{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:15:40Z","timestamp":1750306540075,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,5,18]],"date-time":"2015-05-18T00:00:00Z","timestamp":1431907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Spanish Ministerio de Econom-a y Competitividad","award":["TIN2013-44742-C4-1-R"],"award-info":[{"award-number":["TIN2013-44742-C4-1-R"]}]},{"name":"Spanish Ministerio de Educacin","award":["FPU Grant AP2010-4415"],"award-info":[{"award-number":["FPU Grant AP2010-4415"]}]},{"name":"European Union STREP FP7","award":["610686"],"award-info":[{"award-number":["610686"]}]},{"name":"EU FEDER"},{"name":"Generalitat Valenciana","award":["PROMETEOII\/2015\/013"],"award-info":[{"award-number":["PROMETEOII\/2015\/013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,5,18]]},"DOI":"10.1145\/2740908.2742835","type":"proceedings-article","created":{"date-parts":[[2016,2,6]],"date-time":"2016-02-06T00:01:06Z","timestamp":1454716866000},"page":"155-158","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["TeMex"],"prefix":"10.1145","author":[{"given":"Juli\u00e1n","family":"Alarte","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}]},{"given":"David","family":"Insa","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}]},{"given":"Josep","family":"Silva","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}]},{"given":"Salvador","family":"Tamarit","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e9cnica de Madrid, Madrid, Spain"}]}],"member":"320","published-online":{"date-parts":[[2015,5,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Available from URL: https:\/\/developer.mozilla.org\/en-US\/Add-ons\/Overlay_Extensions","author":"Overlay","year":"2005","unstructured":"Overlay extension. Available from URL: https:\/\/developer.mozilla.org\/en-US\/Add-ons\/Overlay_Extensions , 2005 . Overlay extension. Available from URL: https:\/\/developer.mozilla.org\/en-US\/Add-ons\/Overlay_Extensions, 2005."},{"key":"e_1_3_2_1_2_1","series-title":"Electronic Proceedings in Theoretical Computer Science","first-page":"2","volume-title":"M. H. ter Beek and A","author":"Alarte J.","year":"2014","unstructured":"J. Alarte , D. Insa , J. Silva , and S. Tamarit . Automatic Detection of Webpages that Share the Same Web Template . In M. H. ter Beek and A . Ravara, editors, Proceedings of the 10th International Workshop on Automated Specification and Verification of Web Systems (WWV 14), volume 163 of Electronic Proceedings in Theoretical Computer Science , pages 2 -- 15 . Open Publishing Association , July 2014 . J. Alarte, D. Insa, J. Silva, and S. Tamarit. Automatic Detection of Webpages that Share the Same Web Template. In M. H. ter Beek and A. Ravara, editors, Proceedings of the 10th International Workshop on Automated Specification and Verification of Web Systems (WWV 14), volume 163 of Electronic Proceedings in Theoretical Computer Science, pages 2--15. Open Publishing Association, July 2014."},{"key":"e_1_3_2_1_3_1","volume-title":"A Benchmark Suite for Template Detection and Content Extraction. CoRR, abs\/1409.6182","author":"Alarte J.","year":"2014","unstructured":"J. Alarte , D. Insa , J. Silva , and S. Tamarit . A Benchmark Suite for Template Detection and Content Extraction. CoRR, abs\/1409.6182 , 2014 . J. Alarte, D. Insa, J. Silva, and S. Tamarit. A Benchmark Suite for Template Detection and Content Extraction. CoRR, abs\/1409.6182, 2014."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511522"},{"key":"e_1_3_2_1_5_1","first-page":"638","volume-title":"Proceedings of the International Conference on Language Resources and Evaluation (LREC'08)","author":"Baroni M.","year":"2008","unstructured":"M. Baroni , F. Chantree , A. Kilgarriff , and S. Sharoff . Cleaneval: a Competition for Cleaning Web Pages . In Proceedings of the International Conference on Language Resources and Evaluation (LREC'08) , pages 638 -- 643 . European Language Resources Association, may 2008 . M. Baroni, F. Chantree, A. Kilgarriff, and S. Sharoff. Cleaneval: a Competition for Cleaning Web Pages. In Proceedings of the International Conference on Language Resources and Evaluation (LREC'08), pages 638--643. European Language Resources Association, may 2008."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1062745.1062763"},{"key":"e_1_3_2_1_7_1","first-page":"123","volume-title":"Proceedings of the 2nd International Conference on Internet Technologies and Applications (ITA'07)","author":"Gottron T.","year":"2007","unstructured":"T. Gottron . Evaluating content extraction on HTML documents. In V. Grout, D. Oram, and R. Picking, editors , Proceedings of the 2nd International Conference on Internet Technologies and Applications (ITA'07) , pages 123 -- 132 . National Assembly for Wales, sep 2007 . T. Gottron. Evaluating content extraction on HTML documents. In V. Grout, D. Oram, and R. Picking, editors, Proceedings of the 2nd International Conference on Internet Technologies and Applications (ITA'07), pages 123--132. National Assembly for Wales, sep 2007."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988740"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-009-0059-3"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183614.1183654"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772789"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/956750.956785"}],"event":{"name":"WWW '15: 24th International World Wide Web Conference","sponsor":["IW3C2 International World Wide Web Conference Committee","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Florence Italy","acronym":"WWW '15"},"container-title":["Proceedings of the 24th International Conference on World Wide Web"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2740908.2742835","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2740908.2742835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:12:25Z","timestamp":1750227145000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2740908.2742835"}},"subtitle":["The Web Template Extractor"],"short-title":[],"issued":{"date-parts":[[2015,5,18]]},"references-count":12,"alternative-id":["10.1145\/2740908.2742835","10.1145\/2740908"],"URL":"https:\/\/doi.org\/10.1145\/2740908.2742835","relation":{},"subject":[],"published":{"date-parts":[[2015,5,18]]},"assertion":[{"value":"2015-05-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}