PHP 简易爬虫

1. function get_urls($url)
2. {
3. $url_array=array();
4. $the_first_content=file_get_contents($url);
5. $the_second_content=file_get_contents($url);
6. $pattern1 = "/http:\/\/[a-zA-Z0-9\.\?\/\-\=\&\:\+\-\_\'\"]+/";
7. $pattern2="/http:\/\/[a-zA-Z0-9\.]+/";
8. preg_match_all($pattern2, $the_second_content, $matches2);
9. preg_match_all($pattern1, $the_first_content, $matches1);
10. $new_array1=array_unique($matches1[0]);
11. $new_array2=array_unique($matches2[0]);
12. $final_array=array_merge($new_array1,$new_array2);
13. $final_array=array_unique($final_array);
14. for($i=0;$i {
15. echo $final_array[$i]."
    ";
16. }
17. }
18. get_urls("http://www.baidu.com");

复制代码