in reply to Re: CGI to Pull links off webpage fails on second run
in thread CGI to Pull links off webpage fails on second run

a little code ... this is just the link retrieval section, but it alone will not run two times in a row (except over 30+ minutes between runs).

$url = "http://biz.yahoo.com/rf/archive.html"; $ua = new LWP::UserAgent; # Set up a callback that collect links my @links = (); sub callback { my($tag, %attr) = @_; return if $tag ne 'a'; # only look closer at written d +ocuments, not images push(@links, values %attr); + } # Make the parser. $p = HTML::LinkExtor->new(\&callback); # Request document and parse it as it arrives $res = $ua->request(HTTP::Request->new(GET => $url), sub {$p->parse($_[0])}); #Expand all URLs to absolute ones my $base = $res->base; @links = map { $_ = url($_, $base)->abs; } @links; print "Links: <P>@links<p>"; exit;