feat(reader): a Google Takeout export becomes watch state and Watch later

The YouTube API reads neither a user's watch history nor their Watch later list, so the Takeout
export is the only way in. `POST /api/takeout` takes one file of it (watch-history.json or
Watch later-videos.csv, told apart by content), keeps its videos in `takeout_items` and queues the
user's `takeout_import` run, whose outcome reaches their inbox.

The run marks watched the known videos the Shorts probe has cleared, at the Takeout time; a Short
is not marked, and a state the user set here (watched, hidden, or changed after that time) wins, by
the upsert's own condition. A video the catalog does not know yet waits with no outcome. Watch later
videos are fetched if unknown and appended oldest first.

An ad-hoc run can now ask for a completion notice (`run_ad_hoc(..., notify=True)`).
This commit is contained in:
2026-10-23 17:04:54 +02:00
parent bf5ceec8a1
commit 7b8505af95
15 changed files with 978 additions and 29 deletions
+58 -5
View File
@@ -1,18 +1,25 @@
from datetime import date
from functools import partial
from fastapi import APIRouter, Depends, Query
from fastapi import APIRouter, Depends, Query, Request
from pydantic import BaseModel
from sqlalchemy.orm import Session
from sqlalchemy.orm.exc import StaleDataError
from app import quota
from app import quota, scheduler
from app.auth import current_user
from app.db import get_db
from app.db import get_db, release_read_connection
from app.mailtext import lang_for_user
from app.feedquery import BadCursor, facet_counts, feed_count, feed_page, feed_summary, feed_years
from app.models import User
from app.reader import queries, service
from app.routes._common import ProgressIn, kept_position, not_found, youtube_refusal
from app.reader import queries, service, takeout
from app.routes._common import (
ProgressIn,
capped_body,
kept_position,
not_found,
youtube_refusal,
)
from app.sync.videos import parse_iso8601_duration
from app.utils import iso
from app.youtube.client import YouTubeClient, YouTubeError
@@ -293,3 +300,49 @@ def get_video_detail(
items[0].get("contentDetails", {}).get("duration")
),
}
# --- Google Takeout ------------------------------------------------------------------------------
async def _takeout_body(request: Request, db: Session = Depends(get_db)) -> bytes:
# The sign-in check has run, and it was a SELECT: hand the connection back before a file of
# megabytes arrives, so a slow upload does not hold one `idle in transaction`.
release_read_connection(db)
return await capped_body(request, takeout.MAX_BYTES)
@router.post("/takeout")
def upload_takeout(
# The sign-in check FIRST: dependencies resolve in order, so a stranger's file is refused before
# a byte of it is read.
user: User = Depends(current_user),
body: bytes = Depends(_takeout_body),
db: Session = Depends(get_db),
):
"""One file of the user's Google Takeout export — the watch history or the Watch later list.
Its videos are kept and the import runs in the background; its outcome reaches the user's inbox."""
try:
parsed = takeout.parse(body)
except takeout.TakeoutError as exc:
if exc.reason == "no_videos":
raise refused(422, "takeout_no_videos") from None
raise refused(422, "takeout_unreadable") from None
service.stage_takeout(db, user, parsed.kind, parsed.videos)
db.commit()
scheduler.run_ad_hoc(
scheduler.TAKEOUT_IMPORT,
partial(takeout.run_import, user.id),
actor_id=user.id,
target=f"user:{user.id}",
notify=True,
)
return {
"ok": True,
"kind": parsed.kind,
"videos": len(parsed.videos),
"entries": parsed.entries,
"ads": parsed.ads,
"other": parsed.other,
"malformed": parsed.malformed,
}