我是一个新手，想使用php抓取微信页面的正文和标题，标题直接用正则表达式|(.*?)<\/title>|i</code>就抓取到了，但是正文我想的是<code>|>(.*?)<\/|i</code>匹配标签间的内容，再去掉空格，但是还是会匹配到一堆标签，是怎么回事？或者说有其他更好的方法吗？求指教！</p>
<p>http://mp.weixin.qq.com/s?__biz=MzA5NTQ2NjUzMA==&mid=207136729&...</p>
<p>这是一般的微信文章内容链接</p>
<p>下面是这链接的页面代码</p>
<pre class='brush:php;toolbar:false;'><code><br><!DOCTYPE html><html> <head> <script type="text/javascript">
var sampling = Math.random() < 0.001;
var page_begintime = (+new Date());
(sampling) && ((new Image()).src = "http://isdspeed.qq.com/cgi-bin/r.cgi?flag1=7839&flag2=7&flag3=8&15=1000&r=" + Math.random());
var biz = "MzA5NTQ2NjUzMA==";
var sn = "a82af7b7ba0bee9a7017b607dc7e5d4b" || "";
var mid = "207136729" || "";
var idx = "1" || "" ;
//辟谣需求
var is_rumor = ""*1;
var norumor = ""*1;
if (!!is_rumor&&!norumor){
if (!document.referrer || document.referrer.indexOf("mp.weixin.qq.com/mp/rumor") == -1){
location.href = "http://mp.weixin.qq.com/mp/rumor?action=info&__biz=" + biz + "&mid=" + mid + "&idx=" + idx + "&sn=" + sn + "#wechat_redirect";
}
}
//原创需求，需要跳转到中间页
/*
var copyrightInfo = {
display_source : ""*1,
nocopyrightsource : ""*1
};
if (!!copyrightInfo.display_source&&!copyrightInfo.nocopyrightsource){
if (!document.referrer || document.referrer.indexOf("mp.weixin.qq.com/mp/reprint") == -1){
location.href = "http://mp.weixin.qq.com/mp/reprint?action=info&__biz=" + biz + "&mid=" + mid + "&idx=" + idx + "&sn=" + sn + "#wechat_redirect";
}
}*/
</script> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"><link rel="dns-prefetch" href="//res.wx.qq.com"><link rel="dns-prefetch" href="//mmbiz.qpic.cn"><meta http-equiv="X-UA-Compatible" content="IE=edge"><meta name="viewport" content="width=device-width,initial-scale=1.0,maximum-scale=1.0,user-scalable=0" /><link rel="shortcut icon" type="image/x-icon" href="http://res.wx.qq.com/mmbizwap/zh_CN/htmledition/images/icon/common/favicon22c41b.ico"><meta name="apple-mobile-web-app-capable" content="yes"><meta name="apple-mobile-web-app-status-bar-style" content="black"><meta name="format-detection" content="telephone=no"><script type="text/javascript">
var uin = "";
var key = "";
var pass_ticket = "";
String.prototype.html= function(encode) {
var replace =["'", "'", """, '"', " ", " ", ">", ">", "<", "<", "&", "&", "¥", "¥"];
//console.log(replace);
if(encode){
replace.reverse();
}
for (var i=0,str=this;i< replace.length;i+= 2){
str=str.replace(new RegExp(replace[i],'g'),replace[i+1]);
}
return str;
};
pass_ticket = encodeURIComponent(pass_ticket.html(false).html(false).replace(/\s/g,"+"));
</script> <title>Living Music校园歌唱大赛半决赛距离开赛还有？？？
提交
我的评论
加载中
已评论
2015-04-27 gzgsytw gzgsytw
gzgsytw ![]()
gzgsytw0
校园内有关团委的一切动态一切资讯都可在这里接收查找。
阅读
举报
![]()
微信扫一扫
关注该公众号
0 
11
2225