diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml
index 3ba3e8d..530490f 100644
--- a/.github/workflows/docker.yml
+++ b/.github/workflows/docker.yml
@@ -1,17 +1,33 @@
-name: Build and Push Multi-Arch Docker Images
+name: Build and Push Docker Images
 
 on:
   push:
-    tags: ["v*"]
+    tags:
+      - "v*" # 主项目版本
+      - "mcp-v*" # MCP 版本
   workflow_dispatch:
+    inputs:
+      image:
+        description: "选择要构建的镜像"
+        required: true
+        default: "all"
+        type: choice
+        options:
+          - all
+          - crawler
+          - mcp
 
 env:
   REGISTRY: docker.io
-  IMAGE_NAME: wantcat/trendradar
 
 jobs:
-  build:
+  build-crawler:
     runs-on: ubuntu-latest
+    # 条件：v* 标签（排除 mcp-v*）或手动触发选择 all/crawler
+    if: |
+      (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') && !startsWith(github.ref, 'refs/tags/mcp-v')) ||
+      (github.event_name == 'workflow_dispatch' && (github.event.inputs.image == 'all' || github.event.inputs.image == 'crawler'))
+
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -35,12 +51,11 @@ jobs:
         id: meta
         uses: docker/metadata-action@v5
         with:
-          images: ${{ env.IMAGE_NAME }}
+          images: wantcat/trendradar
           tags: |
-            type=ref,event=branch
             type=semver,pattern={{version}}
             type=semver,pattern={{major}}.{{minor}}
-            type=raw,value=latest,enable={{is_default_branch}}
+            type=raw,value=latest
 
       - name: Build and push
         uses: docker/build-push-action@v5
@@ -55,5 +70,65 @@ jobs:
           labels: ${{ steps.meta.outputs.labels }}
           cache-from: type=gha
           cache-to: type=gha,mode=max
-          build-args: |
-            BUILDKIT_INLINE_CACHE=1
+
+  build-mcp:
+    runs-on: ubuntu-latest
+    # 条件：mcp-v* 标签 或手动触发选择 all/mcp
+    if: |
+      (github.event_name == 'push' && startsWith(github.ref, 'refs/tags/mcp-v')) ||
+      (github.event_name == 'workflow_dispatch' && (github.event.inputs.image == 'all' || github.event.inputs.image == 'mcp'))
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: |
+            network=host
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract version from tag
+        id: version
+        run: |
+          if [[ "${{ github.ref }}" == refs/tags/mcp-v* ]]; then
+            VERSION="${GITHUB_REF#refs/tags/mcp-v}"
+            echo "version=${VERSION}" >> $GITHUB_OUTPUT
+            echo "major_minor=$(echo $VERSION | cut -d. -f1,2)" >> $GITHUB_OUTPUT
+          else
+            echo "version=latest" >> $GITHUB_OUTPUT
+            echo "major_minor=latest" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Extract metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: wantcat/trendradar-mcp
+          tags: |
+            type=raw,value=${{ steps.version.outputs.version }}
+            type=raw,value=${{ steps.version.outputs.major_minor }}
+            type=raw,value=latest
+
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        env:
+          BUILDKIT_PROGRESS: plain
+        with:
+          context: .
+          file: ./docker/Dockerfile.mcp
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
diff --git a/README-EN.md b/README-EN.md
index bd06fd2..a2c148b 100644
--- a/README-EN.md
+++ b/README-EN.md
@@ -4,7 +4,7 @@
   <img src="/_image/banner.webp" alt="TrendRadar Banner" width="80%">
 </a>
 
-🚀 Deploy in <strong>30 seconds</strong> — Your Smart Trending News Assistant
+🚀 Deploy in <strong>30 seconds</strong> — Say goodbye to endless scrolling, only see the news you truly care about
 
 <a href="https://trendshift.io/repositories/14726" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14726" alt="sansan0%2FTrendRadar | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
 
@@ -14,7 +14,7 @@
 [![GitHub Stars](https://img.shields.io/github/stars/sansan0/TrendRadar?style=flat-square&logo=github&color=yellow)](https://github.com/sansan0/TrendRadar/stargazers)
 [![GitHub Forks](https://img.shields.io/github/forks/sansan0/TrendRadar?style=flat-square&logo=github&color=blue)](https://github.com/sansan0/TrendRadar/network/members)
 [![License](https://img.shields.io/badge/license-GPL--3.0-blue.svg?style=flat-square)](LICENSE)
-[![Version](https://img.shields.io/badge/version-v3.4.1-blue.svg)](https://github.com/sansan0/TrendRadar)
+[![Version](https://img.shields.io/badge/version-v3.5.0-blue.svg)](https://github.com/sansan0/TrendRadar)
 [![MCP](https://img.shields.io/badge/MCP-v1.0.3-green.svg)](https://github.com/sansan0/TrendRadar)
 
 [![WeWork](https://img.shields.io/badge/WeWork-Notification-00D4AA?style=flat-square)](https://work.weixin.qq.com/)
@@ -44,6 +44,34 @@
 
 > This project is designed to be lightweight and easy to deploy
 
+<details>
+<summary>⚠️ Click to expand: <strong>Fork Guide: Docs, Resource Limits & Deployment Options</strong></summary>
+<br>
+
+**📄 Documentation Version:**
+
+If you use this project via **Fork**, you might be viewing outdated documentation. Fork copies the documentation version at that time, but the original project may have been updated.
+
+**👉 [Click to View Latest Official Documentation](https://github.com/sansan0/TrendRadar?tab=readme-ov-file)**
+
+**How to Tell?** Check the repository address at the top of the page:
+- `github.com/your-username/TrendRadar` ← Your forked version
+- `github.com/sansan0/TrendRadar` ← Latest official version
+
+---
+
+**🛡️ Resource Limits & Safety Tips:**
+
+GitHub provides limited Actions resources per account. To avoid being flagged for abuse and risking account suspension:
+
+- **Platform Count**: Keep it around **10 platforms** — more platforms consume more resources
+- **Run Frequency**: Minimum interval of **30 minutes** — more frequent runs are unnecessary
+- **Fair Use**: GitHub Actions is designed for lightweight scheduled tasks, not high-frequency crawlers
+
+💡 **Want more freedom?** Try [🐳 Docker Deployment](#6-docker-deployment) on your own server with no restrictions.
+
+</details>
+
 <br>
 
 ## 📑 Quick Navigation
@@ -156,23 +184,25 @@ Default monitoring of 11 mainstream platforms, with support for adding custom pl
 >
 > For detailed comparison and configuration, see [Configuration Guide - Push Mode Details](#3-push-mode-details)
 
-**Additional Feature - Push Time Window Control** (Optional):
+**Additional Features** (Optional):
 
-- Set push time range (e.g., 09:00-18:00), push only within specified time
-- Configure multiple pushes within window or once per day
-- Avoid notifications during non-work hours
+| Feature | Description | Default |
+|---------|-------------|---------|
+| **Push Time Window Control** | Set push time range (e.g., 09:00-18:00) to avoid non-work hours notifications | Disabled |
+| **Content Order Configuration** | Adjust display order of "Trending Keywords Stats" and "New Trending News" (v3.5.0 new) | Stats first |
 
-> 💡 This feature is disabled by default, see [Quick Start](#-quick-start) for configuration
+> 💡 For detailed configuration, see [Configuration Guide - Report Configuration](#7-report-configuration) and [Configuration Guide - Push Window](#8-push-window-configuration)
 
 ### **Precise Content Filtering**
 
 Set personal keywords (e.g., AI, BYD, Education Policy) to receive only relevant trending news, filtering out noise.
 
-**Basic Syntax** (4 types):
+**Basic Syntax** (5 types):
 - Normal words: Basic matching
 - Required words `+`: Narrow scope
 - Filter words `!`: Exclude noise
 - Count limit `@`: Control display count (v3.2.0 new)
+- Global filter `[GLOBAL_FILTER]`: Globally exclude specified content (v3.5.0 new)
 
 **Advanced Features** (v3.2.0 new):
 - 🔢 **Keyword Sorting Control**: Sort by popularity or config order
@@ -214,6 +244,14 @@ No longer controlled by platform algorithms, TrendRadar reorganizes all trending
 
 Supports **WeWork** (+ WeChat push solution), **Feishu**, **DingTalk**, **Telegram**, **Email**, **ntfy**, **Bark**, **Slack** — messages delivered directly to phone and email.
 
+**📌 Multi-Account Push Notes (v3.5.0 New Feature):**
+
+- ✅ **Multi-Account Configuration Support**: All push channels (Feishu, DingTalk, WeWork, Telegram, ntfy, Bark, Slack) support configuring multiple accounts
+- ✅ **Configuration Method**: Use English semicolon `;` to separate multiple account values
+- ✅ **Example**: Set `FEISHU_WEBHOOK_URL` Secret value to `https://webhook1;https://webhook2`
+- ⚠️ **Paired Configuration**: Telegram and ntfy require paired parameter quantities to match (e.g., token and chat_id both have 2 values)
+- ⚠️ **Quantity Limit**: Default maximum 3 accounts per channel, exceeded values will be truncated
+
 ### **Multi-Platform Support**
 - **GitHub Pages**: Auto-generate beautiful web reports, PC/mobile adapted
 - **Docker Deployment**: Supports multi-architecture containerized operation
@@ -272,6 +310,62 @@ Transform from "algorithm recommendation captivity" to "actively getting the inf
 - **Major Version Upgrade**: Upgrading from v1.x to v2.y, recommend deleting existing fork and re-forking to save effort and avoid config conflicts
 
 
+### 2025/12/03 - v3.5.0
+
+**🎉 Core Feature Enhancements**
+
+1. **Multi-Account Push Support**
+   - All push channels (Feishu, DingTalk, WeWork, Telegram, ntfy, Bark, Slack) support multiple account configuration
+   - Use semicolon `;` to separate multiple accounts, e.g., `FEISHU_WEBHOOK_URL=url1;url2`
+   - Automatic validation for paired configurations (e.g., Telegram's token and chat_id)
+
+2. **Configurable Push Content Order**
+   - Added `reverse_content_order` configuration option
+   - Customize display order of trending keywords stats and new trending news
+
+3. **Global Filter Keywords**
+   - Added `[GLOBAL_FILTER]` region marker for filtering unwanted content globally
+   - Use cases: Filter ads, marketing, low-quality content, etc.
+
+**🐳 Docker Dual-Path HTML Generation Optimization**
+
+- **Bug Fix**: Resolved issue where `index.html` could not sync to host in Docker environment
+- **Dual-Path Generation**: Daily summary HTML is generated to two locations simultaneously
+  - `index.html` (project root): For GitHub Pages access
+  - `output/index.html`: Accessible on host via Docker Volume mount
+- **Compatibility**: Ensures web reports are accessible in Docker, GitHub Actions, and local environments
+
+**🐳 Docker MCP Image Support**
+
+- Added independent MCP service image `wantcat/trendradar-mcp`
+- Supports Docker deployment of AI analysis features via HTTP interface (port 3333)
+- Dual-container architecture: News push service and MCP service run independently, can be scaled and restarted separately
+- See [Docker Deployment - MCP Service](#6-docker-deployment) for details
+
+**🌐 Web Server Support**
+
+- Added built-in web server for browser access to generated reports
+- Control via `manage.py` commands: `docker exec -it trend-radar python manage.py start_webserver`
+- Access URL: `http://localhost:8080` (port configurable)
+- Security features: Static file service, directory restriction, localhost binding
+- Supports both auto-start and manual control modes
+
+**📖 Documentation Optimization**
+
+- Added [Report Configuration](#7-report-configuration) section: report-related parameter details
+- Added [Push Window Configuration](#8-push-window-configuration) section: push_window configuration tutorial
+- Added [Execution Frequency Configuration](#9-execution-frequency-configuration) section: Cron expression explanation and common examples
+- Added [Multi-Account Push Configuration](#10-multiple-account-push-configuration) section: multi-account push configuration details
+- Optimized all configuration sections: Unified "Configuration Location" instructions
+- Simplified Quick Start configuration: Three core files at a glance
+- Optimized [Docker Deployment](#6-docker-deployment) section: Added image description, recommended git clone deployment, reorganized deployment methods
+
+**🔧 Upgrade Instructions**:
+- **GitHub Fork Users**: Update `main.py`, `config/config.yaml` (Added multi-account push support, existing single-account configuration unaffected)
+- **Docker Users**: Update `.env`, `docker-compose.yml` or set environment variables `REVERSE_CONTENT_ORDER`, `MAX_ACCOUNTS_PER_CHANNEL`
+- **Multi-Account Push**: New feature, disabled by default, existing single-account configuration unaffected
+
+
 ### 2025/11/28 - v3.4.1
 
 **🔧 Format Optimization**
@@ -705,6 +799,24 @@ frequency_words.txt file added **required word** feature, using + sign
    - ⚠️ **DO NOT Create Custom Names**: The Secret Name must **strictly use** the names listed below (e.g., `WEWORK_WEBHOOK_URL`, `FEISHU_WEBHOOK_URL`, etc.). Do not modify or create new names arbitrarily, or the system will not recognize them
    - 💡 **Can Configure Multiple Platforms**: The system will send notifications to all configured platforms
 
+   **📌 Multi-Account Push Notes (v3.5.0 New Feature):**
+
+   - ✅ **Multi-Account Configuration Support**: All push channels (Feishu, DingTalk, WeWork, Telegram, ntfy, Bark, Slack) support configuring multiple accounts
+   - ✅ **Configuration Method**: Use English semicolon `;` to separate multiple account values
+   - ✅ **Example**: Set `FEISHU_WEBHOOK_URL` Secret value to `https://webhook1;https://webhook2`
+   - ⚠️ **Paired Configuration**: Telegram and ntfy require paired parameter quantities to match (e.g., token and chat_id both have 2 values)
+   - ⚠️ **Quantity Limit**: Default maximum 3 accounts per channel, exceeded values will be truncated
+
+   **Multi-Account Configuration Examples**:
+
+   | Name | Secret (Value) Example |
+   |------|------------------------|
+   | `FEISHU_WEBHOOK_URL` | `https://webhook1;https://webhook2;https://webhook3` |
+   | `TELEGRAM_BOT_TOKEN` | `token1;token2` |
+   | `TELEGRAM_CHAT_ID` | `chatid1;chatid2` |
+   | `NTFY_TOPIC` | `topic1;topic2` |
+   | `NTFY_TOKEN` | `;token2` (1st has no token, use empty string as placeholder) |
+
    **Configuration Example:**
 
    <img src="_image/secrets.png" alt="GitHub Secrets Configuration Example"/>
@@ -1316,15 +1428,21 @@ frequency_words.txt file added **required word** feature, using + sign
    3. Click **"Run workflow"** button on the right to run
    4. Wait about 1 minute, messages will be pushed to your configured platform
 
+   > ⏱️ **Testing Tips**:
+   > - Don't test too frequently to avoid triggering GitHub Actions limits
+   > - After clicking Run workflow, you need to **refresh the browser page** to see the new run record
+
 4. **Configuration Notes (Optional)**:
 
-    > 💡 Default configuration works normally, only adjust if you need personalization
+    > 💡 **Default configuration works normally**, only adjust if you need personalization, understand these three files:
 
-    - **Push Settings**: Configure push mode and notification options in [config/config.yaml](config/config.yaml) → [Push Mode Details](#3-push-mode-details)
-    - **Keyword Settings**: Add your interested keywords in [config/frequency_words.txt](config/frequency_words.txt) → [Keyword Configuration Tutorial](#2-keyword-configuration)
-    - **Push Frequency Adjustment**: In [.github/workflows/crawler.yml](.github/workflows/crawler.yml) adjust carefully, don't be greedy
+    | File | Purpose |
+    |------|---------|
+    | `config/config.yaml` | Main config file: push mode, time window, platform list, hotspot weights, etc. |
+    | `config/frequency_words.txt` | Keyword file: set your interested keywords, filter push content |
+    | `.github/workflows/crawler.yml` | Execution frequency: control how often to run (⚠️ modify carefully) |
 
-    **Note**: Suggest only adjusting explicitly documented config items, other options mainly for author's development testing
+    👉 **Detailed Configuration Tutorial**: [Configuration Guide](#configuration-guide)
 
 5. **🎉 Deployment Success! Share Your Experience**
 
@@ -1365,6 +1483,8 @@ frequency_words.txt file added **required word** feature, using + sign
 <summary>👉 Click to expand: <strong>Custom Monitoring Platforms</strong></summary>
 <br>
 
+**Configuration Location:** `platforms` section in `config/config.yaml`
+
 This project's news data comes from [newsnow](https://github.com/ourongxing/newsnow). You can click the [website](https://newsnow.busiyi.world/), click [More], to see if there are platforms you want.
 
