Initial commit

.editorconfig

@@ -0,0 +1,12 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+charset = utf-8
+indent_style = space
+indent_size = 4
+trim_trailing_whitespace = true
+
+[*.yaml]
+indent_size = 2

.gitattributes

@@ -0,0 +1,4 @@
+*.json          linguist-generated
+*.xml           linguist-generated
+*.tsv           linguist-generated
+*.csv           linguist-generated

.github/dependabot.yml

@@ -0,0 +1,23 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for more information:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# https://containers.dev/guide/dependabot
+
+version: 2
+updates:
+  - package-ecosystem: "pip" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"
+  # Enable version updates for Actions
+  - package-ecosystem: "github-actions"
+    # Look for `.github/workflows` in the `root` directory
+    directory: "/"
+    # Check for updates once a week
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "devcontainers"
+    directory: "/"
+    schedule:
+      interval: weekly

.github/workflows/scrape.yml

@@ -0,0 +1,44 @@
+name: "Scrape platform"
+on:
+  workflow_dispatch:
+  push:
+    paths:
+      - "scraper/*"
+  schedule:
+    - cron: "0 12 * * 0"
+permissions:
+  contents: write
+jobs:
+  Scrape:
+    name: "Scrape platform and convert as Media object"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: "Load secrets, if any"
+        uses: oNaiPs/secrets-to-env-action@v1
+        with:
+          secrets: ${{ toJson(secrets) }}
+      - name: "Setup python"
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "pip"
+      - name: "Install dependencies"
+        run: pip install -U -r requirements.txt
+      - name: "Run scraper"
+        shell: pwsh
+        run: |
+          try {
+            python3 scraper
+            $date = Get-Date -Format "yyyy-MM-dd'T'HH:mm:sszzzz"
+            git config --local user.email "167072439+rensetsu-bot@users.noreply.github.com"
+            git config --local user.name "Rensetsu[bot]"
+            git add .
+            git commit -m "Scrape data, $date update"
+            git push
+          }
+          catch {
+            "Failed to commit, check logs!"
+            exit 1
+          }

.gitignore

@@ -0,0 +1,160 @@
+# 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/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Rensetsu
+
+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.

README.md

@@ -0,0 +1,30 @@
+# Rensetsu Service Scraper for {PLATFORM}
+
+This is a command-line utility to scrape {PLATFORM} data and convert it to
+Rensetsu Media object format
+
+## Requirements
+
+* Python >= 3.10
+
+## Setup
+
+Simply running following commands before using the app:
+
+```sh
+git clone https://github.com/rensetsu/{REPO_NAME}
+cd {REPO_NAME}
+python3 -m venv venv
+source ./venv/bin/activate
+pip install -U -r requirements.txt
+```
+
+## Usage
+
+```sh
+python scraper
+```
+
+## License
+
+This repo is licensed under [MIT License](LICENSE), unless stated otherwise.

pyproject.toml

@@ -0,0 +1,7 @@
+[project]
+requires-python = ">=3.10"
+name = "rensetsu"
+
+[tool.ruff]
+line-length = 80
+

requirements.txt

@@ -0,0 +1 @@
+git+https://github.com/rensetsu/librensetsu.git

scraper/__main__.py

@@ -0,0 +1,29 @@
+from sys import exit as sysexit
+from time import time
+from traceback import print_exc
+
+from consts import Status, pprint
+from librensetsu.humanclock import convert_float_to_time
+from loops import do_loop
+
+
+def main() -> None:
+    """Main process of the util"""
+    start = time()
+    ex = 0
+    pprint.print(Status.INFO, "Starting...")
+    try:
+        do_loop()
+    except Exception as e:
+        pprint.print(Status.ERR, f"An error occurred: {e}")
+        print_exc()
+        ex = 1
+    end = time()
+    pprint.print(
+        Status.INFO, f"Time elapsed: {convert_float_to_time(end - start)}"
+    )
+    sysexit(ex)
+
+
+if __name__ == "__main__":
+    main()

scraper/consts.py

@@ -0,0 +1,9 @@
+from librensetsu.prettyprint import PrettyPrint, Platform, Status
+
+pprint = PrettyPrint(Platform.SYSTEM)
+PLATFORM = ""
+RAW_DB = f"{PLATFORM}_raw.json"
+DEST = f"{PLATFORM}.json"
+DESTM = f"{PLATFORM}_min.json"
+
+__all__ = ['pprint', 'Platform', 'Status', 'RAW_DB', 'DEST', 'DESTM']