Introduction - If you have any usage issues, please Google them yourself
Web-Harvest is a Java open-source Web data extraction tool. It can collect the specified Web page and extracts from these pages useful data. Web-Harvest is mainly used as XSLT, XQuery, regular expressions, such as these technologies to realize the text/xml operation
Packet : 119128680webharvest1-project.zip filelist
build.xml
config/
config/config.xsd
config/log4j.properties
config/MANIFEST.MF
examples/
examples/canon.xml
examples/crawler.xml
examples/expekt.xml
examples/flickr.xml
examples/functions.xml
examples/google_images.xml
examples/nytimes.xml
examples/xquery.xml
examples/yahoomail.xml
lib/
lib/bsh.jar
lib/commons-cli-1.1.jar
lib/commons-codec-1.3.jar
lib/commons-collections-3.1.jar
lib/commons-httpclient-3.1.jar
lib/commons-logging.jar
lib/groovy-all-1.0.jar
lib/htmlcleaner.jar
lib/js.jar
lib/log4j-1.2.13.jar
lib/saxon8-dom.jar
lib/saxon8.jar
licences/
licences/apache_licence.txt
licences/asm_licence.txt
licences/beanshell_licence.txt
licences/bounce_licence.txt
licences/groovy_licence.txt
licences/htmlcleaner_licence.txt
licences/rhino_licence.txt
licences/saxon_licence.txt
licences/webharvest_licence.txt
src/
src/CommandLine.java
src/org/
src/org/apache/
src/org/apache/commons/
src/org/apache/commons/httpclient/
src/org/apache/commons/httpclient/contrib/
src/org/apache/commons/httpclient/contrib/ssl/
src/org/apache/commons/httpclient/contrib/ssl/AuthSSLInitializationError.java
src/org/apache/commons/httpclient/contrib/ssl/AuthSSLProtocolSocketFactory.java
src/org/apache/commons/httpclient/contrib/ssl/AuthSSLX509TrustManager.java
src/org/apache/commons/httpclient/contrib/ssl/EasySSLProtocolSocketFactory.java
src/org/apache/commons/httpclient/contrib/ssl/EasyX509TrustManager.java
src/org/apache/commons/httpclient/contrib/ssl/StrictSSLProtocolSocketFactory.java
src/org/bounce/
src/org/bounce/text/
src/org/bounce/text/ScrollableEditorPanel.java
src/org/bounce/text/xml/
src/org/bounce/text/xml/WrappedXMLView.java
src/org/bounce/text/xml/XMLContext.java
src/org/bounce/text/xml/XMLDocument.java
src/org/bounce/text/xml/XMLEditorKit.java
src/org/bounce/text/xml/XMLInputReader.java
src/org/bounce/text/xml/XMLInputStream.java
src/org/bounce/text/xml/XmlParserUtils.java
src/org/bounce/text/xml/XMLScanner.java
src/org/bounce/text/xml/XMLStyleConstants.java
src/org/bounce/text/xml/XMLView.java
src/org/bounce/text/xml/XMLViewUtilities.java
src/org/webharvest/
src/org/webharvest/definition/
src/org/webharvest/definition/BaseElementDef.java
src/org/webharvest/definition/CallDef.java
src/org/webharvest/definition/CallParamDef.java
src/org/webharvest/definition/CaseDef.java
src/org/webharvest/definition/ConstantDef.java
src/org/webharvest/definition/DefinitionResolver.java
src/org/webharvest/definition/ElementInfo.java
src/org/webharvest/definition/EmptyDef.java
src/org/webharvest/definition/ExitDef.java
src/org/webharvest/definition/FileDef.java
src/org/webharvest/definition/FunctionDef.java
src/org/webharvest/definition/HtmlToXmlDef.java
src/org/webharvest/definition/HttpDef.java
src/org/webharvest/definition/HttpHeaderDef.java
src/org/webharvest/definition/HttpParamDef.java
src/org/webharvest/definition/IElementDef.java
src/org/webharvest/definition/IfDef.java
src/org/webharvest/definition/IncludeDef.java
src/org/webharvest/definition/LoopDef.java
src/org/webharvest/definition/RegexpDef.java
src/org/webharvest/definition/ReturnDef.java
src/org/webharvest/definition/ScraperConfiguration.java
src/org/webharvest/definition/ScriptDef.java
src/org/webharvest/definition/TemplateDef.java
src/org/webharvest/definition/TextDef.java
