first commit

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+# 配置文件不打包，由 volumes 挂载
+VOLUME ["/app/config.yaml", "/app/last_notifications.json"]
+
+CMD ["python", "main.py"]

README.md

@@ -0,0 +1,84 @@
+# 教务处通知监控工具
+
+## 功能特点
+
+- 定时监控教务处网站通知
+- 有新通知时自动发送邮件
+- 可配置监控频率（分钟）
+- 状态持久化，记录已发送通知避免重复
+
+## 部署步骤
+
+### 1. 安装依赖
+
+```bash
+pip install -r requirements.txt
+```
+
+### 2. 配置
+
+编辑 `config.yaml`：
+
+```yaml
+monitor:
+  url: "https://jwc.your.edu.cn/tzgg.htm"  # 改为你的教务处地址
+  frequency_minutes: 30  # 监控频率
+  encoding: "utf-8"
+
+notification:
+  smtp_host: "smtp.gmail.com"  # 邮件服务器
+  smtp_port: 587
+  smtp_user: "your_email@gmail.com"
+  smtp_password: "your_app_password"  # 推荐使用应用专用密码
+  to_email: "notify@example.com"
+  use_tls: true
+```
+
+### 3. 运行
+
+```bash
+python main.py
+```
+
+### 4. 后台运行（Linux）
+
+```bash
+nohup python main.py > output.log 2>&1 &
+```
+
+或使用 systemd 服务：
+
+```ini
+[Unit]
+Description=JWC Monitor
+After=network.target
+
+[Service]
+Type=simple
+User=your_user
+WorkingDirectory=/path/to/project
+ExecStart=/usr/bin/python3 main.py
+Restart=always
+
+[Install]
+WantedBy=multi-user.target
+```
+
+### 5. 常见邮件服务商 SMTP 设置
+
+| 服务商 | SMTP Host | 端口 |
+|--------|-----------|------|
+| Gmail | smtp.gmail.com | 587 |
+| QQ | smtp.qq.com | 587 |
+| 163 | smtp.163.com | 465/994 |
+
+**Gmail 提示**：需要开启"应用专用密码"或降低账户安全级别。
+
+## 适配不同网站
+
+如果抓取不到通知，可能需要调整选择器。参考 `main.py` 中的 `_parse_page` 方法，根据实际网页结构修改选择器。
+
+常见问题：
+1. 通知列表在哪个标签里？(ul/div/table)
+2. 每条通知的标题和链接在哪？
+3. 网页编码是什么？

config.yaml

@@ -0,0 +1,20 @@
+monitor:
+  frequency_minutes: 30
+
+sites:
+  - name: "物理与电子科学学院"
+    url: "https://www.csust.edu.cn/wdxy/xytz.htm"
+    encoding: "utf-8"
+  - name: "教务处"
+    url: "https://www.csust.edu.cn/jwc/index/tzgg.htm"
+    encoding: "utf-8"
+
+notification:
+  smtp_host: "smtp.163.com"
+  smtp_port: 25
+  smtp_user: "chenyouyuan0505@163.com"
+  smtp_password: "AEszrLBtZZK5fJSv"
+  to_email: "3289288508@qq.com"
+  use_tls: true
+
+state_file: "last_notifications.json"

docker-compose.yml

@@ -0,0 +1,16 @@
+version: '3'
+
+services:
+  monitor:
+    build: .
+    restart: unless-stopped
+    volumes:
+      - ./config.yaml:/app/config.yaml:ro
+      - ./last_notifications.json:/app/last_notifications.json
+      - ./monitor.log:/app/monitor.log
+    # 环境变量方式配置邮件（可选，优先级高于 config.yaml）
+    # environment:
+    #   - SMTP_HOST=smtp.gmail.com
+    #   - SMTP_PORT=587
+    #   - SMTP_USER=your_email@gmail.com
+    #   - SMTP_PASSWORD=your_app_password

