{"id":"https://openalex.org/W4236477802","doi":"https://doi.org/10.1145/3495018.3495061","title":"Design and Research of Web Crawler Based on Distributed Architecture","display_name":"Design and Research of Web Crawler Based on Distributed Architecture","publication_year":2021,"publication_date":"2021-10-23","ids":{"openalex":"https://openalex.org/W4236477802","doi":"https://doi.org/10.1145/3495018.3495061"},"language":"en","primary_location":{"id":"doi:10.1145/3495018.3495061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3495018.3495061","pdf_url":null,"source":{"id":"https://openalex.org/S4363607741","display_name":"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture","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/A5100356404","display_name":"Lili Wang","orcid":"https://orcid.org/0000-0002-5669-5281"},"institutions":[{"id":"https://openalex.org/I4210124427","display_name":"City College of Dongguan University of Technology","ror":"https://ror.org/02vdh2x09","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029","https://openalex.org/I4210124427"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lili Wang","raw_affiliation_strings":["Dongguan City College, China"],"affiliations":[{"raw_affiliation_string":"Dongguan City College, China","institution_ids":["https://openalex.org/I4210124427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100775993","display_name":"Haoliang Wang","orcid":"https://orcid.org/0000-0003-4222-9893"},"institutions":[{"id":"https://openalex.org/I4210124427","display_name":"City College of Dongguan University of Technology","ror":"https://ror.org/02vdh2x09","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029","https://openalex.org/I4210124427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoliang Wang","raw_affiliation_strings":["Dongguan City College, China"],"affiliations":[{"raw_affiliation_string":"Dongguan City College, China","institution_ids":["https://openalex.org/I4210124427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100356404"],"corresponding_institution_ids":["https://openalex.org/I4210124427"],"apc_list":null,"apc_paid":null,"fwci":0.5672,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67226098,"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":"254","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9921000003814697,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9921000003814697,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.991100013256073,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.9719130396842957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7797935009002686},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.7104749083518982},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5338403582572937},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4850586950778961},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4701398015022278},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4518806040287018},{"id":"https://openalex.org/keywords/distributed-data-store","display_name":"Distributed data store","score":0.42585426568984985},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42089641094207764},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.2104175090789795},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.19109848141670227}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9719130396842957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7797935009002686},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.7104749083518982},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5338403582572937},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4850586950778961},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4701398015022278},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4518806040287018},{"id":"https://openalex.org/C24885549","wikidata":"https://www.wikidata.org/wiki/Q339678","display_name":"Distributed data store","level":2,"score":0.42585426568984985},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42089641094207764},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.2104175090789795},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.19109848141670227},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3495018.3495061","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3495018.3495061","pdf_url":null,"source":{"id":"https://openalex.org/S4363607741","display_name":"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture","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":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1509615044","https://openalex.org/W2034835104","https://openalex.org/W2093933578","https://openalex.org/W2260026176","https://openalex.org/W2331924699","https://openalex.org/W2790955046","https://openalex.org/W2895947459","https://openalex.org/W3093170916"],"related_works":["https://openalex.org/W1501777393","https://openalex.org/W2042034567","https://openalex.org/W2548443989","https://openalex.org/W2375180657","https://openalex.org/W2102887023","https://openalex.org/W3169657889","https://openalex.org/W3179424333","https://openalex.org/W4248730791","https://openalex.org/W3201312643","https://openalex.org/W1566984846"],"abstract_inverted_index":{"Internet":[0],"data":[1,25,80,90],"is":[2,40,111],"abundance":[3],"in":[4,8,117],"content":[5],"and":[6,20,26,49,61,98,122],"diverse":[7],"organization.":[9],"In":[10],"order":[11],"to":[12,66,113],"automatically":[13],"complete":[14],"the":[15,29,56,71,77,83,92,99,104,108,114],"process":[16],"of":[17,24,58,73,79,85,88,107,119],"collecting,":[18],"analyzing,":[19],"storing":[21],"large":[22],"amounts":[23],"information":[27],"on":[28,36,96],"web,":[30],"a":[31],"web":[32],"crawler":[33,44,94,101,105,116],"technology":[34],"based":[35,95],"Hadoop":[37,46],"distributed":[38,47,51,59,74,93,109],"clusters":[39],"proposed.":[41],"Using":[42],"Nutch":[43,97],"framework,":[45,54],"technology,":[48],"Zookeeper":[50],"coordination":[52],"service":[53],"through":[55],"construction":[57],"clusters,":[60],"high-performance":[62],"Key-Value":[63],"database":[64],"Redis":[65],"store":[67],"data,":[68],"it":[69],"verifies":[70],"feasibility":[72],"crawlers.":[75],"Through":[76],"analysis":[78],"collection":[81,120],"experiments,":[82],"comparison":[84],"multiple":[86],"sets":[87],"experimental":[89],"between":[91],"traditional":[100,115],"shows":[102],"that":[103],"design":[106],"architecture":[110],"superior":[112],"terms":[118],"speed":[121],"efficiency.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
