{"id":"https://openalex.org/W2140077965","doi":"https://doi.org/10.1145/1148170.1148223","title":"Structure-driven crawler generation by example","display_name":"Structure-driven crawler generation by example","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2140077965","doi":"https://doi.org/10.1145/1148170.1148223","mag":"2140077965"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5013954836","display_name":"M\u00e1rcio L. A. Vidal","orcid":"https://orcid.org/0000-0003-0463-4812"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"M\u00e1rcio L. A. Vidal","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus -- Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus -- Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015763962","display_name":"Altigran S. da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Altigran S. da Silva","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus -- Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus -- Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015781017","display_name":"Edleno Silva de Moura","orcid":"https://orcid.org/0000-0002-7860-9575"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edleno S. de Moura","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus -- Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus -- Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101933416","display_name":"Jo\u00e3o M. B. Cavalcanti","orcid":"https://orcid.org/0000-0003-1424-2230"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o M. B. Cavalcanti","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus -- Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus -- Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013954836"],"corresponding_institution_ids":["https://openalex.org/I62885914"],"apc_list":null,"apc_paid":null,"fwci":13.1335,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98290867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"292","last_page":"299"},"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":0.9854000210762024,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9528999924659729,"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/web-crawler","display_name":"Web crawler","score":0.9243613481521606},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.8861590623855591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7757445573806763},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7538085579872131},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.7040383219718933},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6410671472549438},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6066293120384216},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5679080486297607},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5547013282775879},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4855794310569763},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.462558388710022},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.44232267141342163},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.23479196429252625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05771276354789734}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9243613481521606},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8861590623855591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757445573806763},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7538085579872131},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.7040383219718933},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6410671472549438},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6066293120384216},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5679080486297607},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5547013282775879},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4855794310569763},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.462558388710022},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.44232267141342163},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.23479196429252625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05771276354789734},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1148170.1148223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1513707202","https://openalex.org/W1599730494","https://openalex.org/W1973625941","https://openalex.org/W2007687650","https://openalex.org/W2017726337","https://openalex.org/W2022120051","https://openalex.org/W2048001624","https://openalex.org/W2049365470","https://openalex.org/W2049461910","https://openalex.org/W2057308086","https://openalex.org/W2066309116","https://openalex.org/W2108584692","https://openalex.org/W2110780226","https://openalex.org/W2128915886","https://openalex.org/W2129595335","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W2157752164","https://openalex.org/W4243938628"],"related_works":["https://openalex.org/W4248730791","https://openalex.org/W1506122440","https://openalex.org/W2377634017","https://openalex.org/W2088345472","https://openalex.org/W2092706362","https://openalex.org/W2023856424","https://openalex.org/W2371838993","https://openalex.org/W2388966984","https://openalex.org/W2064214115","https://openalex.org/W2166088942"],"abstract_inverted_index":{"Many":[0],"Web":[1,26,87,112],"IR":[2],"and":[3,106,114],"Digital":[4],"Library":[5],"applications":[6,32],"require":[7],"a":[8,38,45,66,82,91,103,111,116,129],"crawling":[9,72],"process":[10,73],"to":[11,35,41,49,69,99,110,132,134,140,160],"collect":[12,161],"pages":[13,64,137,163,171],"with":[14],"the":[15,33,50,59,63,71,127,136,141,145,166],"ultimate":[16],"goal":[17],"of":[18,21,30,62,124],"taking":[19],"advantage":[20],"useful":[22],"information":[23],"available":[24],"on":[25,120],"sites.":[27],"For":[28],"some":[29],"these":[31],"criteria":[34,68],"determine":[36],"when":[37],"page":[39,51,105],"is":[40,98],"be":[42],"present":[43,81],"in":[44,57],"collection":[46],"are":[47,55],"related":[48],"content.":[52,76],"However,":[53],"there":[54],"situations":[56],"which":[58],"inner":[60],"structure":[61],"provides":[65],"better":[67],"guide":[70],"than":[74],"their":[75,174],"In":[77,144],"this":[78],"paper,":[79],"we":[80,147],"structure-driven":[83,117,151],"approach":[84,157],"for":[85,126],"generating":[86],"crawlers":[88,152],"that":[89,164],"requires":[90],"minimum":[92],"effort":[93],"from":[94],"users.":[95],"The":[96],"idea":[97],"take":[100],"as":[101],"input":[102],"sample":[104,142],"an":[107],"entry":[108],"point":[109],"site":[113],"generate":[115],"crawler":[118,130],"based":[119],"navigation":[121],"patterns,":[122],"sequences":[123],"patterns":[125],"links":[128],"has":[131],"follow":[133],"reach":[135],"structurally":[138],"similar":[139],"page.":[143],"experiments":[146],"have":[148],"carried":[149],"out,":[150],"generated":[153],"by":[154],"our":[155],"new":[156],"were":[158],"able":[159],"all":[162],"match":[165],"samples":[167],"given,":[168],"including":[169],"those":[170],"added":[172],"after":[173],"generation.":[175]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
