{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T01:17:52Z","timestamp":1746235072760,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030029210"},{"type":"electronic","value":"9783030029227"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-02922-7_27","type":"book-chapter","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T05:42:24Z","timestamp":1539927744000},"page":"393-407","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Main Content Extraction from Heterogeneous Webpages"],"prefix":"10.1007","author":[{"given":"Julian","family":"Alarte","sequence":"first","affiliation":[]},{"given":"David","family":"Insa","sequence":"additional","affiliation":[]},{"given":"Josep","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Salvador","family":"Tamarit","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,20]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Adam, G., Bouras, C., Poulopoulos, V.: CUTER: an efficient useful text extraction mechanism. In: 2009 International Conference on Advanced Information Networking and Applications Workshops, pp. 703\u2013708, May 2009","DOI":"10.1109\/WAINA.2009.60"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Alarte, J., Insa, D., Silva, J., Tamarit, S.: Automatic detection of webpages that share the same web template. In: ter Beek, M.H., Ravara, A. (eds.) Proceedings of the 10th International Workshop on Automated Specification and Verification of Web Systems (WWV 2014). Electronic Proceedings in Theoretical Computer Science, vol. 163, pp. 2\u201315. Open Publishing Association, July 2014","DOI":"10.4204\/EPTCS.163.2"},{"key":"27_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-319-41579-6_4","volume-title":"Perspectives of System Informatics","author":"J Alarte","year":"2016","unstructured":"Alarte, J., Insa, D., Silva, J., Tamarit, S.: Site-level web template extraction based on DOM analysis. In: Mazzara, M., Voronkov, A. (eds.) PSI 2015. LNCS, vol. 9609, pp. 36\u201349. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-41579-6_4"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Bar-Yossef, Z., Rajagopalan, S.: Template detection via data mining and its applications. In: Proceedings of the 11th International Conference on World Wide Web (WWW 2002), pp. 580\u2013591. ACM, New York (2002)","DOI":"10.1145\/511446.511522"},{"key":"27_CR5","unstructured":"Baroni, M., Chantree, F., Kilgarriff, A., Sharoff, S.: Cleaneval: a competition for cleaning web pages. In: Proceedings of the International Conference on Language Resources and Evaluation (LREC 2008), pp. 638\u2013643. European Language Resources Association, May 2008"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Burget, R., Rudolfova, I.: Web page element classification based on visual features. In: Proceedings of the 1st Asian Conference on Intelligent Information and Database Systems (ACIIDS 2009), pp. 67\u201372. IEEE Computer Society, Washington, DC (2009)","DOI":"10.1109\/ACIIDS.2009.71"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Cardoso, E., Jabour, I., Laber, E., Rodrigues, R., Cardoso, P.: An efficient language-independent method to extract content from news webpages. In: Proceedings of the 11th ACM Symposium on Document Engineering (DocEng 2011), pp. 121\u2013128. ACM, New York (2011)","DOI":"10.1145\/2034691.2034720"},{"key":"27_CR8","unstructured":"Ferraresi, A., Zanchetta, E., Baroni, M., Bernardini, S.: Introducing and evaluating ukWaC, a very large web-derived corpus of English. In: Proceedings of the 4th Web as Corpus Workshop (WAC-4), pp. 47\u201354 (2008)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Gottron, T.: Content code blurring: a new approach to content extraction. In: Proceedings of the 2008 19th International Conference on Database and Expert Systems Application, DEXA 2008, pp. 29\u201333. IEEE Computer Society, Washington, DC, September 2008","DOI":"10.1109\/DEXA.2008.43"},{"issue":"8","key":"27_CR10","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.jlap.2013.01.002","volume":"82","author":"D Insa","year":"2013","unstructured":"Insa, D., Silva, J., Tamarit, S.: Using the words\/leafs ratio in the DOM tree for content extraction. J. Log. Algebr. Program. 82(8), 311\u2013325 (2013)","journal-title":"J. Log. Algebr. Program."