使用URLConnection获取网页信息的根本流程

2013-10-13

使用URLConnection获取网页信息的基本流程参考自core java v2, chapter3 Networking.使用URL类可以简单获

使用URLConnection获取网页信息的基本流程

参考自core java v2, chapter3 Networking.

使用URL类可以简单获取网页信息，

package com.ljh.corejava;import java.io.IOException;import java.io.InputStream;import java.net.URL;import java.net.URLConnection;import java.util.List;import java.util.Map;import java.util.Scanner;public class URLConnectionTest {public static void main(String[] args) {try{//1、创建URLConnction.URL url = new URL("http://www.baidu.com");URLConnection connection = url.openConnection();//2、设置connection的属性connection.setConnectTimeout(10000);connection.setReadTimeout(10000);//3.连接connection.connect();//4.获取头部信息之一：获取所有头部信息后再遍历Map<String, List<String>> headers = connection.getHeaderFields();for(Map.Entry<String,List<String>> entry : headers.entrySet()){System.out.println(entry.getKey()+" : ");for(String value : entry.getValue()){System.out.println(value+" , ");}}//4.获取头部信息之二：使用简便方法         System.out.println("----------");         System.out.println("getContentType: " + connection.getContentType());         System.out.println("getContentLength: " + connection.getContentLength());         System.out.println("getContentEncoding: " + connection.getContentEncoding());         System.out.println("getDate: " + connection.getDate());         System.out.println("getExpiration: " + connection.getExpiration());         System.out.println("getLastModifed: " + connection.getLastModified());         System.out.println("----------");                  //5.获取内容         InputStream is = connection.getInputStream();         Scanner sc = new Scanner(is);         while(sc.hasNextLine()){         System.out.println(sc.nextLine());         }                  sc.close();         is.close();}catch(IOException e){e.printStackTrace();}}}

