{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:41:54Z","timestamp":1783615314360,"version":"3.55.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,9,7]],"date-time":"2012-09-07T00:00:00Z","timestamp":1346976000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2013,2]]},"DOI":"10.1007\/s10844-012-0221-8","type":"journal-article","created":{"date-parts":[[2012,9,6]],"date-time":"2012-09-06T10:24:59Z","timestamp":1346927099000},"page":"159-184","source":"Crossref","is-referenced-by-count":23,"title":["E-FFC: an enhanced form-focused crawler for domain-specific deep web databases"],"prefix":"10.1007","volume":"40","author":[{"given":"Yanni","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jintao","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2012,9,7]]},"reference":[{"key":"221_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., AL-Garawi, F., Yu, P.S. (2001). Intelligent crawling on the world wide web with arbitrary predicates. In Proc. of the 10th international conference on world wide web (WWW\u201901) (pp.\u00a096\u2013105).","DOI":"10.1145\/371920.371955"},{"key":"221_CR2","doi-asserted-by":"crossref","unstructured":"Akilandeswari, J., & Gopalan, N.P. (2008). An architectural framework of a crawler for locating deep web repositories using learning multi-agent systems. In the Proc. of the third international conference on internet and web applications and services (ICIW\u201908) (pp.\u00a0558\u2013562).","DOI":"10.1109\/ICIW.2008.94"},{"key":"221_CR3","unstructured":"Barbosa, L., & Freire, J. (2005). Searching for hidden-web databases. In Proc. of WebDB (pp.\u00a01\u20136)."},{"key":"221_CR4","doi-asserted-by":"crossref","unstructured":"Barbosa, L., & Freire, J. (2007). An adaptive crawler for locating hidden-web entry points. In Proc. of WWW 2007 (WWW\u201907) (pp.\u00a0441\u2013450). ACM.","DOI":"10.1145\/1242572.1242632"},{"key":"221_CR5","doi-asserted-by":"crossref","unstructured":"Barbosa, L., Freire, J., Silva, A. (2007). Organizing hidden-web databases by clustering visible web documents. In Proc. of IEEE the 23rd international of conference on data engineering (ICDE\u20192007) (pp.\u00a0326\u2013335).","DOI":"10.1109\/ICDE.2007.367878"},{"key":"221_CR6","first-page":"1","volume":"1","author":"M Bazarganigilani","year":"2011","unstructured":"Bazarganigilani, M., Syed, A., & Burki, S. (2011). Focused web crawling using decay content and genetic programming. International Journal of Data Mining & Knowledge Management Process (IJDKP), 1, 1\u201311.","journal-title":"International Journal of Data Mining & Knowledge Management Process (IJDKP)"},{"key":"221_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3998\/3336451.0007.104","volume":"7","author":"MK Bergman","year":"2001","unstructured":"Bergman, M.K. (2001). The deep web: surfacing hidden value, Journal of Electronic Publishing, 7, 1\u201317.","journal-title":"Journal of Electronic Publishing"},{"key":"221_CR8","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/S0169-7552(98)80047-0","volume":"30","author":"K Bharat","year":"1998","unstructured":"Bharat, K., Broder, A., Henzinger, M., Kumar, P., Venkatasubramanian, S. (1998). The connectivity server: fast access to linkage information on the web. Computer Networks and ISDN Systems, 30, 469\u2013477.","journal-title":"Computer Networks and ISDN Systems"},{"key":"221_CR9","unstructured":"BrightPlanet.com (2001). The deep web: Surfacing hidden value, Accessible at http:\/\/brightplanet.com . Accessed 1 March 2012"},{"key":"221_CR10","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1145\/1067268.1067287","volume":"39","author":"C Castillo","year":"2005","unstructured":"Castillo, C. (2005). Effective web crawling. ACM SIGIR Forum, 39, 55\u201356.","journal-title":"ACM SIGIR Forum"},{"key":"221_CR11","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1145\/1031570.1031584","volume":"33","author":"KC-C Chang","year":"2004","unstructured":"Chang, K.C.-C., He, B., Li, C., et al. (2004). Structured databases on the web: observations and implications. ACM SIGMOD Record, 33, 61\u201370.","journal-title":"ACM SIGMOD Record"},{"key":"221_CR12","unstructured":"Chang, K.C.-C., He, B., Zhang, Z. (2005). Toward large-scale integration: building a metaQuerier over databases on the web. In Proc. of CIDR (CIDR\u201905) (pp.\u00a044\u201355)."},{"key":"221_CR13","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1016\/S1389-1286(99)00052-3","volume":"31","author":"S Chakrabarti","year":"1999","unstructured":"Chakrabarti, S., van den Berg, M., Dom, B. (1999). Focused crawling: a new approach to topic-specific web resource discovery. Computer Networks, 31, 1623\u20131640.","journal-title":"Computer Networks"},{"key":"221_CR14","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., Punera, K., Subramanyam, M. (2002). Accelerated focused crawling through online relevance feedback. In Proc. of the 9th international conference on world wide web (WWW\u201902) (pp.