#!/usr/bin/perl use LWP::Simple; use HTML::TokeParser::Simple; use Data::Dumper; use strict; use warnings; my $start = 'http://155.69.224.75:8000/eeepeople/AcadStaff.asp'; my $file = './index.html'; LWP::Simple::mirror($start, $file); my $p = HTML::TokeParser::Simple->new($file); my $state = 0; my ($url, $name, @teachers ); while (my $t = $p->get_token) { if ($state == 0) { if ($t->is_start_tag('a')) { my $attr = $t->return_attr; if (exists $attr->{href} and $attr->{href} =~ /\/cv\//) { $url = $attr->{href}; $state = 1; } } } elsif ($state == 1) { if ($t->is_end_tag('a')) { push @teachers, { name => $name, url => $url }; $name = ''; $url = ''; $state = 0; } elsif ($t->is_text) { $name .= $t->as_is; } } } print Dumper(\@teachers), "\n"; foreach my $teacher (@teachers) { my $filename = lc($teacher->{name}); $filename =~ s/\s+/_/g; $filename .= '.html'; LWP::Simple::mirror($teacher->{url}, $filename); my $p = HTML::TokeParser::Simple->new($filename); $state = 0; my ($pub, $res, @publications, @interests); while (my $t = $p->get_token) { if ($state == 0) { if ($t->is_text and $t->as_is =~ /publication/i) { $state = 2; } } elsif ($state == 2) { if ($t->is_start_tag('li')) { $state = 3; } elsif ($t->is_end_tag('ul')) { $state = 0; } } elsif ($state == 3) { if ($t->is_text) { $pub .= $t->as_is; } elsif ($t->is_end_tag('li')) { push @publications, $pub; $pub = ''; $state = 2; } } } print $teacher->{name} ." published:\n"; print Dumper(\@publications), "\n"; }