可以通过正则表达式去除html标签
import java.util.regex.Matcherimport java.util.regex.Pattern
public class HtmlUtil {
private static final String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>" // 定义script的正则表达式
private static final String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>" // 定义style的正则表达式
private static final String regEx_html = "<[^>]+>" // 定义HTML标签的正则表达式
private static final String regEx_space = "\\s*|\t|\r|\n"//定义空格回车换行符
/**
* @param htmlStr
* @return
* 删除Html标签
*/
public static String delHTMLTag(String htmlStr) {
Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE)
Matcher m_script = p_script.matcher(htmlStr)
htmlStr = m_script.replaceAll("") // 过滤script标签
Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE)
Matcher m_style = p_style.matcher(htmlStr)
htmlStr = m_style.replaceAll("") // 过滤style标签
Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE)
Matcher m_html = p_html.matcher(htmlStr)
htmlStr = m_html.replaceAll("") // 过滤html标签
Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE)
Matcher m_space = p_space.matcher(htmlStr)
htmlStr = m_space.replaceAll("") // 过滤空格回车标签
return htmlStr.trim() // 返回文本字符串
}
public static String getTextFromHtml(String htmlStr){
htmlStr = delHTMLTag(htmlStr)
htmlStr = htmlStr.replaceAll(" ", "")
htmlStr = htmlStr.substring(0, htmlStr.indexOf("。")+1)
return htmlStr
}
public static void main(String[] args) {
String str = "<div style='text-align:center'> 整治“四风” 清弊除垢<br/><span style='font-size:14px'> </span><span style='font-size:18px'>公司召开党的群众路线教育实践活动动员大会</span><br/></div>"
System.out.println(getTextFromHtml(str))
}
}
java处理html指定标签最好用正则表达式。例如要去除html中所有的h1标签和类容就可以用下面的演示代码：
package konw.regimport java.io.BufferedReader
import java.io.BufferedWriter
import java.io.FileNotFoundException
import java.io.FileReader
import java.io.FileWriter
import java.io.IOException
import java.util.regex.Matcher
import java.util.regex.Pattern
public class RemoveTag
{
public static void main(String[] args)
{
FileReader fr
String content =null
String regex = "<[Hh]1>.*</[Hh]1>"
try
{
fr = new FileReader("tag.html")
BufferedReader br = new BufferedReader(fr)
String str = null
StringBuffer sb = new StringBuffer()
while((str = br.readLine()) != null)
{
sb.append(str+"\n")
}
content = sb.toString()
br.close()
} catch (FileNotFoundException e)
{
e.printStackTrace()
} catch (IOException e)
{
e.printStackTrace()
}
Pattern pattern = Pattern.compile(regex)
Matcher matcher = pattern.matcher(content)
StringBuffer sb1 = new StringBuffer()
while(matcher.find())
{
sb1.append(matcher.replaceAll("")+"\n")
}
try
{
FileWriter fw = new FileWriter("tag.html")
BufferedWriter bw = new BufferedWriter(fw)
fw.write(sb1.toString())
bw.close()
} catch (IOException e)
{
e.printStackTrace()
}
}
}
