Extract all HTML Objects from a Web Page

Download Chilkat .NET for 2.0 / 3.5 Framework

Download Chilkat .NET for 1.0 / 1.1 Framework

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

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

bool success;
success = mht.UnlockComponent("30-day trial");
if (success != true) {
    MessageBox.Show("Mht component unlock failed");
    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/");
// On failure, the mhtDoc will be a zero-length string.
// Check the LastErrorText property for error information.

// Now extract the HTML and embedded objects:
string unpackDir;
unpackDir = "c:/temp/";
string htmlFilename;
htmlFilename = "gopackaging.html";
string partsSubdir;
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) {
    MessageBox.Show(mht.LastErrorText);
}
else {
    MessageBox.Show("Unpacked!");
}