Disappointing quality of PDF page scraping
We have several documents which contain tables with a lot of relevant information for AI tools. How can I create good markdown files from thes PDF's?
4 Replies
Hi @jvdstoel could you please share what configuration are you using to scrape the pdf?
here's the guide for scraping pdf in markdown format https://docs.firecrawl.dev/advanced-scraping-guide#scraping-pdfs
Firecrawl Docs
Advanced Scraping Guide | Firecrawl
Learn how to improve your Firecrawl scraping with advanced options.
Hi, I am using the Playground on your website.
Can you elaborate on the issue you're facing? I just now tested scraping a sample PDF with lots of tables on the playground. It is giving a well-structured format. Please note that you'll need to disable the main content only to check the option to scrape all PDF pages/tables.
I have tried now a single pdf file... and indeed, this is much better. Thank you!