Parse ATOM rss feed and remove html tags

Question

am developing this code using powershell. I need to be able to extract the html tags.

  Invoke-WebRequest -Uri \'https://psu.box.com/shared/static/jf36ohodxnw7oe         


        

Answer 1

You should be able to use the following script. It makes use of the HTMLFile com object.

  Invoke-WebRequest -Uri 'https://*.rss' -  OutFile C:\*.rss
  [xml]$Content = Get-Content C:\*.rss -Raw
  $Regex = '(?s)SE1046.*?Description := "(?.*?)"'

 If ($Content -match $Regex) {
      "Description is '$($Matches['Description'])'"
      # do something here with $Matches['Description']
    }
 Else {
    "No match."
      }
   $Feed = $Content.rss.channel
 ForEach ($msg in $Feed.Item){


     $ParseData = $msg.description
    ForEach ($Datum in $ParseData){
     If ($Datum -like "Title"){[int]$Upvote = ($Datum).split(' ') | Select-Object -First 1}#EndIf
     If ($Datum -like "comments"){[int]$Downvote = ($Datum).split(' ') | Select-Object -First 1}    #EndIf
    }#EndForEach     

    $HTML = New-Object -ComObject "HTMLFile"
    $HTML.IHTMLDocument2_write($ParseData.InnerText)

     [PSCustomObject]@{
     'LastUpdated' = [datetime]$msg.pubDate
     'Title' = $msg.title
     'Category' = $msg.category
     'Author' = $msg.author
     'Link' = $msg.link
     'UpVotes' = $Upvote
     'DownVotes' = $Downvote
     'Validations' = $Validation
     'WorkArounds' = $Workaround
     'Comments' = $HTML.all.tags("p") | % InnerText           
     'FeedbackID' = $FeedBackID
    }#EndPSCustomObject
   }