 For specific additions, visit [project source code](https://github.com/ourongxing/newsnow/tree/main/server/sources), based on the file names there, modify the `platforms` configuration in `config/config.yaml` file:
@@ -1379,13 +1499,18 @@ platforms:
     name: "Wallstreetcn"
   # Add more platforms...
 ```
-If you don't know how to look, you can directly copy the partially organized [Platform Configuration](https://github.com/sansan0/TrendRadar/issues/95)
+
+> 💡 **Shortcut**: If you don't know how to read source code, you can copy from others' organized [Platform Configuration Summary](https://github.com/sansan0/TrendRadar/issues/95)
+
+> ⚠️ **Note**: More platforms is not always better, suggest choosing 10-15 core platforms. Too many platforms will cause information overload and actually reduce user experience.
 
 </details>
 
 ### 2. Keyword Configuration
 
-Configure monitoring keywords in `frequency_words.txt` with four syntax types and grouping features.
+**Configuration Location:** `config/frequency_words.txt`
+
+Configure monitoring keywords in `frequency_words.txt` with five syntax types, region markers, and grouping features.
 
 | Syntax Type | Symbol | Purpose | Example | Matching Logic |
 |------------|--------|---------|---------|----------------|
@@ -1393,6 +1518,7 @@ Configure monitoring keywords in `frequency_words.txt` with four syntax types an
 | **Required** | `+` | Scope limiting | `+phone` | Must include both |
 | **Filter** | `!` | Noise exclusion | `!ad` | Exclude if included |
 | **Count Limit** | `@` | Control display count | `@10` | Max 10 news (v3.2.0 new) |
+| **Global Filter** | `[GLOBAL_FILTER]` | Globally exclude content | See example below | Filter under any circumstances (v3.5.0 new) |
 
 #### 2.1 Basic Syntax
 
@@ -1437,6 +1563,55 @@ Musk
 
 **Priority:** `@number` > Global config > Unlimited
 
+##### 5. **Global Filter** `[GLOBAL_FILTER]` - Globally Exclude Content (v3.5.0 new)
+```txt
+[GLOBAL_FILTER]
+advertisement
+promotion
+marketing
+shocking
+clickbait
+
+[WORD_GROUPS]
+technology
+AI
+
+Huawei
+HarmonyOS
+!car
+```
+**Effect:** Filters news containing specified words under **any circumstances**, with **highest priority**
+
+**Use Cases:**
+- Filter low-quality content: shocking, clickbait, breaking news, etc.
+- Filter marketing content: advertisement, promotion, sponsorship, etc.
+- Filter specific topics: entertainment, gossip (based on needs)
+
+**Filter Priority:** Global Filter > Group Filter(`!`) > Group Matching
+
+**Region Markers:**
+- `[GLOBAL_FILTER]`: Global filter region, words are filtered under any circumstances
+- `[WORD_GROUPS]`: Keyword groups region, maintains existing syntax (`!`, `+`, `@`)
+- If no region markers are used, all content is treated as keyword groups (backward compatible)
+
+**Matching Examples:**
+```txt
+[GLOBAL_FILTER]
+advertisement
+
+[WORD_GROUPS]
+technology
+AI
+```
+- ❌ "Advertisement: Latest tech product launch" ← Contains global filter word "advertisement", rejected
+- ✅ "Tech company launches new AI product" ← No global filter words, matches "technology" group
+- ✅ "AI technology breakthrough draws attention" ← No global filter words, matches "AI" in "technology" group
+
+**Important Notes:**
+- Use global filter words carefully to avoid over-filtering and missing valuable content
+- Recommended to keep global filter words under 5-15
+- For group-specific filtering, prioritize using group filter words (`!` prefix)
+
 ---
 
 #### 🔗 Group Feature - Importance of Empty Lines
@@ -1625,6 +1800,15 @@ BYD
 <summary>👉 Click to expand: <strong>Three Push Modes Detailed Comparison</strong></summary>
 <br>
 
+**Configuration Location:** `report.mode` in `config/config.yaml`
+
+```yaml
+report:
+  mode: "daily"  # Options: "daily" | "incremental" | "current"
+```
+
+**Docker Environment Variable:** `REPORT_MODE=incremental`
+
 #### Detailed Comparison Table
 
 | Mode | Target Users | Push Timing | Display Content | Typical Use Case |
@@ -1678,6 +1862,15 @@ Assume you monitor "Apple" keyword, execute once per hour:
 <summary>👉 Click to expand: <strong>Hotspot Weight Adjustment</strong></summary>
 <br>
 
+**Configuration Location:** `weight` section in `config/config.yaml`
+
+```yaml
+weight:
+  rank_weight: 0.6       # Ranking weight
+  frequency_weight: 0.3  # Frequency weight
+  hotness_weight: 0.1    # Hotness weight
+```
+
 Current default configuration is balanced.
 
 #### Two Core Scenarios
@@ -1775,50 +1968,33 @@ Updated: 2025-01-15 12:30:15
 <summary>👉 Click to expand: <strong>Complete Docker Deployment Guide</strong></summary>
 <br>
 
-#### Method 1: Quick Experience (One-Line Command)
+**Image Description:**
 
-**Linux/macOS System:**
-```bash
-# Create config directory and download config files
-mkdir -p config output
-wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/config.yaml -P config/
-wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/frequency_words.txt -P config/
-```
-Or **Manual Creation**:
-1. Create `config` folder in current directory
-2. Download config files:
-   - Visit https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/config.yaml → Right-click "Save As" → Save to `config\config.yaml`
-   - Visit https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/frequency_words.txt → Right-click "Save As" → Save to `config\frequency_words.txt`
+TrendRadar provides two independent Docker images, deploy according to your needs:
 
-Final directory structure should be:
-```
-current directory/
-└── config/
-    ├── config.yaml
-    └── frequency_words.txt
-```
+| Image Name | Purpose | Description |
+|---------|------|------|
+| `wantcat/trendradar` | News Push Service | Scheduled news crawling, push notifications (Required) |
+| `wantcat/trendradar-mcp` | AI Analysis Service | MCP protocol support, AI dialogue analysis (Optional) |
 
-```bash
-docker run -d --name trend-radar \
-  -v ./config:/app/config:ro \
-  -v ./output:/app/output \
-  -e FEISHU_WEBHOOK_URL="your feishu webhook" \
-  -e DINGTALK_WEBHOOK_URL="your dingtalk webhook" \
-  -e WEWORK_WEBHOOK_URL="your wework webhook" \
-  -e TELEGRAM_BOT_TOKEN="your telegram_bot_token" \
-  -e TELEGRAM_CHAT_ID="your telegram_chat_id" \
-  -e EMAIL_FROM="your sender email" \
-  -e EMAIL_PASSWORD="your email password or auth code" \
-  -e EMAIL_TO="recipient email" \
-  -e CRON_SCHEDULE="*/30 * * * *" \
-  -e RUN_MODE="cron" \
-  -e IMMEDIATE_RUN="true" \
-  wantcat/trendradar:latest
-```
+> 💡 **Recommendations**:
+> - Only need push functionality: Deploy `wantcat/trendradar` image only
+> - Need AI analysis: Deploy both images
 
-#### Method 2: Using docker-compose (Recommended)
+---
+
+#### Method 1: Using docker-compose (Recommended)
 
 1. **Create Project Directory and Config**:
+
+   **Method 1-A: Using git clone (Recommended, Simplest)**
+   ```bash
+   # Clone project to local
+   git clone https://github.com/sansan0/TrendRadar.git
+   cd TrendRadar
+   ```
+
+   **Method 1-B: Using wget to download config files**
    ```bash
    # Create directory structure
    mkdir -p trendradar/{config,docker}
@@ -1829,11 +2005,11 @@ docker run -d --name trend-radar \
    wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/frequency_words.txt -P config/
 
    # Download docker-compose config
-   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/.env
-   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/docker-compose.yml
+   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/.env -P docker/
+   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/docker-compose.yml -P docker/
    ```
 
-Final directory structure should be:
+   > 💡 **Note**: Key directory structure required for Docker deployment:
 ```
 current directory/
 ├── config/
@@ -1858,10 +2034,13 @@ current directory/
    | `ENABLE_CRAWLER` | `crawler.enable_crawler` | `true` / `false` | Enable crawler |
    | `ENABLE_NOTIFICATION` | `notification.enable_notification` | `true` / `false` | Enable notification |
    | `REPORT_MODE` | `report.mode` | `daily` / `incremental` / `current`| Report mode |
+   | `MAX_ACCOUNTS_PER_CHANNEL` | `notification.max_accounts_per_channel` | `3` | Maximum accounts per channel |
    | `PUSH_WINDOW_ENABLED` | `notification.push_window.enabled` | `true` / `false` | Push time window switch |
    | `PUSH_WINDOW_START` | `notification.push_window.time_range.start` | `08:00` | Push start time |
    | `PUSH_WINDOW_END` | `notification.push_window.time_range.end` | `22:00` | Push end time |
-   | `FEISHU_WEBHOOK_URL` | `notification.webhooks.feishu_url` | `https://...` | Feishu Webhook |
+   | `ENABLE_WEBSERVER` | - | `true` / `false` | Auto-start web server |
+   | `WEBSERVER_PORT` | - | `8080` | Web server port (default 8080) |
+   | `FEISHU_WEBHOOK_URL` | `notification.webhooks.feishu_url` | `https://...` | Feishu Webhook (supports multi-account, use `;` separator) |
 
