xpath java html_Java 使用HtmlCleaner、Saxon和XPath(XPathEvaluator)进行html查找解析的方法...

1、安装引用HtmlCleaner和Saxon

Maven中Pom.xml中添加依赖：

net.sourceforge.htmlcleaner

htmlcleaner

net.sf.saxon

Saxon-HE

2、使用HtmlCleaner、Saxon和XPath(XPathEvaluator)示例代码

package us.codecraft.webmagic.selector;

import net.sf.saxon.lib.NamespaceConstant;

import net.sf.saxon.xpath.XPathEvaluator;

import org.htmlcleaner.CleanerProperties;

import org..DomSerializer;

import org.htmlcleaner.HtmlCleaner;

import org.htmlcleaner.TagNode;

import org.slf4j.Logger;

import org.slf4j.LoggerFactory;

import org.w3c.dom.Document;

import org.w3c.dom.Node;

import org.w3c.dom.NodeList;

import javax.xml.namespace.NamespaceContext;

import javax.xml.transform.OutputKeys;

import javax.xml.transform.Transformer;

import javax.xml.transform.TransformerFactory;

import javax.xml.transform.dom.DOMSource;

import javax.xml.transform.stream.StreamResult;

import javax.xml.xpath.XPathConstants;

import javax.xml.xpath.XPathExpression;

import javax.xml.xpath.XPathExpressionException;

import java.io.StringWriter;

import java.util.ArrayList;

import java.util.Iterator;

import java.util.List;

import java.util.Map;

import java.util.concurrent.ConcurrentHashMap;

/**

* 支持xpath2.0的选择器。包装了HtmlCleaner和Saxon HE。

*