{"id":"https://openalex.org/W4416649875","doi":"https://doi.org/10.1109/access.2025.3636662","title":"Web Scraping by End Users","display_name":"Web Scraping by End Users","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416649875","doi":"https://doi.org/10.1109/access.2025.3636662"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3636662","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3636662","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3636662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002098205","display_name":"Alex Tacuri","orcid":"https://orcid.org/0000-0003-3159-5556"},"institutions":[{"id":"https://openalex.org/I874386039","display_name":"Universidad Nacional de La Plata","ror":"https://ror.org/01tjs6929","country_code":"AR","type":"education","lineage":["https://openalex.org/I874386039"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Alex Tacuri","raw_affiliation_strings":["LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina"],"raw_orcid":"https://orcid.org/0000-0003-3159-5556","affiliations":[{"raw_affiliation_string":"LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I874386039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079684317","display_name":"S\u00e9rgio Firmenich","orcid":"https://orcid.org/0000-0001-9502-2189"},"institutions":[{"id":"https://openalex.org/I243381257","display_name":"Universidad Loyola Andaluc\u00eda","ror":"https://ror.org/0075gfd51","country_code":"ES","type":"education","lineage":["https://openalex.org/I243381257"]},{"id":"https://openalex.org/I4210107451","display_name":"Universidad Loyola","ror":"https://ror.org/01wfnf418","country_code":"BO","type":"education","lineage":["https://openalex.org/I4210107451"]}],"countries":["BO","ES"],"is_corresponding":false,"raw_author_name":"Sergio Firmenich","raw_affiliation_strings":["Universidad Loyola Andaluc&#x00ED;a, Dos Hermanas, Sevilla Espa\u00f1a, Spain","Universidad Loyola Andaluc&#x00ED;a, Espa&#x00F1;a"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Loyola Andaluc&#x00ED;a, Dos Hermanas, Sevilla Espa\u00f1a, Spain","institution_ids":["https://openalex.org/I243381257"]},{"raw_affiliation_string":"Universidad Loyola Andaluc&#x00ED;a, Espa&#x00F1;a","institution_ids":["https://openalex.org/I4210107451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675385","display_name":"Alejandro Fern\u00e1ndez","orcid":"https://orcid.org/0000-0002-7968-6871"},"institutions":[{"id":"https://openalex.org/I874386039","display_name":"Universidad Nacional de La Plata","ror":"https://ror.org/01tjs6929","country_code":"AR","type":"education","lineage":["https://openalex.org/I874386039"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Alejandro Fern\u00e1ndez","raw_affiliation_strings":["LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina"],"raw_orcid":"https://orcid.org/0000-0002-7968-6871","affiliations":[{"raw_affiliation_string":"LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I874386039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103160866","display_name":"Mar\u00eda Florencia Riva","orcid":"https://orcid.org/0009-0007-0607-9855"},"institutions":[{"id":"https://openalex.org/I874386039","display_name":"Universidad Nacional de La Plata","ror":"https://ror.org/01tjs6929","country_code":"AR","type":"education","lineage":["https://openalex.org/I874386039"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Florencia Riva","raw_affiliation_strings":["LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina"],"raw_orcid":"https://orcid.org/0009-0007-0607-9855","affiliations":[{"raw_affiliation_string":"LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I874386039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091483607","display_name":"Mat\u00edas Urbieta","orcid":"https://orcid.org/0000-0002-4508-1209"},"institutions":[{"id":"https://openalex.org/I874386039","display_name":"Universidad Nacional de La Plata","ror":"https://ror.org/01tjs6929","country_code":"AR","type":"education","lineage":["https://openalex.org/I874386039"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Mat\u00edas Urbieta","raw_affiliation_strings":["LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I874386039"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016635868","display_name":"Gustavo Rossi","orcid":"https://orcid.org/0000-0002-3348-2144"},"institutions":[{"id":"https://openalex.org/I874386039","display_name":"Universidad Nacional de La Plata","ror":"https://ror.org/01tjs6929","country_code":"AR","type":"education","lineage":["https://openalex.org/I874386039"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Gustavo Rossi","raw_affiliation_strings":["LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina"],"raw_orcid":"https://orcid.org/0000-0002-3348-2144","affiliations":[{"raw_affiliation_string":"LIFIA, Facultad de Inform&#x00E1;tica, UNLP, La Plata, Buenos Aires, Argentina","institution_ids":["https://openalex.org/I874386039"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45956497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"205027","last_page":"205044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9016000032424927,"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":0.9016000032424927,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.052400000393390656,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.007699999958276749,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/disk-formatting","display_name":"Disk formatting","score":0.8039000034332275},{"id":"https://openalex.org/keywords/scraper-site","display_name":"Scraper