HttpClient下载地址:http://hc.apache.org/downloads.cgi
Jsoup下载地址:https://jsoup.org/download
本次使用的是httpclient(4.5.6版)Jsoup(1.11.3版),适合初学者入门与了解Java爬虫,本次爬取豆瓣《纸牌屋》第一季讨论区链接地址与主题。
import java.io.IOException;
import org.apache.http.HttpEntity;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.protocol.HttpClientContext;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class Test {
public static void main(String[] args) throws IOException {
//纸牌屋第一季讨论
String url ="https://movie.douban.com/subject/6037429/";
// 创建httpclient对象
CloseableHttpClient httpclient = HttpClients.createDefault();
//设置超时时间
RequestConfig requestConfig = RequestConfig.custom()
.setSocketTimeout(10000)
.setConnectTimeout(10000)
.build();
// 创建get对象
HttpGet get = new HttpGet(url);
get.setConfig(requestConfig);
// 创建context对象
HttpClientContext context = HttpClientContext.create();
// 创建response对象
CloseableHttpResponse response = httpclient.execute(get, context);
//获取网页源码
if(response.getStatusLine().getStatusCode()==200) {
//获取实体对象
HttpEntity entity = response.getEntity();
String res = EntityUtils.toString(entity, "utf-8");
//使用Jsoup解析网页
Document doc = Jsoup.parse(res);
Elements elements = doc.select(".title");
if(!elements.isEmpty()) {
//输出
for (Element element : elements) {
String temp =element.child(0).attr("href")+"\t"+element.text();
System.out.println(temp);
}
}
else {
System.out.println("《《《《《《《《 *** failed *** 》》》》》》》》");
}
}else {
System.out.println("服务器连接失败");
}
response.close();
httpclient.close();
}
}
分析:HttpClient负责将网页回复的数据生成entity实体对象;Jsoup负责将entity实体对象解析,这里解析可以使用Jquery和Css的选择器。
此处分析网页源码发现每个评论属于title类,所以Jsoup直接选取".title"进行元素选择,最终输出为: