{"id":8056,"date":"2025-02-04T23:15:52","date_gmt":"2025-02-05T04:15:52","guid":{"rendered":"https:\/\/www.mcgurrin.info\/robots\/?p=8056"},"modified":"2025-03-01T23:12:49","modified_gmt":"2025-03-02T04:12:49","slug":"chatgpt-to-extract-data-from-pdfs","status":"publish","type":"post","link":"https:\/\/www.mcgurrin.info\/robots\/8056\/","title":{"rendered":"Quick Post #2: ChatGPT to extract data from PDFs"},"content":{"rendered":"<div id=\"attachment_8057\" style=\"width: 167px\" class=\"wp-caption alignright\"><a href=\"https:\/\/www.mcgurrin.info\/robots\/wp-content\/uploads\/2025\/02\/temp.png\"><img aria-describedby=\"caption-attachment-8057\" decoding=\"async\" loading=\"lazy\" class=\"size-medium wp-image-8057\" src=\"https:\/\/www.mcgurrin.info\/robots\/wp-content\/uploads\/2025\/02\/temp-157x300.png\" alt=\"Screen shot of a page with a table split across a two column layout. The table has four actual columns.\" width=\"157\" height=\"300\" srcset=\"https:\/\/www.mcgurrin.info\/robots\/wp-content\/uploads\/2025\/02\/temp-157x300.png 157w, https:\/\/www.mcgurrin.info\/robots\/wp-content\/uploads\/2025\/02\/temp.png 368w\" sizes=\"(max-width: 157px) 100vw, 157px\" \/><\/a><p id=\"caption-attachment-8057\" class=\"wp-caption-text\">PDF of a table with Social Security tax info<\/p><\/div>\n<p>Just a quick note on a useful application of ChatGPT. You can use it to extract just the subset of the data you want from a table in a pdf document, a really nice time saver.<\/p>\n<p>I wanted the year, max. earnings, and OASDI tax rate for the years 1982 through 2022 from the pdf page here: <a class=\"status-link unhandled-link\" title=\"https:\/\/taxpolicycenter.org\/sites\/default\/files\/statistics\/pdf\/ssrate_historical_2.pdf\" translate=\"no\" href=\"https:\/\/taxpolicycenter.org\/sites\/default\/files\/statistics\/pdf\/ssrate_historical_2.pdf\" target=\"_blank\" rel=\"nofollow noopener\"><span class=\"invisible\">https:\/\/<\/span><span class=\"ellipsis\">taxpolicycenter.org\/sites\/defa<\/span><span class=\"invisible\">ult\/files\/statistics\/pdf\/ssrate_historical_2.pdf<\/span><\/a>. A real pain to cut and paste into excel given the double column and then convert to numbers. So I gave ChatGPT the URL and listed the years and columns I wanted. And I got back a nice table with exactly what I asked for. Nice time saver!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Just a quick note on a useful application of ChatGPT. You can use it to extract just the subset of the data you want from a table in a pdf document, a really nice time saver. I wanted the year, &hellip; <a href=\"https:\/\/www.mcgurrin.info\/robots\/8056\/\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[110,112,109,111],"_links":{"self":[{"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/posts\/8056"}],"collection":[{"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/comments?post=8056"}],"version-history":[{"count":5,"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/posts\/8056\/revisions"}],"predecessor-version":[{"id":8088,"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/posts\/8056\/revisions\/8088"}],"wp:attachment":[{"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/media?parent=8056"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/categories?post=8056"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.mcgurrin.info\/robots\/wp-json\/wp\/v2\/tags?post=8056"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}