environment.yml

@@ -0,0 +1,12 @@
+name: jwc-monitor
+channels:
+  - defaults
+  - conda-forge
+dependencies:
+  - python=3.11
+  - pip
+  - pip:
+    - requests>=2.28.0
+    - beautifulsoup4>=4.11.0
+    - pyyaml>=6.0
+    - schedule>=1.1.0

main.py

@@ -0,0 +1,245 @@
+#!/usr/bin/env python3
+"""
+教务处通知监控系统
+支持多网站监控，有新通知时发送邮件提醒
+"""
+
+import json
+import logging
+import re
+import sys
+import time
+from datetime import datetime
+from pathlib import Path
+from urllib.parse import urljoin
+
+import requests
+from bs4 import BeautifulSoup
+import schedule
+import yaml
+
+from notifier import EmailNotifier
+
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler('monitor.log'),
+        logging.StreamHandler(sys.stdout)
+    ]
+)
+logger = logging.getLogger(__name__)
+
+
+class JWCMonitor:
+    def __init__(self, config_path='config.yaml'):
+        self.config = self._load_config(config_path)
+        self.session = requests.Session()
+        self.session.headers.update({
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+        })
+        self.notifier = EmailNotifier(self.config['notification'])
+        self.state_file = Path(self.config.get('state_file', 'last_notifications.json'))
+        self.state = self._load_state()
+
+    def _load_config(self, path):
+        with open(path, 'r', encoding='utf-8') as f:
+            return yaml.safe_load(f)
+
+    def _load_state(self):
+        if self.state_file.exists():
+            with open(self.state_file, 'r', encoding='utf-8') as f:
+                return json.load(f)
+        return {}
+
+    def _save_state(self):
+        with open(self.state_file, 'w', encoding='utf-8') as f:
+            json.dump(self.state, f, ensure_ascii=False, indent=2)
+
+    def fetch_notifications(self, site):
+        """抓取单个网站的通知列表"""
+        url = site['url']
+        encoding = site.get('encoding', 'utf-8')
+
+        try:
+            logger.info(f"正在抓取 [{site['name']}]: {url}")
+            response = self.session.get(url, timeout=30)
+            response.encoding = encoding
+            soup = BeautifulSoup(response.text, 'html.parser')
+
+            notifications = self._parse_page(soup, url)
+            logger.info(f"[{site['name']}] 获取到 {len(notifications)} 条通知")
+            return notifications
+
+        except Exception as e:
+            logger.error(f"[{site['name']}] 抓取失败: {e}")
+            return []
+
+    def _parse_page(self, soup, base_url):
+        """解析通知列表页面"""
+        notifications = []
+
+        selectors = [
+            ('ul', 'list'),
+            ('ul', 'news-list'),
+            ('ul', 'tzgg'),
+            ('div', 'list'),
+            ('div', 'news'),
+            ('div', 'article-list'),
+            ('table', 'list'),
+        ]
+
+        for tag, class_name in selectors:
+            items = soup.find_all(tag, class_=class_name)
+            for container in items:
+                links = container.find_all('a', href=True)
+                for a_tag in links:
+                    href = a_tag['href']
+                    # 过滤 mailto 和 javascript
+                    if not href or 'mailto:' in href or 'javascript' in href.lower():
+                        continue
+                    title = a_tag.get_text(strip=True)
+                    if len(title) > 8 and not title.startswith('#') and not title.startswith('http'):
+                        link = self._abs_url(href, base_url)
+                        date = self._extract_date_from_element(a_tag)
+                        notifications.append({
+                            'title': title,
+                            'link': link,
+                            'date': date,
+                            'id': href
+                        })
+            if notifications:
+                break
+
+        if not notifications:
+            for a_tag in soup.find_all('a', href=True):
+                href = a_tag['href']
+                if not href or 'mailto:' in href or 'javascript' in href.lower():
+                    continue
+                title = a_tag.get_text(strip=True)
+                if len(title) > 8 and not title.startswith('http'):
