{"id":"https://openalex.org/W2148317291","doi":"https://doi.org/10.1016/j.knosys.2014.07.007","title":"Web data extraction, applications and techniques: A survey","display_name":"Web data extraction, applications and techniques: A survey","publication_year":2014,"publication_date":"2014-07-24","ids":{"openalex":"https://openalex.org/W2148317291","doi":"https://doi.org/10.1016/j.knosys.2014.07.007","mag":"2148317291"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2014.07.007","doi":"https://doi.org/10.1016/j.knosys.2014.07.007","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2014.07.007","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-b","fnege-4","jufo-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1207.0246","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078699564","display_name":"Emilio Ferrara","orcid":"https://orcid.org/0000-0002-1942-2831","observed_orcids":["https://orcid.org/0000-0002-1942-2831"]},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Emilio Ferrara","raw_affiliation_strings":["Center for Complex Networks and Systems Research, Indiana University, Bloomington, IN 47408, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Complex Networks and Systems Research, Indiana University, Bloomington, IN 47408, USA","institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018975350","display_name":"Pasquale De Meo","orcid":"https://orcid.org/0000-0001-7421-216X","observed_orcids":["https://orcid.org/0000-0001-7421-216X"]},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pasquale De Meo","raw_affiliation_strings":["Univ. of Messina, Dept. of Ancient and Modern Civilization, Polo Annunziata, I-98166 Messina, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Messina, Dept. of Ancient and Modern Civilization, Polo Annunziata, I-98166 Messina, Italy","institution_ids":["https://openalex.org/I112862951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079151275","display_name":"Giacomo Fiumara","orcid":"https://orcid.org/0000-0003-1528-7203","observed_orcids":["https://orcid.org/0000-0003-1528-7203"]},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giacomo Fiumara","raw_affiliation_strings":["Univ. of Messina, Dept. of Mathematics and Informatics, viale F. Stagno D\u2019Alcontres 31, I-98166 Messina, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Messina, Dept. of Mathematics and Informatics, viale F. Stagno D\u2019Alcontres 31, I-98166 Messina, Italy","institution_ids":["https://openalex.org/I112862951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055923468","display_name":"Robert Baumgartner","orcid":"https://orcid.org/0000-0003-0899-4903","observed_orcids":["https://orcid.org/0000-0003-0899-4903"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Baumgartner","raw_affiliation_strings":["Lixto Software GmbH, Favoritenstra\u00dfe 16, 1040 Wien, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lixto Software GmbH, Favoritenstra\u00dfe 16, 1040 Wien, Austria","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078699564"],"corresponding_institution_ids":["https://openalex.org/I4210119109","https://openalex.org/I592451"],"apc_list":{"value":3430,"currency":"USD","value_usd":3430},"apc_paid":null,"fwci":116.003,"has_fulltext":false,"cited_by_count":397,"citation_normalized_percentile":{"value":0.99968159,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"70","issue":null,"first_page":"301","last_page":"323"},"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/T14435","display_name":"Information Retrieval and Data Mining","score":0.0,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/web-scraping","display_name":"web scraping","score":0.968999981880188},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.9380000233650208},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"business intelligence","score":0.7210000157356262},{"id":"https://openalex.org/keywords/competitive-intelligence","display_name":"competitive intelligence","score":0.9959999918937683},{"id":"https://openalex.org/keywords/business-process-reengineering","display_name":"business process reengineering","score":0.9819999933242798},{"id":"https://openalex.org/keywords/social-media-data","display_name":"social media data","score":0.7009999752044678},{"id":"https://openalex.org/keywords/web-2-0","display_name":"Web 2.0","score":0.9259999990463257},{"id":"https://openalex.org/keywords/online-social-networks","display_name":"social networking sites","score":0.7879999876022339},{"id":"https://openalex.org/keywords/human-behavior-analysis","display_name":"human behavior analysis","score":0.7739999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553274631500244},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.6229146122932434},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.6171990036964417},{"id":"https://openalex.org/C97200028","wikidata":"https://www.wikidata.org/wiki/Q1196135","display_name":"Web engineering","level":5,"score":0.5809718370437622},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5112002491950989},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.509538471698761},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4882490932941437},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4495497941970825},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4315636157989502},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.3702598810195923},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1016/j.knosys.2014.07.007","doi":"https://doi.org/10.1016/j.knosys.2014.07.007","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2014.07.007","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-b","fnege-4","jufo-2","norway-2","poland-200","russia-white-list-1","vabb-shw"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1207.0246","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1207.0246","pdf_url":"https://arxiv.org/pdf/1207.0246","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.747.8354","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.747.8354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1207.0246.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.958.729","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.958.729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://giacomofiumara.altervista.org/pubblicazioni/ur02.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1207.0246","doi":"https://doi.org/10.48550/arxiv.1207.0246","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1207.0246","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1207.0246","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1207.0246","pdf_url":"https://arxiv.org/pdf/1207.0246","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":154,"referenced_works":["https://openalex.org/W11750719","https://openalex.org/W25706487","https://openalex.org/W46452414","https://openalex.org/W48123735","https://openalex.org/W56723464","https://openalex.org/W74181463","https://openalex.org/W77717277","https://openalex.org/W130296414","https://openalex.org/W141724566","https://openalex.org/W143867266","https://openalex.org/W185754135","https://openalex.org/W202809283","https://openalex.org/W259338706","https://openalex.org/W286387202","https://openalex.org/W836144344","https://openalex.org/W1491318189","https://openalex.org/W1494823533","https://openalex.org/W1496564895","https://openalex.org/W1547917241","https://openalex.org/W1553019137","https://openalex.org/W1567298333","https://openalex.org/W1569908913","https://openalex.org/W1573579329","https://openalex.org/W1574901103","https://openalex.org/W1592633451","https://openalex.org/W1600645063","https://openalex.org/W1600978165","https://openalex.org/W1602242617","https://openalex.org/W1602270052","https://openalex.org/W1610496399","https://openalex.org/W1766968125","https://openalex.org/W1767117126","https://openalex.org/W1927338256","https://openalex.org/W1964521983","https://openalex.org/W1965685479","https://openalex.org/W1966355874","https://openalex.org/W1968130046","https://openalex.org/W1973846084","https://openalex.org/W1975185960","https://openalex.org/W1975419194","https://openalex.org/W1983728141","https://openalex.org/W1984625874","https://openalex.org/W1989134410","https://openalex.org/W1990117407","https://openalex.org/W1999509537","https://openalex.org/W2002956097","https://openalex.org/W2003581263","https://openalex.org/W2005646337","https://openalex.org/W2005814556","https://openalex.org/W2008896880","https://openalex.org/W2016589434","https://openalex.org/W2024665458","https://openalex.org/W2028993035","https://openalex.org/W2029396209","https://openalex.org/W2030908643","https://openalex.org/W2035015991","https://openalex.org/W2038734451","https://openalex.org/W2042359627","https://openalex.org/W2047443612","https://openalex.org/W2048001624","https://openalex.org/W2049461910","https://openalex.org/W2050707999","https://openalex.org/W2051575094","https://openalex.org/W2057294899","https://openalex.org/W2064682298","https://openalex.org/W2065568440","https://openalex.org/W2067416210","https://openalex.org/W2069692868","https://openalex.org/W2070632872","https://openalex.org/W2080132606","https://openalex.org/W2082413760","https://openalex.org/W2083413555","https://openalex.org/W2085533860","https://openalex.org/W2086627840","https://openalex.org/W2094526067","https://openalex.org/W2096175520","https://openalex.org/W2096700076","https://openalex.org/W2098344513","https://openalex.org/W2101196063","https://openalex.org/W2101843930","https://openalex.org/W2102189859","https://openalex.org/W2102694093","https://openalex.org/W2102720960","https://openalex.org/W2103388840","https://openalex.org/W2104086170","https://openalex.org/W2107286848","https://openalex.org/W2108730513","https://openalex.org/W2109584946","https://openalex.org/W2110882317","https://openalex.org/W2111023939","https://openalex.org/W2113839561","https://openalex.org/W2114452345","https://openalex.org/W2115022330","https://openalex.org/W2115023510","https://openalex.org/W2118020653","https://openalex.org/W2118338035","https://openalex.org/W2119577990","https://openalex.org/W2120101509","https://openalex.org/W2120736575","https://openalex.org/W2122750868","https://openalex.org/W2124157324","https://openalex.org/W2125570474","https://openalex.org/W2128678576","https://openalex.org/W2129595335","https://openalex.org/W2131150402","https://openalex.org/W2132381269","https://openalex.org/W2134150392","https://openalex.org/W2135479443","https://openalex.org/W2137135938","https://openalex.org/W2137235842","https://openalex.org/W2138731074","https://openalex.org/W2140190241","https://openalex.org/W2143286114","https://openalex.org/W2143309843","https://openalex.org/W2143349571","https://openalex.org/W2143513829","https://openalex.org/W2148210463","https://openalex.org/W2148242152","https://openalex.org/W2148606196","https://openalex.org/W2151378814","https://openalex.org/W2152608246","https://openalex.org/W2153072229","https://openalex.org/W2153837623","https://openalex.org/W2154444297","https://openalex.org/W2157140910","https://openalex.org/W2162340487","https://openalex.org/W2162858242","https://openalex.org/W2163915185","https://openalex.org/W2165424625","https://openalex.org/W2165698076","https://openalex.org/W2166531833","https://openalex.org/W2167699886","https://openalex.org/W2168358004","https://openalex.org/W2169262681","https://openalex.org/W2170379762","https://openalex.org/W2170541679","https://openalex.org/W2279779665","https://openalex.org/W2303615896","https://openalex.org/W2421105961","https://openalex.org/W2497068810","https://openalex.org/W2543315719","https://openalex.org/W2913389685","https://openalex.org/W3104624354","https://openalex.org/W3105126546","https://openalex.org/W3105369876","https://openalex.org/W4213074579","https://openalex.org/W4232987262","https://openalex.org/W4250860020","https://openalex.org/W4256152203","https://openalex.org/W4285719527","https://openalex.org/W6605756948","https://openalex.org/W6635982700","https://openalex.org/W6647075091","https://openalex.org/W6680347370"],"related_works":["https://openalex.org/W2792695632","https://openalex.org/W2100071482","https://openalex.org/W2187012497","https://openalex.org/W2945931694","https://openalex.org/W2729360854","https://openalex.org/W1583761149","https://openalex.org/W2181420802","https://openalex.org/W2518065836","https://openalex.org/W1861234877","https://openalex.org/W3127569824"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":50},{"year":2017,"cited_by_count":44},{"year":2016,"cited_by_count":37},{"year":2015,"cited_by_count":35},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":5}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}