├── .gitignore
├── Annual-Report.py
├── Get-Eat-Data.py
├── LICENSE
├── README.md
├── figs
    ├── example-poster.png
    └── example.png
├── generate-poster.py
├── html-template
└── requirements.txt


/.gitignore:
--------------------------------------------------------------------------------
 1 | eat-data.json
 2 | 
 3 | **/__pycache__/
 4 | 
 5 | /.idea
 6 | /.vscode
 7 | **/.DS_Store
 8 | 
 9 | *.json
10 | *.html


--------------------------------------------------------------------------------
/Annual-Report.py:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import datetime as dt
  3 | import matplotlib.pyplot as plt
  4 | import matplotlib.cm as cm
  5 | import warnings
  6 | import json
  7 | 
  8 | # 指定字体
  9 | plt.rcParams['font.sans-serif'] = ['MiSans', 'SimHei', 'Hiragino Sans GB', 'Noto Sans SC', 'Noto Sans']
 10 | 
 11 | def convert_time(timestamp, time_zone = 8):
 12 |     '''
 13 |     时间转换
 14 |     '''
 15 |     # 转换为 UTC 时间
 16 |     utc_time = dt.datetime.fromtimestamp(timestamp, tz = dt.timezone.utc)
 17 |     # 转换为东八区时间
 18 |     converted_time = utc_time.astimezone(dt.timezone(dt.timedelta(hours = time_zone)))
 19 |     return converted_time
 20 | 
 21 | 
 22 | def load_eat_data(eat_data, time_zone = 8):
 23 |     '''
 24 |     加载消费数据
 25 |     '''
 26 | 
 27 |     data = json.load(eat_data)
 28 |     entities = data.get("entities", [])
 29 |     df = pd.DataFrame(entities)
 30 | 
 31 |     # 取反并乘100取整，修复浮点精度问题
 32 |     df['amount'] = (df['amount'] * -100).round().astype(int)
 33 |     df['amount'] = df['amount'] / 100
 34 |     df['orderTime'] = df['orderTime'].apply(lambda x: convert_time(x, time_zone))
 35 |     df['payTime'] = df['payTime'].apply(lambda x: convert_time(x, time_zone))
 36 | 
 37 |     # 去除年份、秒和时区
 38 |     df['formatted_orderTime'] = df['orderTime'].dt.strftime('%m月%d日%H点%M分')
 39 |     df['formatted_payTime'] = df['payTime'].dt.strftime('%m月%d日%H点%M分')
 40 | 
 41 |     # 提取日期和时分秒
 42 |     df['date'] = df['payTime'].dt.date  # 提取日期部分
 43 |     df['time'] = df['payTime'].dt.time  # 提取时分秒部分
 44 | 
 45 |     return df
 46 | 
 47 | def filter(df):
 48 |     '''
 49 |     过滤数据
 50 |     '''
 51 |     # 非消费（支出）数据
 52 |     df = df[~(df['amount'] < 0)]
 53 | 
 54 |     # 非餐饮数据
 55 |     filter_keys = ['电瓶车', '游泳', '核减', '浴室', '教材科' ,'校医院', '充值', r'沪(?:\w){6,7}'] # 需要继续补充
 56 |     for k in filter_keys:
 57 |         df = df[~df['merchant'].str.contains(k)]
 58 |     return df
 59 | 
 60 | def annual_analysis(df):
 61 |     '''
 62 |     年度消费分析
 63 |     '''
 64 | 
 65 |     print("\n思源码年度消费报告：")
 66 | 
 67 |     # 总消费
 68 |     total_value = df['amount'].sum()
 69 |     print(f"\n  2024年，你在交大共消费了 {total_value:.2f} 元。")
 70 | 
 71 |     # 第一笔消费
 72 |     first_row = df.iloc[-1]
 73 |     print(f"\n  {first_row['formatted_payTime']}，你在 {first_row['merchant']} 开启了第一笔在交大的消费，花了 {first_row['amount']:.2f} 元。")
 74 |     print("  在交大的每一年都要有一个美好的开始。")
 75 | 
 76 |     # 最大消费
 77 |     max_row = df.loc[df['amount'].idxmax()]
 78 |     print(f"\n  今年 {max_row['formatted_payTime']}，你在交大的 {max_row['merchant']} 单笔最多消费了 {max_row['amount']:.2f} 元。")
 79 |     print("  哇，真是胃口大开的一顿！")
 80 | 
 81 |     # 最常消费
 82 |     most_frequent_merchant = df['merchant'].mode()[0]
 83 |     most_frequent_merchant_count = df[df['merchant'] == most_frequent_merchant].shape[0]
 84 |     most_frequent_merchant_total = df[df['merchant'] == most_frequent_merchant]['amount'].sum()
 85 |     print(f"\n  你最常前往 {most_frequent_merchant} ，一共 {most_frequent_merchant_count} 次，总共花了 {most_frequent_merchant_total:.2f} 元。")
 86 |     print("  这里的美食真是让你回味无穷。")
 87 | 
 88 |     # 最多消费
 89 |     most_expensive_merchant = df.groupby('merchant')['amount'].sum().idxmax()
 90 |     most_expensive_merchant_count = df[df['merchant'] == most_expensive_merchant].shape[0]
 91 |     most_expensive_merchant_total = df.groupby('merchant')['amount'].sum().max()
 92 |     print(f"\n  你在 {most_expensive_merchant} 消费最多，{most_expensive_merchant_count} 次消费里，一共花了 {most_expensive_merchant_total:.2f} 元。")
 93 |     print("  想来这里一定有你钟爱的菜品。")
 94 | 
 95 |     # 早中晚消费
