{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T18:40:13Z","timestamp":1739299213245,"version":"3.37.0"},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642033476"},{"type":"electronic","value":"9783642033483"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-03348-3_32","type":"book-chapter","created":{"date-parts":[[2009,8,8]],"date-time":"2009-08-08T05:01:20Z","timestamp":1249707680000},"page":"326-337","source":"Crossref","is-referenced-by-count":15,"title":["Crawling Deep Web Using a New Set Covering Algorithm"],"prefix":"10.1007","author":[{"given":"Yan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jessica","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Bergman, M.K.: The deepweb: Surfacing hidden value. The Journal of Electronic Publishing\u00a07(1) (2001)","DOI":"10.3998\/3336451.0007.104"},{"key":"32_CR2","unstructured":"Barbosa, L., Freire, J.: Siphoning hidden-web data through keyword-based interfaces. In: Proc. of SBBD (2004)"},{"issue":"10","key":"32_CR3","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1109\/TKDE.2006.152","volume":"18","author":"C.H. Chang","year":"2006","unstructured":"Chang, C.H., Kayed, M., Girgis, M.R., Shaalan, K.F.: A survey of web information extraction systems. IEEE Transactions on Knowledge and Data Engineering\u00a018(10), 1411\u20131428 (2006)","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"32_CR4","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-540-45275-1_35","volume-title":"Advanced Conceptual Modeling Techniques","author":"S.W. Liddle","year":"2003","unstructured":"Liddle, S.W., Embley, D.W., Scott, D.T., Yau, S.H.: Extracting data behind web forms. In: Oliv\u00e9, \u00c0., Yoshikawa, M., Yu, E.S.K. (eds.) ER 2003, vol.\u00a02784, pp. 402\u2013413. Springer, Heidelberg (2003)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Ntoulas, A., Zerfos, P., Cho, J.: Downloading textual hidden web content through keyword queries. In: Proc. of the Joint Conference on Digital Libraries (JCDL), pp. 100\u2013109 (2005)","DOI":"10.1145\/1065385.1065407"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Wu, P., Wen, J.R., Liu, H., Ma, W.Y.: Query selection techniques for efficient crawling of structured web sources. In: Proc. of ICDE, pp. 47\u201356 (2006)","DOI":"10.1109\/ICDE.2006.124"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Lu, J., Wang, Y., Iiang, J., Chen, J., Liu, J.: An approach to deep web crawling by sampling. In: Proc. of Web Intelligence, pp. 718\u2013724 (2008)","DOI":"10.1109\/WIIAT.2008.392"},{"key":"32_CR8","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1023\/A:1019225027893","volume":"98","author":"A. Caprara","year":"2004","unstructured":"Caprara, A., Toth, P., Fishetti, M.: Algorithms for the set covering problem. Annals of Operations Research\u00a098, 353\u2013371 (2004)","journal-title":"Annals of Operations Research"},{"key":"32_CR9","unstructured":"Hatcher, E., Gospodnetic, O.: Lucene in Action. Manning Publications (2004)"},{"issue":"4","key":"32_CR10","first-page":"33","volume":"23","author":"C.A. Knoblock","year":"2000","unstructured":"Knoblock, C.A., Lerman, K., Minton, S., Muslea, I.: Accurately and reliably extracting data from the web: a machine learning approach. IEEE Data Engineering Bulletin\u00a023(4), 33\u201341 (2000)","journal-title":"IEEE Data Engineering Bulletin"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Nelson, M.L., Smith, J.A., Campo, I.G.D.: Efficient, automatic web resource harvesting. In: Proc. of RECOMB, pp. 43\u201350 (2006)","DOI":"10.1145\/1183550.1183560"},{"issue":"2","key":"32_CR12","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1016\/j.datak.2007.10.002","volume":"64","author":"M. Alvarez","year":"2008","unstructured":"Alvarez, M., Pan, A., Raposo, J., Bellas, F., Cacheda, F.: Extracting lists of data records from semi-structured web pages. Data Knowl. Eng.\u00a064(2), 491\u2013509 (2008)","journal-title":"Data Knowl. Eng."},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Ipeirotis, P.G., Jain, P., Gravano, L.: Towards a query optimizer for text-centric tasks. ACM Transactions on Database Systems\u00a032 (2007)","DOI":"10.1145\/1292609.1292611"},{"issue":"1","key":"32_CR14","first-page":"1","volume":"25","author":"L. Gravano","year":"2002","unstructured":"Gravano, L., Ipeirotis, P.G., Sahami, M.: Query- vs. crawling-based classification of searchable web databases. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering\u00a025(1), 1\u20138 (2002)","journal-title":"Bulletin of the IEEE Computer Society Technical Committee on Data Engineering"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Caverlee, J., Liu, L., Buttler, D.: Probe, cluster, and discover: focused extraction of qa-pagelets from the deep web. In: Proc. of the 28th international conference on Very Large Data Bases, pp. 103\u2013114 (2004)","DOI":"10.1109\/ICDE.2004.1319988"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Ibrahim, A., Fahmi, S.A., Hashmi, S.I., Choi, H.: Addressing effective hidden web search using iterative deepening search and graph theory. In: Proc. of IEEE 8th International Conference on Computer and Information Technology Workshops, pp. 145\u2013149 (2008)","DOI":"10.1109\/CIT.2008.Workshops.81"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Callan, J., Connell, M.: Query-based sampling of text databases. ACM Transactions on Information Systems, 97\u2013130 (2001)","DOI":"10.1145\/382979.383040"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-03348-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T18:03:46Z","timestamp":1739297026000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-03348-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642033476","9783642033483"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-03348-3_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}