{"id":"https://openalex.org/W3092782196","doi":"https://doi.org/10.3233/jcm-204658","title":"UCrawler: A learning-based web crawler using a URL knowledge base","display_name":"UCrawler: A learning-based web crawler using a URL knowledge base","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3092782196","doi":"https://doi.org/10.3233/jcm-204658","mag":"3092782196"},"language":"en","primary_location":{"id":"doi:10.3233/jcm-204658","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jcm-204658","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","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/A5115590684","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-8676-1190"},"institutions":[{"id":"https://openalex.org/I4210165441","display_name":"Hangzhou Medical College","ror":"https://ror.org/05gpas306","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165441"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Computer Lab, Hangzhou Medical College, Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Computer Lab, Hangzhou Medical College, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210165441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102674412","display_name":"Lihua Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Yu","raw_affiliation_strings":["Netease Hangzhou Network Ltd., Hangzhou, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Netease Hangzhou Network Ltd., Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5115590684"],"corresponding_institution_ids":["https://openalex.org/I4210165441"],"apc_list":null,"apc_paid":null,"fwci":0.5338,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75483708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"21","issue":"2","first_page":"461","last_page":"474"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9786999821662903,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9487337470054626},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.942639946937561},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.8004249334335327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7981154918670654},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6152185797691345},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5184606909751892},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5108780264854431},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4787944257259369},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.386299192905426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2045019567012787},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.1847623586654663},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.08820351958274841}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9487337470054626},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.942639946937561},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.8004249334335327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981154918670654},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6152185797691345},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5184606909751892},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5108780264854431},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4787944257259369},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.386299192905426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2045019567012787},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.1847623586654663},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.08820351958274841},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jcm-204658","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jcm-204658","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6100000143051147,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W99860076","https://openalex.org/W1489992655","https://openalex.org/W1542053855","https://openalex.org/W1546584079","https://openalex.org/W1996718000","https://openalex.org/W1999267468","https://openalex.org/W2038643757","https://openalex.org/W2083089853","https://openalex.org/W2109487122","https://openalex.org/W2118230419","https://openalex.org/W2130221750","https://openalex.org/W2138621811","https://openalex.org/W2151809999","https://openalex.org/W2155293951","https://openalex.org/W2158420658","https://openalex.org/W2169917945","https://openalex.org/W2326804586","https://openalex.org/W2369627348","https://openalex.org/W2393874032","https://openalex.org/W2735787354","https://openalex.org/W6604185511","https://openalex.org/W6632686070","https://openalex.org/W6649450335"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Focused":[0],"crawlers,":[1],"as":[2],"fundamental":[3],"components":[4],"of":[5,28,31,55,59,97,115,144],"vertical":[6],"search":[7,136],"engines,":[8],"focus":[9],"on":[10,94],"crawling":[11,32,91],"the":[12,26,53,57,60,65,86,112,132,140],"web":[13],"pages":[14,33],"related":[15],"to":[16],"a":[17,42,47,90,95,125],"specific":[18],"topic.":[19],"Existing":[20],"focused":[21,44],"crawlers":[22],"commonly":[23],"suffer":[24],"from":[25],"problems":[27],"low":[29],"efficiency":[30],"and":[34,71,80,83,100,110,134,138],"subject":[35],"migration.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,88],"propose":[41],"learning-based":[43],"crawler":[45,104],"using":[46],"URL":[48,72,75],"knowledge":[49],"base.":[50],"To":[51],"improve":[52],"accuracy":[54],"similarity,":[56],"similarity":[58],"topic":[61],"is":[62,77],"measured":[63],"with":[64],"parent":[66],"page":[67],"content,":[68],"anchor":[69],"information,":[70],"content.":[73],"The":[74],"content":[76,98],"also":[78],"learned":[79],"updated":[81],"iteratively":[82],"continuously.":[84],"Within":[85],"crawler,":[87],"implement":[89],"mechanism":[92],"based":[93],"combination":[96],"analysis":[99,103],"simple":[101],"link":[102],"strategy,":[105],"which":[106],"decreases":[107],"computational":[108],"complexity":[109],"avoids":[111,139],"locality":[113],"problem":[114,143],"crawling.":[116,145],"Experimental":[117],"results":[118],"show":[119],"that":[120],"our":[121],"proposed":[122],"algorithm":[123],"achieves":[124],"better":[126],"precision":[127],"than":[128],"traditional":[129],"methods":[130],"including":[131],"shark-search":[133],"best-first":[135],"algorithms,":[137],"local":[141],"optimum":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
