{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T16:05:06Z","timestamp":1774195506115,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,4,20]],"date-time":"2009-04-20T00:00:00Z","timestamp":1240185600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,4,20]]},"DOI":"10.1145\/1526709.1526841","type":"proceedings-article","created":{"date-parts":[[2009,4,21]],"date-time":"2009-04-21T14:17:17Z","timestamp":1240323437000},"page":"981-990","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":106,"title":["Extracting data records from the web using tag path clustering"],"prefix":"10.1145","author":[{"given":"Gengxin","family":"Miao","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Tatemura","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang-Pin","family":"Hsiung","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arsany","family":"Sawires","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louise E.","family":"Moser","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2009,4,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872799"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/876878.879311"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/1453856.1453916"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372182"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1031570.1031584"},{"key":"e_1_3_2_1_6_1","unstructured":"Cobra: Java HTML Renderer and Parser http:\/\/lobobrowser.org\/cobra.jsp.  Cobra: Java HTML Renderer and Parser http:\/\/lobobrowser.org\/cobra.jsp."},{"key":"e_1_3_2_1_7_1","first-page":"109","volume-title":"Proceedings of the 27th International Conference on Very Large Data Bases","author":"Crescenzi V.","year":"2001","unstructured":"V. Crescenzi , G. Mecca , and P. Merialdo . RoadRunner: Towards automatic data extraction from large Web sites . In Proceedings of the 27th International Conference on Very Large Data Bases , pages 109 -- 118 , 2001 . V. Crescenzi, G. Mecca, and P. Merialdo. RoadRunner: Towards automatic data extraction from large Web sites. In Proceedings of the 27th International Conference on Very Large Data Bases, pages 109--118, 2001."},{"key":"e_1_3_2_1_8_1","unstructured":"DBLP Computer Science Bibliography http:\/\/www.informatik.uni-trier.de\/~ley\/db\/.  DBLP Computer Science Bibliography http:\/\/www.informatik.uni-trier.de\/~ley\/db\/."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/565117.565137"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007584"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956826"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/11581062_39"},{"key":"e_1_3_2_1_13_1","first-page":"849","volume-title":"Proceedings of the Neural Information Processing Systems Conference","author":"Ng A. Y.","year":"2001","unstructured":"A. Y. Ng , M. I. Jordan , and Y. Weiss . On spectral clustering: Analysis and an algorithm . In Proceedings of the Neural Information Processing Systems Conference , pages 849 -- 856 , 2001 . A. Y. Ng, M. I. Jordan, and Y. Weiss. On spectral clustering: Analysis and an algorithm. In Proceedings of the Neural Information Processing Systems Conference, pages 849--856, 2001."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1099554.1099672"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376754"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775179"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1013367.1013468"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060761"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060760"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281286"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150457"}],"event":{"name":"WWW '09: The 18th International World Wide Web Conference","location":"Madrid Spain","acronym":"WWW '09","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","ACM Association for Computing Machinery"]},"container-title":["Proceedings of the 18th international conference on World wide web"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1526709.1526841","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1526709.1526841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:29:47Z","timestamp":1750253387000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1526709.1526841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,4,20]]},"references-count":22,"alternative-id":["10.1145\/1526709.1526841","10.1145\/1526709"],"URL":"https:\/\/doi.org\/10.1145\/1526709.1526841","relation":{},"subject":[],"published":{"date-parts":[[2009,4,20]]},"assertion":[{"value":"2009-04-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}