youtube-to-docs 0.0.1__tar.gz

youtube_to_docs-0.0.1/.github/workflows/ci.yml

@@ -0,0 +1,38 @@
+name: CI
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+
+    - name: Set up Python
+      run: uv python install
+
+    - name: Create virtual environment
+      run: uv venv
+
+    - name: Install dependencies
+      run: uv pip install -r requirements.txt
+
+    - name: Ruff Lint
+      run: uv tool run ruff check .
+
+    - name: Ruff Format
+      run: uv tool run ruff format --check .
+
+    - name: Type Check
+      run: uv tool run ty check
+
+    - name: Run Tests
+      run: uv run --with-requirements requirements.txt pytest

youtube_to_docs-0.0.1/.gitignore

@@ -0,0 +1,215 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+youtube-docs.csv
+transcript-files/
+summary-files/
+
+implementation_plan.md
+
+uv.lock

youtube_to_docs-0.0.1/.pre-commit-config.yaml

@@ -0,0 +1,30 @@
+repos:
+  - repo: local
+    hooks:
+      - id: ruff-format
+        name: Ruff Format
+        entry: uv tool run ruff format
+        language: system
+        types: [python]
+        args: ["."]
+
+      - id: ruff-check
+        name: Ruff Lint
+        entry: uv tool run ruff check
+        language: system
+        types: [python]
+        args: ["--fix", "."]
+
+      - id: ty-check
+        name: Type Check (Ty)
+        entry: uv tool run ty check
+        language: system
+        types: [python]
+        pass_filenames: false
+
+      - id: pytest
+        name: Run Tests
+        entry: uv run --with-requirements requirements.txt pytest
+        language: system
+        types: [python]
+        pass_filenames: false

youtube_to_docs-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 DoIT - Artifical Intelligence
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

youtube_to_docs-0.0.1/PKG-INFO

@@ -0,0 +1,23 @@
+Metadata-Version: 2.4
+Name: youtube-to-docs
+Version: 0.0.1
+Summary: Convert YouTube videos to docs/sheets for discoverability
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: google-auth>=2.45.0
+Requires-Dist: google-genai>=1.56.0
+Requires-Dist: google-api-python-client>=2.187.0
+Requires-Dist: isodate>=0.7.2
+Requires-Dist: openai>=1.56.0
+Requires-Dist: polars>=1.36.1
+Requires-Dist: requests>=2.32.5
+Requires-Dist: youtube-transcript-api>=1.2.3
+Dynamic: license-file
+
+# youtube-to-docs
+Convert YouTube videos to docs/sheets for discoverability.
+
+
+
+*Created with the help of AI. All artifacts have been checked and work as expected.*

youtube_to_docs-0.0.1/README.md

@@ -0,0 +1,6 @@
+# youtube-to-docs
+Convert YouTube videos to docs/sheets for discoverability.
+
+
+
+*Created with the help of AI. All artifacts have been checked and work as expected.*

youtube_to_docs-0.0.1/docs/development.md

@@ -0,0 +1,102 @@
+# Development Guide
+
+## Prerequisites
+
+- Python 3.14 or higher
+- `uv` (recommended) or `pip`
+
+## Installation
+
+1. Install dependencies:
+   ```bash
+   uv pip install -r requirements.txt
+   # OR
+   pip install -r requirements.txt
+   ```
+
+## Running Tests
+
+We use `pytest` for testing.
+
+### Using `uv` (Recommended)
+
+To run tests with all dependencies automatically handled:
+
+```bash
+uv run --with-requirements requirements.txt pytest
+```
+
+## Project Structure
+
+- `main.py`: Main application script.
+- `tests/`: Directory containing test files.
+- `requirements.txt`: Python package dependencies.
+
+## Tooling
+
+This project uses modern Python tooling for code quality:
+
+- **Ruff**: For linting and code formatting.
+- **Ty**: For static type checking.
+
+These tools are configured in `pyproject.toml`.
+
+### Running Ruff
+
+To check for linting errors:
+
+```bash
+uv tool run ruff check .
+```
+
+To fix fixable linting errors automatically:
+
+```bash
+uv tool run ruff check --fix .
+```
+
+To format the code:
+
+```bash
+uv tool run ruff format .
+```
+
+### Running Ty (Type Checking)
+
+To run type checks:
+
+```bash
+uv tool run ty check
+```
+
+### Pre-commit
+
+To run pre-commit hook:
+
+```bash
+uv tool run pre-commit run --all-files
+```   
+
+
+## Release to PyPI
+
+To publish a new version of the package to PyPI, follow these steps:
+
+1.  **Build the package**:
+    This will create a `dist/` directory with the distribution files.
+    ```bash
+    uv tool run --from build pyproject-build
+    ```
+
+2.  **Upload to PyPI**:
+    Use `twine` to upload the distribution files. 
+    
+    If your `.pypirc` is already configured with your API key:
+    ```bash
+    uv tool run twine upload --repository testpypi dist/*
+    ```
+
+    Or, to explicitly use your `PYPI_API_KEY` environment variable:
+    ```bash
+    uv tool run twine upload -u __token__ -p $env:PYPI_API_KEY dist/*
+    ```

