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

Chilkat.Mht mht = new Chilkat.Mht();

bool success;
success = mht.UnlockComponent("Anything for 30-day trial");
if (success != true) {
    textBox1.Text += mht.LastErrorText + "\r\n";
    return;
}

//  Download a URL into an in-memory MHT web archive contained
//  in a string variable:
string mhtDoc;
mhtDoc = mht.GetMHT("http://www.gopackaging.com/");
if (mhtDoc == null ) {
    textBox1.Text += mht.LastErrorText + "\r\n";
    return;
}

//  Now extract the HTML and embedded objects:
string unpackDir;
unpackDir = "/Users/chilkat/temp/";
string htmlFilename;
htmlFilename = "gopackaging.html";
string partsSubdir;
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) {
    textBox1.Text += mht.LastErrorText + "\r\n";
}
else {
    MessageBox.Show("Unpacked!");
}