diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..c1eba660d4aacf3794784091d0d8139d7a2bab71 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,14 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/numpy.libs/libgfortran-040039e1-0352e75f.so.5.0.0 filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/numpy.libs/libscipy_openblas64_-ff651d7f.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/numpy/_core/_multiarray_umath.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/numpy/_core/_simd.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/numpy/random/_generator.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/pandas/_libs/algos.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/pandas/_libs/groupby.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/pandas/_libs/hashtable.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/pandas/_libs/interval.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/pandas/_libs/join.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text +cmrithackathon-master/.venv/lib/python3.11/site-packages/pandas/_libs/tslibs/offsets.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text diff --git a/cmrithackathon-master/.venv/bin/Activate.ps1 b/cmrithackathon-master/.venv/bin/Activate.ps1 new file mode 100644 index 0000000000000000000000000000000000000000..eeea3583fa130d4702a05012a2103152daf51487 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/Activate.ps1 @@ -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)$Env:PATH" diff --git a/cmrithackathon-master/.venv/bin/activate b/cmrithackathon-master/.venv/bin/activate new file mode 100644 index 0000000000000000000000000000000000000000..a76fef7586917f89daba97711a68376c2eb15192 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/activate @@ -0,0 +1,69 @@ +# This file must be used with "source bin/activate" *from bash* +# you cannot run it directly + +deactivate () { + # reset old environment variables + if [ -n "${_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/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv" +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="(.venv) ${PS1:-}" + export PS1 + VIRTUAL_ENV_PROMPT="(.venv) " + 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 diff --git a/cmrithackathon-master/.venv/bin/activate.csh b/cmrithackathon-master/.venv/bin/activate.csh new file mode 100644 index 0000000000000000000000000000000000000000..eb68ddaaaf9f2561638442cc31d29d61338b3fa5 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/activate.csh @@ -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 . +# Ported to Python 3.3 venv by Andrew Svetlov + +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/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv" + +set _OLD_VIRTUAL_PATH="$PATH" +setenv PATH "$VIRTUAL_ENV/bin:$PATH" + + +set _OLD_VIRTUAL_PROMPT="$prompt" + +if (! "$?VIRTUAL_ENV_DISABLE_PROMPT") then + set prompt = "(.venv) $prompt" + setenv VIRTUAL_ENV_PROMPT "(.venv) " +endif + +alias pydoc python -m pydoc + +rehash diff --git a/cmrithackathon-master/.venv/bin/activate.fish b/cmrithackathon-master/.venv/bin/activate.fish new file mode 100644 index 0000000000000000000000000000000000000000..4b89558b5963a63d8a1061e6520cded3ee1bbb6e --- /dev/null +++ b/cmrithackathon-master/.venv/bin/activate.fish @@ -0,0 +1,69 @@ +# This file must be used with "source /bin/activate.fish" *from fish* +# (https://fishshell.com/); you cannot run it directly. + +function deactivate -d "Exit virtual environment and return to normal shell environment" + # reset old environment variables + if test -n "$_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" + set -e _OLD_FISH_PROMPT_OVERRIDE + # prevents error when using nested fish instances (Issue #93858) + if functions -q _old_fish_prompt + functions -e fish_prompt + functions -c _old_fish_prompt fish_prompt + functions -e _old_fish_prompt + end + 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/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv" + +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) "(.venv) " (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 "(.venv) " +end diff --git a/cmrithackathon-master/.venv/bin/f2py b/cmrithackathon-master/.venv/bin/f2py new file mode 100644 index 0000000000000000000000000000000000000000..c57c504694f08ade0aad6e339ce3ce639d16fd6e --- /dev/null +++ b/cmrithackathon-master/.venv/bin/f2py @@ -0,0 +1,8 @@ +#!/home/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv/bin/python +# -*- coding: utf-8 -*- +import re +import sys +from numpy.f2py.f2py2e import main +if __name__ == '__main__': + sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) + sys.exit(main()) diff --git a/cmrithackathon-master/.venv/bin/normalizer b/cmrithackathon-master/.venv/bin/normalizer new file mode 100644 index 0000000000000000000000000000000000000000..ca4da6b5b0411e579442f23e749041dd108e93c5 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/normalizer @@ -0,0 +1,8 @@ +#!/home/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv/bin/python +# -*- coding: utf-8 -*- +import re +import sys +from charset_normalizer.cli import cli_detect +if __name__ == '__main__': + sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) + sys.exit(cli_detect()) diff --git a/cmrithackathon-master/.venv/bin/numpy-config b/cmrithackathon-master/.venv/bin/numpy-config new file mode 100644 index 0000000000000000000000000000000000000000..e1c72abf35f56b68d98a86dbc84794c4ab8cb4d4 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/numpy-config @@ -0,0 +1,8 @@ +#!/home/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv/bin/python +# -*- coding: utf-8 -*- +import re +import sys +from numpy._configtool import main +if __name__ == '__main__': + sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) + sys.exit(main()) diff --git a/cmrithackathon-master/.venv/bin/pip b/cmrithackathon-master/.venv/bin/pip new file mode 100644 index 0000000000000000000000000000000000000000..47eb07a6d6c828ae4bcd2d0252e21bed26aa4151 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/pip @@ -0,0 +1,8 @@ +#!/home/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv/bin/python +# -*- coding: utf-8 -*- +import re +import sys +from pip._internal.cli.main import main +if __name__ == '__main__': + sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) + sys.exit(main()) diff --git a/cmrithackathon-master/.venv/bin/pip3 b/cmrithackathon-master/.venv/bin/pip3 new file mode 100644 index 0000000000000000000000000000000000000000..47eb07a6d6c828ae4bcd2d0252e21bed26aa4151 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/pip3 @@ -0,0 +1,8 @@ +#!/home/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv/bin/python +# -*- 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)?$', '', sys.argv[0]) + sys.exit(main()) diff --git a/cmrithackathon-master/.venv/bin/pip3.11 b/cmrithackathon-master/.venv/bin/pip3.11 new file mode 100644 index 0000000000000000000000000000000000000000..47eb07a6d6c828ae4bcd2d0252e21bed26aa4151 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/pip3.11 @@ -0,0 +1,8 @@ +#!/home/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv/bin/python +# -*- coding: utf-8 -*- +import re +import sys +from pip._internal.cli.main import main +if __name__ == '__main__': + sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) + sys.exit(main()) diff --git a/cmrithackathon-master/.venv/bin/python b/cmrithackathon-master/.venv/bin/python new file mode 100644 index 0000000000000000000000000000000000000000..b8a0adbbb97ea11f36eb0c6b2a3c2881e96f8e26 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/python @@ -0,0 +1 @@ +python3 \ No newline at end of file diff --git a/cmrithackathon-master/.venv/bin/python3 b/cmrithackathon-master/.venv/bin/python3 new file mode 100644 index 0000000000000000000000000000000000000000..898ccd71f956e4f2082ab44b96af396727adc676 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/python3 @@ -0,0 +1 @@ +/bin/python3 \ No newline at end of file diff --git a/cmrithackathon-master/.venv/bin/python3.11 b/cmrithackathon-master/.venv/bin/python3.11 new file mode 100644 index 0000000000000000000000000000000000000000..b8a0adbbb97ea11f36eb0c6b2a3c2881e96f8e26 --- /dev/null +++ b/cmrithackathon-master/.venv/bin/python3.11 @@ -0,0 +1 @@ +python3 \ No newline at end of file diff --git a/cmrithackathon-master/.venv/bin/tqdm b/cmrithackathon-master/.venv/bin/tqdm new file mode 100644 index 0000000000000000000000000000000000000000..ba01f1949cc23c78be5e13497787f082c9ad1e2b --- /dev/null +++ b/cmrithackathon-master/.venv/bin/tqdm @@ -0,0 +1,8 @@ +#!/home/nareshkarthigeyan/Naresh/cs/code/cmrithackathon/.venv/bin/python +# -*- coding: utf-8 -*- +import re +import sys +from tqdm.cli import main +if __name__ == '__main__': + sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) + sys.exit(main()) diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/__pycache__/six.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/__pycache__/six.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d2661bb64561def2427323b6b58c8bebf2870e8a Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/__pycache__/six.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__init__.py b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..f987a5367fdfaa4f17cd4bf700d56f4b50992368 --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__init__.py @@ -0,0 +1,222 @@ +# don't import any costly modules +import sys +import os + + +is_pypy = '__pypy__' in sys.builtin_module_names + + +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 + import warnings + + 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 + import warnings + + warnings.warn("Setuptools is replacing distutils.") + mods = [ + name + for name in sys.modules + if name == "distutils" or name.startswith("distutils.") + ] + for name in mods: + del sys.modules[name] + + +def enabled(): + """ + Allow selection of distutils by environment variable. + """ + which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'local') + return which == 'local' + + +def ensure_local_distutils(): + import importlib + + clear_distutils() + + # With the DistutilsMetaFinder in place, + # perform an import to cause distutils to be + # loaded from setuptools._distutils. Ref #2906. + with shim(): + importlib.import_module('distutils') + + # check that submodules load as expected + core = importlib.import_module('distutils.core') + assert '_distutils' in core.__file__, core.__file__ + assert 'setuptools._distutils.log' not in sys.modules + + +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 _TrivialRe: + def __init__(self, *patterns): + self._patterns = patterns + + def match(self, string): + return all(pat in string for pat in self._patterns) + + +class DistutilsMetaFinder: + def find_spec(self, fullname, path, target=None): + # optimization: only consider top level modules and those + # found in the CPython test suite. + if path is not None and not fullname.startswith('test.'): + return + + method_name = 'spec_for_{fullname}'.format(**locals()) + method = getattr(self, method_name, lambda: None) + return method() + + def spec_for_distutils(self): + if self.is_cpython(): + return + + import importlib + import importlib.abc + import importlib.util + + try: + mod = importlib.import_module('setuptools._distutils') + except Exception: + # There are a couple of cases where setuptools._distutils + # may not be present: + # - An older Setuptools without a local distutils is + # taking precedence. Ref #2957. + # - Path manipulation during sitecustomize removes + # setuptools from the path but only after the hook + # has been loaded. Ref #2980. + # In either case, fall back to stdlib behavior. + return + + class DistutilsLoader(importlib.abc.Loader): + def create_module(self, spec): + mod.__name__ = 'distutils' + return mod + + def exec_module(self, module): + pass + + return importlib.util.spec_from_loader( + 'distutils', DistutilsLoader(), origin=mod.__file__ + ) + + @staticmethod + def is_cpython(): + """ + Suppress supplying distutils for CPython (build and tests). + Ref #2965 and #3007. + """ + return os.path.isfile('pybuilddir.txt') + + 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 + + @classmethod + def pip_imported_during_build(cls): + """ + Detect if pip is being imported in a build script. Ref #2355. + """ + import traceback + + return any( + cls.frame_file_is_setup(frame) for frame, line in traceback.walk_stack(None) + ) + + @staticmethod + def frame_file_is_setup(frame): + """ + Return True if the indicated frame suggests a setup.py file. + """ + # some frames may not have __file__ (#2940) + return frame.f_globals.get('__file__', '').endswith('setup.py') + + def spec_for_sensitive_tests(self): + """ + Ensure stdlib distutils when running select tests under CPython. + + python/cpython#91169 + """ + clear_distutils() + self.spec_for_distutils = lambda: None + + sensitive_tests = ( + [ + 'test.test_distutils', + 'test.test_peg_generator', + 'test.test_importlib', + ] + if sys.version_info < (3, 10) + else [ + 'test.test_distutils', + ] + ) + + +for name in DistutilsMetaFinder.sensitive_tests: + setattr( + DistutilsMetaFinder, + f'spec_for_{name}', + DistutilsMetaFinder.spec_for_sensitive_tests, + ) + + +DISTUTILS_FINDER = DistutilsMetaFinder() + + +def add_shim(): + DISTUTILS_FINDER in sys.meta_path or insert_shim() + + +class shim: + def __enter__(self): + insert_shim() + + def __exit__(self, exc, value, tb): + remove_shim() + + +def insert_shim(): + sys.meta_path.insert(0, DISTUTILS_FINDER) + + +def remove_shim(): + try: + sys.meta_path.remove(DISTUTILS_FINDER) + except ValueError: + pass diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__pycache__/__init__.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__pycache__/__init__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1c8b96024ae10df0f52c70d3cacc3ef8c6fc9378 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__pycache__/__init__.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__pycache__/override.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__pycache__/override.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2169b8cb4a63bb9cf0e90e58462e4153115f9d35 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/__pycache__/override.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/override.py b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/override.py new file mode 100644 index 0000000000000000000000000000000000000000..2cc433a4a55e3b41fa31089918fb62096092f89f --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/_distutils_hack/override.py @@ -0,0 +1 @@ +__import__('_distutils_hack').do_override() diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/INSTALLER b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/INSTALLER new file mode 100644 index 0000000000000000000000000000000000000000..a1b589e38a32041e49332e5e81c2d363dc418d68 --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/INSTALLER @@ -0,0 +1 @@ +pip diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/METADATA b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/METADATA new file mode 100644 index 0000000000000000000000000000000000000000..a2681d725d16adcfced6185da1d25883c2a6323b --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/METADATA @@ -0,0 +1,122 @@ +Metadata-Version: 2.1 +Name: beautifulsoup4 +Version: 4.12.3 +Summary: Screen-scraping library +Project-URL: Download, https://www.crummy.com/software/BeautifulSoup/bs4/download/ +Project-URL: Homepage, https://www.crummy.com/software/BeautifulSoup/bs4/ +Author-email: Leonard Richardson +License: MIT License +License-File: AUTHORS +License-File: LICENSE +Keywords: HTML,XML,parse,soup +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 :: Software Development :: Libraries :: Python Modules +Classifier: Topic :: Text Processing :: Markup :: HTML +Classifier: Topic :: Text Processing :: Markup :: SGML +Classifier: Topic :: Text Processing :: Markup :: XML +Requires-Python: >=3.6.0 +Requires-Dist: soupsieve>1.2 +Provides-Extra: cchardet +Requires-Dist: cchardet; extra == 'cchardet' +Provides-Extra: chardet +Requires-Dist: chardet; extra == 'chardet' +Provides-Extra: charset-normalizer +Requires-Dist: charset-normalizer; extra == 'charset-normalizer' +Provides-Extra: html5lib +Requires-Dist: html5lib; extra == 'html5lib' +Provides-Extra: lxml +Requires-Dist: lxml; extra == 'lxml' +Description-Content-Type: text/markdown + +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("

