{"id":"https://openalex.org/W1569165351","doi":"https://doi.org/10.1016/b978-012088469-8.50137-6","title":"An Automatic Data Grabber for Large Web Sites","display_name":"An Automatic Data Grabber for Large Web Sites","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W1569165351","doi":"https://doi.org/10.1016/b978-012088469-8.50137-6","mag":"1569165351"},"language":"en","primary_location":{"id":"doi:10.1016/b978-012088469-8.50137-6","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-012088469-8.50137-6","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/A5030700727","display_name":"Valter Crescenzi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Valter Crescenzi","raw_affiliation_strings":["Universit\u00e0 Roma Tre Roma-Italy","Universit\u00e0 Roma Tre,Roma,Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre Roma-Italy","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Universit\u00e0 Roma Tre,Roma,Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008291639","display_name":"Giansalvatore Mecca","orcid":"https://orcid.org/0000-0002-1189-1481"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giansalvatore Mecca","raw_affiliation_strings":["Universit\u00e0 della Basilicata Potenza-Italy","Universit\u00e0 della Basilicata, Potenza, Italy#TAB#"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 della Basilicata Potenza-Italy","institution_ids":["https://openalex.org/I20272500"]},{"raw_affiliation_string":"Universit\u00e0 della Basilicata, Potenza, Italy#TAB#","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022736687","display_name":"Paolo Merialdo","orcid":"https://orcid.org/0000-0002-3852-8092"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Paolo Merialdo","raw_affiliation_strings":["Universit\u00e0 Roma Tre Roma-Italy","Universit\u00e0 Roma Tre,Roma,Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre Roma-Italy","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Universit\u00e0 Roma Tre,Roma,Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018918066","display_name":"Paolo Missier","orcid":"https://orcid.org/0000-0002-0978-2446"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Paolo Missier","raw_affiliation_strings":["Universit\u00e0 Roma Tre Roma-Italy","Universit\u00e0 Roma Tre,Roma,Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre Roma-Italy","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Universit\u00e0 Roma Tre,Roma,Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008291639","https://openalex.org/A5018918066","https://openalex.org/A5022736687","https://openalex.org/A5030700727"],"corresponding_institution_ids":["https://openalex.org/I119003972","https://openalex.org/I20272500"],"apc_list":null,"apc_paid":null,"fwci":1.0711,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78713312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1321","last_page":"1324"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9793000221252441,"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/computer-science","display_name":"Computer science","score":0.7760941982269287},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.731838047504425},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5819125175476074},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5699496269226074},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5378920435905457},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5330069661140442},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.521079421043396},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47333580255508423},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4369357228279114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24960637092590332},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23668387532234192},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08519059419631958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760941982269287},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.731838047504425},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5819125175476074},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5699496269226074},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5378920435905457},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5330069661140442},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.521079421043396},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47333580255508423},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4369357228279114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24960637092590332},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23668387532234192},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08519059419631958},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1016/b978-012088469-8.50137-6","is_oa":false,"landing_page_url":"https://doi.org/10.1016/b978-012088469-8.50137-6","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:10.1.1.2.1908","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.1908","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/DEMP18.PDF","raw_type":"text"},{"id":"pmh:oai:iris.uniroma3.it:11590/172479","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/172479","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.uniroma3.it:11590/176453","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/176453","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/69adeb41-f279-4d6b-90e3-222ec9b9af90","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/69adeb41-f279-4d6b-90e3-222ec9b9af90","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Crescenzi , V , Merialdo , P , Missier , P & Mecca , G 2004 , An Automatic Data Grabber for Large Web Sites . in Proceedings 2004 VLDB Conference : The 30th International Conference on Very Large Databases (VLDB) . Elsevier Korea , pp. 1321-1324 . https://doi.org/10.1016/B978-012088469-8.50137-6","raw_type":"bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W2004356755","https://openalex.org/W2085016361","https://openalex.org/W2104086170","https://openalex.org/W2112546875","https://openalex.org/W2119966992","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2170188121","https://openalex.org/W4285719527","https://openalex.org/W6600601489","https://openalex.org/W6614564550","https://openalex.org/W6676829831","https://openalex.org/W6682150279","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W2611741382","https://openalex.org/W3135843367","https://openalex.org/W2613685774","https://openalex.org/W3112355890","https://openalex.org/W4220741973","https://openalex.org/W2326464900","https://openalex.org/W2096382848","https://openalex.org/W3175996217","https://openalex.org/W2360858150","https://openalex.org/W370365947"],"abstract_inverted_index":null,"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