    **Config Priority**: Environment Variables > config.yaml
 
@@ -1872,22 +2051,52 @@ current directory/
 
 
 3. **Start Service**:
+
+   **Option A: Start All Services (Push + AI Analysis)**
    ```bash
-   # Pull latest image and start
+   # Pull latest images
    docker-compose pull
+
+   # Start all services (trend-radar + trend-radar-mcp)
    docker-compose up -d
    ```
 
-4. **Check Running Status**:
+   **Option B: Start News Push Service Only**
    ```bash
-   # View logs
-   docker logs -f trend-radar
-
-   # View container status
-   docker ps | grep trend-radar
+   # Start trend-radar only (scheduled crawling and push)
+   docker-compose pull trend-radar
+   docker-compose up -d trend-radar
    ```
 
-#### Method 3: Local Build (Developer Option)
+   **Option C: Start MCP AI Analysis Service Only**
+   ```bash
+   # Start trend-radar-mcp only (AI analysis interface)
+   docker-compose pull trend-radar-mcp
+   docker-compose up -d trend-radar-mcp
+   ```
+
+   > 💡 **Tips**:
+   > - Most users only need to start `trend-radar` for news push functionality
+   > - Only start `trend-radar-mcp` when using Claude/ChatGPT for AI dialogue analysis
+   > - Both services are independent and can be flexibly combined
+
+4. **Check Running Status**:
+   ```bash
+   # View news push service logs
+   docker logs -f trend-radar
+
+   # View MCP AI analysis service logs
+   docker logs -f trend-radar-mcp
+
+   # View all container status
+   docker ps | grep trend-radar
+
+   # Stop specific service
+   docker-compose stop trend-radar      # Stop push service
+   docker-compose stop trend-radar-mcp  # Stop MCP service
+   ```
+
+#### Method 2: Local Build (Developer Option)
 
 If you need custom code modifications or build your own image:
 
@@ -1903,17 +2112,38 @@ vim config/frequency_words.txt
 # Use build version docker-compose
 cd docker
 cp docker-compose-build.yml docker-compose.yml
+```
 
-# Build and start
+**Build and Start Services**:
+
+```bash
+# Option A: Build and start all services
 docker-compose build
 docker-compose up -d
+
+# Option B: Build and start news push service only
+docker-compose build trend-radar
+docker-compose up -d trend-radar
+
+# Option C: Build and start MCP AI analysis service only
+docker-compose build trend-radar-mcp
+docker-compose up -d trend-radar-mcp
 ```
 
+> 💡 **Architecture Parameter Notes**:
+> - Default builds `amd64` architecture images (suitable for most x86_64 servers)
+> - To build `arm64` architecture (Apple Silicon, Raspberry Pi, etc.), set environment variable:
+>   ```bash
+>   export DOCKER_ARCH=arm64
+>   docker-compose build
+>   ```
+
 #### Image Update
 
 ```bash
-# Method 1: Manual update
+# Method 1: Manual update (Crawler + MCP images)
 docker pull wantcat/trendradar:latest
+docker pull wantcat/trendradar-mcp:latest
 docker-compose down
 docker-compose up -d
 
@@ -1922,6 +2152,13 @@ docker-compose pull
 docker-compose up -d
 ```
 
+**Available Images**:
+
+| Image Name | Purpose | Description |
+|---------|------|---------|
+| `wantcat/trendradar` | News Push Service | Scheduled news crawling, push notifications |
+| `wantcat/trendradar-mcp` | MCP Service | AI analysis features (optional) |
+
 #### Service Management Commands
 
 ```bash
@@ -1940,6 +2177,11 @@ docker exec -it trend-radar python manage.py config
 # Display output files
 docker exec -it trend-radar python manage.py files
 
+# Web server management (for browser access to generated reports)
+docker exec -it trend-radar python manage.py start_webserver   # Start web server
+docker exec -it trend-radar python manage.py stop_webserver    # Stop web server
+docker exec -it trend-radar python manage.py webserver_status  # Check web server status
+
 # View help info
 docker exec -it trend-radar python manage.py help
 
@@ -1953,10 +2195,52 @@ docker stop trend-radar
 docker rm trend-radar
 ```
 
+> 💡 **Web Server Notes**:
+> - After starting, access latest report at `http://localhost:8080`
+> - Access historical reports via directory navigation (e.g., `http://localhost:8080/2025年xx月xx日/`)
+> - Port can be configured in `.env` file with `WEBSERVER_PORT` parameter
+> - Auto-start: Set `ENABLE_WEBSERVER=true` in `.env`
+> - Security: Static files only, limited to output directory, localhost binding only
+
 #### Data Persistence
 
 Generated reports and data are saved in `./output` directory by default. Data persists even if container is restarted or removed.
 
+**📊 Web Report Access Paths**:
+
+TrendRadar generates daily summary HTML reports to two locations simultaneously:
+
+| File Location | Access Method | Use Case |
+|--------------|---------------|----------|
+| `output/index.html` | Direct host access | **Docker Deployment** (via Volume mount, visible on host) |
+| `index.html` | Root directory access | **GitHub Pages** (repository root, auto-detected by Pages) |
+| `output/YYYY年MM月DD日/html/当日汇总.html` | Historical reports | All environments (archived by date) |
+
+**Local Access Examples**:
+```bash
+# Method 1: Via Web Server (recommended, Docker environment)
+# 1. Start web server
+docker exec -it trend-radar python manage.py start_webserver
+# 2. Access in browser
+http://localhost:8080                           # Access latest report (default index.html)
+http://localhost:8080/2025年xx月xx日/            # Access reports for specific date
+http://localhost:8080/2025年xx月xx日/html/       # Browse all HTML files for that date
+
+# Method 2: Direct file access (local environment)
+open ./output/index.html             # macOS
+start ./output/index.html            # Windows
+xdg-open ./output/index.html         # Linux
+
+# Method 3: Access historical archives
+open ./output/2025年xx月xx日/html/当日汇总.html
+```
+
+**Why two index.html files?**
+- `output/index.html`: Docker Volume mounted to host, can be opened locally
+- `index.html`: Pushed to repository by GitHub Actions, auto-deployed by GitHub Pages
+
+> 💡 **Tip**: Both files have identical content, choose either one to access.
+
 #### Troubleshooting
 
