perl 获取网页内容

一、LWP::Simple 模块  获取代码：

#!/usr/bin/perl
use strict;
use warnings;
use LWP::Simple;
my $url="";
my $page=get ($url);
print ("\n $page \n \n");
my $status=getprint($url);
print ("\n\n $status\n");
$status=getstore($url,"page.txt");
print ("\n $status \n");

 

 

 

 

二、HTML解析：  HTML::TokeParser模块 

 

 

#!/usr/bin/perl
  2 use strict;
  3 use warnings;
  4 use LWP::UserAgent;
  5 use HTML::TokeParser;
  6 my $url="";
  7 my $agent=new LWP::UserAgent();
  8 my $request=new HTTP::Request('GET'=>$url);
  9 my $response=$agent->request($request);
 10 my $document=$response->content();
 11
 12 my $page=HTML::TokeParser->new (\$document);
 13 while (my $token=$page->get_token()){
 14     my $type=shift(@{$token});
 15     my $text=shift(@{$token});
 16     if ($type eq "T"){
 17         print ("$text");
 18     }
 19 }