由于所爬取的网站需要验证码,通过网页的开发人员工具【F12】及在线http post,get接口测试请求工具(http://coolaf.com/)发现访问时加上请求头header 信息时可以跳过验证码校验。
而且该网站只接受post请求,对提交的参数也只接受json格式,否则请求失败。
现将通过 post 方式提交json参数的方法记录如下:
import java.io.UnsupportedEncodingException;
import java.net.URI;
import java.net.URLDecoder;
import java.util.ArrayList;
import java.util.List;
import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.client.methods.HttpRequestBase;
import org.apache.http.client.utils.URIBuilder;
import org.apache.http.entity.StringEntity;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClientBuilder;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
/**
* <p>@PostJsonParamsTest.java</p>
* @version 1.0
* @author zxk
* @Date 2018-3-3
*/
public class PostJsonParamsTest {
// 超时时间
private static final int RUN_TIME =10000;
// 爬取初始页数
private String page;
public static void main(String[] args) throws Exception {
PostJsonParamsTest crawl = new PostJsonParamsTest();
// 请求的url地址
String url ="http://www.gzcredit.gov.cn/Service/CreditService.asmx/searchOrgWithPage";
// 设置起始访问页码
crawl.setPage("1");
String isStop = "";
// 设置请求
HttpRequestBase request = null;
request = new HttpPost(url);
try {
// 设置config
RequestConfig requestConfig = RequestConfig.custom()
.setSocketTimeout(RUN_TIME)
.setConnectTimeout(RUN_TIME)
.setConnectionRequestTimeout(RUN_TIME)
.build();
request.setConfig(requestConfig);
// json 格式的 post 参数
String postParams ="{"condition":{"qymc":"%%%%","cydw":""},"pageNo":"+crawl.getPage()+","pageSize":100,count:2709846}";
System.out.println(postParams);
HttpEntity httpEntity = new StringEntity(postParams);
((HttpPost) request).setEntity(httpEntity);
// 添加请求头,可以绕过验证码
request.addHeader("Accept","application/json, text/javascript, */*");
request.addHeader("Accept-Encoding","gzip, deflate");
request.addHeader("Accept-Language", "zh-CN,zh;q=0.8");
request.addHeader("Connection", "keep-alive");
request.addHeader("Host", "www.gzcredit.gov.cn");
request.addHeader("Content-Type", "application/json; charset=UTF-8");
URIBuilder builder = new URIBuilder(url);
URI uri = builder.build();
uri = new URI(URLDecoder.decode(uri.toString(), "UTF-8"));
request.setURI(uri);
while(!isStop.equals("停止")||isStop.equals("重跑")){
isStop = crawl.crawlList(request);
if(isStop.equals("爬取")){
crawl.setPage(String.valueOf(Integer.parseInt(crawl.getPage())+1));
}
// if("2713".equals(crawl.getPage())) break;
if("2".equals(crawl.getPage())){
break;
}
}
} catch (NumberFormatException e) {
e.printStackTrace();
throw new NumberFormatException("数字格式错误");
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
throw new UnsupportedEncodingException("不支持的编码集");
}
}
/**
* 爬取搜索列表
* @param page
* @return
*/
private String crawlList(HttpRequestBase request){
int statusCode = 0;
// 下面两种方式都可以用来创建客户端连接,相当于打开了一个浏览器
CloseableHttpClient httpClient = HttpClients.createDefault();
// HttpClient httpClient = HttpClientBuilder.create().build();
HttpEntity httpEntity = null;
HttpResponse response = null;
try {
try {
response = httpClient.execute(request);
} catch (Exception e){
e.printStackTrace();
EntityUtils.consumeQuietly(httpEntity);
return "重跑";
}
//打印状态
statusCode =response.getStatusLine().getStatusCode();
if(statusCode!=200){
EntityUtils.consumeQuietly(httpEntity);
return "重跑";
}
//实体
httpEntity = response.getEntity();
String searchListStr = EntityUtils.toString(httpEntity,"GBK").replaceAll("\\米", "米");
String allData = (String) JSONObject.parseObject(searchListStr).get("d");
// 字符串值中间含双引号的替换处理
String s = allData.replaceAll("\{"","{'")
.replaceAll("":"", "':'")
.replaceAll("","", "','")
.replaceAll("":", "':")
.replaceAll(","", ",'")
.replaceAll(""\}", "'}")
.replaceAll(""", "")
.replaceAll("'", """)
.replaceAll("<br />", "")
.replaceAll(" ", "")
.replaceAll("\\", "?");
JSONObject jsonData = JSONObject.parseObject(s);
JSONArray jsonContent = jsonData.getJSONArray("orgList");
searchListStr = null;
allData = null;
s = null;
if (jsonContent==null || jsonContent.size()<1) {
return "重跑";
}
System.out.println(jsonContent.toJSONString());
return "爬取";
} catch (Exception e) {
e.printStackTrace();
return "重跑";
} finally{
EntityUtils.consumeQuietly(httpEntity);
}
}
private String getPage() {
return page;
}
private void setPage(String page) {
this.page = page;
}
}
补充知识:JAVA利用HttpClient发送post请求,将请求数据放到body里
我就废话不多说了,大家还是直接看代码吧~
/**
* post请求 ,请求数据放到body里
* @param url 请求地址
* @param bodyData 参数
* @author wangyj
* @date 2019年4月20日
*/
public static String doPostBodyData(String url, String bodyData) throws Exception{
String result = "";
CloseableHttpClient httpClient = null;
CloseableHttpResponse response = null;
try {
HttpPost httpPost = getHttpPost(url, null); // 请求地址
httpPost.setEntity(new StringEntity(bodyData, Encoding));
httpClient = getHttpClient();
// 得到返回的response
response = httpClient.execute(httpPost);
HttpEntity entity = response.getEntity();
result = getResult(entity, Encoding);
} catch (Exception e) {
throw e;
} finally {
// 关闭httpClient
if (null != httpClient) {
httpClient.close();
}
// 关闭response
if (null != response) {
EntityUtils.consume(response.getEntity()); // 会自动释放连接
response.close();
}
}
return result;
}
以上这篇java 实现通过 post 方式提交json参数操作就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持米米素材网。
发表评论