{"id":"https://openalex.org/W1990853665","doi":"https://doi.org/10.3390/fi6030518","title":"ARCOMEM Crawling Architecture","display_name":"ARCOMEM Crawling Architecture","publication_year":2014,"publication_date":"2014-08-19","ids":{"openalex":"https://openalex.org/W1990853665","doi":"https://doi.org/10.3390/fi6030518","mag":"1990853665"},"language":"en","primary_location":{"id":"doi:10.3390/fi6030518","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi6030518","pdf_url":"https://www.mdpi.com/1999-5903/6/3/518/pdf?version=1408441033","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/6/3/518/pdf?version=1408441033","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110866799","display_name":"Vassilis Plachouras","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vassilis Plachouras","raw_affiliation_strings":["Institute for the Management of Information Systems, Athena Research and Innovation Center, Artemidos 6 & Epidavrou, Maroussi 15125, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for the Management of Information Systems, Athena Research and Innovation Center, Artemidos 6 & Epidavrou, Maroussi 15125, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081272286","display_name":"Florent Carpentier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160905","display_name":"Internet Memory Foundation","ror":"https://ror.org/05vhqss82","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I4210160905"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florent Carpentier","raw_affiliation_strings":["Internet Memory Foundation, 45 ter rue de la R\u00e9volution, 93100 Montreuil, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Internet Memory Foundation, 45 ter rue de la R\u00e9volution, 93100 Montreuil, France","institution_ids":["https://openalex.org/I4210160905"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101798845","display_name":"Muhammad Faheem","orcid":"https://orcid.org/0000-0003-4859-1586"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Muhammad Faheem","raw_affiliation_strings":["CNRS LTCI, Institut Mines-T\u00e9l\u00e9com, T\u00e9l\u00e9com ParisTech, 46 rue Barrault, 75634 Paris Cedex 13, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS LTCI, Institut Mines-T\u00e9l\u00e9com, T\u00e9l\u00e9com ParisTech, 46 rue Barrault, 75634 Paris Cedex 13, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I205703379","https://openalex.org/I1294671590","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053866570","display_name":"Julien Masan\u00e9s","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160905","display_name":"Internet Memory Foundation","ror":"https://ror.org/05vhqss82","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I4210160905"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Masan\u00e8s","raw_affiliation_strings":["Internet Memory Foundation, 45 ter rue de la R\u00e9volution, 93100 Montreuil, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Internet Memory Foundation, 45 ter rue de la R\u00e9volution, 93100 Montreuil, France","institution_ids":["https://openalex.org/I4210160905"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070155789","display_name":"Thomas Risse","orcid":"https://orcid.org/0000-0001-6248-1709"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Risse","raw_affiliation_strings":["Research Center, University of Hannover, Appelstr. 9a, 30167 Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center, University of Hannover, Appelstr. 9a, 30167 Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035414136","display_name":"Pierre Senellart","orcid":"https://orcid.org/0000-0002-7909-5369"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Senellart","raw_affiliation_strings":["CNRS LTCI, Institut Mines-T\u00e9l\u00e9com, T\u00e9l\u00e9com ParisTech, 46 rue Barrault, 75634 Paris Cedex 13, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS LTCI, Institut Mines-T\u00e9l\u00e9com, T\u00e9l\u00e9com ParisTech, 46 rue Barrault, 75634 Paris Cedex 13, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I205703379","https://openalex.org/I1294671590","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067981741","display_name":"Patrick Siehndel","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick Siehndel","raw_affiliation_strings":["Research Center, University of Hannover, Appelstr. 9a, 30167 Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center, University of Hannover, Appelstr. 9a, 30167 Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072033746","display_name":"Yannis Stavrakas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Stavrakas","raw_affiliation_strings":["Institute for the Management of Information Systems, Athena Research and Innovation Center, Artemidos 6 & Epidavrou, Maroussi 15125, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for the Management of Information Systems, Athena Research and Innovation Center, Artemidos 6 & Epidavrou, Maroussi 15125, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5110866799"],"corresponding_institution_ids":[],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":3.2803,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92694233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":"3","first_page":"518","last_page":"541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9914000034332275,"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":0.9725000262260437,"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/web-crawler","display_name":"Web crawler","score":0.9414635896682739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8950778245925903},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7799535989761353},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7508385181427002},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6283929347991943},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.594390332698822},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5651100873947144},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5443621873855591},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5339844226837158},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46615374088287354},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.46555620431900024},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.3803747296333313},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.37754806876182556}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9414635896682739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8950778245925903},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7799535989761353},