+                    notifications.append({
+                        'title': title,
+                        'link': self._abs_url(href, base_url),
+                        'date': '',
+                        'id': href
+                    })
+
+        seen = set()
+        unique = []
+        for n in notifications:
+            if n['title'] not in seen and n['link']:
+                seen.add(n['title'])
+                unique.append(n)
+
+        return unique[:20]
+
+    def _extract_date_from_element(self, element):
+        parent = element.parent
+        if parent:
+            text = parent.get_text(strip=True)
+            match = re.search(r'\d{4}-\d{2}-\d{2}', text)
+            if match:
+                return match.group(0)
+        for sibling in element.find_next_siblings():
+            text = sibling.get_text(strip=True)
+            match = re.search(r'\d{4}-\d{2}-\d{2}', text)
+            if match:
+                return match.group(0)
+        title = element.get_text(strip=True)
+        match = re.search(r'(\d{4}-\d{2}-\d{2})', title)
+        if match:
+            return match.group(1)
+        return ''
+
+    def _abs_url(self, href, base_url):
+        if not href or href.startswith('#') or 'javascript' in href.lower():
+            return ''
+        if href.startswith('http'):
+            return href
+        return urljoin(base_url, href)
+
+    def _is_valid_date(self, notification):
+        """过滤2026年之前的通知"""
+        date_str = notification.get('date', '')
+        if not date_str:
+            match = re.search(r'(\d{4})-\d{2}-\d{2}', notification.get('title', ''))
+            if match:
+                date_str = match.group(1)
+            else:
+                return True
+
+        try:
+            year = int(date_str)
+            return year >= 2026
+        except (ValueError, IndexError):
+            return True
+
+    def check_updates(self):
+        """检查所有网站的更新"""
+        sites = self.config.get('sites', [])
+        if not sites:
+            # 兼容单网站配置
+            if 'monitor' in self.config and 'url' in self.config['monitor']:
+                sites = [{
+                    'name': '默认网站',
+                    'url': self.config['monitor']['url'],
+                    'encoding': self.config['monitor'].get('encoding', 'utf-8')
+                }]
+
+        all_new = []
+
+        for site in sites:
+            current = self.fetch_notifications(site)
+            if not current:
+                continue
+
+            # 过滤日期
+            current = [n for n in current if self._is_valid_date(n)]
+
+            # 获取该网站的历史状态
+            site_url = site['url']
+            existing_ids = set(self.state.get(site_url, []))
+
+            new_notifications = []
+            for n in current:
+                if n['id'] not in existing_ids:
+                    new_notifications.append(n)
+                    existing_ids.add(n['id'])
+
+            if new_notifications:
+                for n in new_notifications:
+                    n['source'] = site['name']
+                all_new.extend(new_notifications)
+                logger.info(f"[{site['name']}] 发现 {len(new_notifications)} 条新通知")
+
+            # 更新该网站状态
+            self.state[site_url] = list(existing_ids)
+
+        if all_new:
+            logger.info(f"共发现 {len(all_new)} 条新通知")
+            self.notifier.send(all_new)
+            self._save_state()
+        else:
+            logger.info("没有新通知")
+
+    def run(self):
+        """启动监控"""
+        frequency = self.config.get('monitor', {}).get('frequency_minutes', 30)
+        sites = self.config.get('sites', [])
+        site_names = [s['name'] for s in sites] if sites else ['默认网站']
+        logger.info(f"启动监控，每 {frequency} 分钟检查一次")
+        logger.info(f"监控网站: {', '.join(site_names)}")
+
+        self.check_updates()
+
+        schedule.every(frequency).minutes.do(self.check_updates)
+
+        while True:
+            schedule.run_pending()
+            time.sleep(30)
+
+
+if __name__ == '__main__':
+    monitor = JWCMonitor()
+    monitor.run()

