HTML转义真的很难做对-我绝对建议使用库代码来做这件事，因为它比你想象的要微妙得多。在Apache的StringEscapeUtils中有一个非常好的库，可以在Java中处理这个问题。

我知道这个问题已经有一段时间没有被问到了，但我找到了另一个解决方案，这对我来说很有效:

Pattern REMOVE_TAGS = Pattern.compile("<.+?>");
    Source source= new Source(htmlAsString);
 Matcher m = REMOVE_TAGS.matcher(sourceStep.getTextExtractor().toString());
                        String clearedHtml= m.replaceAll("");

这里有一个稍微更充实的更新，试图处理一些格式的休息和列表。我用Amaya的输出作为指导。

import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.util.Stack;
import java.util.logging.Logger;

import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;

public class HTML2Text extends HTMLEditorKit.ParserCallback {
    private static final Logger log = Logger
            .getLogger(Logger.GLOBAL_LOGGER_NAME);

    private StringBuffer stringBuffer;

    private Stack<IndexType> indentStack;

    public static class IndexType {
        public String type;
        public int counter; // used for ordered lists

        public IndexType(String type) {
            this.type = type;
            counter = 0;
        }
    }

    public HTML2Text() {
        stringBuffer = new StringBuffer();
        indentStack = new Stack<IndexType>();
    }

    public static String convert(String html) {
        HTML2Text parser = new HTML2Text();
        Reader in = new StringReader(html);
        try {
            // the HTML to convert
            parser.parse(in);
        } catch (Exception e) {
            log.severe(e.getMessage());
        } finally {
            try {
                in.close();
            } catch (IOException ioe) {
                // this should never happen
            }
        }
        return parser.getText();
    }

    public void parse(Reader in) throws IOException {
        ParserDelegator delegator = new ParserDelegator();
        // the third parameter is TRUE to ignore charset directive
        delegator.parse(in, this, Boolean.TRUE);
    }

    public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos) {
        log.info("StartTag:" + t.toString());
        if (t.toString().equals("p")) {
            if (stringBuffer.length() > 0
                    && !stringBuffer.substring(stringBuffer.length() - 1)
                            .equals("\n")) {
                newLine();
            }
            newLine();
        } else if (t.toString().equals("ol")) {
            indentStack.push(new IndexType("ol"));
            newLine();
        } else if (t.toString().equals("ul")) {
            indentStack.push(new IndexType("ul"));
            newLine();
        } else if (t.toString().equals("li")) {
            IndexType parent = indentStack.peek();
            if (parent.type.equals("ol")) {
                String numberString = "" + (++parent.counter) + ".";
                stringBuffer.append(numberString);
                for (int i = 0; i < (4 - numberString.length()); i++) {
                    stringBuffer.append(" ");
                }
            } else {
                stringBuffer.append("*   ");
            }
            indentStack.push(new IndexType("li"));
        } else if (t.toString().equals("dl")) {
            newLine();
        } else if (t.toString().equals("dt")) {
            newLine();
        } else if (t.toString().equals("dd")) {
            indentStack.push(new IndexType("dd"));
            newLine();
        }
    }

    private void newLine() {
        stringBuffer.append("\n");
        for (int i = 0; i < indentStack.size(); i++) {
            stringBuffer.append("    ");
        }
    }

    public void handleEndTag(HTML.Tag t, int pos) {
        log.info("EndTag:" + t.toString());
        if (t.toString().equals("p")) {
            newLine();
        } else if (t.toString().equals("ol")) {
            indentStack.pop();
            ;
            newLine();
        } else if (t.toString().equals("ul")) {
            indentStack.pop();
            ;
            newLine();
        } else if (t.toString().equals("li")) {
            indentStack.pop();
            ;
            newLine();
        } else if (t.toString().equals("dd")) {
            indentStack.pop();
            ;
        }
    }

    public void handleSimpleTag(HTML.Tag t, MutableAttributeSet a, int pos) {
        log.info("SimpleTag:" + t.toString());
        if (t.toString().equals("br")) {
            newLine();
        }
    }

    public void handleText(char[] text, int pos) {
        log.info("Text:" + new String(text));
        stringBuffer.append(text);
    }

    public String getText() {
        return stringBuffer.toString();
    }

    public static void main(String args[]) {
        String html = "<html><body><p>paragraph at start</p>hello<br />What is happening?<p>this is a<br />mutiline paragraph</p><ol>  <li>This</li>  <li>is</li>  <li>an</li>  <li>ordered</li>  <li>list    <p>with</p>    <ul>      <li>another</li>      <li>list        <dl>          <dt>This</dt>          <dt>is</dt>            <dd>sdasd</dd>            <dd>sdasda</dd>            <dd>asda              <p>aasdas</p>            </dd>            <dd>sdada</dd>          <dt>fsdfsdfsd</dt>        </dl>        <dl>          <dt>vbcvcvbcvb</dt>          <dt>cvbcvbc</dt>            <dd>vbcbcvbcvb</dd>          <dt>cvbcv</dt>          <dt></dt>        </dl>        <dl>          <dt></dt>        </dl></li>      <li>cool</li>    </ul>    <p>stuff</p>  </li>  <li>cool</li></ol><p></p></body></html>";
        System.out.println(convert(html));
    }
}

要获得格式化的纯html文本，您可以这样做:

String BR_ESCAPED = "<br/>";
Element el=Jsoup.parse(html).select("body");
el.select("br").append(BR_ESCAPED);
el.select("p").append(BR_ESCAPED+BR_ESCAPED);
el.select("h1").append(BR_ESCAPED+BR_ESCAPED);
el.select("h2").append(BR_ESCAPED+BR_ESCAPED);
el.select("h3").append(BR_ESCAPED+BR_ESCAPED);
el.select("h4").append(BR_ESCAPED+BR_ESCAPED);
el.select("h5").append(BR_ESCAPED+BR_ESCAPED);
String nodeValue=el.text();
nodeValue=nodeValue.replaceAll(BR_ESCAPED, "<br/>");
nodeValue=nodeValue.replaceAll("(\\s*<br[^>]*>){3,}", "<br/><br/>");

要获得格式化的纯文本，将<br/>更改\n，并更改最后一行:

nodeValue=nodeValue.replaceAll("(\\s*\n){3,}", "<br/><br/>");

从字符串中删除HTML标签。在某个地方，我们需要解析一些字符串，这些字符串是由服务器端的Httpresponse等响应接收到的。

所以我们需要解析它。

在这里，我将展示如何从字符串中删除html标签。

    // sample text with tags

    string str = "<html><head>sdfkashf sdf</head><body>sdfasdf</body></html>";



    // regex which match tags

    System.Text.RegularExpressions.Regex rx = new System.Text.RegularExpressions.Regex("<[^>]*>");



    // replace all matches with empty strin

    str = rx.Replace(str, "");



    //now str contains string without html tags

另一种方法是使用javax.swing.text.html.HTMLEditorKit来提取文本。

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
            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();
        }
    }
}

ref:从文件中删除HTML标记，只提取文本