输出结果如下：

null :
HTTP/1.1 200 OK ,
Expires :
Sat, 12 Oct 2013 16:16:20 GMT ,
Set-Cookie :
H_PS_PSSID=; path=/; domain=.baidu.com ,
BDSVRTM=0; path=/ ,
BAIDUID=2CD6C90F50267C4DD25F1DA90D209AB5:FG=1; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com ,
Connection :
Keep-Alive ,
Server :
BWS/1.0 ,
Cache-Control :
private ,
Date :
Sat, 12 Oct 2013 16:16:51 GMT ,
BDQID :
0xad03b06b916405ea ,
Vary :
Accept-Encoding ,
Transfer-Encoding :
chunked ,
P3P :
CP=" OTI DSP COR IVA OUR IND COM " ,
BDPAGETYPE :
1 ,
Content-Type :
text/html;charset=utf-8 ,
BDUSERID :
0 ,
----------
getContentType: text/html;charset=utf-8
getContentLength: -1
getContentEncoding: null
getDate: 1381594611000
getExpiration: 1381594580000
getLastModifed: 0
----------
<!DOCTYPE html><html><head><meta http-equiv="content-type" content="text/html;charset=utf-8"><title>百度一下，你就知道</title><style >html,body{height:100%}html{overflow-y:auto}#wrapper{position:relative;_position:;min-height:100%}#content{padding-bottom:100px;text-align:center}#ftCon{height:100px;position:absolute;bottom:44px;text-align:center;width:100%;margin:0 auto;z-index:0;overflow:hidden}#ftConw{width:720px;margin:0 auto}body{font:12px arial;text-align:;background:#fff}body,p,form,ul,li{margin:0;padding:0;list-style:none}body,form,#fm{position:relative}td{text-align:left}img{border:0}a{color:#00c}a:active{color:#f60}.bg{background-image:url(http://s1.bdstatic.com/r/www/cache/static/global/img/icons_db1b0e67.png);background-repeat:no-repeat;_background-image:url(http://s1.bdstatic.com/r/www/cache/static/global/img/icons_190dda05.gif)}.c-icon{display:inline-block;width:14px;height:14px;vertical-align:text-bottom;font-style normal;overflow:hidden;background:url(http://s1.bdstatic.com/r/www/cache/static/global/img/icons_db1b0e67.png) no-repeat 0 0;_background-image:url(http://s1.bdstatic.com/r/www/cache/static/global/img/icons_190dda05.gif)}.c-icon-triangle-down-blue{background-position:-480px -24px}.c-icon-chevron-unfold2{background-position:-504px -24px}#u{color:#999;padding:4px 10px 5px 0;text-align:right}#u a{margin:0 5px}#u .reg{margin:0}#m{width:720px;margin:0 auto}#nv a,#nv b,.btn,#lk{font-size:14px}#fm{padding-left:110px;text-align:left;z-index:1}input{border:0;padding:0}#nv{height:19px;font-size:16px;margin:0 0 4px;text-align:left;text-indent:137px}.s_ipt_wr{width:418px;height:30px;display:inline-block;margin-right:5px;background-position:0 -288px;border:1px solid #b6b6b6;border-color:#9a9a9a #cdcdcd #cdcdcd #9a9a9a;vertical-align:top}.s_ipt{width:405px;height:22px;font:16px/22px arial;margin:5px 0 0 7px;background:#fff;outline:0;-webkit-appearance:none}.s_btn{width:95px;height:32px;padding-top:2px\9;font-size:14px;background-color:#ddd;background-position:0 -240px;cursor:pointer}.s_btn_h{background-position:-240px -240px}.s_btn_wr{width:97px;height:34px;display:inline-block;background-position:-120px -240px;*position:relative;z-index:0;vertical-align:top}#lg img{vertical-align:top;margin-bottom:3px}#lk{margin:33px 0}#lk span{font:14px "宋体"}#lm{height:60px}#lh{margin:16px 0 5px;word-spacing:3px}.tools{position:absolute;top:-4px;*top:10px;right:7px}#mHolder{width:62px;position:relative;z-index:296;display:none}#mCon{height:18px;line-height:18px;position:absolute;cursor:pointer}#mCon span{color:#00c;cursor:default;display:block}#mCon .hw{text-decoration:underline;cursor:pointer;display:inline-block}#mCon .pinyin{display:inline-block}#mCon .c-icon-chevron-unfold2{margin-left:5px}#mMenu a{width:100%;height:100%;display:block;line-height:22px;text-indent:6px;text-decoration:none;filter:none\9}#mMenu,#user ul{box-shadow:1px 1px 2px #ccc;-moz-box-shadow:1px 1px 2px #ccc;-webkit-box-shadow:1px 1px 2px #ccc;filter:progid:DXImageTransform.Microsoft.Shadow(Strength=2,Direction=135,Color="#cccccc")\9}#mMenu{width:56px;border:1px solid #9b9b9b;list-style:none;position:absolute;right:27px;top:28px;display:none;background:#fff}#mMenu a:hover{background:#ebebeb}#mMenu .ln{height:1px;background:#ebebeb;overflow:hidden;font-size:1px;line-height:1px;margin-top:-1px}#cp,#cp a{color:#666}#seth{display:none;behavior:url(#default#homepage)}#setf{display:none}#sekj{margin-left:14px}#shouji{margin-right:14px}</style><script >function h(obj){obj.style.behavior='url(#default#homepage)';var a = obj.setHomePage('http://www.baidu.com/');}</script></head><body><div id="wrapper"><div id="content"><div id="u"><a href="http://www.baidu.com/gaoji/preferences.html" name="tj_setting">搜索设置</a>|<a href="https://passport.baidu.com/v2/?login&tpl=mn&u=http%3A%2F%2Fwww.baidu.com%2F" name="tj_login" id="lb" onclick="return false;">登录</a><a href="https://passport.baidu.com/v2/?reg&regType=1&tpl=mn&u=http%3A%2F%2Fwww.baidu.com%2F" target="_blank" name="tj_reg" class="reg">注册</a></div><div id="m"><p id="lg"><img src="http://www.baidu.com/img/270%EF%BC%8F129_f01c4e74c976a9e3baf6cfa8a3f97c8f.gif" width="270" height="129" usemap="#mp"><map name="mp"><area shape="rect" coords="0,1,270,129" href="http://www.baidu.com/s?wd=%E9%87%8D%E9%98%B3%E8%8A%82" target="_blank" title="九九重阳，关爱老人"onmousedown="return ns_c({'fm':'behs','tab':'bdlogo'})"></map></p><p id="nv"><a href="http://news.baidu.com">新 闻</a>　<b>网 页</b>　<a href="http://tieba.baidu.com">贴 吧</a>　<a href="http://zhidao.baidu.com">知 道</a>　<a href="http://music.baidu.com">音 乐</a>　<a href="http://image.baidu.com">图 片</a>　<a href="http://v.baidu.com">视 频</a>　<a href="http://map.baidu.com">地 图</a></p><div id="fm"><form name="f" action="/s"><span class="bg s_ipt_wr"><input type="text" name="wd" id="kw" maxlength="100" class="s_ipt"></span><input type="hidden" name="rsv_bp" value="0"><input type="hidden" name="rsv_spt" value="3"><input type="hidden" name="ie" value="utf-8"><span class="bg s_btn_wr"><input type="submit" value="百度一下" id="su" class="bg s_btn" onmousedown="this.className='bg s_btn s_btn_h'" onmouseout="this.className='bg s_btn'"></span></form><span class="tools"><span id="mHolder"><div id="mCon"><span>输入法</span></div></span></span><ul id="mMenu"><li><a href="#" name="ime_hw">手写</a></li><li><a href="#" name="ime_py">拼音</a></li><li class="ln"></li><li><a href="#" name="ime_cl">关闭</a></li></ul></div><p id="lk"><a href="http://baike.baidu.com">百科</a>　<a href="http://wenku.baidu.com">文库</a>　<a href="http://www.hao123.com">hao123</a><span> | <a href="http://www.baidu.com/more/">更多>></a></span></p><p id="lm"></p></div></div><div id="ftCon"><div id="ftConw"><p ><a id="seth" onClick="h(this)" href="/" onmousedown="return ns_c({'fm':'behs','tab':'homepage','pos':0})">把百度设为主页</a><a id="setf" href="http://www.baidu.com/cache/sethelp/index.html" onmousedown="return ns_c({'fm':'behs','tab':'favorites','pos':0})" target="_blank">把百度设为主页</a><span id="sekj"><a href="http://weishi.baidu.com/?shouye" target="_blank" onmousedown="return ns_c({'fm':'behs','tab':'bdbrwlk','pos':1})">安装百度卫士</a></span></p><p id="lh"><a href="http://e.baidu.com/?refer=888" onmousedown="return ns_c({'fm':'behs','tab':'btlink','pos':2})">加入百度推广</a> | <a onmousedown="return ns_c({'fm':'behs','tab':'tj_bang'})" href="http://top.baidu.com">搜索风云榜</a> | <a onmousedown="return ns_c({'fm':'behs','tab':'tj_about'})" href="http://home.baidu.com">关于百度</a> | <a onmousedown="return ns_c({'fm':'behs','tab':'tj_about_en'})" href="http://ir.baidu.com">About Baidu</a></p><p id="cp">©2013 Baidu <a href="/duty/" name="tj_duty">使用百度前必读</a> 京ICP证030173号 <img src="http://www.baidu.com/cache/global/img/gs.gif"></p></div></div></div></body><script>var bds={se:{},comm : {ishome : 1,sid : "",user : "",username : "",sugHost : "http://suggestion.baidu.com/su",loginAction : []}}</script><script type="text/javascript" src="http://s1.bdstatic.com/r/www/cache/static/global/js/home_f813a739.js" charset="utf-8"></script><script>var bdUser = null;var w=window,d=document,n=navigator,k=d.f.wd,a=d.getElementById("nv").getElementsByTagName("a"),isIE=n.userAgent.indexOf("MSIE")!