("lxml-xml")
try:
from lxml import etree
print(("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))))
except ImportError as e:
print(
"lxml is not installed or couldn't be imported.")
if 'html5lib' in basic_parsers:
try:
import html5lib
print(("Found html5lib version %s" % html5lib.__version__))
except ImportError as e:
print(
"html5lib is not installed or couldn't be imported.")
if hasattr(data, 'read'):
data = data.read()
elif data.startswith("http:") or data.startswith("https:"):
print(('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data))
print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
return
else:
try:
if os.path.exists(data):
print(('"%s" looks like a filename. Reading data from the file.' % data))
with open(data) as fp:
data = fp.read()
except ValueError:
# This can happen on some platforms when the 'filename' is
# too long. Assume it's data and not a filename.
pass
print("")
for parser in basic_parsers:
print(("Trying to parse your markup with %s" % parser))
success = False
try:
soup = BeautifulSoup(data, features=parser)
success = True
except Exception as e:
print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
print(("Here's what %s did with the markup:" % parser))
print((soup.prettify()))
print(("-" * 80))
def lxml_trace(data, html=True, **kwargs):
"""Print out the lxml events that occur during parsing.
This lets you see how lxml parses a document when no Beautiful
Soup code is running. You can use this to determine whether
an lxml-specific problem is in Beautiful Soup's lxml tree builders
or in lxml itself.
:param data: Some markup.
:param html: If True, markup will be parsed with lxml's HTML parser.
if False, lxml's XML parser will be used.
"""
from lxml import etree
recover = kwargs.pop('recover', True)
if isinstance(data, str):
data = data.encode("utf8")
reader = BytesIO(data)
for event, element in etree.iterparse(
reader, html=html, recover=recover, **kwargs
):
print(("%s, %4s, %s" % (event, element.tag, element.text)))
class AnnouncingParser(HTMLParser):
"""Subclass of HTMLParser that announces parse events, without doing
anything else.
You can use this to get a picture of how html.parser sees a given
document. The easiest way to do this is to call `htmlparser_trace`.
"""
def _p(self, s):
print(s)
def handle_starttag(self, name, attrs):
self._p("%s START" % name)
def handle_endtag(self, name):
self._p("%s END" % name)
def handle_data(self, data):
self._p("%s DATA" % data)
def handle_charref(self, name):
self._p("%s CHARREF" % name)
def handle_entityref(self, name):
self._p("%s ENTITYREF" % name)
def handle_comment(self, data):
self._p("%s COMMENT" % data)
def handle_decl(self, data):
self._p("%s DECL" % data)
def unknown_decl(self, data):
self._p("%s UNKNOWN-DECL" % data)
def handle_pi(self, data):
self._p("%s PI" % data)
def htmlparser_trace(data):
"""Print out the HTMLParser events that occur during parsing.
This lets you see how HTMLParser parses a document when no
Beautiful Soup code is running.
:param data: Some markup.
"""
parser = AnnouncingParser()
parser.feed(data)
_vowels = "aeiou"
_consonants = "bcdfghjklmnpqrstvwxyz"
def rword(length=5):
"Generate a random word-like string."
s = ''
for i in range(length):
if i % 2 == 0:
t = _consonants
else:
t = _vowels
s += random.choice(t)
return s
def rsentence(length=4):
"Generate a random sentence-like string."
return " ".join(rword(random.randint(4,9)) for i in range(length))
def rdoc(num_elements=1000):
"""Randomly generate an invalid HTML document."""
tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
elements = []
for i in range(num_elements):
choice = random.randint(0,3)
if choice == 0:
# New tag.
tag_name = random.choice(tag_names)
elements.append("<%s>" % tag_name)
elif choice == 1:
elements.append(rsentence(random.randint(1,4)))
elif choice == 2:
# Close a tag.
tag_name = random.choice(tag_names)
elements.append("</%s>" % tag_name)
return "<html>" + "\n".join(elements) + "</html>"
def benchmark_parsers(num_elements=100000):
"""Very basic head-to-head performance benchmark."""
print(("Comparative parser benchmark on Beautiful Soup %s" % __version__))
data = rdoc(num_elements)
print(("Generated a large invalid HTML document (%d bytes)." % len(data)))
for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
success = False
try:
a = time.time()
soup = BeautifulSoup(data, parser)
b = time.time()
success = True
except Exception as e:
print(("%s could not parse the markup." % parser))
traceback.print_exc()
if success:
print(("BS4+%s parsed the markup in %.2fs." % (parser, b-a)))
from lxml import etree
a = time.time()
etree.HTML(data)
b = time.time()
print(("Raw lxml parsed the markup in %.2fs." % (b-a)))
import html5lib
parser = html5lib.HTMLParser()
a = time.time()
parser.parse(data)
b = time.time()
print(("Raw html5lib parsed the markup in %.2fs." % (b-a)))
def profile(num_elements=100000, parser="lxml"):
"""Use Python's profiler on a randomly generated document."""
filehandle = tempfile.NamedTemporaryFile()
filename = filehandle.name
data = rdoc(num_elements)
vars = dict(bs4=bs4, data=data, parser=parser)
cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
stats = pstats.Stats(filename)
# stats.strip_dirs()
stats.sort_stats("cumulative")
stats.print_stats('_html5lib|bs4', 50)
# If this file is run as a script, standard input is diagnosed.
if __name__ == '__main__':
diagnose(sys.stdin.read())

2291
acer-env/lib/python3.10/site-packages/bs4/element.py Normal file
View File

File diff suppressed because it is too large Load Diff

185
acer-env/lib/python3.10/site-packages/bs4/formatter.py Normal file
View File

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

1191
acer-env/lib/python3.10/site-packages/bs4/tests/__init__.py Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/__init__.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_builder.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_builder_registry.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_dammit.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_docs.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_element.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_formatter.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_html5lib.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_htmlparser.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_lxml.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_navigablestring.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_pageelement.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_soup.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_tag.cpython-310.pyc Normal file
View File

Binary file not shown.

BIN
acer-env/lib/python3.10/site-packages/bs4/tests/__pycache__/test_tree.cpython-310.pyc Normal file
View File

Binary file not shown.

29
acer-env/lib/python3.10/site-packages/bs4/tests/test_builder.py Normal file
View File

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

136
acer-env/lib/python3.10/site-packages/bs4/tests/test_builder_registry.py Normal file
View File

@ -0,0 +1,136 @@
"""Tests of the builder registry."""
import pytest
import warnings
from bs4 import BeautifulSoup
from bs4.builder import (
builder_registry as registry,
HTMLParserTreeBuilder,
TreeBuilderRegistry,
)
try:
from bs4.builder import HTML5TreeBuilder
HTML5LIB_PRESENT = True
except ImportError:
HTML5LIB_PRESENT = False
try:
from bs4.builder import (
LXMLTreeBuilderForXML,
LXMLTreeBuilder,
)
LXML_PRESENT = True
except ImportError:
LXML_PRESENT = False
class TestBuiltInRegistry(object):
"""Test the built-in registry with the default builders registered."""
def test_combination(self):
assert registry.lookup('strict', 'html') == HTMLParserTreeBuilder
if LXML_PRESENT:
assert registry.lookup('fast', 'html') == LXMLTreeBuilder
assert registry.lookup('permissive', 'xml') == LXMLTreeBuilderForXML
if HTML5LIB_PRESENT:
assert registry.lookup('html5lib', 'html') == HTML5TreeBuilder
def test_lookup_by_markup_type(self):
if LXML_PRESENT:
assert registry.lookup('html') == LXMLTreeBuilder
assert registry.lookup('xml') == LXMLTreeBuilderForXML
else:
assert registry.lookup('xml') == None
if HTML5LIB_PRESENT:
assert registry.lookup('html') == HTML5TreeBuilder
else:
assert registry.lookup('html') == HTMLParserTreeBuilder
def test_named_library(self):
if LXML_PRESENT:
assert registry.lookup('lxml', 'xml') == LXMLTreeBuilderForXML
assert registry.lookup('lxml', 'html') == LXMLTreeBuilder
if HTML5LIB_PRESENT:
assert registry.lookup('html5lib') == HTML5TreeBuilder
assert registry.lookup('html.parser') == HTMLParserTreeBuilder
def test_beautifulsoup_constructor_does_lookup(self):
with warnings.catch_warnings(record=True) as w:
# This will create a warning about not explicitly
# specifying a parser, but we'll ignore it.
# You can pass in a string.
BeautifulSoup("", features="html")
# Or a list of strings.
BeautifulSoup("", features=["html", "fast"])
pass
# You'll get an exception if BS can't find an appropriate
# builder.
with pytest.raises(ValueError):
BeautifulSoup("", features="no-such-feature")
class TestRegistry(object):
"""Test the TreeBuilderRegistry class in general."""
def setup_method(self):
self.registry = TreeBuilderRegistry()
def builder_for_features(self, *feature_list):
cls = type('Builder_' + '_'.join(feature_list),
(object,), {'features' : feature_list})
self.registry.register(cls)
return cls
def test_register_with_no_features(self):
builder = self.builder_for_features()
# Since the builder advertises no features, you can't find it
# by looking up features.
assert self.registry.lookup('foo') is None
# But you can find it by doing a lookup with no features, if
# this happens to be the only registered builder.
assert self.registry.lookup() == builder
def test_register_with_features_makes_lookup_succeed(self):
builder = self.builder_for_features('foo', 'bar')
assert self.registry.lookup('foo') is builder
assert self.registry.lookup('bar') is builder
def test_lookup_fails_when_no_builder_implements_feature(self):
builder = self.builder_for_features('foo', 'bar')
assert self.registry.lookup('baz') is None
def test_lookup_gets_most_recent_registration_when_no_feature_specified(self):
builder1 = self.builder_for_features('foo')
builder2 = self.builder_for_features('bar')
assert self.registry.lookup() == builder2
def test_lookup_fails_when_no_tree_builders_registered(self):
assert self.registry.lookup() is None
def test_lookup_gets_most_recent_builder_supporting_all_features(self):
has_one = self.builder_for_features('foo')
has_the_other = self.builder_for_features('bar')
has_both_early = self.builder_for_features('foo', 'bar', 'baz')
has_both_late = self.builder_for_features('foo', 'bar', 'quux')
lacks_one = self.builder_for_features('bar')
has_the_other = self.builder_for_features('foo')
# There are two builders featuring 'foo' and 'bar', but
# the one that also features 'quux' was registered later.
assert self.registry.lookup('foo', 'bar') == has_both_late
# There is only one builder featuring 'foo', 'bar', and 'baz'.
assert self.registry.lookup('foo', 'bar', 'baz') == has_both_early
def test_lookup_fails_when_cannot_reconcile_requested_features(self):
builder1 = self.builder_for_features('foo', 'bar')
builder2 = self.builder_for_features('foo', 'baz')
assert self.registry.lookup('bar', 'baz') is None

371
acer-env/lib/python3.10/site-packages/bs4/tests/test_dammit.py Normal file
View File

