powershell pdf/word parser

gistfile1.txt

$pyscript = "C:\Users\324240\Desktop\pdfminer-master\tools\pdf2txt.py"
$input_folder = "C:\Users\324240\Desktop\Markets Surveillance Meetings\"
 
$output_folder = ($input_folder+"test\")
 
## Python pdf converter
## Uses the python library here https://github.com/euske/pdfminer/tree/master/tools
#Get-ChildItem $folder -Filter *.pdf | `
#Foreach-Object{
#    print ($input_folder+$_.BaseName)
#    python $pyscript $_.FullName | Out-File ($folder+"output\"+$_.BaseName+".txt")
#}

## grep method for word documents
## from here https://woozle.org/neale/papers/docx.html
## - requires unzip for windows
Get-ChildItem $input_folder -Filter *.docx | `
Foreach-Object{
    unzip -qc $_.FullName | grep '<w:t' | sed 's/<[^<]*>//g' | grep -v '^[[:space:]]*$' | Out-File ($output_folder+$_.BaseName+".txt")
}

## powershell method for word documents
## TODO: fix 
#Get-ChildItem $folder -Filter *.docx | `
#Foreach-Object{
#    $objWord = New-Object -Com Word.Application
#    $objWord.Visible = $false
#    $objDocument = $objWord.Documents.Open(($folder+$_.FullName))
#    $paras = $objDocument.Paragraphs
#    foreach ($para in $paras)
#    {
#        print $para.Range.Text
#    }
#}