{"id":"https://openalex.org/W4387924929","doi":"https://doi.org/10.1016/j.softx.2023.101569","title":"WebCollectives: A light regular expression based web content extractor in Java","display_name":"WebCollectives: A light regular expression based web content extractor in Java","publication_year":2023,"publication_date":"2023-10-24","ids":{"openalex":"https://openalex.org/W4387924929","doi":"https://doi.org/10.1016/j.softx.2023.101569"},"language":"en","primary_location":{"id":"doi:10.1016/j.softx.2023.101569","doi":"https://doi.org/10.1016/j.softx.2023.101569","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2023.101569","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-200","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"volume":null,"type":"software-paper","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.softx.2023.101569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078860359","display_name":"Hayri Volkan Agun","orcid":"https://orcid.org/0000-0002-4253-8920","observed_orcids":["https://orcid.org/0000-0002-4253-8920"]},"institutions":[{"id":"https://openalex.org/I192257213","display_name":"Bursa Technical University","ror":"https://ror.org/03rdpn141","country_code":"TR","type":"education","lineage":["https://openalex.org/I192257213"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Hayri Volkan Agun","raw_affiliation_strings":["Bursa Technical University, Bursa, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-4253-8920","affiliations":[{"raw_affiliation_string":"Bursa Technical University, Bursa, Turkey","institution_ids":["https://openalex.org/I192257213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078860359"],"corresponding_institution_ids":["https://openalex.org/I192257213"],"apc_list":{"value":760,"currency":"USD","value_usd":760},"apc_paid":{"value":760,"currency":"USD","value_usd":760},"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"101569","last_page":"101569"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"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/T14435","display_name":"Information Retrieval and Data Mining","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawling","display_name":"web crawling","score":0.9039999842643738},{"id":"https://openalex.org/keywords/web-content-extraction","display_name":"web content extraction","score":0.9829999804496765},{"id":"https://openalex.org/keywords/regular-expressions","display_name":"regular expressions","score":0.8650000095367432},{"id":"https://openalex.org/keywords/link-extraction","display_name":"link extraction","score":0.949999988079071},{"id":"https://openalex.org/keywords/selenium","display_name":"selenium","score":0.800000011920929},{"id":"https://openalex.org/keywords/xml-generation","display_name":"XML generation","score":0.4650000035762787},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464533090591431},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.7157260179519653},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.6108261942863464},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5608883500099182},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5354300737380981},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.4823307693004608},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4678764045238495},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.46031686663627625},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44630712270736694},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.41410428285598755},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.408353716135025},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34764331579208374},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2841643691062927},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/j.softx.2023.101569","doi":"https://doi.org/10.1016/j.softx.2023.101569","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2023.101569","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-200","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},{"id":"doi:10.2139/ssrn.4480037","doi":"https://doi.org/10.2139/ssrn.4480037","is_oa":true,"landing_page_url":"https://doi.org/10.2139/ssrn.4480037","pdf_url":null,"source":{"id":"https://openalex.org/S4210172589","display_name":"SSRN Electronic Journal","issn_l":"1556-5068","issn":["1556-5068"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1318003438","host_organization_name":"RELX Group (Netherlands)","host_organization_lineage":["https://openalex.org/I1318003438"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:acikerisim.btu.edu.tr:20.500.12885/7084","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.12885/7084","pdf_url":null,"source":{"id":"https://openalex.org/S7407055330","display_name":"Bursa Technical University Institutional Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:148e0ad744fe452fb44a6ea9a400fd17","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/148e0ad744fe452fb44a6ea9a400fd17","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,"listed_in":[],"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":"SoftwareX, Vol 24, Iss , Pp 101569- (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.softx.2023.101569","doi":"https://doi.org/10.1016/j.softx.2023.101569","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2023.101569","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","norway-1","poland-200","vabb-shw"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1501777393","https://openalex.org/W1559557735","https://openalex.org/W2120101509","https://openalex.org/W2123354009","https://openalex.org/W2208078047","https://openalex.org/W2246090375","https://openalex.org/W2594899909","https://openalex.org/W2741613270","https://openalex.org/W2743928556","https://openalex.org/W2782975741","https://openalex.org/W2942159279","https://openalex.org/W2956482477","https://openalex.org/W2964016568","https://openalex.org/W3006281832","https://openalex.org/W3008479101","https://openalex.org/W3014183340","https://openalex.org/W3202059926","https://openalex.org/W4200146754","https://openalex.org/W4242482041","https://openalex.org/W4296341474","https://openalex.org/W4316042130","https://openalex.org/W4327927559","https://openalex.org/W4375853925","https://openalex.org/W4385166326","https://openalex.org/W4386001693","https://openalex.org/W6747242169","https://openalex.org/W6807655789"],"related_works":["https://openalex.org/W1559557735","https://openalex.org/W2361283489","https://openalex.org/W1997537096","https://openalex.org/W3164753811","https://openalex.org/W7164882935","https://openalex.org/W2186043421","https://openalex.org/W3014183340","https://openalex.org/W2761031172","https://openalex.org/W2012575882","https://openalex.org/W7019196138"],"abstract_inverted_index":{"Conventional":[0],"web":[1,15,88,110],"crawling":[2,23,31,45,62],"methods":[3],"typically":[4],"involve":[5],"a":[6,29,43,52,65,76,81],"sequence":[7],"of":[8,20,28,122,148,160],"distinct":[9],"steps":[10],"for":[11,104],"downloading":[12],"and":[13,144,164],"extracting":[14],"content.":[16,123],"A":[17],"noteworthy":[18],"limitation":[19],"these":[21],"conventional":[22],"approaches":[24],"is":[25],"their":[26],"lack":[27],"focus-based":[30,69],"strategy.":[32],"The":[33,113],"software":[34],"introduced":[35],"in":[36,141,158],"this":[37],"paper,":[38],"known":[39],"as":[40],"WebCollectives,":[41],"introduces":[42],"straightforward":[44],"approach":[46,137],"by":[47],"integrating":[48],"content":[49,114],"extraction":[50,94,115,142,162],"into":[51],"hierarchical":[53,98],"regular":[54,99],"expression":[55],"definition":[56],"model.":[57],"Furthermore,":[58],"it":[59,91,151],"streamlines":[60],"the":[61,127,135],"process":[63,95],"through":[64],"pipeline-oriented":[66],"framework,":[67],"emphasizing":[68],"link":[70],"extraction.":[71],"This":[72],"crawler":[73],"employs":[74],"either":[75],"configurable":[77],"Selenium":[78,102],"mechanism":[79],"or":[80],"direct":[82],"HTTP":[83],"GET":[84],"method":[85],"to":[86,108],"fetch":[87],"pages.":[89],"Subsequently,":[90],"undergoes":[92],"an":[93],"based":[96],"on":[97],"expressions.":[100],"Notably,":[101],"allows":[103],"adaptable":[105],"JavaScript":[106],"functions":[107],"navigate":[109],"pages":[111],"effectively.":[112],"generates":[116],"XML":[117],"structures":[118],"from":[119],"diverse":[120],"types":[121],"Comparative":[124],"analysis":[125],"with":[126],"standard":[128,154],"DOM":[129,155],"(Document":[130],"Object":[131],"Model)":[132],"reveals":[133],"that":[134],"proposed":[136],"yields":[138],"significant":[139],"improvements":[140],"efficiency":[143],"requires":[145],"fewer":[146],"lines":[147],"code.":[149],"Specifically,":[150],"outperforms":[152],"non-recursive":[153],"hierarchy":[156],"definitions":[157],"terms":[159],"both":[161],"speed":[163],"code":[165],"complexity.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2023-10-25T00:00:00"}