src/org/webharvest/definition/TryDef.java
src/org/webharvest/definition/VarDef.java
src/org/webharvest/definition/VarDefDef.java
src/org/webharvest/definition/WhileDef.java
src/org/webharvest/definition/XmlNode.java
src/org/webharvest/definition/XmlParser.java
src/org/webharvest/definition/XPathDef.java
src/org/webharvest/definition/XQueryDef.java
src/org/webharvest/definition/XQueryExternalParamDef.java
src/org/webharvest/definition/XsltDef.java
src/org/webharvest/exception/
src/org/webharvest/exception/BaseException.java
src/org/webharvest/exception/ConfigurationException.java
src/org/webharvest/exception/ErrMsg.java
src/org/webharvest/exception/FileException.java
src/org/webharvest/exception/FunctionException.java
src/org/webharvest/exception/HttpException.java
src/org/webharvest/exception/ParserException.java
src/org/webharvest/exception/ScraperXPathException.java
src/org/webharvest/exception/ScraperXQueryException.java
src/org/webharvest/exception/ScriptException.java
src/org/webharvest/exception/TemplateException.java
src/org/webharvest/exception/TemplaterException.java
src/org/webharvest/exception/VariableException.java
src/org/webharvest/exception/XsltException.java
src/org/webharvest/gui/
src/org/webharvest/gui/AboutWindow.java
src/org/webharvest/gui/AutoCompleter.java
src/org/webharvest/gui/component/
src/org/webharvest/gui/component/DropDownButton.java
src/org/webharvest/gui/component/DropDownButtonListener.java
src/org/webharvest/gui/component/GCPanel.java
src/org/webharvest/gui/component/ProportionalSplitPane.java
src/org/webharvest/gui/ConfigDocument.java
src/org/webharvest/gui/ConfigPanel.java
src/org/webharvest/gui/DialogHelper.java
src/org/webharvest/gui/FindReplaceDialog.java
src/org/webharvest/gui/HelpFrame.java
src/org/webharvest/gui/Ide.java
src/org/webharvest/gui/NodeRenderer.java
src/org/webharvest/gui/PropertiesGrid.java
src/org/webharvest/gui/PropertiesGridModel.java
src/org/webharvest/gui/ResourceManager.java
src/org/webharvest/gui/resources/
src/org/webharvest/gui/resources/about.html
src/org/webharvest/gui/resources/headerbg.jpg
src/org/webharvest/gui/resources/help/
src/org/webharvest/gui/resources/help.xml
src/org/webharvest/gui/resources/help/basics.html
src/org/webharvest/gui/resources/help/call.html
src/org/webharvest/gui/resources/help/case.html
src/org/webharvest/gui/resources/help/config.html
src/org/webharvest/gui/resources/help/diagram1.gif
src/org/webharvest/gui/resources/help/empty.html
src/org/webharvest/gui/resources/help/exit.html
src/org/webharvest/gui/resources/help/file.html
src/org/webharvest/gui/resources/help/function.html
src/org/webharvest/gui/resources/help/htmltoxml.html
src/org/webharvest/gui/resources/help/http.html
src/org/webharvest/gui/resources/help/httpheader.html
src/org/webharvest/gui/resources/help/httpparam.html
src/org/webharvest/gui/resources/help/httpproc.html
src/org/webharvest/gui/resources/help/include.html
src/org/webharvest/gui/resources/help/licence.html
src/org/webharvest/gui/resources/help/loop.html
src/org/webharvest/gui/resources/help/overview.html
src/org/webharvest/gui/resources/help/regexp.html
src/org/webharvest/gui/resources/help/release.html
src/org/webharvest/gui/resources/help/return.html
src/org/webharvest/gui/resources/help/script.html
src/org/webharvest/gui/resources/help/sys.html
src/org/webharvest/gui/resources/help/template.html
src/org/webharvest/gui/resources/help/text.html
src/org/webharvest/gui/resources/help/try.html
src/org/webharvest/gui/resources/help/var.html
src/org/webharvest/gui/resources/help/vardef.html
src/org/webharvest/gui/resources/help/while.html
