Merge pull request #7 from mbaraa/refactor/optimize-yt-dl

Feat: optimize yt download

Author: mbaraa

.dockerignore

@@ -13,3 +13,4 @@ views/**/*.txt
 docker-compose.yml
 .github
 README.md
+ytdl

.env.example

@@ -3,6 +3,7 @@ HOSTNAME="http://localhost:${PORT}"
 JWT_SECRET="spoikoninochi"
 
 YOUTUBE_SCAPER_URL="http://localhost:1234"
+YOUTUBE_DOWNLOADER_URL="http://localhost:4321"
 YOUTUBE_MUSIC_DOWNLOAD_PATH="."
 
 GOOGLE_APPLICATION_CREDENTIALS="./google-service-account.json"

Dockerfile

@@ -9,8 +9,6 @@ RUN go install github.com/a-h/templ/cmd/templ@latest &&\
 
 FROM alpine:latest as run
 
-RUN apk add yt-dlp
-
 WORKDIR /app
 COPY --from=build /app/dankmuzikk ./dankmuzikk
 COPY --from=build /app/run.sh ./run.sh

config/env.go

@@ -15,11 +15,13 @@ func initEnvVars() {
 		Hostname:  getEnv("HOSTNAME"),
 		JwtSecret: getEnv("JWT_SECRET"),
 		YouTube: struct {
-			ScraperUrl string
-			MusicDir   string
+			ScraperUrl    string
+			DownloaderUrl string
+			MusicDir      string
 		}{
-			ScraperUrl: getEnv("YOUTUBE_SCAPER_URL"),
-			MusicDir:   getEnv("YOUTUBE_MUSIC_DOWNLOAD_PATH"),
+			ScraperUrl:    getEnv("YOUTUBE_SCAPER_URL"),
+			DownloaderUrl: getEnv("YOUTUBE_DOWNLOADER_URL"),
+			MusicDir:      getEnv("YOUTUBE_MUSIC_DOWNLOAD_PATH"),
 		},
 		Google: struct {
 			ApiServiceAccount string
@@ -60,8 +62,9 @@ type config struct {
 	Hostname  string
 	JwtSecret string
 	YouTube   struct {
-		ScraperUrl string
-		MusicDir   string
+		ScraperUrl    string
+		DownloaderUrl string
+		MusicDir      string
 	}
 	Google struct {
 		ApiServiceAccount string

docker-compose-dev.yml

@@ -21,13 +21,26 @@ services:
     ports:
       - "1234:8080"
 
+  yt-dl:
+    container_name: "yt-dl"
+    build:
+      context: ./ytdl
+    image: "ytdl"
+    restart: "always"
+    ports:
+      - "4321:8000"
+    env_file:
+      - .env.docker
+    volumes:
+      - dankuploads-dir:/app/_serve
+
 volumes:
   dankuploads-dir:
     driver: local
     driver_opts:
       type: none
       o: bind
-      device: .
+      device: ./_serve/
   db-config:
     driver: local
     driver_opts:

docker-compose.yml

@@ -20,6 +20,7 @@ services:
     depends_on:
       - dank-db
       - yt-scraper
+      - yt-dl
 
   dank-db:
     image: "mariadb:10.8"
@@ -41,7 +42,23 @@ services:
     image: "baraamasri/yt-scrape"
     restart: "always"
     ports:
-      - "8080"
+      - 8080
+    networks:
+      - danknetwork
+
+  yt-dl:
+    container_name: "ytdl"
+    build:
+      context: ./ytdl
+    image: "ytdl"
+    restart: "always"
+    ports:
+      - 8000
+    stdin_open: true
+    env_file:
+      - .env.docker
+    volumes:
+      - dankuploads-dir:/app/_serve
     networks:
       - danknetwork
 
@@ -54,7 +71,7 @@ volumes:
     driver_opts:
       type: none
       o: bind
-      device: .
+      device: ./_serve/
   db-config:
     driver: local
     driver_opts:

services/youtube/download/download.go

@@ -8,8 +8,8 @@ import (
 	"dankmuzikk/models"
 	"errors"
 	"fmt"
+	"net/http"
 	"os"
-	"os/exec"
 )
 
 type DownloadService struct {
@@ -24,19 +24,18 @@ func NewDownloadService(repo db.CRUDRepo[models.Song]) *DownloadService {
 // YOUTUBE_MUSIC_DOWNLOAD_PATH, where the file name will be <video_id.mp3> to be served under /music/{id}
 // and retuens an occurring error
 func (d *DownloadService) DownloadYoutubeSong(req entities.SongDownloadRequest) error {
-	log.Infoln(req)
 	path := fmt.Sprintf("%s/%s.mp3", config.Env().YouTube.MusicDir, req.Id)
 	if _, err := os.Stat(path); err == nil {
 		log.Infof("The song with id %s is already downloaded\n", req.Id)
 		return nil
 	}
-	// TODO: write a downloader instead of using this sub process command thingy.
-	cmd := exec.Command("yt-dlp", "-x", "--audio-format", "mp3", "--audio-quality", "best", "-o", path, "https://www.youtube.com/watch?v="+req.Id)
-	cmd.Stdout = os.Stdout
-	cmd.Stderr = os.Stderr
-	err := cmd.Run()
+
+	resp, err := http.Get(fmt.Sprintf("%s/download/%s", config.Env().YouTube.DownloaderUrl, req.Id))
 	if err != nil {
-		return errors.New("Download failed:" + err.Error())
+		return err
+	}
+	if resp.StatusCode != http.StatusOK {
+		return errors.New("something went wrong when downloading a song; id: " + req.Id)
 	}
 
 	err = d.repo.Add(&models.Song{

ytdl/.dockerinore

@@ -0,0 +1,3 @@
+venv
+.*
+__pycache__

ytdl/.gitignore

@@ -0,0 +1,161 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+

ytdl/Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.11-slim AS build
+
+WORKDIR /app
+
+ADD requirements.txt /tmp
+RUN pip install --upgrade pip && \
+    pip install -r /tmp/requirements.txt
+COPY . /app
+
+
+FROM python:3.11-slim
+
+RUN apt-get update -y &&\
+    apt-get install ffmpeg -y
+
+WORKDIR /app
+
+COPY --from=build /usr/local/lib/python3.11/site-packages  /usr/local/lib/python3.11/site-packages
+COPY --from=build /usr/local/bin/ /usr/local/bin/
+COPY --from=build /app .
+
+EXPOSE 8000
+CMD [ "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000" ]
+