peter
0cff964ff2
25 literal names covered 34 modules. plex/client.py, plex/stream.py, plex/subtitles.py, plex/sync.py and two Plex route modules all called themselves `siftlode.plex`; downloads/pipeline.py called itself `siftlode.worker`; routes/channels.py called itself `siftlode.api`. The `logger` column is in every stored row so E22.6's console can filter on it, and so an operator can pin a level to one part of the system — neither works when six modules share a name. `logs.get_logger(__name__)` derives it: app/plex/sync.py -> siftlode.plex.sync. One name per module, and it cannot drift from the file it sits in. tests/test_logger_names.py pins the derivation, that everything stays under the one `siftlode` tree the handler and the tests attach to, and that no module hand-rolls a name again unless the line says why (`# logger-name-ok: <why>`). Two do: get_logger's own call, and `siftlode.http`, which is named for the traffic it carries rather than the module it lives in — it replaced uvicorn's access log and is what an operator pins when they want request lines and nothing else. app/scheduler.py called its logger `logger`; every other module calls it `log`. ruff gains LOG, G, T20, TRY400, TRY401 and S112. Four findings cleared with them: worker.py logged `str(exc)[:120]` where the traceback was the whole question, and three prints/f-strings that are deliberate now say so on the line. S110 and BLE001 stay off until S3 — 23 handlers are outstanding and each is a judgement about one of them; enabling the rules first would just mean 23 blanket noqas.
171 lines
6.6 KiB
Python
171 lines
6.6 KiB
Python
"""Import the authenticated user's YouTube subscriptions and channel metadata."""
|
|
|
|
from datetime import datetime, timezone
|
|
|
|
from sqlalchemy import select
|
|
from sqlalchemy.orm import Session
|
|
|
|
from app import logs
|
|
from app.models import Channel, Subscription, User
|
|
from app.utils import normalize_description
|
|
from app.youtube.client import YouTubeClient, best_thumbnail
|
|
|
|
log = logs.get_logger(__name__)
|
|
|
|
|
|
def _to_int(value) -> int | None:
|
|
try:
|
|
return int(value) if value is not None else None
|
|
except (TypeError, ValueError):
|
|
return None
|
|
|
|
|
|
def _parse_dt(value: str | None) -> datetime | None:
|
|
if not value:
|
|
return None
|
|
try:
|
|
return datetime.fromisoformat(value.replace("Z", "+00:00"))
|
|
except ValueError:
|
|
return None
|
|
|
|
|
|
def _external_links(branding: dict) -> list | None:
|
|
"""Channel "About" links. The API exposes a few in brandingSettings.channel.profileColor/
|
|
/... varies; the durable spot is brandingSettings.channel.links is gone post-2023, so we
|
|
read what's present (settings/links) defensively and keep [{title, url}] pairs."""
|
|
channel = branding.get("channel", {})
|
|
links = channel.get("links") or []
|
|
out = [
|
|
{"title": item.get("title"), "url": item.get("url")}
|
|
for item in links
|
|
if isinstance(item, dict) and item.get("url")
|
|
]
|
|
return out or None
|
|
|
|
|
|
def apply_channel_details(db: Session, items: list[dict]) -> None:
|
|
now = datetime.now(timezone.utc)
|
|
for item in items:
|
|
channel = db.get(Channel, item["id"])
|
|
if channel is None:
|
|
continue
|
|
snippet = item.get("snippet", {})
|
|
content = item.get("contentDetails", {})
|
|
stats = item.get("statistics", {})
|
|
topics = item.get("topicDetails", {})
|
|
branding = item.get("brandingSettings", {})
|
|
|
|
channel.title = snippet.get("title") or channel.title
|
|
channel.handle = snippet.get("customUrl")
|
|
channel.description = normalize_description(snippet.get("description"))
|
|
channel.thumbnail_url = best_thumbnail(snippet.get("thumbnails")) or channel.thumbnail_url
|
|
channel.default_language = snippet.get("defaultLanguage")
|
|
channel.country = snippet.get("country")
|
|
channel.uploads_playlist_id = content.get("relatedPlaylists", {}).get("uploads")
|
|
channel.subscriber_count = _to_int(stats.get("subscriberCount"))
|
|
channel.video_count = _to_int(stats.get("videoCount"))
|
|
channel.total_view_count = _to_int(stats.get("viewCount"))
|
|
channel.published_at = _parse_dt(snippet.get("publishedAt"))
|
|
channel.banner_url = branding.get("image", {}).get("bannerExternalUrl")
|
|
channel.external_links = _external_links(branding)
|
|
channel.topic_categories = topics.get("topicCategories")
|
|
channel.keywords = (branding.get("channel") or {}).get("keywords")
|
|
channel.details_synced_at = now
|
|
|
|
|
|
def should_prune(fetched_count: int, existing_count: int) -> bool:
|
|
"""Whether an import may delete the local subscriptions missing from this fetch.