youtube_to_docs-0.0.1/pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "youtube-to-docs"
+version = "0.0.1"
+description = "Convert YouTube videos to docs/sheets for discoverability"
+readme = "README.md"
+requires-python = ">=3.14"
+dependencies = [
+    "google-auth>=2.45.0",
+    "google-genai>=1.56.0",
+    "google-api-python-client>=2.187.0",
+    "isodate>=0.7.2",
+    "openai>=1.56.0",
+    "polars>=1.36.1",
+    "requests>=2.32.5",
+    "youtube-transcript-api>=1.2.3",
+]
+
+[tool.setuptools.packages.find]
+include = ["youtube_to_docs*"]
+exclude = ["tests*", "docs*", "summary-files*", "transcript-files*"]
+
+[tool.ruff]
+# Match the project's Python version requirement
+target-version = "py314"
+line-length = 88
+
+[tool.ruff.lint]
+# Enable Pyflakes (`F`), pycodestyle (`E`, `W`), and isort (`I`)
+select = ["E", "F", "I", "W"]
+ignore = []
+
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+unfixable = []
+
+[tool.ruff.format]
+# Use double quotes for strings.
+quote-style = "double"
+# Indent with spaces, rather than tabs.
+indent-style = "space"
+# Respect magic trailing commas.
+skip-magic-trailing-comma = false
+# Automatically detect the appropriate line ending.
+line-ending = "auto"
+
+[tool.ty.environment]
+# Target Python 3.14 to match project requirements
+python-version = "3.14"

youtube_to_docs-0.0.1/requirements.txt

@@ -0,0 +1,9 @@
+google-auth>=2.45.0
+google-genai>=1.56.0
+google-api-python-client>=2.187.0
+isodate>=0.7.2
+openai>=1.56.0
+polars>=1.36.1
+requests>=2.32.5
+youtube-transcript-api>=1.2.3
+pytest

