"need help with the web mining"

link http://www.rapid-i.com http://www.yahoo.com

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="5.0.8" expanded="true" name="Process">
    <process expanded="true" height="492" width="829">
      <operator activated="true" class="read_csv" compatibility="5.0.8" expanded="true" height="60" name="Read CSV" width="90" x="45" y="75">
        <parameter key="file_name" value="file:/C:/Users/SebastianLoh/tmp/links.csv"/>
        <list key="data_set_meta_data_information"/>
      </operator>
      <operator activated="true" class="web:retrieve_webpages" compatibility="5.0.3" expanded="true" height="60" name="Get Pages" width="90" x="179" y="75">
        <parameter key="link_attribute" value="link"/>
        <parameter key="page_attribute" value="page"/>
        <parameter key="random_user_agent" value="true"/>
      </operator>
      <operator activated="true" class="text:data_to_documents" compatibility="5.0.7" expanded="true" height="60" name="Data to Documents" width="90" x="313" y="75">
        <list key="specify_weights"/>
      </operator>
      <connect from_op="Read CSV" from_port="output" to_op="Get Pages" to_port="Example Set"/>
      <connect from_op="Get Pages" from_port="Example Set" to_op="Data to Documents" to_port="example set"/>
      <connect from_op="Data to Documents" from_port="documents" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>