php网络爬虫技术-PHP源码

php网络爬虫技术-PHP源码

function get_urls($url){  

       $url_array=array();  

       $the_first_content=file_get_contents($url);  

       $the_second_content=file_get_contents($url);  

       $pattern1 = "/http:\/\/[a-zA-Z0-9\.\?\/\-\=\&\:\+\-\_\'\"]+/";  

       $pattern2="/http:\/\/[a-zA-Z0-9\.]+/";  

       preg_match_all($pattern2, $the_second_content, $matches2);  

       preg_match_all($pattern1, $the_first_content, $matches1);  

       $new_array1=array_unique($matches1[0]);  

       $new_array2=array_unique($matches2[0]);  

       $final_array=array_merge($new_array1,$new_array2);  

       $final_array=array_unique($final_array);  

       for($i=0;$i

/php/34238.htmlwww.phpzy.comtrue/php/34238.htmlTechArticlephp网络爬虫技术-PHP源码 php代码 function get_urls($url){ $url_array=array(); $the_first_content=file_get_contents($url); $the_second_content=file_get_contents($url); $pattern1 = "/http:\/\/[a-zA-Z0-9\.\?\/\-\=\#39;\"]+/"; $pattern...