FEAR::API FEAR::API - There's no fear with this elegant site scraper #24

Extraction

Extract data from CPAN

url("http://search.cpan.org/recent")->();
submit_form(
        form_name => "f",
        fields => {
                   query => "perl"
                  });
template("<!--item-->[% p %]<!--end item-->");
extract;
print Dumper extresult;

Extract data from CPAN after some HTML cleanup

url("http://search.cpan.org/recent")->();
submit_form(
        form_name => "f",
        fields => {
                   query => "perl"
                  });
preproc(q(s/\A.+<!--results-->(.+)<!--end results-->.+\Z/$1/s));
print document->as_string;    # print content to STDOUT
template("<!--item-->[% p %]<!--end item-->");
extract;
print Dumper extresult;
continued...
Copyright © 2006 Yung-chung Lin