youtube_to_docs-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

youtube_to_docs-0.0.1/tests/test_main.py

@@ -0,0 +1,196 @@
+import os
+import unittest
+from unittest.mock import MagicMock, patch
+
+from youtube_to_docs import main
+
+
+class TestYoutubeToDocs(unittest.TestCase):
+    def setUp(self):
+        # Mock environment variables
+        self.env_patcher = patch.dict(
+            os.environ,
+            {
+                "YOUTUBE_DATA_API_KEY": "fake_youtube_key",
+                "GEMINI_API_KEY": "fake_gemini_key",
+                "PROJECT_ID": "fake_project_id",
+                "AWS_BEARER_TOKEN_BEDROCK": "fake_bedrock_token",
+                "AZURE_FOUNDRY_ENDPOINT": "https://fake.openai.azure.com/",
+                "AZURE_FOUNDRY_API_KEY": "fake_foundry_key",
+            },
+        )
+        self.env_patcher.start()
+
+    def tearDown(self):
+        self.env_patcher.stop()
+
+    @patch("youtube_to_docs.main.build")
+    def test_get_youtube_service(self, mock_build):
+        service = main.get_youtube_service()
+        self.assertIsNotNone(service)
+        mock_build.assert_called_with("youtube", "v3", developerKey="fake_youtube_key")
+
+    def test_get_youtube_service_no_key(self):
+        with patch.dict(os.environ, {}, clear=True):
+            service = main.get_youtube_service()
+            self.assertIsNone(service)
+
+    def test_resolve_video_ids_single(self):
+        ids = main.resolve_video_ids("KuPc06JgI_A", None)
+        self.assertEqual(ids, ["KuPc06JgI_A"])
+
+    def test_resolve_video_ids_list(self):
+        ids = main.resolve_video_ids("KuPc06JgI_A,GalhDyf3F8g", None)
+        self.assertEqual(ids, ["KuPc06JgI_A", "GalhDyf3F8g"])
+
+    def test_resolve_video_ids_playlist_no_service(self):
+        with self.assertRaises(SystemExit):
+            main.resolve_video_ids("PL8ZxoInteClyHaiReuOHpv6Z4SPrXtYtW", None)
+
+    @patch("youtube_to_docs.main.build")
+    def test_resolve_video_ids_playlist(self, mock_build):
+        mock_service = MagicMock()
+        mock_request = MagicMock()
+        mock_response = {
+            "items": [
+                {"contentDetails": {"videoId": "vid1"}},
+                {"contentDetails": {"videoId": "vid2"}},
+            ]
+        }
+        mock_request.execute.return_value = mock_response
+        # Mock list_next to return None to stop iteration
+        mock_service.playlistItems().list.return_value = mock_request
+        mock_service.playlistItems().list_next.return_value = None
+
+        ids = main.resolve_video_ids("PL123", mock_service)
+        self.assertEqual(ids, ["vid1", "vid2"])
+
+    @patch("youtube_to_docs.main.build")
+    def test_resolve_video_ids_channel_handle(self, mock_build):
+        mock_service = MagicMock()
+
+        # Mock channel list response
+        mock_channel_req = MagicMock()
+        mock_channel_resp = {
+            "items": [{"contentDetails": {"relatedPlaylists": {"uploads": "UU123"}}}]
+        }
+        mock_channel_req.execute.return_value = mock_channel_resp
+        mock_service.channels().list.return_value = mock_channel_req
+
+        # Mock playlist items response (since it calls resolve_video_ids internally
+        # with the playlist ID)
+        mock_playlist_req = MagicMock()
+        mock_playlist_resp = {
+            "items": [{"contentDetails": {"videoId": "vid_from_channel"}}]
+        }
+        mock_playlist_req.execute.return_value = mock_playlist_resp
+        mock_service.playlistItems().list.return_value = mock_playlist_req
+        mock_service.playlistItems().list_next.return_value = None
+
+        ids = main.resolve_video_ids("@channel", mock_service)
+        self.assertEqual(ids, ["vid_from_channel"])
+
+    def test_get_video_details_none(self):
+        details = main.get_video_details("vid1", None)
+        self.assertEqual(
+            details, ("", "", "", "", "", "", "https://www.youtube.com/watch?v=vid1")
+        )
+
+    def test_get_video_details_success(self):
+        mock_service = MagicMock()
+        mock_req = MagicMock()
+        mock_resp = {
+            "items": [
+                {
+                    "snippet": {
+                        "title": "Test Video",
+                        "description": "Desc",
+                        "publishedAt": "2023-01-01",
+                        "channelTitle": "Test Channel",
+                        "tags": ["tag1", "tag2"],
+                    },
+                    "contentDetails": {"duration": "PT1M10S"},
+                }
+            ]
+        }
+        mock_req.execute.return_value = mock_resp
+        mock_service.videos().list.return_value = mock_req
+
+        details = main.get_video_details("vid1", mock_service)
+        self.assertIsNotNone(details)
+        assert details is not None
+        self.assertEqual(details[0], "Test Video")
+        self.assertEqual(details[5], "0:01:10")  # Duration
+
+    @patch("youtube_to_docs.main.ytt_api")
+    def test_fetch_transcript(self, mock_ytt_api):
+        mock_transcript_obj = MagicMock()
+        mock_transcript_obj.to_raw_data.return_value = [
+            {"text": "Hello"},
+            {"text": "world"},
+        ]
+        mock_ytt_api.fetch.return_value = mock_transcript_obj
+
+        text = main.fetch_transcript("vid1")
+        self.assertEqual(text, "Hello world")
+
+    @patch("youtube_to_docs.main.ytt_api")
+    def test_fetch_transcript_error(self, mock_ytt_api):
+        mock_ytt_api.fetch.side_effect = Exception("Transcript disabled")
+        text = main.fetch_transcript("vid1")
+        self.assertIsNone(text)
+
+    @patch("youtube_to_docs.main.genai.Client")
+    def test_generate_summary_gemini(self, mock_client_cls):
+        mock_client = mock_client_cls.return_value
+        mock_resp = MagicMock()
+        mock_resp.text = "Gemini Summary"
+        mock_client.models.generate_content.return_value = mock_resp
+
+        summary = main.generate_summary("gemini-pro", "transcript", "Title", "url")
+        self.assertEqual(summary, "Gemini Summary")
+
+    @patch("youtube_to_docs.main.requests.post")
+    @patch("youtube_to_docs.main.google.auth.default")
+    def test_generate_summary_vertex(self, mock_auth, mock_post):
+        mock_creds = MagicMock()
+        mock_creds.token = "fake_token"
+        mock_auth.return_value = (mock_creds, "proj")
+
+        mock_resp = MagicMock()
+        mock_resp.status_code = 200
+        mock_resp.json.return_value = {"content": [{"text": "Vertex Summary"}]}
+        mock_post.return_value = mock_resp
+
+        summary = main.generate_summary(
+            "vertex-claude-3-5", "transcript", "Title", "url"
+        )
+        self.assertEqual(summary, "Vertex Summary")
+
+    @patch("youtube_to_docs.main.requests.post")
+    def test_generate_summary_bedrock(self, mock_post):
+        mock_resp = MagicMock()
+        mock_resp.status_code = 200
+        mock_resp.json.return_value = {
+            "output": {"message": {"content": [{"text": "Bedrock Summary"}]}}
+        }
+        mock_post.return_value = mock_resp
+
+        summary = main.generate_summary(
+            "bedrock-claude-3-5", "transcript", "Title", "url"
+        )
+        self.assertEqual(summary, "Bedrock Summary")
+
+    @patch("youtube_to_docs.main.OpenAI")
+    def test_generate_summary_foundry(self, mock_openai):
+        mock_client = mock_openai.return_value
+        mock_completion = MagicMock()
+        mock_completion.choices[0].message.content = "Foundry Summary"
+        mock_client.chat.completions.create.return_value = mock_completion
+
+        summary = main.generate_summary("foundry-gpt-4", "transcript", "Title", "url")
+        self.assertEqual(summary, "Foundry Summary")
+
+
+if __name__ == "__main__":
+    unittest.main()

