{"id":"https://openalex.org/W3164753811","doi":"https://doi.org/10.3906/elk-2004-67","title":"A regular expression generator based on CSS selectors for efficient extractionfrom HTML pages","display_name":"A regular expression generator based on CSS selectors for efficient extractionfrom HTML pages","publication_year":2020,"publication_date":"2020-08-11","ids":{"openalex":"https://openalex.org/W3164753811","doi":"https://doi.org/10.3906/elk-2004-67","mag":"3164753811"},"language":"en","primary_location":{"id":"doi:10.3906/elk-2004-67","is_oa":true,"landing_page_url":"https://doi.org/10.3906/elk-2004-67","pdf_url":"https://journals.tubitak.gov.tr/cgi/viewcontent.cgi?article=1242&context=elektrik","source":{"id":"https://openalex.org/S32837994","display_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","issn_l":"1300-0632","issn":["1300-0632","1303-6203"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318422","host_organization_name":"Scientific and Technological Research Council of Turkey (TUBITAK)","host_organization_lineage":["https://openalex.org/P4310318422"],"host_organization_lineage_names":["Scientific and Technological Research Council of Turkey (TUBITAK)"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING &amp; COMPUTER SCIENCES","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://journals.tubitak.gov.tr/cgi/viewcontent.cgi?article=1242&context=elektrik","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078816512","display_name":"Erdin\u00e7 Uzun","orcid":"https://orcid.org/0000-0003-4351-2244"},"institutions":[{"id":"https://openalex.org/I125454184","display_name":"Nam\u0131k Kemal University","ror":"https://ror.org/01a0mk874","country_code":"TR","type":"education","lineage":["https://openalex.org/I125454184"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Erdin Uzun","raw_affiliation_strings":["Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey","Department of Computer Engineering, \u00c7orlu Faculty of Engineering, Tekirda\u011f Nam\u0131k Kemal University, Tekirda\u011f, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Engineering, \u00c7orlu Faculty of Engineering, Tekirda\u011f Nam\u0131k Kemal University, Tekirda\u011f, Turkey","institution_ids":["https://openalex.org/I125454184"]}]},{"author_position":"middle","author":{"id":null,"display_name":"E Uzun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Uzun","raw_affiliation_strings":["Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"H Agun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H Agun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"T Yerlikaya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T Yerlikaya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Ferrara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Ferrara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"P Meo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P Meo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"G Fiumara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G Fiumara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"R Baumgartner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Baumgartner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Q Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Q Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"M Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M Shao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"L Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"G Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"J Alarte","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J Alarte","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"J Silva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J Silva","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"S Tamarit","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Tamarit","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"K Suleman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K Suleman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"O Vechtomova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"O Vechtomova","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Uar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Uar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Uzun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Uzun","raw_affiliation_strings":["Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"P Tfekci","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P Tfekci","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Uzun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Uzun","raw_affiliation_strings":["Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"E Gner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Gner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Y Klaslan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Y Klaslan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"T Yerlikaya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T Yerlikaya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"H Agun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H Agun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Uzun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Uzun","raw_affiliation_strings":["Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"H Bulu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H Bulu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"A Doruk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A Doruk","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E zhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Uzun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Uzun","raw_affiliation_strings":["Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, orlu Faculty of Engineering, Tekirda Namk Kemal University, Tekirda, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"T Yerlikaya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T Yerlikaya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"O Krat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"O Krat","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"A Bartoli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A Bartoli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"G Davanzo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G Davanzo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"A Lorenzo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A Lorenzo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Medvet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Medvet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Sorio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Sorio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"A Bartoli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A Bartoli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"D Lorenzo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D Lorenzo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Medvet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Medvet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"F Tarlao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F Tarlao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"N Kushman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N Kushman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"R Barzilay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Barzilay","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"N Locascio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N Locascio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"K Narasimhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K Narasimhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Leon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Leon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"N Kushman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N Kushman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"R Barzilay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Barzilay","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"C Flores","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C Flores","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"R Figueroa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Figueroa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"J Pezoa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J Pezoa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Q Zeng-Treitler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Q Zeng-Treitler","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"M Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M Cui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"R Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Bai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Z Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Z Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"X Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"X Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"U Aickelin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"U Aickelin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"S Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"L He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"S Vucetic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Vucetic","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Dragut","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Dragut","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"S Khalid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Khalid","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"S