问网络爬虫优化

EN

use warnings;

use LWP::Simple;
use LWP::UserAgent;
use HTTP::Request;
use HTTP::Response;
use HTML::LinkExtor;

my $starting_url = 'http://en.wikipedia.org/wiki/Main_Page';
my @urls = $starting_url;
my %alreadyvisited;
my $browser = LWP::UserAgent->new();
$browser->timeout(5);
my $url_count = 0;

while (@urls) 
{ 
     my $url = shift @urls;
     next if $alreadyvisited{$url}; ## check if already visited

     my $request = HTTP::Request->new(GET => $url);
     my $response = $browser->request($request);

     if ($response->is_error())
     {
         print $response->status_line, "\n"; ## check for bad URL
     }
     my $contents = $response->content(); ## get contents from URL
     push @c, $contents;
     my @text = &RemoveSGMLtags(\@c);
     #print "@text\n";

     $alreadyvisited{$url} = 1; ## store URL in hash for future reference
     $url_count++;
     print "$url\n";

     if ($url_count == 500) ## exit if number of crawled pages exceed limit
     {
         exit 0; 
     } 


     my ($page_parser) = HTML::LinkExtor->new(undef, $url); 
     $page_parser->parse($contents)->eof; ## parse page contents
     my @links = $page_parser->links; 

     foreach my $link (@links) 
     {
             $test = $$link[2];
             $test =~ s!^https?://(?:www\.)?!!i;
             $test =~ s!/.*!!;
             $test =~ s/[\?\#\:].*//;
             if ($test eq "en.wikipedia.org")  ## check if URL belongs to unt domain
             {
                 next if ($$link[2] =~ m/^mailto/); 
                 next if ($$link[2] =~ m/s?html?|xml|asp|pl|css|jpg|gif|pdf|png|jpeg/);
                 push @urls, $$link[2];
             }
     }
     sleep 1;
}


sub RemoveSGMLtags 
{
    my ($input) = @_;
    my @INPUTFILEcontent = @$input;
    my $j;my @raw_text;
    for ($j=0; $j<$#INPUTFILEcontent; $j++)
    {
        my $INPUTFILEvalue = $INPUTFILEcontent[$j];
        use HTML::Parse;
        use HTML::FormatText;
        my $plain_text = HTML::FormatText->new->format(parse_html($INPUTFILEvalue));
        push @raw_text, ($plain_text);
    }
    return @raw_text;
}