@inproceedings{baeza02balancing, author = {Ricardo Baeza-Yates and Carlos Castillo}, title = {Balancing Volume, Quality and Freshness in Web Crawling}, booktitle = {Soft Computing Systems - Design, Management and Applications}, year = {2002}, pages = {565--572}, noeditor = {Ajith Abraham and Javier {Ruiz-del-Solar} and Mario K{\"o}ppen}, chapter = {Web Computing}, noseries = {Frontiers in Artificial Intelligence and Applications Vol. 87}, publisher = {IOS Press Amsterdam}, address = "Santiago, Chile", url = "http://www.dcc.uchile.cl/\%7Eccastill/papers/baeza02balancing.pdf", abstract = {We describe a crawling software designed for high-performance, large-scale information discovery and gathering on the Web. This crawler allows the administrator to seek for a balance between the volume of a Web collection and its freshness; and also provides flexibility for defining a quality metric to prioritize certain pages. } }