Zig

Extract all HTML Objects from a Web Page

See more MHT / HTML Email Examples

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

const std = @import("std");
const chilkat = @import("chilkat");

pub fn main(init: std.process.Init) !void {
    const alloc = init.arena.allocator();

    var success: bool = false;

    // This example assumes the Chilkat API to have been previously unlocked.
    // See Global Unlock Sample for sample code.

    const mht = try chilkat.Mht.init();
    defer mht.deinit();

    // Download a URL into an in-memory MHT web archive contained
    // in a string variable.
    // The following URL is randomly picked and was valid at the time of writing this example:
    const mht_doc = mht.getMHT(alloc, "https://www.tetonlodge.com/") catch {
        std.debug.print("{s}\n", .{try mht.getLastErrorText(alloc)});
        return;
    };

    // Extract the HTML and embedded objects:
    const unpack_dir = "C:/AAWorkarea/mhtTesting/";
    const html_filename = "lodge.html";
    const parts_subdir = "objects";

    // Extract to C:/AAWorkarea/mhtTesting/lodge.html.
    // images and other embedded objects are placed in
    // C:/AAWorkarea/mhtTesting/objects.  Directories are automatically
    // created if they don't already exist.
    success = if (mht.unpackMHTString(mht_doc, unpack_dir, html_filename, parts_subdir)) true else |_| false;
    if (!success) {
        std.debug.print("{s}\n", .{try mht.getLastErrorText(alloc)});
    } else {
        std.debug.print("Unpacked!\n", .{});
    }
}