{"id":"https://openalex.org/W2965892115","doi":"https://doi.org/10.23919/tma.2019.8784660","title":"Kraaler: A User-Perspective Web Crawler","display_name":"Kraaler: A User-Perspective Web Crawler","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2965892115","doi":"https://doi.org/10.23919/tma.2019.8784660","mag":"2965892115"},"language":"en","primary_location":{"id":"doi:10.23919/tma.2019.8784660","is_oa":false,"landing_page_url":"https://doi.org/10.23919/tma.2019.8784660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Network Traffic Measurement and Analysis Conference (TMA)","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/A5051503339","display_name":"Thomas Kobber Panum","orcid":null},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Thomas Kobber Panum","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051122243","display_name":"Ren\u00e9 Rydhof Hansen","orcid":"https://orcid.org/0000-0002-5688-6432"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rene Rydhof Hansen","raw_affiliation_strings":["Department of Computer Science, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034797912","display_name":"Jens Myrup Pedersen","orcid":"https://orcid.org/0000-0002-1903-2921"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jens Myrup Pedersen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051503339"],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":1.4088,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86608669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"160"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9829000234603882,"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/T11478","display_name":"Caching and Content Delivery","score":0.9746000170707703,"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":0.8518368005752563},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.845356822013855},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6197814345359802},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5879384875297546},{"id":"https://openalex.org/keywords/comet","display_name":"Comet","score":0.5322693586349487},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5123254060745239},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.47264567017555237},{"id":"https://openalex.org/keywords/web-api","display_name":"Web API","score":0.46205204725265503},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.431723415851593},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4228779375553131},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4117448031902313},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3693541884422302},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1329163908958435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518368005752563},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.845356822013855},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6197814345359802},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5879384875297546},{"id":"https://openalex.org/C94081185","wikidata":"https://www.wikidata.org/wiki/Q3559","display_name":"Comet","level":2,"score":0.5322693586349487},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5123254060745239},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.47264567017555237},{"id":"https://openalex.org/C127613066","wikidata":"https://www.wikidata.org/wiki/Q557770","display_name":"Web API","level":4,"score":0.46205204725265503},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.431723415851593},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4228779375553131},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4117448031902313},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3693541884422302},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1329163908958435},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/tma.2019.8784660","is_oa":false,"landing_page_url":"https://doi.org/10.23919/tma.2019.8784660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Network Traffic Measurement and Analysis Conference (TMA)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/02e7c7cf-7877-4369-9da2-1ca2bf93f18d","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/02e7c7cf-7877-4369-9da2-1ca2bf93f18d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Panum , T K , Hansen , R R &amp; Pedersen , J M 2019 , Kraaler: A User-Perspective Web Crawler . in S Secci , I Chrisment , M Fiore , L Tabourier &amp; K-W Lim (eds) , 2019 Network Traffic Measurement and Analysis Conference (TMA) . , 8784660 , IEEE , pp. 153-160 , 2019 Network Traffic Measurement and Analysis Conference (TMA) , Paris , France , 19/06/2019 . https://doi.org/10.23919/TMA.2019.8784660","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1613836731","https://openalex.org/W1807253697","https://openalex.org/W2072764742","https://openalex.org/W2096791889","https://openalex.org/W2106390192","https://openalex.org/W2107549403","https://openalex.org/W2125958378","https://openalex.org/W2258998514","https://openalex.org/W2743928556","https://openalex.org/W6675652131"],"related_works":["https://openalex.org/W1593328609","https://openalex.org/W1963685508","https://openalex.org/W2074126298","https://openalex.org/W2167278502","https://openalex.org/W2169405834","https://openalex.org/W2102691836","https://openalex.org/W2404573736","https://openalex.org/W2389737178","https://openalex.org/W2106737497","https://openalex.org/W2535301253"],"abstract_inverted_index":{"Adaption":[0],"of":[1,72,124],"technologies":[2],"being":[3],"used":[4],"on":[5,91],"the":[6,16,65,70,73,92,96,109,122,125],"web":[7,17,30,40,45,61],"is":[8],"changing":[9],"frequently,":[10],"requiring":[11],"applications":[12],"that":[13,50,63],"interact":[14],"with":[15,47],"to":[18,23,32,105],"continuously":[19],"change":[20],"their":[21],"ability":[22],"parse":[24],"it.":[25],"This":[26],"has":[27,98,114],"led":[28],"most":[29],"crawlers":[31],"either":[33],"inherent":[34],"simplistic":[35],"parsing":[36,126],"capabilities,":[37],"differentiating":[38],"from":[39],"browsers,":[41],"or":[42],"use":[43,71],"a":[44,88,102,118],"browser":[46,75],"high-level":[48],"interactions":[49],"restricts":[51],"observable":[52],"information.":[53,82],"We":[54],"introduce":[55],"Kraaler,":[56],"an":[57],"open":[58],"source":[59],"universal":[60],"crawler":[62,84],"uses":[64],"Chrome":[66],"Debugging":[67],"Protocol,":[68],"enabling":[69],"Blink":[74],"engine":[76],"for":[77,128],"parsing,":[78],"while":[79],"obtaining":[80],"protocol-level":[81],"The":[83],"stores":[85],"information":[86],"in":[87,101,108,117],"database":[89],"and":[90,95],"file":[93],"system":[94],"implementation":[97],"been":[99,115],"evaluated":[100,116],"predictable":[103],"environment":[104],"ensure":[106],"correctness":[107],"collected":[110],"data.":[111],"Additionally,":[112],"it":[113],"real-world":[119],"scenario,":[120],"demonstrating":[121],"impact":[123],"capabilities":[127],"data":[129],"collection.":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
