PHP 采集获取指定网址的内容
2019/6/30 15:29:50
本文主要是介绍PHP 采集获取指定网址的内容,对大家解决编程问题具有一定的参考价值,需要的程序猿们随着小编来一起学习吧!
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。
<?php
/*
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('/<a(.*?)href="(.*?)">(.*?)<\/a>/',$this->content,$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;
$this->GetContent(); //提取内容
preg_match_all('/<title>(.*?)<\/title>/',$this->content,$files); //取标题
$filename=$files[1][0].".html"; //存储名
$content=$this->str_cut($this->content,'http://pagead2.googlesyndication.com/pagead/show_ads.js','<div id="article_detail">');
$file=fopen($filename,"w");
fwrite($file,$content);
fclose($file);
echo $filename."保存 OK<br>\n";
}
}
function str_cut($str ,$start, $end) {
$content = strstr( $str, $start );
$content = substr( $content, strlen( $start ), strpos( $content, $end ) - strlen( $start ) );
return $content;
}
}
$w=new GetUrl("http://www.ijavascript.cn/jiaocheng/javascript-jiaocheng-352.html");
?>
复制代码 代码如下:
<?php
/*
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('/<a(.*?)href="(.*?)">(.*?)<\/a>/',$this->content,$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;
$this->GetContent(); //提取内容
preg_match_all('/<title>(.*?)<\/title>/',$this->content,$files); //取标题
$filename=$files[1][0].".html"; //存储名
$content=$this->str_cut($this->content,'http://pagead2.googlesyndication.com/pagead/show_ads.js','<div id="article_detail">');
$file=fopen($filename,"w");
fwrite($file,$content);
fclose($file);
echo $filename."保存 OK<br>\n";
}
}
function str_cut($str ,$start, $end) {
$content = strstr( $str, $start );
$content = substr( $content, strlen( $start ), strpos( $content, $end ) - strlen( $start ) );
return $content;
}
}
$w=new GetUrl("http://www.ijavascript.cn/jiaocheng/javascript-jiaocheng-352.html");
?>
这篇关于PHP 采集获取指定网址的内容的文章就介绍到这儿,希望我们推荐的文章对大家有所帮助,也希望大家多多支持为之网!
- 2024-09-28怎么把PHP程序打包?-icode9专业技术文章分享
- 2024-09-28怎么用Phar打包PHP程序?-icode9专业技术文章分享
- 2024-09-13手动在github上下载的mfpt包,怎么放到thinkphp5.0框架并正常使用-icode9专业技术文章分享
- 2024-09-05python的<class 'bytearray'>相当于php的哪个数据类型-icode9专业技术文章分享
- 2024-09-05php 导出银行卡号避免科学技术法的方法-icode9专业技术文章分享
- 2024-08-30什么样的php代码质量差被称为垃圾代码-icode9专业技术文章分享
- 2024-08-30用 PHP 调用拼多多的接口以获取订单状态消息的步骤方法和代码示例-icode9专业技术文章分享
- 2024-08-27phpunit单元测试框架的入门和使用方法介绍-icode9专业技术文章分享
- 2024-08-24PHP 中date("w") 周一是多少-icode9专业技术文章分享
- 2024-08-14thinkphp8.0获取域名或主机名方法-icode9专业技术文章分享