 96 |     df['hour'] = df['payTime'].dt.hour
 97 |     morning = df[(df['hour'] >= 6) & (df['hour'] < 9)]['amount'].shape[0]
 98 |     noon = df[(df['hour'] >= 11) & (df['hour'] < 14)]['amount'].shape[0]
 99 |     night = df[(df['hour'] >= 17) & (df['hour'] < 19)]['amount'].shape[0]
100 |     print(f"\n  你今年一共在交大吃了 {morning} 顿早餐，{noon} 顿午餐，{night} 顿晚餐。")
101 |     print("  在交大的每一顿都要好好吃饭～")
102 | 
103 |     # 按日期分组，找到每一天中最早的时间
104 |     try:
105 |         earliest_rows_per_day = df.loc[df.groupby('date')['time'].idxmin()]
106 |         overall_earliest_row = earliest_rows_per_day.loc[earliest_rows_per_day['time'].idxmin()]
107 |         print(f"\n  {overall_earliest_row['formatted_payTime']} 是你今年最早的一次用餐，你一早就在 {overall_earliest_row['merchant']} 吃了 {overall_earliest_row['amount']:.2f} 元。")
108 |     # 错误似乎是因为pandas版本过低导致的，建议更新
109 |     except Exception:
110 |         print(f"\n  获取每日最早消费时出错，请更新pandas: pip install --upgrade pandas")
111 | 
112 | 
113 |     # 月份消费金额分布
114 |     df['month'] = df['payTime'].dt.month
115 |     most_expensive_month = df.groupby('month')['amount'].sum().idxmax()
116 |     most_expensive_month_total = df.groupby('month')['amount'].sum().max()
117 |     print(f"\n  你在 {most_expensive_month} 月消费最多，一共花了 {most_expensive_month_total:.2f} 元。")
118 |     print("  来看看你的月份分布图")
119 | 
120 |     # 按食堂分组，统计总消费金额
121 |     grouped = df.groupby('merchant')['amount'].sum().sort_values(ascending=False)
122 |     # 计算总消费金额
123 |     total_amount = grouped.sum()
124 |     # 找到占比 >= 1% 的食堂
125 |     threshold = 0.01  # 占比 1%
126 |     major_merchants = grouped[grouped / total_amount >= threshold]
127 |     # 将占比 < 1% 的合并为 "其他"
128 |     other_sum = grouped[grouped / total_amount < threshold].sum()
129 |     # 合并为新的 Series
130 |     final_grouped = pd.concat([major_merchants, pd.Series({'其他': other_sum})])
131 | 
132 | 
133 |     # 绘图
134 |     fig, axs = plt.subplots(1, 3, figsize=(20, 6))
135 | 
136 |     # 食堂消费金额饼图
137 |     final_grouped.plot(
138 |         kind='pie', autopct='%1.1f%%', startangle=90, textprops={'fontsize': 12}, ax=axs[0]
139 |     )
140 |     axs[0].set_ylabel('')  # 去掉 y 轴标签
141 |     axs[0].set_title('各食堂总消费金额分布', fontsize=16)
142 | 
143 |     # 月份消费金额分布
144 |     df['month'] = df['payTime'].dt.month
145 |     monthly_amount = df.groupby('month')['amount'].sum()
146 |     axs[1].bar(monthly_amount.index, monthly_amount.values, color='skyblue')
147 |     axs[1].set_title('月份消费金额分布', fontsize=16)
148 |     axs[1].set_xlabel('月份', fontsize=12)
149 |     axs[1].set_ylabel('消费金额', fontsize=12)
150 |     axs[1].set_xticks(range(1, 13))  # 确保横坐标是 1 到 12 月份
151 | 
152 |     # 一天内消费时间分布
153 |     axs[2].hist(df['hour'], bins=24, color='skyblue', edgecolor='black')
154 |     axs[2].set_title('一天内消费时间分布', fontsize=16)
155 |     axs[2].set_xlabel('时间 (小时)', fontsize=12)
156 |     axs[2].set_ylabel('消费次数', fontsize=12)
157 |     axs[2].set_xticks(range(0, 24))  # 确保横坐标是 0 到 23 小时
158 | 
159 |     print("\n不管怎样，吃饭要紧")
160 |     print("2025年也要记得好好吃饭喔(⌒▽⌒)☆ \n")
161 | 
162 |     # 调整布局和显示
163 |     plt.tight_layout()
164 |     with warnings.catch_warnings(record=True) as warns:
165 |         warnings.simplefilter("always", UserWarning)
166 |         plt.show()
167 |         if not any(item.category == UserWarning for item in warns):
168 |             print("未知`plt.show()`错误。请更新matplotlib: pip install --upgrade matplotlib")
169 |             raise
170 |         print("对不起，当前无法显示图表。你可以输入图片名称保存图表，也可以回车并不保存图片。")
171 |         filename = input("图片名称（不需要后缀）：")
172 |         if filename:
173 |             plt.savefig(f"{filename}.png")
174 | 
175 |     input()
176 | 
177 | 
178 | 
179 | if __name__ == "__main__":
180 |     try:
181 |         with open("eat-data.json", 'r', encoding='utf-8') as eat_data:
182 |             eat_data_df = load_eat_data(eat_data)
183 | 
184 |         # 现在默认启用过滤
185 |         eat_data_df = filter(eat_data_df)
186 |         annual_analysis(eat_data_df)
187 |     except FileNotFoundError:
188 |         print("\n首次运行，请先运行 Get-Eat-Data 以获取消费数据")
189 |         print("如果已经运行过 Get-Eat-Data，请查看 README 中的问题解答")
190 |         input("按回车键退出...")
