add fastapi rest api and celery workers

This commit is contained in:
qananasikq
2026-04-08 22:54:33 +03:00
parent 6e97991c68
commit f4b9d20191
15 changed files with 982 additions and 0 deletions

58
alembic/env.py Normal file
View File

@@ -0,0 +1,58 @@
"""Alembic env.py — подключение к БД через Settings."""
import os
import sys
from logging.config import fileConfig
from alembic import context
from sqlalchemy import engine_from_config, pool
# Добавляем корень проекта в sys.path
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
from iaai_scraper.core.config import Settings
from iaai_scraper.storage.models import Base
config = context.config
# Logging
if config.config_file_name is not None:
fileConfig(config.config_file_name)
# Подставляем URL из Settings (env vars имеют приоритет)
settings = Settings()
config.set_main_option("sqlalchemy.url", settings.database.url)
target_metadata = Base.metadata
def run_migrations_offline() -> None:
"""Run migrations in 'offline' mode."""
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."""
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()

25
alembic/script.py.mako Normal file
View File

@@ -0,0 +1,25 @@
"""${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"}

View File

@@ -0,0 +1,105 @@
"""Initial schema — cars, images, sync_runs, scrape_tasks
Revision ID: 001_initial
Revises:
Create Date: 2026-04-08
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
revision: str = "001_initial"
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# --- cars ---
op.create_table(
"cars",
sa.Column("id", sa.BigInteger, primary_key=True, autoincrement=True),
sa.Column("parser_id", sa.String(50), nullable=False, unique=True),
sa.Column("brand", sa.String(50), nullable=False),
sa.Column("model", sa.String(50), nullable=False),
sa.Column("year", sa.Integer, nullable=True),
sa.Column("price", sa.BigInteger, nullable=True),
sa.Column("currency", sa.String(10), nullable=False, server_default="USD"),
sa.Column("mileage", sa.Integer, nullable=False, server_default="0"),
sa.Column("country", sa.String(10), nullable=False, server_default="NA"),
sa.Column("is_sold", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("color", sa.String, nullable=False, server_default="other"),
sa.Column("drive", sa.String(10), nullable=True),
sa.Column("gearbox", sa.String(10), nullable=True),
sa.Column("steering_wheel", sa.String(10), nullable=True),
sa.Column("body_type", sa.String(20), nullable=False, server_default="OTHER"),
sa.Column("engine_volume", sa.Integer, nullable=True),
sa.Column("selling_type", sa.String(20), nullable=False, server_default="NA"),
sa.Column("one_owner", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("new_car", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("is_hidden", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("origin", sa.String(20), nullable=False, server_default="NA"),
sa.Column("origin_url", sa.String, nullable=False),
sa.Column("origin_id", sa.String, nullable=False, unique=True),
sa.Column("is_damaged", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("evaluation", sa.String, nullable=True),
sa.Column("non_smoking", sa.Boolean, nullable=False, server_default=sa.text("true")),
sa.Column("rental", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("repair_history", sa.Boolean, nullable=False, server_default=sa.text("false")),
sa.Column("slug", sa.String, nullable=False),
sa.Column("last_seen_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.func.now()),
sa.Column("content_hash", sa.String(64), nullable=False, server_default=""),
sa.Column("raw_attributes", sa.Text, nullable=True),
)
op.create_index("ix_cars_origin_url", "cars", ["origin_url"])
op.create_index("ix_cars_origin_id", "cars", ["origin_id"], unique=True)
op.create_index("ix_cars_content_hash", "cars", ["content_hash"])
# --- images ---
op.create_table(
"images",
sa.Column("id", sa.BigInteger, primary_key=True, autoincrement=True),
sa.Column("fullres_image", sa.String, nullable=False),
sa.Column("preview_image", sa.String, nullable=False),
sa.Column("order_index", sa.Integer, nullable=False),
sa.Column("car_id", sa.BigInteger, sa.ForeignKey("cars.id", ondelete="CASCADE"), nullable=False),
)
# --- sync_runs ---
op.create_table(
"sync_runs",
sa.Column("id", sa.BigInteger, primary_key=True, autoincrement=True),
sa.Column("started_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.func.now()),
sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("status", sa.Text, nullable=False),
sa.Column("lane", sa.Text, nullable=False),
sa.Column("ids_fetched", sa.Integer, nullable=False, server_default="0"),
sa.Column("cars_upserted", sa.Integer, nullable=False, server_default="0"),
sa.Column("cars_failed", sa.Integer, nullable=False, server_default="0"),
sa.Column("images_upserted", sa.Integer, nullable=False, server_default="0"),
sa.Column("error_summary", sa.Text, nullable=True),
)
# --- scrape_tasks ---
op.create_table(
"scrape_tasks",
sa.Column("id", sa.BigInteger, primary_key=True, autoincrement=True),
sa.Column("celery_task_id", sa.String(255), nullable=False, unique=True),
sa.Column("task_type", sa.String(50), nullable=False),
sa.Column("status", sa.String(20), nullable=False, server_default="pending"),
sa.Column("vehicle_url", sa.Text, nullable=True),
sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.func.now()),
sa.Column("started_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
sa.Column("result_summary", sa.Text, nullable=True),
sa.Column("error_message", sa.Text, nullable=True),
)
op.create_index("ix_scrape_tasks_celery_task_id", "scrape_tasks", ["celery_task_id"], unique=True)
def downgrade() -> None:
op.drop_table("scrape_tasks")
op.drop_table("sync_runs")
op.drop_table("images")
op.drop_table("cars")