{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T21:47:31Z","timestamp":1791928051059,"version":"4.3.4"},"reference-count":17,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T00:00:00Z","timestamp":1789257600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100011937","name":"Nieders\u00e4chsische Ministerium f\u00fcr Wissenschaft und Kultur","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011937","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["MethodsX"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.mex.2026.104166","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:55:44Z","timestamp":1789397744000},"page":"104166","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A reproducible web-scraping pipeline for collecting geolocated German online job advertisements at scale"],"prefix":"10.1016","volume":"17","author":[{"given":"Matthias","family":"Kapa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kerstin J.","family":"Schaefer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.mex.2026.104166_bib0001","doi-asserted-by":"crossref","first-page":"561","DOI":"10.3233\/SJI-190547","article-title":"Towards a shared infrastructure for online job advertisement data","volume":"35","author":"Descy","year":"2019","journal-title":"Stat. J. IAOS"},{"key":"10.1016\/j.mex.2026.104166_bib0002","article-title":"Scraping German online job advertisements to analyse AI skill demand","volume":"V2","author":"Kapa","year":"2026","journal-title":"Mendeley Data"},{"key":"10.1016\/j.mex.2026.104166_bib0003","series-title":"Multilingual Anonymiser Openpii (ai4privacy)","year":"2025"},{"key":"10.1016\/j.mex.2026.104166_bib0004","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1007\/s11135-021-01164-0","article-title":"Algorithmic thinking in the public interest: navigating technical, legal, and ethical hurdles to web scraping in the social sciences","volume":"56","author":"Luscombe","year":"2022","journal-title":"Qual. Quant."},{"key":"10.1016\/j.mex.2026.104166_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2024.110647","article-title":"Data for labor market concentration using lightcast (formerly burning glass technologies)","volume":"55","author":"Choi","year":"2024","journal-title":"Data Brief"},{"key":"10.1016\/j.mex.2026.104166_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.seps.2024.101916","article-title":"Skills in online job ads: an analysis of italian regions","volume":"94","author":"Giambona","year":"2024","journal-title":"Socio-Econ. Plan. Sci."},{"key":"10.1016\/j.mex.2026.104166_bib0007","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s40172-015-0034-4","article-title":"Using online vacancies and web surveys to analyse the labour market: a methodological inquiry","volume":"4","author":"Kurekova","year":"2015","journal-title":"IZA J. Labor Econ."},{"key":"10.1016\/j.mex.2026.104166_bib0008","doi-asserted-by":"crossref","first-page":"51","DOI":"10.3390\/knowledge4010003","article-title":"Web mining of online resources for german labor market research and education: finding the ground truth?","volume":"4","author":"Fischer","year":"2024","journal-title":"Knowledge"},{"key":"10.1016\/j.mex.2026.104166_bib0009","unstructured":"European Commission, CROS Centre, 2nd Virtual sprint report: germany. Comparing StepStone job advertisements against the German job vacancy survey. https:\/\/cros-legacy.ec.europa.eu\/content\/2nd-virtual-sprint-report-germany_en (accessed May 2026). Archived at: https:\/\/web.archive.org\/web\/20231229170313\/https:\/\/cros-legacy.ec.europa.eu\/content\/2nd-virtual-sprint-report-germany_en."},{"key":"10.1016\/j.mex.2026.104166_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/00222429221100750","article-title":"Fields of gold: scraping web data for marketing insights","volume":"86","author":"Boegershausen","year":"2022","journal-title":"J. Mark."},{"key":"10.1016\/j.mex.2026.104166_bib0011","doi-asserted-by":"crossref","DOI":"10.1177\/20539517251381686","article-title":"Web scraping for research: legal, ethical, institutional, and scientific considerations","volume":"12","author":"Brown","year":"2025","journal-title":"Big Data Soc."},{"key":"10.1016\/j.mex.2026.104166_bib0012","series-title":"Scrapy 2.13 Documentation \u2014 Scrapy 2.13.2 Documentation","year":"2025"},{"key":"10.1016\/j.mex.2026.104166_bib0013","series-title":"scrapy-playwright: A Python Framework integrating Playwright with Scrapy","year":"2024"},{"key":"10.1016\/j.mex.2026.104166_bib0014","unstructured":"textcat (2023). N-gram based text categorization. R package version 1.0-6. https:\/\/CRAN.R-project.org\/package=textcat."},{"key":"10.1016\/j.mex.2026.104166_bib0015","series-title":"OECD Employment Outlook 2023: Artificial Intelligence and the Labour Market","year":"2023"},{"key":"10.1016\/j.mex.2026.104166_bib0016","series-title":"Assessing the Representativeness of Online Job Advertisements, Cedefop Working Paper No. 17","author":"Napierala","year":"2022"},{"key":"10.1016\/j.mex.2026.104166_bib0017","article-title":"Analyzing non-random selectivity in online job advertisements using eurostat benchmark data and generalized sample selection models: an application to eu regional labour markets","author":"Lovaglio","year":"2025","journal-title":"LABOUR"}],"container-title":["MethodsX"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2215016126003821?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2215016126003821?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T21:21:21Z","timestamp":1791926481000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2215016126003821"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":17,"alternative-id":["S2215016126003821"],"URL":"https:\/\/doi.org\/10.1016\/j.mex.2026.104166","relation":{},"ISSN":["2215-0161"],"issn-type":[{"value":"2215-0161","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A reproducible web-scraping pipeline for collecting geolocated German online job advertisements at scale","name":"articletitle","label":"Article Title"},{"value":"MethodsX","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.mex.2026.104166","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104166"}}