pdf_loader.py

import requests
from pypdf import PdfReader
from io import BytesIO
import re


def _get_drive_file_id(url: str) -> str | None:
    patterns = [
        r"/d/([a-zA-Z0-9_-]+)",
        r"id=([a-zA-Z0-9_-]+)"
    ]
    for p in patterns:
        m = re.search(p, url)
        if m:
            return m.group(1)
    return None


def _download_from_drive(file_id: str) -> bytes:
    URL = "https://drive.google.com/uc?export=download"
    session = requests.Session()

    response = session.get(URL, params={"id": file_id}, stream=True)
    token = None

    # Google sometimes asks for confirmation
    for k, v in response.cookies.items():
        if k.startswith("download_warning"):
            token = v

    if token:
        response = session.get(
            URL,
            params={"id": file_id, "confirm": token},
            stream=True
        )

    return response.content


def load_pdf_from_url(url: str) -> str:
    url = url.strip()

    if "drive.google.com" in url:
        file_id = _get_drive_file_id(url)
        if not file_id:
            raise ValueError("❌ Invalid Google Drive link")

        file_bytes = _download_from_drive(file_id)

    else:
        response = requests.get(url, timeout=30)
        response.raise_for_status()
        file_bytes = response.content

    # 🔐 Validate PDF signature
    if not file_bytes.startswith(b"%PDF"):
        raise ValueError(
            "❌ Downloaded file is not a valid PDF. "
            "Check permissions or file type."
        )

    reader = PdfReader(BytesIO(file_bytes))

    text = ""
    for page in reader.pages:
        page_text = page.extract_text()
        if page_text:
            text += page_text + "\n"

    if not text.strip():
        raise ValueError("⚠️ PDF loaded but contains no extractable text.")

    return text