{"id":"https://openalex.org/W36911888","doi":"https://doi.org/10.1007/978-3-642-28601-8_16","title":"Information Extraction from Webpages Based on DOM Distances","display_name":"Information Extraction from Webpages Based on DOM Distances","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W36911888","doi":"https://doi.org/10.1007/978-3-642-28601-8_16","mag":"36911888"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-28601-8_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-28601-8_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10251/35896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084282503","display_name":"Carlos Castillo","orcid":"https://orcid.org/0000-0003-4544-0416"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Castillo","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Valencia, Camino de Vera s/n, E-46022, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Valencia, Camino de Vera s/n, E-46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015520925","display_name":"H\u00e9ctor Valero","orcid":null},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Valero","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Valencia, Camino de Vera s/n, E-46022, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Valencia, Camino de Vera s/n, E-46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046093544","display_name":"J. Guadalupe Ramos","orcid":"https://orcid.org/0000-0002-7281-7461"},"institutions":[{"id":"https://openalex.org/I4387154508","display_name":"Instituto Tecnol\u00f3gico de La Paz","ror":"https://ror.org/0460tzy11","country_code":null,"type":"education","lineage":["https://openalex.org/I1302736544","https://openalex.org/I4210090124","https://openalex.org/I4387154508","https://openalex.org/I4405258672"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Guadalupe Ramos","raw_affiliation_strings":["Instituto Tecnol\u00f3gico de La Piedad, La Piedad, M\u00e9xico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Tecnol\u00f3gico de La Piedad, La Piedad, M\u00e9xico","institution_ids":["https://openalex.org/I4387154508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003503212","display_name":"Josep Silva","orcid":"https://orcid.org/0000-0001-5096-0008"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josep Silva","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Valencia, Camino de Vera s/n, E-46022, Valencia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Valencia, Camino de Vera s/n, E-46022, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.0502,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89922947,"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":"181","last_page":"193"},"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9588000178337097,"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/T11478","display_name":"Caching and Content Delivery","score":0.9395999908447266,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8686858415603638},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.867107629776001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7138878107070923},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.7011922001838684},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6581995487213135},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5033554434776306},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4810638427734375},{"id":"https://openalex.org/keywords/plain-text","display_name":"Plain text","score":0.43535545468330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8686858415603638},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.867107629776001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7138878107070923},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.7011922001838684},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6581995487213135},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5033554434776306},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4810638427734375},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.43535545468330383},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-28601-8_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-28601-8_16","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:riunet.upv.es:10251/35896","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/35896","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"pmh:oai:riunet.upv.es:10251/35896","is_oa":true,"landing_page_url":"http://hdl.handle.net/10251/35896","pdf_url":null,"source":{"id":"https://openalex.org/S4306401500","display_name":"RiuNet (Politechnical University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60053951","host_organization_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I60053951"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1521111469","https://openalex.org/W1553019137","https://openalex.org/W1563959936","https://openalex.org/W1972793074","https://openalex.org/W1996777430","https://openalex.org/W2006341092","https://openalex.org/W2024791376","https://openalex.org/W2052399358","https://openalex.org/W2066313135","https://openalex.org/W2087406717","https://openalex.org/W2093559286","https://openalex.org/W2094127255","https://openalex.org/W2120136770","https://openalex.org/W2148242152","https://openalex.org/W2153958417","https://openalex.org/W2158231614","https://openalex.org/W2158893217","https://openalex.org/W2160845726","https://openalex.org/W2466315121","https://openalex.org/W2624907881","https://openalex.org/W4250847188"],"related_works":["https://openalex.org/W4385731361","https://openalex.org/W36911888","https://openalex.org/W1990527953","https://openalex.org/W2030910246","https://openalex.org/W3093218477","https://openalex.org/W4287775364","https://openalex.org/W2529247374","https://openalex.org/W3029858749","https://openalex.org/W13099415","https://openalex.org/W2140970666"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}