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 4.0 Framework

Download Chilkat .NET for 64-bit 4.0 Framework (x64)

Download Chilkat .NET for 2.0 / 3.5 Framework

Download Chilkat .NET for 64-bit 2.0 / 3.5 Framework (x64)

Download Chilkat .NET for 1.0 / 1.1 Framework

Dim mht As New Chilkat.Mht()

Dim success As Boolean
success = mht.UnlockComponent("Anything for 30-day trial")
If (success <> true) Then
    TextBox1.Text = TextBox1.Text & mht.LastErrorText & vbCrLf
    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/")
If (mhtDoc = vbNullString ) Then
    TextBox1.Text = TextBox1.Text & mht.LastErrorText & vbCrLf
    Exit Sub
End If



'  Now extract the HTML and embedded objects:
Dim unpackDir As String
unpackDir = "/Users/chilkat/temp/"
Dim htmlFilename As String
htmlFilename = "gopackaging.html"
Dim partsSubdir As String
partsSubdir = "objects"
'  Extract to /Users/chilkat/temp/gopackaging.html.
'  images and other embedded objects are placed in
'  /Users/chilkat/temp/objects.  Directories are automatically
'  created if they don't already exist.
success = mht.UnpackMHTString(mhtDoc,unpackDir,htmlFilename,partsSubdir)
If (success <> true) Then
    TextBox1.Text = TextBox1.Text & mht.LastErrorText & vbCrLf
Else
    MsgBox("Unpacked!")
End If