youtube_to_docs-0.0.1/youtube_to_docs/main.py

@@ -0,0 +1,506 @@
+# /// script
+# requires-python = ">=3.14"
+# dependencies = [
+#     "google-auth>=2.45.0",
+#     "google-genai>=1.56.0",
+#     "google-api-python-client>=2.187.0",
+#     "isodate>=0.7.2",
+#     "openai>=1.56.0",
+#     "polars>=1.36.1",
+#     "requests>=2.32.5",
+#     "youtube-transcript-api>=1.2.3"
+# ]
+# ///
+#
+# Run as:
+# uv run https://raw.githubusercontent.com/DoIT-Artifical-Intelligence/youtube-to-docs/refs/heads/main/youtube_to_docs/main.py --model gemini-3-flash-preview  # noqa
+# To test locally run one of:
+# uv run youtube_to_docs/main.py --model gemini-3-flash-preview
+# uv run youtube_to_docs/main.py --model vertex-claude-haiku-4-5@20251001
+# uv run youtube_to_docs/main.py --model bedrock-claude-haiku-4-5-20251001-v1
+# uv run youtube_to_docs/main.py --model bedrock-nova-2-lite-v1
+# uv run youtube_to_docs/main.py --model bedrock-claude-haiku-4-5-20251001
+# uv run youtube_to_docs/main.py --model foundry-gpt-5-mini
+
+
+import argparse
+import os
+import re
+import sys
+import time
+from typing import Any, List, Optional, Tuple, cast
+
+import google.auth
+import isodate
+import polars as pl
+import requests
+from google import genai
+from google.auth.transport.requests import Request as GoogleAuthRequest
+from google.genai import types
+from googleapiclient.discovery import Resource, build
+from openai import OpenAI
+from youtube_transcript_api import YouTubeTranscriptApi
+
+# Global instance for transcript API
+ytt_api = YouTubeTranscriptApi()
+
+
+def get_youtube_service() -> Optional[Resource]:
+    """Builds and returns the YouTube Data API service."""
+    try:
+        api_key = os.environ["YOUTUBE_DATA_API_KEY"]
+        return build("youtube", "v3", developerKey=api_key)
+    except KeyError:
+        print(
+            "Warning: YOUTUBE_DATA_API_KEY not found. Playlist and Channel expansion "
+            "will fail."
+        )
+        return None
+
+
+def resolve_video_ids(
+    video_id_input: str, youtube_service: Optional[Resource]
+) -> List[str]:
+    """
+    Resolves the input (video ID, list, playlist, or channel handle)
+    into a list of video IDs.
+    """
+    video_ids: List[str] = []
+
+    # Handle Channel Handles (e.g. @channelname)
+    if video_id_input.startswith("@"):
+        if not youtube_service:
+            print("Error: YOUTUBE_DATA_API_KEY is required to resolve channel handles.")
+            sys.exit(1)
+        service = cast(Any, youtube_service)
+        print(f"Resolving channel handle: {video_id_input}...")
+        request = service.channels().list(
+            part="contentDetails", forHandle=video_id_input
+        )
+        response = request.execute()
+        if not response["items"]:
+            print(f"Error: No channel found for handle {video_id_input}")
+            sys.exit(1)
+        # Get the 'uploads' playlist ID from the channel details
+        video_id_input = response["items"][0]["contentDetails"]["relatedPlaylists"][
+            "uploads"
+        ]
+        print(f"Found uploads playlist: {video_id_input}")
+
+    # Single video (standard ID length is 11)
+    if len(video_id_input) == 11 and "," not in video_id_input:
+        video_ids = [video_id_input]
+    # List of videos
+    elif "," in video_id_input:
+        video_ids = video_id_input.split(",")
+    # Playlist (Standard 'PL' or Uploads 'UU')
+    elif video_id_input.startswith("PL") or video_id_input.startswith("UU"):
+        if not youtube_service:
+            print("Error: YOUTUBE_DATA_API_KEY is required for playlists.")
+            sys.exit(1)
+        service = cast(Any, youtube_service)
+        request = service.playlistItems().list(
+            part="contentDetails", playlistId=video_id_input, maxResults=50
+        )
+        while request:
+            response = request.execute()
+            for item in response["items"]:
+                video_ids.append(item["contentDetails"]["videoId"])
+            request = service.playlistItems().list_next(request, response)
+
+    return video_ids
+
+
+def get_video_details(
+    video_id: str, youtube_service: Optional[Resource]
+) -> Optional[Tuple[str, str, str, str, str, str, str]]:
+    """
+    Fetches video metadata from YouTube Data API.
+    Returns a tuple of (video_title, description, publishedAt,
+    channelTitle, tags, video_duration, url).
+    """
+    url = f"https://www.youtube.com/watch?v={video_id}"
+
+    if not youtube_service:
+        return "", "", "", "", "", "", url
+
+    service = cast(Any, youtube_service)
+    request = service.videos().list(part="snippet,contentDetails", id=video_id)
+    response = request.execute()
+
+    if response["items"]:
