{"id":"https://openalex.org/W4386142179","doi":"https://doi.org/10.1007/s00500-023-09076-x","title":"An efficient content extraction method for webpage based on tag-line-block analysis","display_name":"An efficient content extraction method for webpage based on tag-line-block analysis","publication_year":2023,"publication_date":"2023-08-24","ids":{"openalex":"https://openalex.org/W4386142179","doi":"https://doi.org/10.1007/s00500-023-09076-x"},"language":"en","primary_location":{"id":"doi:10.1007/s00500-023-09076-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00500-023-09076-x","pdf_url":null,"source":{"id":"https://openalex.org/S65753830","display_name":"Soft Computing","issn_l":"1432-7643","issn":["1432-7643","1433-7479"],"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":"Soft Computing","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/A5058976164","display_name":"Zeqiu Chen","orcid":"https://orcid.org/0000-0003-3774-7354"},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeqiu Chen","raw_affiliation_strings":["College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051999669","display_name":"Jianghui Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghui Zhou","raw_affiliation_strings":["JD Tech, Beijing, 100176, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Tech, Beijing, 100176, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034701679","display_name":"Ruizhi Sun","orcid":"https://orcid.org/0000-0001-7267-5283"},"institutions":[{"id":"https://openalex.org/I4210117733","display_name":"National Animal Husbandry Service","ror":"https://ror.org/022ekqa73","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210117733","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruizhi Sun","raw_affiliation_strings":["College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China","Scientific Research Base for Integrated Technologies of Precision Agriculture (Animal Husbandry), The Ministry of Agriculture, Beijing, 100083, China"],"raw_orcid":"https://orcid.org/0000-0001-7267-5283","affiliations":[{"raw_affiliation_string":"College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China","institution_ids":["https://openalex.org/I52158045"]},{"raw_affiliation_string":"Scientific Research Base for Integrated Technologies of Precision Agriculture (Animal Husbandry), The Ministry of Agriculture, Beijing, 100083, China","institution_ids":["https://openalex.org/I4210117733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034701679"],"corresponding_institution_ids":["https://openalex.org/I4210117733","https://openalex.org/I52158045"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.4379,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68878202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"27","issue":"20","first_page":"14631","last_page":"14645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9233999848365784,"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-page","display_name":"Web page","score":0.8511462211608887},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.7682012319564819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7374459505081177},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6181852221488953},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5201606750488281},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5028090476989746},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.44873812794685364},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4471384882926941},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44460174441337585},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.42255327105522156},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.41840702295303345},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40937966108322144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13830304145812988},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1122359037399292}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8511462211608887},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.7682012319564819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7374459505081177},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6181852221488953},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5201606750488281},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5028090476989746},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.44873812794685364},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4471384882926941},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44460174441337585},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.42255327105522156},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.41840702295303345},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40937966108322144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13830304145812988},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1122359037399292},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00500-023-09076-x","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00500-023-09076-x","pdf_url":null,"source":{"id":"https://openalex.org/S65753830","display_name":"Soft Computing","issn_l":"1432-7643","issn":["1432-7643","1433-7479"],"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":"Soft Computing","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":23,"referenced_works":["https://openalex.org/W1566513354","https://openalex.org/W1927338256","https://openalex.org/W1968948072","https://openalex.org/W1975700640","https://openalex.org/W1992657934","https://openalex.org/W2012575882","https://openalex.org/W2019577381","https://openalex.org/W2055383559","https://openalex.org/W2103725015","https://openalex.org/W2117209866","https://openalex.org/W2136072238","https://openalex.org/W2148317291","https://openalex.org/W2158051716","https://openalex.org/W2253768319","https://openalex.org/W2346652761","https://openalex.org/W2742989468","https://openalex.org/W2898301985","https://openalex.org/W2933151537","https://openalex.org/W2979460445","https://openalex.org/W2981630306","https://openalex.org/W4221167659","https://openalex.org/W4367046663","https://openalex.org/W4377089836"],"related_works":["https://openalex.org/W2245616560","https://openalex.org/W2351804282","https://openalex.org/W2048998278","https://openalex.org/W1556894713","https://openalex.org/W2382071381","https://openalex.org/W1490416172","https://openalex.org/W158130761","https://openalex.org/W2588706232","https://openalex.org/W2096877906","https://openalex.org/W2228146393"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
