{"id":"https://openalex.org/W2043978221","doi":"https://doi.org/10.1145/2532443.2532454","title":"A scalable crawler framework for FLOSS data","display_name":"A scalable crawler framework for FLOSS data","publication_year":2013,"publication_date":"2013-10-23","ids":{"openalex":"https://openalex.org/W2043978221","doi":"https://doi.org/10.1145/2532443.2532454","mag":"2043978221"},"language":"en","primary_location":{"id":"doi:10.1145/2532443.2532454","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2532443.2532454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Asia-Pacific Symposium on Internetware","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/A5101795504","display_name":"Lingxiao Zhang","orcid":"https://orcid.org/0000-0001-8922-7639"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lingxiao Zhang","raw_affiliation_strings":["Peking University and Ministry of Education, Beijing, P.R. China","Peking University and Ministry of Education, Beijing, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University and Ministry of Education, Beijing, P.R. China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University and Ministry of Education, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103872660","display_name":"Yanzhen Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhen Zou","raw_affiliation_strings":["Peking University and Ministry of Education, Beijing, P.R. China","Peking University and Ministry of Education, Beijing, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University and Ministry of Education, Beijing, P.R. China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University and Ministry of Education, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102928967","display_name":"Bing Xie","orcid":"https://orcid.org/0000-0002-2988-2575"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Xie","raw_affiliation_strings":["Peking University and Ministry of Education, Beijing, P.R. China","Peking University and Ministry of Education, Beijing, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University and Ministry of Education, Beijing, P.R. China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University and Ministry of Education, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101795504"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.17355841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","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/T10260","display_name":"Software Engineering Research","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/T11675","display_name":"Open Source Software Innovations","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8557336330413818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986763715744019},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6500382423400879},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4994363784790039},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47873446345329285},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4688119888305664},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4679483473300934},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.43367835879325867},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4289345443248749},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.42084017395973206},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4173693358898163},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4149037003517151},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3999004364013672},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3219521641731262},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.20940572023391724},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14568665623664856},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.13703706860542297},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11212354898452759}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8557336330413818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986763715744019},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6500382423400879},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4994363784790039},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47873446345329285},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4688119888305664},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4679483473300934},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.43367835879325867},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4289345443248749},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.42084017395973206},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4173693358898163},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4149037003517151},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3999004364013672},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3219521641731262},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.20940572023391724},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14568665623664856},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.13703706860542297},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11212354898452759},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2532443.2532454","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2532443.2532454","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Asia-Pacific Symposium on Internetware","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7893457563","display_name":null,"funder_award_id":"61103024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8237870450","display_name":null,"funder_award_id":"2009CB320703","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G8605567145","display_name":null,"funder_award_id":"2012AA011202","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W168970045","https://openalex.org/W187312421","https://openalex.org/W1989479444","https://openalex.org/W1995611607","https://openalex.org/W2037786492","https://openalex.org/W2049828091","https://openalex.org/W2050136587","https://openalex.org/W2092382400","https://openalex.org/W2095938258","https://openalex.org/W2107294940","https://openalex.org/W2108693132","https://openalex.org/W2111861834","https://openalex.org/W2126523200","https://openalex.org/W2128689656","https://openalex.org/W2141102013","https://openalex.org/W2142481192","https://openalex.org/W2163732854","https://openalex.org/W2164961799","https://openalex.org/W3143096207","https://openalex.org/W4240298746","https://openalex.org/W4240398231"],"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":{"Free":[0],"/":[1,3],"Libre":[2],"Open":[4],"Source":[5],"Software":[6],"(FLOSS)":[7],"data,":[8,33],"such":[9],"as":[10,51],"bug":[11],"reports,":[12],"mailing":[13],"lists":[14],"and":[15,126,141],"related":[16,167],"webpages,":[17],"contains":[18],"valuable":[19],"information":[20],"for":[21],"reusing":[22],"open":[23],"source":[24],"software":[25],"projects.":[26],"Before":[27],"conducting":[28],"further":[29],"experiment":[30],"on":[31,89,121],"FLOSS":[32,52,77,86],"researchers":[34],"often":[35],"need":[36],"to":[37,48,72,111,133,168],"download":[38],"these":[39],"data":[40,53,78,87],"into":[41,108],"a":[42,61,69,97,101,156],"local":[43],"storage":[44],"system.":[45,135],"We":[46,136,148],"refer":[47],"this":[49,65],"pre-process":[50],"retrieval,":[54],"which":[55],"in":[56,96],"many":[57],"cases":[58],"can":[59,104,116],"be":[60,105],"challenging":[62],"task.":[63],"In":[64],"paper,":[66],"we":[67,92,161],"proposed":[68],"crawler":[70,102],"framework":[71,95,140],"ease":[73],"the":[74,90,94,109,118,134,139,150,153],"process":[75,120],"of":[76,85,123,152,165],"retrieval.":[79],"To":[80],"cope":[81],"with":[82],"various":[83,124,163],"types":[84,125,164],"scattered":[88],"Internet,":[91],"designed":[93],"scalable":[98],"manner":[99],"where":[100,160],"program":[103],"easily":[106],"plugged":[107],"system":[110,154],"extend":[112],"its":[113],"functionality.":[114],"Researchers":[115],"perform":[117],"retrieval":[119],"datasets":[122,166],"sources":[127],"simply":[128],"by":[129,155],"adding":[130],"new":[131],"configurations":[132],"have":[137],"implemented":[138],"provided":[142],"basic":[143],"functions":[144],"via":[145],"web-based":[146],"interfaces.":[147],"presented":[149],"usage":[151],"detailed":[157],"case":[158],"study":[159],"retrieved":[162],"Apache":[169],"Lucene":[170],"project":[171],"using":[172],"our":[173],"framework.":[174]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
