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 on the text/xml operation. Test version.
Packet : 105230310testofwebharvest05-all.zip filelist
build.xml
config/
config/config.xsd
examples/
examples/canon.xml
examples/crawler.xml
examples/expekt.xml
examples/functions.xml
examples/google_images.xml
examples/nytimes.xml
examples/xquery.xml
lib/
lib/bsh.jar
lib/commons-codec-1.3.jar
lib/commons-collections-3.1.jar
lib/commons-httpclient-3.0-rc3.jar
lib/commons-logging.jar
lib/htmlcleaner.jar
lib/log4j-1.2.13.jar
lib/saxon8.jar
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/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/EmptyDef.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/runtime/
src/org/webharvest/runtime/html/
src/org/webharvest/runtime/html/HtmlCleanerProcessor.java
src/org/webharvest/runtime/html/IXHtmlProcessor.java
src/org/webharvest/runtime/processors/
src/org/webharvest/runtime/processors/BaseProcessor.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/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/XQueryProcessor.java
src/org/webharvest/runtime/processors/XsltProcessor.java
src/org/webharvest/runtime/Scraper.java
src/org/webharvest/runtime/ScraperContext.java
src/org/webharvest/runtime/scripting/
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/Appender.java
src/org/webharvest/runtime/variables/EmptyVariable.java
src/org/webharvest/runtime/variables/IVariable.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/web/
src/org/webharvest/runtime/web/HttpClientManager.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/Stack.java
src/org/webharvest/utils/SystemUtilities.java
src/org/webharvest/utils/XMLWriter.java
src/Test.java
TestOfWebharvest05-all/
TestOfWebharvest05-all/build.xml
TestOfWebharvest05-all/config/
TestOfWebharvest05-all/config/config.xsd
TestOfWebharvest05-all/examples/
TestOfWebharvest05-all/examples/canon.xml
TestOfWebharvest05-all/examples/crawler.xml
TestOfWebharvest05-all/examples/expekt.xml
TestOfWebharvest05-all/examples/functions.xml
TestOfWebharvest05-all/examples/google_images.xml
TestOfWebharvest05-all/examples/nytimes.xml
TestOfWebharvest05-all/examples/xquery.xml
TestOfWebharvest05-all/lib/
TestOfWebharvest05-all/lib/bsh.jar
TestOfWebharvest05-all/lib/commons-codec-1.3.jar
TestOfWebharvest05-all/lib/commons-collections-3.1.jar
TestOfWebharvest05-all/lib/commons-httpclient-3.0-rc3.jar
TestOfWebharvest05-all/lib/commons-logging.jar
TestOfWebharvest05-all/lib/htmlcleaner.jar
TestOfWebharvest05-all/lib/log4j-1.2.13.jar
TestOfWebharvest05-all/lib/saxon8.jar
TestOfWebharvest05-all/src/
TestOfWebharvest05-all/src/CommandLine.java
TestOfWebharvest05-all/src/org/
TestOfWebharvest05-all/src/org/apache/
TestOfWebharvest05-all/src/org/apache/commons/
TestOfWebharvest05-all/src/org/apache/commons/httpclient/
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/ssl/
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/ssl/AuthSSLInitializationError.java
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/ssl/AuthSSLProtocolSocketFactory.java
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/ssl/AuthSSLX509TrustManager.java
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/ssl/EasySSLProtocolSocketFactory.java
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/ssl/EasyX509TrustManager.java
TestOfWebharvest05-all/src/org/apache/commons/httpclient/contrib/ssl/StrictSSLProtocolSocketFactory.java
TestOfWebharvest05-all/src/org/webharvest/
TestOfWebharvest05-all/src/org/webharvest/definition/
TestOfWebharvest05-all/src/org/webharvest/definition/BaseElementDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/CallDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/CallParamDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/CaseDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/ConstantDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/DefinitionResolver.java
TestOfWebharvest05-all/src/org/webharvest/definition/EmptyDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/FileDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/FunctionDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/HtmlToXmlDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/HttpDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/HttpHeaderDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/HttpParamDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/IElementDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/IfDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/IncludeDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/LoopDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/RegexpDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/ReturnDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/ScraperConfiguration.java
TestOfWebharvest05-all/src/org/webharvest/definition/ScriptDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/TemplateDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/TextDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/TryDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/VarDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/VarDefDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/WhileDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/XmlNode.java
