app/utils.py

import re
import pdfplumber


# remove not required things and clean the text
def clean_text(text):
    # Remove HTML tags
    text = re.sub(r'<[^>]*?>', '', text)
    # Remove URLs
    text = re.sub(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', '', text)
    # Remove special characters
    text = re.sub(r'[^a-zA-Z0-9 ]', '', text)
    # Replace multiple spaces with a single space
    text = re.sub(r'\s{2,}', ' ', text)
    # Trim leading and trailing whitespace
    text = text.strip()
    # Remove extra whitespace
    text = ' '.join(text.split())
    return text

def extract_text_from_pdf(uploaded_file):
    if uploaded_file is not None:
        with pdfplumber.open(uploaded_file) as pdf:
            pages = [page.extract_text() for page in pdf.pages]
        return "\n".join(pages) if pages else ""
    return ""