将固定格式的html文本分割成ArrayList

package test;

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Test {

public static void main(String[] args) {
	
	 String data = "<p>aa</p>"
			+"<br/>"
	 		+ "<img alt=\"\" src=\"/a/201901.jpg\" id=\"pic1\" class=\"pic\"/>"
	 		+"<br/>"
	 		+ "<p>bb</p>"
	 		+"<br/>"
	 		+ "<img alt=\"\" src=\"/a/201902.jpg\" id=\"pic1\" class=\"pic\"/>"
	 		+"<br/>"
	 		+ "<p>cc</p>"
	 		+"<br/>"
	 		+ "<img alt=\"\" src=\"/a/201903.jpg\" id=\"pic1\" class=\"pic\"/>"
	 		+"<br/>"
	 		+ "<p>dd</p>"
	 		+"<br/>"
	 		+ "<img alt=\"\" src=\"/a/201904.jpg\" id=\"pic1\" class=\"pic\"/>"
	 		+"<br/>";
	 
	/**
	 * [/a/201901.jpg, /a/201902.jpg, /a/201903.jpg, /a/201904.jpg] 
	 */
//		 List<String> data1 = getTextFromHtml(data, true);
	 
	 /**
	  * [<p>aa</p><br/>, 
	  * <img alt="" src="/a/201901.jpg" id="pic1" class="pic"/>, 
	  * <br/><p>bb</p><br/>, 
	  * <img alt="" src="/a/201902.jpg" id="pic1" class="pic"/>, 
	  * <br/><p>cc</p><br/>, 
	  * <img alt="" src="/a/201903.jpg" id="pic1" class="pic"/>, 
	  * <br/><p>dd</p><br/>, 
	  * <img alt="" src="/a/201904.jpg" id="pic1" class="pic"/>, <br/>]
	  */
	 List<String> data1 = cutStringByImgTag(data);
	 System.out.println(data1);
}
public static List<String> cutStringByImgTag(String targetStr) {
    List<String> splitTextList = new ArrayList<String>();
    Pattern pattern = Pattern.compile("<img.*?src=\\\"(.*?)\\\".*?>");
    Matcher matcher = pattern.matcher(targetStr);
    int lastIndex = 0;
    while (matcher.find()) {
        if (matcher.start() > lastIndex) {
            splitTextList.add(targetStr.substring(lastIndex, matcher.start()));
        }
        splitTextList.add(targetStr.substring(matcher.start(), matcher.end()));
        lastIndex = matcher.end();
    }
    if (lastIndex != targetStr.length()) {
        splitTextList.add(targetStr.substring(lastIndex, targetStr.length()));
    }
    return splitTextList;
}

public static String getImgSrc(String content){
    String str_src = null;
    //目前img标签标示有3种表达式
    //<img alt="" src="1.jpg"/>   <img alt="" src="1.jpg"></img>     <img alt="" src="1.jpg">
    //开始匹配content中的<img />标签
    Pattern p_img = Pattern.compile("<(img|IMG)(.*?)(/>|></img>|>)");
    Matcher m_img = p_img.matcher(content);
    boolean result_img = m_img.find();
    if (result_img) {
        while (result_img) {
            //获取到匹配的<img />标签中的内容
            String str_img = m_img.group(2);

            //开始匹配<img />标签中的src
            Pattern p_src = Pattern.compile("(src|SRC)=(\"|\')(.*?)(\"|\')");
            Matcher m_src = p_src.matcher(str_img);
            if (m_src.find()) {
                str_src = m_src.group(3);
            }
            //结束匹配<img />标签中的src

            //匹配content中是否存在下一个<img />标签，有则继续以上步骤匹配<img />标签中的src
            result_img = m_img.find();
        }
    }
    return str_src;
}

public static ArrayList<String> getTextFromHtml(String html, boolean isGetImage){
    ArrayList<String> imageList = new ArrayList<>();
    ArrayList<String> textList = new ArrayList<>();
    //根据img标签分割出图片和字符串
    List<String> list = cutStringByImgTag(html);
    for (int i = 0; i < list.size(); i++) {
        String text = list.get(i);
        if (text.contains("<img") && text.contains("src=")) {
            //从img标签中获取图片地址
            String imagePath = getImgSrc(text);
            imageList.add(imagePath);
        } else {
            textList.add(text);
        }
    }
    //判断是获取图片还是文本
    if (isGetImage) {
        return imageList;
    } else {
        return textList;
    }
}
}