codex

pricewatch/app/tasks/scheduler.py

@@ -0,0 +1,75 @@
+"""
+Planification des jobs de scraping via RQ Scheduler.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from datetime import datetime, timedelta, timezone
+from typing import Optional
+
+import redis
+from rq import Queue
+from rq_scheduler import Scheduler
+
+from pricewatch.app.core.config import AppConfig, get_config
+from pricewatch.app.core.logging import get_logger
+from pricewatch.app.tasks.scrape import scrape_product
+
+logger = get_logger("tasks.scheduler")
+
+
+@dataclass
+class ScheduledJobInfo:
+    """Infos de retour pour un job planifie."""
+
+    job_id: str
+    next_run: datetime
+
+
+class ScrapingScheduler:
+    """Scheduler pour les jobs de scraping avec RQ."""
+
+    def __init__(self, config: Optional[AppConfig] = None, queue_name: str = "default") -> None:
+        self.config = config or get_config()
+        self.redis = redis.from_url(self.config.redis.url)
+        self.queue = Queue(queue_name, connection=self.redis)
+        self.scheduler = Scheduler(queue=self.queue, connection=self.redis)
+
+    def enqueue_immediate(
+        self,
+        url: str,
+        use_playwright: Optional[bool] = None,
+        save_db: bool = True,
+    ):
+        """Enqueue un job immediat."""
+        job = self.queue.enqueue(
+            scrape_product,
+            url,
+            use_playwright=use_playwright,
+            save_db=save_db,
+        )
+        logger.info(f"Job enqueued: {job.id}")
+        return job
+
+    def schedule_product(
+        self,
+        url: str,
+        interval_hours: int = 24,
+        use_playwright: Optional[bool] = None,
+        save_db: bool = True,
+    ) -> ScheduledJobInfo:
+        """Planifie un scraping recurrent (intervalle en heures)."""
+        interval_seconds = int(timedelta(hours=interval_hours).total_seconds())
+        next_run = datetime.now(timezone.utc) + timedelta(seconds=interval_seconds)
+
+        job = self.scheduler.schedule(
+            scheduled_time=next_run,
+            func=scrape_product,
+            args=[url],
+            kwargs={"use_playwright": use_playwright, "save_db": save_db},
+            interval=interval_seconds,
+            repeat=None,
+        )
+        logger.info(f"Job planifie: {job.id}, prochaine execution: {next_run.isoformat()}")
+        return ScheduledJobInfo(job_id=job.id, next_run=next_run)