textextractingvisitortest.java

来自「html解析包 可以很方便的解析html 纯java 实现」· Java 代码 · 共 89 行

JAVA
89 行
字号 
// HTMLParser Library $Name: v1_6_20051112 $ - A java-based parser for HTML// http://sourceforge.org/projects/htmlparser// Copyright (C) 2004 Somik Raha//// Revision Control Information//// $Source: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/TextExtractingVisitorTest.java,v $// $Author: derrickoswald $// $Date: 2004/01/02 16:24:57 $// $Revision: 1.15 $//// This library is free software; you can redistribute it and/or// modify it under the terms of the GNU Lesser General Public// License as published by the Free Software Foundation; either// version 2.1 of the License, or (at your option) any later version.//// This library is distributed in the hope that it will be useful,// but WITHOUT ANY WARRANTY; without even the implied warranty of// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU// Lesser General Public License for more details.//// You should have received a copy of the GNU Lesser General Public// License along with this library; if not, write to the Free Software// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA//package org.htmlparser.tests.visitorsTests;import org.htmlparser.tests.ParserTestCase;import org.htmlparser.visitors.TextExtractingVisitor;public class TextExtractingVisitorTest extends ParserTestCase {    static    {        System.setProperty ("org.htmlparser.tests.visitorsTests.TextExtractingVisitorTest", "TextExtractingVisitorTest");    }    public TextExtractingVisitorTest(String name) {        super(name);    }    public void testSimpleVisit() throws Exception {        createParser("<HTML><HEAD><TITLE>Hello World</TITLE></HEAD></HTML>");        TextExtractingVisitor visitor = new TextExtractingVisitor();        parser.visitAllNodesWith(visitor);        assertStringEquals(            "extracted text",            "Hello World",            visitor.getExtractedText()        );    }    public void testSimpleVisitWithRegisteredScanners() throws Exception {        createParser("<HTML><HEAD><TITLE>Hello World</TITLE></HEAD></HTML>");        TextExtractingVisitor visitor = new TextExtractingVisitor();        parser.visitAllNodesWith(visitor);        assertStringEquals(            "extracted text",            "Hello World",            visitor.getExtractedText()        );    }    public void testVisitHtmlWithSpecialChars() throws Exception {        createParser("<BODY>Hello World&nbsp;&nbsp;</BODY>");        TextExtractingVisitor visitor = new TextExtractingVisitor();        parser.visitAllNodesWith(visitor);        assertStringEquals(            "extracted text",            "Hello World  ",            visitor.getExtractedText()        );    }    public void testVisitHtmlWithPreTags() throws Exception {        createParser(            "Some text with &nbsp;<pre>this &nbsp; should be preserved</pre>"        );        TextExtractingVisitor visitor = new TextExtractingVisitor();        parser.visitAllNodesWith(visitor);        assertStringEquals(            "extracted text",            "Some text with  this &nbsp; should be preserved",            visitor.getExtractedText()        );    }}

textextractingvisitortest.java - 源码说明

本页面展示了「html解析包 可以很方便的解析html 纯java 实现」中的 textextractingvisitortest.java 源码文件，采用 Java 编程语言编写，共 89 行代码。您可以在线阅读完整代码内容，也可以返回资源详情页下载完整源码包进行本地学习和开发。

虫虫下载站收录了大量与html相关的技术资源，包括源代码、技术文档、电路图等，是电子工程师和嵌入式开发者的专业学习平台。

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?