Home
Events
Groups
Members

00 Clay Announcements
01 Community General
01 Props and Wins
01 Watercooler
01 Welcome and Intros
02 Bugs
02 Starting with Clay
02 Support
03 Feedback & Requests
03 Tutorials & Inspiration
04 FT Job Opps
Gtm Career Advice
Member Spotlight

Community Guidelines

Powered by Tightknit

Scraping PDF for Contacts: GPT vs. Instant Data Scraper

Dominick Cappuccilli

·

·

Does anyone know of a way to scrape a PDF to get contacts from it? Can I use GPT for this? Just wondering if there is a solution. I know instant data scraper, but I don't think that will work with a PDF.

Scraping PDF for Contacts: GPT vs. Instant Data Scraper | Clay

8 comments

· Sorted by Oldest

Muhammad
·
·
How many pages on avg each PDF has?
Muhammad
·
·
see this API: https://docs.documentpro.ai/docs/using-api/manage-documents/import-files
Dominick Cappuccilli
·
·
It’s one pdf with 196 pages
Muhammad
·
·
Ok, Dominick Cappuccilli do you want to get the contacts extract one time or you want to add it to a clay flow? If its one time, I can help you extract contacts.
Dominick Cappuccilli
·
·
It would be a clay flow likely but also good to have it in the arsenal
Clay Team
APP
·
·
Hi Dominick Cappuccilli, sorry for the delay here! We are actually in the process of integrating a pdf scraping provider into Clay - don't have an exact ETA on this but it should be done soon!
Clay Team
APP
·
·
In the meantime, if you're able to find an external pdf scraper (examples are Reducto or Unstructured), you can pull them into Clay using the HTTP API function. Tutorials here: https://support.clay.com/docs/enrichments-and-providers/enrichments/all-providers/http-api, https://www.loom.com/share/114ff06973bd4ed7985b32fa031be867
Clay Team
APP
·
·
We'll hopefully have it available on Clay soon!