{"id":"https://openalex.org/W2897171874","doi":"https://doi.org/10.1007/978-3-030-02922-7_27","title":"Main Content Extraction from Heterogeneous Webpages","display_name":"Main Content Extraction from Heterogeneous Webpages","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2897171874","doi":"https://doi.org/10.1007/978-3-030-02922-7_27","mag":"2897171874"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-02922-7_27","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-02922-7_27","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5060938121","display_name":"Juli\u00e1n Alarte","orcid":"https://orcid.org/0009-0006-9825-3066"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Julian Alarte","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071216572","display_name":"David Insa","orcid":null},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Insa","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003503212","display_name":"Josep Silva","orcid":"https://orcid.org/0000-0001-5096-0008"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josep Silva","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016645788","display_name":"Salvador Tamarit","orcid":"https://orcid.org/0000-0001-5103-4153"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Salvador Tamarit","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Cam\u00ed de Vera s/n, 46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060938121"],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.9469,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77296676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"407"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9506000280380249,"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"}},{"id":"https://openalex.org/T13976","display_name":"Web visibility and informetrics","score":0.9273999929428101,"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":0.883189857006073},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8174340724945068},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7893607020378113},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.7311103343963623},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.7080986499786377},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6760752201080322},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5832436680793762},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.5578528046607971},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5446767210960388},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4803113341331482},{"id":"https://openalex.org/keywords/mashup","display_name":"Mashup","score":0.4316314458847046},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42678138613700867},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.426461786031723},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4210919141769409},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4162939190864563},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2603853940963745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883189857006073},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8174340724945068},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7893607020378113},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.7311103343963623},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.7080986499786377},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6760752201080322},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5832436680793762},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.5578528046607971},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5446767210960388},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4803113341331482},{"id":"https://openalex.org/C196126337","wikidata":"https://www.wikidata.org/wiki/Q821080","display_name":"Mashup","level":4,"score":0.4316314458847046},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42678138613700867},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.426461786031723},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4210919141769409},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4162939190864563},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2603853940963745},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-02922-7_27","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-02922-7_27","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W15548","https://openalex.org/W1975700640","https://openalex.org/W1989338554","https://openalex.org/W2019441211","https://openalex.org/W2019577381","https://openalex.org/W2040075907","https://openalex.org/W2042970189","https://openalex.org/W2045986835","https://openalex.org/W2048192672","https://openalex.org/W2072489225","https://openalex.org/W2084358158","https://openalex.org/W2093907956","https://openalex.org/W2097705449","https://openalex.org/W2117694587","https://openalex.org/W2120101509","https://openalex.org/W2129595335","https://openalex.org/W2140208587","https://openalex.org/W2151588647","https://openalex.org/W2157027287","https://openalex.org/W2164565864","https://openalex.org/W2201534957","https://openalex.org/W2476847310","https://openalex.org/W3141179560","https://openalex.org/W3154772965"],"related_works":["https://openalex.org/W2065605022","https://openalex.org/W3183046488","https://openalex.org/W2367158473","https://openalex.org/W2363029778","https://openalex.org/W2063800210","https://openalex.org/W2374762067","https://openalex.org/W2897171874","https://openalex.org/W2372091777","https://openalex.org/W2369251627","https://openalex.org/W2353601037"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
