Java 使用jsoup将html转换为纯文本时，如何保留换行符？
我有以下代码：Java 使用jsoup将html转换为纯文本时，如何保留换行符？,java,jsoup,Java,Jsoup,我有以下代码： public class NewClass { public String noTags(String str){ return Jsoup.parse(str).text(); } public static void main(String args[]) { String strings="<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.0 Transitio
public class NewClass {
public String noTags(String str){
return Jsoup.parse(str).text();
}
public static void main(String args[]) {
String strings="<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.0 Transitional//EN \">" +
"<HTML> <HEAD> <TITLE></TITLE> <style>body{ font-size: 12px;font-family: verdana, arial, helvetica, sans-serif;}</style> </HEAD> <BODY><p><b>hello world</b></p><p><br><b>yo</b> <a href=\"http://google.com\">googlez</a></p></BODY> </HTML> ";
NewClass text = new NewClass();
System.out.println((text.noTags(strings)));
}
hello world
yo googlez
public String noTags(String str){
Document d = Jsoup.parse(str);
TextNode tn = new TextNode(d.body().html(), "");
return tn.getWholeText();
}
"A B"
A
B
descrizione = Jsoup.parse(html.replaceAll("(?i)<br[^>]*>", "br2n")).text();
text = descrizione.replaceAll("br2n", "\n");
descripione=Jsoup.parse（html.replaceAll（“（？i）]*>”，“br2n”）.text（）；
text=descripione.replaceAll（“br2n”，“\n”）；
public static String clean(String bodyHtml,
String baseUri,
Whitelist whitelist,
Document.OutputSettings outputSettings)
Whitelist.none（）通过传递
new OutputSettings（）.prettyPrint（false）public static String cleanPreserveLineBreaks(String bodyHtml) {
// get pretty printed html with preserved br and p tags
String prettyPrintedBodyFragment = Jsoup.clean(bodyHtml, "", Whitelist.none().addTags("br", "p"), new OutputSettings().prettyPrint(true));
// get plain text with preserved line breaks by disabled prettyPrint
return Jsoup.clean(prettyPrintedBodyFragment, "", Whitelist.none(), new OutputSettings().prettyPrint(false));
}
可以遍历给定的元素
public String convertNodeToText(Element element)
{
final StringBuilder buffer = new StringBuilder();
new NodeTraversor(new NodeVisitor() {
boolean isNewline = true;
@Override
public void head(Node node, int depth) {
if (node instanceof TextNode) {
TextNode textNode = (TextNode) node;
String text = textNode.text().replace('\u00A0', ' ').trim();
if(!text.isEmpty())
{
buffer.append(text);
isNewline = false;
}
} else if (node instanceof Element) {
Element element = (Element) node;
if (!isNewline)
{
if((element.isBlock() || element.tagName().equals("br")))
{
buffer.append("\n");
isNewline = true;
}
}
}
}
@Override
public void tail(Node node, int depth) {
}
}).traverse(element);
return buffer.toString();
}
String result = convertNodeToText(JSoup.parse(html))
textNodes（）\nval rawTxt = doc.body().getElementsByTag("div").first.textNodes()
.asScala.mkString("<br />\n")
val rawTxt=doc.body（）.getElementsByTag（“div”）.first.textNodes（）
.asScala.mkString（“
\n”）
公共静态字符串br2nl（字符串html）{
if（html==null）
返回html；
documentdocument=Jsoup.parse（html）；
document.outputSettings（new document.outputSettings（）.prettyPrint（false））；//使html（）保留换行符和间距
文档。选择（“br”）。追加（\\n”）；
文档。选择（“p”）。前置（\\n\\n）；
字符串s=document.html（）；
返回Jsoup.clean（s，“”，Whitelist.none（），new Document.OutputSettings（）.prettyPrint（false））；
}
text=Jsoup.parse（html.replaceAll（“（？i）]*>”，“br2n”））.text（）；
text = Jsoup.parse(html.replaceAll("(?i)<br[^>]*>", "br2n")).text();
text = descrizione.replaceAll("br2n", "\n");
text = Jsoup.parse(html.replaceAll("(?i)<br[^>]*>", "<pre>\n</pre>")).text();
text=descripione.replaceAll（“br2n”，“\n”）；
text=Jsoup.parse（html.replaceAll（“（？i）]*>”，“\n”））.text（）；
工作更可靠、更简单。基于用户121196和绿色贝雷帽的回答，选择
和
s，唯一适合我的解决方案是：
def html2text( rawHtml : String ) : String = {
val htmlDoc = Jsoup.parseBodyFragment( rawHtml, "/" )
htmlDoc.select("br").append("\\nl")
htmlDoc.select("div").prepend("\\nl").append("\\nl")
htmlDoc.select("p").prepend("\\nl\\nl").append("\\nl\\nl")
org.jsoup.parser.Parser.unescapeEntities(
Jsoup.clean(
htmlDoc.html(),
"",
Whitelist.none(),
new org.jsoup.nodes.Document.OutputSettings().prettyPrint(true)
),false
).
