Powershell Parsing+Batch-Processor

English: https://neculaifantanaru.com/en/creating-a-batch-processing-powershell-with-regex-and-html-tags-parsing.html
Romanian: https://neculaifantanaru.com/creating-a-batch-processing-powershell-with-regex-and-html-tags-parsing.html


$sourcedir = "C:\Folder1\"
$resultsdir = "C:\Folder1\"

Get-ChildItem -Path $sourcedir -Filter *.html | ForEach-Object {
    $content = Get-Content -Path $_.FullName -Raw

# Copy the content of the tag <link rel="canonical"  in the tag "OG:URL" and in the tag  "@ID":             #

    $replaceValue = (Select-String -InputObject $content -Pattern '(?<=<link rel="canonical" href=").*(")').Matches.Value
    $content = $content -replace '(?<=<meta property="og:url" content=").*(")',$replaceValue
    $content = $content -replace '(?<="@id": ").*(")',$replaceValue

# Copy the content of the tag <title>  in the tags ABSTRACT, SUBJECT, OG:TITLE, HEADLINE, KEYWORDS            #

    $replaceValue = (Select-String -InputObject $content -Pattern '(?<=<title>).+(?=</title>)').Matches.Value
    $content = $content -replace '(?<=<meta property="og:title" content=").+(?=")',$replaceValue
    $content = $content -replace '(?<=<meta name="abstract" content=").+(?=")',$replaceValue
    $content = $content -replace '(?<=<meta name="keywords" content=").+(?=")',$replaceValue
    $content = $content -replace '(?<=<meta name="Subject" content=").+(?=")',$replaceValue
    $content = $content -replace '(?<="headline": ").+(?=")',$replaceValue
    $content = $content -replace '(?<="keywords": ").+(?=")',$replaceValue

# Copy the content of the tag <meta name="description"  in the tags "OG:DESCRIPTION" and in the tag "description": "        #

    $replaceValue = (Select-String -InputObject $content -Pattern '(?<=<meta name="description" content=").+(?=")').Matches.Value
    $content = $content -replace '(?<=<meta property="og:description" content=").+(?=")',$replaceValue
    $content = $content -replace '(?<="description": ").+(?=")',$replaceValue

   Set-Content -Path $resultsdir\$($_.name) $content
}