site","score":0.6313999891281128},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5849000215530396},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.45969998836517334},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.43130001425743103},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3905999958515167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400999903678894},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.8039000034332275},{"id":"https://openalex.org/C78500136","wikidata":"https://www.wikidata.org/wiki/Q477840","display_name":"Scraper site","level":2,"score":0.6313999891281128},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5849000215530396},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C196126337","wikidata":"https://www.wikidata.org/wiki/Q821080","display_name":"Mashup","level":4,"score":0.3725000023841858},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C61871575","wikidata":"https://www.wikidata.org/wiki/Q384093","display_name":"Master data","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3116999864578247},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3636662","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3636662","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:digital.cic.gba.gob.ar:11746/12582","is_oa":true,"landing_page_url":"https://digital.cic.gba.gob.ar/handle/11746/12582","pdf_url":null,"source":{"id":"https://openalex.org/S4306400034","display_name":"CIC-Digital (Comisi\u00f3n de Investigaciones Cient\u00edficas de la Provincia de Buenos Aires)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:doaj.org/article:a18e2caa89ba4bfab411e6f2e1658842","is_oa":true,"landing_page_url":"https://doaj.org/article/a18e2caa89ba4bfab411e6f2e1658842","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 205027-205044 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3636662","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3636662","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8466661399","display_name":null,"funder_award_id":"PICT-2020-SERIEA-03378","funder_id":"https://openalex.org/F4320337954","funder_display_name":"Fondo para la Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica"}],"funders":[{"id":"https://openalex.org/F4320337954","display_name":"Fondo para la Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica","ror":"https://ror.org/03stxzb56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1966200370","https://openalex.org/W1984315811","https://openalex.org/W2032191478","https://openalex.org/W2102480769","https://openalex.org/W2123354009","https://openalex.org/W2573020254","https://openalex.org/W2622958941","https://openalex.org/W2896298055","https://openalex.org/W2942408928","https://openalex.org/W3008479101","https://openalex.org/W3029176653","https://openalex.org/W3041432933","https://openalex.org/W3042406079","https://openalex.org/W3047468310","https://openalex.org/W3099440908","https://openalex.org/W3139145837","https://openalex.org/W3155276557","https://openalex.org/W3212041623","https://openalex.org/W4200146754","https://openalex.org/W4220701925","https://openalex.org/W4232721352","https://openalex.org/W4291213652","https://openalex.org/W4311410900","https://openalex.org/W4318261469","https://openalex.org/W4327927559","https://openalex.org/W4367856231","https://openalex.org/W4384832219","https://openalex.org/W4388041793","https://openalex.org/W4404781305","https://openalex.org/W4410300348","https://openalex.org/W4414075780"],"related_works":[],"abstract_inverted_index":{"Scraping":[0],"is":[1,52,95],"a":[2,14,96],"topic":[3],"studied":[4],"from":[5,47,57,147],"various":[6],"perspectives,":[7],"encompassing":[8],"automatic":[9],"and":[10,13,42,86,117,125,153,165,171,185,189],"AI-based":[11,92],"approaches,":[12],"wide":[15],"range":[16],"of":[17,26,99,173],"programming":[18,84],"libraries":[19],"that":[20,101,141],"expedite":[21],"development.":[22],"As":[23],"the":[24,48,110,119,168,177],"volume":[25],"available":[27],"web":[28,181],"content":[29],"increases,":[30],"it":[31],"becomes":[32],"increasingly":[33],"challenging":[34,88],"to":[35,44,80,89,159],"anticipate":[36],"end-user":[37,136],"requirements":[38],"regarding":[39],"what,":[40],"how,":[41],"when":[43,54,61],"extract":[45],"data":[46,56,68,120,146],"web.":[49],"This":[50],"challenge":[51],"compounded":[53],"integrating":[55,145],"multiple":[58,148],"websites,":[59],"particularly":[60],"websites\u2019":[62],"search":[63],"engines":[64],"dynamically":[65],"retrieve":[66],"unavailable":[67],"via":[69],"permanent":[70],"links.":[71],"Complex":[72],"scraping":[73],"processes,":[74],"such":[75],"as":[76],"these":[77],"are":[78,87,121],"difficult":[79],"develop":[81],"using":[82],"general-purpose":[83],"languages":[85],"automate":[90],"with":[91,162],"approaches.":[93],"Controllability":[94],"crucial":[97],"aspect":[98],"scraping,":[100],"is,":[102],"how":[103,118],"end":[104],"users":[105,161],"can":[106],"make":[107],"decisions":[108],"during":[109],"scraper":[111],"specification":[112],"process,":[113],"understand":[114],"information":[115],"sources,":[116],"ultimately":[122],"extracted,":[123],"compiled,":[124],"formatted":[126],"for":[127,138],"output.":[128],"In":[129],"response,":[130],"our":[131],"study":[132],"presents":[133],"an":[134],"innovative":[135],"approach":[137,152,184],"specifying":[139],"scrapers":[140],"focuses":[142],"on":[143],"seamlessly":[144],"sources.":[149],"Through":[150],"this":[151],"its":[154],"supporting":[155],"toolset,":[156],"we":[157],"aim":[158],"provide":[160],"greater":[163],"control":[164],"transparency":[166],"over":[167],"extraction,":[169],"integration,":[170],"formatting":[172],"data,":[174],"thereby":[175],"addressing":[176],"key":[178],"concerns":[179],"in":[180],"scraping.":[182],"The":[183],"toolset":[186],"were":[187],"evaluated":[188],"they":[190],"yielded":[191],"promising":[192],"results.":[193]},"counts_by_year":[],"updated_date":"2025-12-11T00:21:10.989143","created_date":"2025-11-25T00:00:00"}