SomebadHTML") +>>> print(soup.prettify()) + + +

+ Some + + bad + + HTML + + +

+ + +>>> soup.find(text="bad") +'bad' +>>> soup.i +HTML +# +>>> soup = BeautifulSoup("SomebadXML", "xml") +# +>>> print(soup.prettify()) + + + Some + + bad + + XML + + +``` + +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 +``` + diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/RECORD b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/RECORD new file mode 100644 index 0000000000000000000000000000000000000000..00bf6c46c69593a0731c77229bd7b77be1174377 --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/RECORD @@ -0,0 +1,79 @@ +beautifulsoup4-4.12.3.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +beautifulsoup4-4.12.3.dist-info/METADATA,sha256=UkOS1koIjlakIy9Q1u2yCNwDEFOUZSrLcsbV-mTInz4,3790 +beautifulsoup4-4.12.3.dist-info/RECORD,, +beautifulsoup4-4.12.3.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +beautifulsoup4-4.12.3.dist-info/WHEEL,sha256=mRYSEL3Ih6g5a_CVMIcwiF__0Ae4_gLYh01YFNwiq1k,87 +beautifulsoup4-4.12.3.dist-info/licenses/AUTHORS,sha256=uSIdbrBb1sobdXl7VrlUvuvim2dN9kF3MH4Edn0WKGE,2176 +beautifulsoup4-4.12.3.dist-info/licenses/LICENSE,sha256=VbTY1LHlvIbRDvrJG3TIe8t3UmsPW57a-LnNKtxzl7I,1441 +bs4/__init__.py,sha256=kq32cCtQiNjjU9XwjD0b1jdXN5WEC87nJqSSW3PhVkM,33822 +bs4/__pycache__/__init__.cpython-311.pyc,, +bs4/__pycache__/css.cpython-311.pyc,, +bs4/__pycache__/dammit.cpython-311.pyc,, +bs4/__pycache__/diagnose.cpython-311.pyc,, +bs4/__pycache__/element.cpython-311.pyc,, +bs4/__pycache__/formatter.cpython-311.pyc,, +bs4/builder/__init__.py,sha256=nwb35ftjcwzOs2WkjVm1zvfi7FxSyJP-nN1YheIVT14,24566 +bs4/builder/__pycache__/__init__.cpython-311.pyc,, +bs4/builder/__pycache__/_html5lib.cpython-311.pyc,, +bs4/builder/__pycache__/_htmlparser.cpython-311.pyc,, +bs4/builder/__pycache__/_lxml.cpython-311.pyc,, +bs4/builder/_html5lib.py,sha256=0w-hmPM5wWR2iDuRCR6MvY6ZPXbg_hgddym-YWqj03s,19114 +bs4/builder/_htmlparser.py,sha256=_VD5Z08j6A9YYMR4y7ZTfdMzwiCBsSUQAPuHiYB-WZI,14923 +bs4/builder/_lxml.py,sha256=yKdMx1kdX7H2CopwSWEYm4Sgrfkd-WDj8HbskcaLauU,14948 +bs4/css.py,sha256=gqGaHRrKeCRF3gDqxzeU0uclOCeSsTpuW9gUaSnJeWc,10077 +bs4/dammit.py,sha256=G0cQfsEqfwJ-FIQMkXgCJwSHMn7t9vPepCrud6fZEKk,41158 +bs4/diagnose.py,sha256=uAwdDugL_67tB-BIwDIFLFbiuzGxP2wQzJJ4_bGYUrA,7195 +bs4/element.py,sha256=Dsol2iehkSjk10GzYgwFyjUEgpqmYZpyaAmbL0rWM2w,92845 +bs4/formatter.py,sha256=Bu4utAQYT9XDJaPPpTRM-dyxJDVLdxf_as-IU5gSY8A,7188 +bs4/tests/__init__.py,sha256=NydTegds_r7MoOEuQLS6TFmTA9TwK3KxJhwEkqjCGTQ,48392 +bs4/tests/__pycache__/__init__.cpython-311.pyc,, +bs4/tests/__pycache__/test_builder.cpython-311.pyc,, +bs4/tests/__pycache__/test_builder_registry.cpython-311.pyc,, +bs4/tests/__pycache__/test_css.cpython-311.pyc,, +bs4/tests/__pycache__/test_dammit.cpython-311.pyc,, +bs4/tests/__pycache__/test_docs.cpython-311.pyc,, +bs4/tests/__pycache__/test_element.cpython-311.pyc,, +bs4/tests/__pycache__/test_formatter.cpython-311.pyc,, +bs4/tests/__pycache__/test_fuzz.cpython-311.pyc,, +bs4/tests/__pycache__/test_html5lib.cpython-311.pyc,, +bs4/tests/__pycache__/test_htmlparser.cpython-311.pyc,, +bs4/tests/__pycache__/test_lxml.cpython-311.pyc,, +bs4/tests/__pycache__/test_navigablestring.cpython-311.pyc,, +bs4/tests/__pycache__/test_pageelement.cpython-311.pyc,, +bs4/tests/__pycache__/test_soup.cpython-311.pyc,, +bs4/tests/__pycache__/test_tag.cpython-311.pyc,, +bs4/tests/__pycache__/test_tree.cpython-311.pyc,, +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-4670634698080256.testcase,sha256=yUdXkbpNK7LVOQ0LBHMoqZ1rWaBfSXWytoO_xdSm7Ho,15 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-4818336571064320.testcase,sha256=Uv_dx4a43TSfoNkjU-jHW2nSXkqHFg4XdAw7SWVObUk,23 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-4999465949331456.testcase,sha256=OEyVA0Ej4FxswOElrUNt0In4s4YhrmtaxE_NHGZvGtg,30 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5000587759190016.testcase,sha256=G4vpNBOz-RwMpi6ewEgNEa13zX0sXhmL7VHOyIcdKVQ,15347 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5167584867909632.testcase,sha256=3d8z65o4p7Rur-RmCHoOjzqaYQ8EAtjmiBYTHNyAdl4,19469 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5270998950477824.testcase,sha256=NfGIlit1k40Ip3mlnBkYOkIDJX6gHtjlErwl7gsBjAQ,12 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5375146639360000.testcase,sha256=xy4i1U0nhFHcnyc5pRKS6JRMvuoCNUur-Scor6UxIGw,4317 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5492400320282624.testcase,sha256=Q-UTYpQBUsWoMgIUspUlzveSI-41s4ABC3jajRb-K0o,11502 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5703933063462912.testcase,sha256=2bq3S8KxZgk8EajLReHD8m4_0Lj_nrkyJAxB_z_U0D0,5 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5843991618256896.testcase,sha256=MZDu31LPLfgu6jP9IZkrlwNes3f_sL8WFP5BChkUKdY,35 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5984173902397440.testcase,sha256=w58r-s6besG5JwPXpnz37W2YTj9-_qxFbk6hiEnKeIQ,51495 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6124268085182464.testcase,sha256=q8rkdMECEXKcqVhOf5zWHkSBTQeOPt0JiLg2TZiPCuk,10380 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6241471367348224.testcase,sha256=QfzoOxKwNuqG-4xIrea6MOQLXhfAAOQJ0r9u-J6kSNs,19 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6306874195312640.testcase,sha256=MJ2pHFuuCQUiQz1Kor2sof7LWeRERQ6QK43YNqQHg9o,47 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6450958476902400.testcase,sha256=EItOpSdeD4ewK-qgJ9vtxennwn_huguzXgctrUT7fqE,3546 +bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6600557255327744.testcase,sha256=a2aJTG4FceGSJXsjtxoS8S4jk_8rZsS3aznLkeO2_dY,124 +bs4/tests/fuzz/crash-0d306a50c8ed8bcd0785b67000fcd5dea1d33f08.testcase,sha256=jRFRtCKlP3-3EDLc_iVRTcE6JNymv0rYcVM6qRaPrxI,2607 +bs4/tests/fuzz/crash-ffbdfa8a2b26f13537b68d3794b0478a4090ee4a.testcase,sha256=7NsdCiXWAhNkmoW1pvF7rbZExyLAQIWtDtSHXIsH6YU,103 +bs4/tests/test_builder.py,sha256=nc2JE5EMrEf-p24qhf2R8qAV5PpFiOuNpYCmtmCjlTI,1115 +bs4/tests/test_builder_registry.py,sha256=7WLj2prjSHGphebnrjQuI6JYr03Uy_c9_CkaFSQ9HRo,5114 +bs4/tests/test_css.py,sha256=jCcgIWem3lyPa5AjhAk9S6fWI07hk1rg0v8coD7bEtI,17279 +bs4/tests/test_dammit.py,sha256=MbSmRN6VEP0Rm56-w6Ja0TW8eC-8ZxOJ-wXWVf_hRi8,15451 +bs4/tests/test_docs.py,sha256=xoAxnUfoQ7aRqGImwW_9BJDU8WNMZHIuvWqVepvWXt8,1127 +bs4/tests/test_element.py,sha256=92oRSRoGk8gIXAbAGHErKzocx2MK32TqcQdUJ-dGQMo,2377 +bs4/tests/test_formatter.py,sha256=eTzj91Lmhv90z-WiHjK3sBJZm0hRk0crFY1TZaXstCY,4148 +bs4/tests/test_fuzz.py,sha256=_K2utiYVkZ22mvh03g8CBioFU1QDJaff1vTaDyXhxNk,6972 +bs4/tests/test_html5lib.py,sha256=2-ipm-_MaPt37WTxEd5DodUTNhS4EbLFKPRaO6XSCW4,8322 +bs4/tests/test_htmlparser.py,sha256=wnngcIlzjEwH21JFfu_mgt6JdpLt0ncJfLcGT7HeGw0,6256 +bs4/tests/test_lxml.py,sha256=nQCmLt7bWk0id7xMumZw--PzEe1xF9PTQn3lvHyNC6I,7635 +bs4/tests/test_navigablestring.py,sha256=RGSgziNf7cZnYdEPsoqL1B2I68TUJp1JmEQVxbh_ryA,5081 +bs4/tests/test_pageelement.py,sha256=VdGjUxx3RhjqmNsJ92ao6VZC_YD7T8mdLkDZjosOYeE,14274 +bs4/tests/test_soup.py,sha256=JmnAPLE1_GXm0wmwEUN7icdvBz9HDch-qoU2mT_TDrs,19877 +bs4/tests/test_tag.py,sha256=FBPDUisDCbFmvl5HmTtN49CGo3YoUXh5Wiuw5FMLS5E,9616 +bs4/tests/test_tree.py,sha256=n9nTQOzJb3-ZnZ6AkmMdZQ5TYcTUPnqHoVgal0mYXfg,48129 diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/REQUESTED b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/REQUESTED new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/WHEEL b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/WHEEL new file mode 100644 index 0000000000000000000000000000000000000000..2860816abecb3c5ad7da6d018a4334b87e6b6cfc --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/WHEEL @@ -0,0 +1,4 @@ +Wheel-Version: 1.0 +Generator: hatchling 1.21.0 +Root-Is-Purelib: true +Tag: py3-none-any diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/licenses/AUTHORS b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/licenses/AUTHORS new file mode 100644 index 0000000000000000000000000000000000000000..1f14fe07de95f73646e1cfa5000a7b7ab45747d4 --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/licenses/AUTHORS @@ -0,0 +1,49 @@ +Behold, mortal, the origins of Beautiful Soup... +================================================ + +Leonard Richardson is the primary maintainer. + +Aaron DeVore and Isaac Muse have made significant contributions to the +code base. + +Mark Pilgrim provided the encoding detection code that forms the base +of UnicodeDammit. + +Thomas Kluyver and Ezio Melotti finished the work of getting Beautiful +Soup 4 working under Python 3. + +Simon Willison wrote soupselect, which was used to make Beautiful Soup +support CSS selectors. Isaac Muse wrote SoupSieve, which made it +possible to _remove_ the CSS selector code from Beautiful Soup. + +Sam Ruby helped with a lot of edge cases. + +Jonathan Ellis was awarded the prestigious Beau Potage D'Or for his +work in solving the nestable tags conundrum. + +An incomplete list of people have contributed patches to Beautiful +Soup: + + Istvan Albert, Andrew Lin, Anthony Baxter, Oliver Beattie, Andrew +Boyko, Tony Chang, Francisco Canas, "Delong", Zephyr Fang, Fuzzy, +Roman Gaufman, Yoni Gilad, Richie Hindle, Toshihiro Kamiya, Peteris +Krumins, Kent Johnson, Marek Kapolka, Andreas Kostyrka, Roel Kramer, +Ben Last, Robert Leftwich, Stefaan Lippens, "liquider", Staffan +Malmgren, Ksenia Marasanova, JP Moins, Adam Monsen, John Nagle, "Jon", +Ed Oskiewicz, Martijn Peters, Greg Phillips, Giles Radford, Stefano +Revera, Arthur Rudolph, Marko Samastur, James Salter, Jouni Seppänen, +Alexander Schmolck, Tim Shirley, Geoffrey Sneddon, Ville Skyttä, +"Vikas", Jens Svalgaard, Andy Theyers, Eric Weiser, Glyn Webster, John +Wiseman, Paul Wright, Danny Yoo + +An incomplete list of people who made suggestions or found bugs or +found ways to break Beautiful Soup: + + Hanno Böck, Matteo Bertini, Chris Curvey, Simon Cusack, Bruce Eckel, + Matt Ernst, Michael Foord, Tom Harris, Bill de hOra, Donald Howes, + Matt Patterson, Scott Roberts, Steve Strassmann, Mike Williams, + warchild at redho dot com, Sami Kuisma, Carlos Rocha, Bob Hutchison, + Joren Mc, Michal Migurski, John Kleven, Tim Heaney, Tripp Lilley, Ed + Summers, Dennis Sutch, Chris Smith, Aaron Swartz, Stuart + Turner, Greg Edwards, Kevin J Kalupson, Nikos Kouremenos, Artur de + Sousa Rocha, Yichun Wei, Per Vognsen diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/licenses/LICENSE b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/licenses/LICENSE new file mode 100644 index 0000000000000000000000000000000000000000..08e3a9cf8c7143d74a4c5716e8a4f00eb3caac41 --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/beautifulsoup4-4.12.3.dist-info/licenses/LICENSE @@ -0,0 +1,31 @@ +Beautiful Soup is made available under the MIT license: + + Copyright (c) Leonard Richardson + + Permission is hereby granted, free of charge, to any person obtaining + a copy of this software and associated documentation files (the + "Software"), to deal in the Software without restriction, including + without limitation the rights to use, copy, modify, merge, publish, + distribute, sublicense, and/or sell copies of the Software, and to + permit persons to whom the Software is furnished to do so, subject to + the following conditions: + + The above copyright notice and this permission notice shall be + included in all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + SOFTWARE. + +Beautiful Soup incorporates code from the html5lib library, which is +also made available under the MIT license. Copyright (c) James Graham +and other contributors + +Beautiful Soup has an optional dependency on the soupsieve library, +which is also made available under the MIT license. Copyright (c) +Isaac Muse diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__init__.py b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..d8ad5e1dc1c6a5e237260ba7b33a8efea958d877 --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__init__.py @@ -0,0 +1,840 @@ +"""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 3.6 and up. It works better if lxml +and/or html5lib is installed. + +For more than you ever wanted to know about Beautiful Soup, see the +documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/ +""" + +__author__ = "Leonard Richardson (leonardr@segfault.org)" +__version__ = "4.12.3" +__copyright__ = "Copyright (c) 2004-2024 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, + HTMLParserTreeBuilder +) +from .dammit import UnicodeDammit +from .element import ( + CData, + Comment, + CSS, + 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
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, stacklevel=3 + ) + 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 _clone(self): + """Create a new BeautifulSoup object with the same TreeBuilder, + but not associated with any markup. + + This is the first step of the deepcopy process. + """ + clone = type(self)("", None, self.builder) + + # Keep track of the encoding of the original document, + # since we won't be parsing it again. + clone.original_encoding = self.original_encoding + return clone + + 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'] = type(self.builder) + # Store the contents as a Unicode string. + d['contents'] = [] + d['markup'] = self.decode() + + # If _most_recent_element is present, it's a Tag object left + # over from initial parse. It might not be picklable and we + # don't need it. + if '_most_recent_element' in d: + del d['_most_recent_element'] + return d + + def __setstate__(self, state): + # If necessary, restore the TreeBuilder by looking it up. + self.__dict__ = state + if isinstance(self.builder, type): + self.builder = self.builder() + elif not self.builder: + # We don't know which builder was used to build this + # parse tree, so use a default we know is always available. + self.builder = HTMLParserTreeBuilder() + self.builder.soup = self + self.reset() + self._feed() + return state + + + @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, + stacklevel=3 + ) + 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, stacklevel=3 + ) + 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._most_recent_element = None + 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", iterator=None): + """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 = '\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, iterator) + +# 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, stacklevel=2 + ) + 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())) diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/__init__.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/__init__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..5feb20aed689a42cc763163453ad5bd289f6d0d1 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/__init__.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/css.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/css.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ab18be7af13c939a4a7ff14581f1fc9ffce38359 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/css.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/dammit.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/dammit.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..49c4797d90be1216ffea46bde1196e43fcb57c58 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/dammit.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/diagnose.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/diagnose.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2874313a1b642fb71f29a76b6787663ae64cb745 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/diagnose.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/element.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/element.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1d503a7515be35af919ffe1b99e9c775187fd2b3 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/element.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/formatter.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/formatter.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..61870e8a43beab402bb10d84d69a0cf306e47f17 Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/__pycache__/formatter.cpython-311.pyc differ diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/builder/__init__.py b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/builder/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..ffb31fc25ef3a089bbde5596199cc0c184bc04b2 --- /dev/null +++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/builder/__init__.py @@ -0,0 +1,636 @@ +# 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 = defaultdict(list) + + # 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 
 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 
 tag to be
+        an empty-element tag (it's not in
+        HTMLBuilder.empty_element_tags). This means an empty 
 tag
+        will be presented as "
", not "
" or "
".
+
+        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.
+        "" will become "", and "bar" 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  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 ( and ) 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 
 and
+            # 
+
This numeric entity is missing the final semicolon: 

+
+
a

+
This document contains (do you see it?)

+
This document ends with That attribute value was bogus

+The doctype is invalid because it contains extra whitespace
+
That boolean attribute had no value

+
Here's a nonexistent entity: &#foo; (do you see it?)

+
This document ends before the entity finishes: >
+
Paragraphs shouldn't contain block display elements, but this one does: 
you see?