src/org/webharvest/gui/resources/help/xpath.html
src/org/webharvest/gui/resources/help/xquery.html
src/org/webharvest/gui/resources/help/xslt.html
src/org/webharvest/gui/resources/icons/
src/org/webharvest/gui/resources/icons/call.gif
src/org/webharvest/gui/resources/icons/case.gif
src/org/webharvest/gui/resources/icons/close.gif
src/org/webharvest/gui/resources/icons/const.gif
src/org/webharvest/gui/resources/icons/copy.gif
src/org/webharvest/gui/resources/icons/cut.gif
src/org/webharvest/gui/resources/icons/default.gif
src/org/webharvest/gui/resources/icons/download.gif
src/org/webharvest/gui/resources/icons/empty.gif
src/org/webharvest/gui/resources/icons/file.gif
src/org/webharvest/gui/resources/icons/find.gif
src/org/webharvest/gui/resources/icons/function.gif
src/org/webharvest/gui/resources/icons/help.gif
src/org/webharvest/gui/resources/icons/help32.gif
src/org/webharvest/gui/resources/icons/helpdir.gif
src/org/webharvest/gui/resources/icons/helptopic.gif
src/org/webharvest/gui/resources/icons/homepage.gif
src/org/webharvest/gui/resources/icons/htmltoxml.gif
src/org/webharvest/gui/resources/icons/html_type.gif
src/org/webharvest/gui/resources/icons/http.gif
src/org/webharvest/gui/resources/icons/httpparam.gif
src/org/webharvest/gui/resources/icons/image_type.gif
src/org/webharvest/gui/resources/icons/include.gif
src/org/webharvest/gui/resources/icons/list_type.gif
src/org/webharvest/gui/resources/icons/loop.gif
src/org/webharvest/gui/resources/icons/new.gif
src/org/webharvest/gui/resources/icons/none.gif
src/org/webharvest/gui/resources/icons/open.gif
src/org/webharvest/gui/resources/icons/paste.gif
src/org/webharvest/gui/resources/icons/pause.gif
src/org/webharvest/gui/resources/icons/prettyprint.gif
src/org/webharvest/gui/resources/icons/process.gif
src/org/webharvest/gui/resources/icons/redo.gif
src/org/webharvest/gui/resources/icons/refresh.gif
src/org/webharvest/gui/resources/icons/regexp.gif
src/org/webharvest/gui/resources/icons/run.gif
src/org/webharvest/gui/resources/icons/runparams.gif
src/org/webharvest/gui/resources/icons/save.gif
src/org/webharvest/gui/resources/icons/settings.gif
src/org/webharvest/gui/resources/icons/small_error.gif
src/org/webharvest/gui/resources/icons/small_finished.gif
src/org/webharvest/gui/resources/icons/small_paused.gif
src/org/webharvest/gui/resources/icons/small_run.gif
src/org/webharvest/gui/resources/icons/small_view.gif
src/org/webharvest/gui/resources/icons/stop.gif
src/org/webharvest/gui/resources/icons/template.gif
src/org/webharvest/gui/resources/icons/text.gif
src/org/webharvest/gui/resources/icons/text_type.gif
src/org/webharvest/gui/resources/icons/trashcan.gif
src/org/webharvest/gui/resources/icons/try.gif
src/org/webharvest/gui/resources/icons/undo.gif
src/org/webharvest/gui/resources/icons/validate.gif
src/org/webharvest/gui/resources/icons/var.gif
src/org/webharvest/gui/resources/icons/vardef.gif
src/org/webharvest/gui/resources/icons/view.gif
src/org/webharvest/gui/resources/icons/webharvest.gif
src/org/webharvest/gui/resources/icons/xml_type.gif
src/org/webharvest/gui/resources/icons/xpath.gif
src/org/webharvest/gui/resources/icons/xquery.gif
src/org/webharvest/gui/resources/icons/xslt.gif
src/org/webharvest/gui/resources/icons/zoomin.gif
src/org/webharvest/gui/resources/icons/zoomout.gif
src/org/webharvest/gui/resources/welcome.html
src/org/webharvest/gui/resources/welcomelogo.jpg
src/org/webharvest/gui/RunParamsDialog.java
src/org/webharvest/gui/ScraperExecutionThread.java
src/org/webharvest/gui/Settings.java
src/org/webharvest/gui/SettingsDialog.java
src/org/webharvest/gui/StatusBar.java
src/org/webharvest/gui/TextAreaAppender.java
