refactor(platforms): promote services/platforms.py → services/platforms/ package with per-platform quirk colocation

Operator-requested 2026-05-27: centralize the per-platform quirks that had been accumulating across credential_service, sidecar, and platforms into a single per-platform module so adding/updating quirks becomes "edit one file." **Layout** services/platforms/ base.py PlatformInfo dataclass + module-default key chains + shared helpers (str_id_value, str_field) __init__.py PLATFORMS dict + public API (auth_type_for, known_platform_keys, to_dict, external_post_id_keys_for, description_keys_for) patreon.py metadata only — the reference platform, no quirks subscribestar.py metadata + augment_cookies (18+ agreement) + derive_post_url (synthetic /posts/<post_id>) hentaifoundry.py metadata + augment_cookies (host-only PHPSESSID duplicate) + derive_post_url (/pictures/user/...) pixiv.py metadata + derive_post_url (/artworks/<id>) discord.py metadata + derive_post_url (channels/<server>/<channel>/<message>) deviantart.py metadata only — un-audited; quirks to be added when an operator first exercises DA **PlatformInfo extensions** Existing fields preserved. Four new optional fields: external_post_id_keys: tuple[str, ...] | None Override the sidecar external_post_id lookup chain. None falls back to DEFAULT_EXTERNAL_POST_ID_KEYS in base.py ("post_id", "id", "index", "message_id") — covers every current platform. description_keys: tuple[str, ...] | None Override the description body lookup chain. None falls back to DEFAULT_DESCRIPTION_KEYS ("content", "description", "caption", "message") — Discord's "message" body field is covered by the default's trailing entry. derive_post_url: Callable[[dict], str | None] | None Synthesize the post permalink from sidecar metadata. None = trust the bare `url` / `post_url` field (patreon, deviantart). subscribestar/pixiv/hf/discord override this because their `url` is the file CDN URL. augment_cookies: Callable[[str], str] | None Post-process the materialized cookies.txt before gallery-dl consumes it. None = no-op. Used by subscribestar (age cookie) and hentaifoundry (host-only PHPSESSID duplicate). **Consumer changes** - credential_service._augment_cookies(platform, netscape) shrunk from a per-platform-conditional dispatcher (~80 lines of inlined helpers) to a 5-line lookup: `info.augment_cookies(netscape) if info and info.augment_cookies else netscape`. The platform-specific helper bodies moved verbatim into the per-platform modules. - sidecar.parse_sidecar similarly delegates: external_post_id chain via external_post_id_keys_for(category), description chain via description_keys_for(category), post_url via PLATFORMS[category].derive_post_url. The _DERIVED_URL_PLATFORMS set and inline _derive_post_url body both gone. Added a shared `_first_id` helper for bool-safe id coercion. **Public API preserved** PLATFORMS, PlatformInfo, auth_type_for, known_platform_keys, to_dict are all re-exported from the package's __init__.py. test_platforms_registry test_credential_service, and test_sidecar_util pass without changes because the behavior is identical; only the implementation moved. **Adding a new platform** 1. Create services/platforms/<name>.py with `INFO = PlatformInfo(...)` and any of the four optional hooks. 2. Import it in services/platforms/__init__.py + add to the PLATFORMS tuple-comprehension. 3. Done. sidecar parsing, cookie materialization, /api/platforms all pick it up automatically.
2026-05-27 19:46:05 -04:00
parent 2394e47370
commit abafc3265e
11 changed files with 512 additions and 305 deletions
@@ -165,99 +165,16 @@ class CredentialService:


