https://github.com/dvelkow/pdf_data_scraper

Scrapes all the data from a pdf and turns it into a relational table in a csv format, uses chatgpt API to do so
https://github.com/dvelkow/pdf_data_scraper

Last synced: 18 days ago
JSON representation

Scrapes all the data from a pdf and turns it into a relational table in a csv format, uses chatgpt API to do so

• Host: GitHub
• URL: https://github.com/dvelkow/pdf_data_scraper
• Owner: dvelkow
• Created: 2024-08-06T20:54:20.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-08-06T22:53:35.000Z (6 months ago)
• Last Synced: 2025-01-11T04:07:05.346Z (19 days ago)
• Language: Python
• Size: 2.93 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## Overview

This project implements a smart PDF data extractor that uses OpenAI's GPT model to go through PDF documents and extract specific information. The extracted data is then saved into a CSV file, making it easy to analyze and process the information.

## Features

- Extract user-specified data fields from PDF documents

- Output extracted data to a CSV file for easy analysis

## How To Run

First, clone the repository:

`` git clone https://github.com/dvelkow/pdf_data_scraper ``

Then navigate to the directory and run the main.py file:

`` python3 main.py ``

#### IMPROTANT: The script will prompt you to enter the data fields you want to extract (comma-separated)