src/org/webharvest/gui/TreeNodeInfo.java
src/org/webharvest/gui/ViewerFrame.java
src/org/webharvest/gui/WelcomePanel.java
src/org/webharvest/gui/XmlEditorScrollPane.java
src/org/webharvest/gui/XmlFileFilter.java
src/org/webharvest/gui/XmlTextPane.java
src/org/webharvest/runtime/
src/org/webharvest/runtime/processors/
src/org/webharvest/runtime/processors/BaseProcessor.java
src/org/webharvest/runtime/processors/BodyProcessor.java
src/org/webharvest/runtime/processors/CallParamProcessor.java
src/org/webharvest/runtime/processors/CallProcessor.java
src/org/webharvest/runtime/processors/CaseProcessor.java
src/org/webharvest/runtime/processors/ConstantProcessor.java
src/org/webharvest/runtime/processors/EmptyProcessor.java
src/org/webharvest/runtime/processors/ExitProcessor.java
src/org/webharvest/runtime/processors/FileProcessor.java
src/org/webharvest/runtime/processors/FunctionProcessor.java
src/org/webharvest/runtime/processors/HtmlToXmlProcessor.java
src/org/webharvest/runtime/processors/HttpHeaderProcessor.java
src/org/webharvest/runtime/processors/HttpParamProcessor.java
src/org/webharvest/runtime/processors/HttpProcessor.java
src/org/webharvest/runtime/processors/IncludeProcessor.java
src/org/webharvest/runtime/processors/LoopProcessor.java
src/org/webharvest/runtime/processors/ProcessorResolver.java
src/org/webharvest/runtime/processors/RegexpProcessor.java
src/org/webharvest/runtime/processors/ReturnProcessor.java
src/org/webharvest/runtime/processors/ScriptProcessor.java
src/org/webharvest/runtime/processors/TemplateProcessor.java
src/org/webharvest/runtime/processors/TextProcessor.java
src/org/webharvest/runtime/processors/TryProcessor.java
src/org/webharvest/runtime/processors/VarDefProcessor.java
src/org/webharvest/runtime/processors/VarProcessor.java
src/org/webharvest/runtime/processors/WhileProcessor.java
src/org/webharvest/runtime/processors/XPathProcessor.java
src/org/webharvest/runtime/processors/XQueryExpressionPool.java
src/org/webharvest/runtime/processors/XQueryProcessor.java
src/org/webharvest/runtime/processors/XsltProcessor.java
src/org/webharvest/runtime/RuntimeConfig.java
src/org/webharvest/runtime/Scraper.java
src/org/webharvest/runtime/ScraperContext.java
src/org/webharvest/runtime/ScraperRuntimeListener.java
src/org/webharvest/runtime/scripting/
src/org/webharvest/runtime/scripting/BeanShellScriptEngine.java
src/org/webharvest/runtime/scripting/GroovyScriptEngine.java
src/org/webharvest/runtime/scripting/JavascriptScriptEngine.java
src/org/webharvest/runtime/scripting/ScriptEngine.java
src/org/webharvest/runtime/scripting/SetContextVar.java
src/org/webharvest/runtime/templaters/
src/org/webharvest/runtime/templaters/BaseTemplater.java
src/org/webharvest/runtime/variables/
src/org/webharvest/runtime/variables/EmptyVariable.java
src/org/webharvest/runtime/variables/ListVariable.java
src/org/webharvest/runtime/variables/NodeVariable.java
src/org/webharvest/runtime/variables/Types.java
src/org/webharvest/runtime/variables/Variable.java
src/org/webharvest/runtime/web/
src/org/webharvest/runtime/web/HttpClientManager.java
src/org/webharvest/runtime/web/HttpInfo.java
src/org/webharvest/runtime/web/HttpResponseWrapper.java
src/org/webharvest/runtime/web/IHttpManager.java
src/org/webharvest/utils/
src/org/webharvest/utils/Catalog.java
src/org/webharvest/utils/CommonUtil.java
src/org/webharvest/utils/Constants.java
src/org/webharvest/utils/KeyValuePair.java
src/org/webharvest/utils/Stack.java
src/org/webharvest/utils/SystemUtilities.java
src/org/webharvest/utils/XmlNodeWrapper.java
src/org/webharvest/utils/XmlUtil.java
src/org/webharvest/utils/XmlValidator.java
src/Test.java