dataimporter tika doesn't extract certain div

[Andreas Owen]

I want tika to only index the content in <div id="content">...</div> for the 
field "text". unfortunately it's indexing the hole page. Can't xpath do this?

data-config.xml:

<dataConfig>
        <dataSource type="BinFileDataSource" name="data"/>
        <dataSource type="BinURLDataSource" name="dataUrl"/>
        <dataSource type="URLDataSource" name="main"/>
<document>
        <entity name="rec" processor="XPathEntityProcessor" 
url="http://127.0.0.1/tkb/internet/docImportUrl.xml"; forEach="/docs/doc" 
dataSource="main"> <!--transformer="script:GenerateId"-->
                <field column="title" xpath="//title" />
                <field column="id" xpath="//id" />
                <field column="file" xpath="//file" />
                <field column="path" xpath="//path" />
                <field column="url" xpath="//url" />
                <field column="Author" xpath="//author" />
                
                <entity name="tika" processor="TikaEntityProcessor" 
url="${rec.path}${rec.file}" dataSource="dataUrl" onError="skip" 
htmlMapper="identity" format="html" >
                        <field column="text" xpath="//div[@id='content']" />
                        
                </entity>
        </entity>
</document>
</dataConfig>