Files
youtube-automate/youtube_automate/runner.py
T
Tom FluxandClaude Opus 5 18bb2e420b Initial implementation of youtube-automate
A DVR for YouTube subscriptions, laid out so Jellyfin presents each channel
as a show and each video as an episode. Cron-driven, idempotent, with a
public admin UI for a non-operator.

Verified end to end on susan against three real channels: PO tokens, h264
downloads, Jellyfin resolution from local NFOs with all providers disabled,
retention and tombstones.

Corrections to the original design handover (specs.md documents each with
the evidence, and specs.handover-original.md preserves the original):

- The format sort selected 360p. Ranking acodec above res makes `bv*` prefer
  the combined 360p stream, which carries AAC, over the 720p video-only
  stream whose acodec is none. vcodec now leads, so a video without h264 at
  720p yields h264 lower down rather than VP9 this hardware cannot transcode.
- yt-dlp now requires a JS runtime and the yt-dlp-ejs solver scripts, which
  only ship with the [default] extra. Without them the n challenge fails and
  the mweb formats disappear entirely.
- --flat-playlist carries no upload dates, so the specced client-side date
  filter for backfill was impossible. Backfill is RSS-first.
- skipped_old was terminal, so raising a channel's retention appeared to do
  nothing. Added an explicit rescan.
- is_upcoming premieres now defer and retry instead of being skipped forever.
- TubeArchivist is gone, so the media root and the tube.jihakuz.xyz vhost
  were both reclaimed; the latter still pointed at its dead port.

240 offline tests, no network and no real yt-dlp invocation.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 21:42:48 +01:00

97 lines
3.0 KiB
Python

"""`run` orchestration: poll, then download, then reap — under a lock."""
from __future__ import annotations
import contextlib
import fcntl
import logging
import sqlite3
from pathlib import Path
from . import config, discovery, download, reap, util, videos
from .settings import Settings
log = logging.getLogger(__name__)
class AlreadyRunning(Exception):
pass
@contextlib.contextmanager
def exclusive_lock(path: Path | None = None):
"""Non-blocking flock. Raises AlreadyRunning if another run holds it.
The cron schedule is hourly and a large backfill can outlast that, so
overlapping runs are expected and must be a silent no-op rather than two
workers fighting over the same queue.
"""
path = path or config.LOCK_PATH
path.parent.mkdir(parents=True, exist_ok=True)
handle = path.open("w")
try:
try:
fcntl.flock(handle, fcntl.LOCK_EX | fcntl.LOCK_NB)
except OSError as exc:
raise AlreadyRunning(f"another run holds {path}") from exc
yield
finally:
with contextlib.suppress(OSError):
fcntl.flock(handle, fcntl.LOCK_UN)
handle.close()
def recover(conn: sqlite3.Connection) -> dict:
"""Undo the effects of a killed run before doing anything else."""
requeued = videos.recover_downloading(conn)
orphans = download.recover_orphans()
if requeued or orphans:
log.info(
"crash recovery: %d row(s) back to pending, %d orphan file(s) cleared",
requeued,
orphans,
)
return {"requeued": requeued, "orphans": orphans}
def run(
conn: sqlite3.Connection, settings: Settings, channel_pk: int | None = None
) -> dict:
"""One full cycle. Assumes the caller holds the lock."""
result = {"recovered": recover(conn)}
result["poll"] = discovery.poll_all(conn, settings, channel_pk)
try:
result["download"] = download.drain(conn, settings)
except RuntimeError as exc:
# The POT provider being down is loud and fatal for this run, but the
# poll results are still worth keeping.
log.error("%s", exc)
result["download"] = {"error": str(exc)}
return result
result["reap"] = reap.run(conn, settings)
settings.set("last_run_at", util.utcnow_iso())
return result
def summarise(result: dict) -> str:
poll = result.get("poll", {})
down = result.get("download", {})
reaped = result.get("reap", {})
parts = [
f"discovered={poll.get('queued', 0)}",
f"repaired={poll.get('repaired', 0)}",
f"poll_failures={poll.get('failed', 0)}",
f"downloaded={down.get(videos.DOWNLOADED, 0)}",
f"failed={down.get(videos.FAILED, 0)}",
f"skipped={down.get(videos.SKIPPED_SHORT, 0) + down.get(videos.SKIPPED_LIVE, 0)}",
f"deferred={down.get(videos.DEFERRED, 0)}",
f"reaped={reaped.get('deleted', 0)}",
f"evicted={reaped.get('evicted', 0)}",
]
if "error" in down:
parts.append(f"ERROR={down['error']}")
return " ".join(parts)