Rust

Must-Match Patterns

See more Spider Examples

You may restrict the spider to only follow links that match any one of a set of "must-match" wildcard patterns. The AddMustMatchPattern can be called repeatedly to add must-match patterns. Rust

let spider = chilkat::Spider::new();

// --------------------------------------------------------------------
// Note: The URLs in this example are no longer valid.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 must-match
// and then re-fetch, to see it work...

spider.initialize("directory.google.com");
spider.add_unspidered("http://directory.google.com/Top/Recreation/Outdoors/Hiking/Backpacking/");

let _ = spider.crawl_next().is_ok();

// Display the outbound links
for i in 0..spider.num_outbound_links() {
    println!("{}", spider.get_outbound_link(i).unwrap_or_default());
}

// The output:
// http://www.backpacker.com
// http://www.cmc.org
// http://www.backpacking.net
// http://www.thebackpacker.com/
// http://www.rei.com/online/store/LearnShareArticlesList?categoryId=Camping
// http://www.trailspace.com/
// http://www.catskillhikes.com/
// http://gorp.away.com/gorp/location/asia/nepal/favpicks.htm
// http://www.backpackinglight.com/cgi-bin/backpackinglight/index.html
// http://www.yetizone.com/
// http://www.backpackingfun.com
// http://www.freezerbagcooking.com/
// http://www.spadout.com/backpacking/
// http://sierrabackpacker.com
// http://www.abovecalifornia.com/
// http://www.personal.psu.edu/faculty/r/p/rpc1/bbb/
// http://www.thebackpackersguide.com
// http://www.journeywest.com/WB/index.html
// http://www.johann-sandra.com/backpackdir.htm
// http://www.geocities.com/amytys/
// http://www.cloudwalkersbasecamp.com
// http://www.netbackpacking.com
// http://members.tripod.com/~stooges/
// http://www.thebackpackingsite.com
// http://www.thruhikers.com/
// http://www.redcompservices.com/AT/
// http://members.aol.com/CMorHiker/backpack
// http://mywebpages.comcast.net/midwestpacker/
// http://www.midwesthiker.com/
// http://www.WeBackpack.com
// http://www.michiganhiker.com
// http://www.host33.com/backpack/
// http://www.wilderness-backpacking.com
// http://www.thetravelmonkey.net
// http://dmoz.org/cgi-bin/add.cgi?where=Recreation/Outdoors/Hiking/Backpacking
// http://dmoz.org/about.html
// http://dmoz.org/cgi-bin/apply.cgi?where=Recreation/Outdoors/Hiking/Backpacking
// http://dmoz.org
// http://dmoz.org/profiles/cdog.html
// http://dmoz.org/profiles/justinwp.html

// Do it again, but this time with avoid patterns.
spider.initialize("directory.google.com");
spider.add_unspidered("http://directory.google.com/Top/Recreation/Outdoors/Hiking/Backpacking/");

// Add some must-match patterns:
spider.add_must_match_pattern("*.com/*");
spider.add_must_match_pattern("*.net/*");

// Add some avoid-patterns:
spider.add_avoid_outbound_link_pattern("*.mypages.*");
spider.add_avoid_outbound_link_pattern("*.personal.*");
spider.add_avoid_outbound_link_pattern("*.comcast.*");
spider.add_avoid_outbound_link_pattern("*.aol.*");
spider.add_avoid_outbound_link_pattern("*~*");

let _ = spider.crawl_next().is_ok();

println!("-----------------------");

// Display the outbound links
for i in 0..spider.num_outbound_links() {
    println!("{}", spider.get_outbound_link(i).unwrap_or_default());
}

// Output:
// http://www.thebackpacker.com/
// http://www.rei.com/online/store/LearnShareArticlesList?categoryId=Camping
// http://www.trailspace.com/
// http://www.catskillhikes.com/
// http://gorp.away.com/gorp/location/asia/nepal/favpicks.htm
// http://www.backpackinglight.com/cgi-bin/backpackinglight/index.html
// http://www.yetizone.com/
// http://www.freezerbagcooking.com/
// http://www.spadout.com/backpacking/
// http://www.abovecalifornia.com/
// http://www.journeywest.com/WB/index.html
// http://www.johann-sandra.com/backpackdir.htm
// http://www.geocities.com/amytys/
// http://www.thruhikers.com/
// http://www.redcompservices.com/AT/
// http://www.midwesthiker.com/
// http://www.host33.com/backpack/