{"id":"https://openalex.org/W2022158118","doi":"https://doi.org/10.1016/j.datak.2007.10.002","title":"Extracting lists of data records from semi-structured web pages","display_name":"Extracting lists of data records from semi-structured web pages","publication_year":2007,"publication_date":"2007-10-12","ids":{"openalex":"https://openalex.org/W2022158118","doi":"https://doi.org/10.1016/j.datak.2007.10.002","mag":"2022158118"},"language":"en","primary_location":{"id":"doi:10.1016/j.datak.2007.10.002","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.datak.2007.10.002","pdf_url":null,"source":{"id":"https://openalex.org/S136993123","display_name":"Data & Knowledge Engineering","issn_l":"0169-023X","issn":["0169-023X","1872-6933"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data &amp; Knowledge Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101786992","display_name":"Manuel \u00c1lvarez","orcid":"https://orcid.org/0000-0001-7204-2689"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Manuel \u00c1lvarez","raw_affiliation_strings":["Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031134938","display_name":"Alberto Pan-Bermudez","orcid":"https://orcid.org/0000-0003-3720-9791"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alberto Pan","raw_affiliation_strings":["Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020728818","display_name":"Juan Raposo","orcid":"https://orcid.org/0000-0003-4913-618X"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Raposo","raw_affiliation_strings":["Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068360111","display_name":"Francisco Bellas","orcid":"https://orcid.org/0000-0001-6043-1468"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Bellas","raw_affiliation_strings":["Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070668196","display_name":"Fidel Cacheda","orcid":"https://orcid.org/0000-0002-6438-1661"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fidel Cacheda","raw_affiliation_strings":["Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n, 15071 A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]},{"raw_affiliation_string":"Department of Information and Communication Technologies, University of A Coru\u00f1a, Campus de Elvina s/n, 15071 A Coruna, Spain","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101786992"],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":{"value":2590,"currency":"USD","value_usd":2590},"apc_paid":null,"fwci":10.7726,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97856175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"64","issue":"2","first_page":"491","last_page":"509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8331083059310913},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6734161376953125},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6115810871124268},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5618565082550049},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42954036593437195},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4245452582836151},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4190506935119629},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.41548144817352295},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.17802470922470093},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12146532535552979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331083059310913},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6734161376953125},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6115810871124268},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5618565082550049},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42954036593437195},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4245452582836151},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4190506935119629},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.41548144817352295},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.17802470922470093},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12146532535552979},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.datak.2007.10.002","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.datak.2007.10.002","pdf_url":null,"source":{"id":"https://openalex.org/S136993123","display_name":"Data & Knowledge Engineering","issn_l":"0169-023X","issn":["0169-023X","1872-6933"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data &amp; Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1492472380","https://openalex.org/W1506845741","https://openalex.org/W1553019137","https://openalex.org/W1558832481","https://openalex.org/W1573714593","https://openalex.org/W1601949013","https://openalex.org/W1616576116","https://openalex.org/W1647671624","https://openalex.org/W1821155018","https://openalex.org/W1822119045","https://openalex.org/W1946389870","https://openalex.org/W2005646337","https://openalex.org/W2005677600","https://openalex.org/W2027864253","https://openalex.org/W2046725473","https://openalex.org/W2049365470","https://openalex.org/W2053045757","https://openalex.org/W2065568440","https://openalex.org/W2069388662","https://openalex.org/W2073384429","https://openalex.org/W2084801987","https://openalex.org/W2085016361","https://openalex.org/W2096496923","https://openalex.org/W2104086170","https://openalex.org/W2119088569","https://openalex.org/W2123718938","https://openalex.org/W2128613007","https://openalex.org/W2136072238","https://openalex.org/W2136812450","https://openalex.org/W2138405339","https://openalex.org/W2148210463","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2168358004","https://openalex.org/W2170188121","https://openalex.org/W2406080254","https://openalex.org/W4206031975","https://openalex.org/W6633712013","https://openalex.org/W6636915900"],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W4239898202","https://openalex.org/W2069679074","https://openalex.org/W2115253914","https://openalex.org/W3116613346","https://openalex.org/W4237456423","https://openalex.org/W2911454453","https://openalex.org/W2055154498","https://openalex.org/W1559090489","https://openalex.org/W2351131669"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":15}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}
