import os, io, json
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from googleapiclient.http import MediaIoBaseDownload
import pymupdf

token_path = os.path.expanduser("~/.hermes/profiles/reviewer/google_token.json")
with open(token_path, "r") as f:
    creds_data = json.load(f)

creds = Credentials.from_authorized_user_info(creds_data)
drive_service = build("drive", "v3", credentials=creds)

doc_id = "1sjTe7Im51CY2Tl0SNQrm8xmO7bYweMkq44E0WXaxs1I"

request = drive_service.files().export_media(fileId=doc_id, mimeType="application/pdf")
pdf_bytes = io.BytesIO()
downloader = MediaIoBaseDownload(pdf_bytes, request)
done = False
while not done:
    status, done = downloader.next_chunk()

pdf_bytes.seek(0)
doc = pymupdf.open(stream=pdf_bytes.read(), filetype="pdf")
print(f"Total pages: {len(doc)}")

for page_idx, page in enumerate(doc):
    pix = page.get_pixmap(dpi=150)
    img_path = f"/tmp/doc_page_{page_idx+1}.png"
    pix.save(img_path)
    print(f"Saved page {page_idx+1} to {img_path}")