{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:55:38Z","timestamp":1774936538616,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2013,8,14]],"date-time":"2013-08-14T00:00:00Z","timestamp":1376438400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1007\/s11280-013-0248-y","type":"journal-article","created":{"date-parts":[[2013,8,13]],"date-time":"2013-08-13T09:16:48Z","timestamp":1376385408000},"page":"1109-1139","source":"Crossref","is-referenced-by-count":13,"title":["Information extraction for deep web using repetitive subject pattern"],"prefix":"10.1007","volume":"17","author":[{"given":"Wachirawut","family":"Thamviset","sequence":"first","affiliation":[]},{"given":"Sartra","family":"Wongthanavasu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,8,14]]},"reference":[{"key":"248_CR1","doi-asserted-by":"crossref","unstructured":"Adelberg, B.: NoDoSE - A tool for Semi-Automatically Extracting Structured and Semistructured Data from Text Documents. Proceedings of the 1998 ACM SIGMOD in-ternational conference on Management of data. pp. 283\u2013294 ACM, New York, NY, USA (1998). doi: 10.1145\/276304.276330","DOI":"10.1145\/276304.276330"},{"issue":"2","key":"248_CR2","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/j.datak.2007.10.002","volume":"64","author":"M \u00c1lvarez","year":"2008","unstructured":"\u00c1lvarez, M., Pan, A., Raposo, J., Bellas, F., Cacheda, F.: Extracting lists of data records from semi-structured web pages. Data Knowl. Eng 64(2), 491\u2013509 (2008). doi: 10.1016\/ j.datak.2007.10.002","journal-title":"Data Knowl. Eng"},{"key":"248_CR3","doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from Web pages. Proceedings of the 2003 ACM SIGMOD international conference on Management of data. pp. 337\u2013348 ACM, New York, NY, USA (2003). doi: 10.1145\/872757.872799","DOI":"10.1145\/872757.872799"},{"key":"248_CR4","doi-asserted-by":"crossref","unstructured":"Arocena, G.O., Mendelzon, A.O.: WebOQL: Restructuring Documents, Databases, and Webs. Proceedings of the Fourteenth International Conference on Data Engineering. pp. 24\u201333 I.E. Computer Society, Washington, DC, USA (1998)","DOI":"10.1109\/ICDE.1998.655754"},{"key":"248_CR5","doi-asserted-by":"crossref","unstructured":"Cai, D., Yu, S., Wen, J.-R., Ma, W.-Y.: Extracting content structure for web pages based on visual representation. APWeb. 406\u2013417 (2003)","DOI":"10.1007\/3-540-36901-5_42"},{"issue":"10","key":"248_CR6","doi-asserted-by":"crossref","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 Trans Knowl Data Eng 18(10), 1411\u20131428 (2006). doi: 10.1109\/TKDE.2006.152","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"6","key":"248_CR7","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/MIS.2004.71","volume":"19","author":"C-H Chang","year":"2004","unstructured":"Chang, C.-H., Kuo, S.-C.: OLERA: semisupervised Web-data extraction with visual support. IEEE Intell Syst 19(6), 56\u201364 (2004). doi: 10.1109\/MIS.2004.71","journal-title":"IEEE Intell Syst"},{"key":"248_CR8","doi-asserted-by":"crossref","unstructured":"Chang, C.-H., Lui, S.-C.: IEPAD: information extraction based on pattern discovery. Proceedings of the 10th international conference on World Wide Web. pp. 681\u2013688 ACM, New York, USA (2001). doi: 10.1145\/371920.372182","DOI":"10.1145\/371920.372182"},{"key":"248_CR9","doi-asserted-by":"crossref","unstructured":"Ciravegna, F., Dingli, A., Wilks, Y., Petrelli, D.: Adaptive information extraction for document annotation in amilcare. Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval. pp. 451\u2013451 ACM, New York, NY, USA (2002). doi: 10.1145\/564376.564492","DOI":"10.1145\/564376.564492"},{"key":"248_CR10","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: RoadRunner: Towards Automatic Data Extraction from Large Web Sites. Proceedings of the 27th International Conference on Very Large Data Bases. pp. 109\u2013118 Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2001)","DOI":"10.1145\/564691.564778"},{"issue":"5","key":"248_CR11","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1145\/1230819.1241670","volume":"50","author":"B He","year":"2007","unstructured":"He, B., Patel, M., Zhang, Z., Chang, K.C.-C.: Accessing the deep web. Commun of the ACM. 50(5), 94\u2013101 (2007). doi: 10.1145\/1230819.1241670","journal-title":"Commun of the ACM."