{"id":"https://openalex.org/W2124291742","doi":"https://doi.org/10.1109/laweb.2003.1250304","title":"SharpSpider: spidering the Web through Web services","display_name":"SharpSpider: spidering the Web through Web services","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2124291742","doi":"https://doi.org/10.1109/laweb.2003.1250304","mag":"2124291742"},"language":"en","primary_location":{"id":"doi:10.1109/laweb.2003.1250304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/laweb.2003.1250304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/LEOS 3rd International Conference on Numerical Simulation of Semiconductor Optoelectronic Devices (IEEE Cat. No.03EX726)","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/A5110189849","display_name":"Ken Moody","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"K. Moody","raw_affiliation_strings":["Computer Laboratory, University of Cambridge, Cambridge, UK","[Comput. Lab., Cambridge Univ., UK]"],"affiliations":[{"raw_affiliation_string":"Computer Laboratory, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"[Comput. Lab., Cambridge Univ., UK]","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074811611","display_name":"Marco A. Palomino","orcid":"https://orcid.org/0000-0001-7850-416X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Palomino","raw_affiliation_strings":["Computer Laboratory, University of Cambridge, Cambridge, UK","[Comput. Lab., Cambridge Univ., UK]"],"affiliations":[{"raw_affiliation_string":"Computer Laboratory, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"[Comput. Lab., Cambridge Univ., UK]","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110189849"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.8075,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.85997754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"219","last_page":"221"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9847000241279602,"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/T11478","display_name":"Caching and Content Delivery","score":0.9836999773979187,"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":0.7657820582389832},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7336710691452026},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5569267868995667},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5562498569488525},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.5409541726112366},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5339041948318481},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.5236701369285583},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.4979891777038574},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.476606547832489},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.47038188576698303},{"id":"https://openalex.org/keywords/web-api","display_name":"Web API","score":0.47029468417167664},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.45505836606025696},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.44353193044662476},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2043670415878296},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.15215462446212769}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657820582389832},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7336710691452026},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5569267868995667},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5562498569488525},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.5409541726112366},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5339041948318481},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.5236701369285583},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.4979891777038574},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.476606547832489},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.47038188576698303},{"id":"https://openalex.org/C127613066","wikidata":"https://www.wikidata.org/wiki/Q557770","display_name":"Web API","level":4,"score":0.47029468417167664},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.45505836606025696},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.44353193044662476},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2043670415878296},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.15215462446212769}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/laweb.2003.1250304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/laweb.2003.1250304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/LEOS 3rd International Conference on Numerical Simulation of Semiconductor Optoelectronic Devices (IEEE Cat. No.03EX726)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.3736","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.3736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cwr.cl/la-web/stamped/32_palomino_m.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W58642631","https://openalex.org/W1591568670","https://openalex.org/W1604630858","https://openalex.org/W1709754610","https://openalex.org/W2018928332","https://openalex.org/W2066636486","https://openalex.org/W2140279085","https://openalex.org/W2164542999","https://openalex.org/W2227630426","https://openalex.org/W6602361498","https://openalex.org/W6635637122","https://openalex.org/W6667169455","https://openalex.org/W6680536191"],"related_works":["https://openalex.org/W2058873586","https://openalex.org/W2100071482","https://openalex.org/W2116470944","https://openalex.org/W2535301253","https://openalex.org/W3147180876","https://openalex.org/W2133426335","https://openalex.org/W1977547331","https://openalex.org/W4288492206","https://openalex.org/W2980871857","https://openalex.org/W1554682334"],"abstract_inverted_index":{"Web":[0,16,62],"search":[1,17,27,35],"engines":[2,18],"have":[3],"become":[4],"an":[5,74,85],"indispensable":[6],"utility":[7],"for":[8,76],"Internet":[9],"users.":[10],"In":[11],"the":[12,53,66,71,82,99],"near":[13],"future,":[14],"however,":[15],"will":[19],"not":[20],"only":[21],"be":[22],"expected":[23],"to":[24,31,34,51,65,89],"provide":[25],"quality":[26],"results,":[28],"but":[29],"also":[30],"enable":[32],"applications":[33],"and":[36,58],"exploit":[37],"their":[38],"index":[39,93],"repositories":[40],"directly.":[41],"We":[42],"present":[43],"here":[44],"SharpSpider,":[45],"a":[46,61,90],"distributed,":[47],"C#":[48],"spider":[49],"designed":[50],"address":[52],"issues":[54],"of":[55,60,68,73,98],"scalability,":[56],"decentralisation":[57],"continuity":[59],"crawl.":[63],"Fundamental":[64],"design":[67],"SharpSpider":[69],"is":[70],"publication":[72],"API":[75,86],"use":[77],"by":[78],"other":[79],"services":[80],"on":[81],"network.":[83],"Such":[84],"grants":[87],"access":[88],"constantly":[91],"refreshed":[92],"buiU":[94],"after":[95],"successive":[96],"crawls":[97],"Web.":[100]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