+Multiple values for the same attribute.
+
Here's a table

+

+
This tag contains nothing but whitespace:     

+
This p tag is cut off by
the end of the blockquote tag

+
Here's a nested table:
foo
This table contains bare markup

+
+
This document contains a surprise doctype

+
+
Tag name contains Unicode characters

+
+
+"""
+
+
+class SoupTest(object):
+
+    @property
+    def default_builder(self):
+        return default_builder
+
+    def soup(self, markup, **kwargs):
+        """Build a Beautiful Soup object from markup."""
+        builder = kwargs.pop('builder', self.default_builder)
+        return BeautifulSoup(markup, builder=builder, **kwargs)
+
+    def document_for(self, markup, **kwargs):
+        """Turn an HTML fragment into a document.
+
+        The details depend on the builder.
+        """
+        return self.default_builder(**kwargs).test_fragment_to_document(markup)
+   
+    def assert_soup(self, to_parse, compare_parsed_to=None):
+        """Parse some markup using Beautiful Soup and verify that
+        the output markup is as expected.
+        """
+        builder = self.default_builder
+        obj = BeautifulSoup(to_parse, builder=builder)
+        if compare_parsed_to is None:
+            compare_parsed_to = to_parse
+
+        # Verify that the documents come out the same.
+        assert obj.decode() == self.document_for(compare_parsed_to)
+
+        # Also run some checks on the BeautifulSoup object itself:
+
+        # Verify that every tag that was opened was eventually closed.
+
+        # There are no tags in the open tag counter.
+        assert all(v==0 for v in list(obj.open_tag_counter.values()))
+
+        # The only tag in the tag stack is the one for the root
+        # document.
+        assert [obj.ROOT_TAG_NAME] == [x.name for x in obj.tagStack]
+
+    assertSoupEquals = assert_soup
+        
+    def assertConnectedness(self, element):
+        """Ensure that next_element and previous_element are properly
+        set for all descendants of the given element.
+        """
+        earlier = None
+        for e in element.descendants:
+            if earlier:
+                assert e == earlier.next_element
+                assert earlier == e.previous_element
+            earlier = e
+
+    def linkage_validator(self, el, _recursive_call=False):
+        """Ensure proper linkage throughout the document."""
+        descendant = None
+        # Document element should have no previous element or previous sibling.
+        # It also shouldn't have a next sibling.
+        if el.parent is None:
+            assert el.previous_element is None,\
+                "Bad previous_element\nNODE: {}\nPREV: {}\nEXPECTED: {}".format(
+                    el, el.previous_element, None
+                )
+            assert el.previous_sibling is None,\
+                "Bad previous_sibling\nNODE: {}\nPREV: {}\nEXPECTED: {}".format(
+                    el, el.previous_sibling, None
+                )
+            assert el.next_sibling is None,\
+                "Bad next_sibling\nNODE: {}\nNEXT: {}\nEXPECTED: {}".format(
+                    el, el.next_sibling, None
+                )
+
+        idx = 0
+        child = None
+        last_child = None
+        last_idx = len(el.contents) - 1
+        for child in el.contents:
+            descendant = None
+
+            # Parent should link next element to their first child
+            # That child should have no previous sibling
+            if idx == 0:
+                if el.parent is not None:
+                    assert el.next_element is child,\
+                       "Bad next_element\nNODE: {}\nNEXT: {}\nEXPECTED: {}".format(
+                            el, el.next_element, child
+                        )
+                    assert child.previous_element is el,\
+                       "Bad previous_element\nNODE: {}\nPREV: {}\nEXPECTED: {}".format(
+                            child, child.previous_element, el
+                        )
+                    assert child.previous_sibling is None,\
+                       "Bad previous_sibling\nNODE: {}\nPREV {}\nEXPECTED: {}".format(
+                            child, child.previous_sibling, None
+                        )
+
+            # If not the first child, previous index should link as sibling to this index
+            # Previous element should match the last index or the last bubbled up descendant
+            else:
+                assert child.previous_sibling is el.contents[idx - 1],\
+                    "Bad previous_sibling\nNODE: {}\nPREV {}\nEXPECTED {}".format(
+                        child, child.previous_sibling, el.contents[idx - 1]
+                    )
+                assert el.contents[idx - 1].next_sibling is child,\
+                    "Bad next_sibling\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
+                        el.contents[idx - 1], el.contents[idx - 1].next_sibling, child
+                    )
+
+                if last_child is not None:
+                    assert child.previous_element is last_child,\
+                        "Bad previous_element\nNODE: {}\nPREV {}\nEXPECTED {}\nCONTENTS {}".format(
+                            child, child.previous_element, last_child, child.parent.contents
+                        )
+                    assert last_child.next_element is child,\
+                        "Bad next_element\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
+                            last_child, last_child.next_element, child
+                        )
+
+            if isinstance(child, Tag) and child.contents:
+                descendant = self.linkage_validator(child, True)
+                # A bubbled up descendant should have no next siblings
+                assert descendant.next_sibling is None,\
+                    "Bad next_sibling\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
+                        descendant, descendant.next_sibling, None
+                    )
+
+            # Mark last child as either the bubbled up descendant or the current child
+            if descendant is not None:
+                last_child = descendant
+            else:
+                last_child = child
+
+            # If last child, there are non next siblings
+            if idx == last_idx:
+                assert child.next_sibling is None,\
+                    "Bad next_sibling\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
+                        child, child.next_sibling, None
+                    )
+            idx += 1
+
+        child = descendant if descendant is not None else child
+        if child is None:
+            child = el
+
+        if not _recursive_call and child is not None:
+            target = el
+            while True:
+                if target is None:
+                    assert child.next_element is None, \
+                        "Bad next_element\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
+                            child, child.next_element, None
+                        )
+                    break
+                elif target.next_sibling is not None:
+                    assert child.next_element is target.next_sibling, \
+                        "Bad next_element\nNODE: {}\nNEXT {}\nEXPECTED {}".format(
+                            child, child.next_element, target.next_sibling
+                        )
+                    break
+                target = target.parent
+
+            # We are done, so nothing to return
+            return None
+        else:
+            # Return the child to the recursive caller
+            return child
+
+    def assert_selects(self, tags, should_match):
+        """Make sure that the given tags have the correct text.
+
+        This is used in tests that define a bunch of tags, each
+        containing a single string, and then select certain strings by
+        some mechanism.
+        """
+        assert [tag.string for tag in tags] == should_match
+
+    def assert_selects_ids(self, tags, should_match):
+        """Make sure that the given tags have the correct IDs.
+
+        This is used in tests that define a bunch of tags, each
+        containing a single string, and then select certain strings by
+        some mechanism.
+        """
+        assert [tag['id'] for tag in tags] == should_match
+
+
+class TreeBuilderSmokeTest(object):
+    # Tests that are common to HTML and XML tree builders.
+
+    @pytest.mark.parametrize(
+        "multi_valued_attributes",
+        [None, {}, dict(b=['class']), {'*': ['notclass']}]
+    )
+    def test_attribute_not_multi_valued(self, multi_valued_attributes):
+        markup = ''
+        soup = self.soup(markup, multi_valued_attributes=multi_valued_attributes)
+        assert soup.a['class'] == 'a b c'
+
+    @pytest.mark.parametrize(
+        "multi_valued_attributes", [dict(a=['class']), {'*': ['class']}]
+    )
+    def test_attribute_multi_valued(self, multi_valued_attributes):
+        markup = ''
+        soup = self.soup(
+            markup, multi_valued_attributes=multi_valued_attributes
+        )
+        assert soup.a['class'] == ['a', 'b', 'c']
+
+    def test_invalid_doctype(self):
+        markup = 'content'
+        markup = ''
+        soup = self.soup(markup)
+
+class HTMLTreeBuilderSmokeTest(TreeBuilderSmokeTest):
+
+    """A basic test of a treebuilder's competence.
+
+    Any HTML treebuilder, present or future, should be able to pass
+    these tests. With invalid markup, there's room for interpretation,
+    and different parsers can handle it differently. But with the
+    markup in these tests, there's not much room for interpretation.
+    """
+
+    def test_empty_element_tags(self):
+        """Verify that all HTML4 and HTML5 empty element (aka void element) tags
+        are handled correctly.
+        """
+        for name in [
+                'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
+                'spacer', 'frame'
+        ]:
+            soup = self.soup("")
+            new_tag = soup.new_tag(name)
+            assert new_tag.is_empty_element == True
+
+    def test_special_string_containers(self):
+        soup = self.soup(
+            ""
+        )
+        assert isinstance(soup.style.string, Stylesheet)
+        assert isinstance(soup.script.string, Script)
+
+        soup = self.soup(
+            ""
+        )
+        assert isinstance(soup.style.string, Stylesheet)
+        # The contents of the style tag resemble an HTML comment, but
+        # it's not treated as a comment.
+        assert soup.style.string == ""
+        assert isinstance(soup.style.string, Stylesheet)
+        
+    def test_pickle_and_unpickle_identity(self):
+        # Pickling a tree, then unpickling it, yields a tree identical
+        # to the original.
+        tree = self.soup("foo")
+        dumped = pickle.dumps(tree, 2)
+        loaded = pickle.loads(dumped)
+        assert loaded.__class__ == BeautifulSoup
+        assert loaded.decode() == tree.decode()
+
+    def assertDoctypeHandled(self, doctype_fragment):
+        """Assert that a given doctype string is handled correctly."""
+        doctype_str, soup = self._document_with_doctype(doctype_fragment)
+
+        # Make sure a Doctype object was created.
+        doctype = soup.contents[0]
+        assert doctype.__class__ == Doctype
+        assert doctype == doctype_fragment
+        assert soup.encode("utf8")[:len(doctype_str)] == doctype_str
+
+        # Make sure that the doctype was correctly associated with the
+        # parse tree and that the rest of the document parsed.
+        assert soup.p.contents[0] == 'foo'
+
+    def _document_with_doctype(self, doctype_fragment, doctype_string="DOCTYPE"):
+        """Generate and parse a document with the given doctype."""
+        doctype = '' % (doctype_string, doctype_fragment)
+        markup = doctype + '\n
foo
'
+        soup = self.soup(markup)
+        return doctype.encode("utf8"), soup
+
+    def test_normal_doctypes(self):
+        """Make sure normal, everyday HTML doctypes are handled correctly."""
+        self.assertDoctypeHandled("html")
+        self.assertDoctypeHandled(
+            'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"')
+
+    def test_empty_doctype(self):
+        soup = self.soup("")
+        doctype = soup.contents[0]
+        assert "" == doctype.strip()
+
+    def test_mixed_case_doctype(self):
+        # A lowercase or mixed-case doctype becomes a Doctype.
+        for doctype_fragment in ("doctype", "DocType"):
+            doctype_str, soup = self._document_with_doctype(
+                "html", doctype_fragment
+            )
+
+            # Make sure a Doctype object was created and that the DOCTYPE
+            # is uppercase.
+            doctype = soup.contents[0]
+            assert doctype.__class__ == Doctype
+            assert doctype == "html"
+            assert soup.encode("utf8")[:len(doctype_str)] == b""
+
+            # Make sure that the doctype was correctly associated with the
+            # parse tree and that the rest of the document parsed.
+            assert soup.p.contents[0] == 'foo'
+        
+    def test_public_doctype_with_url(self):
+        doctype = 'html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"'
+        self.assertDoctypeHandled(doctype)
+
+    def test_system_doctype(self):
+        self.assertDoctypeHandled('foo SYSTEM "http://www.example.com/"')
+
+    def test_namespaced_system_doctype(self):
+        # We can handle a namespaced doctype with a system ID.
+        self.assertDoctypeHandled('xsl:stylesheet SYSTEM "htmlent.dtd"')
+
+    def test_namespaced_public_doctype(self):
+        # Test a namespaced doctype with a public id.
+        self.assertDoctypeHandled('xsl:stylesheet PUBLIC "htmlent.dtd"')
+
+    def test_real_xhtml_document(self):
+        """A real XHTML document should come out more or less the same as it went in."""
+        markup = b"""
+
+
+Hello.
+Goodbye.
+"""
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup(markup)
+        assert soup.encode("utf-8").replace(b"\n", b"") == markup.replace(b"\n", b"")
+
+        # No warning was issued about parsing an XML document as HTML,
+        # because XHTML is both.
+        assert w == []
+
+
+    def test_namespaced_html(self):
+        # When a namespaced XML document is parsed as HTML it should
+        # be treated as HTML with weird tag names.
+        markup = b"""content"""
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup(markup)
+
+        assert 2 == len(soup.find_all("ns1:foo"))
+            
+        # n.b. no "you're parsing XML as HTML" warning was given
+        # because there was no XML declaration.
+        assert [] == w
+
+    def test_detect_xml_parsed_as_html(self):
+        # A warning is issued when parsing an XML document as HTML,
+        # but basic stuff should still work.
+        markup = b"""string"""
+        with warnings.catch_warnings(record=True) as w:
+            soup = self.soup(markup)
+            assert soup.tag.string == 'string'
+        [warning] = w
+        assert isinstance(warning.message, XMLParsedAsHTMLWarning)
+        assert str(warning.message) == XMLParsedAsHTMLWarning.MESSAGE
+
+        # NOTE: the warning is not issued if the document appears to
+        # be XHTML (tested with test_real_xhtml_document in the
+        # superclass) or if there is no XML declaration (tested with
+        # test_namespaced_html in the superclass).
+        
+    def test_processing_instruction(self):
+        # We test both Unicode and bytestring to verify that
+        # process_markup correctly sets processing_instruction_class
+        # even when the markup is already Unicode and there is no
+        # need to process anything.
+        markup = """"""
+        soup = self.soup(markup)
+        assert markup == soup.decode()
+
+        markup = b""""""
+        soup = self.soup(markup)
+        assert markup == soup.encode("utf8")
+
+    def test_deepcopy(self):
+        """Make sure you can copy the tree builder.
+
+        This is important because the builder is part of a
+        BeautifulSoup object, and we want to be able to copy that.
+        """
+        copy.deepcopy(self.default_builder)
+
+    def test_p_tag_is_never_empty_element(self):
+        """A 
 tag is never designated as an empty-element tag.
+
+        Even if the markup shows it as an empty-element tag, it
+        shouldn't be presented that way.
+        """
+        soup = self.soup("
")
+        assert not soup.p.is_empty_element
+        assert str(soup.p) == "
"
+
+    def test_unclosed_tags_get_closed(self):
+        """A tag that's not closed by the end of the document should be closed.
+
+        This applies to all tags except empty-element tags.
+        """
+        self.assert_soup("
", "
")
+        self.assert_soup("", "")
+
+        self.assert_soup("
", "
")
+
+    def test_br_is_always_empty_element_tag(self):
+        """A 
 tag is designated as an empty-element tag.
+
+        Some parsers treat 

