org.jfantasy.framework.util.htmlcleaner

Class HtmlCleanerUtil

java.lang.Object

org.jfantasy.framework.util.htmlcleaner.HtmlCleanerUtil

public class HtmlCleanerUtil
extends java.lang.Object

HtmlCleaner是一个开源的Java语言的Html文档解析器。HtmlCleaner能够重新整理HTML文档的每个元素并生成结构良好(Well-Formed)的 HTML 文档。

Since:

2013-8-13 下午01:41:42

Method Summary

Modifier and Type	Method and Description
static java.lang.String[]	evaluateXPath(org.htmlcleaner.TagNode node, java.lang.String xpath)
static java.lang.String	findByAttValue(java.lang.String htmlPath, java.lang.String att, java.lang.String value)
static org.htmlcleaner.TagNode	findFristTagNode(java.lang.String html, java.lang.String xpath)
static org.htmlcleaner.TagNode	findFristTagNode(org.htmlcleaner.TagNode node, java.lang.String xpath)
static org.htmlcleaner.TagNode	findFristTagNode(java.net.URL url, java.lang.String xpath)
static org.htmlcleaner.TagNode	findFristTagNode(java.net.URL url, java.lang.String charset, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.io.File file, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.io.File file, java.lang.String charset, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.io.InputStream in, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.io.InputStream in, java.lang.String charset, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.io.Reader reader, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.lang.String html, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(org.htmlcleaner.TagNode node, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.net.URL url, java.lang.String xpath)
static org.htmlcleaner.TagNode[]	findTagNodes(java.net.URL url, java.lang.String charset, java.lang.String xpath)
static java.lang.String	getAsString(org.htmlcleaner.TagNode tagNode)
static java.lang.String	getAsString(org.htmlcleaner.XmlSerializer xmlSerializer, org.htmlcleaner.TagNode tagNode)
static org.htmlcleaner.XmlSerializer	getBrowserCompactXmlSerializer(org.htmlcleaner.HtmlCleaner hc)
static org.htmlcleaner.TagNode	htmlCleaner(java.io.File file)
static org.htmlcleaner.TagNode	htmlCleaner(java.io.File file, java.lang.String charset)
static org.htmlcleaner.TagNode	htmlCleaner(java.io.InputStream in)
static org.htmlcleaner.TagNode	htmlCleaner(java.io.InputStream in, java.lang.String charset)
static org.htmlcleaner.TagNode	htmlCleaner(java.io.Reader reader)
static org.htmlcleaner.TagNode	htmlCleaner(java.lang.String html)
static org.htmlcleaner.TagNode	htmlCleaner(java.net.URL url)
static org.htmlcleaner.TagNode	htmlCleaner(java.net.URL url, java.lang.String charset)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.lang.String html,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.io.Reader reader,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.io.InputStream in,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.io.InputStream in,
                                                     java.lang.String charset,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.net.URL url,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.net.URL url,
                                                     java.lang.String charset,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.io.File file,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(java.io.File file,
                                                     java.lang.String charset,
                                                     java.lang.String xpath)

findTagNodes

public static org.htmlcleaner.TagNode[] findTagNodes(org.htmlcleaner.TagNode node,
                                                     java.lang.String xpath)

findFristTagNode

public static org.htmlcleaner.TagNode findFristTagNode(org.htmlcleaner.TagNode node,
                                                       java.lang.String xpath)

findFristTagNode

public static org.htmlcleaner.TagNode findFristTagNode(java.net.URL url,
                                                       java.lang.String xpath)

findFristTagNode

public static org.htmlcleaner.TagNode findFristTagNode(java.net.URL url,
                                                       java.lang.String charset,
                                                       java.lang.String xpath)

findFristTagNode

public static org.htmlcleaner.TagNode findFristTagNode(java.lang.String html,
                                                       java.lang.String xpath)

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.io.File file)
                                           throws java.io.IOException

Throws:

java.io.IOException

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.io.File file,
                                                  java.lang.String charset)
                                           throws java.io.IOException

Throws:

java.io.IOException

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.net.URL url)
                                           throws java.io.IOException

Throws:

java.io.IOException

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.net.URL url,
                                                  java.lang.String charset)
                                           throws java.io.IOException

Throws:

java.io.IOException

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.io.InputStream in)
                                           throws java.io.IOException

Throws:

java.io.IOException

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.io.InputStream in,
                                                  java.lang.String charset)
                                           throws java.io.IOException

Throws:

java.io.IOException

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.io.Reader reader)
                                           throws java.io.IOException

Throws:

java.io.IOException

htmlCleaner

public static org.htmlcleaner.TagNode htmlCleaner(java.lang.String html)

findByAttValue

public static java.lang.String findByAttValue(java.lang.String htmlPath,
                                              java.lang.String att,
                                              java.lang.String value)

evaluateXPath

public static java.lang.String[] evaluateXPath(org.htmlcleaner.TagNode node,
                                               java.lang.String xpath)

getBrowserCompactXmlSerializer

public static org.htmlcleaner.XmlSerializer getBrowserCompactXmlSerializer(org.htmlcleaner.HtmlCleaner hc)

getAsString

public static java.lang.String getAsString(org.htmlcleaner.XmlSerializer xmlSerializer,
                                           org.htmlcleaner.TagNode tagNode)

getAsString

public static java.lang.String getAsString(org.htmlcleaner.TagNode tagNode)