6 
import java.io.IOException;
import java.util.logging.Level;
import java.util.logging.Logger;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class JavaApplication14 {


public static void main(String[] args)  {
    try {
        Document doc = Jsoup.connect("tanmoy_mahathir.makes.org/thimble/146").get();  
         String html= "<html><head></head>" + "<body><p>Parsed HTML into a doc."
                 + "</p></body></html>"; 
  Elements paragraphs = doc.select("p");
  for(Element p : paragraphs)
    System.out.println(p.text());
    } catch (IOException ex) {
        Logger.getLogger(JavaApplication14.class.getName()).log(Level.SEVERE, null, ex);
    }
}

}

谁能用jsoup代码帮我

Hello ,World!
Nothing is impossible
4

3 回答 3

5

对于这一小段 html，您只需要做

String html= "<html><head></head>" + "<body><p>Parsed HTML into a doc."+
                    +"</p></body></html>"; 
Document doc = Jsoup.parse(html); 
Elements paragraphs = doc.select("p");
for(Element p : paragraphs)
  System.out.println(p.text());

正如我所看到的，您的链接包含几乎相同的 html，然后您也可以将定义替换doc为

Document doc = Jsoup.connect("https://tanmoy_mahathir.makes.org/thimble/146").get();

更新

这是对我来说编译和运行良好的完整代码。

import java.io.IOException;
import java.util.logging.*;
import org.jsoup.*;
import org.jsoup.nodes.*;
import org.jsoup.select.*;

public class JavaApplication14 {

  public static void main(String[] args)  {
    try {
      String url = "https://tanmoy_mahathir.makes.org/thimble/146";
      Document doc = Jsoup.connect(url).get();
      Elements paragraphs = doc.select("p");
      for(Element p : paragraphs)
        System.out.println(p.text());
    } 
    catch (IOException ex) {
      Logger.getLogger(JavaApplication14.class.getName())
            .log(Level.SEVERE, null, ex);
    }
  }
}
于 2013-06-18T06:51:25.857 回答
0

你可以先试试这个......

String url = "url of the html page";
Document page = Jsoup.parse(url);

Elements elements = page.select("div[class=class_name] p");
于 2013-06-18T06:20:46.893 回答
0
  1. 元素 firstPara = d.select("div.post-content p").first() ;2
  2. System.out.println(firstPara);

您可以选择带有其类的标签，然后可以更具体地获取第一段

于 2014-09-03T03:15:51.647 回答