replaceAll("\\\\nl", "\n").
replaceAll("\r","").
replaceAll("\n\\s+\n","\n").
replaceAll("\n\n+","\n\n").
trim()
}
package org.jsoup.examples;
import org.jsoup.Jsoup;
import org.jsoup.helper.StringUtil;
import org.jsoup.helper.Validate;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;
import org.jsoup.select.Elements;
import org.jsoup.select.NodeTraversor;
import org.jsoup.select.NodeVisitor;
import java.io.IOException;
/**
* HTML to plain-text. This example program demonstrates the use of jsoup to convert HTML input to lightly-formatted
* plain-text. That is divergent from the general goal of jsoup's .text() methods, which is to get clean data from a
* scrape.
* <p>
* Note that this is a fairly simplistic formatter -- for real world use you'll want to embrace and extend.
* </p>
* <p>
* To invoke from the command line, assuming you've downloaded the jsoup jar to your current directory:</p>
* <p><code>java -cp jsoup.jar org.jsoup.examples.HtmlToPlainText url [selector]</code></p>
* where <i>url</i> is the URL to fetch, and <i>selector</i> is an optional CSS selector.
*
* @author Jonathan Hedley, jonathan@hedley.net
*/
public class HtmlToPlainText {
private static final String userAgent = "Mozilla/5.0 (jsoup)";
private static final int timeout = 5 * 1000;
public static void main(String... args) throws IOException {
Validate.isTrue(args.length == 1 || args.length == 2, "usage: java -cp jsoup.jar org.jsoup.examples.HtmlToPlainText url [selector]");
final String url = args[0];
final String selector = args.length == 2 ? args[1] : null;
// fetch the specified URL and parse to a HTML DOM
Document doc = Jsoup.connect(url).userAgent(userAgent).timeout(timeout).get();
HtmlToPlainText formatter = new HtmlToPlainText();
if (selector != null) {
Elements elements = doc.select(selector); // get each element that matches the CSS selector
for (Element element : elements) {
String plainText = formatter.getPlainText(element); // format that element to plain text
System.out.println(plainText);
}
} else { // format the whole doc
String plainText = formatter.getPlainText(doc);
System.out.println(plainText);
}
}
/**
* Format an Element to plain-text
* @param element the root element to format
* @return formatted text
*/
public String getPlainText(Element element) {
FormattingVisitor formatter = new FormattingVisitor();
NodeTraversor traversor = new NodeTraversor(formatter);
traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node
return formatter.toString();
}
// the formatting rules, implemented in a breadth-first DOM traverse
private class FormattingVisitor implements NodeVisitor {
private static final int maxWidth = 80;
private int width = 0;
private StringBuilder accum = new StringBuilder(); // holds the accumulated text
// hit when the node is first seen
public void head(Node node, int depth) {
String name = node.nodeName();
if (node instanceof TextNode)
append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
else if (name.equals("li"))
append("\n * ");
else if (name.equals("dt"))
append(" ");
else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr"))
append("\n");
}
// hit when all of the node's children (if any) have been visited
public void tail(Node node, int depth) {
String name = node.nodeName();
if (StringUtil.in(name, "br", "dd", "dt", "p", "h1", "h2", "h3", "h4", "h5"))
append("\n");
else if (name.equals("a"))
append(String.format(" <%s>", node.absUrl("href")));
}
// appends text to the string builder with a simple word wrap method
private void append(String text) {
if (text.startsWith("\n"))
width = 0; // reset counter if starts with a newline. only from formats above, not in natural text
if (text.equals(" ") &&
(accum.length() == 0 || StringUtil.in(accum.substring(accum.length() - 1), " ", "\n")))
return; // don't accumulate long runs of empty spaces
