{"id":"https://openalex.org/W4402667000","doi":"https://doi.org/10.18653/v1/2024.acl-demos.29","title":"Fundus: A Simple-to-Use News Scraper Optimized for High Quality Extractions","display_name":"Fundus: A Simple-to-Use News Scraper Optimized for High Quality Extractions","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402667000","doi":"https://doi.org/10.18653/v1/2024.acl-demos.29"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-demos.29","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-demos.29","pdf_url":"https://aclanthology.org/2024.acl-demos.29.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.acl-demos.29.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094246452","display_name":"Max Dallabetta","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Max Dallabetta","raw_affiliation_strings":["Humboldt Universit\u00e4t zu Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt Universit\u00e4t zu Berlin","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094246453","display_name":"Conrad Dobberstein","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Conrad Dobberstein","raw_affiliation_strings":["Humboldt Universit\u00e4t zu Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt Universit\u00e4t zu Berlin","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094246454","display_name":"Adrian Breiding","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adrian Breiding","raw_affiliation_strings":["Humboldt Universit\u00e4t zu Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt Universit\u00e4t zu Berlin","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032877157","display_name":"Alan Akbik","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alan Akbik","raw_affiliation_strings":["Humboldt Universit\u00e4t zu Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt Universit\u00e4t zu Berlin","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I39343248"],"apc_list":null,"apc_paid":null,"fwci":0.2367,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5241727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9039000272750854,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9039000272750854,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/scraper-site","display_name":"Scraper site","score":0.946589469909668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.707108736038208},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6665480732917786},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5149058103561401},{"id":"https://openalex.org/keywords/fundus","display_name":"Fundus (uterus)","score":0.4475102722644806},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12472644448280334},{"id":"https://openalex.org/keywords/ophthalmology","display_name":"Ophthalmology","score":0.10523569583892822},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10240283608436584}],"concepts":[{"id":"https://openalex.org/C78500136","wikidata":"https://www.wikidata.org/wiki/Q477840","display_name":"Scraper site","level":2,"score":0.946589469909668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707108736038208},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6665480732917786},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5149058103561401},{"id":"https://openalex.org/C2776391266","wikidata":"https://www.wikidata.org/wiki/Q9612","display_name":"Fundus (uterus)","level":2,"score":0.4475102722644806},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12472644448280334},{"id":"https://openalex.org/C118487528","wikidata":"https://www.wikidata.org/wiki/Q161437","display_name":"Ophthalmology","level":1,"score":0.10523569583892822},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10240283608436584},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.acl-demos.29","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-demos.29","pdf_url":"https://aclanthology.org/2024.acl-demos.29.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.acl-demos.29","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-demos.29","pdf_url":"https://aclanthology.org/2024.acl-demos.29.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5729854464","display_name":"Eidetische Repr\u00e4sentationen Nat\u00fcrlicher Sprache","funder_award_id":"448414230","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6510858048","display_name":"EXC 2002: Science of Intelligence (SCIoI)","funder_award_id":"390523135","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6532450817","display_name":null,"funder_award_id":"EXC 2002","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402667000.pdf","grobid_xml":"https://content.openalex.org/works/W4402667000.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2351413189","https://openalex.org/W2352031027","https://openalex.org/W2362264299","https://openalex.org/W2389718375","https://openalex.org/W2378574380","https://openalex.org/W2357222887","https://openalex.org/W2393563204","https://openalex.org/W2386629175"],"abstract_inverted_index":{"This":[0],"paper":[1,110],"introduces":[2],"FUNDUS,":[3],"a":[4,20,86,90,94,123],"user-friendly":[5],"news":[6,16,26,59,129,143],"scraper":[7],"that":[8,35,57,133],"enables":[9],"users":[10],"to":[11,39,50,101],"obtain":[12],"millions":[13],"of":[14,23,43,97,114],"high-quality":[15],"articles":[17,60],"with":[18],"just":[19],"few":[21],"lines":[22],"code.Unlike":[24],"existing":[25],"scrapers,":[27],"we":[28,99],"use":[29],"manually":[30],"crafted,":[31],"bespoke":[32],"content":[33,83],"extractors":[34],"are":[36,61],"specifically":[37],"tailored":[38],"the":[40,76,115],"formatting":[41],"guidelines":[42],"each":[44],"supported":[45],"online":[46],"newspaper.This":[47],"allows":[48],"us":[49],"optimize":[51],"our":[52,68,118],"scraping":[53],"for":[54,93,107],"quality":[55,138],"such":[56],"retrieved":[58],"textually":[62],"complete":[63],"and":[64,82,121,141],"without":[65],"HTML":[66,74],"artifacts.Further,":[67],"framework":[69,148],"combines":[70],"both":[71],"crawling":[72],"(retrieving":[73],"from":[75],"web":[77,80],"or":[78],"large":[79],"archives)":[81],"extraction":[84],"into":[85],"single":[87],"pipeline.By":[88],"providing":[89],"unified":[91],"interface":[92],"predefined":[95],"collection":[96],"newspapers,":[98],"aim":[100],"make":[102],"FUNDUS":[103,134],"broadly":[104],"usable":[105],"even":[106],"non-technical":[108],"users.This":[109],"gives":[111],"an":[112],"overview":[113],"framework,":[116],"discusses":[117],"design":[119],"choices,":[120],"presents":[122],"comparative":[124],"evaluation":[125,131],"against":[126],"other":[127],"popular":[128],"scrapers.Our":[130],"shows":[132],"yields":[135],"significantly":[136],"higher":[137],"extractions":[139],"(complete":[140],"artifact-free":[142],"articles)":[144],"than":[145],"prior":[146],"work.The":[147],"is":[149],"available":[150],"on":[151],"GitHub":[152],"under":[153],"https://github.com/flairNLP/fundusand":[154],"can":[155],"be":[156],"simply":[157],"installed":[158],"using":[159],"pip.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
