Java 从字符串中删除HTML标记_Java_Html_Regex_Parsing

Java 从字符串中删除HTML标记

java html regex parsing

Java 从字符串中删除HTML标记,java,html,regex,parsing,Java,Html,Regex,Parsing,有没有从Java字符串中删除HTML的好方法？一个简单的正则表达式 replaceAll（“\\”，“”）将起作用，但像&无法正确转换，两个尖括号之间的非HTML将被删除（即正则表达式中的*？将消失）。如果用户输入嘿，是否要显示嘿或嘿？如果是第一个，转义小于s，并且html编码为符号（和可选的引号），那么就可以了。为实现第二个选项而对代码进行的修改如下： replaceAll("\\<[^>]*>","") replaceAll（“\\]*>”，“”）但是，如果

有没有从Java字符串中删除HTML的好方法？一个简单的正则表达式

replaceAll（“\\”，“”）

将起作用，但像

&无法正确转换，两个尖括号之间的非HTML将被删除（即正则表达式中的*？
将消失）。
如果用户输入嘿，是否要显示嘿或嘿？如果是第一个，转义小于s，并且html编码为符号（和可选的引号），那么就可以了。为实现第二个选项而对代码进行的修改如下：
replaceAll("\\<[^>]*>","")

replaceAll（“\\]*>”，“”）

但是，如果用户输入了一些格式不正确的内容，例如HTML转义确实很难正确执行，那么您将遇到问题-我绝对建议使用库代码来完成这项工作，因为它比您想象的要微妙得多。查看Apache以获得一个很好的Java库来处理这个问题。
您可能希望在剥离HTML之前用换行符替换
和
标记，以防止它像Tim建议的那样变得难以辨认
我能想到的删除HTML标记但将非HTML保留在尖括号中的唯一方法是检查是否存在错误。沿着这条线的东西
replaceAll("\\<[\s]*tag[^>]*>","")

replaceAll（“\\]*>”，“”）

然后HTML解码特殊字符，如&。不应将结果视为已清理。
听起来您希望从HTML转换为纯文本。

如果是这样，请访问www.htmlparser.org。下面是一个从URL中找到的html文件中删除所有标记的示例。

它使用org.htmlparser.beans.StringBean
另一种方法是使用javax.swing.text.html.HTMLEditorKit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();
        }
    }
}

参考：
这里有一个稍微充实的更新，尝试处理一些分隔符和列表的格式。我用阿玛亚的作品作为指导
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));
    }
}

import java.io.IOException；
导入java.io.Reader；
导入java.io.StringReader；
导入java.util.Stack；
导入java.util.logging.Logger；
导入javax.swing.text.MutableAttributeSet；
导入javax.swing.text.html.html；
导入javax.swing.text.html.HTMLEditorKit；
导入javax.swing.text.html.parser.ParserDelegator；
公共类HTML2Text扩展了HTMLEditorKit.ParserCallback{
专用静态最终记录器日志=记录器
.getLogger（Logger.GLOBAL_Logger_NAME）；
私有字符串缓冲区字符串缓冲区；
私有堆栈缩进堆栈；
公共静态类索引类型{
公共字符串类型；
public int counter；//用于有序列表
公共索引类型（字符串类型）{
this.type=type；
计数器=0；
}
}
公共HTML2Text（）{
stringBuffer=新的stringBuffer（）；
indentStack=新堆栈（）；
}
公共静态字符串转换（字符串html）{
HTML2Text解析器=新的HTML2Text（）；
Reader in=新的StringReader（html）；
试一试{
//要转换的HTML
parser.parse（in）；
}捕获（例外e）{
log.severy（如getMessage（））；
}最后{
试一试{
in.close（）；
}捕获（ioe异常ioe）{
//这永远不应该发生
}
}
返回parser.getText（）；
}
公共void解析（读取器in）引发IOException{
ParserDelegator delegator=新的ParserDelegator（）；
//第三个参数为TRUE以忽略字符集指令
parse（in，this，Boolean.TRUE）；
}
public void handleStartTag（HTML.Tag t、MutableAttributeSet a、int pos）{
log.info（“StartTag:+t.toString（））；
如果（t.toString（）.equals（“p”））{
如果（stringBuffer.length（）>0
&&！stringBuffer.substring（stringBuffer.length（）-1）
.equals（“\n”））{
换行符（）；
}
换行符（）；
}else如果（t.toString（）.equals（“ol”））{
push（新的索引类型（“ol”）；
换行符（）；
}else如果（t.toString（）.equals（“ul”））{
push（新索引类型（“ul”）；
换行符（）；
}else如果（t.toString（）等于（“li”））{
IndexType parent=indentStack.peek（）；
if（parent.type.equals（“ol”））{
字符串编号String=“”+（++parent.counter）+“；
追加（numberString）；
对于（int i=0；i<（4-numberString.length（））；i++）{
stringBuffer.append（“”）；
}
}否则{
stringBuffer.append（“*”）；
}
push（新的索引类型（“li”）；
}else如果（t.toString（）.equals（“dl”））{
换行符（）；
}否则，如果（t.toString（）.equals（“dt”））{
换行符（）；
}else如果（t.toString（）.equals（“dd”））{
push（新的索引类型（“dd”）；
换行符（）；
}
}
私有无效换行符（）{
stringBuffer.append（“\n”）；
对于（int i=0；iimport 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));
    }
}

