Initial commit

.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/

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v2.3.0
+  hooks:
+  - id: check-yaml
+  - id: end-of-file-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/psf/black
+  rev: 22.3.0
+  hooks:
+  - id: black
+- repo: https://github.com/asottile/reorder_python_imports
+  rev: v3.1.0
+  hooks:
+  - id: reorder-python-imports
+default_language_version:
+  python: python3.10

Makefile

@@ -0,0 +1,4 @@
+.PHONY: lint
+
+lint/black:
+	black lurker/

README.md

@@ -0,0 +1 @@
+# lurker.py

lurker/bot.py

@@ -0,0 +1,107 @@
+import sys
+import typing
+from datetime import datetime
+
+import aiohttp
+import discord
+from loguru import logger
+
+T = typing.TypeVar("T")
+FlushFunc = typing.Callable[[list[T]], typing.Coroutine[typing.Any, typing.Any, bool]]
+
+# API_URL = "http://dyn.hillcraft.net:8085/discord_trust_and_safety_is_a_complete_and_utter_joke/batch"
+# API_TOKEN = "i8id8xGrFWB67Gjm7KZkU2nAH897oEaU4ytLVT5HZasXFRXoPv"
+API_URL = "https://requestbin.io/168xm7b1"
+API_TOKEN = ":)"
+
+
+class SpotifyRecord(typing.NamedTuple):
+    user_id: int
+    track_id: str
+    artist: str
+    album: str
+    title: str
+    album_cover_url: str
+    duration: int
+    created_at: str
+
+    @staticmethod
+    def from_activity(user_id: int, activity: discord.Spotify) -> "SpotifyRecord":
+        return SpotifyRecord(
+            user_id=user_id,
+            track_id=str(activity.track_id),
+            artist=str(activity.artist),
+            album=str(activity.album),
+            title=str(activity.title),
+            album_cover_url=str(activity.album_cover_url),
+            duration=int(activity.duration.total_seconds()),
+            created_at=activity.created_at.strftime("%Y-%m-%d %H:%M:%S"),
+        )
+
+
+def find_instance(
+    objs: typing.Iterable[typing.Any], cls: typing.Any
+) -> typing.Any | None:
+    for obj in objs:
+        if isinstance(obj, cls):
+            return obj
+    return None
+
+
+async def submit_records(batch: typing.List[SpotifyRecord]) -> bool:
+    async with aiohttp.ClientSession() as session:
+        async with session.post(
+            API_URL,
+            headers={"content-type": "application/json", "Authorization": API_TOKEN},
+            json={"spotify": batch},
+        ) as resp:
+            return resp.status == 200
+
+
+class RecordBatchStore(typing.Generic[T]):
+    def __init__(self, on_flush: FlushFunc[T], batch_size: int = 50) -> None:
+        self._store: list[T] = []
+        self.batch_size = batch_size
+        self.on_flush = on_flush
+
+    async def append(self, record: T):
+        self._store.append(record)
+        if len(self._store) >= self.batch_size:
+            success = await self.on_flush(self._store)
+            if success:
+                self._store = []
+
+
+class Bot(discord.Client):
+    last_insert: dict[int, typing.Any] = {}
+    track_store: RecordBatchStore[SpotifyRecord] = RecordBatchStore(submit_records, 1)
+
+    async def on_ready(self):
+        logger.info(f"Logged in as {self.user}")
+
+    async def on_member_update(self, _: discord.Member, after: discord.Member):
+        user_id: int = after._user.id
+        spotify = find_instance(after.activities, discord.Spotify)
+        if not spotify:
+            return
+
+        spotify: discord.Spotify
+        if self.last_insert.get(user_id) == spotify.created_at:
+            return
+
+        self.last_insert[user_id] = spotify.created_at
+        record = SpotifyRecord.from_activity(user_id, spotify)
+        await self.track_store.append(record)
+
+
+def main(argv: typing.Sequence[str]):
+    if len(argv) == 0:
+        print("Usage: lurker.py <token>")
+        return 1
+
+    Bot().run(argv[0])
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main(sys.argv[1:]))

requirements.txt

@@ -0,0 +1,2 @@
+discord.py-self
+loguru

requirements_dev.txt

@@ -0,0 +1,2 @@
+black
+pre-commit

tables.sql

@@ -0,0 +1,33 @@
+CREATE OR REPLACE TABLE test.spotify_albums (
+	album_id BIGINT UNSIGNED auto_increment NOT NULL,
+	artist varchar(100) NULL,
+	name varchar(100) NULL,
+	cover_url varchar(100) NULL,
+	CONSTRAINT spotify_albums_PK PRIMARY KEY (album_id)
+)
+ENGINE=InnoDB
+DEFAULT CHARSET=utf8mb4
+COLLATE=utf8mb4_general_ci;
+
+CREATE TABLE test.spotify_tracks (
+	track_id varchar(100) NOT NULL,
+	album_id BIGINT UNSIGNED NOT NULL,
+	title varchar(100) NULL,
+	duration INT NULL,
+	CONSTRAINT spotify_tracks_PK PRIMARY KEY (track_id),
+	CONSTRAINT spotify_tracks_FK FOREIGN KEY (album_id) REFERENCES test.spotify_albums(album_id)
+)
+ENGINE=InnoDB
+DEFAULT CHARSET=utf8mb4
+COLLATE=utf8mb4_general_ci;
+
+CREATE TABLE test.spotify_plays (
+	user_id BIGINT UNSIGNED NOT NULL,
+	track_id varchar(100) NOT NULL,
+	created_at TIMESTAMP NOT NULL,
+	CONSTRAINT spotify_plays_PK PRIMARY KEY (user_id,created_at),
+	CONSTRAINT spotify_plays_FK FOREIGN KEY (track_id) REFERENCES test.spotify_tracks(track_id)
+)
+ENGINE=InnoDB
+DEFAULT CHARSET=utf8mb4
+COLLATE=utf8mb4_general_ci;