auto backup 2026-06-26 08:10:49

.shared_skill_hashes

@@ -43,3 +43,4 @@ lark-workflow-meeting-summary 7479f4b43979627fde453c48b5b50970a81030d4c74d62185f
 feishu-group-monitor 8c3a459ae1383d51bc43e75e9ec39c910eb14406bda4d8c7875270058f1d3d15
 lark-send-message-as-bot 5502e41e032a1b86adc91ebe42285735b12d17b9a6be8f5acb922a8a4fa6dad6
 gpt-image-2-generator e1842d74b29c63ba218764e8156a50a47aa0f3d7be540af54d6d2db9d59c7382
+vala-data-export 10b848c9c91084e4a8aab3c3c917225a07ceeaa5510537b40d0f7b5d2a40412f

scripts/export_review_audio.py

@@ -56,7 +56,8 @@ with pg_conn.cursor(cursor_factory=RealDictCursor) as cur:
     """, (user_ids,))
     review_rows = cur.fetchall()
 
-# Parse question_list JSON for readable summary
+# Parse question_list JSON — explode each question into its own row
+expanded_rows = []  # one row per question
 for row in review_rows:
     ql = row["question_list"]
     if isinstance(ql, str):
@@ -64,17 +65,34 @@ for row in review_rows:
             ql = json.loads(ql)
         except:
             pass
-    questions = []
+    base = {
+        "角色ID": row["user_id"],
+        "Level": row["level"],
+        "Story ID": row["story_id"],
+        "Chapter ID": row["chapter_id"],
+        "Unique ID": row["unique_id"],
+        "更新时间": str(row["updated_at"]),
+    }
     if isinstance(ql, list):
         for item in ql:
             if isinstance(item, dict):
                 q = item.get("question", {})
                 qtype = q.get("type", "")
                 qtitle = q.get("title", "")
-                user_answer = item.get("userAnswer", "")
+                is_right = item.get("isRight")
-                score = item.get("score", "")
+                status = "正确" if is_right is True else "错误"
-                questions.append(f"[{qtype}] {qtitle} | 回答: {user_answer} | 得分: {score}")
+                audio_url = item.get("userAudio", "")
-    row["question_summary"] = "\n".join(questions)
+                user_answer = item.get("userAnswer", "") or item.get("userAnswers", "")
+                if isinstance(user_answer, list):
+                    user_answer = ", ".join(str(a) for a in user_answer)
+                expanded_rows.append({
+                    **base,
+                    "题目类型": qtype,
+                    "题目内容": qtitle,
+                    "题目对错": status,
+                    "音频URL": audio_url,
+                    "用户答案": user_answer,
+                })
     row["question_count"] = len(ql) if isinstance(ql, list) else 0
 
 pg_conn.close()
@@ -149,26 +167,25 @@ from openpyxl.styles import Font, Alignment, PatternFill
 
 wb = Workbook()
 
-# Sheet 1: 课程巩固记录
+# Sheet 1: 课程巩固记录（每题一行）
 ws1 = wb.active
 ws1.title = "课程巩固记录"
+
+# Build DataFrame from expanded_rows
 review_data = []
-for row in review_rows:
+for row in expanded_rows:
     review_data.append({
-        "角色ID": row["user_id"],
+        "角色ID": row["角色ID"],
-        "Level": row["level"],
+        "Level": row["Level"],
-        "Story ID": row["story_id"],
+        "Story ID": row["Story ID"],
-        "Chapter ID": row["chapter_id"],
+        "Chapter ID": row["Chapter ID"],
-        "Unique ID": row["unique_id"],
+        "Unique ID": row["Unique ID"],
-        "得分": row["score"],
+        "题目类型": row["题目类型"],
-        "评级": row["score_text"],
+        "题目内容": row["题目内容"],
-        "SP值": row["sp_value"],
+        "题目对错": row["题目对错"],
-        "经验值": row["exp"],
+        "音频URL": row["音频URL"],
-        "题目数": row["question_count"],
+        "用户答案": row["用户答案"],
-        "耗时(秒)": row["play_time"],
+        "更新时间": row["更新时间"],
-        "题目详情": row["question_summary"],
-        "更新时间": str(row["updated_at"]),
-        "创建时间": str(row["created_at"]),
     })
 
 df1 = pd.DataFrame(review_data)
@@ -186,8 +203,16 @@ for cell in ws1[1]:
 
 # Column widths
 ws1.column_dimensions["A"].width = 10
-ws1.column_dimensions["L"].width = 12
+ws1.column_dimensions["B"].width = 8
-ws1.column_dimensions["M"].width = 60
+ws1.column_dimensions["C"].width = 12
+ws1.column_dimensions["D"].width = 12
+ws1.column_dimensions["E"].width = 36
+ws1.column_dimensions["F"].width = 24
+ws1.column_dimensions["G"].width = 30
+ws1.column_dimensions["H"].width = 10
+ws1.column_dimensions["I"].width = 55
+ws1.column_dimensions["J"].width = 30
+ws1.column_dimensions["K"].width = 22
 