191 |     except Exception:
192 |         print("\n发生其他错误")
193 |         raise
194 | 


--------------------------------------------------------------------------------
/Get-Eat-Data.py:
--------------------------------------------------------------------------------
  1 | import json
  2 | from requests import get, post
  3 | from requests.auth import HTTPBasicAuth
  4 | from urllib.parse import urlencode
  5 | 
  6 | # 配置参数
  7 | AUTHORIZATION_URL = "https://jaccount.sjtu.edu.cn/oauth2/authorize"
  8 | API_URL = "https://api.sjtu.edu.cn/v1/unicode/transactions"
  9 | TOKEN_URL = "https://jaccount.sjtu.edu.cn/oauth2/token"
 10 | REDIRECT_URI = "https://net.sjtu.edu.cn"
 11 | STATE = ""  
 12 | BEGIN_DATE = 1704038400
 13 | 
 14 | # 设置 client_id 和 client_secret
 15 | CLIENT_ID = ""  
 16 | CLIENT_SECRET = ""  
 17 | 
 18 | def get_authorization_code():
 19 |     """
 20 |     构造授权请求 URL
 21 |     """
 22 |     params = {
 23 |         "response_type": "code",
 24 |         "client_id": CLIENT_ID,
 25 |         "redirect_uri": REDIRECT_URI,
 26 |         "scope": "",
 27 |         "state": STATE
 28 |     }
 29 |     auth_url = f"{AUTHORIZATION_URL}?{urlencode(params)}"
 30 |     print(f"\n请在浏览器中打开以下链接并登录:\n{auth_url}\n")
 31 | 
 32 |     # 手动输入授权后的回调 URL
 33 |     redirect_response = input("登录完毕后，请稍等片刻至跳转到网络信息中心页面\n此时复制浏览器地址栏中的完整链接，并粘贴到这里，按回车确认: ")
 34 |     # 提取 code 参数
 35 |     from urllib.parse import urlparse, parse_qs
 36 |     query_params = parse_qs(urlparse(redirect_response).query)
 37 |     return query_params.get("code", [None])[0]
 38 | 
 39 | def get_access_token(authorization_code):
 40 |     """
 41 |     使用授权码获取访问令牌 (Access Token)
 42 |     """
 43 |     # 构造请求头，使用 Basic Auth 传递 client_id 和 client_secret
 44 |     headers = {
 45 |         "Content-Type": "application/x-www-form-urlencoded"
 46 |     }
 47 |     # 使用 HTTPBasicAuth 自动生成 Basic Authorization 头
 48 |     auth = HTTPBasicAuth(CLIENT_ID, CLIENT_SECRET)
 49 | 
 50 |     # 构造请求体
 51 |     data = {
 52 |         "grant_type": "authorization_code",  # 固定参数
 53 |         "code": authorization_code,         # 授权码
 54 |         "redirect_uri": REDIRECT_URI        # 重定向 URI，必须与之前一致
 55 |     }
 56 | 
 57 |     # 发起 POST 请求到 TOKEN_URL
 58 |     response = post(TOKEN_URL, headers=headers, auth=auth, data=data)
 59 | 
 60 |     # 检查返回结果
 61 |     if response.status_code == 200:
 62 |         # 成功获取令牌，返回 JSON 响应
 63 |         return response.json()
 64 |     else:
 65 |         # 发生错误，打印状态码和错误信息
 66 |         print("获取令牌失败:")
 67 |         print(f"状态码: {response.status_code}")
 68 |         print(f"响应: {response.text}")
 69 |         return None
 70 | 
 71 | def get_eat_data(access_token, begin_date = BEGIN_DATE):
 72 |     """
 73 |     获取消费数据
 74 |     """
 75 |     params = {
 76 |         "access_token": access_token,
 77 |         "channel": "",
 78 |         "start": 0,
 79 |         "beginDate": begin_date,
 80 |         "status": ""
 81 |     }
 82 | 
 83 |     # 发起请求
 84 |     try:
 85 |         response = get(API_URL, params=params)
 86 |         
 87 |         # 检查请求是否成功
 88 |         if response.status_code == 200:
 89 |             # 解析响应 JSON 数据
 90 |             data = response.json()
 91 |             
 92 |             if data.get('errno', 0) != 0:
 93 |                 print(data)
 94 |                 # 防止泄露 client_id 和 client_secret，只放错误码
 95 |                 error_code = data.get('errno', '无错误码')
 96 |                 print(f"API 错误: {error_code})")
 97 |                 raise Exception()
 98 |             else:
 99 |                 print("消费数据获取成功")
100 |                 
101 |                 # 保存到文件
102 |                 with open("eat-data.json", "w", encoding="utf-8") as file:
103 |                     json.dump(data, file, ensure_ascii=False, indent=4)
104 |                 
105 |                 print("\n消费数据已保存")
