JAVA爬虫 爬取 https://www.zhipin.com/?ka=header-home 出现问题 ,自己使用了ip代理
public static Elements getJsoupDocGet(String url) throws IOException {
Document doc = null;
Random random = new Random();
int i = 0;
while (i < 10 && doc == null) {
try {
trustEveryone();
IpProxy ipProxy = getRandomIP();
System.out.println(ipProxy.getIp()+" "+ipProxy.getPort());
System.setProperty("http.maxRedirects", "50");
System.getProperties().setProperty("proxySet", "true");
System.getProperties().setProperty("http.proxyHost", ipProxy.getIp());
System.getProperties().setProperty("http.proxyPort", ipProxy.getPort());
doc =
Jsoup.connect(url)
.userAgent(getUserAgent(ua))
.header("Accept-Encoding", "gzip, deflate,br")
.header("Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3")
.header("User-Agent", "Mozilla/31.0 (compatible; MSIE 10.0; Windows NT; DigExt)")
.header("Content-Type", "application/x-www-form-urlencoded")
.header("Cache-Control","no-cache" )
.header("Pragma", "no-cache")
.header("Upgrade-Insecure-Requests", "1")
.header("Connection", "Keep-alive")
.header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8")
.ignoreContentType(true)
.ignoreHttpErrors(true)
.timeout(1000 * 60)
.cookie("auth", "token")
.post();
if (doc != null) {
System.out.println("代理成功");
//System.out.println(doc.toString());
return doc.select("body");
}
} catch (Exception e) {
}
i++;
}
if (doc == null) {
doc = Jsoup.connect(url).header("Accept", "*/*").header("Accept-Encoding", "gzip, deflate")
.header("Accept-Encoding", "gzip, deflate")
.header("Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3")
.header("User-Agent", "Mozilla/31.0 (compatible; MSIE 10.0; Windows NT; DigExt)")
.header("Content-Type", "application/x-www-form-urlencoded")
.header("Cache-Control","no-cache" )
.header("Pragma", "no-cache")
.header("Upgrade-Insecure-Requests", "1")
.header("Connection", "Keep-alive")
.header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8")
.timeout(1000 * 60)
.userAgent(getUserAgent(ua))
.cookie("auth", "token")
.post();
}
return doc.select("body");
}
爬取网站时出现了下面的问题
但是有浏览器可以正常看，且代码也是完整的
代理成功
<body>
<div style="font-size: 12px;">
请稍后...
</div>
<input type="hidden" id="page_key_name" value="security_bridge">
<script>
var _T=_T||[];!function(){var b,a=document.createElement("script");a.src="https://static.zhipin.com/library/js/analytics/ka.js",b=document.getElementsByTagName("script")[0],b.parentNode.insertBefore(a,b)}(),function(){var e,f,g,h,a=function(a,b){var c,d,e,f;"object"!=typeof a&&(a=[a]),c=document.getElementsByTagName("head").item(0)||document.documentElement,d=new Array,e=a.length-1,f=function(g){d[g]=document.createElement("script"),d[g].setAttribute("type","text/javascript"),d[g].setAttribute("charset","UTF-8"),d[g].onload=d[g].onreadystatechange=function(){this.onload=this.onreadystatechange=null,this.parentNode.removeChild(this),g!=e?f(g+1):"function"==typeof b&&b()},d[g].setAttribute("src",a[g]),c.appendChild(d[g])},f(0)},b=function(a){var b=new RegExp("(^|&)"+a+"=([^&]*)(&|$)"),c=window.location.search.substr(1).match(b);return null!=c?unescape(c[2]):null},c={get:function(a){var b,c=new RegExp("(^| )"+a+"=([^;]*)(;|$)");return(b=document.cookie.match(c))?unescape(b[2]):null},set:function(a,b,c,d,e){var g,f=a+"="+encodeURIComponent(b);c&&(g=new Date(c).toGMTString(),f+=";expires="+g),f=d?f+";domain="+d:f,f=e?f+";path="+e:f,document.cookie=f}};window.location.href,e=decodeURIComponent(b("seed"))||"",f=b("ts"),g=b("name"),h=decodeURIComponent(b("callbackUrl")),e&&f&&g&&a("security-js/"+g+".js",function(){var a=(new Date).getTime()+2304e5,b=".zhipin.com",d=(new ABC).z(e,parseInt(f));window.location.host.indexOf(".weizhipin.com")>-1&&(b=".weizhipin.com"),c.set("__zp_stoken__",d,a,b,"/");try{_T.sendEvent("security_bridge_"+d)}catch(g){}h?window.location.href=h:window.history.back()})}();
</script>
</body>
求大佬给出解答方式，求救救，自己在网上搜的设置ip代理代码，应该没错，别的网页可以，只有自己爬取的网页有问题