Khusro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Khusro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"I Ullah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I Ullah","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"R Fayzrakhmanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R Fayzrakhmanov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"E Sallinger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Sallinger","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"B Spencer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B Spencer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"T Furche","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T Furche","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"G Gottlob","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G Gottlob","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":70,"corresponding_author_ids":["https://openalex.org/A5078816512"],"corresponding_institution_ids":["https://openalex.org/I125454184"],"apc_list":null,"apc_paid":null,"fwci":1.3345,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87086563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"28","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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":0.9986000061035156,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9564999938011169,"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/T12799","display_name":"Mobile and Web Applications","score":0.9363999962806702,"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/regular-expression","display_name":"Regular expression","score":0.8448213338851929},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.8189587593078613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852686643600464},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6279191374778748},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5783453583717346},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5748996734619141},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5743399858474731},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.5595377683639526},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5589118003845215},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.47800126671791077},{"id":"https://openalex.org/keywords/cascading-style-sheets","display_name":"Cascading Style Sheets","score":0.47250425815582275},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4664698541164398},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4582047462463379},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4492899775505066},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4211437702178955},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3675425052642822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2580399513244629},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20966291427612305},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16107216477394104},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14425146579742432},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11793974041938782}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.8448213338851929},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.8189587593078613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852686643600464},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6279191374778748},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5783453583717346},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5748996734619141},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5743399858474731},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.5595377683639526},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5589118003845215},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.47800126671791077},{"id":"https://openalex.org/C93213560","wikidata":"https://www.wikidata.org/wiki/Q46441","display_name":"Cascading Style Sheets","level":3,"score":0.47250425815582275},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4664698541164398},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4582047462463379},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4492899775505066},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4211437702178955},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3675425052642822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2580399513244629},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20966291427612305},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16107216477394104},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14425146579742432},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11793974041938782},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3906/elk-2004-67","is_oa":true,"landing_page_url":"https://doi.org/10.3906/elk-2004-67","pdf_url":"https://journals.tubitak.gov.tr/cgi/viewcontent.cgi?article=1242&context=elektrik","source":{"id":"https://openalex.org/S32837994","display_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","issn_l":"1300-0632","issn":["1300-0632","1303-6203"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318422","host_organization_name":"Scientific and Technological Research Council of Turkey (TUBITAK)","host_organization_lineage":["https://openalex.org/P4310318422"],"host_organization_lineage_names":["Scientific and Technological Research Council of Turkey (TUBITAK)"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING &amp; COMPUTER SCIENCES","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3906/elk-2004-67","is_oa":true,"landing_page_url":"https://doi.org/10.3906/elk-2004-67","pdf_url":"https://journals.tubitak.gov.tr/cgi/viewcontent.cgi?article=1242&context=elektrik","source":{"id":"https://openalex.org/S32837994","display_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES","issn_l":"1300-0632","issn":["1300-0632","1303-6203"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318422","host_organization_name":"Scientific and Technological Research Council of Turkey (TUBITAK)","host_organization_lineage":["https://openalex.org/P4310318422"],"host_organization_lineage_names":["Scientific and Technological Research Council of Turkey (TUBITAK)"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TURKISH JOURNAL OF ELECTRICAL ENGINEERING &amp; COMPUTER SCIENCES","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3164753811.pdf","grobid_xml":"https://content.openalex.org/works/W3164753811.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1559557735","https://openalex.org/W1601674470","https://openalex.org/W1885684381","https://openalex.org/W2049488566","https://openalex.org/W2059383863","https://openalex.org/W2148317291","https://openalex.org/W2175619924","https://openalex.org/W2275294428","https://openalex.org/W2514393974","https://openalex.org/W2741613270","https://openalex.org/W2788315304","https://openalex.org/W2793853743","https://openalex.org/W2890881297","https://openalex.org/W2925629331","https://openalex.org/W2964284687","https://openalex.org/W2979602634","https://openalex.org/W3004838227","https://openalex.org/W4248891174"],"related_works":["https://openalex.org/W2151311386","https://openalex.org/W1563775010","https://openalex.org/W2992855911","https://openalex.org/W279807723","https://openalex.org/W2361898571","https://openalex.org/W2065605022","https://openalex.org/W3164753811","https://openalex.org/W2364692302","https://openalex.org/W11315421","https://openalex.org/W567182004"],"abstract_inverted_index":{"Cascading":[0],"style":[1],"sheets":[2],"(CSS)":[3],"selectors":[4,126],"are":[5,13,22,133],"patterns":[6,104,123,145],"used":[7],"to":[8,24,32,35,161,183,192],"select":[9],"HTML":[10,55,83],"elements.":[11],"They":[12],"often":[14],"preferred":[15],"in":[16,198],"web":[17,39,137],"data":[18,37],"extraction":[19,68,155,168],"because":[20],"they":[21],"easy":[23],"prepare":[25],"and":[26,66,75,85,129,196],"have":[27],"short":[28],"expressions.":[29],"In":[30,109],"order":[31],"be":[33,95,189],"able":[34],"extract":[36],"from":[38,158,170,180],"pages":[40],"by":[41,53,147],"using":[42,70],"these":[43,90,122],"patterns,":[44],"a":[45,58,98,106,112,136,171],"document":[46],"object":[47],"model":[48],"(DOM)":[49],"tree":[50,65,72],"is":[51,105,127],"constructed":[52],"an":[54],"parser":[56],"for":[57],"webpage.":[59],"The":[60,139],"construction":[61],"process":[62,69,169],"of":[63,82],"this":[64,71,110,148,199],"the":[67,80,153,167,175,193],"increase":[73],"time":[74,156],"memory":[76,177],"costs":[77],"depending":[78],"on":[79,135],"number":[81],"elements":[84],"their":[86],"hierarchies.":[87],"For":[88],"reducing":[89],"costs,":[91],"regular":[92,102,143],"expressions":[93],"can":[94,150,188],"considered":[96],"as":[97],"solution.":[99],"However,":[100],"preparing":[101],"expression":[103,144],"laborious":[107],"task.":[108,200],"study,":[111],"heuristic":[113],"approach,":[114],"namely":[115],"Regex":[116],"Generator":[117],"(REGEXN),":[118],"that":[119,142],"automatically":[120],"generates":[121],"through":[124],"CSS":[125],"introduced":[128],"th":[130],"eperformance":[131],"gains":[132],"analyzed":[134],"crawler.":[138],"analysis":[140],"shows":[141],"generated":[146],"approach":[149],"significantly":[151],"reduce":[152],"average":[154,176],"results":[157],"743.31":[159],"ms":[160,163],"1.03":[162],"when":[164],"compared":[165],"with":[166],"DOM":[172],"tree.":[173],"Similarly,":[174],"usage":[178],"drops":[179],"1054.01":[181],"B":[182],"1.59":[184],"B.":[185],"Moreover,":[186],"REGEXN":[187],"easily":[190],"adapted":[191],"existing":[194],"frameworks":[195],"tools":[197]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-01-09T06:25:30.743933","created_date":"2021-06-07T00:00:00"}
