“Hey, I’m new to the platform. Sorry for the trouble, but there’s something I can’t figure out. I’m trying to convert PDF files into text. My idea is simple: take invoices in PDF format and load them into Google Sheets or Excel tables. That’s it.”
Hi Matias,
Welcome to the Make community!
PDFs are more complicated than standard text files.
It might be a bit of an overkill, but if you PDF file is extremely complex you could use Google Cloud Vision (or some OCR software) to get the correct text from your PDF
Hello everyone! 
I’m working on a project and have put together some ideas and connections based on similar examples I’ve seen. But I’m facing two major issues that I could use some advice on:
- ChatGPT isn’t recognizing my files and instead seems to be inventing data.
- When I try to save everything in a JSON file, I get an error saying the format is incorrect, and I get stuck there.
If anyone has any tips or has run into similar problems, I’d love to hear how you solved them! Thanks in advance!
Hello Matias_Gallardo,
PDF.co provides a solution for converting PDF documents into text format. You can find more information in our documentation here: PDF to Text Documentation.
Additionally, we offer tools that allow you to convert PDF documents directly into Excel files, which can also be imported into Google Sheets. For more details, please refer to our documentation here: PDF to Excel Documentation.
If you have any questions or need further assistance, please feel free to reach out!
Hello, although I have tried exporting it from ChatGPT as JSON or using PDFco, I keep getting the same error. I don’t know how to fix it. If anyone has any ideas, I would appreciate it
Hello Matias_Gallardo,
We’d like to assist you in resolving the issue you encountered. To help us better understand the situation, could you please provide more details and screenshots, especially about your setup? This will help us determine how the issue might have occurred.
Best regards,
PDF.co Support Team
Hello, good day! I’m sharing these screenshots, but I also want to clarify that I have tried, in the step from pdfco to parse JSON, to use both JSON file formats offered by pdfco: “legacy” and “new”. In the parse JSON step, I tried using the output from pdfco and also manually entering the JSON string
Hello Matias_Gallardo.
Thank you for sharing the screenshot! To proceed, please use the generated data from PDF.co PDF to JSON as a JSON string. For your reference, we have provided a sample screenshot below:
If you continue to encounter any issues or need further assistance, please don’t hesitate to reach out. We’re here to help!
Best regards,
PDF.co Support Team