{"id":"https://openalex.org/W2168573064","doi":"https://doi.org/10.1016/s0306-4379(01)00040-0","title":"An XML-enabled data extraction toolkit for web sources","display_name":"An XML-enabled data extraction toolkit for web sources","publication_year":2001,"publication_date":"2001-12-01","ids":{"openalex":"https://openalex.org/W2168573064","doi":"https://doi.org/10.1016/s0306-4379(01)00040-0","mag":"2168573064"},"language":"en","primary_location":{"id":"doi:10.1016/s0306-4379(01)00040-0","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4379(01)00040-0","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","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/A5100343991","display_name":"Ling Liu","orcid":"https://orcid.org/0000-0002-4138-3082"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ling Liu","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081442372","display_name":"Calton Pu","orcid":"https://orcid.org/0000-0002-6616-8987"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calton Pu","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100898103","display_name":"Wei Han","orcid":"https://orcid.org/0009-0006-4921-2399"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100343991"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":2970,"currency":"USD","value_usd":2970},"apc_paid":null,"fwci":5.104,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.96035546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"26","issue":"8","first_page":"563","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9882000088691711,"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":0.9004859328269958},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5687891840934753},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.537074089050293},{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.5350566506385803},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5273562073707581},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.45968103408813477},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.44936832785606384},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.44592535495758057},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.42801207304000854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9004859328269958},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5687891840934753},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.537074089050293},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.5350566506385803},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5273562073707581},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45968103408813477},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.44936832785606384},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.44592535495758057},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.42801207304000854}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/s0306-4379(01)00040-0","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4379(01)00040-0","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W33041674","https://openalex.org/W180117042","https://openalex.org/W1534002024","https://openalex.org/W1544205754","https://openalex.org/W1553019137","https://openalex.org/W1560626952","https://openalex.org/W1638026557","https://openalex.org/W1927338256","https://openalex.org/W1966200370","https://openalex.org/W1990117407","https://openalex.org/W2003981282","https://openalex.org/W2026080185","https://openalex.org/W2048845959","https://openalex.org/W2083317499","https://openalex.org/W2087060113","https://openalex.org/W2097432384","https://openalex.org/W2109660182","https://openalex.org/W2123718938","https://openalex.org/W2128836931","https://openalex.org/W2131165428","https://openalex.org/W2137096228","https://openalex.org/W2140327372","https://openalex.org/W2145404631","https://openalex.org/W2147100344","https://openalex.org/W2149532506","https://openalex.org/W2163126391","https://openalex.org/W2164235596","https://openalex.org/W2198176844","https://openalex.org/W4255502538","https://openalex.org/W6627914615"],"related_works":["https://openalex.org/W2097396510","https://openalex.org/W1554870463","https://openalex.org/W2111274946","https://openalex.org/W169802313","https://openalex.org/W2601954520","https://openalex.org/W1494225641","https://openalex.org/W2087121382","https://openalex.org/W2597540929","https://openalex.org/W1557539681","https://openalex.org/W207633616"],"abstract_inverted_index":null,"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
