{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T16:41:46Z","timestamp":1778776906653,"version":"3.51.4"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2984503","type":"journal-article","created":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T21:23:09Z","timestamp":1585689789000},"page":"61726-61740","source":"Crossref","is-referenced-by-count":76,"title":["A Novel Web Scraping Approach Using the Additional Information Obtained From Web Pages"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4351-2244","authenticated-orcid":false,"given":"Erdinc","family":"Uzun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36901-5_42"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WSCS.2008.17"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5121\/ijdkp.2012.2303"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WAINA.2009.60"},{"key":"ref31","article-title":"Fact or fiction: Content classification for digital libraries","author":"finn","year":"2001","journal-title":"Proceedings of the DELOS-NSF Workshop on Personalization and Recommender Systems in Digital Libraries"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1083356.1083384"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ITCS.2010.16"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242582"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511522"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jlap.2013.01.002"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775182"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772789"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2011.10.012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-014-0007-7"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2014.07.007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.08.067"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2004.1264821"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-009-0275-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-004-0188-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.6256398"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DEXA.2008.43"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2890088"},{"key":"ref50","first-page":"67","article-title":"A lightweight parser for extracting useful contents from Web pages","author":"uzun","year":"2011","journal-title":"Proc 2nd Int Symp Comput Sci Eng (ISCSE)"},{"key":"ref51","author":"cormen","year":"2009","journal-title":"Introduction to Algorithms"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186008"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380221006"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/359842.359859"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79184"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0030778"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380100608"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380211105"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0030780"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-1286(99)00052-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-009-0266-3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFRKM.2010.5466924"},{"key":"ref12","first-page":"17","article-title":"Finding what people want: Experiences with the WebCrawler","volume":"94","author":"pinkerton","year":"1994","journal-title":"Proc 2nd Int World Wide Web Conf"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/511446.511466"},{"key":"ref14","first-page":"527","article-title":"Focused crawling using context graphs","author":"diligentit","year":"2000","journal-title":"Proc 13th Int Conf Very Large Data Bases (VLDB)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.2980"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1218"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1031114.1031117"},{"key":"ref18","author":"kushmerick","year":"1997","journal-title":"Wrapper Induction for Information Extraction"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2000.839475"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/spe.2195"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2013.02.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2015.12.025"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1177\/0165551516666446","article-title":"A novel algorithm for extracting the user reviews from Web pages","volume":"43","author":"u\u00e7ar","year":"2017","journal-title":"J Inf Sci"},{"key":"ref8","first-page":"279","article-title":"Comparison of string matching algorithms in Web documents","volume":"2","author":"bulu?","year":"2017","journal-title":"Proc Int Sci Conf (UNITECH)"},{"key":"ref7","first-page":"275","article-title":"Evaluation of Hap, AngleSharp and HtmlDocument in Web content extraction","volume":"2","author":"uzun","year":"2017","journal-title":"Proc Int Sci Conf (UNITECH)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/230514.571645"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2307\/1266761"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1062-0"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0687-x"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1956.1056813"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2877592"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/S1005-8885(11)60429-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WISM.2010.82"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2017.02.002"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2017.04.007"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09051800.pdf?arnumber=9051800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T01:08:19Z","timestamp":1641949699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9051800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2984503","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}