utils.py

import fitz  # PyMuPDF
import pdfplumber
from PIL import Image
import io

def extract_text_from_pdf(pdf_path):
    try:
        with pdfplumber.open(pdf_path) as pdf:
            text = "\n".join([page.extract_text() for page in pdf.pages if page.extract_text()])
        return text
    except Exception as e:
        return "Failed to extract text from resume."

def extract_image_from_pdf(pdf_path):
    try:
        doc = fitz.open(pdf_path)
        for page in doc:
            images = page.get_images(full=True)
            for img in images:
                xref = img[0]
                base_image = doc.extract_image(xref)
                image_bytes = base_image["image"]
                return Image.open(io.BytesIO(image_bytes))
        return None
    except Exception as e:
        return None

def load_job_description(path="data/job_desc.txt"):
    try:
        with open(path, "r", encoding="utf-8") as f:
            return f.read()
    except FileNotFoundError:
        return "No job description found."