@ -0,0 +1,371 @@
# encoding: utf-8
import pytest
import logging
import bs4
from bs4 import BeautifulSoup
from bs4.dammit import (
EntitySubstitution,
EncodingDetector,
UnicodeDammit,
)
class TestUnicodeDammit(object):
"""Standalone tests of UnicodeDammit."""
def test_unicode_input(self):
markup = "I'm already Unicode! \N{SNOWMAN}"
dammit = UnicodeDammit(markup)
assert dammit.unicode_markup == markup
def test_smart_quotes_to_unicode(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup)
assert dammit.unicode_markup == "<foo>\u2018\u2019\u201c\u201d</foo>"
def test_smart_quotes_to_xml_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="xml")
assert dammit.unicode_markup == "<foo>&#x2018;&#x2019;&#x201C;&#x201D;</foo>"
def test_smart_quotes_to_html_entities(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="html")
assert dammit.unicode_markup == "<foo>&lsquo;&rsquo;&ldquo;&rdquo;</foo>"
def test_smart_quotes_to_ascii(self):
markup = b"<foo>\x91\x92\x93\x94</foo>"
dammit = UnicodeDammit(markup, smart_quotes_to="ascii")
assert dammit.unicode_markup == """<foo>''""</foo>"""
def test_detect_utf8(self):
utf8 = b"Sacr\xc3\xa9 bleu! \xe2\x98\x83"
dammit = UnicodeDammit(utf8)
assert dammit.original_encoding.lower() == 'utf-8'
assert dammit.unicode_markup == 'Sacr\xe9 bleu! \N{SNOWMAN}'
def test_convert_hebrew(self):
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
assert dammit.original_encoding.lower() == 'iso-8859-8'
assert dammit.unicode_markup == '\u05dd\u05d5\u05dc\u05e9'
def test_dont_see_smart_quotes_where_there_are_none(self):
utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
dammit = UnicodeDammit(utf_8)
assert dammit.original_encoding.lower() == 'utf-8'
assert dammit.unicode_markup.encode("utf-8") == utf_8
def test_ignore_inappropriate_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
dammit = UnicodeDammit(utf8_data, ["iso-8859-8"])
assert dammit.original_encoding.lower() == 'utf-8'
def test_ignore_invalid_codecs(self):
utf8_data = "Räksmörgås".encode("utf-8")
for bad_encoding in ['.utf8', '...', 'utF---16.!']:
dammit = UnicodeDammit(utf8_data, [bad_encoding])
assert dammit.original_encoding.lower() == 'utf-8'
def test_exclude_encodings(self):
# This is UTF-8.
utf8_data = "Räksmörgås".encode("utf-8")
# But if we exclude UTF-8 from consideration, the guess is
# Windows-1252.
dammit = UnicodeDammit(utf8_data, exclude_encodings=["utf-8"])
assert dammit.original_encoding.lower() == 'windows-1252'
# And if we exclude that, there is no valid guess at all.
dammit = UnicodeDammit(
utf8_data, exclude_encodings=["utf-8", "windows-1252"])
assert dammit.original_encoding == None
class TestEncodingDetector(object):
def test_encoding_detector_replaces_junk_in_encoding_name_with_replacement_character(self):
detected = EncodingDetector(
b'<?xml version="1.0" encoding="UTF-\xdb" ?>')
encodings = list(detected.encodings)
assert 'utf-\N{REPLACEMENT CHARACTER}' in encodings
def test_detect_html5_style_meta_tag(self):
for data in (
b'<html><meta charset="euc-jp" /></html>',
b"<html><meta charset='euc-jp' /></html>",
b"<html><meta charset=euc-jp /></html>",
b"<html><meta charset=euc-jp/></html>"):
dammit = UnicodeDammit(data, is_html=True)
assert "euc-jp" == dammit.original_encoding
def test_last_ditch_entity_replacement(self):
# This is a UTF-8 document that contains bytestrings
# completely incompatible with UTF-8 (ie. encoded with some other
# encoding).
#
# Since there is no consistent encoding for the document,
# Unicode, Dammit will eventually encode the document as UTF-8
# and encode the incompatible characters as REPLACEMENT
# CHARACTER.
#
# If chardet is installed, it will detect that the document
# can be converted into ISO-8859-1 without errors. This happens
# to be the wrong encoding, but it is a consistent encoding, so the
# code we're testing here won't run.
#
# So we temporarily disable chardet if it's present.
doc = b"""\357\273\277<?xml version="1.0" encoding="UTF-8"?>
<html><b>\330\250\330\252\330\261</b>
<i>\310\322\321\220\312\321\355\344</i></html>"""
chardet = bs4.dammit.chardet_dammit
logging.disable(logging.WARNING)
try:
def noop(str):
return None
bs4.dammit.chardet_dammit = noop
dammit = UnicodeDammit(doc)
assert True == dammit.contains_replacement_characters
assert "\ufffd" in dammit.unicode_markup
soup = BeautifulSoup(doc, "html.parser")
assert soup.contains_replacement_characters
finally:
logging.disable(logging.NOTSET)
bs4.dammit.chardet_dammit = chardet
def test_byte_order_mark_removed(self):
# A document written in UTF-16LE will have its byte order marker stripped.
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
dammit = UnicodeDammit(data)
assert "<a>áé</a>" == dammit.unicode_markup
assert "utf-16le" == dammit.original_encoding
def test_known_definite_versus_user_encodings(self):
# The known_definite_encodings are used before sniffing the
# byte-order mark; the user_encodings are used afterwards.
# Here's a document in UTF-16LE.
data = b'\xff\xfe<\x00a\x00>\x00\xe1\x00\xe9\x00<\x00/\x00a\x00>\x00'
dammit = UnicodeDammit(data)
# We can process it as UTF-16 by passing it in as a known
# definite encoding.
before = UnicodeDammit(data, known_definite_encodings=["utf-16"])
assert "utf-16" == before.original_encoding
# If we pass UTF-18 as a user encoding, it's not even
# tried--the encoding sniffed from the byte-order mark takes
# precedence.
after = UnicodeDammit(data, user_encodings=["utf-8"])
assert "utf-16le" == after.original_encoding
assert ["utf-16le"] == [x[0] for x in dammit.tried_encodings]
# Here's a document in ISO-8859-8.
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(hebrew, known_definite_encodings=["utf-8"],
user_encodings=["iso-8859-8"])
# The known_definite_encodings don't work, BOM sniffing does
# nothing (it only works for a few UTF encodings), but one of
# the user_encodings does work.
assert "iso-8859-8" == dammit.original_encoding
assert ["utf-8", "iso-8859-8"] == [x[0] for x in dammit.tried_encodings]
def test_deprecated_override_encodings(self):
# override_encodings is a deprecated alias for
# known_definite_encodings.
hebrew = b"\xed\xe5\xec\xf9"
dammit = UnicodeDammit(
hebrew,
known_definite_encodings=["shift-jis"],
override_encodings=["utf-8"],
user_encodings=["iso-8859-8"],
)
assert "iso-8859-8" == dammit.original_encoding
# known_definite_encodings and override_encodings were tried
# before user_encodings.
assert ["shift-jis", "utf-8", "iso-8859-8"] == (
