Zig

Avoiding Outbound Links Matching Patterns

See more Spider Examples

The spider accumulates outbound links when crawling. Your program may specify any number of "avoid patterns" to prevent any link matching at least one of the wildcarded patterns from being added. Zig

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

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

    const spider = try chilkat.Spider.init();
    defer spider.deinit();

    // --------------------------------------------------------------------
    // Note: The URLs in this example are no longer valid.
    // You should replace the URLs with URLs from a site of your
    // own choosing -- preferably your own site if testing.
    // (Google's Directory no longer exists.)
    // --------------------------------------------------------------------

    // First, we'll get the outbound links for a page in the
    // Google directory.  Then we'll add some avoid patterns
    // and then re-fetch, to see it work...

    spider.initialize("directory.google.com");
    spider.addUnspidered("http://directory.google.com/Top/Recreation/Food/Cheese/");

    try spider.crawlNext();

    // Display the outbound links
    var i: i32 = 0;
    i = 0;
    while (i < spider.getNumOutboundLinks()) : (i += 1) {
        std.debug.print("{s}\n", .{try spider.getOutboundLink(alloc, i)});
    }

    // The output:
    // http://www.cheese.com/
    // http://www.cheesediaries.com/
    // http://www.WisDairy.com/
    // http://www.newenglandcheese.com
    // http://www.ilovecheese.com
    // http://www.cheesefromspain.com
    // http://www.realcaliforniacheese.com/
    // http://www.frencheese.co.uk/
    // http://www.cheesesociety.org/
    // http://www.specialcheese.com/queso.htm
    // http://www.franceway.com/cheese/intro.htm
    // http://www.foodsubs.com/Chesfirm.html
    // http://www.cheeseboard.co.uk/
    // http://www.thecheeseweb.com/
    // http://www.vtcheese.com/
    // http://www.coldbacon.com/cheese.html
    // http://www.norwegiancheeses.co.uk/
    // http://www.reluctantgourmet.com/cheese.htm
    // http://www.lancewood.co.za/
    // http://www.switzerlandcheese.ca
    // http://www.frenchcheese.dk/
    // http://www.dolcevita.com/cuisine/cheese/cheese.htm
    // http://cheeseisland.net/
    // http://www.cheestrings.ca/
    // http://www.dreamcheese.co.uk
    // http://hgic.clemson.edu/factsheets/HGIC3506.htm
    // http://www.epicurious.com/cooking/how_to/food_dictionary/entry?id=1815
    // http://www.mousetrapcheese.co.uk
    // http://taquitos.net/yum/gc.shtml
    // http://www.greek-recipe.com/static/greek-cheese
    // http://www.park.org/Netherlands/pavilions/food_and_markets/cheese/introduction.html
    // http://www.dairyfarmers.org/engl/recipes/4_1.asp
    // http://www.prairieridgecheese.com/wischeesguid.html
    // http://dmoz.org/cgi-bin/add.cgi?where=Recreation/Food/Cheese
    // http://dmoz.org/about.html
    // http://dmoz.org/cgi-bin/apply.cgi?where=Recreation/Food/Cheese

    // Do it again, but this time with avoid patterns.
    spider.initialize("directory.google.com");
    spider.addUnspidered("http://directory.google.com/Top/Recreation/Food/Cheese/");

    // Add some avoid patterns:
    spider.addAvoidOutboundLinkPattern("*dmoz.org*");
    spider.addAvoidOutboundLinkPattern("*?id=*");
    spider.addAvoidOutboundLinkPattern("*.co.uk*");
    try spider.crawlNext();

    std.debug.print("-----------------------\n", .{});

    // Display the outbound links
    i = 0;
    while (i < spider.getNumOutboundLinks()) : (i += 1) {
        std.debug.print("{s}\n", .{try spider.getOutboundLink(alloc, i)});
    }

    // Output:
    // http://www.cheese.com/
    // http://www.cheesediaries.com/
    // http://www.WisDairy.com/
    // http://www.newenglandcheese.com
    // http://www.ilovecheese.com
    // http://www.cheesefromspain.com
    // http://www.realcaliforniacheese.com/
    // http://www.cheesesociety.org/
    // http://www.specialcheese.com/queso.htm
    // http://www.franceway.com/cheese/intro.htm
    // http://www.foodsubs.com/Chesfirm.html
    // http://www.thecheeseweb.com/
    // http://www.vtcheese.com/
    // http://www.coldbacon.com/cheese.html
    // http://www.reluctantgourmet.com/cheese.htm
    // http://www.lancewood.co.za/
    // http://www.switzerlandcheese.ca
    // http://www.frenchcheese.dk/
    // http://www.dolcevita.com/cuisine/cheese/cheese.htm
    // http://cheeseisland.net/
    // http://www.cheestrings.ca/
    // http://hgic.clemson.edu/factsheets/HGIC3506.htm
    // http://taquitos.net/yum/gc.shtml
    // http://www.greek-recipe.com/static/greek-cheese
    // http://www.park.org/Netherlands/pavilions/food_and_markets/cheese/introduction.html
    // http://www.dairyfarmers.org/engl/recipes/4_1.asp
    // http://www.prairieridgecheese.com/wischeesguid.html
}