Compare commits
16 Commits
f546c9fbb7
...
v2
| Author | SHA1 | Date | |
|---|---|---|---|
| 18537b9de9 | |||
| 1757318523 | |||
| 90b9dad59c | |||
| 309ce87abb | |||
| 4abd39f884 | |||
| 266ed86217 | |||
| 0aa9950e18 | |||
| 043c8b4df3 | |||
| 5210d2c032 | |||
| 8b21034d78 | |||
| 2a5648506e | |||
| 7926534e54 | |||
| 0ed16eca62 | |||
| 35a2592dce | |||
| 5f78ac6a1a | |||
| 2beb54f219 |
12
.env.example
Normal file
12
.env.example
Normal file
@@ -0,0 +1,12 @@
|
||||
YOUDIS_ENABLE_BACKEND=1
|
||||
YOUDIS_BACKEND_HOST=127.0.0.1
|
||||
YOUDIS_BACKEND_PORT=8000
|
||||
YOUDIS_BACKEND_HEALTH_TIMEOUT=20
|
||||
YOUDIS_BACKEND_HEALTH_INTERVAL=0.5
|
||||
YOUDIS_POLL_INTERVAL_SECONDS=2
|
||||
YOUDIS_YTDLP_EXECUTABLE=yt-dlp
|
||||
YOUDIS_CONFIG_DIR=/home/user/proj/youdis/test/
|
||||
YOUDIS_DOWNLOAD_DIR=/home/user/proj/youdis/downloads
|
||||
ENABLE_DISCORD=1
|
||||
DISCORD_BOT_TOKEN=
|
||||
DISCORD_BOT_SCOPE=2147491904
|
||||
2
.gitignore
vendored
2
.gitignore
vendored
@@ -11,6 +11,7 @@ env/
|
||||
# --- environment files ---
|
||||
.env
|
||||
.env.*
|
||||
!.env.example
|
||||
*.local
|
||||
|
||||
# --- emacs ---
|
||||
@@ -23,6 +24,7 @@ env/
|
||||
/private/
|
||||
archive/
|
||||
downloads/
|
||||
test/
|
||||
data.json
|
||||
|
||||
# --- django ---
|
||||
|
||||
60
README.md
60
README.md
@@ -1,8 +1,60 @@
|
||||
# Running youdis
|
||||
|
||||
build and run the docker container
|
||||
```
|
||||
api_token = [discord bot token]
|
||||
-v [downloads]:/downloads
|
||||
-v [config]:/config
|
||||
-v [host_downloads]:/downloads
|
||||
-v [host_config]:/config
|
||||
-e ENABLE_DISCORD=1
|
||||
-e DISCORD_BOT_TOKEN=<token>
|
||||
-e DISCORD_BOT_SCOPE=<scope-int>
|
||||
```
|
||||
config contains data to persist across container updates, i.e., unraid appdata,
|
||||
such as users.json (authorized users) and yt-dlp's archive.txt
|
||||
such as yt-dlp's archive.txt
|
||||
|
||||
# Development
|
||||
|
||||
v2 architecture draft: `docs/architecture-v2.org`
|
||||
|
||||
The app runs with `youdis.py`.
|
||||
This starts the backend first, waits for health, then starts each enabled adapter explicitly.
|
||||
|
||||
Test components directly with uvicorn:
|
||||
```
|
||||
python3 -m uvicorn youdis.main:app --host 127.0.0.1 --port 8000
|
||||
python3 -m youdis.adapters.discord
|
||||
```
|
||||
|
||||
Key runner/config vars:
|
||||
```
|
||||
YOUDIS_ENABLE_BACKEND=1 #default enabled, dont disable unless testing
|
||||
YOUDIS_BACKEND_HOST=127.0.0.1
|
||||
YOUDIS_BACKEND_PORT=8000
|
||||
YOUDIS_BACKEND_HEALTH_TIMEOUT=20
|
||||
YOUDIS_BACKEND_HEALTH_INTERVAL=0.5
|
||||
YOUDIS_POLL_INTERVAL_SECONDS=2
|
||||
YOUDIS_YTDLP_EXECUTABLE=yt-dlp
|
||||
YOUDIS_CONFIG_DIR=/path/to/config/
|
||||
YOUDIS_DOWNLOAD_DIR=/path/to/downloads/
|
||||
ENABLE_DISCORD=1
|
||||
DISCORD_BOT_TOKEN=<token-string>
|
||||
DISCORD_BOT_SCOPE=123456789
|
||||
```
|
||||
|
||||
|
||||
## Add Adapter
|
||||
Configure adapter selection in .env, like so:
|
||||
```
|
||||
YOUDIS_RUN_BACKEND=1
|
||||
YOUDIS_BACKEND_HOST=127.0.0.1
|
||||
YOUDIS_BACKEND_PORT=8000
|
||||
ENABLE_DISCORD=1
|
||||
DISCORD_BOT_TOKEN=<api_key>
|
||||
DISCORD_BOT_SCOPE=123456789
|
||||
```
|
||||
|
||||
to add a new adapter:
|
||||
1. add `youdis/adapters/<adapter>.py`
|
||||
2. make it independently runnable
|
||||
3. add `start_<adapter>()` to `youdis.py`
|
||||
4. register it in the explicit adapter starter map in `youdis.py`
|
||||
5. add `ENABLE_<adapter>` and supporting env vars to `.env.example`
|
||||
|
||||
24
agents.md
Normal file
24
agents.md
Normal file
@@ -0,0 +1,24 @@
|
||||
# agent rules
|
||||
|
||||
## priorities
|
||||
- optimize for simplicity, boringness, and long-term maintainability
|
||||
- prefer minimal diffs; avoid refactors unless required for the active task
|
||||
|
||||
## tech stack
|
||||
- python
|
||||
- file storage: json and csv, no sqlite or databases
|
||||
- assume local virtual env is available and accessible
|
||||
- do not add new dependencies unless explicitly approved; if unavoidable, document justification in the active task notes
|
||||
|
||||
## workflow
|
||||
- work on ONE task at a time unless explicitly instructed otherwise
|
||||
- at the start of work, state the task id you are executing
|
||||
- do not start work unless a task id is specified; if missing, choose the earliest unchecked task and say so
|
||||
- propose incremental steps
|
||||
- always include basic tests for core logic
|
||||
- add assumptions and questions along-the-way to the ** notes section under the active task
|
||||
- when you complete a task:
|
||||
- mark it [X] in pm/tasks.org
|
||||
- fill in evidence with commit hash + commands run
|
||||
- never mark complete unless acceptance criteria are met
|
||||
- include date and time (HH:MM)
|
||||
@@ -1,11 +1,8 @@
|
||||
# yt-dlp config file (yt-dlp.conf or .config/yt-dlp/config)
|
||||
--simulate
|
||||
# yt-dlp config file
|
||||
-f "bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"
|
||||
--embed-chapters
|
||||
--embed-info-json
|
||||
--write-playlist-metafiles
|
||||
#--paths "{"home":"./downloads"}"
|
||||
--download-archive "/config/archive.txt"
|
||||
--restrict-filenames
|
||||
--output "/downloads/%(uploader)s/%(playlist_title)s/%(playlist_index)s%(playlist_index& - )s%(title)s.%(ext)s"
|
||||
# --split-chapters
|
||||
248
docs/architecture-v2.org
Normal file
248
docs/architecture-v2.org
Normal file
@@ -0,0 +1,248 @@
|
||||
#+TITLE: youdis v2 architecture
|
||||
#+DATE: [2026-03-31 Tue]
|
||||
#+VERSION: 3
|
||||
|
||||
* Purpose
|
||||
Youdis v2 splits the current monolithic Discord bot into:
|
||||
- a private backend worker service that owns yt-dlp execution
|
||||
- thin chat adapters that translate user actions into backend requests
|
||||
|
||||
The goal is to make downloader behavior inspectable, reusable, and easier to debug across multiple frontends without introducing queueing infrastructure or complex deployment.
|
||||
|
||||
** Goals
|
||||
- Keep the backend transport-agnostic.
|
||||
- Preserve archive-first duplicate prevention via `archive.txt`.
|
||||
- Keep single-job semantics explicit.
|
||||
- Treat requester and origin metadata as informational, not authorization.
|
||||
- Make yt-dlp configuration understandable and debuggable.
|
||||
|
||||
** Non-Goals
|
||||
- No backend auth or user membership logic.
|
||||
- No database, Redis, or external queue.
|
||||
- No multi-worker scheduling in v2.
|
||||
- No frontend-owned downloader logic.
|
||||
|
||||
* Proposed Components
|
||||
** Backend worker service
|
||||
Owns:
|
||||
- request validation
|
||||
- single active job state
|
||||
- yt-dlp executable invocation
|
||||
- yt-dlp configuration selection and runtime argument construction
|
||||
- archive behavior
|
||||
- output path behavior
|
||||
- progress and final result events
|
||||
|
||||
Does not own:
|
||||
- Discord slash-command parsing
|
||||
- chat formatting decisions
|
||||
- access control policy
|
||||
|
||||
** Frontend adapters
|
||||
1. Discord
|
||||
2. Zulip
|
||||
3. XMPP
|
||||
|
||||
Own:
|
||||
- command parsing
|
||||
- user-facing message formatting
|
||||
- transport-specific reply behavior
|
||||
- optional frontend-side gating if the deployment wants it
|
||||
|
||||
Do not own:
|
||||
- yt-dlp option construction
|
||||
- archive checks
|
||||
- output path logic
|
||||
- job lifecycle rules
|
||||
|
||||
* Initial Deployment Shape
|
||||
|
||||
V2 should start as a single private process boundary with two layers:
|
||||
1. backend service process
|
||||
2. one Discord adapter process
|
||||
|
||||
The backend is intended for private/local deployment. Trust comes from deployment topology and network placement, not backend auth.
|
||||
|
||||
** Execution model
|
||||
The backend is a thin FastAPI wrapper around the `yt-dlp` executable, not a deep Python integration, unless proven necessary.
|
||||
|
||||
Why this is the default:
|
||||
- keeps behavior closer to native `yt-dlp`
|
||||
- makes container debugging easier because commands can be reproduced manually
|
||||
- avoids reimplementing `yt-dlp` option parsing unless we truly need tighter integration
|
||||
|
||||
This means the backend is primarily responsible for:
|
||||
- deciding when `yt-dlp` may run
|
||||
- constructing a safe effective command
|
||||
- supervising the subprocess while it is active
|
||||
- translating process outcomes into a small API contract
|
||||
|
||||
** Backend Contract
|
||||
*** Request model
|
||||
Minimal fields:
|
||||
- `url`
|
||||
- `requester_id` optional
|
||||
- `requester_name` optional
|
||||
- `origin` optional
|
||||
- `requested_at` optional
|
||||
Only `url` affects downloader behavior in v2. The rest is passthrough metadata for logs and frontend context.