 as one 
 tag, some parsers as
+        two tags, but it should always be an empty-element tag.
+        """
+        soup = self.soup("

")
+        assert soup.br.is_empty_element
+        assert str(soup.br) == "
"
+
+    def test_nested_formatting_elements(self):
+        self.assert_soup("")
+
+    def test_double_head(self):
+        html = '''
+
+
+Ordinary HEAD element test
+
+
+
+Hello, world!
+
+
+'''
+        soup = self.soup(html)
+        assert "text/javascript" == soup.find('script')['type']
+
+    def test_comment(self):
+        # Comments are represented as Comment objects.
+        markup = "
foobaz
"
+        self.assert_soup(markup)
+
+        soup = self.soup(markup)
+        comment = soup.find(string="foobar")
+        assert comment.__class__ == Comment
+
+        # The comment is properly integrated into the tree.
+        foo = soup.find(string="foo")
+        assert comment == foo.next_element
+        baz = soup.find(string="baz")
+        assert comment == baz.previous_element
+
+    def test_preserved_whitespace_in_pre_and_textarea(self):
+        """Whitespace must be preserved in 
 and \n"
+        self.assert_soup(pre_markup)
+        self.assert_soup(textarea_markup)
+
+        soup = self.soup(pre_markup)
+        assert soup.pre.prettify() == pre_markup
+
+        soup = self.soup(textarea_markup)
+        assert soup.textarea.prettify() == textarea_markup
+
+        soup = self.soup("")
+        assert soup.textarea.prettify() == "\n"
+
+    def test_nested_inline_elements(self):
+        """Inline elements can be nested indefinitely."""
+        b_tag = "Inside a B tag"
+        self.assert_soup(b_tag)
+
+        nested_b_tag = "
A nested tag
"
+        self.assert_soup(nested_b_tag)
+
+        double_nested_b_tag = "
A doubly nested tag
"
+        self.assert_soup(nested_b_tag)
+
+    def test_nested_block_level_elements(self):
+        """Block elements can be nested."""
+        soup = self.soup('
Foo
')
+        blockquote = soup.blockquote
+        assert blockquote.p.b.string == 'Foo'
+        assert blockquote.b.string == 'Foo'
+
+    def test_correctly_nested_tables(self):
+        """One table can go inside another one."""
+        markup = (''
+                  ''
+                  "')
+
+        self.assert_soup(
+            markup,
+            '
Here's another table:"
+                  ''
+                  ''
+                  '
foo
Here\'s another table:'
+            '
foo
'
+            '
')
+
+        self.assert_soup(
+            ""
+            ""
+            "
Foo
Bar
Baz
")
+
+    def test_multivalued_attribute_with_whitespace(self):
+        # Whitespace separating the values of a multi-valued attribute
+        # should be ignored.
+
+        markup = '
'
+        soup = self.soup(markup)
+        assert ['foo', 'bar'] == soup.div['class']
+
+        # If you search by the literal name of the class it's like the whitespace
+        # wasn't there.
+        assert soup.div == soup.find('div', class_="foo bar")
+        
+    def test_deeply_nested_multivalued_attribute(self):
+        # html5lib can set the attributes of the same tag many times
+        # as it rearranges the tree. This has caused problems with
+        # multivalued attributes.
+        markup = '
'
+        soup = self.soup(markup)
+        assert ["css"] == soup.div.div['class']
+
+    def test_multivalued_attribute_on_html(self):
+        # html5lib uses a different API to set the attributes ot the
+        #  tag. This has caused problems with multivalued
+        # attributes.
+        markup = ''
+        soup = self.soup(markup)
+        assert ["a", "b"] == soup.html['class']
+
+    def test_angle_brackets_in_attribute_values_are_escaped(self):
+        self.assert_soup('', '')
+
+    def test_strings_resembling_character_entity_references(self):
+        # "&T" and "&p" look like incomplete character entities, but they are
+        # not.
+        self.assert_soup(
+            "
• AT&T is in the s&p 500
",
+            "
\u2022 AT&T is in the s&p 500
"
+        )
+
+    def test_apos_entity(self):
+        self.assert_soup(
+            "
Bob's Bar
",
+            "
Bob's Bar
",
+        )
+        
+    def test_entities_in_foreign_document_encoding(self):
+        # “ and ” are invalid numeric entities referencing
+        # Windows-1252 characters. - references a character common
+        # to Windows-1252 and Unicode, and ☃ references a
+        # character only found in Unicode.
+        #
+        # All of these entities should be converted to Unicode
+        # characters.
+        markup = "
“Hello” -☃
"
+        soup = self.soup(markup)
+        assert "“Hello†-☃" == soup.p.string
+        
+    def test_entities_in_attributes_converted_to_unicode(self):
+        expect = '
'
+        self.assert_soup('
', expect)
+        self.assert_soup('
', expect)
+        self.assert_soup('
', expect)
+        self.assert_soup('
', expect)
+
+    def test_entities_in_text_converted_to_unicode(self):
+        expect = '
pi\N{LATIN SMALL LETTER N WITH TILDE}ata
'
+        self.assert_soup("
piñata
", expect)
+        self.assert_soup("
piñata
", expect)
+        self.assert_soup("
piñata
", expect)
+        self.assert_soup("
piñata
", expect)
+
+    def test_quot_entity_converted_to_quotation_mark(self):
+        self.assert_soup("
I said "good day!"
",
+                              '
I said "good day!"
')
+
+    def test_out_of_range_entity(self):
+        expect = "\N{REPLACEMENT CHARACTER}"
+        self.assert_soup("�", expect)
+        self.assert_soup("�", expect)
+        self.assert_soup("�", expect)
+       
+    def test_multipart_strings(self):
+        "Mostly to prevent a recurrence of a bug in the html5lib treebuilder."
+        soup = self.soup("
\nfoo
")
+        assert "p" == soup.h2.string.next_element.name
+        assert "p" == soup.p.name
+        self.assertConnectedness(soup)
+
+    def test_empty_element_tags(self):
+        """Verify consistent handling of empty-element tags,
+        no matter how they come in through the markup.
+        """
+        self.assert_soup('


', "


")
+        self.assert_soup('


', "


