@jakende/media-info-cli 0.1.0

package/media_tui.py

@@ -0,0 +1,8 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+from media_information_download.tui import main
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/package.json

@@ -0,0 +1,36 @@
+{
+  "name": "@jakende/media-info-cli",
+  "version": "0.1.0",
+  "description": "Terminal app for downloading media from YouTube or RSS feeds, converting to MP3, and generating Whisper transcripts.",
+  "license": "UNLICENSED",
+  "bin": {
+    "media-information-download": "bin/media-information-download.js",
+    "media-info-download": "bin/media-information-download.js"
+  },
+  "files": [
+    "bin/",
+    "media_information_download/**/*.py",
+    "media_tui.py",
+    "youtube_download.py",
+    "youtube_download_transcribe.py",
+    "requirements.txt",
+    "requirements-transcribe.txt",
+    "pyproject.toml",
+    "README.md"
+  ],
+  "scripts": {
+    "test": "python3 -m unittest discover -s tests",
+    "pack:check": "npm pack --dry-run"
+  },
+  "engines": {
+    "node": ">=18"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/Jakende/media-information-download.git"
+  },
+  "bugs": {
+    "url": "https://github.com/Jakende/media-information-download/issues"
+  },
+  "homepage": "https://github.com/Jakende/media-information-download#readme"
+}

package/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["setuptools>=69"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "media-information-download"
+version = "0.1.0"
+description = "Terminal app for downloading media from YouTube or RSS feeds, converting to MP3, and generating Whisper transcripts."
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+  "yt-dlp>=2024.1.1",
+]
+
+[project.optional-dependencies]
+transcribe = [
+  "openai-whisper>=20231117",
+  "torch>=2.2.0",
+]
+
+[project.scripts]
+media-information-download = "media_information_download.tui:main"
+media-info-download = "media_information_download.tui:main"
+
+[tool.setuptools.packages.find]
+include = ["media_information_download*"]

package/requirements-transcribe.txt

@@ -0,0 +1,3 @@
+yt-dlp>=2024.1.1
+openai-whisper>=20231117
+torch>=2.2.0

package/requirements.txt

@@ -0,0 +1 @@
+yt-dlp>=2024.1.1

package/youtube_download.py

@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import sys
+
+from media_information_download.config import get_output_dir
+from media_information_download.pipeline import MediaPipeline, ProcessOptions
+from media_information_download.sources.youtube import parse_urls, validate_url
+
+
+def print_error(message: str) -> None:
+    print(f"[ERROR] {message}", file=sys.stderr)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Download YouTube video and extract MP3.")
+    parser.add_argument(
+        "--url",
+        help="One or more YouTube URLs, comma-separated. If omitted, prompts interactively.",
+        default="",
+    )
+    parser.add_argument(
+        "--delay",
+        type=float,
+        default=2.0,
+        help="Delay in seconds between batch entries. Default: 2.0",
+    )
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = parse_args()
+    raw_urls = args.url.strip()
+    if not raw_urls:
+        if sys.stdin.isatty():
+            raw_urls = input("YouTube URL(s), comma-separated: ").strip()
+        else:
+            print_error("No URL provided. Use: python3 youtube_download.py --url <URL1,URL2,...>")
+            return 1
+
+    urls = parse_urls(raw_urls)
+    invalid_urls = [url for url in urls if not validate_url(url)]
+    if not urls or invalid_urls:
+        for invalid_url in invalid_urls:
+            print_error(f"Invalid YouTube URL: {invalid_url}")
+        return 1
+
+    pipeline = MediaPipeline(progress=lambda message: print(message, flush=True))
+    results = pipeline.process(
+        ProcessOptions(
+            source_type="youtube",
+            raw_input=raw_urls,
+            output_dir=get_output_dir(),
+            transcribe=False,
+            delay_seconds=args.delay,
+        )
+    )
+    return 1 if any(result.error for result in results) else 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

package/youtube_download_transcribe.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import sys
+
+from media_information_download.config import get_model_name, get_output_dir, get_whisper_language
+from media_information_download.pipeline import MediaPipeline, ProcessOptions
+from media_information_download.sources.youtube import parse_urls, validate_url
+
+
+def print_error(message: str) -> None:
+    print(f"[ERROR] {message}", file=sys.stderr)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Download YouTube video, extract MP3, transcribe to Markdown.")
+    parser.add_argument(
+        "--url",
+        default="",
+        help="One or more YouTube URLs, comma-separated.",
+    )
+    parser.add_argument(
+        "--delay",
+        type=float,
+        default=2.0,
+        help="Delay in seconds between batch entries. Default: 2.0",
+    )
+    parser.add_argument("--model", default="", help="Whisper model name. Defaults to WHISPER_MODEL or large.")
+    parser.add_argument("--language", default=None, help="Optional Whisper language code. Defaults to auto.")
+    return parser.parse_args()
+
+
+def main() -> int:
+    args = parse_args()
+    raw_urls = args.url.strip()
+    if not raw_urls:
+        if sys.stdin.isatty():
+            raw_urls = input("YouTube URL(s), comma-separated: ").strip()
+        else:
+            print_error("No URL provided. Use: python3 youtube_download_transcribe.py --url <URL1,URL2,...>")
+            return 1
+
+    urls = parse_urls(raw_urls)
+    invalid_urls = [url for url in urls if not validate_url(url)]
+    if not urls or invalid_urls:
+        for invalid_url in invalid_urls:
+            print_error(f"Invalid YouTube URL: {invalid_url}")
+        return 1
+
+    pipeline = MediaPipeline(progress=lambda message: print(message, flush=True))
+    results = pipeline.process(
+        ProcessOptions(
+            source_type="youtube",
+            raw_input=raw_urls,
+            output_dir=get_output_dir(),
+            transcribe=True,
+            model_name=args.model or get_model_name(),
+            language=args.language if args.language is not None else get_whisper_language(),
+            delay_seconds=args.delay,
+        )
+    )
+    return 1 if any(result.error for result in results) else 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())