|
||||
|
||||
*** Result states
|
||||
The backend should keep its external state model deliberately small:
|
||||
- `accepted`
|
||||
- `busy`
|
||||
- `running`
|
||||
- `completed`
|
||||
- `failed`
|
||||
- `cancelled`
|
||||
|
||||
These states should be transport-agnostic, human-debuggable, and only distinct when a frontend would behave differently.
|
||||
|
||||
Internal phases and details may be richer, but they should usually be carried as metadata rather than promoted to top-level states.
|
||||
|
||||
Examples of detail fields that can travel alongside the small state model:
|
||||
- `phase=validating`
|
||||
- `phase=downloading`
|
||||
- `disposition=archive_hit`
|
||||
- `message=already in archive`
|
||||
- `result_path=/downloads/...`
|
||||
|
||||
This keeps the API simple while still leaving room for useful operator-facing detail.
|
||||
|
||||
*** Minimal endpoints
|
||||
The first backend seam should stay small:
|
||||
- `POST /jobs`
|
||||
- `GET /jobs/current`
|
||||
- `POST /jobs/current/cancel`
|
||||
- `GET /health`
|
||||
- `GET /version`
|
||||
|
||||
Polling is the default integration model for v2. Streaming or push delivery is deferred unless a real frontend need appears.
|
||||
|
||||
** Single-Job Semantics
|
||||
V2 explicitly supports one active job at a time.
|
||||
- If idle, the backend accepts a new job and marks it active.
|
||||
- If busy, the backend rejects the new request with a `busy` result.
|
||||
- Cancel is coarse and best-effort.
|
||||
- The backend clears active state when the job reaches `completed`, `failed`, or `cancelled`.
|
||||
|
||||
This is a feature, not a limitation, for the initial service.
|
||||
|
||||
* yt-dlp Configuration Ownership
|
||||
|
||||
This is the most important v2 cleanup.
|
||||
|
||||
The backend owns all yt-dlp invocation behavior. Frontends must not build `yt-dlp` commands or option dictionaries.
|
||||
|
||||
** Config split
|
||||
|
||||
Static settings belong in `default-yt-dlp.conf`:
|
||||
- archive path
|
||||
- output template
|
||||
- embedding and metadata preferences
|
||||
- stable format defaults
|
||||
- retry defaults
|
||||
|
||||
Runtime settings belong in backend code:
|
||||
- target URL
|
||||
- config-file path, if explicitly set at launch
|
||||
- request-scoped flags or overrides
|
||||
- subprocess lifecycle and cancellation behavior
|
||||
- any values that must vary per request
|
||||
|
||||
*** Merge rule
|
||||
The backend should invoke `yt-dlp` with the default config first, then apply a small set of explicit runtime overrides.
|
||||
|
||||
If a runtime override conflicts with file-backed config, the override wins and the backend should log the effective value used.
|
||||
|
||||
*** Debuggability requirement
|
||||
For each job, the backend should make it easy to inspect:
|
||||
|
||||
- config file path used
|
||||
- effective `yt-dlp` command or key override arguments
|
||||
- final normalized job result
|
||||
|
||||
This exists specifically because the current config behavior has been difficult to reason about.
|
||||
|
||||
*** Config hygiene expectations
|
||||
|
||||
The default config should be safe for real downloads in production-like use.
|
||||
|
||||
That means test-only settings such as `--simulate` should not remain enabled in the default runtime path unless the backend intentionally supports an explicit dry-run mode.
|
||||
|
||||
** Recommended Repo Shape
|
||||
One reasonable first cut:
|
||||
|
||||
#+begin_quote
|
||||
youdis/
|
||||
README.md
|
||||
default-yt-dlp.conf
|
||||
youdis/
|
||||
__init__.py
|
||||
main.py
|
||||
models.py
|
||||
adapters/
|
||||
__init__.py
|
||||
discord.py
|
||||
docs/
|
||||
architecture-v2.org
|
||||
#+end_quote
|
||||
|
||||
Notes:
|
||||
|
||||
- `main.py` owns the FastAPI app, active-job state, and `yt-dlp` subprocess lifecycle.
|
||||
- `models.py` owns request and response models.
|
||||
- `adapters/discord.py` becomes a thin client of the backend.
|
||||
|
||||
** Example response shape
|
||||
|
||||
One likely response shape for v1:
|
||||
|
||||
#+begin_src json
|
||||
{
|
||||
"state": "completed",
|
||||
"disposition": "archive_hit",
|
||||
"message": "already in archive",
|
||||
"job_id": "abc123"
|
||||
}
|
||||
#+end_src
|
||||
|
||||
And for an active job:
|
||||
|
||||
#+begin_src json
|
||||
{
|
||||
"state": "running",
|
||||
"phase": "downloading",
|
||||
"message": "downloading 3 of 9",
|
||||
"job_id": "abc123"
|
||||
}
|
||||
#+end_src
|
||||
|
||||
** Framework Recommendation
|
||||
|
||||
FastAPI is the current recommendation for the backend seam.
|
||||
|
||||
Why it fits:
|
||||
|
||||
- typed request and response models help define the contract cleanly
|
||||
- built-in docs make local inspection easier during early iterations
|
||||
- it stays small enough for this service if we keep the surface area disciplined
|
||||
|
||||
Why this is not a strong ideological choice:
|
||||
|
||||
- Flask would also work if we decide the type/model ergonomics are not worth it
|
||||
- the important decision is keeping the seam small, not choosing a fashionable framework
|
||||
|
||||
** Immediate Next Task
|
||||
|
||||
`2.0.1` should implement the backend skeleton with just enough real behavior to prove the seam:
|
||||
|
||||
- package/module layout
|
||||
- health and version endpoint
|
||||
- single active-job state holder
|
||||
- one submit-job path
|
||||
- one current-job status path
|
||||
- `yt-dlp` subprocess invocation using `default-yt-dlp.conf`
|
||||
- explicit runtime overrides for request URL and cancel behavior
|
||||
|
||||
The Discord adapter should remain unchanged until that backend skeleton can accept a job and report status coherently.
|
||||
@@ -1,17 +1,18 @@
|
||||
#+title: Task Log
|
||||
#+updated: [2026-03-18 Wed 14:19]
|
||||
#+updated: [2026-03-31 Tue 16:03]
|
||||
|
||||
Use the template below, which should be a top-level org-mode header.
|
||||
A sample task is below the template
|
||||
|
||||
* [ ] M.m.m: Task Title (estimate # commits)
|
||||
replace the old observed/canonical workflow with a review-first pipeline that groups normalized rows only during review/combine and links them to catalog items
|
||||
* [ ] M.m.m: Task Title (<estimated # of commits>)
|
||||
description of the task
|
||||
** pm notes: amplifying information
|
||||
|
||||
** Acceptance Criteria
|
||||
1. Criterion
|
||||
- expanded data
|
||||
2. Criterion
|
||||
|
||||
- pm note: amplifying information
|
||||
3f. Criterion added after initial task completion
|
||||
|
||||
** evidence
|
||||
- commit: abc123, bcd234
|
||||
@@ -20,3 +21,61 @@ replace the old observed/canonical workflow with a review-first pipeline that gr
|
||||
|
||||
** notes
|
||||
- explanation of work done, decisions made, reasoning
|
||||
|
||||
|
||||
* [ ] 2.0.1: build backend yt-dlp worker (3)
|
||||
create the minimal backend/service skeleton and establish a working yt-dlp baseline with clean hooks for future frontends
|
||||
** pm notes
|
||||
- foundation; don't need the full finished service here, just the basic shape plus enough real yt-dlp execution to validate the seam and build on it.
|
||||
- keep single-job semantics
|
||||
- prioritize inspectable behavior over polish
|
||||
|
||||
** Acceptance Criteria
|
||||
1. create the backend/service skeleton
|
||||
- app/module layout exists
|
||||
- core request path is stubbed or minimally working
|
||||
2. establish a working yt-dlp baseline
|
||||
- archive behavior is preserved
|
||||
- output path behavior is preserved or intentionally updated
|
||||
- use yt-dlp .conf and set reasonable default
|
||||
3. expose basic hooks/interfaces for future frontends
|
||||
- submit/request path exists
|
||||
- status/progress hook exists
|
||||
- basic health/version visibility exists
|
||||
4f. print env vars to stdout on fastapi launch
|
||||
- repo_root
|
||||
- default_config
|
||||
- ytdlp_executable
|
||||
5f. create ytdlp conf to facilitate tests
|
||||
** evidence
|
||||
- commit:
|
||||
- tests:
|
||||
1. `python3 -m py_compile ./youdis/main.py ./youdis/models.py ./youdis/adapters/__init__.py ./youdis/adapters/discord.py`
|
||||
2. `python3 -m uvicorn youdis.main:app --host 127.0.0.1 --port 8000`
|
||||
3. `sudo curl -L https://github.com/yt-dlp/yt-dlp/releases/download/2026.03.17/yt-dlp -o /usr/local/bin/yt-dlp`
|
||||
4. `sudo chmod +x /usr/local/bin/yt-dlp`
|
||||
5. `yt-dlp --version`
|
||||
6. `curl http://127.0.0.1:8000/health`
|
||||
7. `curl http://127.0.0.1:8000/version`
|
||||
8. `curl -X POST http://127.0.0.1:8000/jobs -H 'content-type: application/json' -d '{"url":"https://www.youtube.com/watch?v=dQw4w9WgXcQ"}'`
|
||||
9. `curl http://127.0.0.1:8000/jobs/current`
|
||||
10. if testing in container: `docker build -t youdis:v2 .`
|
||||
11. if testing in container: `docker run --rm -p 8000:8000 -v [config]:/config -v [downloads]:/downloads youdis:v2`
|
||||
:OUTPUT_STEP1-9:
|
||||
user@paladin:~/proj/youdis$ curl http://127.0.0.1:8000/health
|
||||
{"status":"ok"}user@paladin:~/proj/youdis$
|
||||
user@paladin:~/proj/youdis$ curl http://127.0.0.1:8000/version
|
||||
{"version":"20250829-ec72c56","active_job":false}user@paladin:~/proj/youdis$
|
||||
user@paladin:~/proj/youdis$ curl -X POST http://127.0.0.1:8000/jobs -H 'content-type: application/json' -d '{"url":"https://www.youtube.com/watch?v=3i72yY_LaW4"}'
|
||||
{"job_id":"cc85165e-d906-4eee-864f-1a398b6de2e0","state":"accepted","url":"https://www.youtube.com/watch?v=3i72yY_LaW4","message":"accepted","phase":"queued","disposition":null,"requester_id":null,"requester_name":null,"origin":null,"result_path":null,"command":[],"returncode":null,"created_at":"2026-04-01T00:44:35.657196","updated_at":"2026-04-01T00:44:35.657198"}user@paladin:~/proj/youdis$ curl http://127.0.0.1:8000/jobs/current
|
||||
{"active":false,"job":{"job_id":"cc85165e-d906-4eee-864f-1a398b6de2e0","state":"failed","url":"https://www.youtube.com/watch?v=3i72yY_LaW4","message":"ERROR: unable to create directory [Errno 13] Permission denied: '/downloads'","phase":null,"disposition":null,"requester_id":null,"requester_name":null,"origin":null,"result_path":null,"command":["yt-dlp","--config-locations","/home/user/proj/youdis/default-yt-dlp.conf","https://www.youtube.com/watch?v=3i72yY_LaW4"],"returncode":1,"created_at":"2026-04-01T00:44:35.657196","updated_at":"2026-03-31T20:44:36.653353"}}user@paladin:~/proj/youdis$
|
||||
:END:
|
||||
- datetime: [2026-03-31 Tue 20:45]
|
||||
|
||||
** notes
|
||||
- validate `yt-dlp` subprocess invocation in-container; not verifiable in the current shell because `yt-dlp` is not installed here
|
||||
- confirm `--config-locations` behavior against the installed `yt-dlp` version during integration testing
|
||||
- current backend scaffold is not yet wired into `dockerfile` or `run-youdis.sh`
|
||||
- archive-hit and result-path parsing currently depend on `yt-dlp` stdout text patterns, so treat them as provisional until integration-tested
|
||||
|
||||
|
||||
|
||||
349
pm/tasks-v2.org
Normal file
349
pm/tasks-v2.org
Normal file
@@ -0,0 +1,349 @@
|
||||
#+title: Task Log
|
||||
#+updated: [2026-03-31 Tue 16:03]
|
||||
#+startup: overview
|
||||
# Local Variables:
|
||||
# org-babel-python-command: "/home/user/proj/youdis/.venv/bin/python"
|
||||
# project-dir: "~/proj/youdis"
|
||||
# End:
|
||||
|
||||
* youdis v2 goals:
|
||||
1. Separate backend from frontend
|
||||
2. Offload auth
|
||||
3. Ensure auto nightly builds
|
||||
4. Default output format supports plex browsing youtube channels as "tv shows"
|
||||
5. Facilitate multiple GUI inbounds: Discord, Zulip, XMPP
|
||||
|
||||
* [X] 2.0.0: define architecture (2-4)
|
||||
define the target architecture for a private backend yt-dlp worker with thin chat frontends
|
||||
** pm notes:
|
||||
- keep this iterative. the point is to choose the shape and seam, not prematurely implement infra. likely decisions include backend framework, request/status model, and how thin the discord shim should be.
