Google's Deep Web crawl Export

@article{citeulike:4012166, abstract = {The Deep Web, i.e., content hidden behind HTML forms, has long been acknowledged as a significant gap in search engine coverage. Since it represents a large portion of the structured data on the Web, accessing Deep-Web content has been a long-standing challenge for the database community. This paper describes a system for surfacing Deep-Web content, i.e., pre-computing submissions for each HTML form and adding the resulting HTML pages into a search engine index. The results of our surfacing have been incorporated into the Google search engine and today drive more than a thousand queries per second to Deep-Web content.}, author = {Madhavan, Jayant and Ko, David and Kot, Lucja and Ganapathy, Vignesh and Rasmussen, Alex and Halevy, Alon}, citeulike-article-id = {4012166}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1454159.1454163}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1454159.1454163}, doi = {10.1145/1454159.1454163}, journal = {Proc. VLDB Endow.}, keywords = {deep-web, google}, number = {2}, pages = {1241--1252}, posted-at = {2009-04-19 00:30:49}, priority = {2}, publisher = {VLDB Endowment}, title = {Google's Deep Web crawl}, url = {http://dx.doi.org/10.1145/1454159.1454163}, volume = {1}, year = {2008} }

TY - JOUR ID - citeulike:4012166 L3 - citeulike-article-id:4012166 N2 - The Deep Web, i.e., content hidden behind HTML forms, has long been acknowledged as a significant gap in search engine coverage. Since it represents a large portion of the structured data on the Web, accessing Deep-Web content has been a long-standing challenge for the database community. This paper describes a system for surfacing Deep-Web content, i.e., pre-computing submissions for each HTML form and adding the resulting HTML pages into a search engine index. The results of our surfacing have been incorporated into the Google search engine and today drive more than a thousand queries per second to Deep-Web content. IS - 2 JF - Proc. VLDB Endow. EP - 1252 TI - Google's Deep Web crawl PB - VLDB Endowment VL - 1 SP - 1241 KW - deep-web KW - google AU - Madhavan, Jayant AU - Ko, David AU - Kot, Lucja AU - Ganapathy, Vignesh AU - Rasmussen, Alex AU - Halevy, Alon PY - 2008/// UR - http://dx.doi.org/10.1145/1454159.1454163 ER -