Different approach

sql_crawler/Makefile

@@ -0,0 +1,10 @@
+alembic-init:
+	@alembic init schema
+
+init_db:
+	@python -c "from sc_crawler.models import init_db; init_db()"
+
+editable-env:
+	@pip install --editable .
+
+.PHONY: alembic-init editable-env init_db

sql_crawler/README.md

@@ -0,0 +1,17 @@
+docker run --rm -ti -v $PWD:/data python:3.11 bash
+pip install -y alembic
+
+# Prepare env
+$ make editable-env
+
+# Init DB
+$ make init_db
+
+# Fill it up
+python -m sc_crawler.main
+
+# Example query
+```python
+import sc_crawler
+sc_crawler.main.query_dc()
+```

sql_crawler/alembic.ini

@@ -0,0 +1,116 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = schema
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to schema/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:schema/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = sqlite:////tmp/data.db
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

sql_crawler/pyproject.toml

@@ -0,0 +1,21 @@
+[project]
+name = "sc_crawler"
+version = "0.0.1"
+description = "Spare Cores crawler"
+readme = "README.md"
+requires-python = ">=3.8"
+authors = [
+    {name = "John Doe", email = "[email protected]" }
+]
+
+dependencies = [
+    "alembic",
+    "validators",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/SpareCores/sc-crawler"
+"Source" = "https://github.com/SpareCores/sc-crawler"
+
+[tool.setuptools.packages.find]
+where = ["src"]

sql_crawler/schema/README

@@ -0,0 +1 @@
+Generic single-database configuration.

sql_crawler/schema/env.py

@@ -0,0 +1,76 @@
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+target_metadata = None
+from sc_crawler.models import Base
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

sql_crawler/schema/script.py.mako

@@ -0,0 +1,26 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

sql_crawler/src/sc_crawler/__init__.py

@@ -0,0 +1 @@
+print("SCRAWLER2")

sql_crawler/src/sc_crawler/main.py

@@ -0,0 +1,24 @@
+from .models import db_session, Datacenter, Vendor
+
+
+def app():
+    with db_session()() as session:
+        session.add_all(
+            [
+                Vendor(id="aws", name="Amazon Web Services"),
+                Datacenter(id="us-east-1a", vendor_id="aws", name="US East"),
+            ]
+        )
+        session.commit()
+
+
+def query_dc():
+    with db_session()() as session:
+        r = session.query(Datacenter).filter(Datacenter.vendor_id == "aws")
+        for dc in r.all():
+            print(dc.id, dc.name)
+
+
+if __name__ == "__main__":
+    app()
+

sql_crawler/src/sc_crawler/models.py

@@ -0,0 +1,55 @@
+from typing import Optional, List
+from sqlalchemy.ext.declarative import declarative_base
+from sqlalchemy import create_engine, DateTime, ForeignKey, String, Integer, func
+from sqlalchemy.orm import Mapped, mapped_column, relationship, sessionmaker, validates
+import datetime
+import os
+import functools
+import validators
+
+DB_ENGINE = os.getenv("SC_CRAWLER_DB_ENGINE", "sqlite:////tmp/sc_crawler.db")
+
+Base = declarative_base()
+metadata = Base.metadata
+
+
+class Vendor(Base):
+    __tablename__ = "vendors"
+
+    id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    name: Mapped[str] = mapped_column(String(256), unique=True, nullable=False)
+    logo_url: Mapped[Optional[str]] = mapped_column(String(256), unique=True)
+    created_at: Mapped[datetime.datetime] = mapped_column(DateTime, default=func.now(), nullable=False)
+    datacenters: Mapped[List["Datacenter"]] = relationship()
+
+    def __repr__(self):
+        return f"id: {self.id}, name: {self.name}"
+
+    @validates("logo_url")
+    def validate_url(self, k, url):
+        res = validators.url(url)
+        if res:
+            return url
+        raise res
+
+
+class Datacenter(Base):
+    __tablename__ = "datacenters"
+
+    id: Mapped[str] = mapped_column(String(64), primary_key=True)
+    vendor_id: Mapped[str] = mapped_column(ForeignKey("vendors.id", primary_key=True))
+    name: Mapped[str] = mapped_column(String(256), unique=True, nullable=False)
+
+
+@functools.cache
+def db_engine():
+    return create_engine(DB_ENGINE, echo=True)
+
+
+@functools.cache
+def db_session():
+    return sessionmaker(bind=db_engine())
+
+
+def init_db():
+    metadata.create_all(db_engine())