|
||||
- goal is simple, private, maintainable deployment
|
||||
- avoid auth, queues, or persistence beyond clear & immediate needs
|
||||
|
||||
** Acceptance Criteria
|
||||
1. document the target architecture at a high level
|
||||
- backend owns yt-dlp execution and job state
|
||||
- frontends own chat-specific UX
|
||||
2. identify key decisions still open
|
||||
- backend choice
|
||||
- service seam/endpoints
|
||||
- status/progress model
|
||||
3. capture enough structure to begin implementation
|
||||
- repo/component layout is sketched
|
||||
- next implementation task is unblocked
|
||||
|
||||
** evidence
|
||||
- commit: 0ed16ec
|
||||
- tests: n/a
|
||||
- datetime: [2026-03-31 Tue 18:48]
|
||||
|
||||
** notes
|
||||
- first architecture draft captured in `docs/architecture-v2.org`
|
||||
|
||||
* [X] 2.0.1: build backend yt-dlp worker (3)
|
||||
create the minimal backend/service skeleton and establish a working yt-dlp baseline with clean hooks for future frontends
|
||||
** pm notes
|
||||
- foundation; don't need the full finished service here, just the basic shape plus enough real yt-dlp execution to validate the seam and build on it.
|
||||
- keep single-job semantics
|
||||
- prioritize inspectable behavior over polish
|
||||
|
||||
** Acceptance Criteria
|
||||
1. create the backend/service skeleton
|
||||
- app/module layout exists
|
||||
- core request path is stubbed or minimally working
|
||||
2. establish a working yt-dlp baseline
|
||||
- archive behavior is preserved
|
||||
- output path behavior is preserved or intentionally updated
|
||||
- use yt-dlp .conf and set reasonable default
|
||||
3. expose basic hooks/interfaces for future frontends
|
||||
- submit/request path exists
|
||||
- status/progress hook exists
|
||||
- basic health/version visibility exists
|
||||
4. make local testing practical without breaking container defaults
|
||||
- backend can run when `/config` or `/downloads` are not writable in local dev
|
||||
- env vars may override executable/config/download paths
|
||||
- status makes the effective runtime command/paths inspectable
|
||||
|
||||
** evidence
|
||||
- commit: 7926534,2a56485
|
||||
- tests:
|
||||
1. `python3 -m py_compile ./youdis/main.py ./youdis/models.py ./youdis/adapters/__init__.py ./youdis/adapters/discord.py`
|
||||
2. `python3 -m uvicorn youdis.main:app --host 127.0.0.1 --port 8000`
|
||||
3. `sudo curl -L https://github.com/yt-dlp/yt-dlp/releases/download/2026.03.17/yt-dlp -o /usr/local/bin/yt-dlp`
|
||||
4. `sudo chmod +x /usr/local/bin/yt-dlp`
|
||||
5. `yt-dlp --version`
|
||||
6. `curl http://127.0.0.1:8000/health`
|
||||
7. `curl http://127.0.0.1:8000/version`
|
||||
8. `curl -X POST http://127.0.0.1:8000/jobs -H 'content-type: application/json' -d '{"url":"https://www.youtube.com/watch?v=dQw4w9WgXcQ"}'`
|
||||
9. `curl http://127.0.0.1:8000/jobs/current`
|
||||
10. if testing in container: `docker build -t youdis:v2 .`
|
||||
11. if testing in container: `docker run --rm -p 8000:8000 -v [config]:/config -v [downloads]:/downloads youdis:v2`
|
||||
:OUTPUT_STEP1-9:
|
||||
user@paladin:~/proj/youdis$ curl http://127.0.0.1:8000/health
|
||||
{"status":"ok"}
|
||||
user@paladin:~/proj/youdis$ curl http://127.0.0.1:8000/version
|
||||
{"version":"20250829-ec72c56","active_job":false}
|
||||
user@paladin:~/proj/youdis$ curl -X POST http://127.0.0.1:8000/jobs -H 'content-type: application/json' -d '{"url":"https://www.youtube.com/watch?v=3i72yY_LaW4"}'
|
||||
{"job_id":"cc85165e-d906-4eee-864f-1a398b6de2e0","state":"accepted","url":"https://www.youtube.com/watch?v=3i72yY_LaW4","message":"accepted","phase":"queued","disposition":null,"requester_id":null,"requester_name":null,"origin":null,"result_path":null,"command":[],"returncode":null,"created_at":"2026-04-01T00:44:35.657196","updated_at":"2026-04-01T00:44:35.657198"}
|
||||
user@paladin:~/proj/youdis$ curl http://127.0.0.1:8000/jobs/current
|
||||
{"active":false,"job":{"job_id":"cc85165e-d906-4eee-864f-1a398b6de2e0","state":"failed","url":"https://www.youtube.com/watch?v=3i72yY_LaW4","message":"ERROR: unable to create directory [Errno 13] Permission denied: '/downloads'","phase":null,"disposition":null,"requester_id":null,"requester_name":null,"origin":null,"result_path":null,"command":["yt-dlp","--config-locations","/home/user/proj/youdis/default-yt-dlp.conf","https://www.youtube.com/watch?v=3i72yY_LaW4"],"returncode":1,"created_at":"2026-04-01T00:44:35.657196","updated_at":"2026-03-31T20:44:36.653353"}}user@paladin:~/proj/youdis$
|
||||
:END:
|
||||
- datetime: [2026-03-31 Tue 20:45]
|
||||
|
||||
** notes
|
||||
- validate `yt-dlp` subprocess invocation in-container; not verifiable in the current shell because `yt-dlp` is not installed here
|
||||
- confirm `--config-locations` behavior against the installed `yt-dlp` version during integration testing
|
||||
- current backend scaffold is not yet wired into `dockerfile` or `run-youdis.sh`
|
||||
- archive-hit and result-path parsing currently depend on `yt-dlp` stdout text patterns, so treat them as provisional until integration-tested
|
||||
- local dev now falls back to repo-local `.runtime/{config,downloads}` when `/config` or `/downloads` are not writable
|
||||
- had to uninstall yt-dlp python pkg from the venv, which resulted in a '403 Forbidden'
|
||||
|
||||
* [X] 2.0.2: update discord bot to use new backend (3)
|
||||
update the discord bot into a thin frontend that talks to the backend and verify the flow end to end
|
||||
** pm notes
|
||||
- this is the first real frontend proof. once this works cleanly, zulip/xmpp should mostly be adapter work rather than downloader rewrites.