106 |             
107 |             return data
108 |         else:
109 |             print(f"\n请求失败，状态码: {response.status_code}")
110 |             print(f"错误信息: {response.text}")
111 |     except Exception as e:
112 |         print(f"\n请求过程中发生错误，请检查网络及代理设置，或删除目录下的 eat-data.json 文件后重试")
113 | 
114 | 
115 | if __name__ == "__main__":
116 |     try:
117 |         print("\n首次运行，请先登录并获取消费数据")
118 |         # 获取授权码
119 |         authorization_code = get_authorization_code()
120 |         if not authorization_code:
121 |             print("\n授权码获取失败，请检查你的返回 URL\n")
122 |             exit()
123 |         print(f"\n取得授权码: {authorization_code}")
124 | 
125 |         # 获取访问令牌
126 |         token_response = get_access_token(authorization_code)
127 |         access_token = token_response.get('access_token')
128 |         if token_response:
129 |             print("\n成功获取访问令牌(Access Token):")
130 |             print(f"{access_token}\n")
131 | 
132 |         # 获取消费数据
133 |         if get_eat_data(access_token):
134 |             input("请前往 Annual-Report.py 以继续...")
135 | 
136 |     except Exception:
137 |         print("Unknown Error：500")
138 |         input("按回车键退出...")
139 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2024 Milvoid
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # SJTU-Annual-Eat
  2 | 
  3 | 思源码消费年度总结
  4 | 
  5 | 来看看你今年都在交大消费了些什么吧
  6 | 
  7 | ## Quick Start
  8 | 
  9 | > 同时支持 Windows 与 macOS
 10 | 
 11 | 前往 [Release 页面](https://github.com/Milvoid/SJTU-Annual-Eat/releases/tag/1.0.1) 下载 `Release.zip`
 12 | 
 13 | 解压后得到 `Get-Eat-Data` 与 `Annual-Report.py` 
 14 | 
 15 | 首先运行  `Get-Eat-Data` ，按照提示获取数据后得到 `eat-data.json`
 16 | 
 17 | 之后再运行  `Annual-Report.py`  即可生成年度报告啦
 18 | 
 19 | ## Common Issues
 20 | 
 21 | - Annual-Report.py 闪了一下就没了
 22 | 
 23 | 可能是所需的库没有安装，可以用文本编辑器打开文件，之后查看最上方需要导入的模块是否有缺失
 24 | 
 25 | - Access Token 获取失败
 26 | 
 27 | 可以确认一下自己没有使用代理，sjtu服务器好像会somehow因为代理拒绝访问
 28 | 
 29 | - 运行到早中晚餐之后报错
 30 | 
 31 | 应该是统计最早一餐部分的兼容性问题，可以手动注释掉该部分，或者下载新的 Release 这部分失败之后自动跳过
 32 | 
 33 | 代码有点bug，按日期分组,找到每一天中最早的时间那边会错误，不知道是不是 pandas 版本问题
 34 | 
 35 | 如果是 `reduction operation 'argmin' not allowed for this dtype` 问题，可以在函数load_eat_data的最后加一行
 36 | 
 37 | ```python
 38 | df['time_in_seconds'] = df['payTime'].dt.hour * 3600 + df['payTime'].dt.minute * 60 + df['payTime'].dt.second
 39 | ```
 40 | 
 41 | 然后把“按日期分组，找到每一天中最早的时间”下面两行中的'time'都改成'time_in_seconds'就行了。
 42 | 
 43 | - 运行 Get-Eat-Data 后仍然找不到 json 文件
 44 | 
 45 | 可以在终端里先 cd 到 json 文件所在路径，之后从终端运行 Annual-Report.py；或者直接把 Annual-Report.py 的文件路径改成绝对路径
 46 | 
 47 | ## Example
 48 | 
 49 | 运行 `Annual-Report.py` 之后，你就可以看到今年的一些 Highlight 以及相关统计图，譬如：
 50 | 
 51 | ```shell
 52 | 思源码年度消费报告：
 53 | 
 54 |   2024年，你在交大共消费了 1885.17 元。
 55 | 
 56 |   01月01日17点43分，你在 闵行三餐外婆桥 开启了第一笔在交大的消费，花了 17.0 元。
 57 |   在交大的每一年都要有一个美好的开始。
 58 | 
 59 |   今年 02月20日11点56分，你在交大的 教材科 单笔最多消费了 41.5 元。
 60 |   哇，真是胃口大开的一顿！
 61 | 
 62 |   你在 闵行三餐学生餐厅 消费最多，38 次消费里，一共花了 493.38 元。
 63 |   想来这里一定有你钟爱的菜品。
 64 | 
 65 |   你今年一共在交大吃了 0 顿早餐，62 顿午餐，55 顿晚餐。
 66 |   在交大的每一顿都要好好吃饭～
 67 | 
 68 |   05月08日09点57分 是你今年最早的一次用餐，你一早就在 沪FP2215 吃了 6.0 元。
 69 | 
 70 |   你在 10 月消费最多，一共花了 308.2 元。
 71 |   来看看你的月份分布图
 72 | 
 73 | 不管怎样，吃饭要紧
 74 | 2025年也要记得好好吃饭喔(⌒▽⌒)☆ 
 75 | ```
 76 | 
 77 | ![example](https://raw.githubusercontent.com/Milvoid/SJTU-Annual-Eat/main/figs/example.png)
 78 | 
 79 | ## Poster
 80 | 
 81 | 你也可以通过运行下面的脚本来生成一幅简单的海报，你可以用你的浏览器打开```海报.html```和截图。
 82 | ```
 83 | python generate-poster.py
 84 | ```
 85 | 
 86 | ![](./figs/example-poster.png)
 87 | 
 88 | ## Notes
 89 | 
 90 | `Get-Eat-Data.exe` 可直接运行；如果需要运行 `Get-Eat-Data.py`，请参考 [SJTU 开发者文档](https://developer.sjtu.edu.cn/auth/oauth.html) 填写 `client_id` 和 `client_secret`
 91 | 
 92 | 特别感谢来自 Boar 大佬的帮助
 93 | 
 94 | 以及感谢本仓库帮忙修代码的 Contributors
 95 | 
 96 | ## Related Links
 97 | 
 98 | https://github.com/wzh656/SJTU-Annual-Report
 99 | 
100 | 网页版本的年度报告，适合直接运行