")
+        
+    def test_head_tag_between_head_and_body(self):
+        "Prevent recurrence of a bug in the html5lib treebuilder."
+        content = """
+  
+  foo
+
+"""
+        soup = self.soup(content)
+        assert soup.html.body is not None
+        self.assertConnectedness(soup)
+
+    def test_multiple_copies_of_a_tag(self):
+        "Prevent recurrence of a bug in the html5lib treebuilder."
+        content = """
+
+ 
+   
+  
+
+"""
+        soup = self.soup(content)
+        self.assertConnectedness(soup.article)
+
+    def test_basic_namespaces(self):
+        """Parsers don't need to *understand* namespaces, but at the
+        very least they should not choke on namespaces or lose
+        data."""
+
+        markup = b'4'
+        soup = self.soup(markup)
+        assert markup == soup.encode()
+        html = soup.html
+        assert 'http://www.w3.org/1999/xhtml' == soup.html['xmlns']
+        assert 'http://www.w3.org/1998/Math/MathML' == soup.html['xmlns:mathml']
+        assert 'http://www.w3.org/2000/svg' == soup.html['xmlns:svg']
+
+    def test_multivalued_attribute_value_becomes_list(self):
+        markup = b''
+        soup = self.soup(markup)
+        assert ['foo', 'bar'] == soup.a['class']
+        
+    #
+    # Generally speaking, tests below this point are more tests of
+    # Beautiful Soup than tests of the tree builders. But parsers are
+    # weird, so we run these tests separately for every tree builder
+    # to detect any differences between them.
+    #
+
+    def test_can_parse_unicode_document(self):
+        # A seemingly innocuous document... but it's in Unicode! And
+        # it contains characters that can't be represented in the
+        # encoding found in the  declaration! The horror!
+        markup = 'Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!'
+        soup = self.soup(markup)
+        assert 'Sacr\xe9 bleu!' == soup.body.string
+
+    def test_soupstrainer(self):
+        """Parsers should be able to work with SoupStrainers."""
+        strainer = SoupStrainer("b")
+        soup = self.soup("A bold  statement",
+                         parse_only=strainer)
+        assert soup.decode() == "bold"
+
+    def test_single_quote_attribute_values_become_double_quotes(self):
+        self.assert_soup("",
+                              '')
+
+    def test_attribute_values_with_nested_quotes_are_left_alone(self):
+        text = """a"""
+        self.assert_soup(text)
+
+    def test_attribute_values_with_double_nested_quotes_get_quoted(self):
+        text = """a"""
+        soup = self.soup(text)
+        soup.foo['attr'] = 'Brawls happen at "Bob\'s Bar"'
+        self.assert_soup(
+            soup.foo.decode(),
+            """a""")
+
+    def test_ampersand_in_attribute_value_gets_escaped(self):
+        self.assert_soup('',
+                              '')
+
+        self.assert_soup(
+            'foo',
+            'foo')
+
+    def test_escaped_ampersand_in_attribute_value_is_left_alone(self):
+        self.assert_soup('')
+
+    def test_entities_in_strings_converted_during_parsing(self):
+        # Both XML and HTML entities are converted to Unicode characters
+        # during parsing.
+        text = "
<<sacré bleu!>>
"
+        expected = "
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
"
+        self.assert_soup(text, expected)
+
+    def test_smart_quotes_converted_on_the_way_in(self):
+        # Microsoft smart quotes are converted to Unicode characters during
+        # parsing.
+        quote = b"
\x91Foo\x92
"
+        soup = self.soup(quote)
+        assert soup.p.string == "\N{LEFT SINGLE QUOTATION MARK}Foo\N{RIGHT SINGLE QUOTATION MARK}"
+
+    def test_non_breaking_spaces_converted_on_the_way_in(self):
+        soup = self.soup("  ")
+        assert soup.a.string == "\N{NO-BREAK SPACE}" * 2
+
+    def test_entities_converted_on_the_way_out(self):
+        text = "
<<sacré bleu!>>
"
+        expected = "
<<sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!>>
".encode("utf-8")
+        soup = self.soup(text)
+        assert soup.p.encode("utf-8") == expected
+
+    def test_real_iso_8859_document(self):
+        # Smoke test of interrelated functionality, using an
+        # easy-to-understand document.
+
+        # Here it is in Unicode. Note that it claims to be in ISO-8859-1.
+        unicode_html = '
Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!
'
+
+        # That's because we're going to encode it into ISO-8859-1,
+        # and use that to test.
+        iso_latin_html = unicode_html.encode("iso-8859-1")
+
+        # Parse the ISO-8859-1 HTML.
+        soup = self.soup(iso_latin_html)
+
+        # Encode it to UTF-8.
+        result = soup.encode("utf-8")
+
+        # What do we expect the result to look like? Well, it would
+        # look like unicode_html, except that the META tag would say
+        # UTF-8 instead of ISO-8859-1.
+        expected = unicode_html.replace("ISO-8859-1", "utf-8")
+
+        # And, of course, it would be in UTF-8, not Unicode.
+        expected = expected.encode("utf-8")
+
+        # Ta-da!
+        assert result == expected
+
+    def test_real_shift_jis_document(self):
+        # Smoke test to make sure the parser can handle a document in
+        # Shift-JIS encoding, without choking.
+        shift_jis_html = (
+            b'
'
+            b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
+            b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
+            b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B'
+            b'
')
+        unicode_html = shift_jis_html.decode("shift-jis")
+        soup = self.soup(unicode_html)
+
+        # Make sure the parse tree is correctly encoded to various
+        # encodings.
+        assert soup.encode("utf-8") == unicode_html.encode("utf-8")
+        assert soup.encode("euc_jp") == unicode_html.encode("euc_jp")
+
+    def test_real_hebrew_document(self):
+        # A real-world test to make sure we can convert ISO-8859-9 (a
+        # Hebrew encoding) to UTF-8.
+        hebrew_document = b'Hebrew (ISO 8859-8) in Visual Directionality
Hebrew (ISO 8859-8) in Visual Directionality
\xed\xe5\xec\xf9'
+        soup = self.soup(
+            hebrew_document, from_encoding="iso8859-8")
+        # Some tree builders call it iso8859-8, others call it iso-8859-9.
+        # That's not a difference we really care about.
+        assert soup.original_encoding in ('iso8859-8', 'iso-8859-8')
+        assert soup.encode('utf-8') == (
+            hebrew_document.decode("iso8859-8").encode("utf-8")
+        )
+
+    def test_meta_tag_reflects_current_encoding(self):
+        # Here's the  tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '\n%s\n'
+            ''
+            'Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', {'http-equiv': 'Content-type'})
+        content = parsed_meta['content']
+        assert 'text/html; charset=x-sjis' == content
+
+        # But that value is actually a ContentMetaAttributeValue object.
+        assert isinstance(content, ContentMetaAttributeValue)
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        assert 'text/html; charset=utf8' == content.encode("utf8")
+
+        # For the rest of the story, see TestSubstitutions in
+        # test_tree.py.
+
+    def test_html5_style_meta_tag_reflects_current_encoding(self):
+        # Here's the  tag saying that a document is
+        # encoded in Shift-JIS.
+        meta_tag = ('')
+
+        # Here's a document incorporating that meta tag.
+        shift_jis_html = (
+            '\n%s\n'
+            ''
+            'Shift-JIS markup goes here.') % meta_tag
+        soup = self.soup(shift_jis_html)
+
+        # Parse the document, and the charset is seemingly unaffected.
+        parsed_meta = soup.find('meta', id="encoding")
+        charset = parsed_meta['charset']
+        assert 'x-sjis' == charset
+
+        # But that value is actually a CharsetMetaAttributeValue object.
+        assert isinstance(charset, CharsetMetaAttributeValue)
+
+        # And it will take on a value that reflects its current
+        # encoding.
+        assert 'utf8' == charset.encode("utf8")
+
+    def test_python_specific_encodings_not_used_in_charset(self):
+        # You can encode an HTML document using a Python-specific
+        # encoding, but that encoding won't be mentioned _inside_ the
+        # resulting document. Instead, the document will appear to
+        # have no encoding.
+        for markup in [
+            b''
+            b''
+        ]:
+            soup = self.soup(markup)
+            for encoding in PYTHON_SPECIFIC_ENCODINGS:
+                if encoding in (
+                    'idna', 'mbcs', 'oem', 'undefined',
+                    'string_escape', 'string-escape'
+                ):
+                    # For one reason or another, these will raise an
+                    # exception if we actually try to use them, so don't
+                    # bother.
+                    continue
+                encoded = soup.encode(encoding)
+                assert b'meta charset=""' in encoded
+                assert encoding.encode("ascii") not in encoded
+        
+    def test_tag_with_no_attributes_can_have_attributes_added(self):
+        data = self.soup("text")
+        data.a['foo'] = 'bar'
+        assert 'text' == data.a.decode()
+
+    def test_closing_tag_with_no_opening_tag(self):
+        # Without BeautifulSoup.open_tag_counter, the  tag will
+        # cause _popToTag to be called over and over again as we look
+        # for a  tag that wasn't there. The result is that 'text2'
+        # will show up outside the body of the document.
+        soup = self.soup("
text1
text2
")
+        assert "
text1
text2
" == soup.body.decode()
+        
+    def test_worst_case(self):
+        """Test the worst case (currently) for linking issues."""
+
+        soup = self.soup(BAD_DOCUMENT)
+        self.linkage_validator(soup)
+
+
+class XMLTreeBuilderSmokeTest(TreeBuilderSmokeTest):
+
+    def test_pickle_and_unpickle_identity(self):
+        # Pickling a tree, then unpickling it, yields a tree identical
+        # to the original.
+        tree = self.soup("foo")
+        dumped = pickle.dumps(tree, 2)
+        loaded = pickle.loads(dumped)
+        assert loaded.__class__ == BeautifulSoup
+        assert loaded.decode() == tree.decode()
+
+    def test_docstring_generated(self):
+        soup = self.soup("")
+        assert soup.encode() == b'\n'
+
+    def test_xml_declaration(self):
+        markup = b"""\n"""
+        soup = self.soup(markup)
+        assert markup == soup.encode("utf8")
+
+    def test_python_specific_encodings_not_used_in_xml_declaration(self):
+        # You can encode an XML document using a Python-specific
+        # encoding, but that encoding won't be mentioned _inside_ the
+        # resulting document.
+        markup = b"""\n"""
+        soup = self.soup(markup)
+        for encoding in PYTHON_SPECIFIC_ENCODINGS:
+            if encoding in (
+                'idna', 'mbcs', 'oem', 'undefined',
+                'string_escape', 'string-escape'
+            ):
+                # For one reason or another, these will raise an
+                # exception if we actually try to use them, so don't
+                # bother.
+                continue
+            encoded = soup.encode(encoding)
+            assert b'' in encoded
+            assert encoding.encode("ascii") not in encoded
+
+    def test_processing_instruction(self):
+        markup = b"""\n"""
+        soup = self.soup(markup)
+        assert markup == soup.encode("utf8")
+
+    def test_real_xhtml_document(self):
+        """A real XHTML document should come out *exactly* the same as it went in."""
+        markup = b"""
+
+
+Hello.
+Goodbye.
+"""
+        soup = self.soup(markup)
+        assert soup.encode("utf-8") == markup
+       
+    def test_nested_namespaces(self):
+        doc = b"""
+
+
+
+
+
+"""
+        soup = self.soup(doc)
+        assert doc == soup.encode()
+        
+    def test_formatter_processes_script_tag_for_xml_documents(self):
+        doc = """
+  
+"""
+        soup = BeautifulSoup(doc, "lxml-xml")
+        # lxml would have stripped this while parsing, but we can add
+        # it later.
+        soup.script.string = 'console.log("< < hey > > ");'
+        encoded = soup.encode()
+        assert b"< < hey > >" in encoded
+
+    def test_can_parse_unicode_document(self):
+        markup = 'Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!'
+        soup = self.soup(markup)
+        assert 'Sacr\xe9 bleu!' == soup.root.string
+
+    def test_can_parse_unicode_document_begining_with_bom(self):
+        markup = '\N{BYTE ORDER MARK}Sacr\N{LATIN SMALL LETTER E WITH ACUTE} bleu!'
+        soup = self.soup(markup)
+        assert 'Sacr\xe9 bleu!' == soup.root.string
+        
+    def test_popping_namespaced_tag(self):
+        markup = 'b2012-07-02T20:33:42Zcd'
+        soup = self.soup(markup)
+        assert str(soup.rss) == markup
+
+    def test_docstring_includes_correct_encoding(self):
+        soup = self.soup("")
+        assert soup.encode("latin1") == b'\n'
+
+    def test_large_xml_document(self):
+        """A large XML document should come out the same as it went in."""
+        markup = (b'\n'
+                  + b'0' * (2**12)
+                  + b'')
+        soup = self.soup(markup)
+        assert soup.encode("utf-8") == markup
+
+    def test_tags_are_empty_element_if_and_only_if_they_are_empty(self):
+        self.assert_soup("
", "
")
+        self.assert_soup("
foo
")
+
+    def test_namespaces_are_preserved(self):
+        markup = 'This tag is in the a namespaceThis tag is in the b namespace'
+        soup = self.soup(markup)
+        root = soup.root
+        assert "http://example.com/" == root['xmlns:a']
+        assert "http://example.net/" == root['xmlns:b']
+
+    def test_closing_namespaced_tag(self):
+        markup = '
20010504
'
+        soup = self.soup(markup)
+        assert str(soup.p) == markup
+
+    def test_namespaced_attributes(self):
+        markup = ''
+        soup = self.soup(markup)
+        assert str(soup.foo) == markup
+
+    def test_namespaced_attributes_xml_namespace(self):
+        markup = 'bar'
+        soup = self.soup(markup)
+        assert str(soup.foo) == markup
+
+    def test_find_by_prefixed_name(self):
+        doc = """
+
+    foo
+    bar
+    baz
+
+"""
+        soup = self.soup(doc)
+
+        # There are three  tags.
+        assert 3 == len(soup.find_all('tag'))
+
+        # But two of them are ns1:tag and one of them is ns2:tag.
+        assert 2 == len(soup.find_all('ns1:tag'))
+        assert 1 == len(soup.find_all('ns2:tag'))
+        
+        assert 1, len(soup.find_all('ns2:tag', key='value'))
+        assert 3, len(soup.find_all(['ns1:tag', 'ns2:tag']))
+        
+    def test_copy_tag_preserves_namespace(self):
+        xml = """
+"""
+    
+        soup = self.soup(xml)
+        tag = soup.document
+        duplicate = copy.copy(tag)
+
+        # The two tags have the same namespace prefix.
+        assert tag.prefix == duplicate.prefix
+
+    def test_worst_case(self):
+        """Test the worst case (currently) for linking issues."""
+
+        soup = self.soup(BAD_DOCUMENT)
+        self.linkage_validator(soup)
+
+
+class HTML5TreeBuilderSmokeTest(HTMLTreeBuilderSmokeTest):
+    """Smoke test for a tree builder that supports HTML5."""
+
+    def test_real_xhtml_document(self):
+        # Since XHTML is not HTML5, HTML5 parsers are not tested to handle
+        # XHTML documents in any particular way.
+        pass
+
+    def test_html_tags_have_namespace(self):
+        markup = ""
+        soup = self.soup(markup)
+        assert "http://www.w3.org/1999/xhtml" == soup.a.namespace
+
+    def test_svg_tags_have_namespace(self):
+        markup = ''
+        soup = self.soup(markup)
+        namespace = "http://www.w3.org/2000/svg"
+        assert namespace == soup.svg.namespace
+        assert namespace == soup.circle.namespace
+
+
+    def test_mathml_tags_have_namespace(self):
+        markup = '5'
+        soup = self.soup(markup)
+        namespace = 'http://www.w3.org/1998/Math/MathML'
+        assert namespace == soup.math.namespace
+        assert namespace == soup.msqrt.namespace
+
+    def test_xml_declaration_becomes_comment(self):
+        markup = ''
+        soup = self.soup(markup)
+        assert isinstance(soup.contents[0], Comment)
+        assert soup.contents[0] == '?xml version="1.0" encoding="utf-8"?'
+        assert "html" == soup.contents[0].next_element.name
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/__init__.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/__init__.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..81099df623ecdeb056ba0938ea6929beecb576c9
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/__init__.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_builder.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_builder.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..8bbf9590fe377b14359a429b7156707565b6d8b5
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_builder.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_builder_registry.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_builder_registry.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..3485ad63e1fa043a37abf70ebcfece1cdd1b41c6
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_builder_registry.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_css.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_css.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..1244793eb6bd8cb6ea129fee5bd48e50efec56f6
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_css.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_dammit.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_dammit.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..a6c4f1dac0eb74668940399ec8d2764601e909ba
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_dammit.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_docs.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_docs.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..7851549d06677aa0c4e94a8418c21f736d8999bd
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_docs.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_element.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_element.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..660b39c59f1b21b8332ce0b1e926a8a0a1a71402
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_element.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_formatter.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_formatter.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..765f5d35e7bd2bb52225e5558353467cf074faa1
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_formatter.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_fuzz.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_fuzz.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..62e17031b0f6be21b15a92911f174c0f3a8535af
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_fuzz.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_html5lib.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_html5lib.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..fd03b28334eb3f808a6a263f7f2cae88f5e93f1f
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_html5lib.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_htmlparser.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_htmlparser.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..198ecc3a74a28cebee46d3aa25eca755128a6993
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_htmlparser.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_lxml.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_lxml.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..e1164625946c7a120619bf193aaeff03c04e1886
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_lxml.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_navigablestring.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_navigablestring.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..1c3132a9deb6f313734edcd74341d5ea7f469b02
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_navigablestring.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_pageelement.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_pageelement.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..6ab3545acdd2aa3013f614b9a78be3fe31037e43
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_pageelement.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_soup.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_soup.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..cd46e64f68e33b80bbf5ae56d91446f52568d11d
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_soup.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_tag.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_tag.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..3f18efcfe0f72a847fdff42646bb69bdb5242910
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_tag.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_tree.cpython-311.pyc b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_tree.cpython-311.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..5f537ad0a87b85837d3fead89ac2df229708cc0c
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/__pycache__/test_tree.cpython-311.pyc differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-4670634698080256.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-4670634698080256.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..4828f8a4238386304bd8a9c74a0ac83cba211e70
--- /dev/null
+++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-4670634698080256.testcase
@@ -0,0 +1 @@
+ ÿÿ      ÿ 

