feat(downloads): auto-heal patreon campaign-ID failures via resolver retry

This commit is contained in:
2026-04-18 14:11:11 -04:00
parent 8e3da096ec
commit 35589e996a
2 changed files with 308 additions and 3 deletions
@@ -0,0 +1,226 @@
"""Integration tests for the Patreon campaign-ID retry hook in downloads.py.
These tests exercise _execute_download_with_retry — the pure async helper
that owns the download → resolver → retry logic — without standing up a
full Celery + DB environment.
"""
from types import SimpleNamespace
from unittest.mock import AsyncMock
import pytest
from app.tasks import downloads as downloads_module
from app.tasks.downloads import _execute_download_with_retry
def _make_gdl_service(results):
"""Build a fake GalleryDLService whose .download() returns results in order."""
service = SimpleNamespace()
service.download = AsyncMock(side_effect=list(results))
return service
def _success(url="https://www.patreon.com/id:12345"):
return SimpleNamespace(
success=True, stdout="", stderr="",
files_downloaded=3, url=url, error_type=None, error_message=None,
)
def _campaign_id_failure(url="https://www.patreon.com/mstsu"):
return SimpleNamespace(
success=False,
stdout="",
stderr="[patreon][error] Failed to extract campaign ID",
files_downloaded=0, url=url, error_type=None,
error_message="Failed to extract campaign ID",
)
def _other_failure(url="https://www.patreon.com/mstsu"):
return SimpleNamespace(
success=False, stdout="", stderr="HTTP 401 Unauthorized",
files_downloaded=0, url=url, error_type=None,
error_message="Authentication failed",
)
async def test_happy_path_heal(monkeypatch):
"""Patreon source fails with campaign-ID error, resolver returns ID, retry succeeds."""
gdl = _make_gdl_service([_campaign_id_failure(), _success()])
monkeypatch.setattr(
downloads_module,
"resolve_campaign_id",
AsyncMock(return_value="12345"),
)
result = await _execute_download_with_retry(
gdl_service=gdl,
platform="patreon",
source_url="https://www.patreon.com/mstsu",
source_metadata={},
subscription_name="MSTSU",
source_config=SimpleNamespace(),
cookies_path="/data/cookies/patreon_cookies.txt",
auth_token=None,
)
assert result.dl_result.success is True
assert result.resolved_campaign_id == "12345"
assert gdl.download.call_count == 2
first_call_url = gdl.download.call_args_list[0].kwargs["url"]
second_call_url = gdl.download.call_args_list[1].kwargs["url"]
assert first_call_url == "https://www.patreon.com/mstsu"
assert second_call_url == "https://www.patreon.com/id:12345"
async def test_resolver_returns_none(monkeypatch):
"""Campaign-ID failure + resolver returns None → no retry, no metadata, original failure surfaced."""
first_failure = _campaign_id_failure()
gdl = _make_gdl_service([first_failure])
monkeypatch.setattr(
downloads_module,
"resolve_campaign_id",
AsyncMock(return_value=None),
)
result = await _execute_download_with_retry(
gdl_service=gdl,
platform="patreon",
source_url="https://www.patreon.com/mstsu",
source_metadata={},
subscription_name="MSTSU",
source_config=SimpleNamespace(),
cookies_path="/data/cookies/patreon_cookies.txt",
auth_token=None,
)
assert result.dl_result is first_failure
assert result.resolved_campaign_id is None
assert gdl.download.call_count == 1
async def test_already_cached_campaign_id(monkeypatch):
"""Source has cached campaign_id → first download uses id-URL, no resolver call."""