public static String html2text(String html) {
    return Jsoup.parse(html).text();
}

MyWriter.toConsole(HtmlToText.htmlToPlainText(htmlResponse));

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

import org.ccil.cowan.tagsoup.Parser;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;

/**
 * Take HTML and give back the text part while dropping the HTML tags.
 *
 * There is some risk that using TagSoup means we'll permute non-HTML text.
 * However, it seems to work the best so far in test cases.
 *
 * @author dan
 * @see <a href="http://home.ccil.org/~cowan/XML/tagsoup/">TagSoup</a> 
 */
public class Html2Text2 implements ContentHandler {
private StringBuffer sb;

public Html2Text2() {
}

public void parse(String str) throws IOException, SAXException {
    XMLReader reader = new Parser();
    reader.setContentHandler(this);
    sb = new StringBuffer();
    reader.parse(new InputSource(new StringReader(str)));
}

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

@Override
public void characters(char[] ch, int start, int length)
    throws SAXException {
    for (int idx = 0; idx < length; idx++) {
    sb.append(ch[idx+start]);
    }
}

@Override
public void ignorableWhitespace(char[] ch, int start, int length)
    throws SAXException {
    sb.append(ch);
}

// The methods below do not contribute to the text
@Override
public void endDocument() throws SAXException {
}

@Override
public void endElement(String uri, String localName, String qName)
    throws SAXException {
}

@Override
public void endPrefixMapping(String prefix) throws SAXException {
}


@Override
public void processingInstruction(String target, String data)
    throws SAXException {
}

@Override
public void setDocumentLocator(Locator locator) {
}

@Override
public void skippedEntity(String name) throws SAXException {
}

@Override
public void startDocument() throws SAXException {
}

@Override
public void startElement(String uri, String localName, String qName,
    Attributes atts) throws SAXException {
}

@Override
public void startPrefixMapping(String prefix, String uri)
    throws SAXException {
}
}

private static final Pattern REMOVE_TAGS = Pattern.compile("<.+?>");

public static String removeTags(String string) {
    if (string == null || string.length() == 0) {
        return string;
    }

    Matcher m = REMOVE_TAGS.matcher(string);
    return m.replaceAll("");
}

noHTMLString.replaceAll("\\&.*?\\;", "");

html = html.replaceAll("&nbsp;","");
html = html.replaceAll("&amp;"."");

android.text.HtmlCompat.fromHtml(instruction, HtmlCompat.FROM_HTML_MODE_LEGACY).toString()

    Source htmlSource = new Source(htmlText);
    Segment htmlSeg = new Segment(htmlSource, 0, htmlSource.length());
    Renderer htmlRend = new Renderer(htmlSeg);
    System.out.println(htmlRend.toString());

