Perl语言的特点和数据分析示例

usestrict;
usewarnings;
useLWP::UserAgent;
useThread::Pool;
useHTTP::Proxy;
usePDF::API2;
# 亿牛云代理# 爬虫加强版 设置代理服务器的主机、端口、用户名和密码my$proxy_ip='www.16yun.cn';
my$proxy_port='31000';
my$proxy_username='16YUN';
my$proxy_password='16IP';
# 随机 User-Agent 列表my@user_agents= (
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 11_4) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/605.1.15');
# 创建 UserAgent 对象my$ua=LWP::UserAgent->new();
# 设置代理服务器my$proxy=HTTP::Proxy->new(
host=>$proxy_ip,
port=>$proxy_port,
proxy_user=>$proxy_username,
proxy_pass=>$proxy_password);
# 创建线程池my$pool=Thread::Pool->new(
    {
workers=>5,    # 设置线程数do=> \&process_url,    # 处理函数    }
);
# 采集热搜数据my$url='https://weibo.com';
my$response=$ua->get($url);
if ($response->is_success) {
my$content=$response->decoded_content;
my$pdf=PDF::API2->new();
while ($content=~m/<a class="list_item" href=".*?" target="_blank" action-data="(.*?)" suda-uatrack=".*?" >(.*?)<\/a>.*?<\/h3>.*?<span class=".*?" >(.*?)<\/span>/sg) {
my$rank=$1;
my$title=$2;
my$clicks=$3;
$pool->add($rank, $title, $clicks, $pdf);
    }
# 保存为 PDF 文件$pdf->save('hot_searches.pdf');
$pdf->end();
}
else {
die"Failed to retrieve content: ".$response->status_line;
}
# 等待线程池中的任务完成$pool->join();
subprocess_url {
my ($rank, $title, $clicks, $pdf) =@_;
# 在这里可以对热搜数据进行分析和处理# 将结果添加到 PDF 文件中my$page=$pdf->page();
my$font=$pdf->corefont('Helvetica', -encoding=>'latin1');
my$text=$page->text();
$text->font($font, 12);
$text->translate(50, $pdf->height() -50);
$text->text("Rank: $rank\nTitle: $title\nClicks: $clicks\n\n");
}