[x[0] for x in dammit.tried_encodings]
)
def test_detwingle(self):
# Here's a UTF8 document.
utf8 = ("\N{SNOWMAN}" * 3).encode("utf8")
# Here's a Windows-1252 document.
windows_1252 = (
"\N{LEFT DOUBLE QUOTATION MARK}Hi, I like Windows!"
"\N{RIGHT DOUBLE QUOTATION MARK}").encode("windows_1252")
# Through some unholy alchemy, they've been stuck together.
doc = utf8 + windows_1252 + utf8
# The document can't be turned into UTF-8:
with pytest.raises(UnicodeDecodeError):
doc.decode("utf8")
# Unicode, Dammit thinks the whole document is Windows-1252,
# and decodes it into "☃☃☃“Hi, I like Windows!”☃☃☃"
# But if we run it through fix_embedded_windows_1252, it's fixed:
fixed = UnicodeDammit.detwingle(doc)
assert "☃☃☃“Hi, I like Windows!”☃☃☃" == fixed.decode("utf8")
def test_detwingle_ignores_multibyte_characters(self):
# Each of these characters has a UTF-8 representation ending
# in \x93. \x93 is a smart quote if interpreted as
# Windows-1252. But our code knows to skip over multibyte
# UTF-8 characters, so they'll survive the process unscathed.
for tricky_unicode_char in (
"\N{LATIN SMALL LIGATURE OE}", # 2-byte char '\xc5\x93'
"\N{LATIN SUBSCRIPT SMALL LETTER X}", # 3-byte char '\xe2\x82\x93'
"\xf0\x90\x90\x93", # This is a CJK character, not sure which one.
):
input = tricky_unicode_char.encode("utf8")
assert input.endswith(b'\x93')
output = UnicodeDammit.detwingle(input)
assert output == input
def test_find_declared_encoding(self):
# Test our ability to find a declared encoding inside an
# XML or HTML document.
#
# Even if the document comes in as Unicode, it may be
# interesting to know what encoding was claimed
# originally.
html_unicode = '<html><head><meta charset="utf-8"></head></html>'
html_bytes = html_unicode.encode("ascii")
xml_unicode= '<?xml version="1.0" encoding="ISO-8859-1" ?>'
xml_bytes = xml_unicode.encode("ascii")
m = EncodingDetector.find_declared_encoding
assert m(html_unicode, is_html=False) is None
assert "utf-8" == m(html_unicode, is_html=True)
assert "utf-8" == m(html_bytes, is_html=True)
assert "iso-8859-1" == m(xml_unicode)
assert "iso-8859-1" == m(xml_bytes)
# Normally, only the first few kilobytes of a document are checked for
# an encoding.
spacer = b' ' * 5000
assert m(spacer + html_bytes) is None
assert m(spacer + xml_bytes) is None
# But you can tell find_declared_encoding to search an entire
# HTML document.
assert (
m(spacer + html_bytes, is_html=True, search_entire_document=True)
== "utf-8"
)
# The XML encoding declaration has to be the very first thing
# in the document. We'll allow whitespace before the document
# starts, but nothing else.
assert m(xml_bytes, search_entire_document=True) == "iso-8859-1"
assert m(b' ' + xml_bytes, search_entire_document=True) == "iso-8859-1"
assert m(b'a' + xml_bytes, search_entire_document=True) is None
class TestEntitySubstitution(object):
"""Standalone tests of the EntitySubstitution class."""
def setup_method(self):
self.sub = EntitySubstitution
def test_simple_html_substitution(self):
# Unicode characters corresponding to named HTML entites
# are substituted, and no others.
s = "foo\u2200\N{SNOWMAN}\u00f5bar"
assert self.sub.substitute_html(s) == "foo&forall;\N{SNOWMAN}&otilde;bar"
