注:本程序可能很是適合那些作百度貼吧營銷的朋友。php
去逛百度貼吧的時候,常常會看到樓主分享一些資源,要求留下郵箱,樓主纔給發。curl
對於一個熱門的帖子,留下的郵箱數量是很是多的,樓主須要一個一個的去複製那些回覆的郵箱,而後再粘貼發送郵件,不是被折磨死就是被累死。無聊至極寫了一個抓取百度貼吧郵箱數據的程序,須要的拿走。url
程序實現了一鍵抓取帖子所有郵箱和分頁抓取郵箱兩個功能,界面懶得作了,效果以下:spa
老規矩,直接貼源碼code
<?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']; } ?> <form action="" method="get"> <input type="hidden" value="getAll" name="type" /> <table> <tr> <td>帖子連接:</td><td><input type="text" name="url" value="http://tieba.baidu.com/p/2314539885" style="width:300px;" /></td> </tr> <tr> <td>總頁數:</td><td><input type="text" name="page" style="width:300px;" value="<?php echo $page;?>" /></td> </tr> <tr> <td colspan=2><input type="submit" value="抓取所有郵箱數據" /></td> </tr> </table> </form> <form action="" method="get"> <input type="hidden" value="getNow" name="type" /> <table> <tr> <td>帖子連接:</td><td><input type="text" name="url2" value="<?php echo $url2;?>" style="width:300px;" /></td> </tr> <tr> <td colspan=2><input type="submit" value="抓取當前頁面郵箱數據" /></td> </tr> </table> </form> <?php if($_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<count($dat);$j++){ echo $dat[$j]."<br />"; $counts++; } } }else if($_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<count($dat);$i++){ echo $dat[$i]."<br />"; $counts++; } } echo '<h2>共採集到數據:'.$counts.'條</h2>'; } function getEmail($str){ $pattern = "/([a-z0-9\-_\.]+@[a-z0-9]+\.[a-z0-9\-_\.]+)/"; preg_match_all($pattern,$str,$emailArr); return $emailArr[0]; } ?>