{"id":"https://openalex.org/W2075925923","doi":"https://doi.org/10.1108/17440080680000104","title":"Web crawlers compared","display_name":"Web crawlers compared","publication_year":2006,"publication_date":"2006-05-01","ids":{"openalex":"https://openalex.org/W2075925923","doi":"https://doi.org/10.1108/17440080680000104","mag":"2075925923"},"language":"en","primary_location":{"id":"doi:10.1108/17440080680000104","is_oa":false,"landing_page_url":"https://doi.org/10.1108/17440080680000104","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","raw_type":"journal-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/A5103605513","display_name":"Christian Girardi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Christian Girardi","raw_affiliation_strings":["ITC\u2010irst, Istituto per la Ricerca Scientifica e Tecnologica, Via Sommarive 18 \u2010 38050 Povo (Trento), Italy"],"affiliations":[{"raw_affiliation_string":"ITC\u2010irst, Istituto per la Ricerca Scientifica e Tecnologica, Via Sommarive 18 \u2010 38050 Povo (Trento), Italy","institution_ids":["https://openalex.org/I4210097842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019306962","display_name":"Filippo Ricca","orcid":"https://orcid.org/0000-0002-3928-5408"},"institutions":[{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Filippo Ricca","raw_affiliation_strings":["ITC\u2010irst, Istituto per la Ricerca Scientifica e Tecnologica, Via Sommarive 18 \u2010 38050 Povo (Trento), Italy"],"affiliations":[{"raw_affiliation_string":"ITC\u2010irst, Istituto per la Ricerca Scientifica e Tecnologica, Via Sommarive 18 \u2010 38050 Povo (Trento), Italy","institution_ids":["https://openalex.org/I4210097842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025438762","display_name":"Paolo Tonella","orcid":"https://orcid.org/0000-0003-3088-0339"},"institutions":[{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Tonella","raw_affiliation_strings":["ITC\u2010irst, Istituto per la Ricerca Scientifica e Tecnologica, Via Sommarive 18 \u2010 38050 Povo (Trento), Italy"],"affiliations":[{"raw_affiliation_string":"ITC\u2010irst, Istituto per la Ricerca Scientifica e Tecnologica, Via Sommarive 18 \u2010 38050 Povo (Trento), Italy","institution_ids":["https://openalex.org/I4210097842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103605513"],"corresponding_institution_ids":["https://openalex.org/I4210097842"],"apc_list":null,"apc_paid":null,"fwci":2.5819,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91461975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":"2","first_page":"85","last_page":"94"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9825999736785889,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9799000024795532,"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/computer-science","display_name":"Computer science","score":0.8500417470932007},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8028242588043213},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6637892127037048},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.558853030204773},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.5286688804626465},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.5178182721138},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5140737295150757},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.501561164855957},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.488839328289032},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.4736943244934082},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.45675501227378845},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.45102447271347046},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3481885492801666},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34483659267425537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500417470932007},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8028242588043213},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6637892127037048},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.558853030204773},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.5286688804626465},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.5178182721138},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5140737295150757},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.501561164855957},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.488839328289032},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.4736943244934082},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45675501227378845},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.45102447271347046},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3481885492801666},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34483659267425537},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1108/17440080680000104","is_oa":false,"landing_page_url":"https://doi.org/10.1108/17440080680000104","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:iris.unige.it:11567/284523","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/284523","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1516626990","https://openalex.org/W1613836731","https://openalex.org/W1728303734","https://openalex.org/W1900564928","https://openalex.org/W1966598450","https://openalex.org/W1983557808","https://openalex.org/W1994066579","https://openalex.org/W2000273502","https://openalex.org/W2022631875","https://openalex.org/W2032078682","https://openalex.org/W2079333567","https://openalex.org/W2125000816","https://openalex.org/W2135151043","https://openalex.org/W2144378488","https://openalex.org/W2153717260","https://openalex.org/W2164542999","https://openalex.org/W2170188121","https://openalex.org/W2295141584","https://openalex.org/W4245759828","https://openalex.org/W4383905551"],"related_works":["https://openalex.org/W2186697381","https://openalex.org/W175372466","https://openalex.org/W2388966984","https://openalex.org/W2611656663","https://openalex.org/W2117924798","https://openalex.org/W2187606868","https://openalex.org/W2182758442","https://openalex.org/W2520851676","https://openalex.org/W2093406613","https://openalex.org/W2021161024"],"abstract_inverted_index":{"Tools":[0],"for":[1,53,83],"the":[2,5,15,19,22,46,64,68,105],"assessment":[3],"of":[4,9,17,21,77,104],"quality":[6],"and":[7,38,60,72,80],"reliability":[8],"Web":[10,28,36,55,69,84,107],"applications":[11],"are":[12,57],"based":[13],"on":[14],"possibility":[16],"downloading":[18],"target":[20],"analysis.":[23],"This":[24],"is":[25],"achieved":[26],"through":[27],"crawlers,":[29],"which":[30,100],"can":[31],"automatically":[32],"navigate":[33],"within":[34],"a":[35,54],"site":[37,70,85],"perform":[39],"proper":[40],"actions":[41],"(such":[42],"as":[43],"download)":[44],"during":[45],"visit.":[47],"The":[48,75],"most":[49],"important":[50],"performance":[51],"indicators":[52,90],"crawler":[56],"its":[58],"completeness":[59],"robustness,":[61],"measuring":[62],"respectively":[63],"ability":[65],"to":[66,92],"visit":[67],"entirely":[71],"without":[73],"errors.":[74],"variety":[76],"implementation":[78],"languages":[79],"technologies":[81],"used":[82],"development":[86],"makes":[87],"these":[88],"two":[89],"hard":[91],"maximize.":[93],"We":[94],"conducted":[95],"an":[96],"evaluation":[97],"study,":[98],"in":[99],"we":[101],"tested":[102],"several":[103],"available":[106],"crawlers.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
