{"id":"https://openalex.org/W3014183340","doi":"https://doi.org/10.1109/access.2020.2984503","title":"A Novel Web Scraping Approach Using the Additional Information Obtained From Web Pages","display_name":"A Novel Web Scraping Approach Using the Additional Information Obtained From Web Pages","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3014183340","doi":"https://doi.org/10.1109/access.2020.2984503","mag":"3014183340"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2984503","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2984503","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2020.2984503","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078816512","display_name":"Erdin\u00e7 Uzun","orcid":"https://orcid.org/0000-0003-4351-2244"},"institutions":[{"id":"https://openalex.org/I125454184","display_name":"Tekirda\u011f Nam\u0131k Kemal University","ror":"https://ror.org/01a0mk874","country_code":"TR","type":"education","lineage":["https://openalex.org/I125454184"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Erdinc Uzun","raw_affiliation_strings":["Department of Computer Engineering, \u00c7orlu Faculty of Engineering, Tekirda\u011f Nam\u0131k Kemal University, Tekirda\u011f, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-4351-2244","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, \u00c7orlu Faculty of Engineering, Tekirda\u011f Nam\u0131k Kemal University, Tekirda\u011f, Turkey","institution_ids":["https://openalex.org/I125454184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078816512"],"corresponding_institution_ids":["https://openalex.org/I125454184"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":16.1488,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.99054698,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"61726","last_page":"61740"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9941999912261963,"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"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9775000214576721,"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/document-object-model","display_name":"Document Object Model","score":0.9247289896011353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8515354990959167},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6518685817718506},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6346604824066162},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.619753360748291},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5945859551429749},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5548054575920105},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.538992702960968},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5114842653274536},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5096726417541504},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4976344406604767},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.49455639719963074},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4642959535121918},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46273693442344666},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.4330430030822754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34774476289749146},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20318281650543213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0773191750049591}],"concepts":[{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.9247289896011353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8515354990959167},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6518685817718506},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6346604824066162},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.619753360748291},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5945859551429749},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5548054575920105},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.538992702960968},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5114842653274536},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5096726417541504},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4976344406604767},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.49455639719963074},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4642959535121918},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46273693442344666},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.4330430030822754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34774476289749146},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20318281650543213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0773191750049591},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2984503","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2984503","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b2eab4f11a344a4dbd9b241f51643f27","is_oa":true,"landing_page_url":"https://doaj.org/article/b2eab4f11a344a4dbd9b241f51643f27","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 61726-61740 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2984503","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2984503","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W110443600","https://openalex.org/W116870935","https://openalex.org/W1263603112","https://openalex.org/W1489992655","https://openalex.org/W1553019137","https://openalex.org/W1559557735","https://openalex.org/W1566513354","https://openalex.org/W1847991430","https://openalex.org/W1927338256","https://openalex.org/W1973130965","https://openalex.org/W1976978590","https://openalex.org/W1986106281","https://openalex.org/W1994385227","https://openalex.org/W1994584977","https://openalex.org/W2012575882","https://openalex.org/W2017726337","https://openalex.org/W2019441211","https://openalex.org/W2019577381","https://openalex.org/W2030968134","https://openalex.org/W2040075907","https://openalex.org/W2045986835","https://openalex.org/W2048192672","https://openalex.org/W2049488566","https://openalex.org/W2054418412","https://openalex.org/W2063147917","https://openalex.org/W2069205071","https://openalex.org/W2076910790","https://openalex.org/W2080983714","https://openalex.org/W2095648979","https://openalex.org/W2097705449","https://openalex.org/W2101909884","https://openalex.org/W2106262765","https://openalex.org/W2107467543","https://openalex.org/W2117694587","https://openalex.org/W2118023920","https://openalex.org/W2118165382","https://openalex.org/W2119966992","https://openalex.org/W2124479173","https://openalex.org/W2124673015","https://openalex.org/W2126372189","https://openalex.org/W2134826720","https://openalex.org/W2148317291","https://openalex.org/W2151007976","https://openalex.org/W2166915357","https://openalex.org/W2253768319","https://openalex.org/W2328581567","https://openalex.org/W2514393974","https://openalex.org/W2588006593","https://openalex.org/W2612984812","https://openalex.org/W2613027510","https://openalex.org/W2743928556","https://openalex.org/W2788315304","https://openalex.org/W2898301985","https://openalex.org/W2907927219","https://openalex.org/W4231620004","https://openalex.org/W4246219036","https://openalex.org/W6604611248","https://openalex.org/W6604697442"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2065605022","https://openalex.org/W2364692302"],"abstract_inverted_index":{"Web":[0],"scraping":[1,73],"is":[2,76,81],"a":[3,38,86,104,118],"process":[4,52],"of":[5,16,53,65,111,125,160,179],"extracting":[6,134,189],"valuable":[7],"and":[8,41,99,132,168],"interesting":[9],"text":[10],"information":[11,101,198],"from":[12],"web":[13,27,72],"pages.":[14],"Most":[15],"the":[17,31,44,57,62,66,70,96,112,123,137,140,146,150,155,158,165,173,191,209],"current":[18,71],"studies":[19,35],"targeting":[20],"this":[21,48,54,130,180,213,224],"task":[22,225],"are":[23,183],"mostly":[24],"about":[25,184],"automated":[26],"data":[28,46,63],"extraction.":[29],"In":[30,69,139],"extraction":[32,166,174,200],"process,":[33,142,157,167],"these":[34,196],"first":[36],"create":[37],"DOM":[39,67,105],"tree":[40,55],"then":[42,121],"access":[43],"necessary":[45],"through":[47],"tree.":[49],"The":[50,107,176],"construction":[51],"increases":[56],"time":[58,79,201,229],"cost":[59],"depending":[60],"on":[61],"structure":[64],"Tree.":[68,106],"literature,":[74],"it":[75],"observed":[77],"that":[78],"efficiency":[80],"ignored.":[82],"This":[83],"study":[84],"proposes":[85],"novel":[87,181],"approach,":[88],"namely":[89],"UzunExt,":[90],"which":[91],"extracts":[92],"content":[93,135],"quickly":[94],"using":[95,195,207],"string":[97,108,177,210],"methods":[98,109,178],"additional":[100,147,197],"without":[102],"creating":[103],"consist":[110],"following":[113],"consecutive":[114],"steps:":[115],"searching":[116,156],"for":[117,129,136,153,163,171],"given":[119],"pattern,":[120,131],"calculating":[122],"number":[124,159],"closing":[126],"HTML":[127],"elements":[128],"finally":[133],"pattern.":[138],"crawling":[141],"our":[143],"approach":[144,182,214],"collects":[145],"information,":[148],"including":[149],"starting":[151],"position":[152],"enhancing":[154],"inner":[161],"tag":[162,169],"improving":[164],"repetition":[170],"terminating":[172],"process.":[175],"60":[185],"times":[186,204],"faster":[187],"than":[188],"with":[190],"DOM-based":[192,221],"method.":[193],"Moreover,":[194],"improves":[199],"by":[202],"2.35":[203],"compared":[205],"to":[206,219,226],"only":[208],"methods.":[211],"Furthermore,":[212],"can":[215],"easily":[216],"be":[217],"adapted":[218],"other":[220],"studies/parsers":[222],"in":[223],"enhance":[227],"their":[228],"efficiencies.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6}],"updated_date":"2026-05-15T08:27:34.491423","created_date":"2025-10-10T00:00:00"}
