Unit Miner - Web data extraction

DATA RETRIEVED FOR WSJ

EXTRACTION SCRIPT USED

<Section>
    Name main

    Define $output_file wsj-output1.html
    
    <Action ContentURL>
        URL http://chinese.wsj.com/gb/index.asp
        RemoveNewLine
    </Action>
    
    <Action Print>
        FileName {$output_file}
        FileMode Write
        Text <head><meta http-equiv="Content-Type" content="text/html; charset=GB2312"></head>

    </Action>    
    
    <Section While>
        <Pattern>
            RegExp   <tr>*<td><a class=c href="{$relative_link_url}"><span >{$titel}</span>\
            </a><span class="text1">{$text}</span>*</td>*</tr>*<tr>*<td height="30">*\
            <div align="center">* * * </div>*</td>*</tr>

        </Pattern>
        
        <Action Print>
            FileName {$output_file}
            Text {$relative_link_url} - {$titel} - {$text}\n<br>
        </Action>
    </Section>
    

</Section>

Main main