Advanced Search

Return to Snippet

Revision: 49316
at July 19, 2011 22:10 by danfsmith
Updated Code 
add-type -Path c:\dan\tools\html-agility-pack\HtmlAgilityPack.dll
$files = Get-ChildItem -Filter *.htm -Path C:\Path\ -Recurse
$doc = New-Object HtmlAgilityPack.HtmlDocument 
$result = $files | % { 
	#Write-Host "Checking $_"
	$name = $_.FullName.Replace("FILEPATH","WEBPATH").Replace("\", "/")
        #Get second folder of URL as "section"
	$sections = $name.Split("/")
	$section = $sections[3]
	if ($section.Contains(".htm"))
	{
		$section = ""
	}
	$htmldoc = $doc.Load($_.FullName) 
	$titlenode = $doc.DocumentNode.SelectSingleNode("//title")
	$descriptionnode = $doc.DocumentNode.SelectSingleNode("//meta[@name='description']")
	if ($descriptionnode) {
		$description = $descriptionnode.GetAttributeValue("content", "")
	}
	else {
		$description = ""
	}
	$title = $titlenode.InnerText
	New-Object PsObject -Property @{ Name = $name; Section=$section; Title=$title; Description=$description;} | Select Name, Section, Title, Description
}
$result | Sort Section, Name

Revision: 49315
at July 19, 2011 22:05 by danfsmith
Initial Code 
add-type -Path c:\dan\tools\html-agility-pack\HtmlAgilityPack.dll
$files = Get-ChildItem -Filter *.htm -Path C:\WaldenWWW-HTM\ -Recurse
$doc = New-Object HtmlAgilityPack.HtmlDocument 
$result = $files | % { 
	#Write-Host "Checking $_"
	$name = $_.FullName.Replace("C:\WaldenWWW-HTM\","http://www.waldenu.edu/").Replace("\", "/")
	$sections = $name.Split("/")
	$section = $sections[3]
	if ($section.Contains(".htm"))
	{
		$section = ""
	}
	$htmldoc = $doc.Load($_.FullName) 
	$titlenode = $doc.DocumentNode.SelectSingleNode("//title")
	$descriptionnode = $doc.DocumentNode.SelectSingleNode("//meta[@name='description']")
	if ($descriptionnode) {
		$description = $descriptionnode.GetAttributeValue("content", "")
	}
	else {
		$description = ""
	}
	$title = $titlenode.InnerText
	New-Object PsObject -Property @{ Name = $name; Section=$section; Title=$title; Description=$description;} | Select Name, Section, Title, Description
}
$result | Sort Section, Name
Initial URL 

                                

                                                            

                                    

                                        

                                        Initial Description
                                        

                                    

                                    

                                

                                                            

                                    

                                        

                                        Initial Title
                                        

                                    

                                    
Get Title and MetaData from HTML files

                                

                                                            

                                    

                                        

                                        Initial Tags
                                        

                                    

                                    
html

                                

                                                            

                                    

                                        

                                        Initial Language
                                        

                                    

                                    
Windows PowerShell