Patch: Migrate bypasser to pure CDP + Misc fixes (#575)

Bypasser:
- Refactored internal bypasser logic to use SeleniumBase Pure CDP mode,
removed chromedriver dependencies and UC code.
- Added dedicated threading for internal bypasser functions, fixes any
potential asyncio CPU spike behavior
- Fixed WebGL issue with Chromium 144. Reverted 1.0.3 hotfix and updated
to latest Chromium

Misc: 
- Added M4A color mapping
- Fix frontend language filtering with multi-language releases
- Added "days" age for usenet/torrent releases
- Improved entrypoint chown efficiency
- Added `ONBOARDING` env variable, default true
This commit is contained in:
Alex
2026-02-02 20:32:19 +00:00
committed by GitHub
parent f6dba959c9
commit b10458a48b
14 changed files with 518 additions and 500 deletions
+67
View File
@@ -22,3 +22,70 @@ def test_bypass_tries_all_methods_before_abort(monkeypatch):
assert internal_bypasser._bypass(object(), max_retries=10) is False
assert calls == [f"m{i}" for i in range(6)]
def test_extract_cookies_from_cdp_filters_and_stores_ua():
import time
import shelfmark.bypass.internal_bypasser as internal_bypasser
class FakeCookie:
def __init__(self, name, value, domain, path, expires, secure=True):
self.name = name
self.value = value
self.domain = domain
self.path = path
self.expires = expires
self.secure = secure
class FakeSb:
def get_all_cookies(self, requests_cookie_format=False):
assert requests_cookie_format is True
return [
FakeCookie("cf_clearance", "abc", "example.com", "/", int(time.time()) + 3600),
FakeCookie("sessionid", "zzz", "example.com", "/", int(time.time()) + 3600),
]
def get_user_agent(self):
return "TestUA/1.0"
internal_bypasser.clear_cf_cookies()
internal_bypasser._extract_cookies_from_cdp(FakeSb(), "https://www.example.com/path")
cookies = internal_bypasser.get_cf_cookies_for_domain("example.com")
assert cookies == {"cf_clearance": "abc"}
assert internal_bypasser.get_cf_user_agent_for_domain("example.com") == "TestUA/1.0"
def test_extract_cookies_from_cdp_normalizes_session_expiry():
import time
import shelfmark.bypass.internal_bypasser as internal_bypasser
class FakeCookie:
def __init__(self, name, value, domain, path, expires, secure=True):
self.name = name
self.value = value
self.domain = domain
self.path = path
self.expires = expires
self.secure = secure
class FakeSb:
def get_all_cookies(self, requests_cookie_format=False):
assert requests_cookie_format is True
return [
FakeCookie("cf_clearance", "abc", "example.com", "/", 0),
]
def get_user_agent(self):
return "TestUA/1.0"
internal_bypasser.clear_cf_cookies()
internal_bypasser._extract_cookies_from_cdp(FakeSb(), "https://example.com")
stored = internal_bypasser._cf_cookies.get("example.com", {})
assert stored["cf_clearance"]["expiry"] is None
assert internal_bypasser.get_cf_cookies_for_domain("example.com") == {"cf_clearance": "abc"}
# Verify fallback to "expires" key for expiry checks
internal_bypasser._cf_cookies["example.com"]["cf_clearance"]["expires"] = int(time.time()) - 10
assert internal_bypasser.get_cf_cookies_for_domain("example.com") == {}