+        snippet = response["items"][0]["snippet"]
+        video_title: str = snippet["title"]
+        description: str = snippet["description"]
+        publishedAt: str = snippet["publishedAt"]
+        channelTitle: str = snippet["channelTitle"]
+        tags: str = ", ".join(snippet.get("tags", []))
+        iso_duration: str = response["items"][0]["contentDetails"]["duration"]
+        video_duration: str = str(isodate.parse_duration(iso_duration))
+        return (
+            video_title,
+            description,
+            publishedAt,
+            channelTitle,
+            tags,
+            video_duration,
+            url,
+        )
+    else:
+        print(f"Warning: No details found for video ID {video_id}")
+        return None
+
+
+def fetch_transcript(video_id: str) -> Optional[str]:
+    """Fetches the transcript for a given video ID."""
+    try:
+        transcript_obj = ytt_api.fetch(video_id, languages=("en", "en-US"))
+        transcript_data = transcript_obj.to_raw_data()
+        transcript = " ".join([t["text"] for t in transcript_data])
+        return transcript
+    except Exception as e:
+        print(f"Error fetching transcript for {video_id}: {e}")
+        return None
+
+
+def generate_summary(
+    model_name: str, transcript: str, video_title: str, url: str
+) -> str:
+    """Generates a summary using the specified LLM provider."""
+    summary_text = ""
+    prompt = (
+        f"I have included a transcript for {url} ({video_title})"
+        "\n\n"
+        "Can you please summarize this?"
+        "\n\n"
+        f"{transcript}"
+    )
+
+    if model_name.startswith("gemini"):
+        try:
+            GEMINI_API_KEY = os.environ["GEMINI_API_KEY"]
+            google_genai_client = genai.Client(api_key=GEMINI_API_KEY)
+            response = google_genai_client.models.generate_content(
+                model=model_name,
+                contents=[
+                    types.Content(
+                        role="user", parts=[types.Part.from_text(text=prompt)]
+                    )
+                ],
+            )
+            summary_text = response.text or ""
+        except KeyError:
+            print("Error: GEMINI_API_KEY not found")
+            summary_text = "Error: GEMINI_API_KEY not found"
+        except Exception as e:
+            print(f"Gemini API Error: {e}")
+            summary_text = f"Error: {e}"
+
+    elif model_name.startswith("vertex"):
+        try:
+            vertex_project_id = os.environ["PROJECT_ID"]
+            vertex_credentials, _ = google.auth.default()
+            actual_model_name = model_name.replace("vertex-", "")
+
+            if actual_model_name.startswith("claude"):
+                if vertex_credentials.expired:
+                    vertex_credentials.refresh(GoogleAuthRequest())
+                access_token = vertex_credentials.token
+                endpoint = (
+                    "https://us-east5-aiplatform.googleapis.com/v1/"
+                    f"projects/{vertex_project_id}/locations/us-east5/"
+                    f"publishers/anthropic/models/{actual_model_name}:rawPredict"
+                )
+                headers = {
+                    "Authorization": f"Bearer {access_token}",
+                    "Content-Type": "application/json; charset=utf-8",
+                }
+                payload = {
+                    "anthropic_version": "vertex-2023-10-16",
+                    "messages": [{"role": "user", "content": prompt}],
+                    "max_tokens": 64_000,
+                    "stream": False,
+                }
+                response = requests.post(endpoint, headers=headers, json=payload)
+                if response.status_code == 200:
+                    response_json = response.json()
+                    content_blocks = response_json.get("content", [])
+                    if (
+                        content_blocks
+                        and isinstance(content_blocks, list)
+                        and "text" in content_blocks[0]
+                    ):
+                        summary_text = content_blocks[0]["text"]
+                    else:
+                        summary_text = f"Unexpected response format: {response.text}"
+                else:
+                    summary_text = (
+                        f"Vertex API Error {response.status_code}: {response.text}"
+                    )
+                    print(summary_text)
+
+        except KeyError:
+            print(
+                "Error: PROJECT_ID environment variable required for GCPVertex models."
+            )
+            summary_text = "Error: PROJECT_ID required"
+        except Exception as e:
+            print(f"Vertex Request Error: {e}")
+            summary_text = f"Error: {e}"