def test_smart_quote_substitution(self):
# MS smart quotes are a common source of frustration, so we
# give them a special test.
quotes = b"\x91\x92foo\x93\x94"
dammit = UnicodeDammit(quotes)
assert self.sub.substitute_html(dammit.markup) == "&lsquo;&rsquo;foo&ldquo;&rdquo;"
def test_html5_entity(self):
# Some HTML5 entities correspond to single- or multi-character
# Unicode sequences.
for entity, u in (
# A few spot checks of our ability to recognize
# special character sequences and convert them
# to named entities.
('&models;', '\u22a7'),
('&Nfr;', '\U0001d511'),
('&ngeqq;', '\u2267\u0338'),
('&not;', '\xac'),
('&Not;', '\u2aec'),
# We _could_ convert | to &verbarr;, but we don't, because
# | is an ASCII character.
('|' '|'),
# Similarly for the fj ligature, which we could convert to
# &fjlig;, but we don't.
("fj", "fj"),
# We do convert _these_ ASCII characters to HTML entities,
# because that's required to generate valid HTML.
('&gt;', '>'),
('&lt;', '<'),
('&amp;', '&'),
):
template = '3 %s 4'
raw = template % u
with_entities = template % entity
assert self.sub.substitute_html(raw) == with_entities
def test_html5_entity_with_variation_selector(self):
# Some HTML5 entities correspond either to a single-character
# Unicode sequence _or_ to the same character plus U+FE00,
# VARIATION SELECTOR 1. We can handle this.
data = "fjords \u2294 penguins"
markup = "fjords &sqcup; penguins"
assert self.sub.substitute_html(data) == markup
data = "fjords \u2294\ufe00 penguins"
markup = "fjords &sqcups; penguins"
assert self.sub.substitute_html(data) == markup
def test_xml_converstion_includes_no_quotes_if_make_quoted_attribute_is_false(self):
s = 'Welcome to "my bar"'
assert self.sub.substitute_xml(s, False) == s
def test_xml_attribute_quoting_normally_uses_double_quotes(self):
assert self.sub.substitute_xml("Welcome", True) == '"Welcome"'
assert self.sub.substitute_xml("Bob's Bar", True) == '"Bob\'s Bar"'
def test_xml_attribute_quoting_uses_single_quotes_when_value_contains_double_quotes(self):
s = 'Welcome to "my bar"'
assert self.sub.substitute_xml(s, True) == "'Welcome to \"my bar\"'"
def test_xml_attribute_quoting_escapes_single_quotes_when_value_contains_both_single_and_double_quotes(self):
s = 'Welcome to "Bob\'s Bar"'
assert self.sub.substitute_xml(s, True) == '"Welcome to &quot;Bob\'s Bar&quot;"'
def test_xml_quotes_arent_escaped_when_value_is_not_being_quoted(self):
quoted = 'Welcome to "Bob\'s Bar"'
assert self.sub.substitute_xml(quoted) == quoted
def test_xml_quoting_handles_angle_brackets(self):
assert self.sub.substitute_xml("foo<bar>") == "foo&lt;bar&gt;"
def test_xml_quoting_handles_ampersands(self):
assert self.sub.substitute_xml("AT&T") == "AT&amp;T"
def test_xml_quoting_including_ampersands_when_they_are_part_of_an_entity(self):
assert self.sub.substitute_xml("&Aacute;T&T") == "&amp;Aacute;T&amp;T"
def test_xml_quoting_ignoring_ampersands_when_they_are_part_of_an_entity(self):
assert self.sub.substitute_xml_containing_entities("&Aacute;T&T") == "&Aacute;T&amp;T"
def test_quotes_not_html_substituted(self):
"""There's no need to do this except inside attribute values."""
text = 'Bob\'s "bar"'
assert self.sub.substitute_html(text) == text

