|
package com.open1111.jsoup;
import org.apache.http.HttpEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
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 Demo2 {
public static void main(String[] args) throws Exception{
CloseableHttpClient httpclient = HttpClients.createDefault(); // 創(chuàng)建httpclient實例
HttpGet httpget = new HttpGet("http://www.cnblogs.com/"); // 創(chuàng)建httpget實例
CloseableHttpResponse response = httpclient.execute(httpget); // 執(zhí)行g(shù)et請求
HttpEntity entity=response.getEntity(); // 獲取返回實體
String content=EntityUtils.toString(entity, "utf-8");
response.close(); // 關(guān)閉流和釋放系統(tǒng)資源
Document doc=Jsoup.parse(content); // 解析網(wǎng)頁 得到文檔對象
Element navTopElement=doc.getElementById("site_nav_top"); // 根據(jù)id來查詢DOM
String navTop=navTopElement.text(); // 返回元素的文本
System.out.println("口號："+navTop);
Elements titleElements=doc.getElementsByTag("title"); // 根據(jù)tag名稱來查詢DOM
Element titleElement=titleElements.get(0); // 獲取第1個元素
String title=titleElement.text(); // 返回元素的文本
System.out.println("網(wǎng)頁標(biāo)題是："+title);
Elements postItemElements=doc.getElementsByClass("post_item "); // 根據(jù)樣式名稱來查詢DOM
for(Element e:postItemElements){
System.out.println(e.html());
System.out.println("================");
}
Elements widthElements=doc.getElementsByAttribute("width"); // 根據(jù)屬性名來查詢DOM
for(Element e:widthElements){
System.out.println(e.toString());
System.out.println("================");
}
System.out.println("target-_blank");
Elements targetElements=doc.getElementsByAttributeValue("target", "_blank"); // 根據(jù)屬性名和屬性值來查詢DOM
for(Element e:targetElements){
System.out.println(e.toString());
System.out.println("================");
}
}
}
|