monitor.log

@@ -0,0 +1,102 @@
+2026-03-24 21:07:26,073 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:07:26,073 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:07:26,073 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:08:06,509 - INFO - 获取到 15 条通知
+2026-03-24 21:08:06,509 - INFO - 发现 15 条新通知
+2026-03-24 21:08:10,437 - ERROR - 邮件发送失败: (535, b'5.7.8 Username and Password not accepted. For more information, go to\n5.7.8  https://support.google.com/mail/?p=BadCredentials d2e1a72fcca58-82b03bbebbfsm15412218b3a.18 - gsmtp')
+2026-03-24 21:31:12,546 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:31:12,546 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:31:12,546 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:31:42,963 - INFO - 获取到 15 条通知
+2026-03-24 21:31:42,964 - INFO - 发现 15 条新通知
+2026-03-24 21:32:05,402 - ERROR - 邮件发送失败: Connection unexpectedly closed
+2026-03-24 21:36:52,466 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:36:52,466 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:36:52,466 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:37:22,930 - INFO - 获取到 15 条通知
+2026-03-24 21:37:22,930 - INFO - 发现 15 条新通知
+2026-03-24 21:37:43,247 - ERROR - 邮件发送失败: Connection unexpectedly closed
+2026-03-24 21:38:59,146 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:38:59,146 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:38:59,146 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:39:29,536 - INFO - 获取到 15 条通知
+2026-03-24 21:39:29,536 - INFO - 发现 15 条新通知
+2026-03-24 21:39:37,605 - INFO - 邮件发送成功: 【教务通知】发现 15 条新通知
+2026-03-24 21:46:33,382 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:46:33,382 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:46:33,382 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:47:03,777 - INFO - 获取到 15 条通知
+2026-03-24 21:47:03,777 - INFO - 过滤后剩余 15 条通知
+2026-03-24 21:47:03,778 - INFO - 发现 15 条新通知
+2026-03-24 21:47:08,020 - INFO - 邮件发送成功: 【教务通知】发现 15 条新通知
+2026-03-24 21:52:11,622 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:52:11,622 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:52:11,622 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:53:11,704 - ERROR - 抓取失败: HTTPSConnectionPool(host='www.csust.edu.cn', port=443): Read timed out. (read timeout=30)
+2026-03-24 21:53:11,705 - WARNING - 未获取到通知
+2026-03-24 21:53:35,395 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:53:35,395 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:53:35,396 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:54:05,791 - INFO - 通知: 物理与电子科学学院2025年度人才引进公告2024-03-27 -> info/1011/6500.htm
+2026-03-24 21:54:05,792 - INFO - 通知: 关于举办2026年全国大学生光电设计竞赛校内选拔赛的通知2026-03-19 -> info/1011/11927.htm
+2026-03-24 21:54:05,792 - INFO - 通知: 物理与电子科学学院2025级本科生转专业拟接收名单公示2026-03-11 -> info/1011/11911.htm
+2026-03-24 21:54:05,792 - INFO - 获取到 15 条通知
+2026-03-24 21:54:05,792 - INFO - 过滤后剩余 15 条通知
+2026-03-24 21:54:05,792 - INFO - 发现 15 条新通知
+2026-03-24 21:54:11,803 - INFO - 邮件发送成功: 【教务通知】发现 15 条新通知
+2026-03-24 21:55:47,362 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:55:47,362 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:55:47,362 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:56:17,816 - INFO - 获取到 15 条通知
