Thanks everyone for the pointers. On 6/22/22, 7:05 AM, "Code for Libraries on behalf of Julien Tremblay McLellan" <[log in to unmask] on behalf of [log in to unmask]> wrote: Hi, Just a note if someone wants to do this at scale. Statistics Canada has an AI to convert from pdfs to csv. https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.statcan.gc.ca%2Fen%2Fdata-science%2Fprojects%23pdf-extraction&data=05%7C01%7Candrea.medina-smith%40NIST.GOV%7Cc29940e159de452ef18008da543f15f4%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637914927194949931%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=IpriEBpvU4uafB2dTKA2BgN8Cfz1CSAUK%2F%2FS17YCf%2FQ%3D&reserved=0 On Wed, Jun 22, 2022, 5:59 AM Owen Stephens <[log in to unmask]> wrote: > There was some work at the Wellcome Collection several years ago looking at > extracting tabular information from digitised materials - a brief review > suggests that Abbyy FineReader Engine 11 was used to identify tables, > although there were a number of challenges - how far those challenges were > overcome wasn't clear to me from a brief review, but if this is of interest > there's a post at > > https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstacks.wellcomecollection.org%2F1-million-tables-and-counting-7e7e6c9f76e&data=05%7C01%7Candrea.medina-smith%40NIST.GOV%7Cc29940e159de452ef18008da543f15f4%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637914927194949931%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=tdKda6acvapl9spTnGOVsYC3qxGV0aGFHWO3u9FniDo%3D&reserved=0 > plus a report the Wellcome Collection commissioned at > > https://github.com/wellcometrust/wellcomecollection.org/files/2148381/Scoping.MOH.for.data.recovery.report.-.final.pdf > > Christy Henshaw at the Wellcome Collection may be able to share some of > their experience and learning if you reach out to them > https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Ftwitter.com%2Fchenshaw&data=05%7C01%7Candrea.medina-smith%40NIST.GOV%7Cc29940e159de452ef18008da543f15f4%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637914927194949931%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=x4m%2BjEW%2BZnQRF2WCG4rVGujotsYpB%2F7OOhO6sU%2BJveE%3D&reserved=0 > > Best wishes > > Owen > > On Tue, 21 Jun 2022 at 19:47, Medina-Smith, Andrea M. (Fed) < > [log in to unmask]> wrote: > > > Hello List, > > > > Has anyone had success converting tables in a PDF to CSV? These are scans > > of paper from the 70s on forward. I know this isn’t a super easy > > conversion, but I would think it’s not impossible either. > > > > Thanks, > > Andrea > > > > -- > > > > Andrea Medina-Smith > > Data Librarian > > Information Services Office > > National Institute of Standards and Technology > > [log in to unmask]<mailto:[log in to unmask]> > > https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Forcid.org%2F0000-0002-1217-701X&data=05%7C01%7Candrea.medina-smith%40NIST.GOV%7Cc29940e159de452ef18008da543f15f4%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637914927194949931%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=prHifR7W4w2yNbqqJX1USbIhc2wahD5uwlUuM2Q4nWw%3D&reserved=0 > > > > > > > > -- > Owen Stephens > Owen Stephens Consulting > Web: https://gcc02.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.ostephens.com%2F&data=05%7C01%7Candrea.medina-smith%40NIST.GOV%7Cc29940e159de452ef18008da543f15f4%7C2ab5d82fd8fa4797a93e054655c61dec%7C1%7C0%7C637914927194949931%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=IyGvvcqcoDVaAf1c3A9hMR%2BWiwGEiWA%2Biq%2FYE55GGQU%3D&reserved=0 > Email: [log in to unmask] >