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7508385181427002},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6283929347991943},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.594390332698822},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5651100873947144},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5443621873855591},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5339844226837158},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46615374088287354},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.46555620431900024},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.3803747296333313},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.37754806876182556},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":5,"locations":[{"id":"doi:10.3390/fi6030518","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi6030518","pdf_url":"https://www.mdpi.com/1999-5903/6/3/518/pdf?version=1408441033","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01069819v1","is_oa":false,"landing_page_url":"https://imt.hal.science/hal-01069819","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, 2014, 6 (3), pp.518-541","raw_type":"Journal articles"},{"id":"pmh:oai:RePEc:gam:jftint:v:6:y:2014:i:3:p:518-541:d:39354","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/6/3/518/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:ec5ee55717a648f5aa26fb3022e888c3","is_oa":true,"landing_page_url":"https://doaj.org/article/ec5ee55717a648f5aa26fb3022e888c3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 6, Iss 3, Pp 518-541 (2014)","raw_type":"article"},{"id":"pmh:oai:publikationen.ub.uni-frankfurt.de:53651","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:hebis:30:3-536511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400432","display_name":"Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114090438","host_organization_name":"Goethe University Frankfurt","host_organization_lineage":["https://openalex.org/I114090438"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi6030518","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi6030518","pdf_url":"https://www.mdpi.com/1999-5903/6/3/518/pdf?version=1408441033","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4520791364","display_name":null,"funder_award_id":"270239","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W174455191","https://openalex.org/W1489992655","https://openalex.org/W1553448964","https://openalex.org/W1566984846","https://openalex.org/W1588079272","https://openalex.org/W1613836731","https://openalex.org/W1660264423","https://openalex.org/W1967890081","https://openalex.org/W1974064905","https://openalex.org/W1977836056","https://openalex.org/W1990853665","https://openalex.org/W1996718000","https://openalex.org/W2000273502","https://openalex.org/W2001832505","https://openalex.org/W2025869052","https://openalex.org/W2038643757","https://openalex.org/W2044743392","https://openalex.org/W2049582451","https://openalex.org/W2066636486","https://openalex.org/W2081128931","https://openalex.org/W2094930182","https://openalex.org/W2097411811","https://openalex.org/W2099585315","https://openalex.org/W2109028086","https://openalex.org/W2116224704","https://openalex.org/W2118356300","https://openalex.org/W2121294789","https://openalex.org/W2121354841","https://openalex.org/W2124673015","https://openalex.org/W2125596588","https://openalex.org/W2125969310","https://openalex.org/W2127536142","https://openalex.org/W2135397824","https://openalex.org/W2135402295","https://openalex.org/W2140279085","https://openalex.org/W2148738951","https://openalex.org/W2150957091","https://openalex.org/W2157748587","https://openalex.org/W2162502927","https://openalex.org/W2164542999","https://openalex.org/W2167031332","https://openalex.org/W2169557227","https://openalex.org/W2171070229","https://openalex.org/W2252194734","https://openalex.org/W2564771040","https://openalex.org/W2581045609","https://openalex.org/W2911388033","https://openalex.org/W3024113292","https://openalex.org/W4234255778","https://openalex.org/W4235996464","https://openalex.org/W4249960090","https://openalex.org/W6607061821","https://openalex.org/W6674774839","https://openalex.org/W6678701036"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W4385695127","https://openalex.org/W4248730791","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2372594123"],"abstract_inverted_index":{"The":[0,55],"World":[1],"Wide":[2],"Web":[3,18,31,42,53,82,115,131],"is":[4,14,20,61,184],"the":[5,26,39,58,95,105,114,121,128,155,168,171,195],"largest":[6],"information":[7,13,189,196],"repository":[8],"available":[9],"today.":[10],"However,":[11],"this":[12,85],"very":[15],"volatile":[16],"and":[17,46,66,71,98,120,133,193],"archiving":[19,32],"essential":[21],"to":[22,30,44,49,62,67,79,117,135,160,167],"preserve":[23],"it":[24],"for":[25,113],"future.":[27],"Existing":[28],"approaches":[29],"are":[33,47],"based":[34],"on":[35,76,89],"simple":[36],"definitions":[37],"of":[38,41,57,130,170],"scope":[40],"pages":[43,116],"crawl":[45],"limited":[48],"basic":[50],"interactions":[51],"with":[52],"servers.":[54],"aim":[56],"ARCOMEM":[59],"project":[60],"overcome":[63],"these":[64],"limitations":[65],"provide":[68],"flexible,":[69],"adaptive":[70],"intelligent":[72],"content":[73],"acquisition,":[74],"relying":[75],"social":[77,198],"media":[78],"create":[80],"topical":[81],"archives.":[83],"In":[84],"article,":[86],"we":[87,99,157],"focus":[88],"ARCOMEM\u2019s":[90,181],"crawling":[91,182],"architecture.":[92],"We":[93,141],"introduce":[94],"overall":[96],"architecture":[97,183],"describe":[100,143],"its":[101],"modules,":[102],"such":[103],"as":[104,152,154],"online":[106],"analysis":[107],"module,":[108],"which":[109,124],"computes":[110],"a":[111,144,191],"priority":[112],"be":[118],"crawled,":[119],"Application-Aware":[122],"Helper":[123],"takes":[125],"into":[126],"account":[127],"type":[129],"sites":[132],"applications":[134],"extract":[136],"structure":[137],"from":[138,176,197],"crawled":[139],"content.":[140],"also":[142],"large-scale":[145],"distributed":[146],"crawler":[147],"that":[148,180],"has":[149],"been":[150],"developed,":[151],"well":[153],"modifications":[156],"have":[158],"implemented":[159],"adapt":[161],"Heritrix,":[162],"an":[163],"open":[164],"source":[165],"crawler,":[166],"needs":[169],"project.":[172],"Our":[173],"experimental":[174],"results":[175],"real":[177],"crawls":[178],"show":[179],"effective":[185],"in":[186],"acquiring":[187],"focused":[188],"about":[190],"topic":[192],"leveraging":[194],"media.":[199]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
