Download video(s) (first iteration) (#5)

* Updated package.json (and made an excuse to make a branch)

* Video filepath parser (#6)

* Restructured files; Added parser placeholder

* More restructuring

* Added basic parser for hydrating template strings

* Improved docs

* More docs

* Initial implementation of media profiles (#7)

* [WIP] Added basic video download method

* [WIP] Very-WIP first steps at parsing options and downloading

* Made my options safe by default and removed special safe versions

* Ran html generator for mediaprofile model - leaving as-is for now

* Addressed a bunch of TODO comments

* Add "channel" type Media Source (#8)

* [WIP] Working on fetching channel metadata in yt-dlp backend

* Finished first draft of methods to do with querying channels

* Renamed CommandRunnerMock to have a more descriptive name

* Ran the phx generator for the channel model

* Renamed Downloader namespace to MediaClient

* [WIP] saving before attempting LiveView

* LiveView did not work out but here's a working controller how about

* Index a channel (#9)

* Ran a MediaItem generator; Reformatted to my liking

* [WIP] added basic index function

* setup oban

* Added basic Oban job for indexing

* Added in workers for indexing; hooked them into record creation flow

* Added a task model with a phx generator

* Tied together tasks with jobs and channels

* Download indexed videos (#10)

* Clarified documentation

* more comments

* [WIP] hooked up basic video downloading; starting work on metadata

* Added metadata model and parsing

Adding the metadata model made me realize that, in many cases, yt-dlp
returns undesired input in stdout, breaking parsing. In order to get
the metadata model working, I had to change the way in which the app
interacts with yt-dlp. Now, output is written as a file to disk which
is immediately re-read and returned.

* Added tests for video download worker

* Hooked up video downloading to the channel indexing pipeline

* Adds tasks for media items

* Updated video metadata parser to extract the title

* Ran linting
This commit is contained in:
Kieran authored and GitHub committed 2024-01-30 20:15:59 -08:00
1 parent fee39151a8
commit a5e7c48f70
96 files changed
+9358 -158

No files matched your search

@@ -0,0 +1,110 @@
defmodule Pinchflat.Workers.MediaIndexingWorkerTest do
use Pinchflat.DataCase
import Mox
import Pinchflat.MediaFixtures
import Pinchflat.MediaSourceFixtures
alias Pinchflat.Tasks
alias Pinchflat.Workers.MediaIndexingWorker
alias Pinchflat.Workers.VideoDownloadWorker
setup :verify_on_exit!
describe "perform/1" do
test "it does not do any indexing if the channel shouldn't be indexed" do
expect(YtDlpRunnerMock, :run, 0, fn _url, _opts, _ot -> {:ok, ""} end)
channel = channel_fixture(index_frequency_minutes: -1)
perform_job(MediaIndexingWorker, %{id: channel.id})
end
test "it does not reschedule if the channel shouldn't be indexed" do
expect(YtDlpRunnerMock, :run, 0, fn _url, _opts, _ot -> {:ok, ""} end)
channel = channel_fixture(index_frequency_minutes: -1)
perform_job(MediaIndexingWorker, %{id: channel.id})
refute_enqueued(worker: MediaIndexingWorker, args: %{"id" => channel.id})
end
test "it indexes the channel if it should be indexed" do
expect(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, ""} end)
channel = channel_fixture(index_frequency_minutes: 10)
perform_job(MediaIndexingWorker, %{id: channel.id})
end
test "it kicks off a download job for each pending media item" do
expect(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, "video1"} end)
channel = channel_fixture(index_frequency_minutes: 10)
perform_job(MediaIndexingWorker, %{id: channel.id})
assert [_] = all_enqueued(worker: VideoDownloadWorker)
end
test "it starts a job for any pending media item even if it's from another run" do
expect(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, "video1"} end)
channel = channel_fixture(index_frequency_minutes: 10)
media_item_fixture(%{channel_id: channel.id, video_filepath: nil})
perform_job(MediaIndexingWorker, %{id: channel.id})
assert [_, _] = all_enqueued(worker: VideoDownloadWorker)
end
test "it does not kick off a job for media items that could not be saved" do
expect(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, "video1\nvideo1"} end)
channel = channel_fixture(index_frequency_minutes: 10)
perform_job(MediaIndexingWorker, %{id: channel.id})
# Only one job should be enqueued, since the second video is a duplicate
assert [_] = all_enqueued(worker: VideoDownloadWorker)
end
test "it reschedules the job based on the index frequency" do
expect(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, ""} end)
channel = channel_fixture(index_frequency_minutes: 10)
perform_job(MediaIndexingWorker, %{id: channel.id})
assert_enqueued(
worker: MediaIndexingWorker,
args: %{"id" => channel.id},
scheduled_at: now_plus(channel.index_frequency_minutes, :minutes)
)
end
test "it creates a task for the rescheduled job" do
expect(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, ""} end)
channel = channel_fixture(index_frequency_minutes: 10)
task_count_fetcher = fn -> Enum.count(Tasks.list_tasks()) end
assert_changed([from: 0, to: 1], task_count_fetcher, fn ->
perform_job(MediaIndexingWorker, %{id: channel.id})
end)
end
test "it creates the basic media_item records" do
expect(YtDlpRunnerMock, :run, fn _url, _opts, _ot -> {:ok, "video1\nvideo2"} end)
channel = channel_fixture(index_frequency_minutes: 10)
media_item_fetcher = fn ->
channel
|> Repo.preload(:media_items)
|> Map.get(:media_items)
|> Enum.map(fn media_item -> media_item.media_id end)
end
assert_changed([from: [], to: ["video1", "video2"]], media_item_fetcher, fn ->
perform_job(MediaIndexingWorker, %{id: channel.id})
end)
end
end
end