Provided are a system and method for performing deduplication of web content. In one example, the method includes converting search results of a first website into a first fuzzy index and converting search results of a second website into a second fuzzy index, determining a search result of the first website corresponds to a same item as a search result of the second website based on a comparison of the first fuzzy index and the second fuzzy index, and displaying a comparison of web content associated with the item from the first search result and web content associated with item from the second search result. The deduplication of content according to various embodiments may be performed on the fly without storing web content in a centralized database.