feat(patreon): add campaign-ID resolver service

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-18 13:22:36 -04:00
parent d819a184a1
commit ce8ba538b7
3 changed files with 205 additions and 0 deletions
@@ -0,0 +1,119 @@
+"""Patreon campaign-ID resolver.
+
+When gallery-dl fails with "Failed to extract campaign ID" on a Patreon
+source, call resolve_campaign_id(vanity, cookies_path) to look up the
+campaign ID via Patreon's campaigns API. The caller can then retry with
+the id-URL form (patreon.com/id:<id>) to bypass the broken vanity lookup.
+"""
+import asyncio
+import http.cookiejar
+import logging
+import os
+from typing import Optional
+
+import aiohttp
+
+logger = logging.getLogger(__name__)
+
+_CAMPAIGNS_URL = "https://www.patreon.com/api/campaigns"
+_USER_AGENT = (
+    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
+    "(KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
+)
+_REQUEST_TIMEOUT_SECONDS = 10.0
+
+
+def _load_cookie_jar(cookies_path: Optional[str]) -> Optional[aiohttp.CookieJar]:
+    """Load a Netscape-format cookie file into an aiohttp CookieJar.
+
+    Returns None if the path is None, the file is missing, or parsing fails.
+    Never raises.
+    """
+    if not cookies_path or not os.path.isfile(cookies_path):
+        return None
+    try:
+        moz = http.cookiejar.MozillaCookieJar(cookies_path)
+        moz.load(ignore_discard=True, ignore_expires=True)
+    except (OSError, http.cookiejar.LoadError) as e:
+        logger.debug(f"Could not load cookies from {cookies_path}: {e}")
+        return None
+
+    jar = aiohttp.CookieJar()
+    for cookie in moz:
+        jar.update_cookies(
+            {cookie.name: cookie.value},
+            response_url=aiohttp.helpers.URL(
+                f"https://{cookie.domain.lstrip('.')}/"
+            ),
+        )
+    return jar
+
+
+async def resolve_campaign_id(
+    vanity: str,
+    cookies_path: Optional[str],
+) -> Optional[str]:
+    """Resolve a Patreon vanity (creator slug) to a campaign ID.
+
+    Returns the campaign ID as a string, or None on any failure (network
+    error, auth error, empty response, unexpected shape). Never raises.
+    """
+    jar = _load_cookie_jar(cookies_path)
+    headers = {
+        "User-Agent": _USER_AGENT,
+        "Accept": "application/vnd.api+json",
+    }
+    params = {
+        "filter[vanity]": vanity,
+        "fields[campaign]": "name",
+    }
+    timeout = aiohttp.ClientTimeout(total=_REQUEST_TIMEOUT_SECONDS)
+
+    try:
+        async with aiohttp.ClientSession(
+            cookie_jar=jar,
+            headers=headers,
+            timeout=timeout,
+        ) as session:
+            async with session.get(_CAMPAIGNS_URL, params=params) as resp:
+                if resp.status != 200:
+                    logger.warning(
+                        f"Patreon campaigns API returned HTTP {resp.status} for vanity={vanity}"
+                    )
+                    return None
+                try:
+                    payload = await resp.json(content_type=None)
+                except (aiohttp.ContentTypeError, ValueError) as e:
+                    logger.warning(
+                        f"Patreon campaigns API returned non-JSON for vanity={vanity}: {e}"
+                    )
+                    return None
+    except asyncio.TimeoutError:
+        logger.warning(f"Patreon campaigns API timed out for vanity={vanity}")
+        return None
+    except aiohttp.ClientError as e:
+        logger.warning(
+            f"Patreon campaigns API request failed for vanity={vanity}: "
+            f"{type(e).__name__}: {e}"
+        )
+        return None
+
+    data = payload.get("data") if isinstance(payload, dict) else None
+    if not isinstance(data, list) or not data:
+        logger.warning(
+            f"Patreon campaigns API returned empty/missing data for vanity={vanity}: "
+            f"payload keys={list(payload) if isinstance(payload, dict) else type(payload).__name__}"
+        )
+        return None
+
+    first = data[0] if isinstance(data[0], dict) else None
+    campaign_id = first.get("id") if first else None
+    if not isinstance(campaign_id, str) or not campaign_id:
+        logger.warning(
+            f"Patreon campaigns API response missing 'id' for vanity={vanity}: "
+            f"first entry keys={list(first) if isinstance(first, dict) else type(first).__name__}"
+        )
+        return None
+
+    logger.info(f"Resolved Patreon vanity={vanity} → campaign_id={campaign_id}")
+    return campaign_id
@@ -0,0 +1,86 @@
+"""Unit tests for the Patreon campaign-ID resolver."""
+import aiohttp
+import pytest
+from aioresponses import aioresponses
+
+from app.services.patreon_resolver import resolve_campaign_id
+
+
+CAMPAIGNS_URL = "https://www.patreon.com/api/campaigns?filter%5Bvanity%5D=mstsu&fields%5Bcampaign%5D=name"
+
+
+async def test_happy_path_returns_campaign_id():
+    with aioresponses() as mock:
+        mock.get(
+            CAMPAIGNS_URL,
+            payload={"data": [{"id": "12345", "type": "campaign", "attributes": {"name": "MSTSU"}}]},
+        )
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result == "12345"
+
+
+async def test_empty_data_returns_none():
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, payload={"data": []})
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result is None
+
+
+async def test_missing_data_key_returns_none():
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, payload={"errors": [{"code": 1}]})
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result is None
+
+
+async def test_missing_id_field_returns_none():
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, payload={"data": [{"type": "campaign"}]})
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result is None
+
+
+async def test_http_401_returns_none():
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, status=401, body="Unauthorized")
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result is None
+
+
+async def test_network_error_returns_none():
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, exception=aiohttp.ClientConnectionError("boom"))
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result is None
+
+
+async def test_timeout_returns_none():
+    import asyncio
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, exception=asyncio.TimeoutError())
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result is None
+
+
+async def test_invalid_json_returns_none():
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, body="<html>not json</html>", content_type="text/html")
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result is None
+
+
+async def test_missing_cookies_path_proceeds_without_jar(tmp_path):
+    """When cookies_path is None, the request still goes out (cookies are optional)."""
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, payload={"data": [{"id": "99", "type": "campaign"}]})
+        result = await resolve_campaign_id("mstsu", cookies_path=None)
+    assert result == "99"
+
+
+async def test_nonexistent_cookies_path_proceeds_without_jar(tmp_path):
+    """When cookies_path points to a missing file, don't crash — just skip the jar."""
+    ghost = tmp_path / "does-not-exist.txt"
+    with aioresponses() as mock:
+        mock.get(CAMPAIGNS_URL, payload={"data": [{"id": "99"}]})
+        result = await resolve_campaign_id("mstsu", cookies_path=str(ghost))
+    assert result == "99"