+
+    elif model_name.startswith("bedrock"):
+        try:
+            aws_bearer_token_bedrock = os.environ["AWS_BEARER_TOKEN_BEDROCK"]
+            actual_model_name = model_name.replace("bedrock-", "")
+            if actual_model_name.startswith("claude"):
+                actual_model_name = f"us.anthropic.{actual_model_name}:0"
+            elif actual_model_name.startswith("nova"):
+                actual_model_name = f"us.amazon.{actual_model_name}:0"
+
+            endpoint = (
+                f"https://bedrock-runtime.us-east-1.amazonaws.com/model/"
+                f"{actual_model_name}/converse"
+            )
+            response = requests.post(
+                endpoint,
+                headers={
+                    "Content-Type": "application/json",
+                    "Authorization": f"Bearer {aws_bearer_token_bedrock}",
+                },
+                json={
+                    "messages": [
+                        {
+                            "role": "user",
+                            "content": [{"text": prompt}],
+                        }
+                    ],
+                    "max_tokens": 64_000,
+                },
+            )
+            if response.status_code == 200:
+                response_json = response.json()
+                print(response_json)
+                try:
+                    content_blocks = response_json["output"]["message"]["content"]
+                    if (
+                        content_blocks
+                        and isinstance(content_blocks, list)
+                        and "text" in content_blocks[0]
+                    ):
+                        summary_text = content_blocks[0]["text"]
+                    else:
+                        summary_text = f"Unexpected content format: {response_json}"
+                except KeyError:
+                    summary_text = f"Unexpected response structure: {response_json}"
+            else:
+                summary_text = (
+                    f"Bedrock API Error {response.status_code}: {response.text}"
+                )
+                print(summary_text)
+        except KeyError:
+            print(
+                "Error: AWS_BEARER_TOKEN_BEDROCK environment variable required for "
+                "AWS Bedrock models."
+            )
+            summary_text = "Error: AWS_BEARER_TOKEN_BEDROCK required"
+        except Exception as e:
+            print(f"Bedrock Request Error: {e}")
+            summary_text = f"Error: {e}"
+
+    elif model_name.startswith("foundry"):
+        try:
+            AZURE_FOUNDRY_ENDPOINT = os.environ["AZURE_FOUNDRY_ENDPOINT"]
+            AZURE_FOUNDRY_API_KEY = os.environ["AZURE_FOUNDRY_API_KEY"]
+            actual_model_name = model_name.replace("foundry-", "")
+            client = OpenAI(
+                base_url=AZURE_FOUNDRY_ENDPOINT, api_key=AZURE_FOUNDRY_API_KEY
+            )
+            completion = client.chat.completions.create(
+                model=actual_model_name,
+                messages=[
+                    {
+                        "role": "user",
+                        "content": prompt,
+                    }
+                ],
+            )
+            summary_text = completion.choices[0].message.content
+        except KeyError:
+            print(
+                "Error: AZURE_FOUNDRY_ENDPOINT and AZURE_FOUNDRY_API_KEY "
+                "environment variables required."
+            )
+            summary_text = "Error: Foundry vars required"
+        except Exception as e:
+            print(f"Foundry Request Error: {e}")
+            summary_text = f"Error: {e}"
+
+    return summary_text
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "video_id",
+        nargs="?",
+        default="KuPc06JgI_A",
+        help=(
+            "Can be one of: \n"
+            "A Video ID e.g. 'KuPc06JgI_A'\n"
+            "Playlist ID (starts with PL e.g. 'PL8ZxoInteClyHaiReuOHpv6Z4SPrXtYtW')\n"
+            "Channel Handle (starts with @ e.g. '@mga-hgo1740')\n"
+            "Comma-separated list of Video IDs. (e.g. 'KuPc06JgI_A,GalhDyf3F8g')"
+        ),
+    )
+    parser.add_argument(
+        "-o",
+        "--outfile",
+        default="youtube-docs.csv",
+        help=("Can be one of: \nLocal file path to save the output CSV file."),
+    )
+    parser.add_argument(
+        "-m",
+        "--model",
+        default=None,
+        help=(
+            "The LLM to use for summarization. Can be one of: \n"
+            "Gemini model (e.g., 'gemini-3-flash-preview')\n"
+            "GCP Vertex model (prefixed with 'vertex-'). e.g. "
+            "vertex-claude-haiku-4-5@20251001\n"
+            "AWS Bedrock model (prefixed with 'bedrock-'). e.g. "