101 | 


--------------------------------------------------------------------------------
/figs/example-poster.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Milvoid/SJTU-Annual-Eat/3c4fb0b9d66727e037aa1cd1961c7e90c9da37ea/figs/example-poster.png


--------------------------------------------------------------------------------
/figs/example.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Milvoid/SJTU-Annual-Eat/3c4fb0b9d66727e037aa1cd1961c7e90c9da37ea/figs/example.png


--------------------------------------------------------------------------------
/generate-poster.py:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import datetime as dt
  3 | import matplotlib.pyplot as plt
  4 | import matplotlib.cm as cm
  5 | import json
  6 | from jinja2 import Template
  7 | 
  8 | # 指定字体
  9 | # plt.rcParams['font.sans-serif'] = ['MiSans', 'SimHei', 'Hiragino Sans GB', 'Noto Sans SC', 'Noto Sans']
 10 | 
 11 | html_data = {
 12 |     'total_spending_text': '',
 13 |     'first_spending_text': '',
 14 |     'highest_single_spending_text': '',
 15 |     'favorite_place_spending_text': '',
 16 |     'meal_counts_text': '',
 17 |     'earliest_meal_text': '',
 18 |     'most_expensive_month_text': '',
 19 |     'pie_label_1': '',
 20 |     'pie_data_1': '',
 21 |     'pie_data_2': ''
 22 | }
 23 | 
 24 | 
 25 | def convert_time(timestamp, time_zone = 8):
 26 |     '''
 27 |     时间转换
 28 |     '''
 29 |     # 转换为 UTC 时间
 30 |     utc_time = dt.datetime.fromtimestamp(timestamp, tz = dt.timezone.utc)
 31 |     # 转换为东八区时间
 32 |     converted_time = utc_time.astimezone(dt.timezone(dt.timedelta(hours = time_zone)))
 33 |     return converted_time
 34 | 
 35 | 
 36 | def load_eat_data(eat_data, time_zone = 8):
 37 |     '''
 38 |     加载消费数据
 39 |     '''
 40 | 
 41 |     data = json.load(eat_data)
 42 |     entities = data.get("entities", [])
 43 |     df = pd.DataFrame(entities)
 44 | 
 45 |     # 取反并乘100取整，修复浮点精度问题
 46 |     df['amount'] = (df['amount'] * -100).round().astype(int)
 47 |     df['amount'] = df['amount'] / 100
 48 |     df['orderTime'] = df['orderTime'].apply(lambda x: convert_time(x, time_zone))
 49 |     df['payTime'] = df['payTime'].apply(lambda x: convert_time(x, time_zone))
 50 | 
 51 |     # 去除年份、秒和时区
 52 |     df['formatted_orderTime'] = df['orderTime'].dt.strftime('%m月%d日%H点%M分')
 53 |     df['formatted_payTime'] = df['payTime'].dt.strftime('%m月%d日%H点%M分')
 54 | 
 55 |     # 提取日期和时分秒
 56 |     df['date'] = df['payTime'].dt.date  # 提取日期部分
 57 |     df['time'] = df['payTime'].dt.time  # 提取时分秒部分
 58 | 
 59 |     return df
 60 | 
 61 | def filter(df):
 62 |     '''
 63 |     过滤数据
 64 |     '''
 65 |     # 非消费（支出）数据
 66 |     df = df[~(df['amount'] < 0)]
 67 | 
 68 |     # 非餐饮数据
 69 |     filter_keys = ['电瓶车', '游泳', '核减', '浴室', '教材科' ,'校医院', '充值', r'沪(?:\w){6,7}'] # 需要继续补充
 70 |     for k in filter_keys:
 71 |         df = df[~df['merchant'].str.contains(k)]
 72 |     return df
 73 | 
 74 | def annual_analysis(df):
 75 |     '''
 76 |     年度消费分析
 77 |     '''
 78 | 
 79 |     # 总消费
 80 |     total_value = df['amount'].sum()
 81 |     html_data['total_spending_text'] = f"2024年，你在交大共消费了<span class=\"highlight\"> {total_value:.2f} </span>元。"
 82 | 
 83 |     # 第一笔消费
 84 |     first_row = df.iloc[-1]
 85 |     html_data['first_spending_text'] = f"<span class=\"highlight\">{first_row['formatted_payTime']}</span>，你在<span class=\"highlight\"> {first_row['merchant']} </span>开启了第一笔在交大的消费，花了<span class=\"highlight\"> {first_row['amount']:.2f} </span>元。"
 86 | 
 87 |     # 最大消费
 88 |     max_row = df.loc[df['amount'].idxmax()]
 89 |     html_data['highest_single_spending_text'] = f"今年<span class=\"highlight\"> {max_row['formatted_payTime']}</span>，你在交大的<span class=\"highlight\"> {max_row['merchant']} </span>单笔最多消费了<span class=\"highlight\"> {max_row['amount']:.2f} </span>元。"
 90 | 
 91 |     # 最常消费
