81,091
社区成员
发帖
与我相关
我的任务
分享
package com.sssss;
import java.util.regex.Pattern;
public class test {
public test() {
}
public String Html2Text(String inputString) {
String htmlStr = inputString; //含html标签的字符串
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]*?>"; //定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script> }
String regEx_style =
"<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; //定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style> }
String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式
p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); //过滤script标签
p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); //过滤style标签
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); //过滤html标签
textStr = htmlStr;
} catch (Exception e) {
System.err.println("Html2Text: " + e.getMessage());
}
return textStr; //返回文本字符串
}
public static void main(String [] ager){
test in=new test();
String ss="<table class=\"CSDN-PHF\" border=\"0\" cellspacing=\"1\" cellpadding=\"0\"><tr><td><a rel=\"mz\" href=\"http://www.csdn.net/\">首页</a></td><td><a rel=\"mz\" href=\"http://news.csdn.net/\">新闻</a></td><td><a rel=\"mz\" href=\"http://bbs.csdn.net/\">论坛</a></td>";
String test=in.Html2Text(ss);
System.out.println(test);
}
}
package com.sssss;
import java.util.regex.Pattern;
public class test {
public test() {
}
public String Html2Text(String inputString) {
String htmlStr = inputString; //含html标签的字符串
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;
Pattern p = Pattern.compile("(?is)<P\\s+?[^<>]*?/?>");
String output = p.matcher(htmlStr).replaceAll("@zybbr@");
output=output.replaceAll("<P>","@zybbr@");
try {
String regEx_script =
"<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; //定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script> }
String regEx_style =
"<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; //定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style> }
String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式
p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(output);
htmlStr = m_script.replaceAll(""); //过滤script标签
p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); //过滤style标签
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); //过滤html标签
htmlStr=htmlStr.replaceAll("@zybbr@","</br>");
textStr = htmlStr;
} catch (Exception e) {
System.err.println("Html2Text: " + e.getMessage());
}
return textStr; //返回文本字符串
}
public static void main(String [] ager){
test in=new test();
String ss="<table class=\"CSDN-PHF\" border=\"0\" cellspacing=\"1\" cellpadding=\"0\"><tr><td><a rel=\"mz\" href=\"http://www.csdn.net/\">首页</a></td><td><a rel=\"mz\" href=\"http://news.csdn.net/\">新闻</a></td><td><a rel=\"mz\" href=\"http://bbs.csdn.net/\">论坛</a></td>";
String test=in.Html2Text(ss);
System.out.println(test);
}
}
<html>
<head>
<title>Example 1</title>
<script type="text/javascript">
window.onload = function(){
var div1 = document.getElementById("div1");
var text = div1.innerText;
window.alert(text);
};
</script>
</head>
<body>
<div id="div1">
Here is some coding.
</div>
</body>
</html>