{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T10:01:46Z","timestamp":1769162506414,"version":"3.49.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100020409","name":"Analytical Center for the Government of the Russian Federation","doi-asserted-by":"publisher","award":["70-2021-00143 dd.01.11.2021"],"award-info":[{"award-number":["70-2021-00143 dd.01.11.2021"]}],"id":[{"id":"10.13039\/100020409","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020409","name":"Analytical Center for the Government of the Russian Federation","doi-asserted-by":"publisher","award":["IGK 000000D730324P540002"],"award-info":[{"award-number":["IGK 000000D730324P540002"]}],"id":[{"id":"10.13039\/100020409","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2024.3524656","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:39:52Z","timestamp":1735673992000},"page":"15694-15711","source":"Crossref","is-referenced-by-count":3,"title":["Mathematical Model and Algorithm for Accurate Main Content Extraction From News Websites"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9143-5231","authenticated-orcid":false,"given":"Hamza","family":"Salem","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Innopolis University, Innopolis, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6068-0532","authenticated-orcid":false,"given":"Hadi","family":"Salloum","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Innopolis University, Innopolis, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3860-4948","authenticated-orcid":false,"given":"Manuel","family":"Mazzara","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Innopolis University, Innopolis, Russia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1694\/1\/012011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75078-7_61"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28694-0_60"},{"key":"ref4","article-title":"Fact or fiction: Content classification for digital libraries","volume-title":"Proc. DELOS Workshops\/Conf.","author":"Finn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DEXA.2008.43"},{"key":"ref6","first-page":"123","article-title":"Evaluating content extraction on HTML documents","volume-title":"Proc. 2nd Int. Conf. Internet Technol. Appl.","author":"Gottron"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772789"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DEXA.2008.12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2009952"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0687-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jlap.2013.01.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.4204\/EPTCS.98.6"},{"key":"ref13","article-title":"Removing boilerplate and duplicate content from web corpora","author":"Pomik\u00e1lek","year":"2011","journal-title":"Disertacn\u00ed Pr\u00e1ce, Masarykova univerzita, Fakulta Informatiky"},{"key":"ref14","first-page":"486","article-title":"Building large corpora from the web using a new efficient tool chain","volume-title":"Proc. Lrec","author":"Sch\u00e4fer"},{"key":"ref15","first-page":"462","article-title":"Extracting the main content of web documents based on a naive smoothing method","volume-title":"Proc. Int. Conf. Knowl. Discovery Inf. Retr.","author":"Mohammadzadeh"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5220\/0003931906770682"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5626\/JCSE.2017.11.2.39"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3451168"},{"key":"ref19","first-page":"892","article-title":"Language independent content extraction from web pages","author":"Chandramma","year":"2016","journal-title":"Int. J. Eng. Res."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1458082.1458295"},{"key":"ref21","volume-title":"Python Boilerpipe","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591920"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA51294.2020.00162"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40173-2_10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1051\/0004-6361\/201732303"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEOT.2016.7754831"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.22452\/mjcs.vol31no1.3"},{"key":"ref28","volume-title":"Python Readability","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1108\/DTA-05-2020-0104"},{"key":"ref30","volume-title":"Elkateb: AI-Powered Article Writing Tool","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.101739"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10819347.pdf?arnumber=10819347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T17:46:45Z","timestamp":1751046405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10819347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3524656","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}