=-1&&!window.opera;(function(){if(/q=([^&]+)/.test(location.search)){k.value=decodeURIComponent(RegExp["\x241"])}})();if(n.cookieEnabled){bds.se.sug();};function addEV(o, e, f){if(w.attachEvent){o.attachEvent("on" + e, f);}else if(w.addEventListener){ o.addEventListener(e, f, false);}}function G(id){return d.getElementById(id);}function ns_c(q){var p = encodeURIComponent(window.document.location.href), sQ = '', sV = '', mu='', img = window["BD_PS_C" + (new Date()).getTime()] = new Image();for (v in q) {sV = q[v];sQ += v + "=" + sV + "&";} mu= "&mu=" + p ;img.src = "http://nsclick.baidu.com/v.gif?pid=201&pj=www&rsv_sid=&" + sQ + "path="+p+"&t="+new Date().getTime();return true;}if(/\bbdime=[12]/.test(d.cookie)){document.write('<script src="' + "http://s1.bdstatic.com/r/www/cache/static/ime/js/openime_ceac1c4e.js" + '" charset="utf-8"><\/script>');}(function(){var u = G("u").getElementsByTagName("a"), nv = G("nv").getElementsByTagName("a"), lk = G("lk").getElementsByTagName("a"), un = "";var tj_nv = ["news","tieba","zhidao","mp3","img","video","map"];var tj_lk = ["baike","wenku","hao123","more"];un = bds.comm.user == "" ? "" : bds.comm.user;function _addTJ(obj){addEV(obj, "mousedown", function(e){var e = e || window.event;var target = e.target || e.srcElement;ns_c({'fm':'behs','tab':target.name||'tj_user','un':encodeURIComponent(un)});});}for(var i = 0; i < u.length; i++){_addTJ(u[i]);}for(var i = 0; i < nv.length; i++){nv[i].name = 'tj_' + tj_nv[i];}for(var i = 0; i < lk.length; i++){lk[i].name = 'tj_' + tj_lk[i];}})();(function() {var links = {'tj_news': ['word', 'http://news.baidu.com/ns?tn=news&cl=2&rn=20&ct=1&ie=utf-8'],'tj_tieba': ['kw', 'http://tieba.baidu.com/f?ie=utf-8'],'tj_zhidao': ['word', 'http://zhidao.baidu.com/search?pn=0&rn=10&lm=0'],'tj_mp3': ['key', 'http://music.baidu.com/search?fr=ps&ie=utf-8'],'tj_img': ['word', 'http://image.baidu.com/i?ct=201326592&cl=2&nc=1&lm=-1&st=-1&tn=baiduimage&istype=2&fm=&pv=&z=0&ie=utf-8'],'tj_video': ['word', 'http://video.baidu.com/v?ct=301989888&s=25&ie=utf-8'],'tj_map': ['wd', 'http://map.baidu.com/?newmap=1&ie=utf-8&s=s'],'tj_baike': ['word', 'http://baike.baidu.com/search/word?pic=1&sug=1&enc=utf8'],'tj_wenku': ['word', 'http://wenku.baidu.com/search?ie=utf-8']};var domArr = [G('nv'), G('lk'),G('cp')],kw = G('kw');for (var i = 0, l = domArr.length; i < l; i++) {domArr[i].onmousedown = function(e) {e = e || window.event;var target = e.target || e.srcElement,name = target.getAttribute('name'),items = links[name],reg = new RegExp('^\\s+|\\s+\x24'),key = kw.value.replace(reg, '');if (items) {if (key.length > 0) {var wd = items[0], url = items[1],url = url + ( name === 'tj_map' ? encodeURIComponent('&' + wd + '=' + key) : ( ( url.indexOf('?') > 0 ? '&' : '?' ) + wd + '=' + encodeURIComponent(key) ) );target.href = url;} else {target.href = target.href.match(new RegExp('^http:\/\/.+\.baidu\.com'))[0];}}name && ns_c({'fm': 'behs','tab': name,'query': encodeURIComponent(key),'un': encodeURIComponent(bds.comm.user || '') });};}})();addEV(w,"load",function(){k.focus()});w.onunload=function(){};</script><script type="text/javascript" src="http://s1.bdstatic.com/r/www/cache/static/global/js/tangram-1.3.4c1.0_07038476.js"></script><script type="text/javascript" src="http://s1.bdstatic.com/r/www/cache/static/user/js/u_ec0ebfe1.js" charset="utf-8"></script><script>try{document.cookie="WWW_ST=;expires=Sat, 01 Jan 2000 00:00:00 GMT";baidu.on(document.forms[0],"submit",function(){var _t=new Date().getTime();document.cookie = "WWW_ST=" + _t +";expires=" + new Date(_t + 10000).toGMTString()})}catch(e){}</script></html>
<script> var _trace_page_logid = 0980738871; </script>

热点排行

编程

使用URLConnection获取网页信息的根本流程