{"id":"https://openalex.org/W2323426435","doi":"https://doi.org/10.1145/2837185.2837262","title":"Browser GUI for generating web data extraction rules in Ducky","display_name":"Browser GUI for generating web data extraction rules in Ducky","publication_year":2015,"publication_date":"2015-12-11","ids":{"openalex":"https://openalex.org/W2323426435","doi":"https://doi.org/10.1145/2837185.2837262","mag":"2323426435"},"language":"en","primary_location":{"id":"doi:10.1145/2837185.2837262","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837185.2837262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Information Integration and Web-based Applications &amp; Services","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/A5051793306","display_name":"Kei Kanaoka","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kei Kanaoka","raw_affiliation_strings":["Keio University, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Keio University, Yokohama, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103450436","display_name":"Motomichi Toyama","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Motomichi Toyama","raw_affiliation_strings":["Keio University, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Keio University, Yokohama, Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051793306"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":0.7946,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8318036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9922000169754028,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9681000113487244,"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":0.8636437654495239},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6372153162956238},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.6322892308235168},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49144089221954346},{"id":"https://openalex.org/keywords/cursor","display_name":"Cursor (databases)","score":0.4767920970916748},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.41741061210632324},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4103701710700989},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40295320749282837},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.397690087556839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8636437654495239},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6372153162956238},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.6322892308235168},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49144089221954346},{"id":"https://openalex.org/C2776990265","wikidata":"https://www.wikidata.org/wiki/Q2998101","display_name":"Cursor (databases)","level":2,"score":0.4767920970916748},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.41741061210632324},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4103701710700989},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40295320749282837},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.397690087556839},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2837185.2837262","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2837185.2837262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Information Integration and Web-based Applications &amp; Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1980773778","https://openalex.org/W2024091454","https://openalex.org/W2024569041"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173","https://openalex.org/W1544491176","https://openalex.org/W2185387300","https://openalex.org/W2363544243"],"abstract_inverted_index":{"To":[0,30],"benefit":[1],"from":[2,51,71,78,88],"the":[3,7,144,156],"invaluable":[4],"data":[5,41,50,59,63,69,80,83,129,145],"in":[6,134,154],"World":[8],"Wide":[9],"Web,":[10],"manual":[11],"extraction":[12,42,64,130],"or":[13,112],"creation":[14],"of":[15,102],"web":[16,46,52,74],"scraping":[17],"programs":[18],"may":[19],"be":[20,26],"necessary.":[21],"However,":[22],"these":[23],"processes":[24],"can":[25,67,109],"tedious":[27],"and":[28,54,81,132,150],"complicated.":[29],"address":[31],"these,":[32],"we":[33,94,139],"have":[34],"proposed":[35],"Ducky,":[36],"which":[37],"is":[38],"a":[39,45,96,105,114,135],"Web":[40],"system":[43],"including":[44],"wrapper":[47],"that":[48],"extracts":[49],"sources":[53],"translates":[55],"them":[56],"into":[57],"structured":[58,73],"based":[60],"on":[61],"user-defined":[62],"rules.":[65],"Ducky":[66],"extract":[68,143],"flexibly":[70],"various":[72],"pages,":[75],"remove":[76],"noise":[77],"extracted":[79],"integrate":[82],"distributed":[84],"to":[85,118,128,142],"multiple":[86],"pages":[87],"different":[89],"sites.":[90],"In":[91],"this":[92],"paper,":[93],"propose":[95],"browser":[97],"GUI":[98],"for":[99],"Ducky.":[100],"Instead":[101],"manually":[103],"writing":[104],"configuration":[106,136,157],"file,":[107],"users":[108,141],"just":[110],"click":[111],"point":[113],"cursor":[115],"(mouse":[116],"over)":[117],"objective":[119],"elements.":[120],"The":[121],"users'":[122,152],"actions":[123],"are":[124],"then":[125],"automatically":[126],"converted":[127],"rules":[131],"saved":[133],"file.":[137,158],"Thus,":[138],"help":[140],"by":[146],"allowing":[147],"intuitive":[148],"operations":[149],"reduce":[151],"burden":[153],"write":[155]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