\ No newline at end of file
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5000587759190016.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5000587759190016.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..8a585ce9270e58b125922297f2d099298adac822
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5000587759190016.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5167584867909632.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5167584867909632.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..0fe66dd23fe94a8e451dfb1a84da38ed0984c1f9
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5167584867909632.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5270998950477824.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5270998950477824.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..fd411427d765e9b17e1e6a015485a70632bb9554
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5270998950477824.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5375146639360000.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5375146639360000.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..6248b2c54f4f80460c55c03302f6afd6ace6b0b3
--- /dev/null
+++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5375146639360000.testcase
@@ -0,0 +1 @@
+ÿ                 >tet><
\ No newline at end of file
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5492400320282624.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5492400320282624.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..107da539fc15bd1664e35287ace9feda21cb5820
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5492400320282624.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5703933063462912.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5703933063462912.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..367106c76f6408cd57cd51e622cf01a9903e5f34
--- /dev/null
+++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-5703933063462912.testcase
@@ -0,0 +1,2 @@
+
+t
\ No newline at end of file
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6450958476902400.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6450958476902400.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..a823d557b4bebed8a9cdb880d281c9de69a1aa0a
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6450958476902400.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6600557255327744.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6600557255327744.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..65af44d8c1bdb043fa6810902e1ce623533bd34a
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/clusterfuzz-testcase-minimized-bs4_fuzzer-6600557255327744.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/crash-0d306a50c8ed8bcd0785b67000fcd5dea1d33f08.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/crash-0d306a50c8ed8bcd0785b67000fcd5dea1d33f08.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..5559adbb352524a8992fcae8243952cb82d01d27
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/crash-0d306a50c8ed8bcd0785b67000fcd5dea1d33f08.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/crash-ffbdfa8a2b26f13537b68d3794b0478a4090ee4a.testcase b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/crash-ffbdfa8a2b26f13537b68d3794b0478a4090ee4a.testcase
new file mode 100644
index 0000000000000000000000000000000000000000..885711554056588a381fd9a251d48ce76a916a59
Binary files /dev/null and b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/fuzz/crash-ffbdfa8a2b26f13537b68d3794b0478a4090ee4a.testcase differ
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_builder.py b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_builder.py
new file mode 100644
index 0000000000000000000000000000000000000000..75370712a8c38162b167b1ee358e4adc75c6fff2
--- /dev/null
+++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_builder.py
@@ -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),
+         ("obviously HTMLActually XHTML", False),
+         ("            <    html>Tricky XHTML", False),
+         ("", 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()
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_builder_registry.py b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_builder_registry.py
new file mode 100644
index 0000000000000000000000000000000000000000..9327174f3775a763f5379eeaafddbd6cf1c69c52
--- /dev/null
+++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_builder_registry.py
@@ -0,0 +1,137 @@
+"""Tests of the builder registry."""
+
+import pytest
+import warnings
+
+from bs4 import BeautifulSoup
+from bs4.builder import (
+    builder_registry as registry,
+    HTMLParserTreeBuilder,
+    TreeBuilderRegistry,
+)
+
+from . import (
+    HTML5LIB_PRESENT,
+    LXML_PRESENT,
+)
+
+if HTML5LIB_PRESENT:
+    from bs4.builder import HTML5TreeBuilder
+
+if LXML_PRESENT:
+    from bs4.builder import (
+        LXMLTreeBuilderForXML,
+        LXMLTreeBuilder,
+        )
+
+
+# TODO: Split out the lxml and html5lib tests into their own classes
+# and gate with pytest.mark.skipIf.
+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
diff --git a/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_css.py b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_css.py
new file mode 100644
index 0000000000000000000000000000000000000000..359dbcd246168d3e81968341cf3412077ccbd3b7
--- /dev/null
+++ b/cmrithackathon-master/.venv/lib/python3.11/site-packages/bs4/tests/test_css.py
@@ -0,0 +1,487 @@
+import pytest
+import types
+from unittest.mock import MagicMock
+
+from bs4 import (
+    CSS,
+    BeautifulSoup,
+    ResultSet,
+)
+
+from . import (
+    SoupTest,
+    SOUP_SIEVE_PRESENT,
+)
+
+if SOUP_SIEVE_PRESENT:
+    from soupsieve import SelectorSyntaxError
+
+
+@pytest.mark.skipif(not SOUP_SIEVE_PRESENT, reason="Soup Sieve not installed")
+class TestCSSSelectors(SoupTest):
+    """Test basic CSS selector functionality.
+
+    This functionality is implemented in soupsieve, which has a much
+    more comprehensive test suite, so this is basically an extra check
+    that soupsieve works as expected.
+    """
+
+    HTML = """
+
+
+
+The title
+
+
+
+Hello there.
+

