PHP简单爬虫 爬取免费代理ip 一万条

时间:2021-11-30 21:31:29

目标站:http://www.xicidaili.com/

代码:

<?php
require 'lib/phpQuery.php';
require 'lib/QueryList.php';
require "db/shared/ez_sql_core.php";
require "db/mysql/ez_sql_mysql.php";
require "public/function.php";
use QL\QueryList; //抓取猫眼电影TOP100榜单内容
$db = new ezSQL_mysql('root', 'root', 'spider', 'localhost'); for($j=;$j<=;$j++){
$gurl="http://www.xicidaili.com/nn/".$j;
$html=curl_request($gurl);
for($i=;$i<=;$i++){
getIpInfo($html,$i,$db);
}
echo "第".$j."页完成".PHP_EOL;
} function getIpInfo($html,$t,$db){
$rules = array(
//采集id为one这个元素里面的纯文本内容
'ip' => array("#ip_list tr:eq($t) td:eq(1)",'text'),//ip
'port' => array("#ip_list tr:eq($t) td:eq(2)",'text'),//端口
'area' => array("#ip_list tr:eq($t) td:eq(3)",'text'),//位置
'anonymous' => array("#ip_list tr:eq($t) td:eq(4)",'text'),//是否匿名
'type' => array("#ip_list tr:eq($t) td:eq(5)",'text'),//类型
'speed' => array("#ip_list tr:eq($t) td:eq(6)",'html','',function($content){
$num=explode('%', explode(':', $content)[])[];
if($num >= && $num<){
return "一般";
}else if($num >= ){
return "很快";
}else{
return "较慢";
}
}),//速度
'chtime' => array("#ip_list tr:eq($t) td:eq(8)",'text'),//存活时间.
'yztime' => array("#ip_list tr:eq($t) td:eq(9)",'text'),//验证时间 );
$data = QueryList::Query($html,$rules)->data;
print_r($data); $ip=$data[]["ip"];
$port=$data[]["port"];
$area=$data[]["area"];
$anonymous=$data[]["anonymous"];
$type=$data[]["type"];
$speed=$data[]["speed"];
$chtime=$data[]["chtime"];
$yztime=$data[]["yztime"]; $db->query("INSERT INTO ip (ip, port,area,anonymous,type,speed,chtime,yztime)
VALUES ('$ip','$port','$area','$anonymous','$type','$speed','$chtime','$yztime')");
}

结果:

PHP简单爬虫 爬取免费代理ip 一万条

完整项目下载:https://files.cnblogs.com/files/wordblog/spider2.rar