{"id":"https://openalex.org/W1506122440","doi":"https://doi.org/10.1016/b978-012088469-8.50037-1","title":"Accurate and Efficient Crawling for Relevant Websites","display_name":"Accurate and Efficient Crawling for Relevant Websites","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W1506122440","doi":"https://doi.org/10.1016/b978-012088469-8.50037-1","mag":"1506122440"},"language":"en","primary_location":{"id":"doi:10.1016/b978-012088469-8.50037-1","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-012088469-8.50037-1","pdf_url":null,"source":{"id":"https://openalex.org/S4306463230","display_name":"Elsevier eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2004 VLDB Conference","raw_type":"book-chapter"},"type":"book-chapter","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/A5018267399","display_name":"Martin Ester","orcid":"https://orcid.org/0000-0001-7732-2815"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Martin Ester","raw_affiliation_strings":["Simon Fraser University School of Computing Science Burnaby BC, Canada V5A 1S6","Simon Fraser University, School of Computing Science, Burnaby BC, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University School of Computing Science Burnaby BC, Canada V5A 1S6","institution_ids":["https://openalex.org/I18014758"]},{"raw_affiliation_string":"Simon Fraser University, School of Computing Science, Burnaby BC, Canada#TAB#","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109848174","display_name":"Hans\u2010Peter Kriegel","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Hans-Peter Kriegel","raw_affiliation_strings":["University of Munich Institute for Computer Science Oettingenstr. 67, D-80538 Munich, Germany","University of Munich, Institute for Computer Science, Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Munich Institute for Computer Science Oettingenstr. 67, D-80538 Munich, Germany","institution_ids":[]},{"raw_affiliation_string":"University of Munich, Institute for Computer Science, Munich, Germany#TAB#","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003177894","display_name":"Matthias Schubert","orcid":"https://orcid.org/0000-0002-6566-6343"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Matthias Schubert","raw_affiliation_strings":["University of Munich Institute for Computer Science Oettingenstr. 67, D-80538 Munich, Germany","University of Munich, Institute for Computer Science, Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Munich Institute for Computer Science Oettingenstr. 67, D-80538 Munich, Germany","institution_ids":[]},{"raw_affiliation_string":"University of Munich, Institute for Computer Science, Munich, Germany#TAB#","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003177894","https://openalex.org/A5018267399","https://openalex.org/A5109848174"],"corresponding_institution_ids":["https://openalex.org/I18014758","https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":3.9274,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.94040913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"407"},"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":0.9800999760627747,"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/T10260","display_name":"Software Engineering Research","score":0.9688000082969666,"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":0.9669455289840698},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.9319917559623718},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.9190465211868286},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7556334733963013},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7481462359428406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6932060718536377},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6068457365036011},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.47181236743927},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4309423267841339},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.3756273090839386},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.23851123452186584}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9669455289840698},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9319917559623718},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.9190465211868286},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7556334733963013},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7481462359428406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6932060718536377},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6068457365036011},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.47181236743927},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4309423267841339},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3756273090839386},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.23851123452186584},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1016/b978-012088469-8.50037-1","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-012088469-8.50037-1","pdf_url":null,"source":{"id":"https://openalex.org/S4306463230","display_name":"Elsevier eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2004 VLDB Conference","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.117.5222","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.117.5222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sfu.ca/~ester/papers/VLDB-2004.final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.64.8516","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.64.8516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/conf/2004/RS10P3.PDF","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.68.9495","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.9495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dbs.informatik.uni-muenchen.de/Publikationen/Papers/VLDB2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W178180052","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1538805611","https://openalex.org/W1972640883","https://openalex.org/W1981202432","https://openalex.org/W2005422315","https://openalex.org/W2017726337","https://openalex.org/W2029341294","https://openalex.org/W2033709196","https://openalex.org/W2065168033","https://openalex.org/W2076008912","https://openalex.org/W2079672501","https://openalex.org/W2124673015","https://openalex.org/W2149684865","https://openalex.org/W2911640577","https://openalex.org/W6607220178","https://openalex.org/W6614564550","https://openalex.org/W6643381890","https://openalex.org/W6645485993","https://openalex.org/W6651487525","https://openalex.org/W6654984644","https://openalex.org/W6657826343","https://openalex.org/W6659160459","https://openalex.org/W6669651661","https://openalex.org/W6670250956","https://openalex.org/W6678701036","https://openalex.org/W6682304300"],"related_works":["https://openalex.org/W1506122440","https://openalex.org/W2095543197","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/W2166088942","https://openalex.org/W2997495867"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
