html解析 jsoup使用介绍 jsoup解析html - JAVA常用库

一、jsoup做什么

jsoup is a Java library for working with real-world HTML. It provides a very convenient API for extracting and manipulating data, using the best of DOM, CSS, and jquery-like methods.

二、jsoup的maven配置

<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.8.3</version>
</dependency>

三、index.html的内容

<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<title>jsoup use</title>
</head>
<body>
first demo:
show
<div>
<p>how to use jsoup?</p>
</div>
</body>
</html>

四、解析html代码示例

代码下载（浏览器打开可能乱码，请直接下载然后打开）：HtmlParser.java

工程文件：html.rar

import java.io.*;
import org.jsoup.*;
import org.jsoup.nodes.*;
import org.jsoup.select.*;
import org.jsoup.parser.*;
import org.jsoup.helper.*;

public class HtmlParser {

public static class TextVisitor implements NodeVisitor {

//单线程一般用StringBuilder，多线程一般用StringBuffer
private StringBuilder text = new StringBuilder();
private boolean showBlock;

public TextVisitor(boolean showBlock) {
this.showBlock = showBlock;
}

public String getText() {
return text.toString().trim();
}

public static boolean preserveWhitespace(Node node) {
if (node != null && node instanceof Element) {
Element element = (Element)node;
return element.tag().preserveWhitespace() ||
element.parent() != null && element.parent().tag().preserveWhitespace();
}
return false;
}

public static boolean lastCharIsSpace(StringBuilder sb) {
return sb.length() != 0 && sb.charAt(sb.length() - 1) == ' ';
}

public static boolean lastCharIsLineBreak(StringBuilder sb) {
return sb.length() != 0 && sb.charAt(sb.length() - 1) == '\n';
}

private static void appendNormalisedText(StringBuilder accum, TextNode textNode) {
String text = textNode.getWholeText();
text = text.trim();
if (preserveWhitespace(textNode.parent()))
accum.append(text);
else
StringUtil.appendNormalisedWhitespace(accum, text, lastCharIsSpace(accum));
}

public void head(Node node, int depth) {
if (node instanceof TextNode) {
TextNode textNode = (TextNode)node;
appendNormalisedText(text, textNode);
} else if (node instanceof Element) {
Element element = (Element)node;
Tag tag = element.tag();
String tagName = tag.getName();
boolean isBlock = tag.isBlock();
if (showBlock)
System.out.println(tagName + " block state is " + isBlock);

if (text.length() > 0
&& (isBlock || tagName.equals("br"))
&& !lastCharIsLineBreak(text))
text.append("\n");
}
}

public void tail(Node node, int depth) {
}
}

public static void parseSimpleHtml() throws Exception {
InputStream input =
HtmlParser.class.getResourceAsStream("/index.html");
Document doc = Jsoup.parse(input, "utf-8", "http://www.3scard.com");

TextVisitor visitor = new TextVisitor(true);
NodeTraversor traversor = new NodeTraversor(visitor);
traversor.traverse(doc);
System.out.println(visitor.getText());
}

public static void parseComplexHtml() throws Exception {
String url = "http://www.3scard.com/index.php?m=blog&f=index";
Document doc = Jsoup.connect(url).get();
System.out.println(doc.text());

TextVisitor visitor = new TextVisitor(false);
NodeTraversor traversor = new NodeTraversor(visitor);
traversor.traverse(doc);
System.out.println(visitor.getText());
}

public static void main(String[] args) throws Exception {
parseSimpleHtml();
parseComplexHtml();
}
}