{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:33:29Z","timestamp":1725705209918},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642350627"},{"type":"electronic","value":"9783642350634"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-35063-4_39","type":"book-chapter","created":{"date-parts":[[2012,11,7]],"date-time":"2012-11-07T01:36:15Z","timestamp":1352252175000},"page":"538-551","source":"Crossref","is-referenced-by-count":2,"title":["Topic-Sensitive Hidden-Web Crawling"],"prefix":"10.1007","author":[{"given":"Panagiotis","family":"Liakos","sequence":"first","affiliation":[]},{"given":"Alexandros","family":"Ntoulas","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"39_CR1","unstructured":"The Open Directory Project, http:\/\/www.dmoz.org"},{"key":"39_CR2","unstructured":"Stack Exchange, http:\/\/stackexchange.com\/"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"\u00c1lvarez, M., Raposo, J., Pan, A., Cacheda, F., Bellas, F., Carneiro, V.: Deepbot: a focused crawler for accessing hidden web content. In: Proc. of Int. Workshop on Data Enginering Issues in E-commerce and Services, DEECS 2007, NY, USA (2007)","DOI":"10.1145\/1278380.1278385"},{"key":"39_CR4","unstructured":"Angkawattanawit, N., Rungsawang, A.: Learnable crawling: An efficient approach to topic-specific web resource discovery (2002)"},{"key":"39_CR5","unstructured":"Barbosa, L., Freire, J.: Siphoning hidden-web data through keyword-based interfaces. In: Proceedings of SBBD, Brazil, (2004)"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Barbosa, L., Freire, J.: An adaptive crawler for locating hidden-web entry points. In: Proceedings of the WWW Conference, NY, USA (2007)","DOI":"10.1145\/1242572.1242632"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Baykan, E., Henzinger, M., Marian, L., Weber, I.: Purely url-based topic classification. In: Proceedings of the WWW Conference, Madrid, Spain (2009)","DOI":"10.1145\/1526709.1526880"},{"key":"39_CR8","unstructured":"Bergholz, A., Chidlovskii, B.: Crawling for domain-specific hidden web resources. In: Proceedings of WISE, DC, USA (2003)"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., van den Berg, M., Dom, B.: Focused crawling: a new approach to topic-specific web resource discovery. In: Proceedings of the WWW Conference, NY, USA (1999)","DOI":"10.1016\/S1389-1286(99)00052-3"},{"key":"39_CR10","unstructured":"Diligenti, M., Coetzee, F., Lawrence, S., Giles, C.L., Gori, M.: Focused crawling using context graphs. In: Proceedings of VLDB, CA, USA (2000)"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Ipeirotis, P.G., Gravano, L.: Distributed search over the hidden web: hierarchical database sampling and selection. In: Proceedings of VLDB, Hong Kong (2002)","DOI":"10.1016\/B978-155860869-6\/50042-1"},{"key":"39_CR12","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1145\/376284.375671","volume":"30","author":"P.G. Ipeirotis","year":"2001","unstructured":"Ipeirotis, P.G., Gravano, L., Sahami, M.: Probe, count, and classify: categorizing hidden web databases. SIGMOD Rec.\u00a030, 67\u201378 (2001)","journal-title":"SIGMOD Rec."},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Xiao, J., Yang, J.: A sample-guided approach to incremental structured web database crawling. In: Proceedings of ICIA, Harbin, China (2010)","DOI":"10.1109\/ICINFA.2010.5512131"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Madhavan, J., Ko, D., Kot, L., Ganapathy, V., Rasmussen, A., Halevy, A.: Google\u2019s deep web crawl. In: Proceedings of VLDB, Auckland, New Zealand (2008)","DOI":"10.14778\/1454159.1454163"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Menczer, F., Pant, G., Srinivasan, P.: Topic-driven crawlers: Machine learning issues. ACM TOIT (submitted, 2002)","DOI":"10.1145\/383952.383995"},{"key":"39_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-540-28651-6_72","volume-title":"Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2004","author":"S. Noh","year":"2004","unstructured":"Noh, S., Choi, Y., Seo, H., Choi, K., Jung, G.: An Intelligent Topic-Specific Crawler Using Degree of Relevance. In: Yang, Z.R., Yin, H., Everson, R.M. (eds.) IDEAL 2004. LNCS, vol.\u00a03177, pp. 491\u2013498. Springer, Heidelberg (2004)"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Ntoulas, A., Zerfos, P., Cho, J.: Downloading textual hidden web content through keyword queries. In: Proceedings of JCDL, NY, USA (2005)","DOI":"10.1145\/1065385.1065407"},{"key":"39_CR18","unstructured":"Raghavan, S., Garcia-Molina, H.: Crawling the hidden web. In: Proceedings of VLDB, San Francisco, CA, USA (2001)"},{"key":"39_CR19","first-page":"1754","volume":"18","author":"S. Seshadri","year":"2007","unstructured":"Seshadri, S., Cooper, B.F.: Routing queries through a peer-to-peer infobeacons network using information retrieval techniques. IEEE TPDS\u00a018, 1754\u20131765 (2007)","journal-title":"IEEE TPDS"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, J., Chen, J.: Crawling deep web using a new set covering algorithm. In: Proceedings of the ADMA Conference, Berlin, Heidelberg (2009)","DOI":"10.1007\/978-3-642-03348-3_32"},{"key":"39_CR21","unstructured":"Wu, P., Wen, J.-R., Liu, H., Ma, W.-Y.: Query selection techniques for efficient crawling of structured web sources. In: Proceedings of the ICDE, Washington, DC, USA (2006)"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Wu, W., Yu, C., Doan, A., Meng, W.: An interactive clustering-based approach to integrating source query interfaces on the deep web. In: Proceedings of SIGMOD, NY, USA (2004)","DOI":"10.1145\/1007568.1007582"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Yang, Y., Bansal, N., Dakka, W., Ipeirotis, P., Koudas, N., Papadias, D.: Query by document. In: Proceedings of WSDM, NY, USA (2009)","DOI":"10.1145\/1498759.1498806"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering - WISE 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35063-4_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T16:05:15Z","timestamp":1687795515000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35063-4_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642350627","9783642350634"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35063-4_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}