{"id":"https://openalex.org/W2958977883","doi":"https://doi.org/10.1007/978-3-030-24268-8_26","title":"Research on Content Extraction of Rich Text Web Pages","display_name":"Research on Content Extraction of Rich Text Web Pages","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2958977883","doi":"https://doi.org/10.1007/978-3-030-24268-8_26","mag":"2958977883"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-24268-8_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-24268-8_26","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/A5018043618","display_name":"Hangfeng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangfeng Yang","raw_affiliation_strings":["Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486498","display_name":"Hui Lu","orcid":"https://orcid.org/0000-0002-4120-7716"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui Lu","raw_affiliation_strings":["Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043717671","display_name":"Shudong Li","orcid":"https://orcid.org/0000-0001-6381-1984"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shudong Li","raw_affiliation_strings":["Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100716223","display_name":"Mohan Li","orcid":"https://orcid.org/0000-0002-2290-046X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mohan Li","raw_affiliation_strings":["Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065867178","display_name":"Yanbin Sun","orcid":"https://orcid.org/0000-0002-8157-5337"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Sun","raw_affiliation_strings":["Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"Cyberspace Institute of Advance Technology, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101486498"],"corresponding_institution_ids":["https://openalex.org/I37987034"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.12695804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"279","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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":0.9983000159263611,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.96670001745224,"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/computer-science","display_name":"Computer science","score":0.8073725700378418},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.655748188495636},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.640436053276062},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6179772019386292},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5885198712348938},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5069756507873535},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5028385519981384},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.4956091642379761},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.46194061636924744},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.43762820959091187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42792871594429016},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.42788201570510864},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4254952073097229},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23858779668807983},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10394352674484253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09573414921760559}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073725700378418},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.655748188495636},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.640436053276062},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6179772019386292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5885198712348938},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5069756507873535},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5028385519981384},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.4956091642379761},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.46194061636924744},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43762820959091187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42792871594429016},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.42788201570510864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4254952073097229},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23858779668807983},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10394352674484253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09573414921760559},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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:10.1007/978-3-030-24268-8_26","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-24268-8_26","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":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2341078838","https://openalex.org/W2790718085","https://openalex.org/W2886320931","https://openalex.org/W2901014412","https://openalex.org/W2902007313","https://openalex.org/W2907556323","https://openalex.org/W2995820148"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W2131837571","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W1544491176","https://openalex.org/W2897171874","https://openalex.org/W2012575882","https://openalex.org/W2278505189","https://openalex.org/W1987716395"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
