<!DOCTYPE html>
<html>
<head>
<title>test</title>
</head>
<body>
<div id="contnet">
<p>111111111111111111111</p>
<p><img src="1111.jpg"></p>
<p>2222222222222222222222</p>
<p><img src="22222.jpg"></p>
<p><img src="22222222222.jpg"></p>
<p>33333333333333333333333</p>
</div>
</body>
</html>
import java.io.IOException;
import com.integrated.comm.utils.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
public class TestJsoup {
public Document getDocument (String url){
try {
return Jsoup.connect(url).get();
} catch (IOException e) {
e.printStackTrace();
}
return null;
}
public static void main(String[] args) {
TestJsoup t = new TestJsoup();
Document doc = t.getDocument("http://news.163.com/20/0225/08/F67FP2TK0001899O.html");
// 获取目标HTML代码
Elements elements1 = doc.select("[class=post_text][id=endText]").not("[style=white-space:pre-wrap;display: block;border: 3px solid blue;]");
// 今天
Elements elements2 = elements1.select("p");
System.out.println("p标签个数="+elements2.size());
String content = "";
for (int i =1;i<elements2.size();i++){
content += elements2.get(i).text();
}
System.out.println(content);
}
}