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
+82 -3
View File
@@ -3,6 +3,7 @@
import asyncio
import logging
import re
from dataclasses import dataclass
from datetime import datetime, timedelta
from typing import Optional
@@ -19,6 +20,7 @@ from app.models.download import Download, DownloadStatus, ErrorType as DBErrorTy
from app.models.setting import Setting, DEFAULT_SETTINGS
from app.services.gallery_dl import GalleryDLService, SourceConfig, DownloadResult
from app.services.credential_manager import CredentialManager
from app.services.patreon_resolver import resolve_campaign_id
from app.events import publish_event
logger = logging.getLogger(__name__)
@@ -113,6 +115,71 @@ def _extract_vanity_from_url(url: str) -> Optional[str]:
return m.group(1) if m else None
@dataclass
class _DownloadAttempt:
"""Result of executing a download, possibly with a retry after campaign-ID resolution."""
dl_result: DownloadResult
resolved_campaign_id: Optional[str]
async def _execute_download_with_retry(
*,
gdl_service,
platform: str,
source_url: str,
source_metadata: dict,
subscription_name: str,
source_config,
cookies_path: Optional[str],
auth_token: Optional[str],
) -> _DownloadAttempt:
"""Run the download once, auto-heal Patreon campaign-ID failures with one retry.
Returns a _DownloadAttempt wrapping:
- the final DownloadResult (retry's result if we retried, else the first)
- resolved_campaign_id: the newly-resolved ID (if we resolved one this call), else None
The caller is responsible for persisting resolved_campaign_id into source.metadata_.
"""
effective_url = _effective_patreon_url(platform, source_url, source_metadata)
dl_result = await gdl_service.download(
url=effective_url,
subscription_name=subscription_name,
platform=platform,
source_config=source_config,
cookies_path=cookies_path,
auth_token=auth_token,
)
# Only retry if: patreon + campaign-ID failure + no cached id + extractable vanity
if (
platform == "patreon"
and not dl_result.success
and "patreon_campaign_id" not in (source_metadata or {})
and _looks_like_campaign_id_failure(dl_result)
):
vanity = _extract_vanity_from_url(source_url)
if vanity:
logger.info(
f"Attempting campaign-ID resolution for {subscription_name}/patreon ({vanity})"
)
campaign_id = await resolve_campaign_id(vanity, cookies_path)
if campaign_id:
retry_result = await gdl_service.download(
url=f"https://www.patreon.com/id:{campaign_id}",
subscription_name=subscription_name,
platform=platform,
source_config=source_config,
cookies_path=cookies_path,
auth_token=auth_token,
)
return _DownloadAttempt(
dl_result=retry_result, resolved_campaign_id=campaign_id
)
return _DownloadAttempt(dl_result=dl_result, resolved_campaign_id=None)
async def _download_source_async(source_id: int, download_id: int = None) -> dict:
"""Async implementation of source download.
@@ -255,17 +322,22 @@ async def _download_source_async(source_id: int, download_id: int = None) -> dic
source_config = SourceConfig.from_dict(source_metadata)
dl_result = None
dl_error = None
resolved_campaign_id: Optional[str] = None
try:
gdl_service = GalleryDLService(rate_limit=db_rate_limit)
dl_result = await gdl_service.download(
url=source_url,
subscription_name=subscription_name,
attempt = await _execute_download_with_retry(
gdl_service=gdl_service,
platform=source_platform,
source_url=source_url,
source_metadata=source_metadata,
subscription_name=subscription_name,
source_config=source_config,
cookies_path=cookies_path,
auth_token=auth_token,
)
dl_result = attempt.dl_result
resolved_campaign_id = attempt.resolved_campaign_id
except Exception as e:
logger.exception(f"Unexpected error downloading {subscription_name}/{source_platform}: {e}")
dl_error = e
@@ -287,6 +359,13 @@ async def _download_source_async(source_id: int, download_id: int = None) -> dic
logger.error(f"Could not re-fetch download {actual_download_id} or source {source_id} for result update")
return {"source_id": source_id, "status": "error", "error": "Lost DB records"}
# Persist resolved campaign ID (if the retry hook resolved one this run)
if resolved_campaign_id:
source.metadata_ = {
**(source.metadata_ or {}),
"patreon_campaign_id": resolved_campaign_id,
}
if dl_error:
download.status = DownloadStatus.FAILED
download.error_type = DBErrorType.UNKNOWN_ERROR