gdl = _make_gdl_service([_success()])
resolver_mock = AsyncMock(return_value="should-not-be-called")
monkeypatch.setattr(downloads_module, "resolve_campaign_id", resolver_mock)
result = await _execute_download_with_retry(
gdl_service=gdl,
platform="patreon",
source_url="https://www.patreon.com/mstsu",
source_metadata={"patreon_campaign_id": "99999"},
subscription_name="MSTSU",
source_config=SimpleNamespace(),
cookies_path="/data/cookies/patreon_cookies.txt",
auth_token=None,
)
assert result.dl_result.success is True
assert result.resolved_campaign_id is None
assert gdl.download.call_count == 1
assert gdl.download.call_args.kwargs["url"] == "https://www.patreon.com/id:99999"
resolver_mock.assert_not_called()
async def test_non_patreon_failure_skips_retry(monkeypatch):
"""Non-Patreon source with similar-looking output → retry hook doesn't fire."""
failure = SimpleNamespace(
success=False,
stdout="",
stderr="some error that contains failed to extract campaign id text",
files_downloaded=0, url="https://subscribestar.adult/foo",
error_type=None, error_message="unknown",
)
gdl = _make_gdl_service([failure])
resolver_mock = AsyncMock(return_value="should-not-be-called")
monkeypatch.setattr(downloads_module, "resolve_campaign_id", resolver_mock)
result = await _execute_download_with_retry(
gdl_service=gdl,
platform="subscribestar",
source_url="https://subscribestar.adult/foo",
source_metadata={},
subscription_name="Foo",
source_config=SimpleNamespace(),
cookies_path=None,
auth_token=None,
)
assert result.dl_result is failure
assert result.resolved_campaign_id is None
resolver_mock.assert_not_called()
assert gdl.download.call_count == 1
async def test_patreon_different_failure_skips_retry(monkeypatch):
"""Patreon source with non-campaign-ID error → no resolver, no retry."""
failure = _other_failure()
gdl = _make_gdl_service([failure])
resolver_mock = AsyncMock(return_value="should-not-be-called")
monkeypatch.setattr(downloads_module, "resolve_campaign_id", resolver_mock)
result = await _execute_download_with_retry(
gdl_service=gdl,
platform="patreon",
source_url="https://www.patreon.com/mstsu",
source_metadata={},
subscription_name="MSTSU",
source_config=SimpleNamespace(),
cookies_path="/data/cookies/patreon_cookies.txt",
auth_token=None,
)
assert result.dl_result is failure
assert result.resolved_campaign_id is None
resolver_mock.assert_not_called()
assert gdl.download.call_count == 1
async def test_unextractable_vanity_skips_retry(monkeypatch):
"""Patreon source whose URL can't yield a vanity → no resolver call."""
failure = _campaign_id_failure(url="https://www.patreon.com/")
gdl = _make_gdl_service([failure])
resolver_mock = AsyncMock(return_value="should-not-be-called")
monkeypatch.setattr(downloads_module, "resolve_campaign_id", resolver_mock)
result = await _execute_download_with_retry(
gdl_service=gdl,
platform="patreon",
source_url="https://www.patreon.com/",
source_metadata={},
subscription_name="?",
source_config=SimpleNamespace(),
cookies_path=None,
auth_token=None,
)
assert result.dl_result is failure
resolver_mock.assert_not_called()
assert gdl.download.call_count == 1
async def test_retry_itself_fails(monkeypatch):
"""Resolver succeeds but retry fails → cache id, surface retry's failure."""
first_failure = _campaign_id_failure()
retry_failure = _other_failure()
gdl = _make_gdl_service([first_failure, retry_failure])
monkeypatch.setattr(
downloads_module, "resolve_campaign_id", AsyncMock(return_value="12345")
)
result = await _execute_download_with_retry(
gdl_service=gdl,
platform="patreon",
source_url="https://www.patreon.com/mstsu",
source_metadata={},
subscription_name="MSTSU",
source_config=SimpleNamespace(),
cookies_path="/data/cookies/patreon_cookies.txt",
auth_token=None,
)
assert result.dl_result is retry_failure # retry's result wins
assert result.resolved_campaign_id == "12345" # ID still cached
assert gdl.download.call_count == 2