|
||||
- keep discord logic thin; no auth
|
||||
- do not duplicate yt-dlp behavior in the bot
|
||||
|
||||
** Acceptance Criteria
|
||||
1. discord bot submits requests to backend
|
||||
- command/input handling works
|
||||
- acceptance/busy/failure responses are clear
|
||||
2. discord bot relays useful backend status
|
||||
- progress reporting works at a basic level
|
||||
- completion/failure/skipped outcomes are surfaced
|
||||
3. backend-discord flow is tested end to end
|
||||
- valid request path tested
|
||||
- busy or conflict behavior tested
|
||||
- failure path tested
|
||||
4. add dotenv support to ease dev
|
||||
- os.getenv methods remain standard for prod/docker build
|
||||
- populate .env with dev env defaults
|
||||
|
||||
** evidence
|
||||
- commit: 5210d2c, 043cb4
|
||||
- tests: https://youtu.be/20HxMMSqRyg?si=3v7mN2L88c_FxpQR 18m
|
||||
1. start backend: `python3 -m uvicorn youdis.main:app --host 127.0.0.1 --port 8000`
|
||||
2. create local env file: `cp .env.example .env`
|
||||
3. add `api_token` to `.env`
|
||||
4. start adapter: `python3 ./youdis.py`
|
||||
5. in discord, run `/youtube url:https://www.youtube.com/watch?v=dQw4w9WgXcQ`
|
||||
:out:
|
||||
#+begin_src shell
|
||||
(venv) user@paladin:~/proj/youdis$ python ./youdis.py
|
||||
Task exception was never retrieved
|
||||
future: <Task finished name='Task-43' coro=<Client._dispatch_interaction() done, defined at /home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/client/client.py:1773> exception=KeyError('youtube')>
|
||||
Traceback (most recent call last):
|
||||
File "/home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/client/client.py", line 1798, in _dispatch_interaction
|
||||
if ctx.command:
|
||||
File "/home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/models/internal/context.py", line 329, in command
|
||||
return self.client._interaction_lookup[self._command_name]
|
||||
KeyError: 'youtube'
|
||||
#+end_src
|
||||
:end:
|
||||
|
||||
6. confirm channel response says the job was submitted to backend
|
||||
7. confirm requester receives DM updates for accepted/running/completed or failed
|
||||
:out:
|
||||
accepted job 4ef6fde5-57cc-478c-b0e2-18458c693fa4 for https://www.youtube.com/watch?v=dQw4w9WgXcQ
|
||||
state=running | phase=running | [youtube] dQw4w9WgXcQ: Downloading webpage | path=/home/user/proj/youdis/downloads
|
||||
state=running | phase=downloading | [download] Destination: /home/user/proj/youdis/downloads/Rick_Astley/NA/NANARickAstley-_Never_Gonna_Give_You_Up_Official_Video_4K_Remaster.f401.mp4 | path=/home/user/proj/youdis/downloads/Rick_Astley/NA/NANARickAstley-_Never_Gonna_Give_You_Up_Official_Video_4K_Remaster.f401.mp4
|
||||
state=completed | [Metadata] There isn't any metadata to add | path=/home/user/proj/youdis/downloads/Rick_Astley/NA/NANARickAstley-_Never_Gonna_Give_You_Up_Official_Video_4K_Remaster.mp4
|
||||
:end:
|
||||
8. while first job is active, submit another `/youtube` and confirm busy behavior
|
||||
:out:
|
||||
#+begin_src shell
|
||||
Error: AttributeError
|
||||
Traceback (most recent call last):
|
||||
File "/home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/client/client.py", line 1900, in __dispatch_interaction
|
||||
response = await callback
|
||||
File "/home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/client/client.py", line 1771, in _run_slash_command
|
||||
return await command(ctx, **ctx.kwargs)
|
||||
File "/home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/models/internal/command.py", line 132, in __call__
|
||||
await self.call_callback(self.callback, context)
|
||||
File "/home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/models/internal/application_commands.py", line 833, in call_callback
|
||||
return await self.call_with_binding(callback, ctx, *new_args, **new_kwargs)
|
||||
File "/home/user/proj/youdis/venv/lib/python3.10/site-packages/interactions/models/internal/callback.py", line 43, in call_with_binding
|
||||
return await callback(*args, **kwargs)
|
||||
File "/home/user/proj/youdis/youdis/adapters/discord.py", line 167, in youtube
|
||||
await ctx.channel.send(f"Submitted <{url}> to the backend. Status updates via DM.")
|
||||
AttributeError: 'NoneType' object has no attribute 'send'
|
||||
#+end_src
|
||||
busy: busy with https://youtu.be/20HxMMSqRyg?si=3v7mN2L88c_FxpQR
|
||||
state=running | phase=running | cancel requested | path=/home/user/proj/youdis/downloads/James_Hoffmann/NA/NANAThe_Beginner_s_Guide_To_Latte_Art.f401.mp4
|
||||
:end:
|
||||
9. run `/status` and confirm it reflects current or last backend job
|
||||
:out:
|
||||
last job: state=completed | [Metadata] There isn't any metadata to add | path=/home/user/proj/youdis/downloads/Rick_Astley/NA/NANARickAstley-_Never_Gonna_Give_You_Up_Official_Video_4K_Remaster.mp4
|
||||
:end:
|
||||
10. run `/interrupt` as owner and confirm cancellation is surfaced via DM
|
||||
:out:
|
||||
last job: state=cancelled | cancelled | path=/home/user/proj/youdis/downloads/James_Hoffmann/NA/NANAThe_Beginner_s_Guide_To_Latte_Art.f401.mp4
|
||||
:end:
|
||||
- datetime:[2026-04-02 Thu 11:52]
|
||||
|
||||
*** org-block tests
|
||||
#+begin_src shell :dir ~/proj/youdis :results output verbatim
|
||||
source ./venv/bin/activate
|
||||
python3 -m uvicorn youdis.main:app --host 127.0.0.1 --port 8000
|
||||
#+end_src
|
||||
|
||||
#+begin_src shell :results output
|
||||
echo ok
|
||||
#+end_src
|
||||
|
||||
#+RESULTS:
|
||||
: ok
|
||||
|
||||
#+begin_src python :dir ~/proj/youdis :results output verbatim
|
||||
python ./youdis.py
|
||||
#+end_src
|
||||
|
||||
#+RESULTS:
|
||||
|
||||
** notes
|
||||
- discord adapter is now a thin HTTP client of the backend; it no longer imports or configures yt-dlp
|
||||
- `YOUDIS_BACKEND_URL` controls which backend the adapter targets
|
||||
- progress updates are currently implemented by polling `/jobs/current` and DMing only when the summary changes
|
||||
- legacy auth/user-management commands were removed from the active adapter path
|
||||
- `.env` is now supported for local/dev convenience, while real environment variables still override it in prod/docker
|
||||
- command registration required explicit binding plus `@bot.listen()` listeners in this adapter structure
|
||||
* [X] 2.0.3: remove deprecated discord-bot functionality (2)
|
||||
delete or retire legacy bot behaviors that no longer fit once the backend split is in place
|
||||
** pm notes
|
||||
- only remove this after the new path works. this is cleanup, not pioneering work.
|
||||
- favor deletion over compatibility shims
|
||||
- keep operator controls only if still useful
|
||||
|
||||
** Acceptance Criteria
|
||||
1. remove obsolete auth/user-management behavior
|
||||
- old user persistence and commands are removed
|
||||
- backend-facing flow no longer depends on them
|
||||
2. remove obsolete downloader/runtime logic from bot
|
||||
- bot no longer owns yt-dlp execution
|
||||
- dead code paths are deleted
|
||||
3. leave the bot in a coherent state
|
||||
- remaining commands reflect actual supported behavior
|
||||
- deprecated artifacts are clearly removed or marked
|
||||
|
||||
** evidence
|
||||
- commit: 0aa9950
|
||||
- tests:
|
||||
1. `python3 -m py_compile ./youdis.py ./youdis/adapters/discord.py`
|
||||
2. `rg -n "users.json|api_token" README.md unraid-ca-template.xml youdis.py youdis/adapters/discord.py`
|
||||
3. start backend: `python3 -m uvicorn youdis.main:app --host 127.0.0.1 --port 8000`
|
||||
4. start adapter: `python3 ./youdis.py`
|
||||
5. in discord, run `/youtube`, `/status`, and `/interrupt` and confirm the adapter still works after cleanup
|
||||
- datetime: [2026-04-02 Thu 12:09]
|
||||
|
||||
** notes
|
||||
- active bot path no longer includes local auth or user-management behavior
|
||||
- top-level `youdis.py` remains as a thin launcher so existing operator habits and scripts do not break during the refactor
|
||||
- cleanup updated user-facing deployment artifacts to match the v2 naming and architecture, including `DISCORD_BOT_TOKEN` and removal of `users.json` references
|
||||
- archived planning docs were intentionally left untouched: `pm/tasks.org` is historical and `pm/notes.org` is personal working notes
|
||||
|
||||
* [ ] 2.0.4: make youdis.py app runner for backend + adapters (3)
|
||||
Build a simple Python orchestration layer in youdis.py so the standard app stack can be launched from one entrypoint while backend and adapters remain independently runnable for testing.
|
||||
|
||||
** pm notes
|
||||
- keep components independently runnable
|
||||
- youdis.py as app-level orchestrator; let Docker just run python3 /app/youdis.py
|
||||
- no plugin discovery or hot-loading
|
||||
- Docker should package and launch the app, not decide internal process topology
|
||||
- preserve the ability to run backend or adapters directly for debugging
|
||||
- optimize for one obvious default run path
|
||||
|
||||
** Acceptance Criteria
|
||||
1. define the default app startup path
|
||||
- youdis.py launches the standard stack for v2
|
||||
- backend and Discord adapter startup order is explicit
|
||||
- shutdown behavior is coherent enough for local/dev use
|
||||
2. preserve modular run paths
|
||||
- backend can still be run directly
|
||||
- Discord adapter can still be run directly
|
||||
- orchestration layer does not bury component-level testing
|
||||
3. keep orchestration simple
|
||||
- no dynamic adapter discovery
|
||||
- no hot reloading framework
|
||||
- configured components are started explicitly
|
||||
4. document runtime ownership
|
||||
- clarify what Python orchestrates vs what Docker orchestrates
|
||||
- identify env vars or flags that control which components start
|
||||
- leave room for future Zulip/XMPP adapters without redesigning the runner
|
||||
|
||||
** evidence
|
||||
- commit: 309ce87
|
||||
- tests:
|
||||
1. `python3 -m py_compile ./youdis.py ./youdis/adapters/discord.py`
|
||||
2. backend direct run still works: `python3 -m uvicorn youdis.main:app --host 127.0.0.1 --port 8000`
|
||||
3. discord direct run still works: `python3 -m youdis.adapters.discord`
|
||||
4. app runner backend-only smoke test: `ENABLE_DISCORD=0 timeout 5s python3 ./youdis.py`
|
||||
5. app runner default path: `python3 ./youdis.py`
|
||||
- date: [2026-04-02 Thu 14:13]
|
||||
|
||||
** notes
|
||||
- `youdis.py` is now the default v2 app runner and starts the standard stack explicitly rather than dynamically discovering adapters
|
||||
- backend starts first and must pass a health check before the Discord adapter is launched
|
||||
- backend and Discord adapter remain directly runnable for debugging and tests
|
||||
- Docker is intended to invoke `python3 /app/youdis.py`; Python owns app orchestration while Docker owns packaging and runtime environment
|
||||
- adapter startup remains explicit in `youdis.py`, while each adapter gets its own `ENABLE_<ADAPTER>` flag
|
||||
- adding an adapter means creating `youdis/adapters/<adapter>.py`, adding `start_<adapter>()` in `youdis.py`, wiring its `ENABLE_<ADAPTER>` flag, and documenting any supporting env vars in `.env.example`
|
||||
- runner flags currently include `YOUDIS_RUN_BACKEND`, `YOUDIS_BACKEND_HOST`, `YOUDIS_BACKEND_PORT`, and `ENABLE_DISCORD`
|
||||
|
||||
|
||||
* ==== BACKLOG ====
|
||||
Tasks below this line are inactive and should not be touched.
|
||||
* [ ] 2.0.X: fix automation and build pipeline (3)
|
||||
repair and simplify the build/update/deploy path so it matches the new backend-plus-frontend structure
|
||||
** pm notes
|
||||
- this should come after architecture and discord integration stabilize. no point polishing the pipeline for the wrong shape.