|
|
|
|
NEVER on an empty fetch that contradicts local state: the API can answer 200 with no items (a
|
|
transient blip, a scope/token edge), and pruning against that wipes every subscription the user
|
|
has — taking each row's `deep_requested` flag with it — in a single run. Someone who genuinely
|
|
unsubscribed from everything simply keeps their rows until a sync that returns something.
|
|
|
|
Pure so it can be tested without a database; `import_subscriptions` is the only caller."""
|
|
return fetched_count > 0 or existing_count == 0
|
|
|
|
|
|
def import_subscriptions(db: Session, user: User) -> dict:
|
|
"""Pull all subscriptions for `user`, upsert channels + subscription links, prune
|
|
channels the user has unsubscribed from on YouTube, and fetch channel details for
|
|
any channel we don't have details for yet."""
|
|
fetched: dict[str, dict] = {}
|
|
new_channels = 0
|
|
|
|
with YouTubeClient(db, user) as yt:
|
|
for sub in yt.iter_subscriptions():
|
|
cid = sub.get("channel_id")
|
|
if cid:
|
|
fetched[cid] = sub
|
|
|
|
for cid, sub in fetched.items():
|
|
channel = db.get(Channel, cid)
|
|
if channel is None:
|
|
channel = Channel(
|
|
id=cid,
|
|
title=sub.get("title"),
|
|
description=normalize_description(sub.get("description")),
|
|
thumbnail_url=sub.get("thumbnail_url"),
|
|
)
|
|
db.add(channel)
|
|
new_channels += 1
|
|
sub_row = db.execute(
|
|
select(Subscription).where(
|
|
Subscription.user_id == user.id, Subscription.channel_id == cid
|
|
)
|
|
).scalar_one_or_none()
|
|
if sub_row is None:
|
|
sub_row = Subscription(user_id=user.id, channel_id=cid)
|
|
db.add(sub_row)
|
|
sub_row.yt_subscription_id = sub.get("yt_subscription_id")
|
|
db.flush()
|
|
|
|
# Prune subscriptions removed on YouTube — but only when this fetch is trustworthy
|
|
# (see `should_prune`).
|
|
removed = 0
|
|
existing = (
|
|
db.execute(select(Subscription).where(Subscription.user_id == user.id)).scalars().all()
|
|
)
|
|
prune_skipped = not should_prune(len(fetched), len(existing))
|
|
if prune_skipped:
|
|
log.warning(
|
|
"Subscription import (user %s): YouTube returned 0 subscriptions while %d exist "
|
|
"locally — skipping the prune (treating it as a transient empty response)",
|
|
user.id,
|
|
len(existing),
|
|
)
|
|
else:
|
|
for sub_row in existing:
|
|
if sub_row.channel_id not in fetched:
|
|
db.delete(sub_row)
|
|
removed += 1
|
|
db.commit()
|
|
|
|
# Fetch details for channels that don't have them yet.
|
|
need_details = (
|
|
db.execute(
|
|
select(Channel).where(
|
|
Channel.id.in_(fetched.keys()),
|
|
Channel.details_synced_at.is_(None),
|
|
)
|
|
)
|
|
.scalars()
|
|
.all()
|
|
)
|
|
detailed = 0
|
|
if need_details:
|
|
items = yt.get_channels([c.id for c in need_details])
|
|
apply_channel_details(db, items)
|
|
detailed = len(items)
|
|
db.commit()
|
|
|
|
result = {
|
|
"subscriptions": len(fetched),
|
|
"channels_new": new_channels,
|
|
"channels_detailed": detailed,
|
|
"removed_stale": removed,
|
|
"prune_skipped": prune_skipped,
|
|
}
|
|
log.info("Subscription import (user %s): %s", user.id, result)
|
|
return result
|