{"id":"https://openalex.org/W1987391925","doi":"https://doi.org/10.1145/2389936.2389949","title":"Web crawler middleware for search engine digital libraries","display_name":"Web crawler middleware for search engine digital libraries","publication_year":2012,"publication_date":"2012-11-02","ids":{"openalex":"https://openalex.org/W1987391925","doi":"https://doi.org/10.1145/2389936.2389949","mag":"1987391925"},"language":"en","primary_location":{"id":"doi:10.1145/2389936.2389949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2389936.2389949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international workshop on Web information and data management","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/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026411226","display_name":"Pradeep B. Teregowda","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradeep Teregowda","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054253075","display_name":"Madian Khabsa","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madian Khabsa","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047187180","display_name":"Stephen Carman","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Carman","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056835237","display_name":"Douglas Jordan","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Jordan","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045363195","display_name":"Jos\u00e9 San Pedro","orcid":"https://orcid.org/0000-0001-6149-3679"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose San Pedro Wandelmer","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005317945","display_name":"Xin Lu","orcid":"https://orcid.org/0009-0000-3586-144X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Lu","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasenjit Mitra","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5075242841"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":2.1316,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89715643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"64"},"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/T10260","display_name":"Software Engineering Research","score":0.9801999926567078,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8363466262817383},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8207571506500244},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7226632833480835},{"id":"https://openalex.org/keywords/middleware","display_name":"Middleware (distributed applications)","score":0.6518668532371521},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.6193221807479858},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6146928668022156},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5349702835083008},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5226240754127502},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.487751305103302},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4871632754802704},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4240446388721466},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39238184690475464},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3264186382293701},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30462053418159485},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.2538481652736664},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.19229573011398315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363466262817383},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8207571506500244},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7226632833480835},{"id":"https://openalex.org/C169468491","wikidata":"https://www.wikidata.org/wiki/Q146923","display_name":"Middleware (distributed applications)","level":2,"score":0.6518668532371521},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6193221807479858},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6146928668022156},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5349702835083008},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5226240754127502},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.487751305103302},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4871632754802704},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4240446388721466},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39238184690475464},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3264186382293701},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30462053418159485},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.2538481652736664},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.19229573011398315},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2389936.2389949","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2389936.2389949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international workshop on Web information and data management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1524191071","https://openalex.org/W2083089853","https://openalex.org/W2186419784"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W4248730791","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W2372594123","https://openalex.org/W4385695127"],"abstract_inverted_index":{"Middleware":[0],"is":[1,40,56],"an":[2],"important":[3],"part":[4],"of":[5],"many":[6,189],"search":[7,179,190],"engine":[8,191],"web":[9,148,192],"crawling":[10,193],"processes.":[11],"We":[12,145],"developed":[13,146],"a":[14,48,93,99,147],"middleware,":[15],"the":[16,26,30,52,87,103,109,152,169,177],"Crawl":[17],"Document":[18],"Importer":[19],"(CDI),":[20],"which":[21,97],"selectively":[22],"imports":[23],"documents":[24],"and":[25,36,66,107,125,172],"associated":[27],"metadata":[28,105],"to":[29,42,51,58,91,112,168],"digital":[31],"library":[32],"CiteSeerX":[33,178],"crawl":[34,53,170],"repository":[35],"database.":[37,54],"This":[38],"middleware":[39,83,110,133,159],"designed":[41,57,175],"be":[43,186],"extensible":[44],"as":[45],"it":[46],"provides":[47],"universal":[49],"interface":[50,150],"It":[55,72],"support":[59],"input":[60],"from":[61,129],"multiple":[62],"open":[63],"source":[64],"crawlers":[65],"archival":[67],"formats,":[68],"e.g.,":[69],"ARC,":[70],"WARC.":[71],"can":[73,120,134,154,161],"also":[74,162],"import":[75],"files":[76],"downloaded":[77,114],"via":[78],"FTP.":[79],"To":[80],"use":[81],"this":[82,183],"for":[84,176,188],"another":[85],"crawler,":[86],"user":[88,149,153],"only":[89],"needs":[90],"write":[92],"new":[94],"log":[95],"parser":[96],"returns":[98],"resource":[100],"object":[101],"with":[102],"standard":[104],"attributes":[106],"tells":[108],"how":[111],"access":[113],"files.":[115],"When":[116],"importing":[117,156],"documents,":[118],"users":[119],"specify":[121],"document":[122,142],"mime":[123],"types":[124],"obtain":[126],"text":[127],"extracted":[128],"PDF/postscript":[130],"documents.":[131],"The":[132,158],"adaptively":[135],"identify":[136],"academic":[137],"research":[138],"papers":[139],"based":[140],"on":[141,164],"context":[143],"features.":[144],"where":[151],"submit":[155],"jobs.":[157],"package":[160],"work":[163],"supplemental":[165],"jobs":[166],"related":[167],"database":[171],"respository.":[173],"Though":[174],"engine,":[180],"we":[181],"feel":[182],"design":[184],"would":[185],"appropriate":[187],"systems.":[194]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