|
||||
- optimize for simple manual ops first
|
||||
- stop here after pipeline is sane
|
||||
|
||||
** Acceptance Criteria
|
||||
1. align build artifacts with the new structure
|
||||
- docker/build scripts reflect current components
|
||||
- runtime assumptions are consistent
|
||||
2. review old automation artifacts
|
||||
- stale runner/update/restart logic is removed or updated
|
||||
- manual update/rebuild flow is clear
|
||||
3. confirm deployment path works
|
||||
- local or unraid deployment is validated
|
||||
- pipeline is understandable enough to maintain
|
||||
|
||||
** evidence
|
||||
- commit:
|
||||
- tests:
|
||||
- datetime:
|
||||
|
||||
** notes
|
||||
|
||||
* [ ] X.x.x: clean up discord adapter UI
|
||||
|
||||
** acceptance criteria
|
||||
1. fix interaction pattern so it doesnt time out - prefer "command accepted" or somehting
|
||||
2. remove all intermediate messages between "accepted/running" and "complete" - /status handles this!
|
||||
- discord can also output a "busy" signal, research this
|
||||
3. fix output syntax, we dont need to get crazy with discord cards
|
||||
|
||||
** evidence
|
||||
- commit:
|
||||
- tests:
|
||||
- date:
|
||||
|
||||
** notes
|
||||
|
||||
* [ ] X.x.x: fix youtube -> plex default output
|
||||
|
||||
** acceptance criteria
|
||||
1.
|
||||
-
|
||||
|
||||
** evidence
|
||||
- commit:
|
||||
- tests:
|
||||
- date:
|
||||
|
||||
** notes
|
||||
|
||||
* /
|
||||
BIN
requirements.txt
BIN
requirements.txt
Binary file not shown.
@@ -8,11 +8,11 @@
|
||||
<Privileged>false</Privileged>
|
||||
<Support>[Unraid Support Thread]</Support>
|
||||
<Project>https://github.com/eulaly/youdis</Project>
|
||||
<Overview>Discord bot-based wrapper for yt-dlp. Let your friends download videos to your server! Supports playlists, requires a configured Discord bot.</Overview>
|
||||
<Overview>Private yt-dlp worker with a Discord adapter. Submit downloads through Discord while the backend owns yt-dlp execution and job state.</Overview>
|
||||
<Category>Downloaders: Tools:</Category>
|
||||
<TemplateURL>https://raw.githubusercontent.com/eulaly/unraid-templates/refs/heads/master/unraid-ca-template.xml</TemplateURL>
|
||||
<Icon>https://github.com/eulaly/youdis/blob/c978a2326984efa9670678687ed1a1473478d753/yt_dlp.png</Icon>
|
||||
<Config Name="api_token" Target="api_token" Default="" Mode="" Description="Discord bot token" Type="Variable" Display="always" Required="true" Mask="true"/>
|
||||
<Config Name="DISCORD_BOT_TOKEN" Target="DISCORD_BOT_TOKEN" Default="" Mode="" Description="Discord bot token" Type="Variable" Display="always" Required="true" Mask="true"/>
|
||||
<Config Name="Downloads" Target="/downloads" Default="" Mode="rw" Description="Video download location" Type="Path" Display="always" Required="false"/>
|
||||
<Config Name="Config" Target="/config" Default="/mnt/user/appdata/youdis/config" Mode="rw" Description="Config location (archive.txt, users.json)" Type="Path" Display="always" Required="false"/>
|
||||
<Config Name="Config" Target="/config" Default="/mnt/user/appdata/youdis/config" Mode="rw" Description="Config location (archive.txt and backend runtime data)" Type="Path" Display="always" Required="false"/>
|
||||
</Container>
|
||||
|
||||
358
youdis.py
358
youdis.py
@@ -1,235 +1,161 @@
|
||||
#!/usr/bin/env python3
|
||||
'''
|
||||
youdis v1.1
|
||||
bot for downloading youtube videos using yt-dlp
|
||||
discord-py-interactions 5.11.0 has new option
|
||||
requires python>=3.9
|
||||
'''
|
||||
# match_filter: info_dict -> Raise utils.DownloadCancelled(msg) ? interrupt
|
||||
"""App runner for FastAPI backend and discord adapter."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import interactions
|
||||
from os import getenv
|
||||
from pathlib import Path
|
||||
import yt_dlp
|
||||
import json
|
||||
import asyncio
|
||||
import threading
|
||||
import os
|
||||
import sys
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from urllib.error import URLError
|
||||
from urllib.request import urlopen
|
||||
|
||||
userFile = Path('/config/users.json')
|
||||
userFile.parent.mkdir(exist_ok=True, parents=True)
|
||||
from youdis.env import load_project_dotenv
|
||||
|
||||
bot = interactions.Client(intents=interactions.Intents.DEFAULT,default_scope=2147491904)
|
||||
|
||||
def save_authorized_users(authorized_users):
|
||||
with open(userFile, 'w') as f:
|
||||
json.dump({'authorized_users': authorized_users}, f)
|
||||
load_project_dotenv()
|
||||
|
||||
def load_authorized_users():
|
||||
if not userFile.exists():
|
||||
save_authorized_users([])
|
||||
print(f'users.json not found; saving to {userFile}')
|
||||
return []
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent
|
||||
DEFAULT_BACKEND_HOST = os.getenv("YOUDIS_BACKEND_HOST", "127.0.0.1")
|
||||
DEFAULT_BACKEND_PORT = int(os.getenv("YOUDIS_BACKEND_PORT", "8000"))
|
||||
ENABLE_BACKEND = os.getenv("YOUDIS_RUN_BACKEND", "1") not in {"0", "false", "False"}
|
||||
ENABLE_DISCORD = os.getenv("ENABLE_DISCORD", "1") not in {"0", "false", "False"}
|
||||
BACKEND_HEALTH_TIMEOUT = float(os.getenv("YOUDIS_BACKEND_HEALTH_TIMEOUT", "20"))
|
||||
BACKEND_HEALTH_INTERVAL = float(os.getenv("YOUDIS_BACKEND_HEALTH_INTERVAL", "0.5"))
|
||||
|
||||
|
||||
@dataclass
|
||||
class ManagedProcess:
|
||||
name: str
|
||||
process: asyncio.subprocess.Process
|
||||
|
||||
|
||||
def backend_url() -> str:
|
||||
return f"http://{DEFAULT_BACKEND_HOST}:{DEFAULT_BACKEND_PORT}"
|
||||
|
||||
|
||||
def build_child_env() -> dict[str, str]:
|
||||
env = os.environ.copy()
|
||||
env.setdefault("YOUDIS_BACKEND_URL", backend_url())
|
||||
return env
|
||||
|
||||
|
||||
async def start_backend(env: dict[str, str]) -> ManagedProcess:
|
||||
process = await asyncio.create_subprocess_exec(
|
||||
sys.executable,
|
||||
"-m",
|
||||
"uvicorn",
|
||||
"youdis.main:app",
|
||||
"--host",
|
||||
DEFAULT_BACKEND_HOST,
|
||||
"--port",
|
||||
str(DEFAULT_BACKEND_PORT),
|
||||
cwd=str(REPO_ROOT),
|
||||
env=env,
|
||||
)
|
||||
return ManagedProcess(name="backend", process=process)
|
||||
|
||||
|
||||
async def start_discord(env: dict[str, str]) -> ManagedProcess:
|
||||
process = await asyncio.create_subprocess_exec(
|
||||
sys.executable,
|
||||
"-m",
|
||||
"youdis.adapters.discord",
|
||||
cwd=str(REPO_ROOT),
|
||||
env=env,
|
||||
)
|
||||
return ManagedProcess(name="discord", process=process)
|
||||
|
||||
|
||||
ADAPTER_STARTERS = {
|
||||
"discord": start_discord,
|
||||
}
|
||||
|
||||
|
||||
def selected_adapters() -> list[str]:
|
||||
requested: list[str] = []
|
||||
if ENABLE_DISCORD:
|
||||
requested.append("discord")
|
||||
return requested
|
||||
|
||||
|
||||
async def wait_for_backend_health(timeout_seconds: float) -> None:
|
||||
deadline = asyncio.get_running_loop().time() + timeout_seconds
|
||||
health_url = f"{backend_url()}/health"
|
||||
|
||||
while True:
|
||||
try:
|
||||
with urlopen(health_url, timeout=2) as response:
|
||||
if response.status == 200:
|
||||
return
|
||||
except URLError:
|
||||
pass
|
||||
|
||||
if asyncio.get_running_loop().time() >= deadline:
|
||||
raise TimeoutError(f"backend did not become healthy at {health_url}")
|
||||
|
||||
await asyncio.sleep(BACKEND_HEALTH_INTERVAL)
|
||||
|
||||
|
||||
async def stop_process(proc: ManagedProcess) -> None:
|
||||
if proc.process.returncode is not None:
|
||||
return
|
||||
|
||||
proc.process.terminate()
|
||||
try:
|
||||
await asyncio.wait_for(proc.process.wait(), timeout=10)
|
||||
except asyncio.TimeoutError:
|
||||
proc.process.kill()
|
||||
await proc.process.wait()
|
||||
|
||||
|
||||
async def run() -> int:
|
||||
managed: list[ManagedProcess] = []
|
||||
env = build_child_env()
|
||||
adapters = selected_adapters()
|
||||
|
||||
if not ENABLE_BACKEND and not adapters:
|
||||
print("nothing to start: backend is disabled and no adapters are enabled")
|
||||
return 1
|
||||
|
||||
try:
|
||||
with open(userFile, 'r') as f:
|
||||
data = json.load(f)
|
||||
except (json.JSONDecodeError, OSError):
|
||||
save_authorized_users([])
|
||||
print(f'users.json invalid; resetting {userFile}')
|
||||
return []
|
||||
if ENABLE_BACKEND:
|
||||
backend = await start_backend(env)
|
||||
managed.append(backend)
|
||||
print(f"started backend on {backend_url()}")
|
||||
await wait_for_backend_health(BACKEND_HEALTH_TIMEOUT)
|
||||
print("backend is healthy")
|
||||
|
||||
