php结合正则批量抓取网页中邮箱地址

1

2

3

4

5

6

7

8

9

10

11

12

13

<?php

$url='http://www.bkjia.net'; //要采集的网址

$content=file_get_contents($url);

//echo $content;

function getEmail($str) {

//$pattern = "/([a-z0-9]*[-_\.]?[a-z0-9]+)*@([a-z0-9]*[-_]?[a-z0-9]+)+[\.][a-z]{2,3}([\.][a-z]{2})?/i";

$pattern = "/([a-z0-9\-_\.]+@[a-z0-9]+\.[a-z0-9\-_\.]+)/";

preg_match_all($pattern,$str,$emailArr);

return $emailArr[0];

}

print_r( getEmail($content));

?>

1

2

3

4

5

6

7

8

9

10

<?php

$url='http://www.jbkjia.net'; //当页已留邮箱

$content=file_get_contents($url); //获取页面内容

function getEmail($str) { //匹配邮箱内容

$pattern = "/([a-z0-9\-_\.]+@[a-z0-9]+\.[a-z0-9\-_\.]+)/";

preg_match_all($pattern,$str,$emailArr);

return $emailArr[0];

}

print_r( getEmail($content));

?>