{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:11:58Z","timestamp":1743009118582,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319687858"},{"type":"electronic","value":"9783319687865"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-68786-5_19","type":"book-chapter","created":{"date-parts":[[2017,10,3]],"date-time":"2017-10-03T05:08:32Z","timestamp":1507007312000},"page":"229-244","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Extracting Web Content by Exploiting Multi-Category Characteristics"],"prefix":"10.1007","author":[{"given":"Qian","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanchun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,4]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Gupta, S., Kaiser, G., Neistadt, D., Grimm, P.: Dom-based content extraction of html documents. In: Proceedings of the 12th International Conference on World Wide Web, WWW 2003, pp. 207\u2013214. ACM, New York (2003)","key":"19_CR1","DOI":"10.1145\/775181.775182"},{"issue":"2","key":"19_CR2","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s11280-004-4873-3","volume":"8","author":"S Gupta","year":"2005","unstructured":"Gupta, S., Kaiser, G.E., Grimm, P., Chiang, M.F., Starren, J.: Automating content extraction of html documents. World Wide Web 8(2), 179\u2013224 (2005)","journal-title":"World Wide Web"},{"key":"19_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/978-3-642-24396-7_6","volume-title":"Web Information Systems Engineering \u2013 WISE 2010 Workshops","author":"J Zhang","year":"2011","unstructured":"Zhang, J., Zhang, C., Qian, W., Zhou, A.: Automatic Extraction Rules Generation Based on XPath Pattern Learning. In: Chiu, D.K.W., Bellatreche, L., Sasaki, H., Leung, H., Cheung, S.-C., Hu, H., Shao, J. (eds.) WISE 2010. LNCS, vol. 6724, pp. 58\u201369. Springer, Heidelberg (2011). doi:10.1007\/978-3-642-24396-7_6"},{"unstructured":"Alam, H., Rahman, A.F.R., Hartono, R.: Content extraction from html documents. In: Proceedings of 1st International Workshop on Web Document Analysis, WDA2001 (2001)","key":"19_CR4"},{"unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: towards automatic data extraction from large web sites. In: Proceedings of the 27th International Conference on Very Large Data Bases, VLDB 2001, pp. 109\u2013118. Morgan Kaufmann Publishers Inc., San Francisco (2001)","key":"19_CR5"},{"doi-asserted-by":"crossref","unstructured":"Furche, T., Guo, J., Maneth, S., Schallhart, C.: Robust and noise resistant wrapper induction. In: Proceedings of the 2016 International Conference on Management of Data, SIGMOD 2016, pp. 773\u2013784. ACM, New York (2016)","key":"19_CR6","DOI":"10.1145\/2882903.2915214"},{"doi-asserted-by":"crossref","unstructured":"Reis, D.C., Golgher, P.B., Silva, A.S., Laender, A.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)","key":"19_CR7","DOI":"10.1145\/988672.988740"},{"doi-asserted-by":"crossref","unstructured":"Wu, G., Li, L., Hu, X., Wu, X.: Web news extraction via path ratios. In: Proceedings of the 22nd ACM international conference on Conference on information & #38; knowledge management, CIKM 2013, pp. 2059\u20132068. ACM, New York (2013)","key":"19_CR8","DOI":"10.1145\/2505515.2505558"},{"issue":"4","key":"19_CR9","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s11390-016-1655-1","volume":"31","author":"W Gong-Qing","year":"2016","unstructured":"Gong-Qing, W., Li, L., Li, L., Xindong, W.: Web news extraction via tag path feature fusion using ds theory. J. Comput. Sci. Technol. 31(4), 661\u2013672 (2016)","journal-title":"J. Comput. Sci. Technol."},{"key":"19_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/3-540-36901-5_42","volume-title":"Web Technologies and Applications","author":"D Cai","year":"2003","unstructured":"Cai, D., Yu, S., Wen, J.-R., Ma, W.-Y.: Extracting Content Structure for Web Pages Based on Visual Representation. In: Zhou, X., Orlowska, M.E., Zhang, Y. (eds.) APWeb 2003. LNCS, vol. 2642, pp. 406\u2013417. Springer, Heidelberg (2003). doi:10.1007\/3-540-36901-5_42"},{"doi-asserted-by":"crossref","unstructured":"Song, R., Liu, H., Wen, J.