 92 |     most_frequent_merchant = df['merchant'].mode()[0]
 93 |     most_frequent_merchant_count = df[df['merchant'] == most_frequent_merchant].shape[0]
 94 |     most_frequent_merchant_total = df[df['merchant'] == most_frequent_merchant]['amount'].sum()
 95 |     html_data['favorite_place_spending_text'] = f"你最常前往<span class=\"highlight\"> {most_frequent_merchant} </span>，一共<span class=\"highlight\"> {most_frequent_merchant_count} </span>次，总共花了<span class=\"highlight\"> {most_frequent_merchant_total:.2f} </span>元。"
 96 | 
 97 |     # 早中晚消费
 98 |     df['hour'] = df['payTime'].dt.hour
 99 |     morning = df[(df['hour'] >= 6) & (df['hour'] < 9)]['amount'].shape[0]
100 |     noon = df[(df['hour'] >= 11) & (df['hour'] < 14)]['amount'].shape[0]
101 |     night = df[(df['hour'] >= 17) & (df['hour'] < 19)]['amount'].shape[0]
102 |     html_data['meal_counts_text'] = f"你今年一共在交大吃了<span class=\"highlight\"> {morning} </span>顿早餐，<span class=\"highlight\"> {noon} </span>顿午餐，<span class=\"highlight\"> {night} </span>顿晚餐。"
103 | 
104 |     # 按日期分组，找到每一天中最早的时间
105 |     try:
106 |         earliest_rows_per_day = df.loc[df.groupby('date')['time'].idxmin()]
107 |         overall_earliest_row = earliest_rows_per_day.loc[earliest_rows_per_day['time'].idxmin()]
108 |         html_data['earliest_meal_text'] = f"<span class=\"highlight\">{overall_earliest_row['formatted_payTime']} </span>是你今年最早的一次用餐，你一早就在<span class=\"highlight\"> {overall_earliest_row['merchant']} </span>吃了<span class=\"highlight\"> {overall_earliest_row['amount']:.2f} </span>元。"
109 |         # print(f"\n <span class=\"highlight\"> {html_data['earliest_meal_text']}")
110 |     # 错误似乎是因为pandas版本过低导致的，建议更新
111 |     except Exception:
112 |         print(f"\n  获取每日最早消费时出错，请更新pandas: pip install --upgrade pandas")
113 | 
114 | 
115 |     # 月份消费金额分布
116 |     df['month'] = df['payTime'].dt.month
117 |     most_expensive_month = df.groupby('month')['amount'].sum().idxmax()
118 |     most_expensive_month_total = df.groupby('month')['amount'].sum().max()
119 | 
120 |     # 按食堂分组，统计总消费金额
121 |     grouped = df.groupby('merchant')['amount'].sum().sort_values(ascending=False)
122 |     # 计算总消费金额
123 |     total_amount = grouped.sum()
124 |     # 找到占比 >= 1% 的食堂
125 |     threshold = 0.01  # 占比 1%
126 |     major_merchants = grouped[grouped / total_amount >= threshold]
127 |     if len(major_merchants) > 9:
128 |         major_merchants = grouped[:9]
129 |         other_sum = grouped[9:].sum()
130 |     # 将占比 < 1% 的合并为 "其他"
131 |     else:
132 |         other_sum = grouped[grouped / total_amount < threshold].sum()
133 |     # 合并为新的 Series
134 |     final_grouped = pd.concat([major_merchants, pd.Series({'其他': other_sum})])
135 |     html_data['pie_data_1'] = list(final_grouped.values)
136 |     html_data['pie_label_1'] = list(final_grouped.index)
137 | 
138 |     df['month'] = df['payTime'].dt.month
139 |     monthly_amount = df.groupby('month')['amount'].sum()
140 |     html_data['pie_data_2'] = list(monthly_amount.values)
141 | 
142 | 
143 | 
144 | if __name__ == "__main__":
145 |     try:
146 |         with open("eat-data.json", 'r', encoding='utf-8') as eat_data:
147 |             eat_data_df = load_eat_data(eat_data)
148 | 
149 |         # 现在默认启用过滤
150 |         eat_data_df = filter(eat_data_df)
151 |         annual_analysis(eat_data_df)
152 | 
153 |         with open('html-template', 'r', encoding='utf-8') as file:
154 |             template_content = file.read()
155 | 
156 |         template = Template(template_content)
157 |         rendered_html = template.render(html_data)
158 |         with open('海报.html', 'w', encoding='utf-8') as file:
159 |             file.write(rendered_html)
160 | 
161 |     except FileNotFoundError:
162 |         print("\n首次运行，请先运行 Get-Eat-Data 以获取消费数据")
163 |         print("如果已经运行过 Get-Eat-Data，请查看 README 中的问题解答")
164 |         input("按回车键退出...")
