欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  后端开发

PHP 采集获取指定网址的内容_PHP教程

程序员文章站 2024-01-06 15:26:58
...
参考别人想法变成自己的想法,你会发现慢慢下来以后你就拥有了临时解决很多问题的思路与方法。
复制代码 代码如下:

/*
功能:获取页面内容,存储下来阅读; lost63
*/
Class GetUrl{
var $url; //地址
var $result; //结果
var $content; //内容
var $list; //列表
function GetUrl($url){
$this->url=$url;
$this->GetContent();
$this->GetList();
$this->FileSave();
//print_r($this->list[2]);
}
private function GetContent(){
$this->result=fopen($this->url,"r");
while(!feof($this->result)){
$this->content.=fgets($this->result,9999);
}
}
private function GetList(){
preg_match_all('/(.*?)/',$this->content,$this->list);
$this->list[2]=array_unique($this->list[2]); //移除相同的值
while(list($key,$value)=each($this->list[2])){
if(strpos($value,".html")==0||strpos($value,"jiaocheng")==0){
unset($this->list[2][$key]);
}else{
$this->list[2][$key]=substr($value,0,strpos($value,".html")).".html"; //去掉不需要的标签
}
}
}
private function FileSave(){
foreach($this->list[2] as $value){
$this->url=$value; //重新赋值
$this->content=null;
$this->GetContent(); //提取内容
preg_match_all('/(.*?)/',$this->content,$files); //取标题 <br>$filename=$files[1][0].".html"; //存储名 <br>$content=$this->str_cut($this->content,'http://pagead2.googlesyndication.com/pagead/show_ads.js','<div id="article_detail">'); <br>$file=fopen($filename,"w"); <br>fwrite($file,$content); <br>fclose($file); <br>echo $filename."保存 OK<br>\n"; <br>} <br>} <br>function str_cut($str ,$start, $end) { <br>$content = strstr( $str, $start ); <br>$content = substr( $content, strlen( $start ), strpos( $content, $end ) - strlen( $start ) ); <br>return $content; <br>} <br>} <br>$w=new GetUrl("http://www.ijavascript.cn/jiaocheng/javascript-jiaocheng-352.html"); <br>?><br> </div> <p align="left"></p> <div style="display:none;"> <span id="url" itemprop="url">http://www.bkjia.com/PHPjc/321035.html</span><span id="indexUrl" itemprop="indexUrl">www.bkjia.com</span><span id="isOriginal" itemprop="isOriginal">true</span><span id="isBasedOnUrl" itemprop="isBasedOnUrl">http://www.bkjia.com/PHPjc/321035.html</span><span id="genre" itemprop="genre">TechArticle</span><span id="description" itemprop="description">参考别人想法变成自己的想法,你会发现慢慢下来以后你就拥有了临时解决很多问题的思路与方法。 复制代码 代码如下: ?php /* 功能:获取页...</span> </div>