1 需求：比如要從這樣一個網頁上抓取資料 

這個請求最後面的uid其實是百度地圖上查到該點的uid(也就是5ef5edbdc64c1bb49e9d6899)，我的資料庫裡面已經獲取了武漢的房地產的uid，現在要通過uid獲取詳細資訊。
先從一個著手，再多的資料也是迴圈抓取了。

2 傳送請求到網頁 ，用到HttpURLConnection類

package connection;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

public class ConnectionUtil {
public static String Connect(String address){
HttpURLConnection conn = null;
URL url = null;
InputStream in = null;
BufferedReader reader = null;
StringBuffer stringBuffer = null;
try {
url = new URL(address);
conn = (HttpURLConnection) url.openConnection();
conn.setConnectTimeout(5000);
conn.setReadTimeout(5000);
conn.setDoInput(true);
conn.connect();
in = conn.getInputStream();
reader = new BufferedReader(new InputStreamReader(in));
stringBuffer = new StringBuffer();
String line = null;
while((line = reader.readLine()) != null){
stringBuffer.append(line);
}
} catch (Exception e) {
e.printStackTrace();
} finally{
conn.disconnect();
try {
in.close();
reader.close();
} catch (Exception e) {
e.printStackTrace();
}
}

return stringBuffer.toString();
}
}
3 接收伺服器返回的頁面html資料 
返回了html字串之後，首先要明確需要抓取的資料是哪些，分析網頁的特點。 
比如我現在要抓取的資料有： 

        圖片url
        價格
        房屋型別
        建築型別
        建築年代
        容積率
        物業費
        物業公司
        開發商

分析好結構之後就好寫正則表示式了，用來匹配獲取。

4 進行解析

package main;

import connection.ConnectionUtil;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Analyze {

//使用時呼叫此方法，傳入uid，如 5ef5edbdc64c1bb49e9d6899，返回的是一個字串，可以打印出來看一下
public String regexMain(String uid) {
String url="http://map.baidu.com/detail?qt=ninf&from=housezt&detail=house&uid="+uid;
String result = ConnectionUtil.Connect(url);
return getHouseInfo(result);
}

private String getHouseInfo(String targetStr) {

StringBuilder lastInfo=new StringBuilder();
//提取圖片url
Pattern imgpattern=Pattern.compile("<img class=\"img-large\".*\" />");
Matcher imgmatcher=imgpattern.matcher(targetStr);
while (imgmatcher.find()){
String imgString=imgmatcher.group();
int n=imgString.lastIndexOf("=\"");
String imgUrl=imgString.substring(n+2,imgString.length()-3);
//System.out.println("imgRul:"+imgUrl);
lastInfo.append("圖片url:"+imgUrl+"\n");
}
//首先提取出包含房產資訊的html片段，再分別處理
Pattern pattern1 = Pattern
.compile("fcg\">\\w*.+\\s*<dd>\\w*.+</dd>");
Matcher matcher1 = pattern1.matcher(targetStr);
String info = "";
while (matcher1.find()) {
info = matcher1.group(); //提取出的片段
Pattern pattern2 = Pattern
.compile("f24 fcr\">[0-9]+");
Matcher matcher2 = pattern2.matcher(info);
while (matcher2.find()) {

String price = matcher2.group().substring(9); //提取出價格
//System.out.println("價格：" + price);
lastInfo.append("價格:"+price+"元/平米\n");
}

Pattern pattern3 = Pattern
.compile("房屋型別：</dt>\\s*<dd>[\\u4e00-\\u9fa5]+( *[\\u4e00-\\u9fa5]+)*");
Matcher matcher3 = pattern3.matcher(info);
String houseType = ""; //可能有的沒有
while (matcher3.find()) {
int n = matcher3.group().lastIndexOf(">");
houseType = matcher3.group().substring(n + 1);
}
//ystem.out.println("房屋型別：" + houseType);
lastInfo.append("房屋型別:"+houseType+"\n");
//建築型別同理
Pattern pattern4 = Pattern
.compile("建築型別：</dt>\\s*<dd>[\\u4e00-\\u9fa5]+( *[\\u4e00-\\u9fa5]+)*");
Matcher matcher4 = pattern4.matcher(info);
String blockType = ""; //可能有的
while (matcher4.find()) {
int n = matcher4.group().lastIndexOf(">");
blockType = matcher4.group().substring(n + 1);
}
//System.out.println("建築型別：" + blockType);
lastInfo.append("建築型別:"+blockType+"\n");
//建築年代
Pattern pattern5 = Pattern
.compile("建築年代：</dt>\\s*<dd>[0-9]+");
Matcher matcher5 = pattern5.matcher(info);
String blockAge = ""; //可能有的沒有
while (matcher5.find()) {
int n = matcher5.group().lastIndexOf(">");
blockAge = matcher5.group().substring(n + 1);
}
//System.out.println("建築年代：" + blockAge);
lastInfo.append("建築年代:"+blockAge+"\n");
//容積率
Pattern pattern6 = Pattern
.compile("容積率：</dt>\\s*<dd>[0-9]+\\.[0-9]+");
Matcher matcher6 = pattern6.matcher(info);
String FAR = ""; //可能有的沒有
while (matcher6.find()) {
int n = matcher6.group().lastIndexOf(">");
FAR = matcher6.group().substring(n + 1);
}
//System.out.println("容積率：" + FAR);
lastInfo.append("容積率:"+FAR+"\n");
//物業費
Pattern pattern9 = Pattern
.compile("物業費：</dt>\\s*<dd>[0-9]+\\.[0-9]+");
Matcher matcher9 = pattern9.matcher(info);
String fee = ""; //可能有的沒有
while (matcher9.find()) {
int n = matcher9.group().lastIndexOf(">");
fee = matcher9.group().substring(n + 1);
}
//System.out.println("物業費：" + fee);
lastInfo.append("物業費:"+fee+"元/平米/月\n");
//物業公司
Pattern pattern7 = Pattern
.compile("物業公司：</dt>\\s*<dd>[\\u4e00-\\u9fa5]+( *[\\u4e00-\\u9fa5]+)*");
Matcher matcher7 = pattern7.matcher(info);
String pManage = ""; //可能有的沒有
while (matcher7.find()) {
int n = matcher7.group().lastIndexOf(">");
pManage = matcher7.group().substring(n + 1);
}
//System.out.println("物業公司：" + pManage);
lastInfo.append("物業公司:"+pManage+"\n");
//開發商
Pattern pattern8 = Pattern
.compile("開發商：</dt>\\s*<dd>[\\u4e00-\\u9fa5]+( *[\\u4e00-\\u9fa5]+)*");
Matcher matcher8 = pattern8.matcher(info);
String company = ""; //可能有的沒有
while (matcher8.find()) {
int n = matcher8.group().lastIndexOf(">");
pManage = matcher8.group().substring(n + 1);
}
//System.out.println("開發商：" + pManage);
lastInfo.append("開發商:"+pManage+"\n");
}
return lastInfo.toString();
}

}