 def _augment_cookies(platform: str, netscape: str) -> str:
-    """Inject platform-specific synthetic cookies needed to bypass server
-    gates or extractor quirks.
-
-    subscribestar.adult: the server gates artist pages behind the
-    `_personalization_id` age-confirmation cookie. The site's frontend JS
-    uses localStorage to suppress the age popup once dismissed, so after
-    the cookie's annual expiry the user can't easily get a fresh one —
-    visiting the site in a logged-in session doesn't re-show the popup
-    and doesn't re-issue the cookie. gallery-dl's own login flow (which
-    FC doesn't use; we capture cookies via the extension instead)
-    sidesteps this by manually setting `18_plus_agreement_generic=true`
-    on `.subscribestar.adult` — the server accepts that as the
-    age-confirmation marker.
-
-    hentaifoundry: gallery-dl's extractor uses
-    `self.cookies.get("PHPSESSID", domain="www.hentai-foundry.com")` to
-    decide whether the user is logged in. `requests` does EXACT domain
-    matching on .get(); the extension rewrites every captured cookie to
-    a leading-dot subdomain-wide form (`.hentai-foundry.com`), which
-    fails that exact match. The fallback path hits a HEAD
-    `?enterAgree=1` that 401s. Emit host-only duplicates of PHPSESSID +
-    YII_CSRF_TOKEN on `www.hentai-foundry.com` so the lookup succeeds.
-    (The original `.hentai-foundry.com` entries stay — the actual HTTP
-    requests use RFC 6265 subdomain matching, which works either way.)
-
-    All injections are idempotent (no-op if the target cookie is already
-    present) and platform-scoped.
-
-    Operator-flagged 2026-05-27: subscribestar age-confirmation, then
-    hentaifoundry 401 on /?enterAgree=1.
-    """
-    if platform == "subscribestar":
-        return _augment_subscribestar(netscape)
-    if platform == "hentaifoundry":
-        return _augment_hentaifoundry(netscape)
-    return netscape
-
-
-def _augment_subscribestar(netscape: str) -> str:
-    if "18_plus_agreement_generic" in netscape:
+    """Delegate to the platform's `augment_cookies` hook if one is
+    registered (subscribestar, hentaifoundry, etc. — see
+    `services/platforms/<name>.py`). No-op when the platform doesn't
+    register a hook (Patreon, DeviantArt). Centralizing the
+    quirks-per-platform in the platforms package means adding a new
+    platform's cookie quirks doesn't require touching this file."""
+    info = PLATFORMS.get(platform)
+    if info is None or info.augment_cookies is None:
        return netscape
-    # Far-future expiry — gallery-dl's own login flow sets this with no
-    # explicit expiry; the server only checks presence/value.
-    expiry = 4102444800  # 2100-01-01 UTC, opaque "far future"
-    line = "\t".join([
-        ".subscribestar.adult", "TRUE", "/", "TRUE",
-        str(expiry), "18_plus_agreement_generic", "true",
-    ])
-    body = netscape.rstrip("\n")
-    if not body:
-        body = "# Netscape HTTP Cookie File"
-    return body + "\n" + line + "\n"
-
-
-_HF_HOST_ONLY_NAMES = ("PHPSESSID", "YII_CSRF_TOKEN")
-
-
-def _augment_hentaifoundry(netscape: str) -> str:
-    body = netscape.rstrip("\n")
-    if not body:
-        return netscape
-    lines = body.split("\n")
-    existing_host_only = set()
-    by_name: dict[str, list[str]] = {}
-    for raw in lines:
-        if not raw or raw.startswith("#"):
-            continue
-        parts = raw.split("\t")
-        if len(parts) < 7:
-            continue
-        domain, _flag, _path, _secure, _exp, name, _value = parts[:7]
-        if name not in _HF_HOST_ONLY_NAMES:
-            continue
-        if domain == "www.hentai-foundry.com":
-            existing_host_only.add(name)
-        elif domain in (".hentai-foundry.com", "hentai-foundry.com"):
-            by_name.setdefault(name, []).append(raw)
-
-    appended = []
-    for name in _HF_HOST_ONLY_NAMES:
-        if name in existing_host_only or name not in by_name:
-            continue
-        # Duplicate the FIRST subdomain-wide line as host-only on
-        # www.hentai-foundry.com. Same value + expiry; flag=FALSE marks
-        # it host-only in netscape format.
-        parts = by_name[name][0].split("\t")
-        parts[0] = "www.hentai-foundry.com"
-        parts[1] = "FALSE"
-        appended.append("\t".join(parts[:7]))
-
-    if not appended:
-        return netscape
-    return body + "\n" + "\n".join(appended) + "\n"
+    return info.augment_cookies(netscape)


 def _to_netscape(plaintext: str) -> str: