{"id":"https://openalex.org/W2022808337","doi":"https://doi.org/10.2298/csis111215015p","title":"A scale for crawler effectiveness on the client-side hidden web","display_name":"A scale for crawler effectiveness on the client-side hidden web","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2022808337","doi":"https://doi.org/10.2298/csis111215015p","mag":"2022808337"},"language":"en","primary_location":{"id":"doi:10.2298/csis111215015p","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis111215015p","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200015P","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200015P","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014748851","display_name":"V\u00edctor Prieto","orcid":null},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"V\u00edctor Prieto","raw_affiliation_strings":["Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786992","display_name":"Manuel \u00c1lvarez","orcid":"https://orcid.org/0000-0001-7204-2689"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel \u00c1lvarez","raw_affiliation_strings":["Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104357873","display_name":"Rafael L\u00f3pez-Garc\u00eda","orcid":null},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rafael L\u00f3pez-Garc\u00eda","raw_affiliation_strings":["Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070668196","display_name":"Fidel Cacheda","orcid":"https://orcid.org/0000-0002-6438-1661"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fidel Cacheda","raw_affiliation_strings":["Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Comunication and Information Technologies Department, University of A Coru\u00f1a Campus de Elvi, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014748851"],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":null,"apc_paid":null,"fwci":3.5527,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9329024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":"2","first_page":"561","last_page":"583"},"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":0.9717000126838684,"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":0.9700999855995178,"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":0.9152464866638184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8579486012458801},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7491899132728577},{"id":"https://openalex.org/keywords/client-side","display_name":"Client-side","score":0.6494036316871643},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.6292536854743958},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.591842770576477},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5917707085609436},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5850013494491577},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5654206275939941},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5033239722251892},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41230344772338867},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.358553946018219},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32953035831451416},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.26870638132095337},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.14734864234924316}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9152464866638184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579486012458801},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7491899132728577},{"id":"https://openalex.org/C202477664","wikidata":"https://www.wikidata.org/wiki/Q1352449","display_name":"Client-side","level":2,"score":0.6494036316871643},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.6292536854743958},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.591842770576477},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5917707085609436},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5850013494491577},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5654206275939941},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5033239722251892},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41230344772338867},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.358553946018219},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32953035831451416},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.26870638132095337},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.14734864234924316},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.2298/csis111215015p","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis111215015p","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200015P","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:doiserbia:1820-02141200015P","is_oa":false,"landing_page_url":"http://doi.org/10.2298/CSIS111215015P","pdf_url":null,"source":{"id":"https://openalex.org/S4306400515","display_name":"Digital Object Identifier (DOI) Repository Serbia (National Library of Serbia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210142455","host_organization_name":"National Library of Serbia","host_organization_lineage":["https://openalex.org/I4210142455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":". 9(2) 561-583"}],"best_oa_location":{"id":"doi:10.2298/csis111215015p","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis111215015p","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200015P","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2022808337.pdf","grobid_xml":"https://content.openalex.org/works/W2022808337.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W38924359","https://openalex.org/W608337257","https://openalex.org/W1560262122","https://openalex.org/W1589680802","https://openalex.org/W1596028570","https://openalex.org/W1598498208","https://openalex.org/W1854214752","https://openalex.org/W2039219947","https://openalex.org/W2093809932","https://openalex.org/W2094930182","https://openalex.org/W2125969310","https://openalex.org/W2132605240","https://openalex.org/W2139148100","https://openalex.org/W2139731740","https://openalex.org/W2148738951","https://openalex.org/W2160988289","https://openalex.org/W2161433768","https://openalex.org/W2169270715","https://openalex.org/W2170188121","https://openalex.org/W2404900683","https://openalex.org/W3002668116"],"related_works":["https://openalex.org/W1506122440","https://openalex.org/W137473381","https://openalex.org/W3171934134","https://openalex.org/W2186692612","https://openalex.org/W3184561988","https://openalex.org/W1598498208","https://openalex.org/W1564728522","https://openalex.org/W2772576376","https://openalex.org/W2022808337","https://openalex.org/W2051135816"],"abstract_inverted_index":{"The":[0],"main":[1,38,164],"goal":[2],"of":[3,31,40,51,66,79,86,101,162,171,196,219,234,236],"this":[4],"study":[5],"is":[6,150],"to":[7,16,46,75,83,106,118,152,159,199,216],"present":[8,91],"a":[9,28,92,123],"scale":[10,59,227],"that":[11,116,192],"classifies":[12],"crawling":[13],"systems":[14],"according":[15,82],"their":[17],"effectiveness":[18,78],"in":[19,44,64,129],"traversing":[20],"the":[21,32,37,41,48,52,58,77,80,84,87,99,103,107,120,138,145,160,163,172,184,194,197,217,225,232,237],"?clientside?":[22],"Hidden":[23],"Web.":[24],"First,":[25],"we":[26,56,71,90,97,136,174],"perform":[27],"thorough":[29],"analysis":[30],"different":[33],"client-side":[34,131,202,240],"technologies":[35],"and":[36,70,96,113,142,144,179,212],"features":[39],"web":[42,94],"pages":[43],"order":[45],"determine":[47],"basic":[49,62,185],"steps":[50],"aforementioned":[53,104],"scale.":[54,88],"Then,":[55],"define":[57],"by":[60,110],"grouping":[61],"scenarios":[63,173],"terms":[65],"several":[67],"common":[68],"features,":[69],"propose":[72],"some":[73,111],"methods":[74,105],"evaluate":[76],"crawlers":[81,115,125,140,161,198,211,230],"levels":[85],"Finally,":[89],"testing":[93],"site":[95],"show":[98],"results":[100,108,128],"applying":[102],"obtained":[109],"open-source":[112,139],"commercial":[114,146],"tried":[117],"traverse":[119],"pages.":[121],"Only":[122],"few":[124],"achieve":[126],"good":[127],"treating":[130],"technologies.":[132,203,241],"Regarding":[133],"standalone":[134],"crawlers,":[135],"highlight":[137],"Heritrix":[141],"Nutch":[143],"crawler":[147],"WebCopierPro,":[148],"which":[149],"able":[151],"process":[153],"very":[154],"complex":[155],"scenarios.":[156],"With":[157],"regard":[158],"search":[165],"engines,":[166],"only":[167],"Google":[168],"processes":[169],"most":[170,238],"have":[175],"proposed,":[176],"while":[177],"Yahoo!":[178],"Bing":[180],"just":[181],"deal":[182,200],"with":[183,201],"ones.":[186],"There":[187],"are":[188],"not":[189],"many":[190],"studies":[191,206],"assess":[193],"capacity":[195],"Also,":[204],"these":[205],"consider":[207],"fewer":[208,210,213],"technologies,":[209],"combinations.":[214],"Furthermore,":[215],"best":[218],"our":[220,222],"knowledge,":[221],"article":[223],"provides":[224],"first":[226],"for":[228],"classifying":[229],"from":[231],"point":[233],"view":[235],"important":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
