codex2

pricewatch/app/tasks/scrape.py

@@ -4,6 +4,7 @@ Tache de scraping asynchrone pour RQ.
 
 from __future__ import annotations
 
+import time
 from typing import Any, Optional
 
 from pricewatch.app.core.config import AppConfig, get_config
@@ -46,6 +47,9 @@ def scrape_product(
 
     Retourne un dict avec success, product_id, snapshot, error.
     """
+    job_start_time = time.time()
+    logger.info(f"[JOB START] Scraping: {url}")
+
     config: AppConfig = get_config()
     setup_stores()
 
@@ -58,6 +62,8 @@ def scrape_product(
     registry = get_registry()
     store = registry.detect_store(url)
     if not store:
+        elapsed_ms = int((time.time() - job_start_time) * 1000)
+        logger.error(f"[JOB FAILED] Aucun store detecte pour: {url} (duree={elapsed_ms}ms)")
         snapshot = ProductSnapshot(
             source="unknown",
             url=url,
@@ -70,6 +76,8 @@ def scrape_product(
         ScrapingPipeline(config=config).process_snapshot(snapshot, save_to_db=save_db)
         return {"success": False, "product_id": None, "snapshot": snapshot, "error": "store"}
 
+    logger.info(f"[STORE] Detecte: {store.store_id}")
+
     canonical_url = store.canonicalize(url)
 
     html = None
@@ -79,13 +87,16 @@ def scrape_product(
     html_size_bytes = None
     pw_result = None
 
+    logger.debug(f"[FETCH] Tentative HTTP: {canonical_url}")
     http_result = fetch_http(canonical_url)
     duration_ms = http_result.duration_ms
 
     if http_result.success:
         html = http_result.html
         fetch_method = FetchMethod.HTTP
+        logger.info(f"[FETCH] HTTP OK (duree={duration_ms}ms, taille={len(html)})")
     elif use_playwright:
+        logger.debug(f"[FETCH] HTTP echoue ({http_result.error}), fallback Playwright")
         pw_result = fetch_playwright(
             canonical_url,
             headless=not headful,
@@ -97,10 +108,13 @@ def scrape_product(
         if pw_result.success:
             html = pw_result.html
             fetch_method = FetchMethod.PLAYWRIGHT
+            logger.info(f"[FETCH] Playwright OK (duree={duration_ms}ms, taille={len(html)})")
         else:
             fetch_error = pw_result.error
+            logger.warning(f"[FETCH] Playwright echoue: {fetch_error}")
     else:
         fetch_error = http_result.error
+        logger.warning(f"[FETCH] HTTP echoue: {fetch_error}")
 
     if html:
         html_size_bytes = len(html.encode("utf-8"))
@@ -118,12 +132,18 @@ def scrape_product(
                 save_debug_screenshot(pw_result.screenshot, f"{store.store_id}_{ref}")
 
         try:
+            logger.debug(f"[PARSE] Parsing avec {store.store_id}...")
             snapshot = store.parse(html, canonical_url)
             snapshot.debug.method = fetch_method
             snapshot.debug.duration_ms = duration_ms
             snapshot.debug.html_size_bytes = html_size_bytes
             success = snapshot.debug.status != DebugStatus.FAILED
+            if success:
+                logger.info(f"[PARSE] OK - titre={bool(snapshot.title)}, prix={snapshot.price}")
+            else:
+                logger.warning(f"[PARSE] Partiel - status={snapshot.debug.status}")
         except Exception as exc:
+            logger.error(f"[PARSE] Exception: {exc}")
             snapshot = ProductSnapshot(
                 source=store.store_id,
                 url=canonical_url,
@@ -152,6 +172,19 @@ def scrape_product(
 
     product_id = ScrapingPipeline(config=config).process_snapshot(snapshot, save_to_db=save_db)
 
+    # Log final du job
+    elapsed_ms = int((time.time() - job_start_time) * 1000)
+    if success:
+        logger.info(
+            f"[JOB OK] {store.store_id}/{snapshot.reference} "
+            f"product_id={product_id} prix={snapshot.price} duree={elapsed_ms}ms"
+        )
+    else:
+        logger.warning(
+            f"[JOB FAILED] {store.store_id}/{snapshot.reference or 'unknown'} "
+            f"erreur={fetch_error} duree={elapsed_ms}ms"
+        )
+
     return {
         "success": success,
         "product_id": product_id,