闲来无事,刚学会把git部署到远程服务器,没事做,所以简单做了一个抓取网页信息的小工具,里面的一些数值如果设成参数的话可能扩展性能会更好!希望这是一个好的开始把,也让我对字符串的读取掌握的更加熟练了,值得注意的是JAVA1.8 里面在使用String拼接字符串的时候,会自动把你要拼接的字符串用StringBulider来处理,大大优化了String 的性能,闲话不多说,show my XXX code~
运行效果:
首先打开百度百科,搜索词条,比如“演员”,再按F12查看源码
然后抓取你想要的标签,注入LinkedHashMap里面就ok了,很简单是吧!看看代码罗
1 import java.io.BufferedReader;
2 import java.io.IOException;
3 import java.io.InputStreamReader;
4 import java.net.HttpURLConnection;
5 import java.net.URL;
6 import java.util.*;
7
8 /**
9 * Created by chunmiao on 17-3-10.
10 */
11 public class ReadBaiduSearch {
12
13 //储存返回结果
14 private LinkedHashMap<String,String> mapOfBaike;
15
16
17 //获取搜索信息
18 public LinkedHashMap<String,String> getInfomationOfBaike(String infomationWords) throws IOException {
19 mapOfBaike = getResult(infomationWords);
20 return mapOfBaike;
21 }
22
23 //通过网络链接获取信息
24 private static LinkedHashMap<String, String> getResult(String keywords) throws IOException {
25 //搜索的url
26 String keyUrl = "http://baike.baidu.com/search?word=" + keywords;
27 //搜索词条的节点
28 String startNode = "<dl class=\"search-list\">";
29 //词条的链接关键字
30 String keyOfHref = "href=\"";
31 //词条的标题关键字
32 String keyOfTitle = "target=\"_blank\">";
33
34 String endNode = "</dl>";
35
36 boolean isNode = false;
37
38 String title;
39
40 String href;
41
42 String rLine;
43
44 LinkedHashMap<String,String> keyMap = new LinkedHashMap<String,String>();
45
46 //开始网络请求
47 URL url = new URL(keyUrl);
48 HttpURLConnection urlConnection = (HttpURLConnection) url.openConnection();
49 InputStreamReader inputStreamReader = new InputStreamReader(urlConnection.getInputStream(),"utf-8");
50 BufferedReader bufferedReader = new BufferedReader(inputStreamReader);
51
52 //读取网页内容
53 while ((rLine = bufferedReader.readLine()) != null){
54 //判断目标节点是否出现
55 if(rLine.contains(startNode)){
56 isNode = true;
57 }
58 //若目标节点出现,则开始抓取数据
59 if (isNode){
60 //若目标结束节点出现,则结束读取,节省读取时间
61 if (rLine.contains(endNode)) {
62 //关闭读取流
63 bufferedReader.close();
64 inputStreamReader.close();
65 break;
66 }
67 //若值为空则不读取
68 if (((title = getName(rLine,keyOfTitle)) != "") && ((href = getHref(rLine,keyOfHref)) != "")){
69 keyMap.put(title,href);
70 }
71 }
72 }
73 return keyMap;
74 }
75
76 //获取词条对应的url
77 private static String getHref(String rLine,String keyOfHref){
78 String baikeUrl = "http://baike.baidu.com";
79 String result = "";
80 if(rLine.contains(keyOfHref)){
81 //获取url
82 for (int j = rLine.indexOf(keyOfHref) + keyOfHref.length();j < rLine.length()&&(rLine.charAt(j) != '\"');j ++){
83 result += rLine.charAt(j);
84 }
85 //获取的url中可能不含baikeUrl,如果没有则在头部添加一个
86 if(!result.contains(baikeUrl)){
87 result = baikeUrl + result;
88 }
89 }
90 return result;
91 }
92
93 //获取词条对应的名称
94 private static String getName(String rLine,String keyOfTitle){
95 String result = "";
96 //获取标题内容
97 if(rLine.contains(keyOfTitle)){
98 result = rLine.substring(rLine.indexOf(keyOfTitle) + keyOfTitle.length(),rLine.length());
99 //将标题中的内容含有的标签去掉
100 result = result.replaceAll("<em>|</em>|</a>|<a>","");
101 }
102 return result;
103 }
104
105 }