import io, urllib.parse, urllib.request
from pathlib import Path
from pypdf import PdfReader

JEI = Path(r"C:\Users\SJ\.minimax-agent\projects\JEI")
env = {}
for line in (JEI / ".env.local").read_text(encoding="utf-8").splitlines():
    line = line.strip()
    if line and not line.startswith("#") and "=" in line:
        k, v = line.split("=", 1)
        env[k.strip()] = v.strip().strip('"').strip("'")
PB = env.get("NEXT_PUBLIC_PB_URL") or env["PB_URL"]
TOK = env["PB_TOKEN"]

TARGETS = [
    ("STORED resolution.signed_letter", "pbc_266170881", "e0dbxprazb70rqx", "corrected_v2_avwpnq7o93.pdf"),
    ("STORED resignation.letter", "ysterbaard_director_resignations", "8cfie18uhgy0n0o",
     "resignation_letter_the_ultimate_fuel_company_1jk8t34nf3.pdf"),
    ("STORED resignation.signature", "ysterbaard_director_resignations", "8cfie18uhgy0n0o",
     "tbde1evt2m6_8mz8kutpki.pdf"),
]

for label, col, rid, fname in TARGETS:
    url = f"{PB}/api/files/{col}/{rid}/{urllib.parse.quote(fname)}"
    req = urllib.request.Request(url, headers={"Authorization": TOK})
    with urllib.request.urlopen(req, timeout=120) as r:
        b = r.read()
    reader = PdfReader(io.BytesIO(b))
    print("=" * 78)
    print(f"{label}   ({fname})   pages={len(reader.pages)}")
    print("=" * 78)
    for i, p in enumerate(reader.pages):
        t = p.extract_text() or ""
        print(f"--- page {i+1} ---")
        print(t.strip())
    print()