android - 如何使用 Jsoup for android 获取属性和值

Question

如何使用带有 android 的 jsoup 从以下 html 代码中获取属性和值:

<div style='width:100px;height:100px;background:#d8a8d8'>&nbsp;</div> Actual Text <br>Text Inside br<br>
<div style='width:100px;height:100px;background:#dda0dd'>&nbsp;</div> This text Too.

我需要的是:

<强>1。两个 div 标签的背景值 -(即“d8a8d8”和“dda0dd”)

<强>2。 div 之后的文本-(即-“实际文本”和“This text Too.”)

<强>3。 br 标签之后的文本，紧跟在第一个 div 之后(即“Text Inside br”)

那么，我该怎么做呢？

---

我尝试的是:

  String st = "<div style='width:100px;height:100px;background:#d8a8d8'>&nbsp;</div> Actual Text <br>Text Inside br<br>
<div style='width:100px;height:100px;background:#dda0dd'>&nbsp;</div>";

 Document doc = Jsoup.parse(s);
 ements divs = doc.select("div");

 for(Element elem : divs)
{
   System.out.println(elem.html()); //get all elements inside div

   String ss =  elem.attr("style");
   Log.d("logjsoup", "\n after Jsoup: " +  ss);
}

我正在获取 div 样式中的所有值。

如何获得我想要的特定结果？

Answer 1

import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class JsoupTest {

    public static void main(String[] args) {
        String html = "<div style='width:100px;height:100px;background:#d8a8d8'>&nbsp;</div> Actual Text <br>Text Inside br<br> \n"+
                    "<div style='width:100px;height:100px;background:#dda0dd'>&nbsp;</div> This text Too.";
        //parse the html
        Document doc = Jsoup.parse(html);
        //select the divs
        Elements divs = doc.select("div");
        // use a regex matcher to get the background values
        // pattern to look for all characters between "background:#" and "'"
        Pattern p = Pattern.compile("(?<=background:#)(.*)(?=\")");
        for(Element e: divs){
            Matcher m = p.matcher(e.attributes().toString());
            while(m.find()){
                // background value 
                System.out.println(m.group());
            }
            // text after the div which is the next sibling of the div 
            System.out.println(e.nextSibling().toString().trim());
            if(e.nextElementSibling()!= null){
                // text after first br tag; the nextElementsibling returns the br element next sibling of this br is the text after br
                System.out.println(e.nextElementSibling().nextSibling().toString());
            }
            System.out.println("-----------------------");
        }
    } 
}