{"id":"https://openalex.org/W2162936635","doi":"https://doi.org/10.1109/cso.2009.200","title":"The Dynamic Web Pages Information Extraction Algorithm Based on Sequence Alignment","display_name":"The Dynamic Web Pages Information Extraction Algorithm Based on Sequence Alignment","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2162936635","doi":"https://doi.org/10.1109/cso.2009.200","mag":"2162936635"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cso.2009.200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5000761221","display_name":"Dongwei Guo","orcid":"https://orcid.org/0000-0002-2482-0447"},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongwei Guo","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380655","display_name":"Dan Li","orcid":"https://orcid.org/0000-0001-5904-871X"},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Li","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348890","display_name":"Miao Liu","orcid":"https://orcid.org/0000-0002-0127-6899"},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Liu","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630039","display_name":"Yanbin Liu","orcid":"https://orcid.org/0000-0003-3940-2560"},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Liu","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011158651","display_name":"Sha Chen","orcid":"https://orcid.org/0000-0001-6026-652X"},"institutions":[{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]},{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sha Chen","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":64},"biblio":{"volume":null,"issue":null,"first_page":"784","last_page":"786"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9999,"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":0.9999,"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":0.9212,"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/T13976","display_name":"Web visibility and informetrics","score":0.9189,"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/data-extraction","display_name":"Data extraction","score":0.58047},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41010806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80796564},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7154372},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6626747},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.58047},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5041748},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4829923},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.43706265},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41010806},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4076157},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34491238},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.27910548},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cso.2009.200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":9,"referenced_works":["https://openalex.org/W108340680","https://openalex.org/W1963774436","https://openalex.org/W1973483159","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2117030594","https://openalex.org/W2130451161","https://openalex.org/W2137661905","https://openalex.org/W2165666571"],"related_works":["https://openalex.org/W4239898202","https://openalex.org/W3116613346","https://openalex.org/W2368657441","https://openalex.org/W2351131669","https://openalex.org/W2316185946","https://openalex.org/W2168047402","https://openalex.org/W2115253914","https://openalex.org/W2069679074","https://openalex.org/W1979144454","https://openalex.org/W1559090489"],"abstract_inverted_index":{"In":[0],"this":[1,115],"paper,":[2],"'common":[3],"framework'":[4],"is":[5,11,42],"defined":[6],"as":[7,30],"the":[8,14,26,45,51,56,62,80,83,90,112],"information":[9,46,71],"which":[10],"irrelative":[12],"to":[13,49],"kernel":[15],"contents":[16],"of":[17,35,82,92,114],"Web":[18,23,60,75],"pages":[19,24,76],"and":[20,37,89,100,106],"common":[21,52,57,93],"in":[22,44],"from":[25,59,77],"same":[27],"source,":[28],"such":[29],"headers,":[31],"tails,":[32],"advertisements,":[33],"orientations":[34],"browsers":[36],"flash":[38],"etc.":[39],"Sequence":[40],"alignment":[41,84],"adopted":[43],"extraction":[47,87,102],"algorithm":[48],"detect":[50],"framework.":[53],"After":[54],"eliminating":[55],"frameworks":[58],"pages,":[61],"data":[63,98],"fields":[64],"obtained":[65],"will":[66],"be":[67],"more":[68],"suitable":[69],"for":[70],"extraction.":[72],"On":[73],"data-intensive":[74],"real-world":[78],"Websites,":[79],"effects":[81],"parameter":[85],"on":[86,96],"results":[88,110],"phase":[91],"framework":[94],"detection":[95],"decreasing":[97],"quantity":[99],"increasing":[101],"accuracy":[103],"were":[104],"tested":[105],"evaluated.":[107],"The":[108],"experimental":[109],"proved":[111],"validity":[113],"approach":[116],"convincingly.":[117]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2162936635","counts_by_year":[],"updated_date":"2024-12-09T00:36:19.315707","created_date":"2016-06-24"}