java抓取百度百科,实现爬取百度百科头视频的java代码

只供参考，产生的问题本人不负责，不做讲解(因为是作业)

package Example.TestAnnotation;

import com.alibaba.fastjson.JSON;

import com.alibaba.fastjson.JSONArray;

import com.alibaba.fastjson.JSONObject;

import lombok.SneakyThrows;

import java.io.File;

import java.io.FileOutputStream;

import java.net.URI;

import java.net.http.HttpClient;

import java.net.http.HttpRequest;

import java.net.http.HttpResponse;

import java.util.HashMap;

/**

* 依赖项：

* fastjson

*

* com.alibaba

* fastjson

* 1.2.62

*

* lambok

*

* org.projectlombok

* lombok

* 1.18.10

* provided

*

*/

public class BaiduWiki {

private File file;

private long lemmaId;

/**

*

* @param fileName 必须包含存为mp4的名字 例如 C:\Users\dreamlike\Desktop\test.mp4

* @param lemmaId 例如：https://baike.baidu.com/item/网络爬虫/5162711?fromtitle=%E7%88%AC%E8%99%AB&fromid=22046949中5162711就是lemmaId

*/

public BaiduWiki(String fileName, long lemmaId) {

this.file = new File(fileName);

this.lemmaId = lemmaId;

}

@SneakyThrows

public String getMp4Uri(){

String s= "https://baike.baidu.com/api/wikisecond/lemmasecond?lemmaId="+lemmaId;

HttpRequest httpRequest = HttpRequest.newBuilder()

.uri(URI.create(s))

.build();

String body = HttpClient.newBuilder()

.build()

.send(httpRequest, HttpResponse.BodyHandlers.ofString())

.body();

HashMap map = JSON.parseObject(body, HashMap.class);

String l = (String) ((JSONObject) ((JSONArray) ((JSONObject) map.get("list")).get("同词条")).get(0))

.get("playMp4Url");

return l;

}

@SneakyThrows

public void getMp4File(){

HttpRequest httpRequest = HttpRequest.newBuilder()

.uri(URI.create(getMp4Uri()))

.build();

HttpClient.newHttpClient()

.send(httpRequest, HttpResponse.BodyHandlers.ofInputStream())

.body()

.transferTo(new FileOutputStream(file));

}

}

复制代码