app/services/resume_parser.py

import os
import requests
import io
import pdfplumber

def extract_resume_text(file_url: str) -> str:
    HF_TOKEN = os.getenv("HF_TOKEN")
    headers = {"Authorization": f"Bearer {HF_TOKEN}"}

    try:
        response = requests.get(file_url, headers=headers, timeout=30)
        response.raise_for_status()

        pdf_bytes = io.BytesIO(response.content)

        text = ""
        with pdfplumber.open(pdf_bytes) as pdf:
            for page in pdf.pages:
                page_text = page.extract_text()
                if page_text:
                    text += page_text + "\n"

        return text.strip()

    except Exception as e:
        raise RuntimeError(f"Failed to extract text from resume: {str(e)}")