{"id":"https://openalex.org/W188427339","doi":"https://doi.org/10.1007/978-3-540-24571-1_69","title":"EGA:An Algorithm for Automatic Semi-structured Web Documents Extraction","display_name":"EGA:An Algorithm for Automatic Semi-structured Web Documents Extraction","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W188427339","doi":"https://doi.org/10.1007/978-3-540-24571-1_69","mag":"188427339"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-24571-1_69","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-24571-1_69","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/A5014836771","display_name":"Liyu Li","orcid":"https://orcid.org/0000-0001-9082-3585"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyu Li","raw_affiliation_strings":["National Laboratory On Machine Perception, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory On Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036898908","display_name":"Shiwei Tang","orcid":"https://orcid.org/0000-0003-3124-0165"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwei Tang","raw_affiliation_strings":["Computer Science Department, Peking University, Beijing, China","National Laboratory On Machine Perception, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Laboratory On Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106446263","display_name":"Dongqing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongqing Yang","raw_affiliation_strings":["Computer Science Department, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115590373","display_name":"Tengjiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengjiao Wang","raw_affiliation_strings":["Computer Science Department, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055844500","display_name":"Zhihua Su","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Su","raw_affiliation_strings":["Computer Science Department, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.7166,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70188902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"787","last_page":"798"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9767000079154968,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9751999974250793,"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/xpath","display_name":"XPath","score":0.9075771570205688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8649947643280029},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6051632165908813},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5462498068809509},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4793192148208618},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.44925931096076965},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4352155029773712},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.43452364206314087},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41975873708724976},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3659082055091858},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.3143253028392792},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27963268756866455},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16328537464141846}],"concepts":[{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.9075771570205688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8649947643280029},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6051632165908813},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5462498068809509},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4793192148208618},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.44925931096076965},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4352155029773712},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.43452364206314087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41975873708724976},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3659082055091858},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.3143253028392792},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27963268756866455},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16328537464141846},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-540-24571-1_69","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-24571-1_69","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":16,"referenced_works":["https://openalex.org/W1546600388","https://openalex.org/W1554892943","https://openalex.org/W1616576116","https://openalex.org/W1927338256","https://openalex.org/W1969268549","https://openalex.org/W1999595522","https://openalex.org/W2005646337","https://openalex.org/W2053045757","https://openalex.org/W2085016361","https://openalex.org/W2104086170","https://openalex.org/W2135479443","https://openalex.org/W2148210463","https://openalex.org/W2160196229","https://openalex.org/W2163915185","https://openalex.org/W2521955871","https://openalex.org/W4229801762"],"related_works":["https://openalex.org/W1542110834","https://openalex.org/W1554870463","https://openalex.org/W2111274946","https://openalex.org/W151996191","https://openalex.org/W2083329789","https://openalex.org/W36911888","https://openalex.org/W2529247374","https://openalex.org/W2376574812","https://openalex.org/W4385731361","https://openalex.org/W1788528807"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