 ```bash
@@ -1973,6 +2257,521 @@ docker exec -it trend-radar /bin/bash
 docker exec -it trend-radar ls -la /app/config/
 ```
 
+#### MCP Service Deployment (AI Analysis Feature)
+
+If you need to use AI analysis features, you can deploy the standalone MCP service container.
+
+**Architecture Description**:
+
+```mermaid
+flowchart TB
+    subgraph trend-radar["trend-radar"]
+        A1[Scheduled News Fetching]
+        A2[Push Notifications]
+    end
+    
+    subgraph trend-radar-mcp["trend-radar-mcp"]
+        B1[127.0.0.1:3333]
+        B2[AI Analysis API]
+    end
+    
+    subgraph shared["Shared Volume"]
+        C1["config/ (ro)"]
+        C2["output/ (ro)"]
+    end
+    
+    trend-radar --> shared
+    trend-radar-mcp --> shared
+```
+
+**Quick Start**:
+
+Use docker-compose to start both news push and MCP services:
+
+```bash
+# Download latest docker-compose.yml (includes MCP service config)
+wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/docker-compose.yml
+
+# Start all services
+docker-compose up -d
+
+# Check running status
+docker ps | grep trend-radar
+```
+
+**Start MCP Service Separately**:
+
+```bash
+docker run -d --name trend-radar-mcp \
+  -p 127.0.0.1:3333:3333 \
+  -v ./config:/app/config:ro \
+  -v ./output:/app/output:ro \
+  -e TZ=Asia/Shanghai \
+  wantcat/trendradar-mcp:latest
+```
+
+**Verify Service**:
+
+```bash
+# Check if MCP service is running properly
+curl http://127.0.0.1:3333/mcp
+
+# View MCP service logs
+docker logs -f trend-radar-mcp
+```
+
+**Configure in AI Clients**:
+
+After MCP service starts, configure in Claude Desktop, Cherry Studio, Cursor, etc.:
+
+```json
+{
+  "mcpServers": {
+    "trendradar": {
+      "url": "http://127.0.0.1:3333/mcp",
+      "description": "TrendRadar News Trending Analysis"
+    }
+  }
+}
+```
+
+> 💡 **Tip**: MCP service only listens on local port (127.0.0.1) for security. For remote access, configure reverse proxy and authentication yourself.
+
+</details>
+
+### 7. Report Configuration
+
+<details>
+<summary>👉 Click to expand: <strong>Report-Related Parameter Configuration</strong></summary>
+<br>
+
+**Configuration Location:** `report` section in `config/config.yaml`
+
+```yaml
+report:
+  mode: "daily"                    # Push mode
+  rank_threshold: 5                # Ranking highlight threshold
+  sort_by_position_first: false    # Sorting priority
+  max_news_per_keyword: 0          # Maximum display count per keyword
+  reverse_content_order: false     # Content order configuration
+```
+
+#### Configuration Details
+
+| Config Item | Type | Default | Description |
+|------------|------|---------|-------------|
+| `mode` | string | `daily` | Push mode, options: `daily`/`incremental`/`current`, see [Push Mode Details](#3-push-mode-details) |
+| `rank_threshold` | int | `5` | Ranking highlight threshold, news with rank ≤ this value will be displayed in bold |
+| `sort_by_position_first` | bool | `false` | Sorting priority: `false`=sort by news count, `true`=sort by config position |
+| `max_news_per_keyword` | int | `0` | Maximum display count per keyword, `0`=unlimited |
+| `reverse_content_order` | bool | `false` | Content order: `false`=trending keywords stats first, `true`=new trending news first |
+
+#### Content Order Configuration (v3.5.0 New)
+
+Controls display order of two content sections in push messages and HTML reports:
+
+| Config Value | Display Order |
+|-------------|--------------|
+| `false` (default) | ① Trending Keywords Stats → ② New Trending News |
+| `true` | ① New Trending News → ② Trending Keywords Stats |
+
+**Use Cases:**
+- `false` (default): Suitable for users focusing on keyword match results, view categorized stats first
+- `true`: Suitable for users focusing on latest updates, prioritize viewing new trending topics
+
+**Docker Environment Variable:**
+```bash
+REVERSE_CONTENT_ORDER=true
+```
+
+#### Sorting Priority Configuration
+
+**Example Scenario:** Config order A, B, C, news count A(3), B(10), C(5)
+
+| Config Value | Display Order | Use Case |
+|-------------|--------------|----------|
+| `false` (default) | B(10) → C(5) → A(3) | Focus on popularity trends |
+| `true` | A(3) → B(10) → C(5) | Focus on personal priority |
+
+**Docker Environment Variables:**
+```bash
+SORT_BY_POSITION_FIRST=true
+MAX_NEWS_PER_KEYWORD=10
+```
+
+</details>
+
+### 8. Push Window Configuration
+
+<details>
+<summary>👉 Click to expand: <strong>Push Time Window Control Details</strong></summary>
+<br>
+
+**Configuration Location:** `notification.push_window` section in `config/config.yaml`
+
+```yaml
+notification:
+  push_window:
+    enabled: false                    # Whether to enable
+    time_range:
+      start: "20:00"                  # Start time (Beijing time)
+      end: "22:00"                    # End time (Beijing time)
+    once_per_day: true                # Push only once per day
+    push_record_retention_days: 7     # Push record retention days
+```
+
+#### Configuration Details
+
+| Config Item | Type | Default | Description |
+|------------|------|---------|-------------|
+| `enabled` | bool | `false` | Whether to enable push time window control |
+| `time_range.start` | string | `"20:00"` | Push window start time (Beijing time, HH:MM format) |
+| `time_range.end` | string | `"22:00"` | Push window end time (Beijing time, HH:MM format) |
+| `once_per_day` | bool | `true` | `true`=push only once per day within window, `false`=push every execution within window |
+| `push_record_retention_days` | int | `7` | Push record retention days (used to determine if already pushed) |
+
+#### Use Cases
+
+| Scenario | Configuration Example |
+|----------|---------------------|
+| **Working Hours Push** | `start: "09:00"`, `end: "18:00"`, `once_per_day: false` |
+| **Evening Summary Push** | `start: "20:00"`, `end: "22:00"`, `once_per_day: true` |
+| **Lunch Break Push** | `start: "12:00"`, `end: "13:00"`, `once_per_day: true` |