authorized_users = data.get('authorized_users', [])
|
||||
if not isinstance(authorized_users, list):
|
||||
authorized_users = []
|
||||
for adapter_name in adapters:
|
||||
process = await ADAPTER_STARTERS[adapter_name](env)
|
||||
managed.append(process)
|
||||
print(f"started {adapter_name} adapter")
|
||||
|
||||
authorized_users = [str(user_id) for user_id in authorized_users]
|
||||
save_authorized_users(authorized_users)
|
||||
print(f'authorized_users:{authorized_users}')
|
||||
return authorized_users
|
||||
wait_tasks = [asyncio.create_task(proc.process.wait()) for proc in managed]
|
||||
done, pending = await asyncio.wait(wait_tasks, return_when=asyncio.FIRST_COMPLETED)
|
||||
|
||||
authorized_users = load_authorized_users()
|
||||
for task in pending:
|
||||
task.cancel()
|
||||
|
||||
active_job_lock = threading.Lock()
|
||||
active_job = None
|
||||
first_returncode = 0
|
||||
for task in done:
|
||||
first_returncode = task.result()
|
||||
break
|
||||
|
||||
async def send_message(ctx, message):
|
||||
await ctx.author.send(message)
|
||||
|
||||
def claim_active_job(job):
|
||||
global active_job
|
||||
with active_job_lock:
|
||||
if active_job is not None:
|
||||
return active_job
|
||||
active_job = job
|
||||
return None
|
||||
|
||||
def get_active_job():
|
||||
with active_job_lock:
|
||||
return active_job
|
||||
|
||||
def clear_active_job(job):
|
||||
global active_job
|
||||
with active_job_lock:
|
||||
if active_job is job:
|
||||
active_job = None
|
||||
|
||||
def download_video(url, options):
|
||||
with yt_dlp.YoutubeDL(options) as ydl:
|
||||
ydl.download(url)
|
||||
|
||||
def create_hook(ctx, loop, cancel_event):
|
||||
seen_updates = set()
|
||||
|
||||
def hook(d):
|
||||
if cancel_event.is_set():
|
||||
raise yt_dlp.utils.DownloadCancelled('download canceled by /interrupt')
|
||||
|
||||
status = d.get('status')
|
||||
info = d.get('info_dict') or {}
|
||||
|
||||
if status not in {'downloading', 'finished'}:
|
||||
return
|
||||
|
||||
filename = d.get('filename') or info.get('_filename') or info.get('title')
|
||||
update_key = (status, filename)
|
||||
if update_key in seen_updates:
|
||||
return
|
||||
|
||||
seen_updates.add(update_key)
|
||||
playlist_index = info.get('playlist_index')
|
||||
playlist_count = info.get('playlist_count')
|
||||
url = info.get('webpage_url')
|
||||
|
||||
prefix = status
|
||||
if playlist_index and playlist_count:
|
||||
prefix = f'{status} {playlist_index} of {playlist_count}'
|
||||
|
||||
msg = f'{prefix}: {filename}'
|
||||
if url:
|
||||
msg = f'{msg} <{url}>'
|
||||
|
||||
asyncio.run_coroutine_threadsafe(send_message(ctx, msg), loop)
|
||||
|
||||
return hook
|
||||
|
||||
@interactions.slash_command(name="youtube",description="download video from youtube to server")
|
||||
@interactions.slash_option(
|
||||
name='url',
|
||||
opt_type=interactions.OptionType.STRING,
|
||||
required=True,
|
||||
description='url target'
|
||||
)
|
||||
async def youtube(ctx: interactions.SlashContext, url:str):
|
||||
print(f'{ctx.author.id} requested {url}')
|
||||
# check that user is authorized
|
||||
if str(ctx.author.id) not in authorized_users:
|
||||
if ctx.author.id == 127831327012683776:
|
||||
await ctx.author.send('potato stop')
|
||||
await ctx.author.send('you are not authorized to use this command. message my owner to be added.')
|
||||
return
|
||||
|
||||
loop = asyncio.get_running_loop()
|
||||
cancel_event = threading.Event()
|
||||
hook = create_hook(ctx, loop, cancel_event)
|
||||
job = {
|
||||
'requester_id': str(ctx.author.id),
|
||||
'request_url': url,
|
||||
'cancel_event': cancel_event,
|
||||
}
|
||||
existing_job = claim_active_job(job)
|
||||
if existing_job:
|
||||
await ctx.author.send(
|
||||
f'already downloading for <@{existing_job["requester_id"]}>. '
|
||||
'single-job mode is enabled right now; try again after it finishes.'
|
||||
)
|
||||
return
|
||||
|
||||
# use api_to_cli and paste cli options to get the output you need
|
||||
yoptions = {
|
||||
'format':'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best',
|
||||
'fragment_tries': 10,
|
||||
'restrictfilenames':True,
|
||||
'paths': {'home':'/downloads'},
|
||||
'retries':10,
|
||||
'writeinfojson':False,
|
||||
'allow_playlist_files':True,
|
||||
'noplaylist':True,
|
||||
'download_archive':'/config/archive.txt',
|
||||
'progress_hooks':[hook],
|
||||
'outtmpl': '%(uploader)s/%(playlist_title)s/%(playlist_index)s%(playlist_index& - )s%(title)s.%(ext)s',
|
||||
'outtmpl_na_placeholder':'',
|
||||
}
|
||||
await ctx.channel.send(f'Downloading from <{url}>. Status updates via DM. Single-job mode is enabled.')
|
||||
|
||||
try:
|
||||
await asyncio.to_thread(download_video, url, yoptions)
|
||||
except yt_dlp.utils.DownloadCancelled as exc:
|
||||
print(f'download canceled: {exc}')
|
||||
await ctx.author.send(f'download canceled: {exc}')
|
||||
except yt_dlp.utils.DownloadError as exc:
|
||||
print(f'download failed: {exc}')
|
||||
await ctx.author.send(f'download failed: {exc}')
|
||||
except Exception as exc:
|
||||
print(f'unexpected download failure: {exc}')
|
||||
await ctx.author.send(f'unexpected download failure: {exc}')
|
||||
else:
|
||||
await ctx.author.send(f'download complete for <{url}>')
|
||||
return first_returncode
|
||||
finally:
|
||||
clear_active_job(job)
|
||||
for proc in reversed(managed):
|
||||
await stop_process(proc)
|
||||
|
||||
|
||||
@interactions.slash_command(name="interrupt",description="cancel current job")
|
||||
@interactions.check(interactions.is_owner())
|
||||
async def _interrupt(ctx):
|
||||
job = get_active_job()
|
||||
if not job:
|
||||
await ctx.author.send('no active download to interrupt')
|
||||
return
|
||||
def main() -> None:
|
||||
try:
|
||||
raise SystemExit(asyncio.run(run()))
|
||||
except KeyboardInterrupt:
|
||||
raise SystemExit(130)
|
||||
|
||||
job['cancel_event'].set()
|
||||
print(f'interrupt requested for {job["request_url"]}')
|
||||
await ctx.author.send(
|
||||
f'interrupt requested for <{job["request_url"]}>; '
|
||||
'cancellation is coarse and will stop on the next yt-dlp progress update'
|
||||
)
|
||||
|
||||
@interactions.slash_command(name="adduser",description="authorize target user")
|
||||
@interactions.slash_option(
|
||||
name="user",
|
||||
opt_type=interactions.OptionType.USER,
|
||||
required=True,
|
||||
description='enable this bot for target user',
|
||||
)
|
||||
@interactions.check(interactions.is_owner())
|
||||
async def _adduser(ctx: interactions.SlashContext, user:interactions.OptionType.USER):
|
||||
user_id = str(user.id)
|
||||
if user_id not in authorized_users:
|
||||
authorized_users.append(user_id)
|
||||
save_authorized_users(authorized_users)
|
||||
print(f'authorized {user_id}')
|
||||
await ctx.author.send(f'authorized {user.mention}')
|
||||
else:
|
||||
await ctx.author.send(f'{user.mention} is already authorized')
|
||||
|
||||
@interactions.slash_command(name="removeuser",description="deauthorize target user")
|
||||
@interactions.slash_option(
|
||||
name="user",
|
||||
opt_type=interactions.OptionType.USER,
|
||||
required=True,
|
||||
description='disable this bot for target user',
|
||||
)
|
||||
@interactions.check(interactions.is_owner())
|
||||
async def _removeuser(ctx: interactions.SlashContext, user:interactions.OptionType.USER):
|
||||
user_id = str(user.id)
|
||||
if user_id in authorized_users:
|
||||
authorized_users.remove(user_id)
|
||||
save_authorized_users(authorized_users)
|
||||
print(f'deauthorized {user_id}')
|
||||
await ctx.author.send(f'deauthorized {user.mention}')
|
||||
else:
|
||||
await ctx.author.send(f'{user.mention} is not currently authorized')
|
||||
|
||||
api_token = getenv('api_token')
|
||||
if not api_token:
|
||||
raise ValueError('API token not set. Retrieve from your Discord bot.')
|
||||
bot.start(api_token)
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
1
youdis/__init__.py
Normal file
1
youdis/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Youdis v2 backend package."""
|
||||
1
youdis/adapters/__init__.py
Normal file
1
youdis/adapters/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Frontend adapters for the youdis backend."""
|
||||
231
youdis/adapters/discord.py
Normal file
231
youdis/adapters/discord.py
Normal file
@@ -0,0 +1,231 @@
|
||||
"""Discord adapter for interacting with FastAPI backend worker."""
