barrett/cp.nvim
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix(scrapers): harden CSES and CF submit edge cases (#295) (#318)

Browse source 
## Problem

CSES `_web_login` used bare dict indexing on the API response, raising
an opaque `KeyError` on missing fields. `_check_token` swallowed all
exceptions as `False`, conflating transient network errors with invalid
tokens. CF persisted cookies unconditionally and silently swallowed
`_solve_turnstile` failures in `submit_action`.

## Solution

CSES API fields now use `.get()` with a descriptive `RuntimeError` on
absence. `_check_token` re-raises `httpx` network/timeout exceptions
so callers see real failures. CF cookie writes are guarded by an
`X-User-Handle` check (the CF auth cookie). `_solve_turnstile` errors
propagate to the outer error handler instead of being silenced.
This commit is contained in:
Barrett Ruth 2026-03-05 19:00:35 -05:00 • committed by GitHub
parent 6c036a7b2e
commit b959f29bd4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 12 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

10
scrapers/codeforces.py
View file

@ -401,7 +401,8 @@ def _login_headless_cf(credentials: dict[str, str]) -> LoginResult:
try: try:
browser_cookies = session.context.cookies() browser_cookies = session.context.cookies()
cookie_cache.write_text(json.dumps(browser_cookies)) if any(c.get("name") == "X-User-Handle" for c in browser_cookies):
cookie_cache.write_text(json.dumps(browser_cookies))
except Exception: except Exception:
pass pass
@ -478,10 +479,7 @@ def _submit_headless(
if "/enter" in page.url or "/login" in page.url: if "/enter" in page.url or "/login" in page.url:
needs_relogin = True needs_relogin = True
return return
try: _solve_turnstile(page)
_solve_turnstile(page)
except Exception:
pass
try: try:
page.select_option( page.select_option(
'select[name="submittedProblemIndex"]', 'select[name="submittedProblemIndex"]',
@ -550,7 +548,7 @@ def _submit_headless(
try: try:
browser_cookies = session.context.cookies() browser_cookies = session.context.cookies()
if browser_cookies: if any(c.get("name") == "X-User-Handle" for c in browser_cookies):
cookie_cache.write_text(json.dumps(browser_cookies)) cookie_cache.write_text(json.dumps(browser_cookies))
except Exception: except Exception:
pass pass

12
scrapers/cses.py
View file

@ -352,8 +352,12 @@ class CSESScraper(BaseScraper):
f"{API_URL}/login", headers=HEADERS, timeout=HTTP_TIMEOUT f"{API_URL}/login", headers=HEADERS, timeout=HTTP_TIMEOUT
) )
api_data = api_resp.json() api_data = api_resp.json()
token: str = api_data["X-Auth-Token"] token: str | None = api_data.get("X-Auth-Token")
auth_url: str = api_data["authentication_url"] auth_url: str | None = api_data.get("authentication_url")
if not token:
raise RuntimeError("CSES API login response missing 'X-Auth-Token'")
if not auth_url:
raise RuntimeError("CSES API login response missing 'authentication_url'")
auth_page = await client.get(auth_url, headers=HEADERS, timeout=HTTP_TIMEOUT) auth_page = await client.get(auth_url, headers=HEADERS, timeout=HTTP_TIMEOUT)
auth_csrf = re.search(r'name="csrf_token" value="([^"]+)"', auth_page.text) auth_csrf = re.search(r'name="csrf_token" value="([^"]+)"', auth_page.text)
@ -388,8 +392,8 @@ class CSESScraper(BaseScraper):
timeout=HTTP_TIMEOUT, timeout=HTTP_TIMEOUT,
) )
return r.status_code == 200 return r.status_code == 200
except Exception: except (httpx.ConnectError, httpx.TimeoutException, httpx.NetworkError):
return False raise
async def submit( async def submit(
self, self,