view release on metacpan or  search on metacpan

t/test-data/to-split/29.xml  view on Meta::CPAN

          </link>
          <link type="a">
            <anchorText>Google Goes to Congress to Block IAPs Charging for Faster Data</anchorText>
            <location>http://www.webmasterworld.com/forum86/4531.htm</location>
          </link>
          <link type="a">
            <anchorText>Search Engine Guide</anchorText>
            <location>http://www.searchengineguide.com/</location>
          </link>
          <link type="a">
            <anchorText>Does Citing Sources Help Rankings?</anchorText>
            <location>http://www.v7n.com/forums/google-forum/31501-does-citing-sources-help-rankings.html</location>
          </link>
          <link type="a">
            <anchorText>Cache Problems Growing for Directories?</anchorText>
            <location>http://forums.searchenginewatch.com/showthread.php?threadid=11916</location>
          </link>
          <link type="a">
            <anchorText>What Top 5 Skills Would You Study to Become a Better SEO?</anchorText>
            <location>http://forums.searchenginewatch.com/showthread.php?t=11945</location>
          </link>
          <link type="a">
            <anchorText>Google Office Continued: Spreadsheet Application Launched</anchorText>
            <location>http://www.cre8asiteforums.com/forums/index.php?showtopic=37455</location>
          </link>
          <link type="a">
            <anchorText>Separate Page for PPC?</anchorText>
            <location>http://www.webproworld.com/viewtopic.php?t=64119</location>
          </link>
          <link type="a">
            <anchorText>Brin Says Google Compromised Principles</anchorText>
            <location>http://www.webmasterworld.com/forum86/4529.htm</location>
          </link>
          <link type="a">
            <anchorText>Is Reciprocal Linking Dead</anchorText>
            <location>http://www.highrankings.com/forum/index.php?showtopic=22885</location>
          </link>
          <link type="a">
            <anchorText>Google Browser Sync For FireFox</anchorText>
            <location>http://www.webmasterworld.com/forum30/34677.htm</location>
          </link>
        </outlinks>
      </links>
    </acquisition>
  <linguisticAnalysis>
    <semantic_unit_level>
      <semantic_unit><named_entity><form>John McCain</form><named_entity_type>person</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Sergey Brin</form><named_entity_type>person</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Brin</form><named_entity_type>person</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google Inc</form><named_entity_type>comp</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Reciprocal</form><named_entity_type>comp</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>comp</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google Office</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Firefox</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google Browser</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
    </semantic_unit_level>
  </linguisticAnalysis>

  </documentRecord>
<documentRecord id="3DAB2F05CBCFBD7765C7E71C63E6FFE8" xmlns="http://alvis.info/enriched/">
    <acquisition>
      <acquisitionData>
        <modifiedDate>1145563212583</modifiedDate>
        <httpServer>Apache/2.0</httpServer>
        <urls>
          <url>http://google.weblogsinc.com/2006/04/20/google-has-been-testing-google-base-in-search-results/</url>
        </urls>
      </acquisitionData>
      <canonicalDocument>        
        <section>Google is always hard at work fine tuning and trying out new search strategies. Apparantly Google is now hard at work integrating Google Base car searches into the organic results says Jason Dowdell. He recently came across a car sea...
      <metaData>
        <meta name="title">Google has been Testing Google Base in Search Results</meta>
        <meta name="dc:type">text/html</meta>
      </metaData>
      <links>
        <outlinks>
          <link type="a">
            <anchorText>Google Base</anchorText>
            <location>http://base.google.com/</location>
          </link>
          <link type="a">
            <anchorText>ford escape</anchorText>
            <location>http://www.marketingshift.com/images/google-car-search.jpg</location>
          </link>
          <link type="a">
            <anchorText>Jason Dowdell</anchorText>
            <location>http://www.marketingshift.com/2006/04/google-base-car-search-introduced-in.cfm</location>
          </link>
        </outlinks>
      </links>
    </acquisition>
  <linguisticAnalysis>
    <semantic_unit_level>
      <semantic_unit><named_entity><form>Jason Dowdell</form><named_entity_type>person</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>2</form><named_entity_type>person</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Organic</form><named_entity_type>comp</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>comp</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
      <semantic_unit><named_entity><form>Google Base</form><named_entity_type>soft</named_entity_type></named_entity></semantic_unit>
    </semantic_unit_level>
  </linguisticAnalysis>

  </documentRecord>
<documentRecord id="21CED09C683CE568F678E5A8E1683717" xmlns="http://alvis.info/enriched/">
    <acquisition>
      <acquisitionData>
        <modifiedDate>1147533167955</modifiedDate>
        <httpServer>Apache/2.0</httpServer>
        <urls>
          <url>http://sem.weblogsinc.com/2006/05/13/google-trends-for-search-marketing/</url>
        </urls>
      </acquisitionData>
      <canonicalDocument>        
        <section>Google Trends is a hot new tool that uses the Google Zeitgeist to help users find facts and trends that are related to all of Google's usage around the world. Google Trends allows users to watch the collective interests of all of Goo...
      <metaData>
        <meta name="title">Google Trends for Search Marketing</meta>
        <meta name="dc:type">text/html</meta>
      </metaData>
      <links>
        <outlinks>