-R., Ma, W.-Y.: Learning block importance models for web pages. In: Proceedings of the 13th International Conference on World Wide Web, WWW 2004, pp. 203\u2013211. ACM, New York (2004)","key":"19_CR11","DOI":"10.1145\/988672.988700"},{"doi-asserted-by":"crossref","unstructured":"Fernandes, D., de Moura, E.S., Ribeiro-Neto, B., da Silva, A.S., Gon\u00e7alves, M.A.: Computing block importance for searching on web sites. In: Proceedings of the Sixteenth ACM Conference on Conference on Information and Knowledge Management, CIKM 2007, pp. 165\u2013174. ACM, New York (2007)","key":"19_CR12","DOI":"10.1145\/1321440.1321466"},{"doi-asserted-by":"crossref","unstructured":"Sun, F., Song, D., Liao, L.: Dom based content extraction via text density. In: Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2011, pp. 245\u2013254. ACM, New York (2011)","key":"19_CR13","DOI":"10.1145\/2009916.2009952"},{"issue":"4","key":"19_CR14","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."},{"doi-asserted-by":"crossref","unstructured":"Peters, M.E., Lecocq, D.: Content extraction using diverse feature sets. In: Proceedings of the 22nd International Conference on World Wide Web, WWW 2013 Companion, pp. 89\u201390. ACM, New York (2013)","key":"19_CR15","DOI":"10.1145\/2487788.2487828"},{"issue":"12","key":"19_CR16","doi-asserted-by":"publisher","first-page":"1996","DOI":"10.14778\/2824032.2824120","volume":"8","author":"S Ortona","year":"2015","unstructured":"Ortona, S., Orsi, G., Buoncristiano, M., Furche, T.: Wadar: joint wrapper and data repair. Proc. VLDB Endow. 8(12), 1996\u20131999 (2015)","journal-title":"Proc. VLDB Endow."},{"doi-asserted-by":"crossref","unstructured":"Weninger, T., Hsu, W.H., Han, J.: Cetr: Content extraction via tag ratios. In: Proceedings of the 19th International Conference on World Wide Web, WWW 2010, pp. 971\u2013980. ACM, New York (2010)","key":"19_CR17","DOI":"10.1145\/1772690.1772789"},{"issue":"4","key":"19_CR18","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1016\/j.ipm.2013.02.005","volume":"49","author":"E Uzun","year":"2013","unstructured":"Uzun, E., Agun, H.V., Yerlikaya, T.: A hybrid approach for extracting informative content from web pages. Inf. Process. Manage. 49(4), 928\u2013944 (2013)","journal-title":"Inf. Process. Manage."},{"issue":"2","key":"19_CR19","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1145\/2897350.2897353","volume":"17","author":"T Weninger","year":"2016","unstructured":"Weninger, T., Palacios, R., Crescenzi, V., Gottron, T., Merialdo, P.: Web content extraction: a metaanalysis of its past and thoughts on its future. SIGKDD Explor. Newsl. 17(2), 17\u201323 (2016)","journal-title":"SIGKDD Explor. Newsl."},{"unstructured":"Jsoup. https:\/\/jsoup.org\/","key":"19_CR20"},{"doi-asserted-by":"crossref","unstructured":"Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: Proceedings of the Thiry-fourth Annual ACM Symposium on Theory of Computing, STOC 2002, pp. 380\u2013388. ACM, New York (2002)","key":"19_CR21","DOI":"10.1145\/509907.509965"},{"unstructured":"Huaping, Z.: Nlpir. http:\/\/ictclas.nlpir.org\/","key":"19_CR22"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2017"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-68786-5_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:17:16Z","timestamp":1710242236000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-68786-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319687858","9783319687865"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-68786-5_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"4 October 2017","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":"Puschino","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wise2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.wise-conferences.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}