package zp;
import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
/**
* @author 作者:tony chan
* @email 邮箱:chenzs@tedu.cn
* @version v.1.0 创建时间:上午9:47:50
* @description 描述:抓取CSDN某用户的信息
*/
public class TestCSDN {
public static void main(String[] args) throws IOException {
String[] urls = {"weixin_43884234","u012932876","qq_16804847","maitian_2008","weixin_38305440","nutony","weixin_46595435"};
String[] names = {"程晓宇","刘沛霞","刘昱江","齐雷","王海涛","陈子枢","新人"};
for(int i = 0; i<urls.length; i++) {
CSDN csdn = TestCSDN.csdn(names[i], "https://blog.csdn.net/" + urls[i]);
System.out.println(csdn.order());
}
}
public static CSDN csdn(String name, String url) throws IOException {
CSDN csdn = new CSDN();
Document doc = Jsoup.connect(url).get();
csdn.name = doc.select(".user-profile-head-name").get(0).text()+" ("+name+")";
csdn.image = doc.select(".user-profile-avatar").select("img").get(0).attr("src");
csdn.info = doc.select(".user-profile-head-info-r-c").get(0).text();
//1,190,760 被访问 141 原创 1,527 排名 7,143 粉丝
csdn.orderNo = csdn.info.substring(csdn.info.indexOf("原创")+3, csdn.info.indexOf("排名") );
try {
csdn.intro = doc.select(".introduction-fold").select(".default").get(0).text();
}catch(Exception e) {}
return csdn;
}
}
class CSDN{
String name;
String orderNo;
String image;
String info;
String intro;
@Override
public String toString() {
return "CSDN [name=" + name + ", info=" + info + ", intro=" + intro + ", image=" + image + "]";
}
public String order() {
return "CSDN [name=" + name + ", order=" + orderNo + "]";
}
}
爬虫,抓取CSDN某用户的信息
最新推荐文章于 2022-04-10 19:01:32 发布