first commit

.github/workflows/deploy.yml

@@ -0,0 +1,39 @@
+name: Deploy to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main  # 使用你的主分支名
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4  # 使用最新版本的 checkout
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4  # 使用最新版本的 setup-node
+        with:
+          node-version: 'lts/*'  # 使用 Node.js 的最新 LTS 版本
+
+      - name: List directory for debugging
+        run: ls -a
+
+      - name: Install pnpm
+        run: npm install -g pnpm
+
+      - name: Install dependencies with pnpm
+        run: cd pjallcate_frontend && pnpm install
+
+      - name: Build project with pnpm
+        run: cd pjallcate_frontend && pnpm run build-only
+
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v4  # 使用最新版本的 actions-gh-pages
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./pjallcated_frontend/dist  # 确保指向正确的构建输出目录
+          publish_branch: gh-pages

.gitignore

@@ -0,0 +1,16 @@
+# all node_modules
+**/node_modules
+
+# mysql infomation
+config
+
+# log
+**/*.log
+
+# raw html and excel file
+html存档
+
+# backend
+
+# frontend
+pjallcate_frontend/.vscode/settings.json

README.md

@@ -0,0 +1,7 @@
+## BBC6521 Project Allocation 2024/25: Project Allocation - Student View
+1. 网址 http://18.218.128.52/live24.html ，预计开放时间为10.23 15:30到(10.31日)?
+2. 前端和后端分别pnpm install, 前端pnpm dev，后端pnpm start
+3. 哎呀我知道allocated没打对，但是改又得重新配一遍，拉倒吧
+
+## MySQL相关
+会把mysql做成json，到时候部署GitHub Pages

excel2mysql.py

@@ -0,0 +1,53 @@
+import pandas as pd
+import mysql.connector
+from datetime import datetime
+import yaml
+
+with open('./config/mysqlinfo.yaml', 'r') as file:
+    config = yaml.safe_load(file)
+
+try:
+    print('try connecting')
+    conn = mysql.connector.connection.MySQLConnection(
+        host=config['database']['host'],
+        user=config['database']['user'],
+        password=config['database']['password'],
+        database=config['database']['databasename'],
+    )
+    print('connected')
+except mysql.connector.Error as err:
+    print(f"Errors: {err}")
+
+cursor = conn.cursor()
+
+date_part = '20241028'
+
+df = pd.read_excel(f'{date_part}.xlsx', sheet_name=None)
+
+# project_titles = {}
+# for sheet_name, data in df.items():
+#     for _, row in data.iterrows():
+#         project_id = row['Project ID']
+#         project_title = row['Project Title']
+#         if project_id not in project_titles:
+#             # 避免重复插入相同项目
+#             project_titles[project_id] = project_title
+#             sql = config['database']['py_query']['insert_projects']
+#             print(f"[{datetime.now().strftime("%Y-%m-%d %H:%M:%S")}] Inserting: {project_id}, {project_title}")
+#             cursor.execute(sql, (project_id, project_title))
+#         else:
+#             print(f"[{datetime.now().strftime("%Y-%m-%d %H:%M:%S")}] Project {project_id} already exists")
+
+for sheet_name, data in df.items():
+    time_part = sheet_name
+    datetime_value = datetime.strptime(date_part + time_part, '%Y%m%d%H%M%S')
+
+    for _, row in data.iterrows():
+        sql = config['database']['py_query']['insert_project_data']
+        allocated_to= row['Allocated to (BUPT no.)']
+        allocated_to = str(allocated_to).replace(".0",'') if not pd.isna(row['Allocated to (BUPT no.)']) else None
+        print(f"[{datetime.now().strftime("%Y-%m-%d %H:%M:%S")}] Inserting: {datetime_value}, {row['Project ID']}, {allocated_to}")
+        cursor.execute(sql, (datetime_value, row['Project ID'], allocated_to))
+conn.commit()
+cursor.close()
+conn.close()

gethtml.py

@@ -0,0 +1,64 @@
+import requests
+import time
+from datetime import datetime, timedelta
+
+def save_webpage(url):
+    current_time = datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+    filename = f"{current_time}.html"
+    max_retries = 5
+    retry_count = 0
+
+    while retry_count < max_retries:
+        try:
+            response = requests.get(url, timeout=10)
+            response.raise_for_status()
+
+            content = response.text
+
+            with open(filename, 'w', encoding='utf-8') as file:
+                file.write(content)
+
+            message = f"Saved {url} to {filename}"
+            print(message)
+            with open("log.log", "a", encoding="utf-8") as log_file:
+                log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {message}\n")
+            return
+
+        except Exception as e:
+            retry_count += 1
+            message = f"Retry {retry_count}/{max_retries} for {url} due to error: {e}"
+            print(message)
+            with open("log.log", "a", encoding="utf-8") as log_file:
+                log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {message}\n")
+
+            if retry_count == max_retries:
+                error_message = f"Failed to save {url} after {max_retries} retries: {e}"
+                print(error_message)
+                with open("log.log", "a", encoding="utf-8") as log_file:
+                    log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {error_message}\n")
+            else:
+                time.sleep(10)
+
+url = "http://18.218.128.52/live24.html"
+
+# 每5分钟的10秒更新
+while True:
+    now = datetime.now()
+    # 计算下一次5分钟周期的时间点（向上取整到最近的5分钟）
+    next_update = now + timedelta(minutes=(5 - now.minute % 5))
+    next_update = next_update.replace(second=10, microsecond=0)
+
+    # 如果当前时间已经超过了下一个更新时间点，则加5分钟
+    if next_update <= now:
+        next_update += timedelta(minutes=5)
+
+    next_update_message = f"Next update at: {next_update.strftime('%Y-%m-%d %H:%M:%S')}"
+    print(next_update_message)
+    with open("log.log", "a", encoding="utf-8") as log_file:
+        log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {next_update_message}\n")
+
+    # 需要等待的秒数
+    wait_time = (next_update - now).total_seconds()
+    time.sleep(wait_time)
+
+    save_webpage(url)

html2excel.py

@@ -0,0 +1,20 @@
+import pandas as pd
+import glob
+import os
+
+html_files = glob.glob('./html存档/linux/1028/*.html')
+
+if html_files:
+    workbook_name = html_files[0][20:20+10].replace('-', '') + '.xlsx'
+else:
+    raise FileNotFoundError("没有找到符合命名规则的HTML文件")
+
+with pd.ExcelWriter(workbook_name) as writer:
+    for html_file in html_files:
+        tables = pd.read_html(html_file)
+        df = tables[0]
+        sheet_name = os.path.splitext(html_file)[0][11+20:].replace('-', '')
+        df.to_excel(writer, sheet_name=sheet_name, index=False)
+        print(f'sheet_name: {sheet_name} successfully written')
+
+print(f"所有表格已成功写入 {workbook_name}")

html2mysql.py

@@ -0,0 +1,109 @@
+import requests
+import time
+from datetime import datetime, timedelta
+import mysql.connector
+import pandas as pd
+import atexit
+import yaml
+
+with open('./config/mysqlinfo.yaml', 'r') as file:
+    config = yaml.safe_load(file)
+
+LOGfile = f'./html存档/0000/log.log'
+current_time = datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+filename = f'./html存档/0000/{current_time}.html'
+
+def save_webpage(url):
+    global current_time, filename
+    current_time = datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+    filename = f'./html存档/0000/{current_time}.html'
+    max_retries = 5
+    retry_count = 0
+
+    while retry_count < max_retries:
+        try:
+            response = requests.get(url, timeout=10)
+            response.raise_for_status()
+
+            content = response.text
+
+            with open(filename, 'w', encoding='utf-8') as file:
+                file.write(content)
+
+            message = f"Saved {url} to {filename}"
+            print(message)
+            with open(LOGfile, "a", encoding="utf-8") as log_file:
+                log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {message}\n")
+            return
+
+        except Exception as e:
+            retry_count += 1
+            message = f"Retry {retry_count}/{max_retries} for {url} due to error: {e}"
+            print(message)
+            with open(LOGfile, "a", encoding="utf-8") as log_file:
+                log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {message}\n")
+            if retry_count == max_retries:
+                error_message = f"Failed to save {url} after {max_retries} retries: {e}"
+                print(error_message)
+                with open(LOGfile, "a", encoding="utf-8") as log_file:
+                    log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {error_message}\n")
+            else:
+                time.sleep(10)
+
+url = "http://18.218.128.52/live24.html"
+
+try:
+    print('try connecting')
+    conn = mysql.connector.connection.MySQLConnection(
+        host=config['database']['host'],
+        user=config['database']['user'],
+        password=config['database']['password'],
+        database=config['database']['databasename'],
+    )
+    print('connected')
+except mysql.connector.Error as err:
+    print(f"Errors: {err}")
+    exit(1)
+
+cursor = conn.cursor()
+
+def close_db_connection():
+    cursor.close()
+    conn.close()
+    print("Database connection closed.")
+
+atexit.register(close_db_connection)
+
+while True:
+    now = datetime.now()
+    next_update = now + timedelta(minutes=(5 - now.minute % 5))
+    next_update = next_update.replace(second=10, microsecond=0)
+    if next_update <= now:
+        next_update += timedelta(minutes=5)
+
+    next_update_message = f"Next update at: {next_update.strftime('%Y-%m-%d %H:%M:%S')}"
+    print(next_update_message)
+    with open(LOGfile, "a", encoding="utf-8") as log_file:
+        log_file.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {next_update_message}\n")
+
+    wait_time = (next_update - now).total_seconds()
+    time.sleep(wait_time)
+
+    save_webpage(url)
+
+
+    tables = pd.read_html(filename)
+    df = tables[0]
+    data = df
+
+    datetime_value = filename[14:33].replace("-", "")
+
+    for _, row in data.iterrows():
+        allocated_to = row['Allocated to (BUPT no.)'] if not pd.isna(row['Allocated to (BUPT no.)']) else None
+        project_id = row['Project ID']
+
+        sql = config['database']['py_query']['insert_project_data']
+        print(f"[{datetime.now().strftime('%Y-%m-%d-%H-%M-%S')}] ({_}) INSERT INTO project_data {datetime_value, project_id, allocated_to}")
+        cursor.execute(sql, (datetime_value, project_id, allocated_to))
+
+    conn.commit()

pjallcate_backend/package.json

@@ -0,0 +1,19 @@
+{
+  "name": "pjallcate_backend",
+  "version": "1.0.0",
+  "description": "",
+  "main": "server.js",
+  "scripts": {
+    "start": "node server.js",
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "dependencies": {
+    "cors": "^2.8.5",
+    "express": "^4.21.1",
+    "js-yaml": "^4.1.0",
+    "mysql2": "^3.11.3"
+  }
+}