{"id":"https://openalex.org/W2141088846","doi":"https://doi.org/10.1109/icmlc.2011.6016946","title":"Medium sized crawling made fast and easy through Lumbricus webis","display_name":"Medium sized crawling made fast and easy through Lumbricus webis","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2141088846","doi":"https://doi.org/10.1109/icmlc.2011.6016946","mag":"2141088846"},"language":"en","primary_location":{"id":"doi:10.1109/icmlc.2011.6016946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2011.6016946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on Machine Learning and Cybernetics","raw_type":"proceedings-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/A5017447754","display_name":"Claudio Felicioli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Claudio Felicioli","raw_affiliation_strings":["Istituto di Infonnatica e Telematica, CNR, Pisa, Italy","Istituto di Informatica e Telematica, CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Infonnatica e Telematica, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]},{"raw_affiliation_string":"Istituto di Informatica e Telematica, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033343264","display_name":"Filippo Geraci","orcid":"https://orcid.org/0000-0001-6993-6761"},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Filippo Geraci","raw_affiliation_strings":["Istituto di Infonnatica e Telematica, CNR, Pisa, Italy","Istituto di Informatica e Telematica, CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Infonnatica e Telematica, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]},{"raw_affiliation_string":"Istituto di Informatica e Telematica, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028551838","display_name":"Marco Pellegrini","orcid":"https://orcid.org/0000-0003-3151-9481"},"institutions":[{"id":"https://openalex.org/I4210130157","display_name":"Institute of Informatics and Telematics","ror":"https://ror.org/02gdcn153","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210130157","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Pellegrini","raw_affiliation_strings":["Istituto di Infonnatica e Telematica, CNR, Pisa, Italy","Istituto di Informatica e Telematica, CNR, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto di Infonnatica e Telematica, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]},{"raw_affiliation_string":"Istituto di Informatica e Telematica, CNR, Pisa, Italy","institution_ids":["https://openalex.org/I4210130157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017447754"],"corresponding_institution_ids":["https://openalex.org/I4210130157"],"apc_list":null,"apc_paid":null,"fwci":0.7389,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83520499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1920","last_page":"1926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10260","display_name":"Software Engineering Research","score":0.9811999797821045,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9631999731063843,"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":0.9130655527114868},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.9064114093780518},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7954508662223816},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6342349648475647},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6104611754417419},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5360764265060425},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.4866793751716614},{"id":"https://openalex.org/keywords/download","display_name":"Download","score":0.48108264803886414},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4496031403541565},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4487780034542084},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4481281340122223},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4368383586406708},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3516610860824585},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.30189621448516846},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11576032638549805}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9130655527114868},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9064114093780518},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954508662223816},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6342349648475647},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6104611754417419},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5360764265060425},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.4866793751716614},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.48108264803886414},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4496031403541565},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4487780034542084},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4481281340122223},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4368383586406708},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3516610860824585},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.30189621448516846},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11576032638549805},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlc.2011.6016946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmlc.2011.6016946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on Machine Learning and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1561637629","https://openalex.org/W1970614016","https://openalex.org/W2018928332","https://openalex.org/W2040886165","https://openalex.org/W2098293053","https://openalex.org/W2142211218","https://openalex.org/W2169206507","https://openalex.org/W2911388033","https://openalex.org/W4238227199","https://openalex.org/W6633852879","https://openalex.org/W6681034752"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W2019080882"],"abstract_inverted_index":{"Web":[0],"crawlers":[1,45],"have":[2,47],"become":[3],"popular":[4],"tools":[5,97],"for":[6,17,44],"collecting":[7],"large":[8],"portions":[9,75],"of":[10,25,32,37,76,84,91,101,111],"the":[11,26,30,35,71,77,99,102,108],"web":[12,78],"that":[13],"can":[14,117],"be":[15],"used":[16],"many":[18],"tasks":[19,38],"from":[20,70,80],"statistics":[21],"to":[22,29,39,46,67,88],"structural":[23],"analysis":[24],"web.":[27],"Due":[28],"amount":[31],"data":[33,69],"and":[34,50,74,94,113],"heterogeneity":[36],"manage,":[40],"it":[41],"is":[42,87],"essential":[43],"a":[48,62,120],"modular":[49,63],"distributed":[51],"architecture.":[52],"In":[53],"this":[54],"paper":[55,106],"we":[56],"describe":[57],"Lumbricus":[58],"webis,":[59],"(short":[60],"L.webis)":[61],"crawling":[64],"infrastructure":[65],"built":[66],"mine":[68],".it":[72],"domain":[73],"reachable":[79],"it.":[81],"The":[82],"purpose":[83],"our":[85],"crawler":[86],"support":[89],"gathering":[90],"advanced":[92,95],"statistics,":[93],"analytic":[96],"on":[98],"content":[100],"Italian":[103],"Web.":[104],"This":[105],"describes":[107],"architectural":[109],"features":[110],"L.webis":[112,116],"its":[114],"performance.":[115],"currently":[118],"download":[119],"mid-sized":[121],"ccTLD":[122],"such":[123],"as":[124],"\u201c.it\u201d":[125],"in":[126],"about":[127],"one":[128],"week.":[129]},"counts_by_year":[{"year":2018,"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"}
