{"id":"https://openalex.org/W2130760429","doi":"https://doi.org/10.1109/wise.2003.1254476","title":"Crawling for domain-specific hidden Web resources","display_name":"Crawling for domain-specific hidden Web resources","publication_year":2004,"publication_date":"2004-05-13","ids":{"openalex":"https://openalex.org/W2130760429","doi":"https://doi.org/10.1109/wise.2003.1254476","mag":"2130760429"},"language":"en","primary_location":{"id":"doi:10.1109/wise.2003.1254476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wise.2003.1254476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Properties and Applications of Dielectric Materials (Cat. No.03CH37417)","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/A5047771562","display_name":"Andr\u00e9 Bergholz","orcid":null},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"A. Bergholz","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Res. Center Eur., Meylan, France"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Res. Center Eur., Meylan, France","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082646902","display_name":"B. Childlovskii","orcid":null},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"B. Childlovskii","raw_affiliation_strings":["Xerox Res. Center Eur., Meylan, France"],"affiliations":[{"raw_affiliation_string":"Xerox Res. Center Eur., Meylan, France","institution_ids":["https://openalex.org/I33976269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047771562"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":null,"apc_paid":null,"fwci":9.4688,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.97458078,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"133"},"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":0.9793000221252441,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9593999981880188,"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/web-crawler","display_name":"Web crawler","score":0.9233245849609375},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.825713574886322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7264581918716431},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7259065508842468},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.6641073226928711},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5359576344490051},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4914027452468872},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4898204505443573},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.43529146909713745},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.4350054860115051},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43243294954299927},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4101486802101135},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.3286172151565552},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3163142204284668},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.23019835352897644}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9233245849609375},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.825713574886322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264581918716431},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7259065508842468},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.6641073226928711},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5359576344490051},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4914027452468872},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4898204505443573},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.43529146909713745},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.4350054860115051},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43243294954299927},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4101486802101135},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.3286172151565552},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3163142204284668},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.23019835352897644},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wise.2003.1254476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wise.2003.1254476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Properties and Applications of Dielectric Materials (Cat. No.03CH37417)","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":12,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1628571627","https://openalex.org/W2005579877","https://openalex.org/W2029341294","https://openalex.org/W2066636486","https://openalex.org/W2124673015","https://openalex.org/W2131006463","https://openalex.org/W2170188121","https://openalex.org/W2221553715","https://openalex.org/W6636741502","https://openalex.org/W6678701036","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W4385695127","https://openalex.org/W4248730791","https://openalex.org/W1506122440","https://openalex.org/W2026132847","https://openalex.org/W2358310581","https://openalex.org/W2019080882","https://openalex.org/W2384770049","https://openalex.org/W2371725684","https://openalex.org/W3184910030"],"abstract_inverted_index":{"The":[0,80],"Hidden":[1,102,130],"Web,":[2],"the":[3,6,36,42,45,71,77,98,116,120,128],"part":[4],"of":[5,35,101,113,127],"Web":[7,39,47,103,131],"that":[8,34],"remains":[9],"unavailable":[10],"for":[11],"standard":[12],"crawlers,":[13],"has":[14],"become":[15],"an":[16],"important":[17],"research":[18],"topic":[19],"during":[20],"recent":[21],"years.":[22],"Its":[23],"size":[24],"is":[25,48,56,82,85],"estimated":[26],"to":[27,29,50,97],"400":[28],"500":[30],"times":[31],"larger":[32],"than":[33],"publicly":[37],"indexable":[38],"(PIW).":[40],"Furthermore,":[41],"information":[43],"on":[44],"hidden":[46,78],"assumed":[49],"be":[51],"more":[52],"structured,":[53],"because":[54],"it":[55],"usually":[57],"stored":[58],"in":[59,119],"databases.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"describe":[65,94],"a":[66,111],"crawler":[67,81],"which":[68],"starting":[69],"from":[70],"PIW":[72],"finds":[73],"entry":[74],"points":[75],"into":[76],"Web.":[79],"domain-specific":[83],"and":[84,90,123],"initialized":[86],"with":[87],"pre-classified":[88],"documents":[89],"relevant":[91],"keywords.":[92],"We":[93,109],"our":[95,125],"approach":[96],"automatic":[99],"identification":[100],"resources":[104],"among":[105],"encountered":[106],"HTML":[107],"forms.":[108],"conduct":[110],"series":[112],"experiments":[114],"using":[115],"top-level":[117],"categories":[118],"Google":[121],"directory":[122],"report":[124],"analysis":[126],"discovered":[129],"resources.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