},{"key":"248_CR12","doi-asserted-by":"crossref","unstructured":"Hengru, Z., Chun, C.: Web Information Extraction Technology Research Based on Ajax. Proceedings of the 2011 International Conference on Business Computing and Global Informatization. pp. 208\u2013211 I.E. Computer Society, Washington, DC, USA (2011). doi: 10.1109\/BCGIn.2011.60","DOI":"10.1109\/BCGIn.2011.60"},{"key":"248_CR13","doi-asserted-by":"crossref","unstructured":"Hogue, A., Karger, D.: Thresher: automating the unwrapping of semantic content from the World Wide Web. Proceedings of the 14th international conference on World Wide Web. pp. 86\u201395 ACM, New York, NY, USA (2005). doi: 10.1145\/1060745.1060762","DOI":"10.1145\/1060745.1060762"},{"issue":"6","key":"248_CR14","doi-asserted-by":"crossref","first-page":"854","DOI":"10.1109\/TSMCC.2010.2089678","volume":"41","author":"JL Hong","year":"2011","unstructured":"Hong, J.L.: Data extraction for deep Web using WordNet. IEEE Trans Syst Man, Cybern, Part C: Appl Rev 41(6), 854\u2013868 (2011). doi: 10.1109\/TSMCC.2010.2089678","journal-title":"IEEE Trans Syst Man, Cybern, Part C: Appl Rev"},{"issue":"2","key":"248_CR15","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.datak.2009.10.002","volume":"69","author":"JL Hong","year":"2010","unstructured":"Hong, J.L., Siew, E.-G., Egerton, S.: Information extraction for search engines using fast heuristic techniques. Data Knowl. Eng 69(2), 169\u2013196 (2010). doi: 10.1016\/j.datak.2009.10.002","journal-title":"Data Knowl. Eng"},{"issue":"8","key":"248_CR16","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/S0306-4379(98)00027-1","volume":"23","author":"C-N Hsu","year":"1998","unstructured":"Hsu, C.-N., Dung, M.-T.: Generating finite-state transducers for semi-structured data extraction from the Web. Inf Syst. 23(8), 521\u2013538 (1998). doi: 10.1016\/S0306-4379(98)00027-1","journal-title":"Inf Syst."},{"issue":"2","key":"248_CR17","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1109\/TKDE.2009.82","volume":"22","author":"M Kayed","year":"2009","unstructured":"Kayed, M., Chang, C.H.: FiVaTech: page-level Web data extraction from template pages. IEEE Trans Knowl Data Eng 22(2), 249\u2013263 (2009). doi: 10.1109\/TKDE.2009.82","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"248_CR18","doi-asserted-by":"crossref","unstructured":"Liu, B., Grossman, R., Zhai, Y.: Mining data records in Web pages. Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. pp. 601\u2013606 ACM, New York, NY, USA (2003). doi: 10.1145\/956750.956826","DOI":"10.1145\/956750.956826"},{"issue":"3","key":"248_CR19","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TKDE.2009.109","volume":"22","author":"W Liu","year":"2010","unstructured":"Liu, W., Meng, X., Meng, W.: ViDE: a vision-based approach for deep Web data extraction. IEEE IEEE Trans Knowl Data Eng 22(3), 447\u2013460 (2010). doi: 10.1109\/TKDE.2009.109","journal-title":"IEEE IEEE Trans Knowl Data Eng"},{"key":"248_CR20","doi-asserted-by":"crossref","unstructured":"Liu, L., Pu, C., Han, W.: XWRAP: an XML-enabled wrapper construction system for Web information sources. Data Engineering, 2000. Proceedings. 16th International Conference on. pp. 611 \u2013621 (2000). doi: 10.1109\/ICDE.2000.839475","DOI":"10.1109\/ICDE.2000.839475"},{"issue":"5","key":"248_CR21","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/S1389-1286(02)00214-1","volume":"39","author":"J Myllymaki","year":"2002","unstructured":"Myllymaki, J.: Effective Web data extraction with standard XML technologies. Computer Networks. 39(5), 635\u2013644 (2002). doi: 10.1016\/S1389-1286(02)00214-1","journal-title":"Computer Networks."},{"key":"248_CR22","doi-asserted-by":"crossref","unstructured":"Padmadas, V., Gadge, J.: Web data extraction using visual features. Proceedings of the International Conference and Workshop on Emerging Trends in Technology. pp. 218\u2013221 ACM, New York, NY, USA (2010). doi: 10.1145\/1741906.1741954","DOI":"10.1145\/1741906.1741954"},{"issue":"1","key":"248_CR23","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/s13042-011-0037-9","volume":"3","author":"Y Qin","year":"2012","unstructured":"Qin, Y., Zheng, D., Zhao, T.: Research on search results optimization technology with category features integration. Int J Mach Learn Cybern 3(1), 71\u201376 (2012). doi: 10.1007\/s13042-011-0037-9","journal-title":"Int J Mach Learn Cybern"},{"key":"248_CR24","doi-asserted-by":"crossref","unstructured":"Simon, K., Lausen, G.: ViPER: augmenting automatic information extraction with visual perceptions. Proceedings of the 14th ACM international conference on Information and