Perl使用爬虫ip服务器采集图书网站信息

use LWP::UserAgent;
use HTTP::Proxy;
use HTML::TreeBuilder;

# 创建爬虫ip服务器
my $proxy = HTTP::Proxy->new(
    host => "duoip",
    port => 8000,
);

# 创建用户爬虫ip
my $ua = LWP::UserAgent->new(proxies => $proxy);

# 设置要爬取的网站的 URL
my $url = '目标网址';

# 使用用户爬虫ip访问网站
my $response = $ua->get($url);

# 检查请求是否成功
if ($response->is_success) {
    # 解析 HTML 页面
    my $tree = HTML::TreeBuilder->new();
    $tree->parse($response->decoded_content);

    # 找到需要的信息
    my $title = $tree->look_down(_tag => 'title')->as_text;
    my $author = $tree->look_down(_tag => 'span', att => { class => 'author' })->as_text;
    my $price = $tree->look_down(_tag => 'span', att => { class => 'price' })->as_text;

    print "Title: $title\n";
    print "Author: $author\n";
    print "Price: $price\n";
}
else {
    print "Failed to get $url\n";
}