基本信息
源码名称:php 批量检测百度贴吧是否已有吧主
源码大小:3.13KB
文件格式:.php
开发语言:PHP
更新时间:2016-01-15
友情提示:(无需注册或充值,赞助后即可获取资源下载链接)
嘿,亲!知识可是无价之宝呢,但咱这精心整理的资料也耗费了不少心血呀。小小地破费一下,绝对物超所值哦!如有下载和支付问题,请联系我们QQ(微信同号):78630559
本次赞助数额为: 2 元×
微信扫码支付:2 元
×
请留下您的邮箱,我们将在2小时内将文件发到您的邮箱
源码介绍
<!DOCTYPE html>
<html>
<body>
<?php
//这个是要抓取的url地址 把类似的网址填写进去就可以
$crlUrl="http://tieba.baidu.com/f/fdir?fd=%B9%A4%C5%A9%D2%B5%B2%FA%C6%B7&sd=%C4%DC%D4%B4%2F%D2%B1%BD%F0%2F%BD%A8%B2%C4";
//以上网址一共的页数
$page=18;
function getPageLink($url){
set_time_limit(0);
$html=file_get_contents($url);
$html = iconv("gb2312", "utf-8//IGNORE",$html);
preg_match_all("/<a(s*[^>] s*)href=([\"|']?)([^\"'>\s] )([\"|']?)/ies",$html,$out);
$arrLink=$out[3];
$arrUrl=parse_url($url);
$dir='';
if(isset($arrUrl['path'])&&!empty($arrUrl['path'])){
$dir=str_replace("\\","/",$dir=dirname($arrUrl['path']));
if($dir=="/"){
$dir="";
}
}
if(is_array($arrLink)&&count($arrLink)>0){
$arrLink=array_unique($arrLink);
foreach($arrLink as $key=>$val){
$val=strtolower($val);
if(preg_match('/^#*$/isU',$val)){
unset($arrLink[$key]);
}elseif(preg_match('/^\//isU',$val)){
$arrLink[$key]='http://'.$arrUrl['host'].$val;
}elseif(preg_match('/^javascript/isU',$val)){
unset($arrLink[$key]);
}elseif(preg_match('/^mailto:/isU',$val)){
unset($arrLink[$key]);
}elseif(!preg_match('/^\//isU',$val)&&strpos($val,'http://')===FALSE){
$arrLink[$key]='http://'.$arrUrl['host'].$dir.'/'.$val;
}
}
}
sort($arrLink);
return $arrLink;
}
//遍历每一页的链接
$alllinks=array();
for($i=1;$i<$page;$i ){
$url = $crlUrl.'&pn='.$i;
$pagelinks= getPageLink($url);
$alllinks= array_merge($alllinks,$pagelinks);
}
//取得贴吧的链接
$links=array();
foreach($alllinks as $link)
{
if(strpos($link,"tieba.baidu.com/f?kw=")>0)
array_push($links,$link);
}
//var_dump($links);
//检测贴吧是否有吧主
if(true){
foreach($links as $url)
{
$barname=str_replace("http://tieba.baidu.com/f?kw=","",$url);
$link="http://tieba.baidu.com/bawu2/platform/detailsInfo?word=".$barname."&ie=utf-8";
//$link="http://tieba.baidu.com/bawu2/platform/detailsInfo?word=%E5%9B%9E%E6%94%B6%E9%94%A1&ie=utf-8";
$html = file_get_contents($link);
//<span class="card_menNum" >6</span><span class="card_numLabel">贴子:</span><span class="card_infoNum" >1,900</span>
//"member_num":6,"post_num":1900,"first_class"
$member_num=explode('member_num":',$html);
$member_num=explode(',"post_num":',$member_num[1]);
//var_dump($member_num[0]);
$post_num=explode(',',$member_num[1]);
//var_dump($post_num[0]);
if(strpos($html,"本吧还没有吧主")>0)
{
echo urldecode($barname).">>关注".$member_num[0].">>帖子".$post_num[0].">>还没有吧主>>".$link."";
}
else{
echo urldecode($barname).">>关注".$member_num[0].">>帖子".$post_num[0].">>有吧主>>".$link."";
}
echo "<br/>";
}
}
echo "xxx";
$link="http://tieba.baidu.com/bawu2/platform/detailsInfo?word=%E5%9B%9E%E6%94%B6%E9%94%A1&ie=utf-8";
$html = file_get_contents($link);
$member_num=explode('member_num":',$html);
$member_num=explode(',"post_num":',$member_num[1]);
//var_dump($member_num[0]);
$post_num=explode(',',$member_num[1]);
//var_dump($post_num[0]);
//echo "$member_num".$member_num;
//$html = iconv("gb2312", "utf-8//IGNORE",$html);
//echo $html;
//echo htmlspecialchars($html);
?>
</body>
</html>