shell html table转csv,powershell

You need to quote the values you are retrieving from the cells.

Something like this should work:

# load the System.Web assembly to be able to decode HTML entities

Add-Type -AssemblyName System.Web

$result = Invoke-WebRequest 'https://htmlwithtable.htm'

$data = $result.ParsedHtml.getElementsByTagName("table") | Select-Object -First 1

$table = $data.Rows | ForEach-Object {

if ($_.tagName -eq 'tr'){

$csvRow = foreach($cell in $_.children){

if ($cell.tagName -match 't[dh]'){

# decode HTML entities and double-up quotes that the value may contain

$value = [System.Web.HttpUtility]::HtmlDecode($cell.innerText) -replace '"', '""'

if ($cell.innerHtml -match 'href="([^"]*)') {

# if the cell contains a link, add it to the value between brackets

$value += ' ({0})' -f $Matches[1]

}

'"{0}"' -f $value

}

}

$csvRow -join ','

}

}

$table | Out-File 'c:\change\htmltocsv.csv'