|
||||
|
||||
import asyncio
|
||||
from os import getenv
|
||||
|
||||
import aiohttp
|
||||
import interactions
|
||||
|
||||
from ..env import load_project_dotenv
|
||||
|
||||
|
||||
load_project_dotenv()
|
||||
|
||||
|
||||
BACKEND_HOST = getenv("YOUDIS_BACKEND_HOST", "127.0.0.1")
|
||||
BACKEND_PORT = int(getenv("YOUDIS_BACKEND_PORT", "8000"))
|
||||
BACKEND_URL = f"http://{BACKEND_HOST}:{BACKEND_PORT}".rstrip("/")
|
||||
POLL_INTERVAL_SECONDS = float(getenv("YOUDIS_POLL_INTERVAL_SECONDS", "2"))
|
||||
DEFAULT_SCOPE = int(getenv("DISCORD_BOT_SCOPE", "2147491904"))
|
||||
|
||||
|
||||
bot = interactions.Client(
|
||||
intents=interactions.Intents.DEFAULT,
|
||||
default_scope=DEFAULT_SCOPE,
|
||||
)
|
||||
http_session: aiohttp.ClientSession | None = None
|
||||
poll_tasks: dict[str, asyncio.Task] = {}
|
||||
|
||||
|
||||
def backend_url(path: str) -> str:
|
||||
return f"{BACKEND_URL}{path}"
|
||||
|
||||
|
||||
async def get_session() -> aiohttp.ClientSession:
|
||||
global http_session
|
||||
if http_session is None or http_session.closed:
|
||||
http_session = aiohttp.ClientSession()
|
||||
return http_session
|
||||
|
||||
|
||||
async def request_json(method: str, path: str, **kwargs):
|
||||
session = await get_session()
|
||||
async with session.request(method, backend_url(path), **kwargs) as response:
|
||||
data = await response.json()
|
||||
return response.status, data
|
||||
|
||||
|
||||
def format_status_message(job: dict) -> str:
|
||||
state = job.get("state")
|
||||
phase = job.get("phase")
|
||||
disposition = job.get("disposition")
|
||||
message = job.get("message")
|
||||
result_path = job.get("result_path")
|
||||
|
||||
parts = [f"state={state}"]
|
||||
if phase:
|
||||
parts.append(f"phase={phase}")
|
||||
if disposition:
|
||||
parts.append(f"disposition={disposition}")
|
||||
if message:
|
||||
parts.append(message)
|
||||
if result_path:
|
||||
parts.append(f"path={result_path}")
|
||||
return " | ".join(parts)
|
||||
|
||||
|
||||
async def dm(ctx: interactions.SlashContext, message: str) -> None:
|
||||
await ctx.author.send(message)
|
||||
|
||||
|
||||
async def respond(ctx: interactions.SlashContext, message: str) -> None:
|
||||
if ctx.channel is not None:
|
||||
await ctx.channel.send(message)
|
||||
return
|
||||
await dm(ctx, message)
|
||||
|
||||
|
||||
async def poll_job_updates(ctx: interactions.SlashContext, job_id: str) -> None:
|
||||
last_sent = None
|
||||
try:
|
||||
while True:
|
||||
status_code, payload = await request_json("GET", "/jobs/current")
|
||||
if status_code != 200:
|
||||
await dm(ctx, f"backend status check failed: HTTP {status_code}")
|
||||
return
|
||||
|
||||
job = payload.get("job")
|
||||
if not job:
|
||||
await dm(ctx, f"job {job_id} is no longer visible from the backend")
|
||||
return
|
||||
|
||||
if job.get("job_id") != job_id:
|
||||
await dm(ctx, f"job {job_id} is no longer the current backend job")
|
||||
return
|
||||
|
||||
summary = format_status_message(job)
|
||||
if summary != last_sent:
|
||||
await dm(ctx, summary)
|
||||
last_sent = summary
|
||||
|
||||
if job.get("state") in {"completed", "failed", "cancelled"}:
|
||||
return
|
||||
|
||||
await asyncio.sleep(POLL_INTERVAL_SECONDS)
|
||||
except asyncio.CancelledError:
|
||||
raise
|
||||
except aiohttp.ClientError as exc:
|
||||
await dm(ctx, f"backend poll failed: {exc}")
|
||||
finally:
|
||||
poll_tasks.pop(job_id, None)
|
||||
|
||||
|
||||
def ensure_poll_task(ctx: interactions.SlashContext, job_id: str) -> None:
|
||||
existing = poll_tasks.get(job_id)
|
||||
if existing and not existing.done():
|
||||
return
|
||||
poll_tasks[job_id] = asyncio.create_task(poll_job_updates(ctx, job_id))
|
||||
|
||||
@interactions.slash_command(name="youtube", description="submit a youtube download to the backend")
|
||||
@interactions.slash_option(
|
||||
name="url",
|
||||
opt_type=interactions.OptionType.STRING,
|
||||
required=True,
|
||||
description="url target",
|
||||
)
|
||||
async def youtube(ctx: interactions.SlashContext, url: str):
|
||||
payload = {
|
||||
"url": url,
|
||||
"requester_id": str(ctx.author.id),
|
||||
"requester_name": ctx.author.username,
|
||||
"origin": f"discord:{ctx.guild_id or 'dm'}:{ctx.channel_id}",
|
||||
}
|
||||
|
||||
try:
|
||||
status_code, job = await request_json("POST", "/jobs", json=payload)
|
||||
except aiohttp.ClientError as exc:
|
||||
await dm(ctx, f"backend request failed: {exc}")
|
||||
return
|
||||
|
||||
if status_code != 200:
|
||||
await dm(ctx, f"backend request failed: HTTP {status_code}")
|
||||
return
|
||||
|
||||
state = job.get("state")
|
||||
job_id = job.get("job_id", "unknown")
|
||||
if state == "busy":
|
||||
await respond(ctx, "Backend is busy with another job. Details via DM.")
|
||||
await dm(ctx, f"busy: {job.get('message')}")
|
||||
return
|
||||
|
||||
if state != "accepted":
|
||||
await respond(ctx, "Backend rejected the request. Details via DM.")
|
||||
await dm(ctx, format_status_message(job))
|
||||
return
|
||||
|
||||
await respond(ctx, f"Submitted <{url}> to the backend. Status updates via DM.")
|
||||
await dm(ctx, f"accepted job {job_id} for <{url}>")
|
||||
ensure_poll_task(ctx, job_id)
|
||||
|
||||
|
||||
@interactions.slash_command(name="interrupt", description="cancel the current backend job")
|
||||
@interactions.check(interactions.is_owner())
|
||||
async def interrupt(ctx: interactions.SlashContext):
|
||||
try:
|
||||
status_code, payload = await request_json("POST", "/jobs/current/cancel")
|
||||
except aiohttp.ClientError as exc:
|
||||
await dm(ctx, f"backend cancel failed: {exc}")
|
||||
return
|
||||
|
||||
if status_code == 404:
|
||||
await dm(ctx, "no active backend job to interrupt")
|
||||
return
|
||||
|
||||
if status_code != 200:
|
||||
await dm(ctx, f"backend cancel failed: HTTP {status_code}")
|
||||
return
|
||||
|
||||
await dm(ctx, format_status_message(payload))
|
||||
|
||||
|
||||
@interactions.slash_command(name="status", description="show the current backend job status")
|
||||
async def status(ctx: interactions.SlashContext):
|
||||
try:
|
||||
status_code, payload = await request_json("GET", "/jobs/current")
|
||||
except aiohttp.ClientError as exc:
|
||||
await dm(ctx, f"backend status failed: {exc}")
|
||||
return
|
||||
|
||||
if status_code != 200:
|
||||
await dm(ctx, f"backend status failed: HTTP {status_code}")
|
||||
return
|
||||
|
||||
job = payload.get("job")
|
||||
if not job:
|
||||
await dm(ctx, "backend has no active or recent job")
|
||||
return
|
||||
|
||||
active = payload.get("active")
|
||||
prefix = "active" if active else "last"
|
||||
await dm(ctx, f"{prefix} job: {format_status_message(job)}")
|
||||
|
||||
@bot.listen()
|
||||
async def on_startup():
|
||||
await get_session()
|
||||
print(f"discord adapter configured for backend {BACKEND_URL}")
|
||||
print(f"{bot.application_commands.count} registered commands:")
|
||||
for i, x in enumerate(bot.application_commands,start=1):
|
||||
print(f" {i}. {x.name}")
|
||||
|
||||
@bot.listen()
|
||||
async def on_shutdown():
|
||||
global http_session
|
||||
for task in list(poll_tasks.values()):
|
||||
task.cancel()
|
||||
poll_tasks.clear()
|
||||
if http_session is not None and not http_session.closed:
|
||||
await http_session.close()
|
||||
http_session = None
|
||||
|
||||
def main() -> None:
|
||||
api_token = getenv("DISCORD_BOT_TOKEN")
|
||||
if not api_token:
|
||||
raise ValueError("API token not set. Retrieve from your Discord bot.")
|
||||
# bot.add_command(youtube)
|
||||
# bot.add_command(status)
|
||||
# bot.add_command(interrupt)
|
||||
bot.start(api_token)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
13
youdis/env.py
Normal file
13
youdis/env.py
Normal file
@@ -0,0 +1,13 @@
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
from dotenv import load_dotenv
|
||||
except ModuleNotFoundError: # pragma: no cover - optional local convenience dependency
|
||||
load_dotenv = None
|
||||
|
||||
|
||||
def load_project_dotenv() -> None:
|
||||
if load_dotenv is None:
|
||||
return
|
||||
repo_root = Path(__file__).resolve().parent.parent
|
||||
load_dotenv(repo_root / ".env", override=False)
|
||||
311
youdis/main.py
Normal file
311
youdis/main.py
Normal file
@@ -0,0 +1,311 @@
|
||||
"""FastAPI backend worker managing yt-dlp subprocess jobs and exposing job state."""
