
对于一个热门的帖子,留下的邮箱数量是非常多的,楼主需要一个一个的去复制那些回复的邮箱,然后再粘贴发送邮件,不是被折磨死就是被累死。无聊至极写了一个抓取百度贴吧邮箱数据的程序,需要的拿走。
程序实现了一键抓取帖子全部邮箱和分页抓取邮箱两个功能,界面懒得做了,效果如下:

老规矩,直接贴源码
<?php
$url2="";
$page="";
if($_GET['url2']==""){
$url2="http://tieba.baidu.com/p/2314539885?pn=1";
}else{
$url2=$_GET['url2'];
}
if($_GET['page']==""){
$page="1";
}else{
$page=$_GET['page'];
}
?>
<?php
if($_GET['type']!=""){
$counts=0;
if($_GET['type']=="getAll"){
$pages=$_GET['page'];
$url = $_GET['url'];
for($i=0;$i<$pages;$i++){
$ch2 = curl_init();
curl_setopt($ch2, CURLOPT_URL, $url);
curl_setopt($ch2, CURLOPT_FOLLOWLOCATION, TRUE);
curl_setopt($ch2, CURLOPT_SSL_VERIFYHOST, FALSE);
curl_setopt($ch2, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch2, CURLOPT_RETURNTRANSFER, TRUE);
$texts = curl_exec($ch2);
curl_close($ch2);
$dat=getEmail($texts);
for($j=0;$j ";
$counts++;
}
}
}else if($_GET['type']=="getNow"){
$url = $_GET['url2'];
$ch2 = curl_init();
curl_setopt($ch2, CURLOPT_URL, $url);
curl_setopt($ch2, CURLOPT_FOLLOWLOCATION, TRUE);
curl_setopt($ch2, CURLOPT_SSL_VERIFYHOST, FALSE);
curl_setopt($ch2, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch2, CURLOPT_RETURNTRANSFER, TRUE);
$texts = curl_exec($ch2);
curl_close($ch2);
$dat=getEmail($texts);
for($i=0;$i ";
$counts++;
}
}
echo '共采集到数据:'.$counts.'条
';
}
function getEmail($str){
$pattern = "/([a-z0-9-_.]+@[a-z0-9]+.[a-z0-9-_.]+)/";
preg_match_all($pattern,$str,$emailArr);
return $emailArr[0];
}
?>