Java正则获取指定标签的属性值与标签内容

Posted 2022-10-24 BandaYung

比如获取<span>中的data-id跟标签内容

<span contenteditable="false" data-id="1004435" style="color: #598cf2; cursor: pointer;"> @lyh12345 </span>

 其中group(int)其中int是reg中第几个()

public ArrayList<AtAccountInfo> getAtAccountList(String html) 
        ArrayList<AtAccountInfo> list = new ArrayList<>();
        String element = "span";
        String attr = "data-id";
        String reg = "<" + element + "[^<>]*?\\\\s" + attr + "=['\\"]?(.*?)['\\"]?(\\\\s.*?)?>([^><]*)</" + element + ">";
        Matcher m = Pattern.compile(reg).matcher(html);
        while (m.find()) 
            String id = m.group(1);
            String atNameSpace = m.group(3);
            if (!TextUtils.isEmpty(id) && !TextUtils.isEmpty(atNameSpace)) 
                AtAccountInfo infoBean = new AtAccountInfo(Integer.parseInt(id), atNameSpace);
                list.add(infoBean);
            
        
        return list;