{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T18:24:52Z","timestamp":1760984692986,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":4,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,11,2]],"date-time":"2012-11-02T00:00:00Z","timestamp":1351814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,11,2]]},"DOI":"10.1145\/2389936.2389949","type":"proceedings-article","created":{"date-parts":[[2012,11,7]],"date-time":"2012-11-07T16:42:56Z","timestamp":1352306576000},"page":"57-64","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Web crawler middleware for search engine digital libraries"],"prefix":"10.1145","author":[{"given":"Jian","family":"Wu","sequence":"first","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pradeep","family":"Teregowda","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Madian","family":"Khabsa","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Carman","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Douglas","family":"Jordan","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"San Pedro Wandelmer","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prasenjit","family":"Mitra","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. Lee","family":"Giles","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,11,2]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Apress","author":"Holovaty A.","year":"2007","unstructured":"A. Holovaty and J. Kaplan-Moss . The Definitive Guide to Django: Web Development Done Right (Pro) . Apress , Berkely, CA, USA , 2007 . A. Holovaty and J. Kaplan-Moss. The Definitive Guide to Django: Web Development Done Right (Pro). Apress, Berkely, CA, USA, 2007."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 4th International Web Archiving Workshop (IWAW'04)","author":"Mohr G.","year":"2004","unstructured":"G. Mohr , M. Kimpton , M. Stack , and I. Ranitovic . Introduction to Heritrix, an archival quality web crawler . In Proceedings of the 4th International Web Archiving Workshop (IWAW'04) , Sept. 2004 . G. Mohr, M. Kimpton, M. Stack, and I. Ranitovic. Introduction to Heritrix, an archival quality web crawler. In Proceedings of the 4th International Web Archiving Workshop (IWAW'04), Sept. 2004."},{"key":"e_1_3_2_1_3_1","first-page":"14","volume-title":"Proceedings of the 2010 USENIX conference on Web application development, WebApps'10","author":"Teregowda P. B.","year":"2010","unstructured":"P. B. Teregowda , I. G. Council l, R. J. P. Fern\u00e1ndez , M. Khabsa , S. Zheng , and C. L. Giles . Seersuite: developing a scalable and reliable application framework for building digital libraries by crawling the web . In Proceedings of the 2010 USENIX conference on Web application development, WebApps'10 , pages 14 -- 14 , Berkeley, CA, USA , 2010 . USENIX Association. P. B. Teregowda, I. G. Councill, R. J. P. Fern\u00e1ndez, M. Khabsa, S. Zheng, and C. L. Giles. Seersuite: developing a scalable and reliable application framework for building digital libraries by crawling the web. In Proceedings of the 2010 USENIX conference on Web application development, WebApps'10, pages 14--14, Berkeley, CA, USA, 2010. USENIX Association."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2380718.2380762"}],"event":{"name":"CIKM'12: 21st ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Maui Hawaii USA","acronym":"CIKM'12"},"container-title":["Proceedings of the twelfth international workshop on Web information and data management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2389936.2389949","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2389936.2389949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T09:21:11Z","timestamp":1750238471000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2389936.2389949"}},"subtitle":["a case study for citeseerX"],"short-title":[],"issued":{"date-parts":[[2012,11,2]]},"references-count":4,"alternative-id":["10.1145\/2389936.2389949","10.1145\/2389936"],"URL":"https:\/\/doi.org\/10.1145\/2389936.2389949","relation":{},"subject":[],"published":{"date-parts":[[2012,11,2]]},"assertion":[{"value":"2012-11-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}