{"id":"https://openalex.org/W2127901684","doi":"https://doi.org/10.1145/1013367.1013441","title":"Design of a crawler with bounded bandwidth","display_name":"Design of a crawler with bounded bandwidth","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2127901684","doi":"https://doi.org/10.1145/1013367.1013441","mag":"2127901684"},"language":"en","primary_location":{"id":"doi:10.1145/1013367.1013441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","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/A5109267259","display_name":"Michelangelo Diligenti","orcid":null},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michelangelo Diligenti","raw_affiliation_strings":["Universit\u00e0 di Siena Via Roma, Siena, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Siena Via Roma, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080411641","display_name":"Marco Maggini","orcid":"https://orcid.org/0000-0002-6428-1265"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Maggini","raw_affiliation_strings":["Universit\u00e0 di Siena Via Roma, Siena, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Siena Via Roma, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071760315","display_name":"Filippo Maria Pucci","orcid":null},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Filippo Maria Pucci","raw_affiliation_strings":["Universit\u00e0 di Siena Via Roma, Siena, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Siena Via Roma, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020560480","display_name":"Franco Scarselli","orcid":"https://orcid.org/0000-0003-1307-0772"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franco Scarselli","raw_affiliation_strings":["Universit\u00e0 di Siena Via Roma, Siena, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Siena Via Roma, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109267259"],"corresponding_institution_ids":["https://openalex.org/I102064193"],"apc_list":null,"apc_paid":null,"fwci":1.6157,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89789881,"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":"292","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","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/T11478","display_name":"Caching and Content Delivery","score":0.9900000095367432,"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":0.9751999974250793,"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":0.9314457178115845},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.8207187652587891},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.7753965854644775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7370951175689697},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5033087134361267},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5016195774078369},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.33623507618904114},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32413071393966675},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.32163703441619873},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2310856282711029},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19351190328598022},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18122515082359314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12959042191505432},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.1086258590221405},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0621471107006073}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9314457178115845},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8207187652587891},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.7753965854644775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7370951175689697},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5033087134361267},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5016195774078369},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.33623507618904114},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32413071393966675},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32163703441619873},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2310856282711029},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19351190328598022},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18122515082359314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12959042191505432},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.1086258590221405},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0621471107006073},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1013367.1013441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.7211","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.7211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2004.org/proceedings/docs/2p292.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.581.3674","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.581.3674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nautilus.dii.unisi.it/pubblicazioni/files/conference/diligenti.pdf","raw_type":"text"},{"id":"pmh:oai:usiena-air.unisi.it:11365/36100","is_oa":false,"landing_page_url":"http://hdl.handle.net/11365/36100","pdf_url":null,"source":{"id":"https://openalex.org/S4377196319","display_name":"Use Siena air (University of Siena)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102064193","host_organization_name":"University of Siena","host_organization_lineage":["https://openalex.org/I102064193"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1485536830","https://openalex.org/W2007687650","https://openalex.org/W2029341294","https://openalex.org/W2029500199","https://openalex.org/W2124673015","https://openalex.org/W2164542999"],"related_works":["https://openalex.org/W1501777393","https://openalex.org/W2042034567","https://openalex.org/W2102887023","https://openalex.org/W2548443989","https://openalex.org/W2375180657","https://openalex.org/W3169657889","https://openalex.org/W2527201306","https://openalex.org/W3201312643","https://openalex.org/W3179424333","https://openalex.org/W4385695127"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"algorithm":[4],"to":[5,24,37,47],"bound":[6],"the":[7,18,26,39,49,56,59],"bandwidth":[8,28],"of":[9,21,42,58],"a":[10],"Web":[11],"crawler.":[12],"The":[13,33,52],"crawler":[14],"collects":[15],"statistics":[16],"on":[17],"transfer":[19],"rate":[20],"each":[22],"server":[23],"predict":[25],"expected":[27],"use":[29],"for":[30],"future":[31],"downloads.":[32],"prediction":[34],"allows":[35],"us":[36],"activate":[38],"optimal":[40],"number":[41],"fetcher":[43],"threads":[44],"in":[45],"order":[46],"exploit":[48],"assigned":[50],"bandwidth.":[51],"experimental":[53],"results":[54],"show":[55],"effectiveness":[57],"proposed":[60],"technique.":[61]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