+2026-03-24 21:56:17,816 - INFO - 过滤后剩余 15 条通知
+2026-03-24 21:56:17,816 - INFO - 发现 15 条新通知
+2026-03-24 21:56:20,188 - INFO - 邮件发送成功: 【教务通知】发现 15 条新通知
+2026-03-24 21:59:02,678 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 21:59:02,678 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 21:59:02,678 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 22:00:03,068 - ERROR - 抓取失败: HTTPSConnectionPool(host='www.csust.edu.cn', port=443): Read timed out. (read timeout=30)
+2026-03-24 22:00:03,070 - WARNING - 未获取到通知
+2026-03-24 22:00:20,261 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 22:00:20,262 - INFO - 监控地址: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 22:00:20,262 - INFO - 正在抓取: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 22:00:50,819 - INFO - 获取到 15 条通知
+2026-03-24 22:00:50,820 - INFO - 过滤后剩余 8 条通知
+2026-03-24 22:00:50,820 - INFO - 发现 8 条新通知
+2026-03-24 22:00:52,165 - INFO - 邮件发送成功: 【教务通知】发现 8 条新通知
+2026-03-24 22:15:44,640 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 22:15:44,640 - INFO - 监控网站: 物理与电子科学学院, 教务处
+2026-03-24 22:15:44,640 - INFO - 正在抓取 [物理与电子科学学院]: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 22:16:15,123 - INFO - [物理与电子科学学院] 获取到 15 条通知
+2026-03-24 22:16:15,124 - INFO - [物理与电子科学学院] 发现 8 条新通知
+2026-03-24 22:16:15,124 - INFO - 正在抓取 [教务处]: https://www.csust.edu.cn/jwc/index/tzgg.htm
+2026-03-24 22:16:15,191 - INFO - [教务处] 获取到 13 条通知
+2026-03-24 22:16:15,191 - INFO - [教务处] 发现 13 条新通知
+2026-03-24 22:16:15,191 - INFO - 共发现 21 条新通知
+2026-03-24 22:16:19,954 - INFO - 邮件发送成功: 【教务通知】发现 21 条新通知
+2026-03-24 22:22:02,051 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 22:22:02,051 - INFO - 监控网站: 物理与电子科学学院, 教务处
+2026-03-24 22:22:02,051 - INFO - 正在抓取 [物理与电子科学学院]: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 22:22:32,383 - INFO - [物理与电子科学学院] 获取到 15 条通知
+2026-03-24 22:22:32,384 - INFO - [物理与电子科学学院] 发现 8 条新通知
+2026-03-24 22:22:32,385 - INFO - 正在抓取 [教务处]: https://www.csust.edu.cn/jwc/index/tzgg.htm
+2026-03-24 22:22:32,460 - INFO - [教务处] 获取到 8 条通知
+2026-03-24 22:22:32,460 - INFO - [教务处] 发现 8 条新通知
+2026-03-24 22:22:32,460 - INFO - 共发现 16 条新通知
+2026-03-24 22:22:33,731 - INFO - 邮件发送成功: 【教务通知】发现 16 条新通知
+2026-03-24 22:25:16,791 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 22:25:16,791 - INFO - 监控网站: 物理与电子科学学院, 教务处
+2026-03-24 22:25:16,792 - INFO - 正在抓取 [物理与电子科学学院]: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 22:25:47,063 - INFO - [物理与电子科学学院] 获取到 15 条通知
+2026-03-24 22:25:47,065 - INFO - 正在抓取 [教务处]: https://www.csust.edu.cn/jwc/index/tzgg.htm
+2026-03-24 22:25:47,139 - INFO - [教务处] 获取到 8 条通知
+2026-03-24 22:25:47,139 - INFO - 没有新通知
+2026-03-24 22:26:28,009 - INFO - 启动监控，每 30 分钟检查一次
+2026-03-24 22:26:28,009 - INFO - 监控网站: 物理与电子科学学院, 教务处
+2026-03-24 22:26:28,009 - INFO - 正在抓取 [物理与电子科学学院]: https://www.csust.edu.cn/wdxy/xytz.htm
+2026-03-24 22:26:58,282 - INFO - [物理与电子科学学院] 获取到 15 条通知
+2026-03-24 22:26:58,283 - INFO - [物理与电子科学学院] 发现 8 条新通知
+2026-03-24 22:26:58,283 - INFO - 正在抓取 [教务处]: https://www.csust.edu.cn/jwc/index/tzgg.htm
+2026-03-24 22:26:58,364 - INFO - [教务处] 获取到 8 条通知
+2026-03-24 22:26:58,364 - INFO - [教务处] 发现 8 条新通知
+2026-03-24 22:26:58,364 - INFO - 共发现 16 条新通知
+2026-03-24 22:26:59,775 - INFO - 邮件发送成功: 【通知监控】发现 16 条新通知

