{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:16:26Z","timestamp":1740176186465,"version":"3.37.3"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61363005","61462017"],"award-info":[{"award-number":["61363005","61462017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004607","name":"Natural Science Foundation of Guangxi Province","doi-asserted-by":"publisher","award":["2017GXNSFAA198035"],"award-info":[{"award-number":["2017GXNSFAA198035"]}],"id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Sci. Eng."],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1007\/s41019-018-0067-3","type":"journal-article","created":{"date-parts":[[2018,6,7]],"date-time":"2018-06-07T06:47:06Z","timestamp":1528354026000},"page":"101-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Exploiting Multi-Category Characteristics and Unified Framework to Extract Web Content"],"prefix":"10.1007","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7907-2853","authenticated-orcid":false,"given":"Jingwei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Yang","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":[[2018,6,7]]},"reference":[{"key":"67_CR1","doi-asserted-by":"crossref","unstructured":"Gupta S, Kaiser G, Neistadt D, Grimm P (2003) Dom-based content extraction of HTML documents. In: Proceedings of the 12th international conference on World Wide Web (WWW \u201903), pp 207\u2013214","DOI":"10.1145\/775152.775182"},{"issue":"2","key":"67_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 GE, Grimm P, Chiang MF, Starren J (2005) Automating content extraction of HTML documents. World Wide Web 8(2):179\u2013224","journal-title":"World Wide Web"},{"key":"67_CR3","doi-asserted-by":"crossref","unstructured":"Zhang J, Zhang C, Qian W, Zhou A (2011) Automatic extraction rules generation based on xpath pattern learning. In: Proceedings of the 2010 international conference on web information systems engineering (WISS\u201910), pp 58\u201369","DOI":"10.1007\/978-3-642-24396-7_6"},{"key":"67_CR4","unstructured":"Alam H, Rahman AFR, Hartono R (2001) Content extraction from html documents. In: Proceedings of 1st international workshop on web document analysis (WDA2001)"},{"key":"67_CR5","unstructured":"Crescenzi V, Mecca G, Merialdo P (2001) Roadrunner: towards automatic data extraction from large web sites. In: Proceedings of the 27th international conference on very large data bases (VLDB \u201901), pp 109\u2013118"},{"issue":"2","key":"67_CR6","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s00778-011-0223-0","volume":"20","author":"H Elmeleegy","year":"2011","unstructured":"Elmeleegy H, Madhavan J, Halevy A (2011) Harvesting relational tables from lists on the web. VLDB J 20(2):209\u2013226","journal-title":"VLDB J"},{"key":"67_CR7","doi-asserted-by":"crossref","unstructured":"Furche T, Guo J, Maneth S, Schallhart C (2016) Robust and noise resistant wrapper induction. In: Proceedings of the 2016 international conference on management of data (SIGMOD \u201916), pp 773\u2013784","DOI":"10.1145\/2882903.2915214"},{"key":"67_CR8","doi-asserted-by":"crossref","unstructured":"Reis DC, Golgher PB, Silva AS, Laender AF (2004) Automatic web news extraction using tree edit distance. In: Proceedings of the 13th international conference on World Wide Web (WWW \u201904), pp 502\u2013511","DOI":"10.1145\/988672.988740"},{"key":"67_CR9","doi-asserted-by":"crossref","unstructured":"Wu G, Li L, Hu X, Wu X (2013) Web news extraction via path ratios. In: Proceedings of the 22nd ACM international conference on information and knowledge management (CIKM \u201913), pp 2059\u20132068","DOI":"10.1145\/2505515.2505558"},{"issue":"4","key":"67_CR10","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s11390-016-1655-1","volume":"31","author":"G Wu","year":"2016","unstructured":"Wu G, Li L, Li L, Wu X (2016) Web news extraction via tag path feature fusion using ds theory. J Comput Sci Technol 31(4):661\u2013672","journal-title":"J Comput Sci Technol"},{"issue":"13","key":"67_CR11","doi-asserted-by":"publisher","first-page":"2194","DOI":"10.14778\/2831360.2831372","volume":"8","author":"D Qiu","year":"2015","unstructured":"Qiu D, Barbosa L, Dong XL, Shen Y, Srivastava D (2015) Dexter: large-scale discovery and extraction of product specifications on the web. Proc VLDB Endow 8(13):2194\u20132205","journal-title":"Proc VLDB Endow"},{"key":"67_CR12","doi-asserted-by":"crossref","unstructured":"Wu B, Cheng X, Wang Y, Guo Y, Song L (2009) Simultaneous product attribute name and value extraction from web pages. In: Proceedings of the 2009 IEEE\/WIC\/ACM international joint conference on web intelligence and intelligent agent technology (WI-IAT \u201909), pp 295\u2013298","DOI":"10.1109\/WI-IAT.2009.286"},{"key":"67_CR13","doi-asserted-by":"crossref","unstructured":"Cai D, Yu S, Wen J-R, Ma W-Y (2003) Extracting content structure for web pages based on visual representation. In: Proceedings of the 5th Asia-Pacific web conference on web technologies and applications (APWeb\u201903), pp 406\u2013417","DOI":"10.1007\/3-540-36901-5_42"},{"key":"67_CR14","doi-asserted-by":"crossref","unstructured":"Song R, Liu H, Wen J-R, Ma W-Y (2004) Learning block importance models for web pages. In: Proceedings of the 13th International Conference on World Wide Web (WWW \u201904), pp 203\u2013211","DOI":"10.1145\/988672.988700"},{"key":"67_CR15","doi-asserted-by":"crossref","unstructured":"Fernandes D, de Moura ES, Ribeiro-Neto B, da Silva AS, Goncalves MA (2007) Computing block importance for