String[] temp = yourString.split("&amp;");
String tmp = "";
if (temp.length > 1) {

    for (int i = 0; i < temp.length; i++) {
        tmp += temp[i] + "&";
    }
    yourString = tmp.substring(0, tmp.length() - 1);
}

public static String removeHTML(String input) {
    int i = 0;
    String[] str = input.split("");

    String s = "";
    boolean inTag = false;

    for (i = input.indexOf("<"); i < input.indexOf(">"); i++) {
        inTag = true;
    }
    if (!inTag) {
        for (i = 0; i < str.length; i++) {
            s = s + str[i];
        }
    }
    return s;
}

String BR_ESCAPED = "&lt;br/&gt;";
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/>");

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

private CharSequence removeHtmlFrom(String html) {
    return new HtmlCleaner().clean(html).getText();
}

// breaks multi-level of escaping, preventing &amp;lt;script&amp;gt; to be rendered as <script>
String replace = input.replace("&amp;", "");
// decode any encoded html, preventing &lt;script&gt; to be rendered as <script>
String html = StringEscapeUtils.unescapeHtml(replace);
// remove all html tags, but maintain line breaks
String clean = Jsoup.clean(html, "", Whitelist.none(), new Document.OutputSettings().prettyPrint(false));
// decode html again to convert character entities back into text
return StringEscapeUtils.unescapeHtml(clean);

{"regular string", "regular string"},
{"<a href=\"link\">A link</a>", "A link"},
{"<script src=\"http://evil.url.com\"/>", ""},
{"&lt;script&gt;", ""},
{"&amp;lt;script&amp;gt;", "lt;scriptgt;"}, // best effort
{"\" ' > < \n \\ é å à ü and & preserved", "\" ' > < \n \\ é å à ü and & preserved"}

String result = Html.fromHtml(html).toString();

String html = "<p>Line one</p><p>Line two</p>Line three<br/>etc.";
String NEW_LINE_MARK = "NEWLINESTART1234567890NEWLINEEND";
for (String tag: new String[]{"</p>","<br/>","</h1>","</h2>","</h3>","</h4>","</h5>","</h6>","</li>"}) {
    html = html.replace(tag, NEW_LINE_MARK+tag);
}

String text = Jsoup.parse(html).text();

text = text.replace(NEW_LINE_MARK + " ", "\n\n");
text = text.replace(NEW_LINE_MARK, "\n\n");

<a href=”…”> <b>,  <big>, <blockquote>, <br>, <cite>, <dfn>
<div align=”…”>,  <em>, <font size=”…” color=”…” face=”…”>
<h1>,  <h2>, <h3>, <h4>,  <h5>, <h6>
<i>, <p>, <small>
<strike>,  <strong>, <sub>, <sup>, <tt>, <u>

String Str_Html=" <p>This is about me text that the user can put into their profile</p> ";

Your_TextView_Obj.setText(Html.fromHtml(Str_Html).toString());

  text.replaceAll('<.*?>' , " ") -> This will replace all the html tags with a space.

  text.replaceAll('&.*?;' , "")-> this will replace all the tags which starts with "&" and ends with ";" like &nbsp;, &amp;, &gt; etc.

classeString.replaceAll("\\<(/?[^\\>]+)\\>", "\\ ").replaceAll("\\s+", " ").trim() 

    public String htmlToStringFilter(String textToFilter){

    return Html.fromHtml(textToFilter).toString();

    }

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

using ServiceStack.Text;
// ...
"The <b>quick</b> brown <p> fox </p> jumps over the lazy dog".StripHtml();

// delete all comments
response = response.replaceAll("<!--[^>]*-->", "");
// delete all script elements
response = response.replaceAll("<(script|SCRIPT)[^+]*?>[^>]*?<(/script|SCRIPT)>", "");

Document doc = Jsoup.parse(htmlstrl);
Whitelist wl = Whitelist.none();
String plain = Jsoup.clean(doc.text(), wl);