src/functions_pdf.py

import pymupdf
from PyPDF2 import PdfReader
from pdfminer.high_level import extract_text
from langchain.document_loaders import PDFPlumberLoader
import streamlit as st

def pymupdf_pdf_to_text(file_path):
    """
    Extract text from a PDF file using PyMuPDF.
    
    Args:
        file_path (str): Path to the PDF file.
    
    Returns:
        str: Extracted text from the PDF file.
    """
    doc = pymupdf.open(stream=file_path.read(), filetype="pdf")  
    text = ""
    for page in doc: 
        text += page.get_text()  + "\n"
    return text  

def pypdf2_pdf_to_text(file_path):
    """
    Extract text from a PDF file using PyPDF2.
    
    Args:
        file_path (str): Path to the PDF file.
    
    Returns:
        str: Extracted text from the PDF file.
    """
    reader = PdfReader(file_path)
    text = ""
    for page in reader.pages:
        text += page.extract_text() + "\n"
    return text

# def pdfminer_pdf_to_text(file_path):
#     """
#     Extract text from a PDF file using pdfminer.
    
#     Args:
#         file_path (str): Path to the PDF file.
    
#     Returns:
#         str: Extracted text from the PDF file.
#     """
#     # Implementation for pdfminer extraction goes here
#     text = extract_text(file_path)
#     return text

def pdfminer_pdf_to_text(pdf_path: str) -> str:
    try:
        text = extract_text(pdf_path)
        return text.strip()
    except Exception as e:
        st.error(f"Error extracting text: {e}")
        return ""

def pdfplumber_pdf_to_text(file_path):
    """
    Extract text from a PDF file using pdfplumber.
    
    Args:
        file_path (str): Path to the PDF file.
    
    Returns:
        str: Extracted text from the PDF file.
    """
    loader = PDFPlumberLoader(file_path)
    documents = loader.load()
    text = ""
    for doc in documents:
        text += doc.page_content + "\n"
    return text