searching on web sites. In: Proceedings of the 16th ACM conference on conference on information and knowledge management (CIKM \u201907), pp 165\u2013174","DOI":"10.1145\/1321440.1321466"},{"key":"67_CR16","doi-asserted-by":"crossref","unstructured":"Sun F, Song D, Liao L (2011) Dom based content extraction via text density. In: Proceedings of the 34th international ACM SIGIR conference on research and development in information retrieval (SIGIR \u201911), pp 245\u2013254","DOI":"10.1145\/2009916.2009952"},{"issue":"4","key":"67_CR17","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1016\/j.jcss.2011.10.012","volume":"78","author":"PAR Qureshi","year":"2012","unstructured":"Qureshi PAR, Memon N (2012) Hybrid model of content extraction. J Comput Syst Sci 78(4):1248\u20131257","journal-title":"J Comput Syst Sci"},{"key":"67_CR18","unstructured":"Peters ME, Lecocq D (2013) Content extraction using diverse feature sets. In: Proceedings of the 22nd international conference on World Wide Web (WWW \u201913 Companion), pp 89\u201390"},{"issue":"12","key":"67_CR19","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 (2015) Wadar: joint wrapper and data repair. Proc VLDB Endow 8(12):1996\u20131999","journal-title":"Proc VLDB Endow"},{"key":"67_CR20","doi-asserted-by":"crossref","unstructured":"Weninger T, Hsu WH, Han J (2010) CETR: content extraction via tag ratios. In: Proceedings of the 19th international conference on World Wide Web (WWW \u201910), pp 971\u2013980","DOI":"10.1145\/1772690.1772789"},{"issue":"4","key":"67_CR21","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 HV, Yerlikaya T (2013) A hybrid approach for extracting informative content from web pages. Inf Process Manage 49(4):928\u2013944","journal-title":"Inf Process Manage"},{"issue":"2","key":"67_CR22","doi-asserted-by":"publisher","first-page":"12:1","DOI":"10.1145\/2857054","volume":"16","author":"L Bing","year":"2016","unstructured":"Bing L, Wong T-L, Lam W (2016) Unsupervised extraction of popular product attributes from e-commerce web sites by considering customer reviews. ACM Trans Internet Technol 16(2):12:1\u201312:17","journal-title":"ACM Trans Internet Technol"},{"key":"67_CR23","unstructured":"Wong T-L, Lam W, Wong T-S (2008) An unsupervised framework for extracting and normalizing product attributes from multiple web sites. In: Proceedings of the 31st annual international ACM SIGIR conference on research and development in information retrieval (SIGIR \u201908), pp 35\u201342"},{"issue":"9","key":"67_CR24","first-page":"1846","volume":"29","author":"B Zheng","year":"2017","unstructured":"Zheng B, Su H, Hua W, Zheng K, Zhou X, Li G (2017) Efficient clue-based route search on road networks. TKDE 29(9):1846\u20131859","journal-title":"TKDE"},{"key":"67_CR25","doi-asserted-by":"crossref","unstructured":"Zheng B, Zheng K, Xiao X, Su H, Yin H, Zhou X, Li G (2016) Keyword-aware continuous knn query on road networks. In: Proceedings of ICDE, pp 871\u2013882","DOI":"10.1109\/ICDE.2016.7498297"},{"key":"67_CR26","doi-asserted-by":"crossref","unstructured":"Zheng B, Yuan NJ, Zheng K, Xie X, Sadiq S, Zhou X (2015) Approximate keyword search in semantic trajectory database. In: Proceedings of ICDE, pp 975\u2013986","DOI":"10.1109\/ICDE.2015.7113349"},{"issue":"4","key":"67_CR27","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s11280-016-0414-0","volume":"20","author":"K Zheng","year":"2017","unstructured":"Zheng K, Zheng B, Xu J, Liu G, Liu A, Li Z (2017) Popularity-aware spatial keyword search on activity trajectories. World Wide Web J 20(4):749\u2013773","journal-title":"World Wide Web J"},{"key":"67_CR28","doi-asserted-by":"crossref","unstructured":"Zheng K, Su H, Zheng B, Shang S, Xu J, Liu J, Zhou X (2015) Interactive top-k spatial keyword queries. In: Proceedings of ICDE, pp 423\u2013434","DOI":"10.1109\/ICDE.2015.7113303"},{"issue":"2","key":"67_CR29","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 (2016) Web content extraction: a metaanalysis of its past and thoughts on its future. SIGKDD Explor Newsl 17(2):17\u201323","journal-title":"SIGKDD Explor Newsl"},{"key":"67_CR30","unstructured":"Jsoup. \n                    https:\/\/jsoup.org\/\n                    \n                  . Accessed 20 Oct 2017"},{"key":"67_CR31","doi-asserted-by":"crossref","unstructured":"Charikar MS (2002) Similarity estimation techniques from rounding algorithms. In: Proceedings of the 34th annual ACM symposium on theory of computing, STOC \u201902, pp 380\u2013388","DOI":"10.1145\/509907.509965"},{"key":"67_CR32","unstructured":"Zhang H. Nlpir. \n                    http:\/\/ictclas.nlpir.org\/\n                    \n                  . Accessed 15 Dec 2017"}],"container-title":["Data Science and Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41019-018-0067-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-018-0067-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41019-018-0067-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,6]],"date-time":"2019-06-06T19:19:08Z","timestamp":1559848748000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s41019-018-0067-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018,6]]}},"alternative-id":["67"],"URL":"https:\/\/doi.org\/10.1007\/s41019-018-0067-3","relation":{},"ISSN":["2364-1185","2364-1541"],"issn-type":[{"type":"print","value":"2364-1185"},{"type":"electronic","value":"2364-1541"}],"subject":[],"published":{"date-parts":[[2018,6]]},"assertion":[{"value":"4 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}