{"id":"https://openalex.org/W2805710541","doi":"https://doi.org/10.1145/3160017","title":"BUbiNG","display_name":"BUbiNG","publication_year":2018,"publication_date":"2018-05-31","ids":{"openalex":"https://openalex.org/W2805710541","doi":"https://doi.org/10.1145/3160017","mag":"2805710541"},"language":"en","primary_location":{"id":"doi:10.1145/3160017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3160017","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","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/A5038842358","display_name":"Paolo Boldi","orcid":"https://orcid.org/0000-0002-8297-6255"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Boldi","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035852380","display_name":"Andrea Marino","orcid":"https://orcid.org/0000-0002-9854-7885"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Marino","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078458093","display_name":"Massimo Santini","orcid":"https://orcid.org/0000-0003-1416-0673"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Santini","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027824085","display_name":"Sebastiano Vigna","orcid":"https://orcid.org/0000-0002-3257-651X"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sebastiano Vigna","raw_affiliation_strings":["Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3257-651X","affiliations":[{"raw_affiliation_string":"Dipartimento di Informatica, Universit\u00e0 degli Studi di Milano, Milano, MI, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189158943"],"apc_list":null,"apc_paid":null,"fwci":4.8322,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95566226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"12","issue":"2","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9901000261306763,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8806599378585815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8374741077423096},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7486746907234192},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.6774762868881226},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6028096079826355},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5685697197914124},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5570225715637207},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.48195716738700867},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4756835699081421},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43812867999076843},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3970739245414734},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.26901552081108093},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.10289275646209717},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.0993351936340332}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8806599378585815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374741077423096},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7486746907234192},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.6774762868881226},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6028096079826355},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5685697197914124},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5570225715637207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.48195716738700867},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4756835699081421},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43812867999076843},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3970739245414734},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.26901552081108093},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.10289275646209717},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0993351936340332},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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":1,"locations":[{"id":"doi:10.1145/3160017","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3160017","pdf_url":null,"source":{"id":"https://openalex.org/S131231701","display_name":"ACM Transactions on the Web","issn_l":"1559-1131","issn":["1559-1131","1559-114X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on the Web","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.7099999785423279,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324499","display_name":"Universit\u00e0 di Pisa","ror":"https://ror.org/03ad39j10"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W110443600","https://openalex.org/W256861921","https://openalex.org/W1475732121","https://openalex.org/W1506845741","https://openalex.org/W1533628276","https://openalex.org/W1583722687","https://openalex.org/W1613836731","https://openalex.org/W1977836056","https://openalex.org/W1981393723","https://openalex.org/W2000042664","https://openalex.org/W2000273502","https://openalex.org/W2012833704","https://openalex.org/W2013531639","https://openalex.org/W2017274979","https://openalex.org/W2018928332","https://openalex.org/W2023097373","https://openalex.org/W2051804774","https://openalex.org/W2057223122","https://openalex.org/W2066636486","https://openalex.org/W2070472314","https://openalex.org/W2123845384","https://openalex.org/W2134784378","https://openalex.org/W2140279085","https://openalex.org/W2145349611","https://openalex.org/W2169557227","https://openalex.org/W2258998514","https://openalex.org/W2911388033","https://openalex.org/W3037267426","https://openalex.org/W3103362336","https://openalex.org/W4254697110"],"related_works":["https://openalex.org/W1506122440","https://openalex.org/W2152505903","https://openalex.org/W2914040552","https://openalex.org/W2314663776","https://openalex.org/W2066301148","https://openalex.org/W2798451772","https://openalex.org/W3213099714","https://openalex.org/W3099502334","https://openalex.org/W4236035878","https://openalex.org/W3025189687"],"abstract_inverted_index":{"Although":[0],"web":[1,57],"crawlers":[2,112],"have":[3],"been":[4],"around":[5],"for":[6],"twenty":[7],"years":[8,72],"by":[9],"now,":[10],"there":[11],"is":[12,79,123],"virtually":[13],"no":[14],"freely":[15],"available,":[16],"open-source":[17,81,110],"crawling":[18],"software":[19],"that":[20,113],"guarantees":[21],"high":[22,132],"throughput,":[23],"overcomes":[24],"the":[25,32,38,51,61,69,76],"limits":[26],"of":[27,40,53,73],"single-machine":[28],"systems,":[29],"and,":[30],"at":[31,46],"same":[33],"time,":[34],"scales":[35],"linearly":[36],"with":[37,64],"amount":[39],"resources":[41],"available.":[42],"This":[43],"article":[44],"aims":[45],"filling":[47],"this":[48],"gap,":[49],"through":[50],"description":[52],"BUbiNG,":[54],"our":[55],"next-generation":[56],"crawler":[58],"built":[59],"upon":[60],"authors\u2019":[62],"experience":[63],"UbiCrawler":[65],"[9]":[66],"and":[67,106],"on":[68,75,115,125],"last":[70],"ten":[71],"research":[74],"topic.":[77],"BUbiNG":[78,88,120],"an":[80],"Java":[82],"fully":[83],"distributed":[84,111],"crawler;":[85],"a":[86],"single":[87],"agent,":[89],"using":[90],"sizeable":[91],"hardware,":[92],"can":[93],"crawl":[94],"several":[95],"thousand":[96],"pages":[97],"per":[98],"second":[99],"respecting":[100],"strict":[101],"politeness":[102],"constraints,":[103],"both":[104],"host-":[105],"IP-based.":[107],"Unlike":[108],"existing":[109],"rely":[114],"batch":[116],"techniques":[117],"(like":[118],"MapReduce),":[119],"job":[121],"distribution":[122],"based":[124],"modern":[126],"high-speed":[127],"protocols":[128],"to":[129],"achieve":[130],"very":[131],"throughput.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2018-06-13T00:00:00"}