knowledge management. pp. 381\u2013388 ACM, New York, NY, USA (2005). doi:10.1145\/ 1099554.1099672 DOI: 10.1145\/1099554.1099672","DOI":"10.1145\/1099554.1099672"},{"key":"248_CR25","first-page":"631","volume-title":"Web information systems engineering - WISE","author":"HA Sleiman","year":"2012","unstructured":"Sleiman, H.A., Corchuelo, R.: An unsupervised technique to extract information from semi-structured Web pages. In: Wang, X.S., Cruz, I., Delis, A., Huang, G. (eds.) Web information systems engineering - WISE, pp. 631\u2013637. Springer, Berlin (2012)"},{"issue":"0","key":"248_CR26","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.knosys.2012.10.009","volume":"39","author":"HA Sleiman","year":"2013","unstructured":"Sleiman, H.A., Corchuelo, R.: TEX: an efficient and effective unsupervised Web information extracto. Knowl-Based Syst 39(0), 109\u2013123 (2013). doi: 10.1016\/j.knosys.2012.10.009","journal-title":"Knowl-Based Syst"},{"key":"248_CR27","unstructured":"Sleiman, H.A., Corchuelo, R.: A Survey on Region Extractors From Web Documents. IEEE Transactions on Knowledge and Data Engineering. 99, (2012). doi: 10.1109\/TKDE . 2012.135 DOI: 10.1109\/TKDE.2012.135"},{"key":"248_CR28","doi-asserted-by":"crossref","unstructured":"Thamviset, W., Wongthanavasu, S.: Structured web information extraction using repetitive subject pattern. Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2012 9th International Conference on. pp. 1 \u20134 , Thailand (2012). doi: 10.1109\/ECTICon.2012.6254247","DOI":"10.1109\/ECTICon.2012.6254247"},{"issue":"2","key":"248_CR29","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11280-007-0021-1","volume":"10","author":"S Vadrevu","year":"2007","unstructured":"Vadrevu, S., Gelgi, F., Davulcu, H.: Information extraction from Web pages using presentation regularities and domain knowledge. World Wide Web. 10(2), 157\u2013179 (2007). doi: 10.1007\/s11280-007-0021-1","journal-title":"World Wide Web."},{"key":"248_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Lochovsky, F.H.: Data extraction and label assignment for web databases. Proceedings of the 12th international conference on World Wide Web. pp. 187\u2013196 ACM, New York, NY, USA (2003). doi: 10.1145\/775152.775179","DOI":"10.1145\/775152.775179"},{"key":"248_CR31","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, G., Han, Y.: Grubber: Allowing End-Users to Develop XML-Based Wrappers for Web Data Sources. Proceedings of the Joint International Conferences on Advances in Data and Web Management. pp. 647\u2013652 Springer-Verlag, Berlin, Heidelberg (2009). doi: 10.1007\/978-3-642-00672-2_65","DOI":"10.1007\/978-3-642-00672-2_65"},{"issue":"12","key":"248_CR32","doi-asserted-by":"crossref","first-page":"1614","DOI":"10.1109\/TKDE.2006.197","volume":"18","author":"Y Zhai","year":"2006","unstructured":"Zhai, Y., Liu, B.: Structured data extraction from the Web based on partial tree alignment. IEEE Trans Knowledge Data Eng 18(12), 1614\u20131628 (2006). doi: 10.1109\/TKDE.2006.197","journal-title":"IEEE Trans Knowledge Data Eng"},{"key":"248_CR33","doi-asserted-by":"crossref","unstructured":"Zhao, H., Meng, W., Wu, Z., Raghavan, V., Yu, C.: Fully automatic wrapper generation for search engines. Proceedings of the 14th international conference on World Wide Web. pp. 66\u201375 ACM, New York, NY, USA (2005). doi: 10.1145\/1060745.1060760","DOI":"10.1145\/1060745.1060760"},{"key":"248_CR34","doi-asserted-by":"crossref","unstructured":"Zheng, X., Gu, Y., Li, Y.: Data extraction from web pages based on structural-semantic entropy. Proceedings of the 21st international conference companion on World Wide Web. pp. 93\u2013102 ACM, New York, NY, USA (2012). doi: 10.1145\/2187980.2187991","DOI":"10.1145\/2187980.2187991"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-013-0248-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-013-0248-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-013-0248-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T20:55:52Z","timestamp":1688417752000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-013-0248-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,14]]},"references-count":34,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2014,9]]}},"alternative-id":["248"],"URL":"https:\/\/doi.org\/10.1007\/s11280-013-0248-y","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"value":"1386-145X","type":"print"},{"value":"1573-1413","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8,14]]}}}