165 |     except Exception:
166 |         print("\n发生其他错误")
167 |         raise
168 | 


--------------------------------------------------------------------------------
/html-template:
--------------------------------------------------------------------------------
  1 | <!DOCTYPE html>
  2 | <html lang="zh">
  3 | <head>
  4 |     <meta charset="UTF-8">
  5 |     <meta name="viewport" content="width=device-width, initial-scale=1.0">
  6 |     <title>思源码年度消费报告 2024</title>
  7 |     <script src="https://cdn.jsdelivr.net/npm/chart.js"></script> <!-- 引入Chart.js -->
  8 |     <script src="https://cdn.jsdelivr.net/npm/chartjs-plugin-datalabels"></script> <!-- 引入chartjs-plugin-datalabels -->
  9 |     <style>
 10 |         body {
 11 |             font-family: 'Arial', sans-serif;
 12 |             margin: 0;
 13 |             padding: 0;
 14 |             background-color: #f0f4f8; /* 淡灰蓝背景色 */
 15 |             height: 100vh;
 16 |             display: flex;
 17 |             justify-content: center;
 18 |             align-items: center;
 19 |             color: #333;
 20 |         }
 21 |         .container {
 22 |             width: 80%;
 23 |             max-width: 1000px;
 24 |             background-color: rgba(255, 255, 255, 0.95); /* 半透明白色背景 */
 25 |             border-radius: 15px;
 26 |             padding: 30px;
 27 |             box-shadow: 0 6px 18px rgba(0, 0, 0, 0.1);
 28 |         }
 29 |         h1 {
 30 |             text-align: center;
 31 |             font-size: 2.5em;
 32 |             color: #2c3e50;
 33 |             margin-bottom: 20px;
 34 |         }
 35 |         .section {
 36 |             margin-bottom: 20px;
 37 |         }
 38 |         .highlight {
 39 |             font-weight: bold;
 40 |             color: #3498db;
 41 |         }
 42 |         p {
 43 |             line-height: 1.4; /* 普通段落的行间距较小 */
 44 |             font-size: 1.2em;
 45 |             color: #333;
 46 |             margin: 10px 0;
 47 |         }
 48 |         p.double-spacing {
 49 |             line-height: 1.8; /* 两行文字之间保持稍大的行间距 */
 50 |         }
 51 |         .footer {
 52 |             text-align: center;
 53 |             font-size: 1.1em;
 54 |             color: #7f8c8d;
 55 |             margin-top: 40px;
 56 |         }
 57 |         .footer .emoji {
 58 |             font-size: 30px;
 59 |         }
 60 |         .month-charts {
 61 |             display: flex;
 62 |             justify-content: space-around;
 63 |             margin-top: 30px;
 64 |         }
 65 |         .chart-container {
 66 |             width: 45%;
 67 |             max-width: 500px;
 68 |             margin: 0 auto;
 69 |         }
 70 |         .header {
 71 |             background-color: #f7f7f7; /* 更素淡的背景色 */
 72 |             padding: 40px 0;
 73 |             text-align: center;
 74 |             border-radius: 15px;
 75 |             color: #333;
 76 |             font-size: 1.8em;
 77 |         }
 78 |     </style>
 79 | </head>
 80 | <body>
 81 | 
 82 |     <div class="container">
 83 |         <div class="header">
 84 |             思源码年度消费报告 2024
 85 |         </div>
 86 | 
 87 |         <div class="section">
 88 |             <p>{{ total_spending_text }}</p>
 89 |         </div>
 90 | 
 91 |         <div class="section">
 92 |             <p class="double-spacing">{{ first_spending_text }}</p>
 93 |             <p>在交大的每一年都要有一个美好的开始。</p>
 94 |         </div>
 95 | 
 96 |         <div class="section">
 97 |             <p class="double-spacing">{{ highest_single_spending_text }}</p>
 98 |             <p>哇，真是胃口大开的一顿！</p>
 99 |         </div>
100 | 
101 |         <div class="section">
102 |             <p class="double-spacing">{{ favorite_place_spending_text }}</p>
103 |             <p>想来这里一定有你钟爱的菜品。</p>
104 |         </div>
105 | 
106 |         <div class="section">
107 |             <p class="double-spacing">{{ meal_counts_text }}</p>
108 |             <p>在交大的每一顿都要好好吃饭～</p>
109 |         </div>
110 | 
111 |         <div class="section">
112 |             <p class="double-spacing">{{ earliest_meal_text }}</p>
113 |         </div>
114 | 
115 |         <div class="section">
116 |             <p class="double-spacing">{{ most_expensive_month_text }}</p>
117 |         </div>
118 | 
119 |         <!-- 两个并排的饼状图 -->
120 |         <div class="month-charts">
121 |             <div class="chart-container">
122 |                 <h2 style="text-align: center;">食堂消费分布</h2>
123 |                 <canvas id="pieChart1"></canvas> <!-- 第一个饼状图 -->
124 |             </div>
125 |             <div class="chart-container">
126 |                 <h2 style="text-align: center;">月份消费分布</h2>
