@inproceedings{4fbacd49e8f74cfeb7fb6825ab33db43,
title = "RecipeCrawler: Collecting recipe data from WWW incrementally",
abstract = "WWW has posed itself as the largest data repository ever available in the history of humankind. Utilizing the Internet as a data source seems to be natural and many efforts have been made. In this paper we focus on establishing a robust system to collect structured recipe data from the Web incrementally, which, as we believe, is a critical step towards practical, continuous, reliable web data extraction systems and therefore utilizing WWW as data sources for various database applications. The reasons for advocating such an incremental approach are two-fold: (1) it is impractical to crawl all the recipe pages from relevant web sites as the Web is highly dynamic; (2) it is almost impossible to induce a general wrapper for future extraction from the initial batch of recipe web pages. In this paper, we describe such a system called RecipeCrawler which targets at incrementally collecting recipe data from WWW. General issues in establishing an incremental data extraction system are considered and techniques are applied to recipe data collection from the Web. Our RecipeCrawler is actually used as the backend of a fully-fledged multimedia recipe database system being developed jointly by City University of Hong Kong and Renmin University of China.",
author = "Yu Li and Xiaofeng Meng and Liping Wang and Qing Li",
year = "2006",
month = jan,
day = "1",
language = "English",
isbn = "3540352252",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer-Verlag",
pages = "263--274",
booktitle = "Advances in Web-Age Information Management - 7th International Conference, WAIM 2006, Proceedings",
note = "7th International Conference on Advances in Web-Age Information Management, WAIM 2006 ; Conference date: 17-06-2006 Through 19-06-2006",
}