+
+#### Important Notice
+
+> ⚠️ **GitHub Actions Users Note:**
+> - GitHub Actions execution time is unstable, may have ±15 minutes deviation
+> - Time range should be at least **2 hours** wide
+> - For precise timed push, recommend **Docker deployment** on personal server
+
+#### Docker Environment Variables
+
+```bash
+PUSH_WINDOW_ENABLED=true
+PUSH_WINDOW_START=09:00
+PUSH_WINDOW_END=18:00
+PUSH_WINDOW_ONCE_PER_DAY=false
+PUSH_WINDOW_RETENTION_DAYS=7
+```
+
+#### Complete Configuration Examples
+
+**Scenario: Push once between 8-10 PM daily**
+
+```yaml
+notification:
+  push_window:
+    enabled: true
+    time_range:
+      start: "20:00"
+      end: "22:00"
+    once_per_day: true
+    push_record_retention_days: 7
+```
+
+**Scenario: Push every hour during working hours**
+
+```yaml
+notification:
+  push_window:
+    enabled: true
+    time_range:
+      start: "09:00"
+      end: "18:00"
+    once_per_day: false
+    push_record_retention_days: 7
+```
+
+</details>
+
+### 9. Execution Frequency Configuration
+
+<details>
+<summary>👉 Click to expand: <strong>Automatic Execution Frequency Settings</strong></summary>
+<br>
+
+**Configuration Location:** `schedule` section in `.github/workflows/crawler.yml`
+
+```yaml
+on:
+  schedule:
+    - cron: "0 * * * *"  # Run every hour
+```
+
+#### What is a Cron Expression?
+
+Cron is a time-based job scheduler format, consisting of 5 parts: `minute hour day month weekday`
+
+```
+┌───────────── minute (0-59)
+│ ┌───────────── hour (0-23)
+│ │ ┌───────────── day (1-31)
+│ │ │ ┌───────────── month (1-12)
+│ │ │ │ ┌───────────── weekday (0-6, 0=Sunday)
+│ │ │ │ │
+* * * * *
+```
+
+#### Common Configuration Examples
+
+| Desired Effect | Cron Expression | Description |
+|---------------|----------------|-------------|
+| Every hour | `0 * * * *` | Run at minute 0 of every hour (default) |
+| Every 30 minutes | `*/30 * * * *` | Run every 30 minutes |
+| Daily at 8 AM | `0 0 * * *` | UTC 0:00 = Beijing 8:00 AM |
+| Working hours | `*/30 0-14 * * *` | Beijing 8:00-22:00, every 30 minutes |
+| 3 times daily | `0 0,6,12 * * *` | Beijing 8:00, 14:00, 20:00 |
+
+#### Important Notes
+
+> ⚠️ **Time Zone Note**: GitHub Actions uses **UTC time**, Beijing time needs to **subtract 8 hours**
+> - Want Beijing 8:00 AM run → Set UTC 0:00
+> - Want Beijing 8:00 PM run → Set UTC 12:00
+
+> ⚠️ **Frequency Limit**: GitHub has a limit on Actions execution count per account
+> - **Recommendation**: Don't set intervals shorter than 30 minutes
+> - **Reason**: Too frequent may be considered abuse, facing account ban risk
+> - **Reality**: GitHub Actions execution time has inherent deviation, setting too precise is meaningless
+
+#### Modification Method
+
+1. Open your forked repository
+2. Find `.github/workflows/crawler.yml` file
+3. Click edit (pencil icon)
+4. Modify the expression in `cron: "0 * * * *"`
+5. Click "Commit changes" to save
+
+</details>
+
+### 10. Multiple Account Push Configuration
+
+<details>
+<summary>👉 Click to expand: <strong>Multiple Account Push Configuration Guide</strong></summary>
+<br>
+
+**Configuration Location:** `notification` section in `config/config.yaml`
+
+> ### ⚠️ **Security Warning**
+> **GitHub Fork Users: DO NOT configure push information in `config.yaml`!**
+>
+> - **Risk**: `config.yaml` will be committed to public Git repositories. Configuring push information (Webhook URLs, Tokens, etc.) will expose sensitive data
+> - **Recommended Methods**:
+>   - **GitHub Actions Users** → Use GitHub Secrets environment variables
+>   - **Docker Users** → Use [`.env` file configuration](#6-docker-deployment) (`.env` is in `.gitignore` and won't be committed)
+> - **Local Development Users**: Can configure in `config.yaml` (ensure it won't be pushed to public repositories)
+
+#### Supported Channels
+
+| Channel | Configuration Item | Pairing Required | Description |
+|---------|-------------------|-----------------|-------------|
+| **Feishu** | `feishu_url` | No | Multiple webhook URLs |
+| **DingTalk** | `dingtalk_url` | No | Multiple webhook URLs |
+| **WeWork** | `wework_url` | No | Multiple webhook URLs |
+| **Telegram** | `telegram_bot_token` + `telegram_chat_id` | ✅ Yes | Token and chat_id quantities must match |
+| **ntfy** | `ntfy_topic` + `ntfy_token` | ✅ Yes | Topic and token quantities must match (token optional) |
+| **Bark** | `bark_url` | No | Multiple push URLs |
+| **Slack** | `slack_webhook_url` | No | Multiple webhook URLs |
+| **Email** | `email_to` | - | Already supports multiple recipients (comma-separated), no modification needed |
+
+#### Recommended Method 1: GitHub Actions Environment Variables
+
+**Configuration Location**: GitHub Repo → Settings → Secrets and variables → Actions → Repository secrets
+
+**Basic Configuration Example**:
+```bash
+# Multi-account quantity limit
+MAX_ACCOUNTS_PER_CHANNEL=3
+
+# Feishu multi-account (3 groups)
+FEISHU_WEBHOOK_URL=https://hook1.feishu.cn/xxx;https://hook2.feishu.cn/yyy;https://hook3.feishu.cn/zzz
+
+# DingTalk multi-account (2 groups)
+DINGTALK_WEBHOOK_URL=https://oapi.dingtalk.com/xxx;https://oapi.dingtalk.com/yyy
+
+# WeWork multi-account (2 groups)
+WEWORK_WEBHOOK_URL=https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=xxx;https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=yyy
+
+# Bark multi-account (2 devices)
+BARK_URL=https://api.day.app/key1;https://api.day.app/key2
+
+# Slack multi-account (2 channels)
+SLACK_WEBHOOK_URL=https://hooks.slack.com/xxx;https://hooks.slack.com/yyy
+```
+
+**Paired Configuration Examples (Telegram and ntfy)**:
+
+<details>
+<summary><strong>Telegram Paired Configuration</strong></summary>
+
+```bash
+# ✅ Correct: 2 tokens correspond to 2 chat_ids
+TELEGRAM_BOT_TOKEN=123456:AAA-BBB;789012:CCC-DDD
+TELEGRAM_CHAT_ID=-100111;-100222
+
+# ❌ Incorrect: quantities don't match, push will be skipped