},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Kohlsch\u00fctter, C.: A densitometric analysis of web template content. In: Quemada, J., Le\u00f3n, G., Maarek, Y.S., Nejdl, W. (eds.) Proceedings of the 18th International Conference on World Wide Web (WWW 2009), pp. 1165\u20131166. ACM, April 2009","DOI":"10.1145\/1526709.1526909"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Kohlsch\u00fctter, C., Fankhauser, P., Nejdl, W.: Boilerplate detection using shallow text features. In: Davison, B.D., Suel, T., Craswell, N., Liu, B. (eds.) Proceedings of the 3rd International Conference on Web Search and Web Data Mining (WSDM 2010), pp. 441\u2013450. ACM, February 2010","DOI":"10.1145\/1718487.1718542"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Kohlsch\u00fctter, C., Nejdl, W.: A densitometric approach to web page segmentation. In: Shanahan, J.G., et al. (eds.) Proceedings of the 17th ACM Conference on Information and Knowledge Management (CIKM 2008), pp. 1173\u20131182. ACM, October 2008","DOI":"10.1145\/1458082.1458237"},{"issue":"4","key":"27_CR14","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/s10115-004-0188-z","volume":"8","author":"Z Li","year":"2005","unstructured":"Li, Z., Ng, W.K., Sun, A.: Web data extraction based on structural similarity. Knowl. Inf. Syst. 8(4), 438\u2013461 (2005)","journal-title":"Knowl. Inf. Syst."},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Pasternack, J., Roth, D.: Extracting article text from the web with maximum subsequence segmentation. In: Proceedings of the 18th International Conference on World Wide Web, WWW 2009, pp. 971\u2013980. ACM, New York (2009)","DOI":"10.1145\/1526709.1526840"},{"issue":"4","key":"27_CR16","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1016\/j.jcss.2011.10.012","volume":"78","author":"PAR Qureshi","year":"2012","unstructured":"Qureshi, P.A.R., Memon, N.: Hybrid model of content extraction. J. Comput. Syst. Sci. 78(4), 1248\u20131257 (2012)","journal-title":"J. Comput. Syst. Sci."},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Reis, D.d.C., Golgher, P.B., Silva, A.S., Laender, A.H.F.: Automatic web news extraction using tree edit distance. In: Proceedings of the 13th International Conference on World Wide Web (WWW 2004), pp. 502\u2013511. ACM, New York (2004)","DOI":"10.1145\/988672.988740"},{"issue":"2","key":"27_CR18","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s11280-009-0059-3","volume":"12","author":"Karane Vieira","year":"2009","unstructured":"Vieira, K., da Costa Carvalho, A.L., Berlt, K., de Moura, E.S., da Silva, A.S., Freire, J.: On finding templates on web collections. World Wide Web 12(2), 171\u2013211 (2009)","journal-title":"World Wide Web"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Vieira, K., da Silva, A.S., Pinto, N., de Moura, E.S., Cavalcanti, J.a.M.B., Freire, J.: A fast and robust method for web page template detection and removal. In: Proceedings of the 15th ACM International Conference on Information and Knowledge Management (CIKM 2006), pp. 258\u2013267. ACM, New York (2006)","DOI":"10.1145\/1183614.1183654"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fang, B., Cheng, X., Guo, L., Xu, H.: Incremental web page template detection. In: Proceedings of the 17th International Conference on World Wide Web (WWW 2008), pp. 1247\u20131248. ACM, New York (2008)","DOI":"10.1145\/1367497.1367749"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Weninger, T., Henry Hsu, W., Han, J.: CETR: Content Extraction via Tag Ratios. In: Rappa, M., Jones, P., Freire, J., Chakrabarti, S. (eds.) Proceedings of the 19th International Conference on World Wide Web (WWW 2010), pp. 971\u2013980. ACM, April 2010","DOI":"10.1145\/1772690.1772789"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Wu, S., Liu, J., Fan, J.: Automatic web content extraction by combination of learning and grouping. In: Proceedings of the 24th International Conference on World Wide Web, WWW 2015, pp. 1264\u20131274. International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland (2015)","DOI":"10.1145\/2736277.2741659"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Yi, L., Liu, B., Li, X.: Eliminating noisy information in web pages for data mining. In: Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data mining (KDD 2003), pp. 296\u2013305. ACM, New York (2003)","DOI":"10.1145\/956750.956785"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-02922-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T08:50:49Z","timestamp":1710233449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-02922-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030029210","9783030029227"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-02922-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"20 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dubai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Arab Emirates","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wise2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wise2018.connect.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}