HttpRequest.class.php
<?php
/*
* 使用curl扩展发出http的get或post请求
*/
class HttpRequest
{
//url,请求的服务器地址
private $url = '';
//is_return,是否返回结果而不是直接显示
private $is_return = 1;
public function __set($p,$v)
{
if(property_exists($this, $p)){
$this->$p = $v;
}
}
// 发出http请求的方法
//参数:提交的数据,默认是空的
public function send($data = array())
{
//1. 如果传递数据了,说明向服务器提交数据(post),如果没有传递数据,认为从服务器读取资源(get)
$ch = curl_init();
//2. 不管是get、post,跳过证书的验证
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, FALSE);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
//3. 设置请求的服务器地址
curl_setopt($ch, CURLOPT_URL, $this->url);
//4. 判断是get还是post
if(!empty($data)){
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
}
//5. 是否返回数据
if($this->is_return===1){
//说明返回
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$result = curl_exec($ch);
curl_close($ch);
return $result;
}else{
//直接输出
curl_exec($ch);
curl_close($ch);
}
}
}
curlcollect.php
<?php
require_once 'HttpRequest.class.php';
class Kl8_360
{
//接收采集的网址,并制定筛选规则
public function collect()
{
$config = include 'config.php';
$url=$config['url'];
//开始采集
$http = new HttpRequest();
$http -> url = $url;
$string = $http -> send();
$pattern = '#<tr.+?>(.+?)</tr>#';
preg_match($pattern, $string, $match);
// echo '<pre>';
// var_dump($match['0']);
$str=$match['0'];
$qihao=substr($str,18,6);
$pattern1 = '#<span.+?>(.+?)</span>#';
preg_match_all($pattern1, $str, $old_kaijianghao);
$old_kaijianghao=implode('',$old_kaijianghao['0']);
$kaijianghao=substr($old_kaijianghao,0,640);
$new_kaijianghao=strip_tags( $kaijianghao );
$feipan=substr($str,821,2);
$jiangchi=substr($str,839,8);
$kjtime=substr($str,858,19);
$kjtimestamp=time();
$data=array();
$data['qihao']=$qihao;
$data['kaijianghao']=$new_kaijianghao;
$data['feipan']=$feipan;
$data['jiangchi']=$jiangchi;
$data['kjtime']=$kjtime;
$data['kjtimestamp']=time();
return $data;
}
}
$a=new Kl8_360();
var_dump($a->collect());
------------------------------------------------------------------------
补充一个使用file_get_contents的采集方法
<?php
require_once "DAOPDO.class.php";
class Kl8_360{
public function getData(){
$config = include 'config.php';
$url=$config['url'];
// var_dump($url);die;
// $url="http://chart.cp.360.cn/kaijiang/kl8?sb_spm=f35ccf8a8a86029d3082798218e9d902";
$string=file_get_contents($url);
// var_dump($string);die;
$pattern = '#<tr.+?>(.+?)</tr>#';
preg_match($pattern, $string, $match);
// echo '<pre>';
// var_dump($match['0']);
$str=$match['0'];
$qihao=substr($str,18,6);
$pattern1 = '#<span.+?>(.+?)</span>#';
preg_match_all($pattern1, $str, $old_kaijianghao);
$old_kaijianghao=implode('',$old_kaijianghao['0']);
$kaijianghao=substr($old_kaijianghao,0,640);
$new_kaijianghao=strip_tags( $kaijianghao );
$feipan=substr($str,821,2);
$jiangchi=substr($str,839,8);
$kjtime=substr($str,858,19);
$kjtimestamp=time();
$data=array();
$data['qihao']=$qihao;
$data['kaijianghao']=$new_kaijianghao;
$data['feipan']=$feipan;
$data['jiangchi']=$jiangchi;
$data['kjtime']=$kjtime;
$data['kjtimestamp']=time();
return $data;
}
//数据入库
public function insertMysql($data){
$config = include 'config.php';
$option =$config['option'];
$dao=DAOPDO::getSingleton($option);
$qihao=$data['qihao'];
$kaijianghao=$data['kaijianghao'];
$feipan=$data['feipan'];
$jiangchi=$data['jiangchi'];
$kjtime=$data['kjtime'];
$kjtimestamp=$data['kjtimestamp'];
$sql="select * from 360kl8 where qihao=$qihao";
$res=$dao->fetchRow($sql);
if(!$res){
$sql="insert into 360kl8 (qihao,kaijianghao,feipan,jiangchi,kjtime,kjtimestamp) values ('$qihao','$kaijianghao','$feipan','$jiangchi','$kjtime',$kjtimestamp)";
// var_dump($sql);die;
@$res=$dao->exec($sql);
// if($res){
// echo 'ok';
// }else{
// echo 'no ';
// }
}
}
//从数据库提取数据
public function selectMysql($data){
$config = include 'config.php';
$option = $config['option'];
$dao=DAOPDO::getSingleton($option);
$sql="select * from 360kl8 order by qihao desc limit 20";
$res=$dao->fetchAll($sql);
if($res){
var_dump(json_encode($res));
}
// else{
// echo 'no ';
// }
}
}
$a=new Kl8_360();
echo '<pre>';
var_dump($a->getData());
$a->insertMysql($a->getData());
$a->selectMysql($a->getData());