diff --git a/acceptance_service.py b/acceptance_service.py index 3beedf0..9e0e5cb 100644 --- a/acceptance_service.py +++ b/acceptance_service.py @@ -1183,8 +1183,9 @@ def _copy_acceptance_task(public_id: str, *, trigger_source: str = "acceptance") with connection() as conn: conn.execute( """UPDATE acceptance_tasks SET scheduled_from_task_id=?,dashboard_batch_key=?, - use_all_devices=? WHERE public_task_id=?""", - (task["id"], task["dashboard_batch_key"], task["use_all_devices"], child["task_id"]), + use_all_devices=?,batch_date=? WHERE public_task_id=?""", + (task["id"], task["dashboard_batch_key"], task["use_all_devices"], + datetime.now().astimezone().date().isoformat(), child["task_id"]), ) return get_acceptance_task(child["task_id"]) @@ -1195,7 +1196,7 @@ def collect_acceptance_now(public_id: str) -> dict[str, Any]: def collect_acceptance_crawler_now(public_id: str) -> dict[str, Any]: - """按项目搜索词启动独立的 Cookie 爬虫采集批次，不下发截图设备。""" + """按项目搜索词同时启动 Cookie 爬虫和截图设备，按自然日归入批次。""" with connection() as conn: task = conn.execute("SELECT * FROM acceptance_tasks WHERE public_task_id=?", (public_id,)).fetchone() if not task: @@ -1205,8 +1206,8 @@ def collect_acceptance_crawler_now(public_id: str) -> dict[str, Any]: keywords = [row["keyword"] for row in conn.execute("SELECT keyword FROM acceptance_keywords WHERE task_id=? ORDER BY keyword_order", (root_id,)).fetchall()] matches = [row["keyword"] for row in conn.execute("SELECT keyword FROM acceptance_match_keywords WHERE task_id=? ORDER BY keyword_order", (root_id,)).fetchall()] child = create_acceptance_task({ - "name": f"{root['name']}｜爬虫数据采集", - "acceptance_method": "data-analysis", + "name": f"{root['name']}｜立即完整采集", + "acceptance_method": "combined", "feishu_links": [], "keywords": keywords, "match_keywords": matches, @@ -1216,9 +1217,10 @@ def collect_acceptance_crawler_now(public_id: str) -> dict[str, Any]: }) with connection() as conn: conn.execute( - """UPDATE acceptance_tasks SET scheduled_from_task_id=?,dashboard_batch_key=? + """UPDATE acceptance_tasks SET scheduled_from_task_id=?,dashboard_batch_key=?, + use_all_devices=1,batch_date=? WHERE public_task_id=?""", - (root_id, root["dashboard_batch_key"], child["task_id"]), + (root_id, root["dashboard_batch_key"], datetime.now().astimezone().date().isoformat(), child["task_id"]), ) return get_acceptance_task(child["task_id"]) @@ -1559,7 +1561,7 @@ def _task_dict(conn, task) -> dict[str, Any]: ).fetchall()] root_id = task["scheduled_from_task_id"] or task["id"] batches = [dict(row) for row in conn.execute( - """SELECT public_task_id,status,progress_percent,created_at,updated_at + """SELECT public_task_id,status,progress_percent,batch_date,created_at,updated_at FROM acceptance_tasks WHERE id=? OR scheduled_from_task_id=? ORDER BY created_at DESC""", (root_id, root_id), @@ -1701,6 +1703,7 @@ def _task_dict(conn, task) -> dict[str, Any]: "cookie_count": task["cookie_count"], "dashboard_batch_key": task["dashboard_batch_key"], "use_all_devices": bool(task["use_all_devices"]), + "batch_date": task["batch_date"], "schedule_enabled": bool(task["schedule_enabled"]), "schedule_weekday": task["schedule_weekday"], "schedule_weekdays": _decode_json(task["schedule_weekdays"], None) or ( @@ -1733,7 +1736,9 @@ def get_acceptance_task(public_id: str) -> dict[str, Any]: def list_acceptance_tasks() -> dict[str, Any]: with connection() as conn: - rows = conn.execute("SELECT * FROM acceptance_tasks ORDER BY created_at DESC").fetchall() + rows = conn.execute( + "SELECT * FROM acceptance_tasks WHERE scheduled_from_task_id IS NULL ORDER BY created_at DESC" + ).fetchall() items = [_task_dict(conn, row) for row in rows] return {"items": items, "total": len(items)} diff --git a/apifox-business-tasks.openapi.json b/apifox-business-tasks.openapi.json index 8fae6d9..08e81ef 100644 --- a/apifox-business-tasks.openapi.json +++ b/apifox-business-tasks.openapi.json @@ -57,8 +57,8 @@ }, "/api/v1/acceptance-tasks/{task_id}/collect-crawler-now": { "post": { - "summary": "立即启动验收爬虫数据采集", - "description": "使用项目的搜索词和当前全部可用 Cookie 创建独立数据采集批次，不下发截图设备。", + "summary": "立即启动完整验收采集", + "description": "使用项目搜索词、当前全部可用 Cookie 和全部启用截图设备创建完整采集；批次按 Asia/Shanghai 自然日归属，同日重采仍属于同一日期批次。", "tags": ["项目验收"], "parameters": [{"$ref": "#/components/parameters/TaskId"}], "responses": {"201": {"description": "爬虫采集批次已启动"}} diff --git a/database.py b/database.py index fa98ee3..93044b7 100644 --- a/database.py +++ b/database.py @@ -388,6 +388,7 @@ def init_database() -> None: "cookie_count": "INTEGER NOT NULL DEFAULT 0", "dashboard_batch_key": "TEXT", "use_all_devices": "INTEGER NOT NULL DEFAULT 0", + "batch_date": "TEXT", } for column, definition in acceptance_migrations.items(): if column not in acceptance_columns: diff --git a/tests/test_acceptance_creation.py b/tests/test_acceptance_creation.py index 6d28f11..ce645b1 100644 --- a/tests/test_acceptance_creation.py +++ b/tests/test_acceptance_creation.py @@ -142,10 +142,11 @@ class AcceptanceCreationTest(unittest.TestCase): child = collect_acceptance_crawler_now(source["task_id"]) - self.assertEqual(child["acceptance_method"], "data-analysis") + self.assertEqual(child["acceptance_method"], "combined") self.assertEqual(child["keywords"], ["山姆会员卡"]) self.assertEqual(child["match_keywords"], ["民生"]) self.assertEqual(child["cookie_count"], 2) + self.assertIsNotNone(child["batch_date"]) @patch("acceptance_service.threading.Thread", _ThreadWithoutStart) @patch("acceptance_service._copy_acceptance_task")