网页抓取

//根据书名，获取相关图书的ISBN号。抓取的是豆瓣读书的搜索页面。
 1 package cn.edu.xmu.zgy;
 2 
 3 import java.io.BufferedReader;
 4 import java.io.InputStreamReader;
 5 import java.net.HttpURLConnection;
 6 import java.net.URL;
 7 import java.util.ArrayList;
 8 
 9 public class WebpageCapture {
10     public ArrayList<String> captureHtml(String urls,String begins,String ends) throws Exception {
11         String strURL =urls;
12         URL url = new URL(strURL);
13         HttpURLConnection httpConn = (HttpURLConnection) url.openConnection();
14         InputStreamReader input = new InputStreamReader(
15                 httpConn.getInputStream(), "utf-8");
16         BufferedReader bufReader = new BufferedReader(input);
17         String line = "";
18         StringBuilder contentBuf = new StringBuilder();
19         while ((line = bufReader.readLine()) != null) {
20             contentBuf.append(line);
21         }
22         String buf = contentBuf.toString();
23         ArrayList<String> al=new ArrayList<String>();
24         while(true){
25         int beginIx = buf.indexOf(begins);
26         
27         if(beginIx==-1)
28             break;
29         String result = buf.substring(beginIx);
30         int endIx = result.indexOf(ends);
31         if(endIx==-1)
32             break;
33         buf=result.substring(endIx+10);
34         result = result.substring(0, endIx);
35         al.add(result);
36         //System.out.println("captureHtml()的结果：\n" + result);
37         }
38         return al;
39     }
40         
41 
42     public void captureJavascript(String postid) throws Exception {
43         String strURL = "http://www.kiees.cn/sf.php?wen=" + postid
44                 + "&channel=";
45         URL url = new URL(strURL);
46         HttpURLConnection httpConn = (HttpURLConnection) url.openConnection();
47         InputStreamReader input = new InputStreamReader(
48                 httpConn.getInputStream(), "utf-8");
49         BufferedReader bufReader = new BufferedReader(input);
50         String line = "";
51         StringBuilder contentBuf = new StringBuilder();
52         while ((line = bufReader.readLine()) != null) {
53             contentBuf.append(line);
54         }
55         System.out.println("captureJavascript()的结果：\n" + contentBuf.toString());
56     }
57 
58 public static void main(String[] args) {
59         WebpageCapture demo = new WebpageCapture();
60         try {
61             String ip="算法导论";
62             String strURL = "http://book.douban.com/subject_search?search_text="+ip+"&cat=1001";
63             String begin="a class=\"nbg\" href=\"http://book.";
64             String end="/\" "+
65 "  onclick=&#34";
66             ArrayList<String> AL1=new ArrayList<String>();
67             ArrayList<String> AL2=new ArrayList<String>();
68             String result;
69             AL1=demo.captureHtml(strURL,begin,end);
70             for(int i=0;i<AL1.size();i++)
71             {
72                 AL1.set(i, AL1.get(i).substring(AL1.get(i).indexOf("http:")));
73                 System.out.println(AL1.get(i));
74             }
75             
76             begin="ISBN:</span> ";
77             end="<br/>";
78             for(int i=0;i<AL1.size();i++){
79             strURL=AL1.get(i);
80             AL2=demo.captureHtml(strURL,begin,end);
81             AL2.set(0,  AL2.get(0).substring(13));
82             System.out.println(AL2.get(0));
83             }
84             //demo.captureJavascript("107818590577");
85         } catch (Exception e) {
86             e.printStackTrace();
87         }
88     }
89 
90 
91 }
View Code

 

参考链接：http://blog.csdn.net/zgyulongfei/article/details/7909006

 

网页图片下载：http://blog.csdn.net/oyzl68/article/details/9706373

代码很好

 

附带一个看不懂的抓取：http://www.oschina.net/code/snippet_1021353_35133?p=1

posted on 2015-05-12 18:03  蓝 鸟  阅读(212)  评论(0)  编辑  收藏  举报

导航