{"id":"https://openalex.org/W2159185913","doi":"https://doi.org/10.1145/1242572.1242726","title":"A large-scale study of robots.txt","display_name":"A large-scale study of robots.txt","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2159185913","doi":"https://doi.org/10.1145/1242572.1242726","mag":"2159185913"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242726","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/A5102285974","display_name":"Yang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yang Sun","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102106448","display_name":"Ziming Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziming Zhuang","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102285974"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":9.9572,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97769318,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1123","last_page":"1124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9901999831199646,"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/T13976","display_name":"Web visibility and informetrics","score":0.9883999824523926,"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/scale","display_name":"Scale (ratio)","score":0.6312671303749084},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5965325236320496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5603078603744507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36495262384414673},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10072001814842224},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06342092156410217}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6312671303749084},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5965325236320496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5603078603744507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36495262384414673},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10072001814842224},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06342092156410217}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1242572.1242726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242726","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.3649","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.3649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://botseer.ist.psu.edu/pp1034-sun.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323032","display_name":"Asia University","ror":"https://ror.org/038a1tp19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W64454076","https://openalex.org/W1503924817","https://openalex.org/W2041257677","https://openalex.org/W2189431301"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2026800644","https://openalex.org/W2805209921","https://openalex.org/W2002867377","https://openalex.org/W2061090284","https://openalex.org/W2125579716","https://openalex.org/W2283860892","https://openalex.org/W4236636304","https://openalex.org/W3014116036","https://openalex.org/W322005410"],"abstract_inverted_index":{"Search":[0],"engines":[1],"largely":[2],"rely":[3],"on":[4],"Web":[5,108,113],"robots":[6,56,109],"to":[7,14,89],"collect":[8],"information":[9],"from":[10,33,75],"the":[11,15,20,34,39,62,91,98,105,112,120],"Web.":[12],"Due":[13],"unregulated":[16],"open-access":[17],"nature":[18],"of":[19,97,104,107,122],"Web,":[21],"robot":[22],"activities":[23,29],"are":[24],"extremely":[25],"diverse.":[26],"Such":[27],"crawling":[28],"can":[30],"be":[31],"regulated":[32],"server":[35],"side":[36],"by":[37],"deploying":[38],"Robots":[40],"Exclusion":[41],"Protocol":[42],"in":[43,65,87],"a":[44,102],"file":[45],"called":[46],"robots.txt.":[47,66],"Although":[48],"it":[49],"is":[50],"not":[51],"an":[52],"enforcement":[53],"standard,":[54],"ethical":[55],"(and":[57],"many":[58],"commercial)":[59],"will":[60],"follow":[61],"rules":[63,110],"specified":[64],"With":[67],"our":[68],"focused":[69],"crawler,":[70],"we":[71,100],"investigate":[72],"7,593":[73],"websites":[74],"education,":[76],"government,":[77],"news,":[78],"and":[79],"business":[80],"domains.":[81],"Five":[82],"crawls":[83],"have":[84],"been":[85],"conducted":[86],"succession":[88],"study":[90],"temporal":[92],"changes.":[93],"Through":[94],"statistical":[95],"analysis":[96],"data,":[99],"present":[101],"survey":[103],"usage":[106,121],"at":[111],"scale.":[114],"The":[115],"results":[116],"also":[117],"show":[118],"that":[119],"robots.txt":[123],"has":[124],"increased":[125],"over":[126],"time.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
