package com.example.demo;
import org.apache.commons.lang.StringEscapeUtils;
import java.util.regex.Pattern;
public class Html2Text {
public static void main(String[] args) {
//标签反转义
String temp = StringEscapeUtils.unescapeHtml("含html标签的字符串");
String s = html2Text(temp);
System.out.println(s);
}
/**
* 从html中提取纯文本
* @param inputString
* @return
*/
public static String html2Text(String inputString) {
// 含html标签的字符串
String htmlStr = inputString;
String textStr = "";
java.util.regex.Pattern p_script;
java.util.regex.Matcher m_script;
java.util.regex.Pattern p_style;
java.util.regex.Matcher m_style;
java.util.regex.Pattern p_html;
java.util.regex.Matcher m_html;
try {
// 定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script>
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>";
// 定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style>
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>";
// 定义HTML标签的正则表达式
String regEx_html = "<[^>]+>";
p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
// 过滤script标签
htmlStr = m_script.replaceAll(" ");
p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
// 过滤style标签
htmlStr = m_style.replaceAll(" ");
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
// 过滤html标签
htmlStr = m_html.replaceAll(" ");
textStr = htmlStr;
} catch (Exception e) {
System.err.println("Html2Text: " + e.getMessage());
}
//剔除空格行
textStr = textStr.replaceAll("[ ]+", " ");
// textStr = textStr.replaceAll("(?m)^\\s*$(\\n|\\r\\n)", "");
// 返回文本字符串
return textStr;
}
}
另外一种方法
package com.example.demo;
import org.apache.commons.lang.StringEscapeUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;
import java.util.List;
public class HtmlTest {
private static String extractText(Node node){
/* TextNode直接返回结果 */
if(node instanceof TextNode){
return ((TextNode) node).text();
}
/* 非TextNode的Node,遍历其孩子Node */
List<Node> children = node.childNodes();
StringBuffer buffer = new StringBuffer();
for (Node child: children) {
buffer.append(extractText(child));
}
return buffer.toString();
}
/* 使用jsoup解析html并转化为提取字符串*/
public static String html2Str(String html){
Document doc = Jsoup.parse(html);
return extractText(doc);
}
public static void main(String[] args) {
//反转义
String temp = StringEscapeUtils.unescapeHtml("含html标签的字符串");
String s = html2Str(temp);
System.out.println(s);
}
}