{"id":"https://openalex.org/W4241558715","doi":"https://doi.org/10.1145/1242572.1242588","title":"Do not crawl in the dust","display_name":"Do not crawl in the dust","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W4241558715","doi":"https://doi.org/10.1145/1242572.1242588"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","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/A5054834255","display_name":"Ziv Bar-Yossef","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117425","display_name":"Google (Israel)","ror":"https://ror.org/02c20ys54","country_code":"IL","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210117425","https://openalex.org/I4210128969"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ziv Bar-Yossef","raw_affiliation_strings":["Technion and Google, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion and Google, Haifa, Israel","institution_ids":["https://openalex.org/I4210117425"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059238786","display_name":"Idit Keidar","orcid":"https://orcid.org/0000-0002-6417-1250"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Idit Keidar","raw_affiliation_strings":["Technion, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052102699","display_name":"Uri Schonfeld","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Uri Schonfeld","raw_affiliation_strings":["UCLA, Log Angeles, CA"],"affiliations":[{"raw_affiliation_string":"UCLA, Log Angeles, CA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054834255"],"corresponding_institution_ids":["https://openalex.org/I4210117425"],"apc_list":null,"apc_paid":null,"fwci":14.1658,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.98598724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"120"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9955999851226807,"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":0.9934999942779541,"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/crawling","display_name":"Crawling","score":0.8540893793106079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7933081984519958},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7456055283546448},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.7418948411941528},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6834153532981873},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5638886094093323},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5575655698776245},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5438613891601562},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5290055871009827},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5288302302360535},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5180587768554688},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5075486898422241},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.49650055170059204},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.4371755123138428},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.3983810842037201},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.21590900421142578},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.21129411458969116},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.14920473098754883},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1460667848587036}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8540893793106079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933081984519958},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7456055283546448},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.7418948411941528},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6834153532981873},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5638886094093323},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5575655698776245},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5438613891601562},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5290055871009827},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5288302302360535},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5180587768554688},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5075486898422241},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.49650055170059204},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.4371755123138428},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.3983810842037201},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.21590900421142578},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.21129411458969116},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.14920473098754883},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1460667848587036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1242572.1242588","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1536700701","https://openalex.org/W1546842576","https://openalex.org/W1597291463","https://openalex.org/W1991548210","https://openalex.org/W1997438973","https://openalex.org/W2007842132","https://openalex.org/W2011039300","https://openalex.org/W2087303323","https://openalex.org/W2112104357","https://openalex.org/W2136774890","https://openalex.org/W2152505903","https://openalex.org/W2164634022","https://openalex.org/W4250366158","https://openalex.org/W6609796234","https://openalex.org/W6628750762","https://openalex.org/W6685115719"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W2095543197","https://openalex.org/W2371838993","https://openalex.org/W1770021664","https://openalex.org/W2980544443","https://openalex.org/W2070988406"],"abstract_inverted_index":{"We":[0,38],"consider":[1],"the":[2,31,103,112],"problem":[3],"of":[4,105,114],"DUST:":[5],"Different":[6],"URLs":[7,13],"with":[8],"Similar":[9],"Text.":[10],"Such":[11],"duplicate":[12],"are":[14,60],"prevalent":[15],"in":[16],"web":[17,20,75,91],"sites,":[18],"as":[19,118],"server":[21,76],"software":[22],"often":[23],"uses":[24],"aliases":[25],"and":[26,28,110],"redirections,":[27],"dynamically":[29],"generates":[30],"same":[32],"page":[33,80],"from":[34,70,97],"various":[35],"different":[36],"URLrequests.":[37],"present":[39],"a":[40,54],"novel":[41],"algorithm,":[42],"DustBuster,":[43],"for":[44,49],"uncovering":[45],"DUST;":[46],"that":[47,52,59],"is,":[48],"discovering":[50],"rules":[51,84],"transform":[53],"given":[55],"URL":[56],"to":[57,62,101],"others":[58],"likely":[61],"have":[63],"similar":[64],"content.":[65],"DustBuster":[66],"mines":[67],"DUST":[68,100],"effectively":[69],"previous":[71],"crawl":[72],"logs":[73],"or":[74],"logs,":[77],"without":[78],"examining":[79],"contents.":[81],"Verifying":[82],"these":[83],"via":[85],"sampling":[86],"requires":[87],"fetching":[88],"few":[89],"actual":[90],"pages.":[92],"Search":[93],"engines":[94],"can":[95],"benefit":[96],"information":[98],"about":[99],"increase":[102],"effectiveness":[104],"crawling,":[106],"reduce":[107],"indexing":[108],"overhead,":[109],"improve":[111],"quality":[113],"popularity":[115],"statistics":[116],"such":[117],"PageRank.":[119]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}
