{"id":"https://openalex.org/W2897694184","doi":"https://doi.org/10.1109/sera.2018.8477212","title":"The Research of a Lightweight Distributed Crawling System","display_name":"The Research of a Lightweight Distributed Crawling System","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2897694184","doi":"https://doi.org/10.1109/sera.2018.8477212","mag":"2897694184"},"language":"en","primary_location":{"id":"doi:10.1109/sera.2018.8477212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera.2018.8477212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 16th International Conference on Software Engineering Research, Management and Applications (SERA)","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/A5100398500","display_name":"Feng Ye","orcid":"https://orcid.org/0000-0003-0005-2073"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Ye","raw_affiliation_strings":["College of Computer and Information, Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059053658","display_name":"Zongfei Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongfei Jing","raw_affiliation_strings":["College of Computer and Information, Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079178505","display_name":"Qian Huang","orcid":"https://orcid.org/0000-0001-5625-0402"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Huang","raw_affiliation_strings":["College of Computer and Information, Hohai University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Information, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077521546","display_name":"Yong Chen","orcid":"https://orcid.org/0000-0002-9961-9051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Chen","raw_affiliation_strings":["Postdoctoral centre, Nanjing Longyuan Micro-Electronic Company, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Postdoctoral centre, Nanjing Longyuan Micro-Electronic Company, Nanjing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100398500"],"corresponding_institution_ids":["https://openalex.org/I163340411"],"apc_list":null,"apc_paid":null,"fwci":1.1781,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85624013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"69","issue":null,"first_page":"200","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962000250816345,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.849939227104187},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8464576005935669},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7357416152954102},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6943929195404053},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6141533255577087},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.58332759141922},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.43496280908584595},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3513558506965637},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19739443063735962},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1853291392326355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849939227104187},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8464576005935669},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7357416152954102},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6943929195404053},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6141533255577087},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.58332759141922},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.43496280908584595},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3513558506965637},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19739443063735962},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1853291392326355},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sera.2018.8477212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera.2018.8477212","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 16th International Conference on Software Engineering Research, Management and Applications (SERA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1595621137","https://openalex.org/W1613836731","https://openalex.org/W1761577731","https://openalex.org/W2000273502","https://openalex.org/W2033672567","https://openalex.org/W2103778799","https://openalex.org/W2117311042","https://openalex.org/W2119565742","https://openalex.org/W2212564340","https://openalex.org/W2295141584","https://openalex.org/W2599114792","https://openalex.org/W4239670432","https://openalex.org/W4285719527","https://openalex.org/W6675707706","https://openalex.org/W6688410531","https://openalex.org/W6735217810"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2089702591"],"abstract_inverted_index":{"Nowadays,":[0],"information":[1],"on":[2],"the":[3,14,64,73,76,90,99,126,130,134,137,142,151,156],"Internet":[4],"is":[5],"growing":[6],"at":[7],"an":[8,149],"explosive":[9],"rate.":[10],"The":[11],"ability":[12],"of":[13,66,69,92,125,129,136,144],"stand-alone":[15],"web":[16,32,38],"crawling":[17,33,39,111,138],"system":[18,139],"has":[19,160],"come":[20],"to":[21,30,80],"its":[22],"bottleneck,":[23],"so":[24],"more":[25,27],"and":[26,51,108,116,132],"companies":[28],"turn":[29],"distributed":[31,37,110,117,157],"techniques.":[34,119],"However,":[35],"existing":[36],"systems":[40],"have":[41],"some":[42],"shortcomings.":[43],"Thread":[44],"management":[45],"modules":[46,70],"for":[47],"solving":[48],"thread":[49],"synchronization":[50],"resource":[52],"competition":[53],"are":[54],"usually":[55],"designed":[56],"by":[57],"using":[58],"pure":[59],"multithread":[60],"asynchronous":[61],"methods,":[62],"but":[63],"execution":[65,162],"this":[67,103],"kind":[68],"observably":[71],"reduces":[72],"performance.":[74],"Moreover,":[75],"deduplication":[77],"algorithms":[78],"lead":[79],"low":[81],"efficiency":[82,135],"in":[83],"dealing":[84],"with":[85],"large":[86,94],"data":[87,143],"sets":[88],"or":[89],"problem":[91],"occupying":[93],"storage":[95],"space.":[96],"To":[97],"solve":[98],"problems":[100],"mentioned":[101],"above,":[102],"paper":[104],"proposes":[105],"a":[106],"lightweight":[107],"practical":[109],"system,":[112],"which":[113],"combines":[114],"Docker":[115],"computing":[118,127],"It":[120],"can":[121],"make":[122],"full":[123],"use":[124],"resources":[128],"cluster":[131],"improve":[133],"effectively.":[140],"Taking":[141],"Netease":[145],"news":[146],"page":[147],"as":[148],"example,":[150],"experimental":[152],"results":[153],"show":[154],"that":[155],"crawler":[158],"proposed":[159],"higher":[161],"efficiency.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