+TELEGRAM_BOT_TOKEN=token1;token2;token3
+TELEGRAM_CHAT_ID=id1;id2
+```
+
+**Note**: The quantities of `token` and `chat_id` must match exactly, otherwise the channel push will be skipped.
+
+</details>
+
+<details>
+<summary><strong>ntfy Paired Configuration</strong></summary>
+
+```bash
+# ✅ Correct: 3 topics, only the 2nd needs a token
+NTFY_TOPIC=topic1;topic2;topic3
+NTFY_TOKEN=;token_for_topic2;
+
+# ✅ Correct: 2 topics both need tokens
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2
+
+# ❌ Incorrect: topic and token quantities don't match
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2;token3
+```
+
+**Notes**:
+- If a topic doesn't need a token, leave it empty at the corresponding position (between two semicolons)
+- The quantities of `topic` and `token` must match
+
+</details>
+
+---
+
+#### Recommended Method 2: Docker Environment Variables (.env)
+
+**Configuration Location**: `docker/.env` file in project root directory
+
+**Basic Configuration Example**:
+```bash
+# Multi-account quantity limit
+MAX_ACCOUNTS_PER_CHANNEL=3
+
+# Feishu multi-account (3 groups)
+FEISHU_WEBHOOK_URL=https://hook1.feishu.cn/xxx;https://hook2.feishu.cn/yyy;https://hook3.feishu.cn/zzz
+
+# DingTalk multi-account (2 groups)
+DINGTALK_WEBHOOK_URL=https://oapi.dingtalk.com/xxx;https://oapi.dingtalk.com/yyy
+
+# WeWork multi-account (2 groups)
+WEWORK_WEBHOOK_URL=https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=xxx;https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=yyy
+
+# Bark multi-account (2 devices)
+BARK_URL=https://api.day.app/key1;https://api.day.app/key2
+
+# Slack multi-account (2 channels)
+SLACK_WEBHOOK_URL=https://hooks.slack.com/xxx;https://hooks.slack.com/yyy
+```
+
+**Paired Configuration Examples (Telegram and ntfy)**:
+
+<details>
+<summary><strong>Telegram Paired Configuration</strong></summary>
+
+```bash
+# ✅ Correct: 2 tokens correspond to 2 chat_ids
+TELEGRAM_BOT_TOKEN=123456:AAA-BBB;789012:CCC-DDD
+TELEGRAM_CHAT_ID=-100111;-100222
+
+# ❌ Incorrect: quantities don't match, push will be skipped
+TELEGRAM_BOT_TOKEN=token1;token2;token3
+TELEGRAM_CHAT_ID=id1;id2
+```
+
+**Note**: The quantities of `token` and `chat_id` must match exactly, otherwise the channel push will be skipped.
+
+</details>
+
+<details>
+<summary><strong>ntfy Paired Configuration</strong></summary>
+
+```bash
+# ✅ Correct: 3 topics, only the 2nd needs a token
+NTFY_TOPIC=topic1;topic2;topic3
+NTFY_TOKEN=;token_for_topic2;
+
+# ✅ Correct: 2 topics both need tokens
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2
+
+# ❌ Incorrect: topic and token quantities don't match
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2;token3
+```
+
+**Notes**:
+- If a topic doesn't need a token, leave it empty at the corresponding position (between two semicolons)
+- The quantities of `topic` and `token` must match
+
+</details>
+
+---
+
+#### Push Behavior Description
+
+1. **Independent Push**: Each account sends independently, one failure doesn't affect other accounts
+2. **Partial Success**: As long as one account sends successfully, the overall result is considered successful
+3. **Log Differentiation**: Multi-account logs show "Account 1", "Account 2", etc.
+4. **Batch Interval**: Multi-account increases total send time (each account independently calculates batch interval)
+
+---
+
+#### FAQ
+
+<details>
+<summary><strong>Q1: What happens if more than 3 accounts are configured?</strong></summary>
+<br>
+
+The system will automatically truncate to the configured maximum quantity and output warning logs. You can adjust the limit via `max_accounts_per_channel`.
+
+**⚠️ Special Note for GitHub Actions Users**:
+- **Not recommended to configure too many accounts** (suggest no more than 3), which may cause:
+  - **Trigger GitHub Actions rate limits**: Frequent network requests may be identified as abnormal behavior
+  - **Affect Workflow execution time**: Multi-account pushing will extend runtime and may exceed free quotas
+  - **Potential account risks**: Excessive use of GitHub Actions resources may affect account status
+- **Recommended Practices**:
+  - Use `max_accounts_per_channel: 3` or lower values
+  - Adjust Cron execution frequency (e.g., change from hourly to every 2-3 hours)
+  - Prioritize the most important push channels and avoid configuring too many accounts
+
+</details>
+
+<details>
+<summary><strong>Q2: Will multi-accounts affect push speed?</strong></summary>
+<br>
+
+Yes. Each account sends independently, total time = number of accounts × single account send time. Recommend controlling the number of accounts.
+
+</details>
+
+<details>
+<summary><strong>Q3: How can local development users configure in config.yaml?</strong></summary>
+<br>
+
+If you are doing local development and **will not push code to public repositories**, you can configure directly in `config/config.yaml`:
+
+```yaml
+notification:
+  enable_notification: true
+  max_accounts_per_channel: 3
+
+  webhooks:
+    feishu_url: "https://hook1.feishu.cn/xxx;https://hook2.feishu.cn/yyy"
+    telegram_bot_token: "token1;token2"
+    telegram_chat_id: "id1;id2"
+```
+
+**⚠️ Important Reminder**:
+- Ensure `config/config.yaml` is in `.gitignore` (if you will commit code)
+- Or only use in local development environment, **never commit to public repositories**
+
+</details>
+
 </details>
 
 <br>
diff --git a/README.md b/README.md
index 4137b87..45ba621 100644
--- a/README.md
+++ b/README.md
@@ -14,7 +14,7 @@
 [![GitHub Stars](https://img.shields.io/github/stars/sansan0/TrendRadar?style=flat-square&logo=github&color=yellow)](https://github.com/sansan0/TrendRadar/stargazers)
 [![GitHub Forks](https://img.shields.io/github/forks/sansan0/TrendRadar?style=flat-square&logo=github&color=blue)](https://github.com/sansan0/TrendRadar/network/members)
 [![License](https://img.shields.io/badge/license-GPL--3.0-blue.svg?style=flat-square)](LICENSE)
