feat(patreon): capture full post body via adaptive detail-fetch
CI / lint (push) Successful in 4s
CI / frontend-build (push) Successful in 21s
CI / backend-lint-and-test (push) Successful in 38s
CI / integration (push) Successful in 3m24s

The feed endpoint (/api/posts) returns `content` empty for many posts, so post
bodies — their formatting, inline <img>, and external <a href> links — were
never captured (the post showed "(no description)"). Enrich an empty feed body
from the per-post detail endpoint (/api/posts/{id}) before writing the importer
sidecar, memoized by mutating the shared post dict so a multi-image post fetches
detail exactly once and fully-seen posts (no fresh download) pay nothing.
Best-effort by design: a body we can't fetch returns None and never fails the
walk. No-doubling and no-clobber-of-populated-body already hold (post upsert is
keyed on external_post_id; an empty body parses to None and isn't applied).

First slice of milestone #64 (rich post capture + faithful rendering +
external-host downloads). Refs FC #830.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-14 12:29:06 -04:00
parent 7fcef53d5b
commit 2c67c27044
5 changed files with 161 additions and 1 deletions
+54
View File
@@ -9,6 +9,7 @@ import json
from pathlib import Path
import pytest
import requests
from backend.app.services import patreon_client as pc_mod
from backend.app.services.patreon_client import (
@@ -352,3 +353,56 @@ def test_request_sleep_paces_before_fetch(monkeypatch):
monkeypatch.setattr(pc_mod.time, "sleep", lambda s: slept.append(s))
client._fetch("5555", None)
assert slept == [1.5]
# -- fetch_post_detail_content (best-effort full-body enrichment) ----------
def test_fetch_post_detail_content_returns_body(monkeypatch):
payload = {"data": {"id": "42", "attributes": {"content": "<p>full body</p>"}}}
captured: dict = {}
client = PatreonClient(cookies_path=None)
def _get(url, params=None, timeout=None):
captured["url"] = url
captured["params"] = params
return _FakeResp(200, json_data=payload)
monkeypatch.setattr(client._session, "get", _get)
assert client.fetch_post_detail_content("42") == "<p>full body</p>"
assert captured["url"].endswith("/api/posts/42")
assert captured["params"]["fields[post]"] == "content"
def test_fetch_post_detail_content_empty_body_is_none(monkeypatch):
payload = {"data": {"attributes": {"content": " "}}}
client = _client_returning(monkeypatch, _FakeResp(200, json_data=payload))
assert client.fetch_post_detail_content("42") is None
def test_fetch_post_detail_content_blank_id_skips_request(monkeypatch):
calls: list = []
client = PatreonClient(cookies_path=None)
monkeypatch.setattr(
client._session, "get",
lambda *a, **k: calls.append(1) or _FakeResp(200, json_data={}),
)
assert client.fetch_post_detail_content("") is None
assert calls == []
def test_fetch_post_detail_content_swallows_http_and_transport_errors(monkeypatch):
# Non-200 → None (best-effort; a missing body must never fail the walk).
client = _client_returning(monkeypatch, _FakeResp(500))
assert client.fetch_post_detail_content("42") is None
# Non-JSON body (HTML challenge) → None, not a raise.
client = _client_returning(monkeypatch, _FakeResp(200, raise_json=True))
assert client.fetch_post_detail_content("42") is None
# Transport error → None.
client = PatreonClient(cookies_path=None)
def _boom(*a, **k):
raise requests.ConnectionError("boom")
monkeypatch.setattr(client._session, "get", _boom)
assert client.fetch_post_detail_content("42") is None