if (text.length() + width > maxWidth) { // won't fit, needs to wrap
String words[] = text.split("\\s+");
for (int i = 0; i < words.length; i++) {
String word = words[i];
boolean last = i == words.length - 1;
if (!last) // insert a space if not the last word
word = word + " ";
if (word.length() + width > maxWidth) { // wrap and reset counter
accum.append("\n").append(word);
width = word.length();
} else {
accum.append(word);
width += word.length();
}
}
} else { // fits as is, without need to wrap text
accum.append(text);
width += text.length();
}
}
@Override
public String toString() {
return accum.toString();
}
}
}
org.jsoup.nodes.Element元素与HTML=。。。。
elementWithHtml.select（“br”）.append（“\n”）；
elementWithHtml.select（“p”）.prepend（“\n\n”）；
elementWithHtml.text（）；
这是我将html翻译成文本的版本（实际上是user121196答案的修改版本）
这不仅仅是保留换行符，还可以格式化文本并删除过多的换行符、HTML转义符号，这样您就可以从HTML中获得更好的结果（在我的例子中，我是从邮件中收到的）
它最初是用Scala编写的，但您可以轻松地将其更改为Java
String cleanString = Jsoup.parse(htmlString).wholeText();
基于对这个问题的其他回答和评论，似乎大多数来到这里的人都在寻找一个通用的解决方案，该解决方案将为HTML文档提供格式良好的纯文本表示。我知道我是
幸运的是，JSoup已经提供了一个非常全面的示例，说明了如何实现这一点：
示例formatingvisitor
可以根据您的偏好轻松调整，并处理大多数块元素和换行
为避免链接损坏，以下是完整的解决方案：
使用jsoup尝试以下操作：
public static String cleanPreserveLineBreaks(String bodyHtml) {
// get pretty printed html with preserved br and p tags
String prettyPrintedBodyFragment = Jsoup.clean(bodyHtml, "", Whitelist.none().addTags("br", "p"), new OutputSettings().prettyPrint(true));
// get plain text with preserved line breaks by disabled prettyPrint
return Jsoup.clean(prettyPrintedBodyFragment, "", Whitelist.none(), new OutputSettings().prettyPrint(false));
}
doc.outputSettings（新的outputSettings（）.prettyPrint（false））；
//选择所有
标记，然后追加\n
在（\\n）之后选择“文件”（“br”）；
//选择所有标记并在此之前\n预结束
在（\\n）之前选择“p”；
//从文档中获取HTML，并保留原始新行
字符串str=doc.html（）；
对于更复杂的HTML，上面的解决方案没有一个是完全正确的；我能够成功地进行转换，同时通过以下方式保留换行符：
（1.10.3版）在JSOUPV1.11.2上，我们现在可以使用元素.wholeText（）
示例代码：
user121196的
仍然有效。但是wholeText（）
保留文本对齐。编辑文本-您的问题中没有出现换行符。一般来说，请在发布之前阅读问题的预览，以检查所有内容是否正确。我问了相同的问题（没有jsoup要求），但我仍然没有一个好的解决方案：请参阅@zeenosaur的答案。hello world
yo googlez，但我需要hello world yo googlez（没有html标记）这个答案不会返回纯文本；它返回HTML并插入换行符。事实上，这是一个简单的缓和方法，但我想这应该完全由Jsoup库本身来处理（它现在有一些像这样令人不安的行为，否则它就是一个很棒的库！）。Jsoup不是给了你一个DOM吗？为什么不将所有
元素替换为包含新行的文本节点，然后调用.text（）
，而不是执行正则表达式转换，这将导致某些字符串（如
Nice）的不正确输出，但“descripione”从何而来？“descripione”表示纯文本被@MircoAttocchi分配给答案的变量，它最适合我。这个解决方案会留下实体……这不好！i、 e.“La portaè；aperta”保持不变，而我想要“La portaèaperta”。br2nl是
text = Jsoup.parse(html.replaceAll("(?i)<br[^>]*>", "<pre>\n</pre>")).text();
org.jsoup.nodes.Element elementWithHtml = ....
elementWithHtml.select("br").append("<pre>\n</pre>");
elementWithHtml.select("p").prepend("<pre>\n\n</pre>");
elementWithHtml.text();
def html2text( rawHtml : String ) : String = {
val htmlDoc = Jsoup.parseBodyFragment( rawHtml, "/" )
htmlDoc.select("br").append("\\nl")
htmlDoc.select("div").prepend("\\nl").append("\\nl")
htmlDoc.select("p").prepend("\\nl\\nl").append("\\nl\\nl")
org.jsoup.parser.Parser.unescapeEntities(
Jsoup.clean(
htmlDoc.html(),
"",
Whitelist.none(),
new org.jsoup.nodes.Document.OutputSettings().prettyPrint(true)
),false
).
replaceAll("\\\\nl", "\n").
replaceAll("\r","").
replaceAll("\n\\s+\n","\n").
replaceAll("\n\n+","\n\n").
trim()
}
package org.jsoup.examples;
import org.jsoup.Jsoup;
import org.jsoup.helper.StringUtil;
import org.jsoup.helper.Validate;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.nodes.Node;
import org.jsoup.nodes.TextNode;
import org.jsoup.select.Elements;
import org.jsoup.select.NodeTraversor;
import org.jsoup.select.NodeVisitor;
import java.io.IOException;
/**
* HTML to plain-text. This example program demonstrates the use of jsoup to convert HTML input to lightly-formatted
* plain-text. That is divergent from the general goal of jsoup's .text() methods, which is to get clean data from a
* scrape.
