Files
FabledCurator/backend/app/services/platforms/base.py
T

106 lines
3.8 KiB
Python

"""PlatformInfo dataclass + shared defaults + small helpers.
Per-platform modules import from here, register their PlatformInfo via
INFO, optionally attaching `derive_post_url` and/or `augment_cookies`
callables for behavior that diverges from gallery-dl's mainline shape
(Patreon).
Adding a new platform: drop a new module under `services/platforms/`,
declare an INFO, and add it to the import list in
`services/platforms/__init__.py`. Sidecar parsing, cookie
materialization, and the /api/platforms response pick it up
automatically.
"""
from collections.abc import Callable
from dataclasses import dataclass
from typing import Literal
# Sidecar parsing defaults. Per-platform PlatformInfo entries can
# override these by setting `external_post_id_keys=` /
# `description_keys=`. Most don't need to — the defaults already cover
# every platform FC supports.
#
# external_post_id chain: `post_id` MUST come before `id` because
# SubscribeStar gallery-dl puts the per-attachment id in `id` and the
# actual post id in `post_id`; picking `id` first fragments
# multi-image SubscribeStar posts into N Post rows. Patreon/Pixiv have
# no `post_id` so `id` still wins for them; HF uses `index`, Discord
# uses `message_id` — all reached via the remaining chain entries.
# (Banked 2026-05-27 during the sidecar audit.)
DEFAULT_EXTERNAL_POST_ID_KEYS: tuple[str, ...] = (
"post_id", "id", "index", "message_id",
)
# Description body chain: Discord's gallery-dl extractor uses `message`
# (no `content`); appended to the chain so Discord posts surface body
# text.
DEFAULT_DESCRIPTION_KEYS: tuple[str, ...] = (
"content", "description", "caption", "message",
)
@dataclass(frozen=True)
class PlatformInfo:
# --- Identity / metadata ---
key: str
name: str
description: str
auth_type: Literal["cookies", "token"]
requires_auth: bool
url_pattern: str
url_examples: list[str]
default_config: dict
notes: str | None = None
# --- Sidecar parsing overrides ---
# Each is None to mean "use the module default above"; a platform
# only sets one of these when its sidecar shape genuinely differs.
external_post_id_keys: tuple[str, ...] | None = None
description_keys: tuple[str, ...] | None = None
# --- Behavioral hooks ---
# Synthesize a post permalink from sidecar data. Required when
# gallery-dl's `url` field is the file/CDN URL rather than the post
# permalink (subscribestar/pixiv/hf/discord). None = trust the bare
# `url` field (patreon, deviantart).
derive_post_url: Callable[[dict], str | None] | None = None
# Post-process the materialized cookies.txt for gallery-dl. Used by
# platforms whose server gates or extractor quirks need synthetic
# cookies the extension can't capture (subscribestar age cookie, HF
# host-only PHPSESSID duplicate). None = no-op.
augment_cookies: Callable[[str], str] | None = None
def str_id_value(v) -> str | None:
"""Coerce a JSON scalar id into a non-empty string, rejecting bool
(Python's bool is an int subclass so `isinstance(True, int)` is
True; without this guard a sidecar with `"id": true` would produce
external_post_id="True")."""
if isinstance(v, bool):
return None
if isinstance(v, (str, int)) and str(v).strip():
return str(v).strip()
return None
def str_field(v) -> str | None:
"""Same idea as str_id_value but for plain string fields (no int
coercion)."""
if isinstance(v, str) and v.strip():
return v.strip()
return None
# Shared gallery-dl invocation defaults. Embedded in each platform's
# default_config (with platform-specific overrides) so per-platform
# choices stay explicit.
GD_DEFAULTS = {
"sleep": 3.0,
"sleep_request": 1.5,
"skip_existing": True,
"save_metadata": True,
"timeout": 3600,
}