/Get-Pdf-Summary

a pdf summarizer using NLTK :: Natural Language Toolkit.

Primary LanguagePython

PDF Summarizer using Streamlit,NLTK :: Natural Language Toolkit

This project is a simple PDF summarizer built with Streamlit. It allows users to upload a PDF file, extracts the text from the PDF, and generates a summary using NLTK.

Installation

  1. Clone this repository to your local machine:

    git clone (https://github.com/MRH-Romit/Get-Pdf-Summary.git)

  2. Navigate to the project directory:

      cd pdf-summarizer

  3. install the required dependencies:

    pip install streamlit
pip install pdfplumber
pip install nltk

Usage

  1. Run the Streamlit app:
  streamlit run app.py
  1. Once the app is running, you can upload a PDF file using the file uploader.
  2. The app will extract the text from the uploaded PDF file and generate a summary using NLTK.
  3. The generated summary will be displayed in the app.

Dependencies

Streamlit: streamlit PDF text extraction: pdfplumber Natural Language Processing: nltk

#File Structure

  • app.py: Main Streamlit application script.
  • text_extraction.py: Module containing functions for extracting text from PDF files.
  • summarization.py: Module containing functions for summarizing text.
  • requirements.txt: List of dependencies.

#screenshot image

image