{"id":"https://openalex.org/W2110073539","doi":"https://doi.org/10.1109/webmed.2004.1348139","title":"Scheduling algorithms for web crawling","display_name":"Scheduling algorithms for web crawling","publication_year":2004,"publication_date":"2004-11-08","ids":{"openalex":"https://openalex.org/W2110073539","doi":"https://doi.org/10.1109/webmed.2004.1348139","mag":"2110073539"},"language":"en","primary_location":{"id":"doi:10.1109/webmed.2004.1348139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/webmed.2004.1348139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"WebMedia and LA-Web, 2004. Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","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/A5084282503","display_name":"Carlos Castillo","orcid":"https://orcid.org/0000-0003-4544-0416"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"C. Castillo","raw_affiliation_strings":["Center for Web Research, Universidad de Chile, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Web Research, Universidad de Chile, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044981704","display_name":"Mauricio Mar\u0131\u0301n","orcid":"https://orcid.org/0000-0003-0662-7149"},"institutions":[{"id":"https://openalex.org/I63471342","display_name":"Universidad de Magallanes","ror":"https://ror.org/049784n50","country_code":"CL","type":"education","lineage":["https://openalex.org/I63471342"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"M. Marin","raw_affiliation_strings":["Center for Web Research, Universidad de Magallanes, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Web Research, Universidad de Magallanes, Chile","institution_ids":["https://openalex.org/I63471342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075776649","display_name":"M. Andrea Rodr\u00edguez","orcid":"https://orcid.org/0000-0002-8729-5977"},"institutions":[{"id":"https://openalex.org/I172787465","display_name":"University of Concepci\u00f3n","ror":"https://ror.org/0460jpj73","country_code":"CL","type":"education","lineage":["https://openalex.org/I172787465"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"A. Rodriguez","raw_affiliation_strings":["Center for Web Research, Universidad de Concepci\u00f2n, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Web Research, Universidad de Concepci\u00f2n, Chile","institution_ids":["https://openalex.org/I172787465"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"10","last_page":"17"},"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":0.9937999844551086,"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":0.9854999780654907,"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/computer-science","display_name":"Computer science","score":0.8764927983283997},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8579992651939392},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5338519811630249},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4964211583137512},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4304003119468689},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4277839660644531},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34220609068870544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8764927983283997},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8579992651939392},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5338519811630249},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4964211583137512},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4304003119468689},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4277839660644531},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34220609068870544},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/webmed.2004.1348139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/webmed.2004.1348139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"WebMedia and LA-Web, 2004. Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.6387","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.6387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ona.fi.umag.cl/~mmarin/papers/submitted1.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.1782","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.1782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.uchile.cl/~ccastill/papers/castillo04_scheduling_algorithms_web_crawling.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W13754670","https://openalex.org/W110443600","https://openalex.org/W207751643","https://openalex.org/W1546842576","https://openalex.org/W1561637629","https://openalex.org/W1566984846","https://openalex.org/W1578539484","https://openalex.org/W1583640058","https://openalex.org/W1591738266","https://openalex.org/W1613836731","https://openalex.org/W1942958706","https://openalex.org/W1983416950","https://openalex.org/W1987272746","https://openalex.org/W2007687650","https://openalex.org/W2013531639","https://openalex.org/W2016122268","https://openalex.org/W2018928332","https://openalex.org/W2023162794","https://openalex.org/W2029341294","https://openalex.org/W2033289350","https://openalex.org/W2051804774","https://openalex.org/W2054792115","https://openalex.org/W2059713800","https://openalex.org/W2066636486","https://openalex.org/W2079333567","https://openalex.org/W2085736401","https://openalex.org/W2089800021","https://openalex.org/W2105533042","https://openalex.org/W2124379907","https://openalex.org/W2124673015","https://openalex.org/W2132749631","https://openalex.org/W2134308336","https://openalex.org/W2137526809","https://openalex.org/W2138745909","https://openalex.org/W2144189905","https://openalex.org/W2147164982","https://openalex.org/W2151626491","https://openalex.org/W2157748587","https://openalex.org/W2158601853","https://openalex.org/W2164542999","https://openalex.org/W2169189540","https://openalex.org/W2170188121","https://openalex.org/W2175110005","https://openalex.org/W2295141584","https://openalex.org/W4250366158","https://openalex.org/W4251434705","https://openalex.org/W4285719527","https://openalex.org/W6604611248","https://openalex.org/W6608432322","https://openalex.org/W6632830464","https://openalex.org/W6634031162","https://openalex.org/W6634775382","https://openalex.org/W6678701036","https://openalex.org/W6680514838","https://openalex.org/W6684482986","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W4393220254","https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W2171573941","https://openalex.org/W4317382653","https://openalex.org/W4385695127","https://openalex.org/W2000745862"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,14,25,44,60,108],"comparative":[4],"study":[5,56],"of":[6,16,63,95,114],"strategies":[7,76],"for":[8,111],"Web":[9,66],"crawling.":[10],"We":[11,90],"show":[12],"that":[13,46,74],"combination":[15],"breadth-first":[17],"ordering":[18],"with":[19],"the":[20,39,50,64,80,93,100],"largest":[21],"sites":[22],"first":[23],"is":[24,30,47],"practical":[26],"alternative":[27],"since":[28],"it":[29],"fast,":[31],"simple":[32],"to":[33,37,49,86],"implement,":[34],"and":[35,83,104],"able":[36],"retrieve":[38],"best":[40],"ranked":[41],"pages":[42],"at":[43],"rate":[45],"closer":[48],"optimal":[51],"than":[52],"other":[53],"alternatives.":[54],"Our":[55],"was":[57,68],"performed":[58],"on":[59],"large":[61,96],"sample":[62],"Chilean":[65],"which":[67],"crawled":[69],"by":[70],"using":[71],"simulators,":[72],"so":[73],"all":[75],"were":[77],"compared":[78],"under":[79],"same":[81],"conditions,":[82],"actual":[84],"crawls":[85],"validate":[87],"our":[88],"conclusions.":[89],"also":[91],"explored":[92],"effects":[94],"scale":[97],"parallelism":[98],"in":[99,107],"page":[101],"retrieval":[102],"task":[103],"multiple-page":[105],"requests":[106],"single":[109],"connection":[110],"effective":[112],"amortization":[113],"latency":[115],"times.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
