{"id":"https://openalex.org/W2128341918","doi":"https://doi.org/10.1145/1060745.1060760","title":"Fully automatic wrapper generation for search engines","display_name":"Fully automatic wrapper generation for search engines","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2128341918","doi":"https://doi.org/10.1145/1060745.1060760","mag":"2128341918"},"language":"en","primary_location":{"id":"doi:10.1145/1060745.1060760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web  - WWW '05","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/A5062551149","display_name":"Hongkun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hongkun Zhao","raw_affiliation_strings":["SUNY at Binghamton, Binghamton, NY","SUNY at Binghamton, Binghamton, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton, Binghamton, NY","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"SUNY at Binghamton, Binghamton, NY#TAB#","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960531","display_name":"Weiyi Meng","orcid":"https://orcid.org/0000-0002-7246-2058"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyi Meng","raw_affiliation_strings":["SUNY at Binghamton, Binghamton, NY","SUNY at Binghamton, Binghamton, NY#TAB#"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton, Binghamton, NY","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"SUNY at Binghamton, Binghamton, NY#TAB#","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087302495","display_name":"Zonghuan Wu","orcid":"https://orcid.org/0000-0002-3838-5474"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zonghuan Wu","raw_affiliation_strings":["Univ. of Louisiana at Lafayette, Lafayette, LA","University of Louisiana at Lafayette Lafayette, LA"],"affiliations":[{"raw_affiliation_string":"Univ. of Louisiana at Lafayette, Lafayette, LA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"University of Louisiana at Lafayette Lafayette, LA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023699325","display_name":"Vijay V. Raghavan","orcid":"https://orcid.org/0000-0001-7224-7828"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Raghavan","raw_affiliation_strings":["Univ. of Louisiana at Lafayette, Lafayette, LA","University of Louisiana at Lafayette Lafayette, LA"],"affiliations":[{"raw_affiliation_string":"Univ. of Louisiana at Lafayette, Lafayette, LA","institution_ids":["https://openalex.org/I79516672"]},{"raw_affiliation_string":"University of Louisiana at Lafayette Lafayette, LA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109181755","display_name":"Clement Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement Yu","raw_affiliation_strings":["University of Illinois at Chicago, Chicago, IL","University of Illinois at Chicago, Chicago IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago, Chicago, IL","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Illinois at Chicago, Chicago IL","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062551149"],"corresponding_institution_ids":["https://openalex.org/I123946342"],"apc_list":null,"apc_paid":null,"fwci":54.2752,"has_fulltext":false,"cited_by_count":295,"citation_normalized_percentile":{"value":0.99830011,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"66"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9868999719619751,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9635000228881836,"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/computer-science","display_name":"Computer science","score":0.678138792514801},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32009443640708923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678138792514801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32009443640708923}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1060745.1060760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th international conference on World Wide Web  - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.4711","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.4711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.binghamton.edu/~meng/pub.d/p458-zhao.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.4756","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.4756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2005.org/cdrom/docs/p66.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1553019137","https://openalex.org/W1569691642","https://openalex.org/W1748877974","https://openalex.org/W1927338256","https://openalex.org/W1969005071","https://openalex.org/W1969831559","https://openalex.org/W2005646337","https://openalex.org/W2015551056","https://openalex.org/W2045821558","https://openalex.org/W2059513841","https://openalex.org/W2065568440","https://openalex.org/W2069388662","https://openalex.org/W2095680579","https://openalex.org/W2104086170","https://openalex.org/W2121871415","https://openalex.org/W2125969310","https://openalex.org/W2128836931","https://openalex.org/W2138067201","https://openalex.org/W2140327372","https://openalex.org/W2143079043","https://openalex.org/W2148210463","https://openalex.org/W2150721933","https://openalex.org/W2153072229","https://openalex.org/W2160196229","https://openalex.org/W2161424795","https://openalex.org/W2166407869","https://openalex.org/W2170188121"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W4395014643","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"When":[0],"a":[1,6,13,28,34,41,71,149],"query":[2],"is":[3,100,133],"submitted":[4],"to":[5,30,49,56,81,108],"search":[7,10,62,83,93,96,111],"engine,":[8],"the":[9,19,50,57,61,130,138,143,152,157,162],"engine":[11,63],"returns":[12],"dynamically":[14,87],"generated":[15,88],"result":[16,20,42,84,89,97,144,163],"page":[17,43,145],"containing":[18],"records,":[21],"each":[22],"of":[23,27,33,60,119,129,156,161],"which":[24],"usually":[25],"consists":[26],"link":[29],"and/or":[31],"snippet":[32],"retrieved":[35],"Web":[36,124],"page.":[37,164],"In":[38,66],"addition,":[39],"such":[40,52,113],"often":[44],"also":[45],"contains":[46],"information":[47,54],"irrelevant":[48],"query,":[51],"as":[53,114,146],"related":[55],"hosting":[58],"site":[59],"and":[64,117,122,151],"advertisements.":[65],"this":[67,169],"paper,":[68],"we":[69],"present":[70],"technique":[72,132,170],"for":[73,103],"automatically":[74],"producing":[75],"wrappers":[76],"that":[77,106,134,168],"can":[78,171],"be":[79],"used":[80],"extract":[82],"records":[85],"from":[86],"pages":[90],"returned":[91],"by":[92],"engines.":[94],"Automatic":[95],"record":[98],"extraction":[99,175],"very":[101,173],"important":[102],"many":[104],"applications":[105],"need":[107],"interact":[109],"with":[110],"engines":[112,121],"automatic":[115],"construction":[116],"maintenance":[118],"metasearch":[120],"deep":[123],"crawling.":[125],"The":[126],"novel":[127],"aspect":[128],"proposed":[131],"it":[135],"utilizes":[136],"both":[137],"visual":[139],"content":[140],"features":[141],"on":[142,148],"displayed":[147],"browser":[150],"HTML":[153,158],"tag":[154],"structures":[155],"source":[159],"file":[160],"Experimental":[165],"results":[166],"indicate":[167],"achieve":[172],"high":[174],"accuracy.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":29}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