+            "bedrock-claude-haiku-4-5-20251001-v1\n"
+            "Azure Foundry model (prefix with 'foundry-). e.g. 'foundry-gpt-5-mini'\n"
+            "Defaults to None."
+        ),
+    )
+
+    args = parser.parse_args()
+    video_id_input: str = args.video_id
+    outfile: str = args.outfile
+    model_name: Optional[str] = args.model
+
+    youtube_service = get_youtube_service()
+
+    video_ids = resolve_video_ids(video_id_input, youtube_service)
+
+    # Setup Output Directories
+    transcripts_dir: Optional[str] = None
+    summaries_dir: Optional[str] = None
+    if outfile.endswith(".csv"):
+        output_dir = os.path.dirname(outfile)
+        if output_dir and not os.path.exists(output_dir):
+            os.makedirs(output_dir, exist_ok=True)
+        base_dir = output_dir if output_dir else "."
+        transcripts_dir = os.path.join(base_dir, "transcript-files")
+        summaries_dir = os.path.join(base_dir, "summary-files")
+        os.makedirs(transcripts_dir, exist_ok=True)
+        os.makedirs(summaries_dir, exist_ok=True)
+
+    print(f"Processing {len(video_ids)} videos.")
+    print(f"Processing Videos: {video_ids}")
+    print(f"Saving to: {outfile}")
+    if model_name:
+        print(f"Summarizing using model: {model_name}")
+
+    data: List[dict] = []
+    for video_id in video_ids:
+        print(f"Processing Video ID: {video_id}")
+
+        # Get Details
+        details = get_video_details(video_id, youtube_service)
+        if not details:
+            # If explicit None returned, skip
+            continue
+
+        (
+            video_title,
+            description,
+            publishedAt,
+            channelTitle,
+            tags,
+            video_duration,
+            url,
+        ) = details
+        print(f"Processing Video URL: {url}")
+
+        # Fetch Transcript
+        transcript = fetch_transcript(video_id)
+        if not transcript:
+            continue
+
+        # Save Transcript
+        safe_title = (
+            re.sub(r'[\\/*?:"<>|]', "_", video_title)
+            .replace("\n", " ")
+            .replace("\r", "")
+        )
+        transcript_full_path = ""
+        if transcripts_dir:
+            transcript_filename = f"{video_id} - {safe_title}.txt"
+            transcript_full_path = os.path.abspath(
+                os.path.join(transcripts_dir, transcript_filename)
+            )
+            try:
+                with open(transcript_full_path, "w", encoding="utf-8") as f:
+                    f.write(transcript)
+                print(f"Saved transcript: {transcript_filename}")
+            except OSError as e:
+                print(f"Error writing transcript: {e}")
+
+        # Summarize
+        summary_text = ""
+        summary_full_path = ""
+        if model_name:
+            print(f"Summarizing using model: {model_name}")
+            summary_text = generate_summary(model_name, transcript, video_title, url)
+
+            if summaries_dir and summary_text:
+                summary_filename = (
+                    f"{model_name} - {video_id} - {safe_title} - summary.md"
+                )
+                summary_full_path = os.path.abspath(
+                    os.path.join(summaries_dir, summary_filename)
+                )
+                try:
+                    with open(summary_full_path, "w", encoding="utf-8") as f:
+                        f.write(summary_text)
+                    print(f"Saved summary: {summary_filename}")
+                except OSError as e:
+                    print(f"Error writing summary: {e}")
+
+        print(f"Video Title: {video_title}")
+        print(f"Description: {description}")
+        print(f"Published At: {publishedAt}")
+        print(f"Channel Title: {channelTitle}")
+        print(f"Tags: {tags}")
+        print(f"Video Duration: {video_duration}")
+        print(f"Number of Transcript characters: {len(transcript)}")
+
+        row = {
+            "URL": url,
+            "Title": video_title,
+            "Description": description,
+            "Data Published": publishedAt,
+            "Channel": channelTitle,
+            "Tags": tags,
+            "Duration": video_duration,
+            "Transcript characters": len(transcript),
+            "Transcript File": transcript_full_path,
+            "Summary File": summary_full_path,
+            f"Summary Text {model_name}"
+            if model_name
+            else "Summary Text": summary_text,
+        }
+        data.append(row)
+        time.sleep(1)
+
+    if data:
+        df = pl.DataFrame(data)
+        df.write_csv(outfile)
+        print(f"Successfully wrote {len(df)} rows to {outfile}")
+    else:
+        print("No data gathered.")
+
+
+if __name__ == "__main__":
+    main()

