HtmlUtil.java 1008 B

1234567891011121314151617181920212223242526272829303132333435363738
  1. package com.yihu.rehabilitation.util;
  2. import org.apache.commons.lang3.StringEscapeUtils;
  3. import java.io.UnsupportedEncodingException;
  4. import java.net.URLDecoder;
  5. import java.util.ArrayList;
  6. import java.util.List;
  7. import java.util.regex.Matcher;
  8. import java.util.regex.Pattern;
  9. /**
  10. * Created by liub on 2020/12/10.
  11. */
  12. public class HtmlUtil {
  13. public static List<String> getTagContent(String source, String regString) {
  14. List<String> result = new ArrayList<String>();
  15. Matcher m = Pattern.compile(regString).matcher(source);
  16. while (m.find()) {
  17. try {
  18. String r = StringEscapeUtils.unescapeHtml3(URLDecoder.decode(m.group(1),"utf-8"));
  19. result.add(r);
  20. } catch (UnsupportedEncodingException e) {
  21. e.printStackTrace();
  22. }
  23. }
  24. return result;
  25. }
  26. public static void main(String[] args){
  27. try {
  28. }catch (Exception e){
  29. e.printStackTrace();
  30. }
  31. }
  32. }