ALL-teach_sys/frontend_大健康/convert_health_qa_data.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import json
from datetime import datetime

# 读取大健康问答内容数据
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/网页未导入数据/大健康产业/大健康问答内容.json', 'r', encoding='utf-8') as f:
    health_qa_data = json.load(f)

# 导师头像映射
mentor_avatars = {
    "李奇": "https://ddcz-1315997005.cos.ap-nanjing.myqcloud.com/static/img/teach_sys_teacher-avatar/recuW7dDIg60Tg.png",
    "宋积极(配方师gigi)": "https://ddcz-1315997005.cos.ap-nanjing.myqcloud.com/static/img/teach_sys_teacher-avatar/recuW7dxJ5E4Al.png",
    "吴兰": "https://ddcz-1315997005.cos.ap-nanjing.myqcloud.com/static/img/teach_sys_teacher-avatar/recuW7dxJ5t1Ii.jpeg",
    # 其他导师可以添加更多映射
}

# 默认机器人头像
robot_avatar = "https://ddcz-1315997005.cos.ap-nanjing.myqcloud.com/static/img/teach_sys_icon/recuWmDuekBTlr.png"

# 转换为专家支持中心格式
conversations = []

for idx, item in enumerate(health_qa_data, 1):
    messages = []

    # 构建对话消息
    # 流程1 - 用户问题
    if item.get("问题_流程1"):
        messages.append({
            "type": "user",
            "content": item["问题_流程1"],
            "time": item["流程1_时间"]
        })

    # 流程2 - 助手回答
    if item.get("回答_流程2"):
        mentor_name = item.get("查询导师名称", "多多畅职机器人")
        if item.get("问答类型") == "AI答疑":
            mentor_name = "多多畅职机器人"
            mentor_avatar = robot_avatar
        else:
            mentor_avatar = mentor_avatars.get(mentor_name, robot_avatar)
            if mentor_name != "多多畅职机器人":
                mentor_name += "老师"

        messages.append({
            "type": "assistant",
            "content": item["回答_流程2"],
            "mentor": mentor_name,
            "time": item["流程2_时间"],
            "mentorAvatar": mentor_avatar
        })

    # 流程3 - 用户问题
    if item.get("问题_流程3"):
        messages.append({
            "type": "user",
            "content": item["问题_流程3"],
            "time": item["流程3_时间"]
        })

    # 流程4 - 助手回答
    if item.get("回答_流程4"):
        mentor_name = item.get("查询导师名称", "多多畅职机器人")
        if item.get("问答类型") == "AI答疑":
            mentor_name = "多多畅职机器人"
            mentor_avatar = robot_avatar
        else:
            mentor_avatar = mentor_avatars.get(mentor_name, robot_avatar)
            if mentor_name != "多多畅职机器人":
                mentor_name += "老师"

        messages.append({
            "type": "assistant",
            "content": item["回答_流程4"],
            "mentor": mentor_name,
            "time": item["流程4_时间"],
            "mentorAvatar": mentor_avatar
        })

    # 流程5 - 用户问题
    if item.get("问题_流程5"):
        messages.append({
            "type": "user",
            "content": item["问题_流程5"],
            "time": item["流程5_时间"]
        })

    # 流程6 - 助手回答
    if item.get("回答_流程6"):
        mentor_name = item.get("查询导师名称", "多多畅职机器人")
        if item.get("问答类型") == "AI答疑":
            mentor_name = "多多畅职机器人"
            mentor_avatar = robot_avatar
        else:
            mentor_avatar = mentor_avatars.get(mentor_name, robot_avatar)
            if mentor_name != "多多畅职机器人":
                mentor_name += "老师"

        messages.append({
            "type": "assistant",
            "content": item["回答_流程6"],
            "mentor": mentor_name,
            "time": item["流程6_时间"],
            "mentorAvatar": mentor_avatar
        })

    # 获取对话日期（从第一条消息的时间提取年月）
    if messages:
        first_time = messages[0]["time"]
        try:
            # 解析时间格式 "2023/9/12 9:23"
            date_obj = datetime.strptime(first_time, "%Y/%m/%d %H:%M")
            conversation_date = f"{date_obj.year}年{date_obj.month}月"
        except:
            conversation_date = "2024年"

    # 确定问答类型
    qa_type = item.get("问答类型", "常规问题")
    if qa_type == "导师问答":
        qa_type = "专业知识"
    elif qa_type == "AI答疑":
        qa_type = "AI答疑"
    else:
        qa_type = "常规问题"

    # 构建对话对象
    if messages:
        conversation = {
            "id": idx,
            "title": item.get("问题标题（AI）", f"问题{idx}"),
            "status": "finish",
            "date": conversation_date,
            "type": qa_type,
            "messages": messages
        }
        conversations.append(conversation)

# 按时间排序（从最早的第一条消息时间开始）
def get_first_message_time(conv):
    if conv["messages"]:
        time_str = conv["messages"][0]["time"]
        try:
            return datetime.strptime(time_str, "%Y/%m/%d %H:%M")
        except:
            return datetime.now()
    return datetime.now()

# 按时间升序排序（早的在前）
conversations.sort(key=get_first_message_time)

# 构建最终的数据结构
expert_support_data = {
    "conversations": conversations
}

# 生成JS文件内容
js_content = f"""// 从大健康问答内容.json转换的专家支持中心数据
const expertSupportData = {json.dumps(expert_support_data, ensure_ascii=False, indent=2)};

export default expertSupportData;"""

# 保存到文件
output_path = 'src/data/expertSupportData.js'
with open(output_path, 'w', encoding='utf-8') as f:
    f.write(js_content)

print(f"✅ 成功转换 {len(conversations)} 条对话数据")
print(f"✅ 已保存到 {output_path}")