{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T07:06:08Z","timestamp":1746860768437},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540253617"},{"type":"electronic","value":"9783540319702"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/978-3-540-31970-2_3","type":"book-chapter","created":{"date-parts":[[2010,7,9]],"date-time":"2010-07-09T17:12:58Z","timestamp":1278695578000},"page":"34-53","source":"Crossref","is-referenced-by-count":2,"title":["Wrapper Generation for Automatic Data Extraction from Large Web Sites"],"prefix":"10.1007","author":[{"given":"Nitin","family":"Jindal","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: ROADRUNNER: Towards Automatic Data Extraction Large Web Sites. In: VLDB 2001 (2001)","DOI":"10.1145\/564691.564778"},{"key":"3_CR2","unstructured":"Wang, J., Lochovsky, F.H.: Wrapper Induction based on Nested Pattern Discovery. Technical Report HKUST-CS-27-02, Dept. of Computer Science, Hong Kong U. of Science and Technology (2002)"},{"key":"3_CR3","unstructured":"Document Object Model Level 3 Core Specification. World Wide Web Consortium 2001 (2001)"},{"key":"3_CR4","unstructured":"HTML Tidy, http:\/\/www.w3.org\/People\/Raggett\/tidy\/"},{"key":"3_CR5","unstructured":"HTML 4.01, specifications World Wide Web Consortium (1999), http:\/\/www.w3.org\/TR\/REC-html40\/"},{"key":"3_CR6","unstructured":"XHTML 1.0. The Extensible HyperText Markup Language (2002), http:\/\/www.w3.org\/TR\/xhtml1\/"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Gold, E.M.: Language Identification in the limit. Information and Control\u00a010(5) (1967)","DOI":"10.1016\/S0019-9958(67)91165-5"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Gold, E.M.: Complexity of automaton identification from given data. Information and Control\u00a037(3) (1978)","DOI":"10.1016\/S0019-9958(78)90562-4"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Adelberg, B.: NoDOSE \u2013 a tool for semi-automatically extracting structured and semi-structured data from text documents. In: SIGMOD 1998 (1998)","DOI":"10.1145\/276304.276330"},{"key":"3_CR10","unstructured":"Atzeni, P., Mecca, G., Merialdo, P.: To Weave the Web. In: VLDB 1997 (1997)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Chang, C.H., Lui, S.C.: IEPAD: information extraction based on pattern discovery. In: World Wide Web 2001 (2001)","DOI":"10.1145\/371920.372182"},{"key":"3_CR12","unstructured":"Kushmerick, N., Weld, D., Doorenbos, R.: Wrapper induction for information extraction. Artificial Intelligence, 729\u2013735 (1997)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Muslea, S.M., Knoblock, C.: A hierarchical approach to wrapper induction. Autonomous Agents (1999)","DOI":"10.1145\/301136.301191"},{"key":"3_CR14","unstructured":"Extensible Markup Language (XML), http:\/\/www.w3.org\/XML\/"},{"key":"3_CR15","unstructured":"XML Path Language (XPATH). World Wide Web Consortium (1999), http:\/\/www.w3.org\/TR\/xpath"}],"container-title":["Lecture Notes in Computer Science","Databases in Networked Information Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-31970-2_3.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T04:32:29Z","timestamp":1605760349000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-31970-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540253617","9783540319702"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-31970-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}