{"id":"https://openalex.org/W2133059197","doi":"https://doi.org/10.1145/1135777.1135928","title":"Robust web content extraction","display_name":"Robust web content extraction","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2133059197","doi":"https://doi.org/10.1145/1135777.1135928","mag":"2133059197"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135928","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/86019/21/86019.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013154501","display_name":"Marek Kowalkiewicz","orcid":"https://orcid.org/0000-0002-1196-4943"},"institutions":[{"id":"https://openalex.org/I12379730","display_name":"Pozna\u0144 University of Economics and Business","ror":"https://ror.org/0532c1x92","country_code":"PL","type":"education","lineage":["https://openalex.org/I12379730"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Marek Kowalkiewicz","raw_affiliation_strings":["The Poznan University of Economics, Poznan, Poland","The Poznan University of Economics, Poznan, Poland#TAB#"],"affiliations":[{"raw_affiliation_string":"The Poznan University of Economics, Poznan, Poland","institution_ids":["https://openalex.org/I12379730"]},{"raw_affiliation_string":"The Poznan University of Economics, Poznan, Poland#TAB#","institution_ids":["https://openalex.org/I12379730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085238027","display_name":"Maria E. Or\u0142owska","orcid":"https://orcid.org/0000-0002-5234-7925"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Maria E. Orlowska","raw_affiliation_strings":["The University of Queensland, St. Lucia, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, St. Lucia, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055727428","display_name":"Tomasz Kaczmarek","orcid":"https://orcid.org/0000-0003-1828-100X"},"institutions":[{"id":"https://openalex.org/I12379730","display_name":"Pozna\u0144 University of Economics and Business","ror":"https://ror.org/0532c1x92","country_code":"PL","type":"education","lineage":["https://openalex.org/I12379730"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Kaczmarek","raw_affiliation_strings":["The Poznan University of Economics, Poznan, Poland","The Poznan University of Economics, Poznan, Poland#TAB#"],"affiliations":[{"raw_affiliation_string":"The Poznan University of Economics, Poznan, Poland","institution_ids":["https://openalex.org/I12379730"]},{"raw_affiliation_string":"The Poznan University of Economics, Poznan, Poland#TAB#","institution_ids":["https://openalex.org/I12379730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005647308","display_name":"Witold Abramowicz","orcid":"https://orcid.org/0000-0001-5464-9698"},"institutions":[{"id":"https://openalex.org/I12379730","display_name":"Pozna\u0144 University of Economics and Business","ror":"https://ror.org/0532c1x92","country_code":"PL","type":"education","lineage":["https://openalex.org/I12379730"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Witold Abramowicz","raw_affiliation_strings":["The Poznan University of Economics, Poznan, Poland","The Poznan University of Economics, Poznan, Poland#TAB#"],"affiliations":[{"raw_affiliation_string":"The Poznan University of Economics, Poznan, Poland","institution_ids":["https://openalex.org/I12379730"]},{"raw_affiliation_string":"The Poznan University of Economics, Poznan, Poland#TAB#","institution_ids":["https://openalex.org/I12379730"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013154501"],"corresponding_institution_ids":["https://openalex.org/I12379730"],"apc_list":null,"apc_paid":null,"fwci":5.1639,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95157905,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"887","last_page":"888"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9607999920845032,"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/T12285","display_name":"Surface Chemistry and Catalysis","score":0.955299973487854,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/xpath","display_name":"XPath","score":0.9954066276550293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500474452972412},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6285076141357422},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5340743064880371},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.41204190254211426},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.3358762860298157},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.32540959119796753},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18493330478668213},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.0718773603439331}],"concepts":[{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.9954066276550293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500474452972412},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6285076141357422},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5340743064880371},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.41204190254211426},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.3358762860298157},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.32540959119796753},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18493330478668213},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.0718773603439331},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1135777.1135928","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:86019","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/86019/21/86019.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 15th International Conference on World Wide Web","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:86019","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/86019/21/86019.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 15th International Conference on World Wide Web","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2133059197.pdf"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W1563616709","https://openalex.org/W2005646337","https://openalex.org/W2116624620"],"related_works":["https://openalex.org/W1554870463","https://openalex.org/W2111274946","https://openalex.org/W1555764847","https://openalex.org/W151996191","https://openalex.org/W2123430800","https://openalex.org/W2115428687","https://openalex.org/W4255475599","https://openalex.org/W2544674189","https://openalex.org/W2897171874","https://openalex.org/W1987716395"],"abstract_inverted_index":{"We":[0,21,60],"present":[1],"an":[2],"empirical":[3],"evaluation":[4],"and":[5,17],"comparison":[6],"of":[7,49,66],"two":[8],"content":[9,43],"extraction":[10],"methods":[11],"in":[12,35,41,63],"HTML:":[13],"absolute":[14,38,82],"XPath":[15,19,26,39,73,83],"expressions":[16,40,74],"relative":[18,25,72],"expressions.":[20],"argue":[22],"that":[23,62],"the":[24],"expressions,":[27],"although":[28],"not":[29],"widely":[30],"used,":[31],"should":[32],"be":[33],"used":[34],"preference":[36],"to":[37],"extracting":[42],"from":[44],"human-created":[45],"Web":[46],"documents.":[47],"Evaluation":[48],"robustness":[50],"covers":[51],"four":[52],"thousand":[53],"queries":[54],"executed":[55],"on":[56,76],"several":[57],"hundred":[58],"webpages.":[59],"show":[61],"referencing":[64],"parts":[65],"real":[67],"world":[68],"dynamic":[69],"HTML":[70],"documents,":[71],"are":[75],"average":[77],"significantly":[78],"more":[79],"robust":[80],"than":[81],"ones.":[84]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