* <p>
* Note that this is a fairly simplistic formatter -- for real world use you'll want to embrace and extend.
* </p>
* <p>
* To invoke from the command line, assuming you've downloaded the jsoup jar to your current directory:</p>
* <p><code>java -cp jsoup.jar org.jsoup.examples.HtmlToPlainText url [selector]</code></p>
* where <i>url</i> is the URL to fetch, and <i>selector</i> is an optional CSS selector.
*
* @author Jonathan Hedley, jonathan@hedley.net
*/
public class HtmlToPlainText {
private static final String userAgent = "Mozilla/5.0 (jsoup)";
private static final int timeout = 5 * 1000;
public static void main(String... args) throws IOException {
Validate.isTrue(args.length == 1 || args.length == 2, "usage: java -cp jsoup.jar org.jsoup.examples.HtmlToPlainText url [selector]");
final String url = args[0];
final String selector = args.length == 2 ? args[1] : null;
// fetch the specified URL and parse to a HTML DOM
Document doc = Jsoup.connect(url).userAgent(userAgent).timeout(timeout).get();
HtmlToPlainText formatter = new HtmlToPlainText();
if (selector != null) {
Elements elements = doc.select(selector); // get each element that matches the CSS selector
for (Element element : elements) {
String plainText = formatter.getPlainText(element); // format that element to plain text
System.out.println(plainText);
}
} else { // format the whole doc
String plainText = formatter.getPlainText(doc);
System.out.println(plainText);
}
}
/**
* Format an Element to plain-text
* @param element the root element to format
* @return formatted text
*/
public String getPlainText(Element element) {
FormattingVisitor formatter = new FormattingVisitor();
NodeTraversor traversor = new NodeTraversor(formatter);
traversor.traverse(element); // walk the DOM, and call .head() and .tail() for each node
return formatter.toString();
}
// the formatting rules, implemented in a breadth-first DOM traverse
private class FormattingVisitor implements NodeVisitor {
private static final int maxWidth = 80;
private int width = 0;
private StringBuilder accum = new StringBuilder(); // holds the accumulated text
// hit when the node is first seen
public void head(Node node, int depth) {
String name = node.nodeName();
if (node instanceof TextNode)
append(((TextNode) node).text()); // TextNodes carry all user-readable text in the DOM.
else if (name.equals("li"))
append("\n * ");
else if (name.equals("dt"))
append(" ");
else if (StringUtil.in(name, "p", "h1", "h2", "h3", "h4", "h5", "tr"))
append("\n");
}
// hit when all of the node's children (if any) have been visited
public void tail(Node node, int depth) {
String name = node.nodeName();
if (StringUtil.in(name, "br", "dd", "dt", "p", "h1", "h2", "h3", "h4", "h5"))
append("\n");
else if (name.equals("a"))
append(String.format(" <%s>", node.absUrl("href")));
}
// appends text to the string builder with a simple word wrap method
private void append(String text) {
if (text.startsWith("\n"))
width = 0; // reset counter if starts with a newline. only from formats above, not in natural text
if (text.equals(" ") &&
(accum.length() == 0 || StringUtil.in(accum.substring(accum.length() - 1), " ", "\n")))
return; // don't accumulate long runs of empty spaces
if (text.length() + width > maxWidth) { // won't fit, needs to wrap
String words[] = text.split("\\s+");
for (int i = 0; i < words.length; i++) {
String word = words[i];
boolean last = i == words.length - 1;
if (!last) // insert a space if not the last word
word = word + " ";
if (word.length() + width > maxWidth) { // wrap and reset counter
accum.append("\n").append(word);
width = word.length();
} else {
accum.append(word);
width += word.length();
}
}
} else { // fits as is, without need to wrap text
accum.append(text);
width += text.length();
}
}
@Override
public String toString() {
return accum.toString();
}
}
}
doc.outputSettings(new OutputSettings().prettyPrint(false));
//select all <br> tags and append \n after that
doc.select("br").after("\\n");
//select all <p> tags and prepend \n before that
doc.select("p").before("\\n");
//get the HTML from the document, and retaining original new lines
String str = doc.html().replaceAll("\\\\n", "\n");
Document document = Jsoup.parse(myHtml);
String text = new HtmlToPlainText().getPlainText(document);
String cleanString = Jsoup.parse(htmlString).wholeText();