38
acer-env/lib/python3.10/site-packages/bs4/tests/test_docs.py Normal file
View File

@ -0,0 +1,38 @@
"Test harness for doctests."
# TODO: Pretty sure this isn't used and should be deleted.
# pylint: disable-msg=E0611,W0142
__metaclass__ = type
__all__ = [
'additional_tests',
]
import atexit
import doctest
import os
#from pkg_resources import (
# resource_filename, resource_exists, resource_listdir, cleanup_resources)
import unittest
DOCTEST_FLAGS = (
doctest.ELLIPSIS |
doctest.NORMALIZE_WHITESPACE |
doctest.REPORT_NDIFF)
# def additional_tests():
# "Run the doc tests (README.txt and docs/*, if any exist)"
# doctest_files = [
# os.path.abspath(resource_filename('bs4', 'README.txt'))]
# if resource_exists('bs4', 'docs'):
# for name in resource_listdir('bs4', 'docs'):
# if name.endswith('.txt'):
# doctest_files.append(
# os.path.abspath(
# resource_filename('bs4', 'docs/%s' % name)))
# kwargs = dict(module_relative=False, optionflags=DOCTEST_FLAGS)
# atexit.register(cleanup_resources)
# return unittest.TestSuite((
# doctest.DocFileSuite(*doctest_files, **kwargs)))

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