Web data extraction

# we define global logger
# log messages to file

#<Logger File>
#    Global
#    FileName output-main.txt
#    # log all messages up to debug messages
#    Level debug
#</Logger>

<Section>
    Name main
    
    # load content
    <Action ContentURL>
        URL http://www.nhl.com/
        RemoveNewLine
        TagsToStrip br,nobr,b
    </Action>

    Define $output_file nhl-output.php
    
    # truncate file
    <Action Print>
        FileName {$output_dir}{$output_file}
        FileMode Write  
    </Action>
        
    <Section While>
        # match content of the news
        Optional
        <Section>
            EndAt nTarget.push('0');
            <Pattern>
                # NOTE: * is helper character for [^<]* see documentation
                # NOTE: you can split long line with \ followed by new line
                # NOTE: syntax of variable is {$variable:type} see documentation
                RegExp nImage.push('{$image:re(.*?)}');*\
                       nHeadline.push('{$title:re(.*?)}');*\
                       nTeaser.push('{$article_desc:re(.*?)}');*\
                       nLink.push('{$link:re(.*?)}');
            </Pattern>
     
            # print results as html
            <Action Print>
                FileName {$output_dir}{$output_file}
                Text <p><h1><a href="{$link}">{$title}</a></h1></p><p><img src="{$image}" /></p><p>{$article_desc}</p><br><hr>\n
            </Action>
        </Section>
        <Pattern>
            RegExp nTarget.push('0');
        </Pattern>
    </Section>
</Section>

Main main