{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:29:20Z","timestamp":1725550160548},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642124358"},{"type":"electronic","value":"9783642124365"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-12436-5_18","type":"book-chapter","created":{"date-parts":[[2010,3,12]],"date-time":"2010-03-12T13:24:29Z","timestamp":1268400269000},"page":"242-255","source":"Crossref","is-referenced-by-count":0,"title":["Website-Level Data Extraction"],"prefix":"10.1007","author":[{"given":"Jianqiang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Laender, A., da Silva, A., Ribeiro-Neto, B., Teixeira, J.: A Brief Survey of Web Data Extraction Tools. SIGMOD Record (2002)","DOI":"10.1145\/565117.565137"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Arocena, G.O., Mendelzon, A.O.: WebOQL: Restructuring documents, data-bases, and webs. In: Proc. of ICDE (1998)","DOI":"10.1002\/(SICI)1096-9942(1999)5:3<127::AID-TAPO2>3.0.CO;2-X"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting Structured Data from Web Pages. In: SIGMOD 2003 (2003)","DOI":"10.1145\/872757.872799"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Liu, B., Grossman, R., Zhai, Y.: Mining data records in Web pages. In: Proc. of the ACM SIGKDD (2003)","DOI":"10.1145\/956750.956826"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chang, C., Lui, S.: IEPAD: Information extraction based on pattern discovery. In: Proc. of WWW (2001)","DOI":"10.1145\/371920.372182"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Cohen, W., Hurst, M., Jensen, L.: A flexible learning system for wrapping tables and lists in HTML documents. In: Proc. of WWW (2002)","DOI":"10.1145\/511446.511477"},{"key":"18_CR7","unstructured":"Cai, D., Yu, S., Wen, J.-R., Ma, W.-Y.: VIPS: a vision-based page segmentation algorithm. Microsoft Technical Report (MSR-TR-2003-79) (2003)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Hammer, J., Mchvoh, J., Garcia-Molina, H.: Semistructured data: The TSIMMIS experience. In: Proc. of the First East-European Symposium on Advances in Databases and Information Systems (1997)","DOI":"10.14236\/ewic\/ADBIS1997.22"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Davulcu, H., Vadrevu, S., Nagarajan, S., Gelgi, F.: METEOR: metadata and instance extraction from object referral lists on the web. In: Proc. of WWW (2005)","DOI":"10.1145\/1062745.1062928"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Zhu, H., Raghavan, S., Vaithyanathan, S.: Alexander L\u00f6ser: Navigating the intranet with high precision. In: Proc. WWW (2007)","DOI":"10.1145\/1242572.1242639"},{"key":"18_CR11","unstructured":"Kao, H.-Y., Lin, S.-H.: Mining web informative structures and content based on entropy analysis. IEEE Trans. on Knowledge and Data Engineering (2004)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Zhu, J., Nie, Z., Wen, J.-R., Zhang, B., Ma, W.-Y.: Simultaneous record detection and attribute labeling in web data extraction. In: Proc. of KDD (2006)","DOI":"10.1145\/1150402.1150457"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Park, J., Barbosa, D.: Adaptive record extraction from web pages. In: Proc. WWW (2007)","DOI":"10.1145\/1242572.1242838"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Tajima, K., Mizuuchi, Y., Kitagawa, M., Tanaka, K.: Cut as a querying unit for WWW, Netnews, and E-mail. In: Proc. of ACM Hypertext (1998)","DOI":"10.1145\/276627.276653"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Kevin, S., McCurley, A.T.: Mining and Knowledge Discovery from the Web. In: ISPAN (2004)","DOI":"10.1109\/ISPAN.2004.1300449"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Kushmerick, N.: Wrapper induction: efficiency and expressiveness. In: AI (2000)","DOI":"10.1016\/S0004-3702(99)00100-9"},{"key":"18_CR17","unstructured":"Muslea, I., Minton, S., Knoblock, C.: Hierarchical wrapper induction for semi-structured information sources Autonomous Agents and Multi-Agent Sys. (2001)"},{"key":"18_CR18","volume-title":"Modern Information Retrieval","author":"R. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. Addison-Wesley, Reading (1999)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Wong, T.-L., Lam, W.: Adapting Web information extraction knowledge via mining site-invariant and site-dependent features. ACM Trans. Internet Techn. (2007)","DOI":"10.1145\/1189740.1189746"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: Towards Automatic Data Extraction from Large Web Sites. In: Proc. VLDB (2001)","DOI":"10.1145\/564691.564778"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Li, W.S., Ayan, N.F., Takano, H., Shimamura, H.: Constructing multi-granular and topic-focused web site maps. In: Proc. of WWW (2001)","DOI":"10.1145\/371920.372086"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Li, W., Candan, V.K.Q., Agrawal, D.: Retrieving and Organizing Web Pages by Information Unit. In: Proc. of WWW (2001)","DOI":"10.1145\/371920.372057"},{"key":"18_CR23","unstructured":"Nie, Z., Ma, Y.J., Ma, W.-Y.: Web Object Retrieval. In: Proc. of WWW (2001)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Zhai, Y.H., Liu, B.: Structured data extraction from the Web based on partial tree alignment. IEEE Trans. on Knowledge and Data Engineering (2006)","DOI":"10.1145\/1060745.1060761"}],"container-title":["Lecture Notes in Business Information Processing","Web Information Systems and Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-12436-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T23:44:55Z","timestamp":1685490295000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-12436-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642124358","9783642124365"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-12436-5_18","relation":{},"ISSN":["1865-1348","1865-1356"],"issn-type":[{"type":"print","value":"1865-1348"},{"type":"electronic","value":"1865-1356"}],"subject":[],"published":{"date-parts":[[2010]]}}}