{"id":"https://openalex.org/W2022435029","doi":"https://doi.org/10.1109/icin.2015.7073834","title":"A cloud-based web crawler architecture","display_name":"A cloud-based web crawler architecture","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2022435029","doi":"https://doi.org/10.1109/icin.2015.7073834","mag":"2022435029"},"language":"en","primary_location":{"id":"doi:10.1109/icin.2015.7073834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icin.2015.7073834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 18th International Conference on Intelligence in Next Generation Networks","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/A5101407943","display_name":"Mehdi Bahrami","orcid":"https://orcid.org/0000-0002-9935-7899"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehdi Bahrami","raw_affiliation_strings":["Cloud Lab, University of California, Merced, USA","University of California\u2013Merced USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud Lab, University of California, Merced, USA","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"University of California\u2013Merced USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058282709","display_name":"Mukesh Singhal","orcid":"https://orcid.org/0000-0002-0497-1942"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mukesh Singhal","raw_affiliation_strings":["Cloud Lab, University of California, Merced, USA","University of California\u2013Merced USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud Lab, University of California, Merced, USA","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"University of California\u2013Merced USA","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091802679","display_name":"Zixuan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixuan Zhuang","raw_affiliation_strings":["Cloud Lab, University of California, Merced, USA","University of California\u2013Merced USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud Lab, University of California, Merced, USA","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"University of California\u2013Merced USA","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":13.1842,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.98471864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11478","display_name":"Caching and Content Delivery","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.987500011920929,"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":0.9426497220993042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8198831081390381},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.7597262859344482},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6636461615562439},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5577570796012878},{"id":"https://openalex.org/keywords/web-api","display_name":"Web API","score":0.5429711937904358},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5425170063972473},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5367134213447571},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5246087312698364},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5177825689315796},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5169922113418579},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.44772037863731384},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.41151684522628784},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3886030912399292},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.3545585870742798},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32956451177597046},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.2439386546611786},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1392936408519745},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11829650402069092}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9426497220993042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198831081390381},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.7597262859344482},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6636461615562439},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5577570796012878},{"id":"https://openalex.org/C127613066","wikidata":"https://www.wikidata.org/wiki/Q557770","display_name":"Web API","level":4,"score":0.5429711937904358},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5425170063972473},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5367134213447571},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5246087312698364},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5177825689315796},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5169922113418579},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.44772037863731384},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.41151684522628784},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3886030912399292},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.3545585870742798},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32956451177597046},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2439386546611786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1392936408519745},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11829650402069092}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icin.2015.7073834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icin.2015.7073834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 18th International Conference on Intelligence in Next Generation Networks","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5799999833106995,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W18920056","https://openalex.org/W1540703146","https://openalex.org/W1542053855","https://openalex.org/W1549217911","https://openalex.org/W1613836731","https://openalex.org/W2000273502","https://openalex.org/W2018928332","https://openalex.org/W2053854064","https://openalex.org/W2079057568","https://openalex.org/W2124496187","https://openalex.org/W2140279085","https://openalex.org/W2295141584","https://openalex.org/W2372594123","https://openalex.org/W6600797612","https://openalex.org/W6632686070","https://openalex.org/W6650483838"],"related_works":["https://openalex.org/W2417265363","https://openalex.org/W2402678663","https://openalex.org/W2377634017","https://openalex.org/W3201526811","https://openalex.org/W2379145789","https://openalex.org/W2610451498","https://openalex.org/W1994958611","https://openalex.org/W4200125296","https://openalex.org/W2277785728","https://openalex.org/W2109463504"],"abstract_inverted_index":{"Web":[0,30],"crawlers":[1,25,31,110,147],"work":[2],"on":[3,16,83,198,218],"the":[4,17,28,58,79,84,106,150,173,185,224,229,236,239],"behalf":[5],"of":[6,60,64,81,96,216,228,238],"applications":[7],"or":[8,67,76,152],"services":[9],"to":[10,26,50,142,183],"find":[11],"interesting":[12],"and":[13,40,88,119,131,134,172,191,213,226,233],"related":[14],"information":[15,82],"web.":[18],"For":[19],"example,":[20],"search":[21,91],"engines":[22],"use":[23],"web":[24,47,109,146,155,164,179,186,207,231,241,246],"index":[27],"Internet.":[29],"have":[32],"several":[33],"challenges,":[34],"such":[35,71],"as":[36,72],"complexity":[37],"between":[38],"links":[39,66],"highly":[41,116],"intensive":[42,117],"computation":[43],"requirements":[44],"when":[45],"a":[46,61,94,153,162,199],"crawler":[48,165,180,208,232,242],"wants":[49],"retrieve":[51],"complex":[52],"connected":[53],"links.":[54],"Another":[55],"issue":[56],"is":[57],"storage":[59,120],"massive":[62,214],"amount":[63,215],"indexed":[65],"downloaded":[68],"unstructured":[69,99,132,212],"data,":[70,100,133],"binary":[73],"files,":[74],"videos":[75],"images.":[77],"As":[78],"volume":[80],"Internet":[85,151],"increases":[86],"rapidly":[87],"requests":[89],"may":[90],"data":[92,217],"in":[93,105],"variety":[95],"formats":[97],"including":[98],"no":[101],"cloud-based":[102,163],"architecture":[103,166],"exists":[104],"literatures":[107],"for":[108,128,148],"that":[111,138,167],"could":[112,210],"effectively":[113],"address":[114],"both":[115],"computing":[118,124,170],"issues.":[121],"The":[122,177,205],"cloud":[123,169],"paradigm":[125],"provides":[126,135],"support":[127],"elastic":[129],"resources":[130],"pay-peruse":[136],"features":[137,171],"allow":[139],"individual":[140],"businesses":[141],"run":[143],"their":[144],"own":[145,196],"crawling":[149],"limited":[154],"hosts.":[156],"In":[157],"this":[158],"paper,":[159],"we":[160,234],"propose":[161],"uses":[168],"MapReduce":[174],"programming":[175],"technique.":[176],"proposed":[178,206,230,240],"allows":[181],"us":[182],"crawl":[184],"by":[187],"using":[188],"distributed":[189,245],"agents":[190],"each":[192],"agent":[193],"stores":[194],"its":[195],"finding":[197],"Cloud":[200],"Azure":[201,219],"Table":[202],"(NoSQL":[203],"database).":[204],"also":[209],"store":[211],"Blob":[220],"storage.":[221],"We":[222],"analyze":[223],"performance":[225],"scalability":[227],"describe":[235],"advantages":[237],"over":[243],"traditional":[244],"crawlers.":[247]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
