handler.jsp

Heritrix是一个开源,可扩展的web爬虫项目。Heritrix设计成严格按照robots.txt文件的排除指示和META robots标签。

<%@ page import="org.archive.crawler.admin.CrawlJobHandler, org.archive.crawler.Heritrix" %><%
    /**
     * This include page ensures that the handler exists and is ready to be
     * accessed.
     */
    CrawlJobHandler handler =
        (CrawlJobHandler)application.getAttribute("handler");
    Heritrix heritrix = (Heritrix)application.getAttribute("heritrix");
    
    // If handler is empty then this is the first time this bit of code is
    // being run since the server came online. In that case get or create the
    // handler.
    if (handler == null) {
        if(Heritrix.isSingleInstance()) {
            heritrix = Heritrix.getSingleInstance();
            handler = heritrix.getJobHandler();
            application.setAttribute("heritrix", heritrix);
            application.setAttribute("handler", handler);
        } else {
            // TODO:
            // If we get here, then there are multiple heritrix instances
            // and we have to put up a screen allowing the user choose between.
            // Otherwise, there is no Heritrix instance.  Thats a problem.
            throw new RuntimeException("No heritrix instance (or multiple " +
                    "to choose from and we haven't implemented this yet)");
        }
    }
%>