{"id":"https://openalex.org/W2080375353","doi":"https://doi.org/10.1007/s11265-008-0270-y","title":"Finding and Extracting Data Records from Web Pages","display_name":"Finding and Extracting Data Records from Web Pages","publication_year":2008,"publication_date":"2008-09-23","ids":{"openalex":"https://openalex.org/W2080375353","doi":"https://doi.org/10.1007/s11265-008-0270-y","mag":"2080375353"},"language":"en","primary_location":{"id":"doi:10.1007/s11265-008-0270-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11265-008-0270-y","pdf_url":null,"source":{"id":"https://openalex.org/S11258463","display_name":"Journal of Signal Processing Systems","issn_l":"1939-8018","issn":["1939-8018","1939-8115"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Signal Processing Systems","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 Communications Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n. 15071, A Coru\u00f1a, Spain","Department of Information and Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communications 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 Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#","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 Communications Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n. 15071, A Coru\u00f1a, Spain","Department of Information and Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communications 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 Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#","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 Communications Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n. 15071, A Coru\u00f1a, Spain","Department of Information and Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communications 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 Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#","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 Communications Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n. 15071, A Coru\u00f1a, Spain","Department of Information and Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communications 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 Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#","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 Communications Technologies, University of A Coru\u00f1a, Campus de Elvi\u00f1a s/n. 15071, A Coru\u00f1a, Spain","Department of Information and Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communications 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 Communications Technologies, University of A Coru\u00f1a, A Coru\u00f1a, Spain#TAB#","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":2490,"currency":"EUR","value_usd":3090},"apc_paid":null,"fwci":1.7522,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89418164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"59","issue":"1","first_page":"123","last_page":"137"},"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9682000279426575,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692266702651978},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6754343509674072},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6031119227409363},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5895755887031555},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5584638714790344},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5381423234939575},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5206100940704346},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5087326169013977},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4676755368709564},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4309070110321045},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3518650531768799},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24581554532051086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21752139925956726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.100789874792099},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06261399388313293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692266702651978},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6754343509674072},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6031119227409363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5895755887031555},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5584638714790344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5381423234939575},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5206100940704346},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5087326169013977},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4676755368709564},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4309070110321045},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3518650531768799},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24581554532051086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21752139925956726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.100789874792099},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06261399388313293},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11265-008-0270-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11265-008-0270-y","pdf_url":null,"source":{"id":"https://openalex.org/S11258463","display_name":"Journal of Signal Processing Systems","issn_l":"1939-8018","issn":["1939-8018","1939-8115"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Signal Processing Systems","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":39,"referenced_works":["https://openalex.org/W113372867","https://openalex.org/W1492472380","https://openalex.org/W1506845741","https://openalex.org/W1553019137","https://openalex.org/W1573714593","https://openalex.org/W1601949013","https://openalex.org/W1616576116","https://openalex.org/W1647671624","https://openalex.org/W1822119045","https://openalex.org/W1941664561","https://openalex.org/W1946389870","https://openalex.org/W2005646337","https://openalex.org/W2005677600","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/W2104086170","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/W4238290165","https://openalex.org/W4285719527","https://openalex.org/W6633154970","https://openalex.org/W6634457518","https://openalex.org/W6638444108","https://openalex.org/W6681973738","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W1926736923","https://openalex.org/W2942177010"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
