{"id":"https://openalex.org/W2788315304","doi":"https://doi.org/10.1145/3178876.3186008","title":"Browserless Web Data Extraction","display_name":"Browserless Web Data Extraction","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2788315304","doi":"https://doi.org/10.1145/3178876.3186008","mag":"2788315304"},"language":"en","primary_location":{"id":"doi:10.1145/3178876.3186008","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186008","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186008&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3186008&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008812580","display_name":"Ruslan R. Fayzrakhmanov","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ruslan R. Fayzrakhmanov","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012243761","display_name":"Emanuel Sallinger","orcid":"https://orcid.org/0000-0001-7441-129X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emanuel Sallinger","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102668","display_name":"Ben F. Spencer","orcid":"https://orcid.org/0000-0002-1453-5327"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Spencer","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113511969","display_name":"Tim Furche","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Furche","raw_affiliation_strings":["University of Oxford & Meltwater, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford & Meltwater, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050151740","display_name":"Georg Gottlob","orcid":"https://orcid.org/0000-0002-2353-5230"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georg Gottlob","raw_affiliation_strings":["University of Oxford & TU Wien, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford & TU Wien, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008812580"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":2.8782,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92539052,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1095","last_page":"1104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9998000264167786,"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":0.9902999997138977,"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":0.8134433031082153},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.4840787947177887},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.4716213047504425},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4710502624511719},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.44582170248031616},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4155368208885193},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2667706608772278},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2514825165271759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134433031082153},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.4840787947177887},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.4716213047504425},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4710502624511719},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44582170248031616},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4155368208885193},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2667706608772278},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2514825165271759},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178876.3186008","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186008","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186008&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3178876.3186008","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186008","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186008&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5458651130","display_name":null,"funder_award_id":"M025268","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8298339663","display_name":"VADA: Value Added Data Systems -- Principles and Architecture","funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8400180575","display_name":null,"funder_award_id":"EP/M025268/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8891597062","display_name":null,"funder_award_id":"EP/M025268/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320322839","display_name":"Technische Universit\u00e4t Wien","ror":"https://ror.org/04d836q62"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788315304.pdf","grobid_xml":"https://content.openalex.org/works/W2788315304.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W96862218","https://openalex.org/W1493883477","https://openalex.org/W1530285431","https://openalex.org/W1569908913","https://openalex.org/W1772092677","https://openalex.org/W1775663022","https://openalex.org/W1874127181","https://openalex.org/W1964189668","https://openalex.org/W1969192670","https://openalex.org/W1984315811","https://openalex.org/W1987647365","https://openalex.org/W1999753800","https://openalex.org/W2000612086","https://openalex.org/W2008956593","https://openalex.org/W2009766178","https://openalex.org/W2011539648","https://openalex.org/W2030908643","https://openalex.org/W2046166587","https://openalex.org/W2064466058","https://openalex.org/W2083413555","https://openalex.org/W2089965140","https://openalex.org/W2094568767","https://openalex.org/W2104511295","https://openalex.org/W2111206978","https://openalex.org/W2114541504","https://openalex.org/W2124722556","https://openalex.org/W2138405339","https://openalex.org/W2148317291","https://openalex.org/W2152761380","https://openalex.org/W2153072229","https://openalex.org/W2192583762","https://openalex.org/W2238544960","https://openalex.org/W2290206096","https://openalex.org/W2296164608","https://openalex.org/W2406114359","https://openalex.org/W2537005436","https://openalex.org/W2584049620","https://openalex.org/W2594436007","https://openalex.org/W2913389685","https://openalex.org/W2953428146","https://openalex.org/W2961369305","https://openalex.org/W4254697110"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2333822231","https://openalex.org/W236190221","https://openalex.org/W2379779959","https://openalex.org/W285491472","https://openalex.org/W2105505991","https://openalex.org/W2394141650","https://openalex.org/W2390200212","https://openalex.org/W2388028180","https://openalex.org/W1998110896"],"abstract_inverted_index":{"Most":[0],"modern":[1],"web":[2,10,49,114],"scrapers":[3,18],"use":[4,41],"an":[5,106],"embedded":[6],"browser":[7],"to":[8,13,24,40,142,147],"render":[9],"pages":[11],"and":[12,30,54,66,75,102,126,130],"simulate":[14],"user":[15],"actions.":[16],"Such":[17],"(or":[19],"wrappers)":[20],"are":[21],"therefore":[22],"expensive":[23],"execute,":[25],"in":[26,119],"terms":[27],"of":[28,70,89,113,123,152],"time":[29],"network":[31],"traffic.":[32],"In":[33,81],"contrast,":[34],"it":[35],"is":[36,76],"magnitudes":[37],"more":[38],"resource-efficient":[39,132],"a":[42,48,143,148],"\"browserless\"":[43,95],"wrapper":[44],"which":[45],"directly":[46,59],"accesses":[47],"server":[50],"through":[51],"HTTP":[52],"requests,":[53],"takes":[55],"the":[56,61,86,99,120],"desired":[57],"data":[58],"from":[60],"raw":[62],"replies.":[63],"However,":[64],"creating":[65],"maintaining":[67],"browserless":[68],"wrappers":[69,93],"high":[71],"precision":[72],"requires":[73],"specialists,":[74],"prohibitively":[77],"labor-intensive":[78],"at":[79],"scale.":[80],"this":[82],"paper,":[83],"we":[84],"demonstrate":[85],"principal":[87],"feasibility":[88],"automatically":[90],"translating":[91],"browser-based":[92],"into":[94],"wrappers.":[96,133],"We":[97,134],"present":[98],"first":[100],"algorithm":[101],"system":[103,117],"performing":[104],"such":[105],"automated":[107],"translation":[108],"on":[109],"suitably":[110],"restricted":[111],"types":[112],"sites.":[115],"This":[116],"works":[118],"vast":[121],"majority":[122],"test":[124],"cases":[125],"produces":[127],"very":[128],"fast":[129],"extremely":[131],"discuss":[135],"research":[136],"challenges":[137],"for":[138],"extending":[139],"our":[140],"approach":[141],"general":[144],"method":[145],"applicable":[146],"yet":[149],"larger":[150],"number":[151],"cases.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}