Java實現從Html文字中提取純文字
1、應用場景:從一份html檔案中或從String(是html內容)中提取純文字,去掉網頁標籤;
2、程式碼一:replaceAll搞定
//從html中提取純文字
public static String StripHT(String strHtml) {
String txtcontent = strHtml.replaceAll("</?[^>]+>", ""); //剔出<html>的標籤
txtcontent = txtcontent.replaceAll("<a>\\s*|\t|\r|\n</a>", "");//去除字串中的空格,回車,換行符,製表符
return txtcontent;
}
3、程式碼二:正則表示式搞定
//從html中提取純文字
public static String Html2Text(String inputString) {
String htmlStr = inputString; // 含html標籤的字串
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 {
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; // 定義script的正則表示式{或<script[^>]*?>[\\s\\S]*?<\\/script>
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; // 定義style的正則表示式{或<style[^>]*?>[\\s\\S]*?<\\/style>
String regEx_html = "<[^>]+>"; // 定義HTML標籤的正則表示式
p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); // 過濾script標籤
p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); // 過濾style標籤
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); // 過濾html標籤
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)", "");
return textStr;// 返回文字字串
}
3、程式碼三:HTMLEditorKit.ParserCallback搞定,Java自帶的類
package com.util;
import java.io.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;
public class Html2Text extends HTMLEditorKit.ParserCallback {
StringBuffer s;
public Html2Text() {}
public void parse(Reader in) throws IOException {
s = new StringBuffer();
ParserDelegator delegator = new ParserDelegator();
// the third parameter is TRUE to ignore charset directive
delegator.parse(in, this, Boolean.TRUE);
}
public void handleText(char[] text, int pos) {
s.append(text);
}
public String getText() {
return s.toString();
}
public static void main (String[] args) {
try {
// the HTML to convert
//Reader in=new StringReader("string");
FileReader in = new FileReader("java-new.html");
Html2Text parser = new Html2Text();
parser.parse(in);
in.close();
System.out.println(parser.getText());
}
catch (Exception e) {
e.printStackTrace();
}
}