\u00a0148\u2013159).","DOI":"10.1145\/511446.511466"},{"key":"221_CR15","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.dss.2007.06.002","volume":"44","author":"M Chau","year":"2008","unstructured":"Chau, M., & Chen, H. (2008). A machine learning approach to web page filtering using content and structure analysis. Decision Support Systems, 44, 482\u2013494.","journal-title":"Decision Support Systems"},{"key":"221_CR16","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/S0169-7552(98)00108-1","volume":"30","author":"J Cho","year":"1998","unstructured":"Cho, J., Garcia, M.H., Page, L. (1998). Efficient crawling through URL ordering. Computer Networks and ISDN Systems, 30, 161\u2013172.","journal-title":"Computer Networks and ISDN Systems"},{"key":"221_CR17","unstructured":"Cope, J., Craswell, N., Hawking, D. (2003). Automated discovery of search interfaces on the web. In Proc. of ADC (ADC\u201903) (pp.\u00a0181\u2013189)."},{"key":"221_CR18","unstructured":"Dehua, D. (2010). Deep web services crawler. Master Thesis."},{"key":"221_CR19","unstructured":"Diligenti, M., Coetzee, F., Lawrence, S., Giles, C.L., Gori, M. (2000). Focused crawling using context graphs. In Proc. of VLDB(VLDB\u20192000) (pp.\u00a0527\u2013534)."},{"key":"221_CR20","doi-asserted-by":"crossref","unstructured":"Ester, M., Kriegel, H.P., Schubert, M. (2004). Accurate and efficient crawling for relevant websites. In Proc. of the 13th international conference on very large data bases (VLDB\u2019 04) (Vol.\u00a030, pp.\u00a0396\u2013407).","DOI":"10.1016\/B978-012088469-8.50037-1"},{"key":"221_CR21","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/MC.2004.1260731","volume":"73","author":"TM Ghanem","year":"2004","unstructured":"Ghanem, T.M., & Aref, W.G. (2004). Databases deepen the web. IEEE Computer, 73, 116\u2013117.","journal-title":"IEEE Computer"},{"key":"221_CR45","doi-asserted-by":"crossref","unstructured":"He, B., & Chang, K.C.-C. (2003). Statistical schema matching across web query interfaces. In Proc. of the ACM SIGMOD conference (SIGMOD\u201803) (pp. 217\u2013228).","DOI":"10.1145\/872757.872784"},{"key":"221_CR22","unstructured":"He, B., Li, C., Killian, D., Patel, M., Tseng, Y., Chang, K.C.-C. (2006). A structure-driven yield-aware web form crawler: building a database of online databases. UIUC Technical Report: UIUCDCS-R-2006-2752, UIUC-ENG-2006-1792 (pp.\u00a01\u201312)."},{"key":"221_CR23","first-page":"95","volume":"50","author":"B He","year":"2007","unstructured":"He, B., Patel, M., Zhang, Z., Chang, K.C.-C. (2007). Accessing the deep web: a survey. Communications of the ACM, 50, 95\u2013101.","journal-title":"Communications of the ACM"},{"key":"221_CR24","doi-asserted-by":"crossref","unstructured":"He, B., Tao, T., Chang, K.C.-C. (2004). Organizing structured web sources by query schemas: A clustering approach. In Proc. of the thirteenth ACM international conference on information and knowledge management (CIKM\u201904) (pp.\u00a03\u20137).","DOI":"10.1145\/1031171.1031178"},{"key":"221_CR25","doi-asserted-by":"crossref","unstructured":"He, B., Tao, T., Chang, K.C.-C. (2004). Clustering structured web sources: A schema-based, model-differentiation approach. In Proc. of the 9th International Conference on Extending Database Technology (EDBT\u201904) (pp.\u00a0536\u2013546).","DOI":"10.1007\/978-3-540-30192-9_53"},{"key":"221_CR26","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1007\/978-3-642-01344-7_17","volume":"18","author":"T Hornung","year":"2009","unstructured":"Hornung, T., Simon, K., Lausen, G. (2009). Mashups over the deep web. Lecture Notes in Business Information Processing, 18, 228\u2013241.","journal-title":"Lecture Notes in Business Information Processing"},{"key":"221_CR27","doi-asserted-by":"crossref","unstructured":"Jamali, M., Sayyadi, H., Hariri, B.B., Abolhassani, H. (2006). A method for focused crawling using combination of link structure and content similarity. In Proc. of ACM international conference on web intelligence (WI\u201906) (pp.\u00a0753\u2013756).","DOI":"10.1109\/WI.2006.19"},{"key":"221_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Nie, T., Shen, D., Yu, G. (2010). Domain-oriented deep web data sources discovery and identification. In Proc. of the 12th international asia-pacific web conference (pp.