爬取网页时,获取的json数据中,字符串都是问号,如下图
尝试修改编码格式为utf-8,gbk等,都不行,后来给header加accept后编码格式正确,问号转换字符串成功
Request request = new Request.Builder()
.url(url)
.header("Accept", "application/json, text/javascript, */*; q=0.01")
.build();
主要代码如下
package com.msun.util.webConnect;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import net.sf.json.JSONArray;
import net.sf.json.JSONObject;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.Response;
import com.msun.util.FileUtil;
public class CreditchinaUtil {
public static void main(String[] args) {
String url="http://www.baidu.com"
//获取信息
getCreditInfo(url);
}
private static void getCreditInfo(String url) {
// TODO Auto-generated method stub
OkHttpClient okHttpClient = new OkHttpClient();
Request request = new Request.Builder()
.url(url)
.header("Accept", "application/json, text/javascript, */*; q=0.01")
.build();
try {
Response response = okHttpClient.newCall(request).execute();
if (response.isSuccessful()) {
String json = response.body().string();
JSONArray jsonArray = JSONArray.fromObject(json);
System.out.println(jsonArray.size());
for (Object object : jsonArray) {
String number = (String) JSONObject.fromObject(object).get("CARDNUMBER");
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
}
}