1 package cn.xls.util;
2
3 import cn.xls.pojo.City;
4 import org.jsoup.Jsoup;
5 import org.jsoup.nodes.Document;
6 import org.jsoup.nodes.Element;
7 import org.jsoup.select.Elements;
8
9 import java.io.IOException;
10 import java.util.ArrayList;
11 import java.util.List;
12
13 /**
14 * @program:
15 * @description: 获取城市信息
16 * @author: l
17 */
18 public class CityInfoUtil {
19
20 public static List<City> getProvinceData(String requestUrl) {
21 List<City> lists = new ArrayList<City>();
22 try {
23 Document document = Jsoup.connect(requestUrl).timeout(50000).maxBodySize(0).get();
24 //获取所有的省份
25 Elements provinceList = document.select("tr[class='provincetr']").select("td").select("a");
26 //遍历省份
27 for (Element element : provinceList) {
28 //拼接当前省份下的城市地址
29 String url1 = requestUrl.replace("index.html", element.attr("href"));
30 Document document1 = Jsoup.connect(url1).timeout(50000).maxBodySize(0).get();
31
32 //获取该省份下所有城市(第一列为城市区号,第二列为城市名)
33 Elements citys = document1.select("tr[class='citytr']").select("td:eq(1)").select("a");
34 String province = element.html();
35 System.out.println("当前省份 : " + province);
36 System.out.println("当前省份下有 : " + citys.size() + " 个城市");
37 //遍历城市
38 for (Element element1 : citys) {
39 // System.out.println("城市 : " + element1.html());
40 //拼接当前城市下的区域地址
41 String url2 = requestUrl.replace("index.html", element1.attr("href"));
42 Document document2 = Jsoup.connect(url2).timeout(50000).maxBodySize(0).get();
43
44 //获取该城市下所有区域(第一列为区域区号,第二列为区域名)
45 Elements areas = document2.select("tr[class=countytr] td:eq(1)").select("a");
46 String city = element1.html();
47 System.out.println("当前城市 : " + city);
48 System.out.println("当前城市下有 : " + areas.size() + " 个区");
49 for (Element element2 : areas) {
50 System.out.println("区域 : " + element2.html());
51 }
52 }
53 System.out.println("-----------");
54 }
55 } catch (IOException e) {
56 e.printStackTrace();
57 }
58 return lists;
59 }
60
61 //测试
62 public static void main(String[] args) {
63 List<City> lists = getProvinceData("http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/index.html");
64 }
65 }
区域 : 呼和浩特金海工业园区
区域 : 呼和浩特经济技术开发区
城市 : 包头市
java.net.SocketTimeoutException: Read timed out
at java.net.SocketInputStream.socketRead0(Native Method)
at java.net.SocketInputStream.socketRead(SocketInputStream.java:116)
at java.net.SocketInputStream.read(SocketInputStream.java:170)
at java.net.SocketInputStream.read(SocketInputStream.java:141)
at java.io.BufferedInputStream.fill(BufferedInputStream.java:246)
at java.io.BufferedInputStream.read1(BufferedInputStream.java:286)
at java.io.BufferedInputStream.read(BufferedInputStream.java:345)
at sun.net.www.http.HttpClient.parseHTTPHeader(HttpClient.java:704)
at sun.net.www.http.HttpClient.parseHTTP(HttpClient.java:647)
at sun.net.www.protocol.http.HttpURLConnection.getInputStream0(HttpURLConnection.java:1535)
at sun.net.www.protocol.http.HttpURLConnection.getInputStream(HttpURLConnection.java:1440)
at java.net.HttpURLConnection.getResponseCode(HttpURLConnection.java:480)
at org.jsoup.helper.HttpConnection$Response.execute(HttpConnection.java:750)
at org.jsoup.helper.HttpConnection$Response.execute(HttpConnection.java:722)
at org.jsoup.helper.HttpConnection.execute(HttpConnection.java:306)
at org.jsoup.helper.HttpConnection.get(HttpConnection.java:295)
at cn.xls.util.CityInfoUtil.getProvinceData(CityInfoUtil.java:49)
at cn.xls.util.CityInfoUtil.main(CityInfoUtil.java:78)
每次打印了四分之一左右的数据后就会超时,请问该怎么解决啊?
正在学习怎么用jsoup爬取数据,请多指教来自 “ ITPUB博客 ” ,链接:https://blog.itpub.net/4547/viewspace-3143871/ ,如需转载,请注明出处,否则将追究法律责任。