Example - retrieves first 5 products from first 3 categories from hub.shop.ebay.com

# File: ebay_main.w
# Name: eBay - The World's Online Marketplace
# Description: Script retrieves first 5 products from first 3 categories from hub.shop.ebay.com
#              and saves them to CSV file and XLS file
# Input: URL [http://hub.shop.ebay.com/]
# Output format: CSV file, XLS file
# Output fields: Source URL, Category URL, Category Name, Expiration Time, Offer Name,
#                Bid History, Current Bid, Image URL, Image Name, Image Alternative Text

#enable logging for debug purpose
#<Logger File>
#	Global
#	FileName ebay.log
#	Level debug
#</Logger>

#main section of script
<Section>
	#define name of section
	Name ebay_main
	#define website url
	Define $main http://hub.shop.ebay.com/

    Define $path http://www.qualityunit.com/fileadmin/scripts/ebay/img/
	
	#create directory for image storage if it does not exist
	<Action PHP>
		TemplateText if (!file_exists("./img")) mkdir("./img", 0777);
	</Action>
		
	#delete old output CSV and HTML files and stored images
	<Action Exec>
		cmd rm -f *.csv
	</Action>
	
	<Action Exec>
		cmd rm -f *.html
	</Action>

	<Action Exec>
		cmd rm -f img/*.jpg
	</Action>

	
	#load content
	<Action ContentURL>
		#load content from the following URL saved in variable main
		URL {$main}
		#removes newlines from downloaded content for easier matching 
		RemoveNewLine
	</Action>
		
	#in this section we will iterate trough all main categories
	<Section While>
		#set maximum of iterations
		MaxIterations 3
	
		#this pattern should match category url and category name
		<Pattern>
			#defines expression which should match the data
			RegExp <div id="FontGradientLink5"*><a href="{$category_url:re([^"]*)}">{$category_name}
			#replace html encoded characters into their normal representation
			HtmlSpecialChars
			Trim
			Compact
		</Pattern>
		
		#evaluate script saved in file ebay_productlist.w
		<Action Eval>
			File ebay_productlist.w
		</Action>
	</Section>

	#delete old output XLS file
	<Action Exec>
		cmd rm -f *.xls
	</Action>
	
	#convert data from csv file into xls file
	<Action ConvertToXLS>
		InputFile ebay_output.csv
		OutputFile ebay_output.xls
		Separator ;
	</Action>
</Section>

#run section with name "ebay_main"
Main ebay_main

# File: ebay_productlist.w

#main section of script
<Section>
	#define name of section
	Name ebay_productlist
	Optional
	
	#load content
	<Action ContentURL>
		#load content from the following URL saved in variable category_url
		URL {$category_url}
		#removes newlines from downloaded content for easier matching 
		RemoveNewLine
	</Action>
	
	#in this section we will iterate trough all products in particular category
	<Section While>
		#set maximum of iterations
		MaxIterations 5
		
		<Section Or>		
			NoContext
			
			#this pattern should match first version of product url and product name
			<Pattern>
				#defines expression which should match the data
				RegExp <div class="ittl"*>{:re(.*?)}<a href="{$product_url:re([^"]*)}"*>{$product_name}
				Trim
				Compact
			</Pattern>
			
			#this pattern should match second version of product url and product name
			<Pattern>
				#defines expression which should match the data
				RegExp <div class="ttl"*><a href="{$product_url:re([^"]*)}"*>{$product_name}
				Trim
				Compact
			</Pattern>
		</Section>
			
		#evaluate script saved in file ebay_product.w
		<Action Eval>
			File ebay_product.w
		</Action>
	</Section>	
</Section>

#run section with name "ebay_productlist"
Main ebay_productlist

# File: ebay_product.w

#main section of script
<Section>
	#define name of section
	Name ebay_product
	Optional
	
	#load content
	<Action ContentURL>
		#load content from the following URL saved in variable product_url
		URL {$product_url}
		#removes newlines from downloaded content for easier matching 
		RemoveNewLine
	</Action>
	
	#this pattern should match image url and image alternative text
	<Pattern>
		#defines expression which should match the data
		RegExp <img src="{$image_url:re([^"]*)}" id="i_vv4{:re([^"]*)}"*alt="{$image_alternative:re([^"]*)}"{:re([^>]*)}>
		#replace html encoded characters into their normal representation
		HtmlSpecialChars
		Optional
		Trim
		Compact
	</Pattern>

	#define image name, which will be stored in csv file
	<Action Php>
		Code $context->setVariable('$image_name',\
			substr(md5($context->getVariable('$product_name')),0,10).".jpg");
	</Action>
	
	<Section>
		Optional

		#load image from the image url saved in variable image_url and save image to specified file
		<Action URLToFile>
			URL {$image_url}
			FileName img/{$image_name}
		</Action>

	        # add img to HTML
       	 <Action Print>
			FileName ebay_images.html
			Text <img src="{$path}{$image_name}" alt="{$category_name} - {$product_name}" \
				title="{$category_name} - {$product_name}" width="60" />
	        </Action>
	</Section>

	#this pattern should match expiration time
	<Pattern>
		#defines expression which should match the data
		RegExp <td*><span class="vi-is1-dt"*><span*>{:re(.*?)}<span><span>{$expiration_time:re(.*?)}</span></td>
		Optional
		TagsToStrip span
		Trim
		Compact
	</Pattern>
	
	#this pattern should match bid history
	<Pattern>
		#defines expression which should match the data
		RegExp <span class="vi-is1-s6"*><span><a*><span*>{$bid_history}
		Optional
		Trim
		Compact
	</Pattern>
	
	#this pattern should match current bid
	<Pattern>
		#defines expression which should match the data
		RegExp <span*class="vi-is1-prcp"*>{$current_bid}
		Optional
		Trim
		Compact
	</Pattern>
	
	#print matched data to csv file
	<Action SaveCSV>
		FileName ebay_output.csv
		Separator ;
		Column $product_url, Source URL
		Column $category_url, Category URL
		Column $category_name, Category Name
		Column $expiration_time, Expiration Time
		Column $product_name, Offer Name
		Column $bid_history, Bid History
		Column $current_bid, Current Bid
		Column $image_url, Image URL
		Column $image_name, Image Name
		Column $image_alternative, Image Alternative Text
	</Action>

</Section>

#run section with name "ebay_product"
Main ebay_product