ocr.py

import os
import pytesseract
from pdf2image import convert_from_path
from docx import Document

def extract_text_from_file(filepath):
    ext = os.path.splitext(filepath)[1].lower()
    if ext == ".pdf":
        return extract_text_from_pdf(filepath)
    elif ext == ".docx":
        return extract_text_from_docx(filepath)
    elif ext in [".png", ".jpg", ".jpeg"]:
        return extract_text_from_image(filepath)
    elif ext == ".txt":
        with open(filepath, "r", encoding="utf-8") as f:
            return f.read()
    else:
        return ""

def extract_text_from_pdf(filepath):
    images = convert_from_path(filepath)
    text = ""
    for img in images:
        text += pytesseract.image_to_string(img)
    return text

def extract_text_from_docx(filepath):
    doc = Document(filepath)
    return "\n".join([para.text for para in doc.paragraphs])

def extract_text_from_image(filepath):
    return pytesseract.image_to_string(filepath)