+

+
An H1

+
Some text

+
Some more text

+
An H2

+
Another

+Bob
+
Another H2

+me
+
+span1a1
+span1a2 test
+
+span2a1
+
+
+
+

+
+

+
+
+
+
+
+
+
+
+
English

+
English UK

+
English US

+
French

+

+
+
+"""
+
+    def setup_method(self):
+        self.soup = BeautifulSoup(self.HTML, 'html.parser')
+
+    def assert_selects(self, selector, expected_ids, **kwargs):
+        results = self.soup.select(selector, **kwargs)
+        assert isinstance(results, ResultSet)
+        el_ids = [el['id'] for el in results]
+        el_ids.sort()
+        expected_ids.sort()
+        assert expected_ids == el_ids, "Selector %s, expected [%s], got [%s]" % (
+                selector, ', '.join(expected_ids), ', '.join(el_ids)
+        )
+
+    assertSelect = assert_selects
+
+    def assert_select_multiple(self, *tests):
+        for selector, expected_ids in tests:
+            self.assert_selects(selector, expected_ids)
+
+    def test_precompiled(self):
+        sel = self.soup.css.compile('div')
+
+        els = self.soup.select(sel)
+        assert len(els) == 4
+        for div in els:
+            assert div.name == 'div'
+
+        el = self.soup.select_one(sel)
+        assert 'main' == el['id']
+
+    def test_one_tag_one(self):
+        els = self.soup.select('title')
+        assert len(els) == 1
+        assert els[0].name == 'title'
+        assert els[0].contents == ['The title']
+
+    def test_one_tag_many(self):
+        els = self.soup.select('div')
+        assert len(els) == 4
+        for div in els:
+            assert div.name == 'div'
+
+        el = self.soup.select_one('div')
+        assert 'main' == el['id']
+
+    def test_select_one_returns_none_if_no_match(self):
+        match = self.soup.select_one('nonexistenttag')
+        assert None == match
+
+
+    def test_tag_in_tag_one(self):
+        els = self.soup.select('div div')
+        self.assert_selects('div div', ['inner', 'data1'])
+
+    def test_tag_in_tag_many(self):
+        for selector in ('html div', 'html body div', 'body div'):
+            self.assert_selects(selector, ['data1', 'main', 'inner', 'footer'])
+
+
+    def test_limit(self):
+        self.assert_selects('html div', ['main'], limit=1)
+        self.assert_selects('html body div', ['inner', 'main'], limit=2)
+        self.assert_selects('body div', ['data1', 'main', 'inner', 'footer'],
+                           limit=10)
+
+    def test_tag_no_match(self):
+        assert len(self.soup.select('del')) == 0
+
+    def test_invalid_tag(self):
+        with pytest.raises(SelectorSyntaxError):
+            self.soup.select('tag%t')
+
+    def test_select_dashed_tag_ids(self):
+        self.assert_selects('custom-dashed-tag', ['dash1', 'dash2'])
+
+    def test_select_dashed_by_id(self):
+        dashed = self.soup.select('custom-dashed-tag[id=\"dash2\"]')
+        assert dashed[0].name == 'custom-dashed-tag'
+        assert dashed[0]['id'] == 'dash2'
+
+    def test_dashed_tag_text(self):
+        assert self.soup.select('body > custom-dashed-tag')[0].text == 'Hello there.'
+
+    def test_select_dashed_matches_find_all(self):
+        assert self.soup.select('custom-dashed-tag') == self.soup.find_all('custom-dashed-tag')
+
+    def test_header_tags(self):
+        self.assert_select_multiple(
+            ('h1', ['header1']),
+            ('h2', ['header2', 'header3']),
+        )
+
+    def test_class_one(self):
+        for selector in ('.onep', 'p.onep', 'html p.onep'):
+            els = self.soup.select(selector)
+            assert len(els) == 1
+            assert els[0].name == 'p'
+            assert els[0]['class'] == ['onep']
+
+    def test_class_mismatched_tag(self):
+        els = self.soup.select('div.onep')
+        assert len(els) == 0
+
+    def test_one_id(self):
+        for selector in ('div#inner', '#inner', 'div div#inner'):
+            self.assert_selects(selector, ['inner'])
+
+    def test_bad_id(self):
+        els = self.soup.select('#doesnotexist')
+        assert len(els) == 0
+
+    def test_items_in_id(self):
+        els = self.soup.select('div#inner p')
+        assert len(els) == 3
+        for el in els:
+            assert el.name == 'p'
+        assert els[1]['class'] == ['onep']
+        assert not els[0].has_attr('class')
+
+    def test_a_bunch_of_emptys(self):
+        for selector in ('div#main del', 'div#main div.oops', 'div div#main'):
+            assert len(self.soup.select(selector)) == 0
+
+    def test_multi_class_support(self):
+        for selector in ('.class1', 'p.class1', '.class2', 'p.class2',
+            '.class3', 'p.class3', 'html p.class2', 'div#inner .class2'):
+            self.assert_selects(selector, ['pmulti'])
+
+    def test_multi_class_selection(self):
+        for selector in ('.class1.class3', '.class3.class2',
+                         '.class1.class2.class3'):
+            self.assert_selects(selector, ['pmulti'])
+
+    def test_child_selector(self):
+        self.assert_selects('.s1 > a', ['s1a1', 's1a2'])
+        self.assert_selects('.s1 > a span', ['s1a2s1'])
+
+    def test_child_selector_id(self):
+        self.assert_selects('.s1 > a#s1a2 span', ['s1a2s1'])
+
+    def test_attribute_equals(self):
+        self.assert_select_multiple(
+            ('p[class="onep"]', ['p1']),
+            ('p[id="p1"]', ['p1']),
+            ('[class="onep"]', ['p1']),
+            ('[id="p1"]', ['p1']),
+            ('link[rel="stylesheet"]', ['l1']),
+            ('link[type="text/css"]', ['l1']),
+            ('link[href="blah.css"]', ['l1']),
+            ('link[href="no-blah.css"]', []),
+            ('[rel="stylesheet"]', ['l1']),
+            ('[type="text/css"]', ['l1']),
+            ('[href="blah.css"]', ['l1']),
+            ('[href="no-blah.css"]', []),
+            ('p[href="no-blah.css"]', []),
+            ('[href="no-blah.css"]', []),
+        )
+
+    def test_attribute_tilde(self):
+        self.assert_select_multiple(
+            ('p[class~="class1"]', ['pmulti']),
+            ('p[class~="class2"]', ['pmulti']),
+            ('p[class~="class3"]', ['pmulti']),
+            ('[class~="class1"]', ['pmulti']),
+            ('[class~="class2"]', ['pmulti']),
+            ('[class~="class3"]', ['pmulti']),
+            ('a[rel~="friend"]', ['bob']),
+            ('a[rel~="met"]', ['bob']),
+            ('[rel~="friend"]', ['bob']),
+            ('[rel~="met"]', ['bob']),
+        )
+
+    def test_attribute_startswith(self):
+        self.assert_select_multiple(
+            ('[rel^="style"]', ['l1']),
+            ('link[rel^="style"]', ['l1']),
+            ('notlink[rel^="notstyle"]', []),
+            ('[rel^="notstyle"]', []),
+            ('link[rel^="notstyle"]', []),
+            ('link[href^="bla"]', ['l1']),
+            ('a[href^="http://"]', ['bob', 'me']),
+            ('[href^="http://"]', ['bob', 'me']),
+            ('[id^="p"]', ['pmulti', 'p1']),
+            ('[id^="m"]', ['me', 'main']),
+            ('div[id^="m"]', ['main']),
+            ('a[id^="m"]', ['me']),
+            ('div[data-tag^="dashed"]', ['data1'])
+        )
+
+    def test_attribute_endswith(self):
+        self.assert_select_multiple(
+            ('[href$=".css"]', ['l1']),
+            ('link[href$=".css"]', ['l1']),
+            ('link[id$="1"]', ['l1']),
+            ('[id$="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's2a1', 's1a2s1', 'dash1']),
+            ('div[id$="1"]', ['data1']),
+            ('[id$="noending"]', []),
+        )
+
+    def test_attribute_contains(self):
+        self.assert_select_multiple(
+            # From test_attribute_startswith
+            ('[rel*="style"]', ['l1']),
+            ('link[rel*="style"]', ['l1']),
+            ('notlink[rel*="notstyle"]', []),
+            ('[rel*="notstyle"]', []),
+            ('link[rel*="notstyle"]', []),
+            ('link[href*="bla"]', ['l1']),
+            ('[href*="http://"]', ['bob', 'me']),
+            ('[id*="p"]', ['pmulti', 'p1']),
+            ('div[id*="m"]', ['main']),
+            ('a[id*="m"]', ['me']),
+            # From test_attribute_endswith
+            ('[href*=".css"]', ['l1']),
+            ('link[href*=".css"]', ['l1']),
+            ('link[id*="1"]', ['l1']),
+            ('[id*="1"]', ['data1', 'l1', 'p1', 'header1', 's1a1', 's1a2', 's2a1', 's1a2s1', 'dash1']),
+            ('div[id*="1"]', ['data1']),
+            ('[id*="noending"]', []),
+            # New for this test
+            ('[href*="."]', ['bob', 'me', 'l1']),
+            ('a[href*="."]', ['bob', 'me']),
+            ('link[href*="."]', ['l1']),
+            ('div[id*="n"]', ['main', 'inner']),
+            ('div[id*="nn"]', ['inner']),
+            ('div[data-tag*="edval"]', ['data1'])
+        )
+
+    def test_attribute_exact_or_hypen(self):
+        self.assert_select_multiple(
+            ('p[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
+            ('[lang|="en"]', ['lang-en', 'lang-en-gb', 'lang-en-us']),
+            ('p[lang|="fr"]', ['lang-fr']),
+            ('p[lang|="gb"]', []),
+        )
+
+    def test_attribute_exists(self):
+        self.assert_select_multiple(
+            ('[rel]', ['l1', 'bob', 'me']),
+            ('link[rel]', ['l1']),
+            ('a[rel]', ['bob', 'me']),
+            ('[lang]', ['lang-en', 'lang-en-gb', 'lang-en-us', 'lang-fr']),
+            ('p[class]', ['p1', 'pmulti']),
+            ('[blah]', []),
+            ('p[blah]', []),
+            ('div[data-tag]', ['data1'])
+        )
+
+    def test_quoted_space_in_selector_name(self):
+        html = """
nope

+        
yes

+        """
+        soup = BeautifulSoup(html, 'html.parser')
+        [chosen] = soup.select('div[style="display: right"]')
+        assert "yes" == chosen.string
+
+    def test_unsupported_pseudoclass(self):
+        with pytest.raises(NotImplementedError):
+            self.soup.select("a:no-such-pseudoclass")
+
+        with pytest.raises(SelectorSyntaxError):
+            self.soup.select("a:nth-of-type(a)")
+
+    def test_nth_of_type(self):
+        # Try to select first paragraph
+        els = self.soup.select('div#inner p:nth-of-type(1)')
+        assert len(els) == 1
+        assert els[0].string == 'Some text'
+
+        # Try to select third paragraph
+        els = self.soup.select('div#inner p:nth-of-type(3)')
+        assert len(els) == 1
+        assert els[0].string == 'Another'
+
+        # Try to select (non-existent!) fourth paragraph
+        els = self.soup.select('div#inner p:nth-of-type(4)')
+        assert len(els) == 0
+
+        # Zero will select no tags.
+        els = self.soup.select('div p:nth-of-type(0)')
+        assert len(els) == 0
+
+    def test_nth_of_type_direct_descendant(self):
+        els = self.soup.select('div#inner > p:nth-of-type(1)')
+        assert len(els) == 1
+        assert els[0].string == 'Some text'
+
+    def test_id_child_selector_nth_of_type(self):
+        self.assert_selects('#inner > p:nth-of-type(2)', ['p1'])
+
+    def test_select_on_element(self):
+        # Other tests operate on the tree; this operates on an element
+        # within the tree.
+        inner = self.soup.find("div", id="main")
+        selected = inner.select("div")
+        # The 
 tag was selected. The