|
||||
|
||||
import asyncio
|
||||
from asyncio.subprocess import PIPE, STDOUT
|
||||
from collections import deque
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
from os import getenv
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
from uuid import uuid4
|
||||
|
||||
from fastapi import FastAPI, HTTPException
|
||||
|
||||
from .env import load_project_dotenv
|
||||
from .models import CurrentJobResponse, HealthResponse, JobRequest, JobStatus, VersionResponse
|
||||
|
||||
|
||||
load_project_dotenv()
|
||||
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
DEFAULT_CONFIG = REPO_ROOT / "default-yt-dlp.conf"
|
||||
VERSION_FILE = REPO_ROOT / "youdis-version.txt"
|
||||
YTDLP_EXECUTABLE = getenv("YOUDIS_YTDLP_EXECUTABLE", "yt-dlp")
|
||||
PREFERRED_CONFIG_ROOT = Path(getenv("YOUDIS_CONFIG_DIR", "/config"))
|
||||
PREFERRED_DOWNLOAD_ROOT = Path(getenv("YOUDIS_DOWNLOAD_DIR", "/downloads"))
|
||||
LOCAL_RUNTIME_ROOT = REPO_ROOT / ".runtime"
|
||||
FALLBACK_CONFIG_ROOT = LOCAL_RUNTIME_ROOT / "config"
|
||||
FALLBACK_DOWNLOAD_ROOT = LOCAL_RUNTIME_ROOT / "downloads"
|
||||
OUTPUT_TEMPLATE = "%(uploader)s/%(playlist_title)s/%(playlist_index)s%(playlist_index& - )s%(title)s.%(ext)s"
|
||||
|
||||
|
||||
@dataclass
|
||||
class ManagedJob:
|
||||
status: JobStatus
|
||||
process: asyncio.subprocess.Process | None = None
|
||||
task: asyncio.Task | None = None
|
||||
cancel_requested: bool = False
|
||||
output_lines: deque[str] = field(default_factory=lambda: deque(maxlen=25))
|
||||
|
||||
|
||||
app = FastAPI(title="youdis", version="2")
|
||||
job_lock = asyncio.Lock()
|
||||
active_job: ManagedJob | None = None
|
||||
last_job: JobStatus | None = None
|
||||
|
||||
|
||||
def now_utc() -> datetime:
|
||||
return datetime.now()
|
||||
|
||||
|
||||
def read_version() -> str:
|
||||
if VERSION_FILE.exists():
|
||||
return VERSION_FILE.read_text().strip()
|
||||
return "unknown"
|
||||
|
||||
|
||||
def ensure_writable_directory(preferred: Path, fallback: Path) -> Path:
|
||||
for candidate in (preferred, fallback):
|
||||
try:
|
||||
candidate.mkdir(parents=True, exist_ok=True)
|
||||
with tempfile.NamedTemporaryFile(dir=candidate, prefix=".youdis-write-", delete=True):
|
||||
pass
|
||||
return candidate
|
||||
except OSError:
|
||||
continue
|
||||
raise OSError(f"no writable runtime directory available for {preferred} or {fallback}")
|
||||
|
||||
|
||||
def resolve_runtime_paths() -> tuple[Path, Path]:
|
||||
config_root = ensure_writable_directory(PREFERRED_CONFIG_ROOT, FALLBACK_CONFIG_ROOT)
|
||||
download_root = ensure_writable_directory(PREFERRED_DOWNLOAD_ROOT, FALLBACK_DOWNLOAD_ROOT)
|
||||
return config_root, download_root
|
||||
|
||||
|
||||
def build_ytdlp_command(request: JobRequest, config_root: Path, download_root: Path) -> list[str]:
|
||||
return [
|
||||
YTDLP_EXECUTABLE,
|
||||
"--config-locations",
|
||||
str(DEFAULT_CONFIG),
|
||||
"--download-archive",
|
||||
str(config_root / "archive.txt"),
|
||||
"--output",
|
||||
str(download_root / OUTPUT_TEMPLATE),
|
||||
request.url,
|
||||
]
|
||||
|
||||
|
||||
def clone_status(status: JobStatus) -> JobStatus:
|
||||
return JobStatus(**status.model_dump())
|
||||
|
||||
|
||||
def update_status(job: ManagedJob, **changes: object) -> None:
|
||||
for key, value in changes.items():
|
||||
setattr(job.status, key, value)
|
||||
job.status.updated_at = now_utc()
|
||||
|
||||
|
||||
def classify_output_line(job: ManagedJob, line: str) -> None:
|
||||
if not line:
|
||||
return
|
||||
|
||||
job.output_lines.append(line)
|
||||
message = line.strip()
|
||||
if not message:
|
||||
return
|
||||
|
||||
lowered = message.lower()
|
||||
if "has already been recorded in the archive" in lowered:
|
||||
update_status(
|
||||
job,
|
||||
disposition="archive_hit",
|
||||
phase="downloading",
|
||||
message="already in archive",
|
||||
)
|
||||
return
|
||||
|
||||
if "[download]" in lowered:
|
||||
update_status(job, phase="downloading", message=message)
|
||||
if "destination:" in lowered:
|
||||
result_path = message.split(":", 1)[1].strip()
|
||||
update_status(job, result_path=result_path)
|
||||
return
|
||||
|
||||
if "merging formats into" in lowered:
|
||||
result_path = message.split("into", 1)[1].strip().strip('"')
|
||||
update_status(job, phase="postprocessing", message=message, result_path=result_path)
|
||||
return
|
||||
|
||||
update_status(job, message=message)
|
||||
|
||||
|
||||
async def finalize_job(job: ManagedJob, returncode: int) -> None:
|
||||
disposition = job.status.disposition
|
||||
if job.cancel_requested:
|
||||
state = "cancelled"
|
||||
message = "cancelled"
|
||||
elif returncode == 0 and disposition == "archive_hit":
|
||||
state = "completed"
|
||||
message = "already in archive"
|
||||
elif returncode == 0:
|
||||
state = "completed"
|
||||
message = job.status.message or "completed"
|
||||
else:
|
||||
state = "failed"
|
||||
message = job.status.message or f"yt-dlp exited with code {returncode}"
|
||||
|
||||
update_status(job, state=state, phase=None, returncode=returncode, message=message)
|
||||
|
||||
global active_job, last_job
|
||||
async with job_lock:
|
||||
if active_job is job:
|
||||
active_job = None
|
||||
last_job = clone_status(job.status)
|
||||
|
||||
|
||||
async def run_job(job: ManagedJob, request: JobRequest) -> None:
|
||||
update_status(
|
||||
job,
|
||||
state="running",
|
||||
phase="starting",
|
||||
message="starting yt-dlp",
|
||||
)
|
||||
|
||||
try:
|
||||
if not DEFAULT_CONFIG.exists():
|
||||
update_status(
|
||||
job,
|
||||
state="failed",
|
||||
phase=None,
|
||||
message=f"default config not found: {DEFAULT_CONFIG}",
|
||||
returncode=78,
|
||||
)
|
||||
await finalize_job(job, 78)
|
||||
return
|
||||
|
||||
config_root, download_root = resolve_runtime_paths()
|
||||
command = build_ytdlp_command(request, config_root, download_root)
|
||||
update_status(
|
||||
job,
|
||||
command=command,
|
||||
archive_path=str(config_root / "archive.txt"),
|
||||
result_path=str(download_root),
|
||||
)
|
||||
|
||||
process = await asyncio.create_subprocess_exec(
|
||||
*command,
|
||||
stdout=PIPE,
|
||||
stderr=STDOUT,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
update_status(
|
||||
job,
|
||||
state="failed",
|
||||
phase=None,
|
||||
message="yt-dlp executable not found",
|
||||
returncode=127,
|
||||
)
|
||||
await finalize_job(job, 127)
|
||||
return
|
||||
except OSError as exc:
|
||||
update_status(
|
||||
job,
|
||||
state="failed",
|
||||
phase=None,
|
||||
message=f"runtime path setup failed: {exc}",
|
||||
returncode=73,
|
||||
)
|
||||
await finalize_job(job, 73)
|
||||
return
|
||||
|
||||
try:
|
||||
job.process = process
|
||||
update_status(job, phase="running", message="yt-dlp running")
|
||||
|
||||
assert process.stdout is not None
|
||||
while True:
|
||||
line = await process.stdout.readline()
|
||||
if not line:
|
||||
break
|
||||
classify_output_line(job, line.decode(errors="replace").strip())
|
||||
|
||||
returncode = await process.wait()
|
||||
await finalize_job(job, returncode)
|
||||
except Exception as exc:
|
||||
update_status(
|
||||
job,
|
||||
state="failed",
|
||||
phase=None,
|
||||
message=f"backend runner error: {exc}",
|
||||
returncode=1,
|
||||
)
|
||||
await finalize_job(job, 1)
|
||||
|
||||
|
||||
async def create_job(request: JobRequest) -> JobStatus:
|
||||
global active_job
|
||||
async with job_lock:
|
||||
if active_job is not None:
|
||||
busy_job = active_job.status
|
||||
return JobStatus(
|
||||
job_id=busy_job.job_id,
|
||||
state="busy",
|
||||
url=request.url,
|
||||
message=f"busy with {busy_job.url}",
|
||||
requester_id=request.requester_id,
|
||||
requester_name=request.requester_name,
|
||||
origin=request.origin,
|
||||
)
|
||||
|
||||
status = JobStatus(
|
||||
job_id=str(uuid4()),
|
||||
state="accepted",
|
||||
url=request.url,
|
||||
message="accepted",
|
||||
phase="queued",
|
||||
requester_id=request.requester_id,
|
||||
requester_name=request.requester_name,
|
||||
origin=request.origin,
|
||||
)
|
||||
managed_job = ManagedJob(status=status)
|
||||
managed_job.task = asyncio.create_task(run_job(managed_job, request))
|
||||
active_job = managed_job
|
||||
return clone_status(status)
|
||||
|
||||
|
||||
@app.get("/health", response_model=HealthResponse)
|
||||
async def health() -> HealthResponse:
|
||||
return HealthResponse(status="ok")
|
||||
|
||||
|
||||
@app.get("/version", response_model=VersionResponse)
|
||||
async def version() -> VersionResponse:
|
||||
return VersionResponse(
|
||||
version=read_version(),
|
||||
active_job=active_job is not None,
|
||||
ytdlp_executable=YTDLP_EXECUTABLE,
|
||||
)
|
||||
|
||||
|
||||
@app.get("/jobs/current", response_model=CurrentJobResponse)
|
||||
async def current_job() -> CurrentJobResponse:
|
||||
async with job_lock:
|
||||
if active_job is not None:
|
||||
return CurrentJobResponse(active=True, job=clone_status(active_job.status))
|
||||
if last_job is not None:
|
||||
return CurrentJobResponse(active=False, job=clone_status(last_job))
|
||||
return CurrentJobResponse(active=False, job=None)
|
||||
|
||||
|
||||
@app.post("/jobs", response_model=JobStatus)
|
||||
async def submit_job(request: JobRequest) -> JobStatus:
|
||||
return await create_job(request)
|
||||
|
||||
|
||||
@app.post("/jobs/current/cancel", response_model=JobStatus)
|
||||
async def cancel_current_job() -> JobStatus:
|
||||
async with job_lock:
|
||||
if active_job is None:
|
||||
raise HTTPException(status_code=404, detail="no active job")
|
||||
job = active_job
|
||||
if job.process is None:
|
||||
update_status(job, message="cancel requested before yt-dlp started")
|
||||
job.cancel_requested = True
|
||||
return clone_status(job.status)
|
||||
|
||||
job.cancel_requested = True
|
||||
update_status(job, message="cancel requested", phase="running")
|
||||
job.process.terminate()
|
||||
return clone_status(job.status)
|
||||
48
youdis/models.py
Normal file
48
youdis/models.py
Normal file
@@ -0,0 +1,48 @@
|
||||
from datetime import datetime
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
JobState = Literal["accepted", "busy", "running", "completed", "failed", "cancelled"]
|
||||
|
||||
|
||||
class JobRequest(BaseModel):
|
||||
url: str
|
||||
requester_id: str | None = None
|
||||
requester_name: str | None = None
|
||||
origin: str | None = None
|
||||
requested_at: datetime | None = None
|
||||
|
||||
|
||||
class JobStatus(BaseModel):
|
||||
job_id: str
|
||||
state: JobState
|
||||
url: str
|
||||
message: str | None = None
|
||||
phase: str | None = None
|
||||
disposition: str | None = None
|
||||
requester_id: str | None = None
|
||||
requester_name: str | None = None
|
||||
origin: str | None = None
|
||||
result_path: str | None = None
|
||||
archive_path: str | None = None
|
||||
command: list[str] = Field(default_factory=list)
|
||||
returncode: int | None = None
|
||||
created_at: datetime = Field(default_factory=datetime.utcnow)
|
||||
updated_at: datetime = Field(default_factory=datetime.utcnow)
|
||||
|
||||
|
||||
class CurrentJobResponse(BaseModel):
|
||||
active: bool
|
||||
job: JobStatus | None = None
|
||||
|
||||
|
||||
class HealthResponse(BaseModel):
|
||||
status: Literal["ok"]
|
||||
|
||||
|
||||
class VersionResponse(BaseModel):
|
||||
version: str
|
||||
active_job: bool
|
||||
ytdlp_executable: str
|
||||
Reference in New Issue
Block a user