Extract all HTML Objects from a Web Page

Demonstrates how to download a Web page (at a URL) and extract all HTML objects. Eg. images, links, CSS files, JavaScript files, etc.

Download Chilkat .NET for 2.0 Framework

Download Chilkat .NET for 1.0 / 1.1 Framework

Dim mht As New Chilkat.Mht()

Dim success As Boolean
success = mht.UnlockComponent("30-day trial")
If (success <> true) Then
    MsgBox("Mht component unlock failed")
    Exit Sub
End If


' Download a URL into an in-memory MHT web archive contained
' in a string variable:
Dim mhtDoc As String
mhtDoc = mht.GetMHT("http://www.gopackaging.com/")
' On failure, the mhtDoc will be a zero-length string.
' Check the LastErrorText property for error information.


' Now extract the HTML and embedded objects:
Dim unpackDir As String
unpackDir = "c:/temp/"
Dim htmlFilename As String
htmlFilename = "gopackaging.html"
Dim partsSubdir As String
partsSubdir = "objects"
' Extract to c:/temp/gopackaging.html.
' images and other embedded objects are placed in
' c:/temp/objects.  Directories are automatically
' created if they don't already exist.
success = mht.UnpackMHTString(mhtDoc,unpackDir,htmlFilename,partsSubdir)
If (success <> true) Then
    MsgBox(mht.LastErrorText)
Else
    MsgBox("Unpacked!")
End If