youtube_to_docs-0.0.1/youtube_to_docs.egg-info/PKG-INFO

@@ -0,0 +1,23 @@
+Metadata-Version: 2.4
+Name: youtube-to-docs
+Version: 0.0.1
+Summary: Convert YouTube videos to docs/sheets for discoverability
+Requires-Python: >=3.14
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: google-auth>=2.45.0
+Requires-Dist: google-genai>=1.56.0
+Requires-Dist: google-api-python-client>=2.187.0
+Requires-Dist: isodate>=0.7.2
+Requires-Dist: openai>=1.56.0
+Requires-Dist: polars>=1.36.1
+Requires-Dist: requests>=2.32.5
+Requires-Dist: youtube-transcript-api>=1.2.3
+Dynamic: license-file
+
+# youtube-to-docs
+Convert YouTube videos to docs/sheets for discoverability.
+
+
+
+*Created with the help of AI. All artifacts have been checked and work as expected.*

youtube_to_docs-0.0.1/youtube_to_docs.egg-info/SOURCES.txt

@@ -0,0 +1,17 @@
+.gitignore
+.pre-commit-config.yaml
+LICENSE
+README.md
+pyproject.toml
+requirements.txt
+.github/workflows/ci.yml
+docs/development.md
+tests/__init__.py
+tests/test_main.py
+youtube_to_docs/__init__.py
+youtube_to_docs/main.py
+youtube_to_docs.egg-info/PKG-INFO
+youtube_to_docs.egg-info/SOURCES.txt
+youtube_to_docs.egg-info/dependency_links.txt
+youtube_to_docs.egg-info/requires.txt
+youtube_to_docs.egg-info/top_level.txt

youtube_to_docs-0.0.1/youtube_to_docs.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

youtube_to_docs-0.0.1/youtube_to_docs.egg-info/requires.txt

@@ -0,0 +1,8 @@
+google-auth>=2.45.0
+google-genai>=1.56.0
+google-api-python-client>=2.187.0
+isodate>=0.7.2
+openai>=1.56.0
+polars>=1.36.1
+requests>=2.32.5
+youtube-transcript-api>=1.2.3

youtube_to_docs-0.0.1/youtube_to_docs.egg-info/top_level.txt

@@ -0,0 +1 @@
+youtube_to_docs