{"id":"https://openalex.org/W1995855187","doi":"https://doi.org/10.1145/1731740.1731785","title":"One approach to HTML wrappers creation","display_name":"One approach to HTML wrappers creation","publication_year":2009,"publication_date":"2009-06-18","ids":{"openalex":"https://openalex.org/W1995855187","doi":"https://doi.org/10.1145/1731740.1731785","mag":"1995855187"},"language":"en","primary_location":{"id":"doi:10.1145/1731740.1731785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1731740.1731785","pdf_url":null,"source":{"id":"https://openalex.org/S4210222260","display_name":"Proceedings of the International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","issn_l":"1313-8936","issn":["1313-8936","1313-9037"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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 International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","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/A5050597132","display_name":"Viera Rozinajov\u00e1","orcid":"https://orcid.org/0000-0003-1302-6261"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"Viera Rozinajov\u00e1","raw_affiliation_strings":["","Slovak University of Technology in Bratislava, Bratislava, Slovakia"],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]},{"raw_affiliation_string":"Slovak University of Technology in Bratislava, Bratislava, Slovakia","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016642802","display_name":"Ondrej Hluch\u00fd","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ondrej Hluch\u00fd","raw_affiliation_strings":[""],"affiliations":[{"raw_affiliation_string":"","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050597132"],"corresponding_institution_ids":["https://openalex.org/I110757952"],"apc_list":null,"apc_paid":null,"fwci":0.6632,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72718351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9977999925613403,"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/T11106","display_name":"Data Management and Algorithms","score":0.98089998960495,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8210433721542358},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.8155769109725952},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7469355463981628},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6192803978919983},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6038679480552673},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5746667981147766},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5677639245986938},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.49132123589515686},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46819007396698},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4100363254547119},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37155985832214355},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3713621497154236},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.2696143388748169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2585579752922058},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1703808605670929},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09082978963851929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210433721542358},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.8155769109725952},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7469355463981628},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6192803978919983},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6038679480552673},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5746667981147766},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5677639245986938},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.49132123589515686},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46819007396698},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4100363254547119},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37155985832214355},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3713621497154236},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2696143388748169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2585579752922058},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1703808605670929},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09082978963851929},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1731740.1731785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1731740.1731785","pdf_url":null,"source":{"id":"https://openalex.org/S4210222260","display_name":"Proceedings of the International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","issn_l":"1313-8936","issn":["1313-8936","1313-9037"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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 International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G632119277","display_name":null,"funder_award_id":"APVV-0391-06","funder_id":"https://openalex.org/F4320323251","funder_display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja"}],"funders":[{"id":"https://openalex.org/F4320323251","display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja","ror":"https://ror.org/037nx0e70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W100562005","https://openalex.org/W116870935","https://openalex.org/W199362264","https://openalex.org/W2055383559","https://openalex.org/W2087406717","https://openalex.org/W4391233682"],"related_works":["https://openalex.org/W2159024673","https://openalex.org/W3001987467","https://openalex.org/W2968165261","https://openalex.org/W1603161560","https://openalex.org/W4252190074","https://openalex.org/W2154676777","https://openalex.org/W4386439926","https://openalex.org/W2950663250","https://openalex.org/W2133252868","https://openalex.org/W2388039614"],"abstract_inverted_index":{"Most":[0],"of":[1,62],"the":[2,52,60,70,83],"Internet":[3],"sources":[4,21],"are":[5,29],"in":[6,38,51],"unstructured":[7],"HTML":[8],"format,":[9],"which":[10],"is":[11,22,57],"often":[12],"difficult":[13],"to":[14,32],"process":[15],"further.":[16],"Content":[17],"extraction":[18],"from":[19,59],"such":[20],"usually":[23],"carried":[24],"out":[25],"by":[26],"wrappers.":[27],"There":[28],"various":[30],"approaches":[31],"wrapper":[33,85],"construction.":[34],"The":[35],"method":[36],"proposed":[37],"this":[39],"paper":[40],"utilizes":[41],"valued":[42],"Document":[43],"Object":[44],"Model":[45],"(DOM)":[46],"trees.":[47],"For":[48],"each":[49],"tag":[50,65,71],"DOM":[53],"tree":[54],"a":[55],"hash":[56],"computed":[58,81],"sequence":[61],"parent":[63],"tags,":[64],"attributes,":[66],"its":[67],"values":[68],"and":[69,95],"sub-tree.":[72],"This":[73],"conception":[74],"ensures":[75],"that":[76],"same":[77],"hashes":[78],"will":[79],"be":[80],"for":[82,87],"particular":[84],"even":[86],"different":[88],"queries.":[89],"Proposed":[90],"solution":[91],"has":[92],"been":[93],"implemented":[94],"verified.":[96]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
