Extraction of data from PDF files
Hi team @Adobe.Flash @rafaelmiller ,
Do we have the data extraction feature from PDF files (.pdf) using the FireCrawl Service in place at the moment?
4 Replies
Hey @Sachin you should be able to scrape PDF pages. We currently use llama parse for handling that.
@rafaelmiller , I believe that would be for PDF links found in the sitemap. Is there any functionality which allows to provide a local path for the PDF file and get a markdown for the scraped data as well?
It would be helpful if you can guide on the same if we have already have something in the FireCrawl capabilities.
oh I see.. you would have to serve those pdfs for scraping it using firecrawl
ok, thanks.