notifier.py

@@ -0,0 +1,97 @@
+#!/usr/bin/env python3
+"""
+邮件通知模块
+"""
+
+import logging
+import smtplib
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
+
+logger = logging.getLogger(__name__)
+
+
+class EmailNotifier:
+    def __init__(self, config):
+        self.smtp_host = config['smtp_host']
+        self.smtp_port = config['smtp_port']
+        self.smtp_user = config['smtp_user']
+        self.smtp_password = config['smtp_password']
+        self.to_email = config['to_email']
+        self.use_tls = config.get('use_tls', True)
+
+    def send(self, notifications):
+        """发送邮件通知"""
+        if not notifications:
+            return
+
+        subject = f"【通知监控】发现 {len(notifications)} 条新通知"
+
+        html_body = self._build_html(notifications)
+        text_body = self._build_text(notifications)
+
+        msg = MIMEMultipart('alternative')
+        msg['Subject'] = subject
+        msg['From'] = self.smtp_user
+        msg['To'] = self.to_email
+
+        msg.attach(MIMEText(text_body, 'plain', 'utf-8'))
+        msg.attach(MIMEText(html_body, 'html', 'utf-8'))
+
+        try:
+            server = smtplib.SMTP(self.smtp_host, self.smtp_port)
+            if self.use_tls:
+                server.starttls()
+            server.login(self.smtp_user, self.smtp_password)
+            server.send_message(msg)
+            server.quit()
+            logger.info(f"邮件发送成功: {subject}")
+        except Exception as e:
+            logger.error(f"邮件发送失败: {e}")
+
+    def _build_html(self, notifications):
+        # 按来源网站分组
+        from collections import defaultdict
+        by_site = defaultdict(list)
+        for n in notifications:
+            source = n.get('source', '未知来源')
+            by_site[source].append(n)
+
+        html_parts = []
+        for site_name, items in by_site.items():
+            rows = []
+            for n in items:
+                date = n.get('date', '')
+                rows.append(f'<tr><td><a href="{n["link"]}">{n["title"]}</a></td><td>{date}</td></tr>')
+            html_parts.append(f'''
+            <h3>{site_name}</h3>
+            <table border="1" cellpadding="5" cellspacing="0">
+                <thead><tr><th>标题</th><th>日期</th></tr></thead>
+                <tbody>{''.join(rows)}</tbody>
+            </table>
+            ''')
+
+        return f'''
+        <html>
+        <body>
+            <h2>新通知 (共 {len(notifications)} 条)</h2>
+            {''.join(html_parts)}
+        </body>
+        </html>
+        '''
+
+    def _build_text(self, notifications):
+        from collections import defaultdict
+        by_site = defaultdict(list)
+        for n in notifications:
+            source = n.get('source', '未知来源')
+            by_site[source].append(n)
+
+        lines = [f'新通知 (共 {len(notifications)} 条)\n']
+        for site_name, items in by_site.items():
+            lines.append(f'\n=== {site_name} ===')
+            for n in items:
+                date = n.get('date', '')
+                lines.append(f"- {n['title']} {date}")
+                lines.append(f"  {n['link']}")
+        return '\n'.join(lines)

requirements.txt

@@ -0,0 +1,4 @@
+requests>=2.28.0
+beautifulsoup4>=4.11.0
+pyyaml>=6.0
+schedule>=1.1.0