TestOfWebharvest05-all/src/org/webharvest/definition/XmlParser.java
TestOfWebharvest05-all/src/org/webharvest/definition/XPathDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/XQueryDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/XQueryExternalParamDef.java
TestOfWebharvest05-all/src/org/webharvest/definition/XsltDef.java
TestOfWebharvest05-all/src/org/webharvest/exception/
TestOfWebharvest05-all/src/org/webharvest/exception/BaseException.java
TestOfWebharvest05-all/src/org/webharvest/exception/ConfigurationException.java
TestOfWebharvest05-all/src/org/webharvest/exception/ErrMsg.java
TestOfWebharvest05-all/src/org/webharvest/exception/FileException.java
TestOfWebharvest05-all/src/org/webharvest/exception/FunctionException.java
TestOfWebharvest05-all/src/org/webharvest/exception/HttpException.java
TestOfWebharvest05-all/src/org/webharvest/exception/ParserException.java
TestOfWebharvest05-all/src/org/webharvest/exception/ScraperXPathException.java
TestOfWebharvest05-all/src/org/webharvest/exception/ScraperXQueryException.java
TestOfWebharvest05-all/src/org/webharvest/exception/ScriptException.java
TestOfWebharvest05-all/src/org/webharvest/exception/TemplateException.java
TestOfWebharvest05-all/src/org/webharvest/exception/TemplaterException.java
TestOfWebharvest05-all/src/org/webharvest/exception/VariableException.java
TestOfWebharvest05-all/src/org/webharvest/exception/XsltException.java
TestOfWebharvest05-all/src/org/webharvest/runtime/
TestOfWebharvest05-all/src/org/webharvest/runtime/html/
TestOfWebharvest05-all/src/org/webharvest/runtime/html/HtmlCleanerProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/html/IXHtmlProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/BaseProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/CallParamProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/CallProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/CaseProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/ConstantProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/EmptyProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/FileProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/FunctionProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/HtmlToXmlProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/HttpHeaderProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/HttpParamProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/HttpProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/IncludeProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/LoopProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/ProcessorResolver.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/RegexpProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/ReturnProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/ScriptProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/TemplateProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/TextProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/TryProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/VarDefProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/VarProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/WhileProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/XPathProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/XQueryProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/processors/XsltProcessor.java
TestOfWebharvest05-all/src/org/webharvest/runtime/Scraper.java
TestOfWebharvest05-all/src/org/webharvest/runtime/ScraperContext.java
TestOfWebharvest05-all/src/org/webharvest/runtime/scripting/
TestOfWebharvest05-all/src/org/webharvest/runtime/scripting/ScriptEngine.java
TestOfWebharvest05-all/src/org/webharvest/runtime/scripting/SetContextVar.java
TestOfWebharvest05-all/src/org/webharvest/runtime/templaters/
TestOfWebharvest05-all/src/org/webharvest/runtime/templaters/BaseTemplater.java
TestOfWebharvest05-all/src/org/webharvest/runtime/variables/
TestOfWebharvest05-all/src/org/webharvest/runtime/variables/Appender.java
TestOfWebharvest05-all/src/org/webharvest/runtime/variables/EmptyVariable.java
TestOfWebharvest05-all/src/org/webharvest/runtime/variables/IVariable.java
TestOfWebharvest05-all/src/org/webharvest/runtime/variables/ListVariable.java
TestOfWebharvest05-all/src/org/webharvest/runtime/variables/NodeVariable.java
TestOfWebharvest05-all/src/org/webharvest/runtime/variables/Types.java
TestOfWebharvest05-all/src/org/webharvest/runtime/web/
TestOfWebharvest05-all/src/org/webharvest/runtime/web/HttpClientManager.java
TestOfWebharvest05-all/src/org/webharvest/runtime/web/HttpResponseWrapper.java
TestOfWebharvest05-all/src/org/webharvest/runtime/web/IHttpManager.java
TestOfWebharvest05-all/src/org/webharvest/utils/
TestOfWebharvest05-all/src/org/webharvest/utils/Catalog.java
TestOfWebharvest05-all/src/org/webharvest/utils/CommonUtil.java
TestOfWebharvest05-all/src/org/webharvest/utils/Constants.java
TestOfWebharvest05-all/src/org/webharvest/utils/Stack.java
TestOfWebharvest05-all/src/org/webharvest/utils/SystemUtilities.java
TestOfWebharvest05-all/src/org/webharvest/utils/XMLWriter.java
TestOfWebharvest05-all/src/Test.java
webharvest05.jar