127 |                 <canvas id="pieChart2"></canvas> <!-- 第二个饼状图 -->
128 |             </div>
129 |         </div>
130 | 
131 |         <div class="footer">
132 |             <p>不管怎样，吃饭要紧</p>
133 |             <p>2025年也要记得好好吃饭喔 <span class="emoji">⌒▽⌒</span>☆</p>
134 |         </div>
135 |     </div>
136 | 
137 |     <script>
138 |         // 饼状图1数据
139 |         const data1 = {
140 |             labels: {{ pie_label_1 }},
141 |             datasets: [{
142 |                 label: '消费分布',
143 |                 data: {{ pie_data_1 }},
144 |                 backgroundColor: [
145 |                     '#A1C4D5', '#B7D3B2', '#F1E1A6', '#D6B8A8', '#E2C9C2', 
146 |                     '#A8D0B5', '#B8C7D1', '#E4D6C9', '#C1B8D9', '#D9E4B9'
147 |                 ], // 低饱和度的温和颜色
148 |                 borderColor: '#fff',
149 |                 borderWidth: 1
150 |             }]
151 |         };
152 | 
153 |         // 饼状图2数据
154 |         const data2 = {
155 |             labels: ['一月', '二月', '三月', '四月', '五月', '六月', '七月', '八月', '九月', '十月', '十一月', '十二月'],
156 |             datasets: [{
157 |                 label: '消费分布',
158 |                 data: {{ pie_data_2 }},
159 |                 backgroundColor: [
160 |                     '#D6E6F2', '#D0F0C0', '#F4E1B2', '#E1C7D0', '#F0D9C5',
161 |                     '#A7D1B8', '#B1C7E2', '#D9D0D4', '#C9B8E0', '#D4E2C7'
162 |                 ], // 另一组低饱和度颜色
163 |                 borderColor: '#fff',
164 |                 borderWidth: 1
165 |             }]
166 |         };
167 | 
168 |         // 饼状图1配置
169 |         const config1 = {
170 |             type: 'pie',
171 |             data: data1,
172 |             options: {
173 |                 responsive: true,
174 |                 plugins: {
175 |                     legend: {
176 |                         position: 'top',
177 |                     },
178 |                     tooltip: {
179 |                         callbacks: {
180 |                             label: function(tooltipItem) {
181 |                                 return tooltipItem.label + ': ' + tooltipItem.raw + '元';
182 |                             }
183 |                         }
184 |                     },
185 |                     datalabels: {
186 |                         formatter: (value, ctx) => {
187 |                             return value + '元';  // 显示数值
188 |                         },
189 |                         color: '#fff', // 数字颜色
190 |                         font: {
191 |                             weight: 'bold',
192 |                             size: 14
193 |                         },
194 |                         anchor: 'end', // 数字位置
195 |                         align: 'start' // 数字位置
196 |                     }
197 |                 }
198 |             }
199 |         };
200 | 
201 |         // 饼状图2配置
202 |         const config2 = {
203 |             type: 'pie',
204 |             data: data2,
205 |             options: {
206 |                 responsive: true,
207 |                 plugins: {
208 |                     legend: {
209 |                         position: 'top',
210 |                     },
211 |                     tooltip: {
212 |                         callbacks: {
213 |                             label: function(tooltipItem) {
214 |                                 return tooltipItem.label + ': ' + tooltipItem.raw + '元';
215 |                             }
216 |                         }
217 |                     },
218 |                     datalabels: {
219 |                         formatter: (value, ctx) => {
220 |                             return value + '元';  // 显示数值
221 |                         },
222 |                         color: '#fff', // 数字颜色
223 |                         font: {
224 |                             weight: 'bold',
225 |                             size: 14
226 |                         },
227 |                         anchor: 'end', // 数字位置
228 |                         align: 'start' // 数字位置
229 |                     }
230 |                 }
231 |             }
232 |         };
233 | 
234 |         // 渲染饼状图1
235 |         const ctx1 = document.getElementById('pieChart1').getContext('2d');
236 |         new Chart(ctx1, config1);
237 | 
238 |         // 渲染饼状图2
239 |         const ctx2 = document.getElementById('pieChart2').getContext('2d');
240 |         new Chart(ctx2, config2);
241 |     </script>
242 | 
243 | </body>
244 | </html>
245 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | matplotlib
2 | pandas
3 | requests
4 | jinja2


--------------------------------------------------------------------------------