c-stone-invoice-check/backend/fetchers/direct.py
2026-11-13 23:07:22 +01:00

35 lines
1.4 KiB
Python

"""Stufe 2: Rechnungs-PDF per Direktlink laden (Stripe, Paddle, ThriveCart, *.pdf, Tracker-Links z.B. OpenAI)."""
import re
import urllib.request
from typing import Optional
from urllib.parse import urlsplit
from backend.routers.emails import DIRECT_LINK, TRACKERS
MAX_BYTES = 20 * 1024 * 1024
UA = {"User-Agent": "Mozilla/5.0 (C-Stone Invoice Picker)"}
STRIPE_HOSTED = re.compile(r"^https://invoice\.stripe\.com/i/(acct_\w+)/(\w+)", re.I)
def pdf_url(url: str) -> str:
"""Stripe-Rechnungsseite (HTML) -> PDF-Download-URL; alles andere unverändert."""
m = STRIPE_HOSTED.match(url)
if not m:
return url
q = urlsplit(url).query
return f"https://pay.stripe.com/invoice/{m[1]}/{m[2]}/pdf" + (f"?{q}" if q else "")
def fetch_pdf(url: str, timeout: int = 30) -> Optional[bytes]:
"""-> PDF-Bytes oder None (kein PDF, z.B. HTML-Login-Seite)."""
if TRACKERS.match(url): # nur Weiterleitung auflösen, Ziel muss wieder auf der Allowlist stehen
with urllib.request.urlopen(urllib.request.Request(url, headers=UA), timeout=timeout) as r:
url = r.geturl()
if not DIRECT_LINK.search(url):
return None
with urllib.request.urlopen(urllib.request.Request(pdf_url(url), headers=UA), timeout=timeout) as r:
data = r.read(MAX_BYTES + 1)
if len(data) > MAX_BYTES or not data.startswith(b"%PDF-"):
return None
return data