<HTMLScrapperConfig name="NYTimesScraperConfig" >

    <StateTransitions processedResultType="Record" begState="_None_">
        <HTMLEvent eventType="StartTag" tagType="a" fromState="_None_" toState="foundHref" >
            <InputAttribute attrName="href" startWith="http://query.nytimes.com/search/full-page?res=" />
            <OutputAttribute attrName="href" outputTo="linkHref" />
        </HTMLEvent>
        <HTMLEvent eventType="StartTag" tagType="a" fromState="_None_" toState="foundHref" >
            <InputAttribute attrName="href" startWith="http://query.nytimes.com/search/abstract?res=" />
            <OutputAttribute attrName="href" outputTo="linkHref" />
        </HTMLEvent>


        <HTMLEvent eventType="HandleText" fromState="foundHref" toState="foundHref" 
                   outputTo="linkText" append="true" />
        <HTMLEvent eventType="EndTag" tagType="a" fromState="foundHref" toState="_None_" processResult="true" />
    </StateTransitions>

    <OutputFormat>
        <RootTag tagName="Records" />
        <ProcessedResult processedResultType="Record" tagName="Record" >
            <ProcessedElement tagName="Title" charDataFrom="linkText" />
            <ChildElement tagName="Details" elementDataFromHref="linkHref" 
                          host="" 
                          XMLDef="BASE_PATH/NYTimes/NYTimesDetails.xml" />


        </ProcessedResult>
    </OutputFormat>

</HTMLScrapperConfig>