eBay Inc.
Content extraction system

Abstract:

A system includes a content extraction engine comprising at least one processor and configured to receive a content page including first product data for a target product, remove noise content from the content page, thereby generating a remainder content page, compare the remainder content page to a first synonym list to identify the first product data, the first synonym list including a first data field name, and provide the first product data as associated with the first data field name.