 # Sheet 2: 音频数据
 ws2 = wb.create_sheet("音频数据")
@@ -244,13 +269,15 @@ ws3["A3"] = "导出时间"
 ws3["B3"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
 ws3["A4"] = "角色ID"
 ws3["B4"] = ", ".join(str(u) for u in user_ids)
-ws3["A5"] = "课程巩固记录数"
+ws3["A5"] = "课程巩固记录数（题目拆分行）"
-ws3["B5"] = len(review_rows)
+ws3["B5"] = len(expanded_rows)
-ws3["A6"] = "音频记录数"
+ws3["A6"] = "原始巩固回合数"
-ws3["B6"] = len(audio_rows)
+ws3["B6"] = len(review_rows)
+ws3["A7"] = "音频记录数"
+ws3["B7"] = len(audio_rows)
 
 # Per-user breakdown
-row_offset = 8
+row_offset = 10
 ws3[f"A{row_offset}"] = "按角色统计"
 ws3[f"A{row_offset}"].font = Font(bold=True)
 row_offset += 1
@@ -284,6 +311,83 @@ ws3.column_dimensions["D"].width = 28
 
 wb.save(output_path)
 print(f"\n✅ 导出完成: {output_path}")
-print(f"   Sheet 1 — 课程巩固记录: {len(review_rows)} 行")
+print(f"   Sheet 1 — 课程巩固记录（每题一行）: {len(expanded_rows)} 行")
 print(f"   Sheet 2 — 音频数据: {len(audio_rows)} 行")
 print(f"   Sheet 3 — 汇总")
+
+# ── 4. 自动通过飞书发送文件 ──────────────────────────
+# 默认发送给李若松 (user_id: 4aagb443)
+# 可通过环境变量 FEISHU_SEND_TO 覆盖目标 user_id
+SEND_TO = os.environ.get("FEISHU_SEND_TO", "4aagb443")
+SEND_ENABLED = os.environ.get("FEISHU_SEND_ENABLED", "1")
+
+if SEND_ENABLED != "1":
+    print("\n⏭️  飞书自动发送已禁用 (FEISHU_SEND_ENABLED != 1)")
+    sys.exit(0)
+
+print(f"\n[4/4] 通过飞书发送文件到 user_id={SEND_TO}...")
+
+FEISHU_APP_ID = g("FEISHU_APP_ID")
+FEISHU_APP_SECRET = g("FEISHU_APP_SECRET")
+
+if not FEISHU_APP_ID or not FEISHU_APP_SECRET:
+    print("  ⚠️  未找到 FEISHU_APP_ID/FEISHU_APP_SECRET，跳过发送")
+    sys.exit(0)
+
+def feishu_api(method, path, **kwargs):
+    """调用飞书 Open API，返回解析后的 JSON"""
+    cmd = ["curl", "-sk", "--connect-timeout", "10", "--max-time", "60"]
+    if method == "POST":
+        cmd += ["-X", "POST"]
+    cmd += ["-H", f"Authorization: Bearer {kwargs.get('token', '')}"]
+    if "json_data" in kwargs:
+        cmd += ["-H", "Content-Type: application/json", "-d", json.dumps(kwargs["json_data"])]
+    if "form_fields" in kwargs:
+        for key, val in kwargs["form_fields"].items():
+            cmd += ["-F", f"{key}={val}"]
+    cmd.append(f"https://open.feishu.cn{path}")
+    r = subprocess.run(cmd, capture_output=True, text=True, timeout=65)
+    try:
+        return json.loads(r.stdout)
+    except:
+        print(f"  ❌ API 返回解析失败: {r.stdout[:200]}")
+        return {"code": -1, "msg": r.stdout[:200]}
+
+# Step 1: 获取 tenant_access_token
+print("  → 获取 tenant_access_token...")
+token_resp = feishu_api("POST", "/open-apis/auth/v3/tenant_access_token/internal",
+    json_data={"app_id": FEISHU_APP_ID, "app_secret": FEISHU_APP_SECRET})
+token = token_resp.get("tenant_access_token")
+if not token:
+    print(f"  ❌ 获取 token 失败: {token_resp}")
+    sys.exit(1)
+print(f"  → Token 获取成功")
+
+# Step 2: 上传文件
+file_name = os.path.basename(output_path)
+file_ext = os.path.splitext(output_path)[1].lower()
+file_type_map = {".xlsx": "xls", ".xls": "xls", ".pdf": "pdf", ".docx": "doc", ".pptx": "ppt"}
+file_type = file_type_map.get(file_ext, "stream")
+
+print(f"  → 上传文件: {file_name} (type={file_type})...")
+upload_resp = feishu_api("POST", "/open-apis/im/v1/files", token=token,
+    form_fields={"file_type": file_type, "file_name": file_name, "file": f"@{output_path}"})
+file_key = upload_resp.get("data", {}).get("file_key")
+if not file_key:
+    print(f"  ❌ 文件上传失败: {upload_resp}")
+    sys.exit(1)
+print(f"  → 上传成功: {file_key}")
+
+# Step 3: 发送文件消息
+print(f"  → 发送文件到 user_id={SEND_TO}...")
+send_resp = feishu_api("POST", "/open-apis/im/v1/messages?receive_id_type=user_id", token=token,
+    json_data={
+        "receive_id": SEND_TO,
+        "msg_type": "file",
+        "content": json.dumps({"file_key": file_key})
+    })
+msg_id = send_resp.get("data", {}).get("message_id")
+if msg_id:
+    print(f"  ✅ 文件已发送，message_id={msg_id}")
+else:
+    print(f"  ⚠️  发送可能失败: {send_resp}")