\u00a0464\u2013467).","DOI":"10.1109\/APWeb.2010.54"},{"key":"221_CR29","doi-asserted-by":"crossref","unstructured":"Madhavan, J., Ko, D., Kot, L. (2008). Google\u2019s deep-web crawl, In Proc. of the VLDB Endowment (Vol. 1, pp.\u00a01241\u20131251).","DOI":"10.14778\/1454159.1454163"},{"key":"221_CR30","unstructured":"Madhavan, J., Afanasiev, L., Antova, L., Halevy, A. (2009). Harnessing the deep web: present and future. CIDR Perspective available at http:\/\/arxiv.org\/abs\/0909.1785 ."},{"key":"221_CR31","unstructured":"Novak, B. (2004). A survey of focused web crawling algorithms. In Proc. of SIKDD (SIKDD\u201904) (Vol.\u00a05558, pp.\u00a055\u201358)."},{"key":"221_CR32","unstructured":"Peng, Q, Meng, W., He, H., Yu, C.T. (2004). WISE-cluster: clustering e-commerce search engines automatically. In Proc. of the 6th ACM international workshop on web information and data management (VIDM\u201904) (pp.\u00a0104\u2013111)."},{"key":"221_CR33","unstructured":"Raghavan, S., & Garacia-Molina, H. (2001). Crawling the hidden web. In Proc. of VLDB (VLDB\u201901) (pp.\u00a0129\u2013138)."},{"key":"221_CR34","unstructured":"Rennie, J., & McCallum, A.K. (1999). Using reinforcement learning to spider the web efficiently. In Proc. of ICML(ICML\u20191999) (pp.\u00a0335\u2013343)."},{"key":"221_CR35","unstructured":"Rocco, D., Liu, L., Critchlow, T. (2004). Focused crawling of the deep web using service class descriptions. In Proc. of the international conference on service oriented computing (ICSOC\u201904) (pp.\u00a015\u201318)."},{"key":"221_CR36","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1126\/science.280.5360.98","volume":"280","author":"L Steve","year":"1998","unstructured":"Steve, L., & Giles, C.L. (1998). Searching the world wide web. Science, 280, 98\u2013100.","journal-title":"Science"},{"key":"221_CR37","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1038\/21987","volume":"400","author":"L Steve","year":"1999","unstructured":"Steve, L., & Giles C.L. (1999). Accessibility of information on the web. Nature, 400, 107\u2013109.","journal-title":"Nature"},{"key":"221_CR38","unstructured":"The UIUC Web (2003). Integration Repository. available at http:\/\/metaquerier.cs.uiuc.edu\/repository . Accessed 1 March 2012."},{"key":"221_CR39","doi-asserted-by":"crossref","unstructured":"Wang, C., Guan, Z.Y., Chen, C., Bu, J.J., Wang, J.F., Lin, H.Z. (2009). On-line topical importance estimation: An effective focused crawling algorithm combining link and content analysis (Vol. 10, pp.\u00a01114\u20131124). Zhejiang Univ Sci A.","DOI":"10.1631\/jzus.A0820481"},{"key":"221_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, J., Chen, J. (2009). Crawling deep web using a new set covering algorithm. In Proc. of ADMA(ADMA\u20192009) (pp.\u00a0326\u2013337).","DOI":"10.1007\/978-3-642-03348-3_32"},{"key":"221_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zuo, W., Peng, T., He, F. (2008). Domain-specific deep web sources discovery. In Proc. of the international conference on natural computation (ICNC\u201908) (pp.\u00a0202\u2013206).","DOI":"10.1109\/ICNC.2008.350"},{"key":"221_CR42","doi-asserted-by":"crossref","unstructured":"Wu, W., Yu, C.T., Doan, A., Meng, W. (2004). An interactive clustering-based approach to integrating source query interfaces on the deep web. In Proc. of the 23th ACM international conference on management of data (SIGMOD\u20192004) (pp.\u00a095\u2013106).","DOI":"10.1145\/1007568.1007582"},{"key":"221_CR43","first-page":"263","volume":"6","author":"D Yadav","year":"2009","unstructured":"Yadav, D., Sharma, A.K., Gupta, J.P. (2009). Topic web crawling using weighted anchor text and web page change detection techniques, WSEAS. Transactions on Information Science and Applications, 6, 263\u2013275.","journal-title":"Transactions on Information Science and Applications"},{"key":"221_CR44","unstructured":"Zhang, Z., He, B., Chang, K.C.-C. (2005). Light-weight domain-based form assistant: querying web databases on the fly. In Proc. of VLDB conference (VLDB\u201905) (pp.\u00a097\u2013108)."}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-012-0221-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10844-012-0221-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-012-0221-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,25]],"date-time":"2023-06-25T15:59:10Z","timestamp":1687708750000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10844-012-0221-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,9,7]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,2]]}},"alternative-id":["221"],"URL":"https:\/\/doi.org\/10.1007\/s10844-012-0221-8","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,9,7]]}}}