fix(scrapers): cookie fast paths, centralized storage, and reauth hardening (#363)

## Problem

Scraper cookie handling was fragmented across per-platform files with no
shared access, httpx scrapers lacked `checking_login` fast paths on
login, and several re-auth edge cases (CodeChef submit, CF cookie guard,
AtCoder cookie persistence) caused unnecessary full re-logins or silent
failures.

## Solution

Centralize all cookie storage into a single `cookies.json` via helpers
in `base.py`. Add `checking_login` fast paths to `kattis.py` (using the
`x-username` response header as a session probe), `usaco.py`, and
`cses.py` login flows. Fix `kattis.py` submit to emit `checking_login`
only after loading cookies. Remove AtCoder cookie persistence from login
entirely — always do a fresh session. Harden CodeChef and CF reauth
with consistent status logging and cookie guard checks.
This commit is contained in:
Barrett Ruth 2026-03-07 16:10:51 -05:00 committed by GitHub
parent 564f9286da
commit b7ddf4c253
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 813 additions and 194 deletions

View file

@ -8,7 +8,7 @@ from typing import Any, cast
import httpx
from .base import BaseScraper, extract_precision
from .base import BaseScraper, extract_precision, load_platform_cookies, save_platform_cookies
from .timeouts import HTTP_TIMEOUT
from .models import (
ContestListResult,
@ -27,7 +27,6 @@ HEADERS = {
}
CONNECTIONS = 4
_COOKIE_PATH = Path.home() / ".cache" / "cp-nvim" / "usaco-cookies.json"
_LOGIN_PATH = "/current/tpcm/login-session.php"
_SUBMIT_PATH = "/current/tpcm/submit-solution.php"
@ -202,20 +201,16 @@ def _parse_submit_form(
async def _load_usaco_cookies(client: httpx.AsyncClient) -> None:
if not _COOKIE_PATH.exists():
return
try:
for k, v in json.loads(_COOKIE_PATH.read_text()).items():
data = load_platform_cookies("usaco")
if isinstance(data, dict):
for k, v in data.items():
client.cookies.set(k, v)
except Exception:
pass
async def _save_usaco_cookies(client: httpx.AsyncClient) -> None:
cookies = {k: v for k, v in client.cookies.items()}
cookies = dict(client.cookies.items())
if cookies:
_COOKIE_PATH.parent.mkdir(parents=True, exist_ok=True)
_COOKIE_PATH.write_text(json.dumps(cookies))
save_platform_cookies("usaco", cookies)
async def _check_usaco_login(client: httpx.AsyncClient, username: str) -> bool: