{"id":"https://openalex.org/W2012575882","doi":"https://doi.org/10.1145/775152.775182","title":"DOM-based content extraction of HTML documents","display_name":"DOM-based content extraction of HTML documents","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2012575882","doi":"https://doi.org/10.1145/775152.775182","mag":"2012575882"},"language":"en","primary_location":{"id":"doi:10.1145/775152.775182","doi":"https://doi.org/10.1145/775152.775182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775182","pdf_url":null,"source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international conference on World Wide Web - WWW '03","raw_type":"proceedings-article"},"volume":null,"type":"conference-abstract","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d8057t3p","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064707257","display_name":"Suhit Gupta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhit Gupta","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090171418","display_name":"Gail E. Kaiser","orcid":"https://orcid.org/0000-0002-8791-1178","observed_orcids":["https://orcid.org/0000-0002-8791-1178"]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail Kaiser","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084311379","display_name":"David Neistadt","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Neistadt","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053804247","display_name":"Peter Grimm","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Grimm","raw_affiliation_strings":["Columbia University, New York, NY","Columbia University, New York, NY;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]},{"raw_affiliation_string":"Columbia University, New York, NY;","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":318,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"207"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"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/T12799","display_name":"Mobile and Web Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/content-extraction","display_name":"content extraction","score":0.8769999742507935},{"id":"https://openalex.org/keywords/html-documents","display_name":"HTML documents","score":0.9309999942779541},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.8510000109672546},{"id":"https://openalex.org/keywords/web-proxy","display_name":"web proxy","score":0.9079999923706055},{"id":"https://openalex.org/keywords/web-accessibility","display_name":"web accessibility","score":0.4440000057220459},{"id":"https://openalex.org/keywords/text-summarization","display_name":"text summarization","score":0.7379999756813049},{"id":"https://openalex.org/keywords/mobile-browsing","display_name":"mobile web browsing","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8463267087936401},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7861643433570862},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6830002665519714},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5924616456031799},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.555931806564331},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.526107132434845},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.4941408932209015},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.48548582196235657},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4706793427467346},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46731966733932495},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.4452310800552368},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.21538102626800537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14864778518676758}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/775152.775182","doi":"https://doi.org/10.1145/775152.775182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775182","pdf_url":null,"source":{"id":"https://openalex.org/S7407088480","display_name":"International World Wide Web Conference (WWW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international conference on World Wide Web - WWW '03","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.57.9196","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.9196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.psl.cs.columbia.edu/crunch/www2003.pdf","raw_type":"text"},{"id":"pmh:ADA437440","doi":null,"is_oa":false,"landing_page_url":"http://oai.dtic.mil/oai/oai?&amp;verb=getRecord&amp;metadataPrefix=html&amp;identifier=ADA437440","pdf_url":null,"source":{"id":"https://openalex.org/S4406923043","display_name":"Defense Technical Information Center (DTIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DTIC AND NTIS","raw_type":"Text"},{"id":"doi:10.7916/d8057t3p","doi":"https://doi.org/10.7916/d8057t3p","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8057t3p","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.7916/d8057t3p","doi":"https://doi.org/10.7916/d8057t3p","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8057t3p","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W12351416","https://openalex.org/W75626019","https://openalex.org/W100562005","https://openalex.org/W116870935","https://openalex.org/W1479700690","https://openalex.org/W1974083958","https://openalex.org/W2026642282","https://openalex.org/W2070030212","https://openalex.org/W2071655208","https://openalex.org/W2082884138","https://openalex.org/W2153072229"],"related_works":["https://openalex.org/W622138672","https://openalex.org/W2772885702","https://openalex.org/W1484016414","https://openalex.org/W279807723","https://openalex.org/W1540003828","https://openalex.org/W652190910","https://openalex.org/W2801050774","https://openalex.org/W1977272605","https://openalex.org/W2012575882","https://openalex.org/W2087406717"],"abstract_inverted_index":{"Web":[0,154],"pages":[1,35],"often":[2],"contain":[3],"clutter":[4,58],"(such":[5],"as":[6,75],"pop-up":[7],"ads,":[8],"unnecessary":[9],"images":[10],"and":[11,30,42,51,71,85],"extraneous":[12],"links)":[13],"around":[14],"the":[15,48,94,136],"body":[16],"of":[17,28,118,123],"an":[18],"article":[19],"that":[20,113,120],"distracts":[21],"a":[22,81,98,111,151],"user":[23],"from":[24,33,80,159],"actual":[25],"content.":[26],"Extraction":[27],"\"useful":[29],"relevant\"":[31],"content":[32,61,127,158],"web":[34,161],"has":[36],"many":[37],"applications,":[38],"including":[39],"cell":[40],"phone":[41],"PDA":[43],"browsing,":[44],"speech":[45],"rendering":[46],"for":[47],"visually":[49],"impaired,":[50],"text":[52],"summarization.":[53],"Most":[54],"approaches":[55],"to":[56,92,133,156],"removing":[57,69],"or":[59,68],"making":[60],"more":[62,99],"readable":[63],"involve":[64],"changing":[65],"font":[66],"size":[67],"HTML":[70,143,160],"data":[72],"components":[73],"such":[74],"images,":[76],"which":[77,90],"takes":[78],"away":[79],"webpage's":[82],"inherent":[83],"look":[84],"feel.":[86],"Unlike":[87],"\"Content":[88,106],"Reformatting\",":[89],"aims":[91],"reproduce":[93],"entire":[95],"webpage":[96],"in":[97,150],"convenient":[100],"form,":[101],"our":[102,148],"solution":[103],"directly":[104],"addresses":[105],"Extraction\".":[107],"We":[108,145],"have":[109,146],"developed":[110],"framework":[112],"employs":[114],"easily":[115],"extensible":[116],"set":[117],"techniques":[119],"incorporate":[121],"advantages":[122],"previous":[124],"work":[125,134],"on":[126],"extraction.":[128],"Our":[129],"key":[130],"insight":[131],"is":[132],"with":[135,141],"DOM":[137],"trees,":[138],"rather":[139],"than":[140],"raw":[142],"markup.":[144],"implemented":[147],"approach":[149],"publicly":[152],"available":[153],"proxy":[155],"extract":[157],"pages.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":23}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