-[![Version](https://img.shields.io/badge/version-v3.4.1-blue.svg)](https://github.com/sansan0/TrendRadar)
+[![Version](https://img.shields.io/badge/version-v3.5.0-blue.svg)](https://github.com/sansan0/TrendRadar)
 [![MCP](https://img.shields.io/badge/MCP-v1.0.3-green.svg)](https://github.com/sansan0/TrendRadar)
 
 [![企业微信通知](https://img.shields.io/badge/企业微信-通知-00D4AA?style=flat-square)](https://work.weixin.qq.com/)
@@ -44,14 +44,12 @@
 > 本项目以轻量，易部署为目标
 
 <details>
-<summary>⚠️ 点击展开：<strong>查看最新文档</strong>（Fork 用户必读）</summary>
+<summary>⚠️ 点击展开：<strong>Fork 须知：文档更新、资源限制与部署建议</strong></summary>
 <br>
 
-最近有很多第一次接触 GitHub 的新用户使用本项目，因此特别补充这个说明。
+**📄 文档版本说明：**
 
-**问题**：如果你是通过 **Fork** 使用本项目，你看到的可能是旧版文档。
-
-**原因**：Fork 时会复制当时的文档版本，但原项目可能已更新。
+如果你是通过 **Fork** 使用本项目，你看到的可能是旧版文档。因为 Fork 时会复制当时的文档版本，但原项目可能已更新。
 
 **👉 [点击查看最新官方文档](https://github.com/sansan0/TrendRadar?tab=readme-ov-file)**
 
@@ -59,6 +57,18 @@
 - `github.com/你的用户名/TrendRadar` ← 你 fork 的版本
 - `github.com/sansan0/TrendRadar` ← 最新官方版本
 
+---
+
+**🛡️ 资源限制与安全提示：**
+
+GitHub 为每个账号提供的 Actions 资源是有限额的。为了避免被官方判定为滥用而面临封号风险，请注意：
+
+- **监控平台数量**：建议控制在 **10 个左右**，过多平台会消耗更多资源
+- **执行频率**：建议最短间隔为 **30 分钟**，过于频繁无实际意义
+- **合理使用**：GitHub Actions 适合轻量级定时任务，而非高频爬虫
+
+💡 **想要更自由地使用？** 推荐 [🐳 Docker 部署](#6-docker-部署)，在自己的服务器上运行。
+
 </details>
 
 <br>
@@ -222,23 +232,25 @@
 >
 > 详细对比和配置教程见 [配置详解 - 推送模式详解](#3-推送模式详解)
 
-**附加功能 - 推送时间窗口控制**（可选）：
+**附加功能**（可选）：
 
-- 设定推送时间范围（如 09:00-18:00），只在指定时间内推送
-- 可配置窗口内多次推送或每天仅推送一次
-- 避免非工作时间打扰
+| 功能 | 说明 | 默认 |
+|------|------|------|
+| **推送时间窗口控制** | 设定推送时间范围（如 09:00-18:00），避免非工作时间打扰 | 关闭 |
+| **内容顺序配置** | 调整"热点词汇统计"和"新增热点新闻"的显示顺序（v3.5.0 新增） | 统计在前 |
 
-> 💡 此功能默认关闭，配置方法见 [快速开始](#-快速开始)
+> 💡 详细配置教程见 [配置详解 - 报告配置](#7-报告配置) 和 [配置详解 - 推送时间窗口](#8-推送时间窗口配置)
 
 ### **精准内容筛选**
 
 设置个人关键词（如：AI、比亚迪、教育政策），只推送相关热点，过滤无关信息
 
-**基础语法**（4种）：
+**基础语法**（5种）：
 - 普通词：基础匹配
 - 必须词 `+`：限定范围
 - 过滤词 `!`：排除干扰
 - 数量限制 `@`：控制显示数量（v3.2.0 新增）
+- 全局过滤 `[GLOBAL_FILTER]`：全局排除指定内容（v3.5.0 新增）
 
 **高级功能**（v3.2.0 新增）：
 - 🔢 **关键词排序控制**：按热度优先 or 配置顺序优先
@@ -279,6 +291,14 @@
 
 支持**企业微信**(+ 微信推送方案)、**飞书**、**钉钉**、**Telegram**、**邮件**、**ntfy**、**Bark**、**Slack**，消息直达手机和邮箱
 
+**📌 多账号推送说明（v3.5.0 新增）：**
+
+- ✅ **支持多账号配置**：所有推送渠道（飞书、钉钉、企业微信、Telegram、ntfy、Bark、Slack）均支持配置多个账号
+- ✅ **配置方式**：使用英文分号 `;` 分隔多个账号值
+- ✅ **示例**：`FEISHU_WEBHOOK_URL` 的 Secret 值填写 `https://webhook1;https://webhook2`
+- ⚠️ **配对配置**：Telegram 和 ntfy 需要保证配对参数数量一致（如 token 和 chat_id 都是 2 个）
+- ⚠️ **数量限制**：默认每个渠道最多 3 个账号，超出会被截断
+
 ### **多端适配**
 - **GitHub Pages**：自动生成精美网页报告，PC/移动端适配
 - **Docker部署**：支持多架构容器化运行
@@ -337,6 +357,61 @@ GitHub 一键 Fork 即可使用，无需编程基础。
 - **大版本升级**：从 v1.x 升级到 v2.y，建议删除现有 fork 后重新 fork，这样更省力且避免配置冲突
 
 
+### 2025/12/03 - v3.5.0
+
+**🎉 核心功能增强**
+
+1. **多账号推送支持**
+   - 所有推送渠道（飞书、钉钉、企业微信、Telegram、ntfy、Bark、Slack）支持多账号配置
+   - 使用分号 `;` 分隔多个账号，例如：`FEISHU_WEBHOOK_URL=url1;url2`
+   - 自动验证配对配置（如 Telegram 的 token 和 chat_id）数量一致性
+
+2. **推送内容顺序可配置**
+   - 新增 `reverse_content_order` 配置项
+   - 支持自定义热点词汇统计与新增热点新闻的显示顺序
+
+3. **全局过滤关键词**
+   - 新增 `[GLOBAL_FILTER]` 区域标记，支持全局过滤不想看到的内容
+   - 适用场景：过滤广告、营销、低质内容等
+
+**🐳 Docker 双路径 HTML 生成优化**
+
+- **问题修复**：解决 Docker 环境下 `index.html` 无法同步到宿主机的问题
+- **双路径生成**：当日汇总 HTML 同时生成到两个位置
+  - `index.html`（项目根目录）：供 GitHub Pages 访问
+  - `output/index.html`：通过 Docker Volume 挂载，宿主机可直接访问
+- **兼容性**：确保 Docker、GitHub Actions、本地运行环境均能正常访问网页版报告
+
+**🐳 Docker MCP 镜像支持**
+
+- 新增独立的 MCP 服务镜像 `wantcat/trendradar-mcp`
+- 支持 Docker 部署 AI 分析功能，通过 HTTP 接口（端口 3333）提供服务
+- 双容器架构：新闻推送服务与 MCP 服务独立运行，可分别扩展和重启
+- 详见 [Docker 部署 - MCP 服务](#6-docker-部署)
+
+**🌐 Web 服务器支持**
+
+- 新增内置 Web 服务器，支持通过浏览器访问生成的报告
+- 通过 `manage.py` 命令控制启动/停止：`docker exec -it trend-radar python manage.py start_webserver`
+- 访问地址：`http://localhost:8080`（端口可配置）
+- 安全特性：静态文件服务、目录限制、本地访问
+- 支持自动启动和手动控制两种模式
+
+**📖 文档优化**
+
+- 新增 [报告配置](#7-报告配置) 章节：report 相关参数详解
+- 新增 [推送时间窗口配置](#8-推送时间窗口配置) 章节：push_window 配置教程
+- 新增 [执行频率配置](#9-执行频率配置) 章节：Cron 表达式说明和常用示例
+- 新增 [多账号推送配置](#10-多账号推送配置) 章节：多账号推送配置详解
+- 优化各配置章节：统一添加"配置位置"说明
+- 简化快速开始配置说明：三个核心文件一目了然
+- 优化 [Docker 部署](#6-docker-部署) 章节：新增镜像说明、推荐 git clone 部署、重组部署方式
+
+**🔧 升级说明**：
+- **GitHub Fork 用户**：更新 `main.py`、`config/config.yaml`（新增多账号推送支持，无需修改现有配置）
+- **多账号推送**：新功能，默认不启用，现有单账号配置不受影响
+
+
 ### 2025/11/26 - mcp-v1.0.3
 
   **MCP 模块更新:**
@@ -344,6 +419,11 @@ GitHub 一键 Fork 即可使用，无需编程基础。
   - 支持自然语言日期表达式解析(本周、最近7天、上月等)
   - 工具总数从 13 个增加到 14 个
 
+
+<details>
+<summary>👉 点击展开：<strong>历史更新</strong></summary>
+
+
 ### 2025/11/28 - v3.4.1
 
 **🔧 格式优化**
@@ -366,10 +446,6 @@ GitHub 一键 Fork 即可使用，无需编程基础。
 - **GitHub Fork 用户**：更新 `main.py`，`config.yaml`
 
 
-<details>
-<summary>👉 点击展开：<strong>历史更新</strong></summary>
-
-
 ### 2025/11/25 - v3.4.0
 
 **🎉 新增 Slack 推送支持**
@@ -760,6 +836,24 @@ frequency_words.txt 文件增加了一个【必须词】功能，使用 + 号
    - ⚠️ **严禁自创名称**：Secret 的 Name（名称）必须**严格使用**下方列出的名称（如 `WEWORK_WEBHOOK_URL`、`FEISHU_WEBHOOK_URL` 等），不能自己随意修改或创造新名称，否则系统无法识别
    - 💡 **可以同时配置多个平台**：系统会向所有配置的平台发送通知
 
+   **📌 多账号推送说明（v3.5.0 新增）：**
+
+   - ✅ **支持多账号配置**：所有推送渠道（飞书、钉钉、企业微信、Telegram、ntfy、Bark、Slack）均支持配置多个账号
+   - ✅ **配置方式**：使用英文分号 `;` 分隔多个账号值
+   - ✅ **示例**：`FEISHU_WEBHOOK_URL` 的 Secret 值填写 `https://webhook1;https://webhook2`
+   - ⚠️ **配对配置**：Telegram 和 ntfy 需要保证配对参数数量一致（如 token 和 chat_id 都是 2 个）
+   - ⚠️ **数量限制**：默认每个渠道最多 3 个账号，超出部分被截断
+
+   **多账号配置示例**：
+
+   | Name（名称） | Secret（值）示例 |
+   |-------------|-----------------|
+   | `FEISHU_WEBHOOK_URL` | `https://webhook1;https://webhook2;https://webhook3` |
+   | `TELEGRAM_BOT_TOKEN` | `token1;token2` |
+   | `TELEGRAM_CHAT_ID` | `chatid1;chatid2` |
+   | `NTFY_TOPIC` | `topic1;topic2` |
+   | `NTFY_TOKEN` | `;token2`（第一个无 token 时留空占位） |
+
    **配置示例：**
 
    <img src="_image/secrets.png" alt="GitHub Secrets 配置示例"/>
@@ -1364,15 +1458,21 @@ frequency_words.txt 文件增加了一个【必须词】功能，使用 + 号
    3. 点击右侧的 **"Run workflow"** 按钮运行
    4. 等待 1 分钟左右，消息会推送到你配置的平台
 
+   > ⏱️ **测试提示**：
+   > - 手动测试不要太频繁，避免触发 GitHub Actions 限制
+   > - 点击 Run workflow 后需要**刷新浏览器页面**才能看到新的运行记录
+
 4. **配置说明（可选）**：
 
-    > 💡 默认配置已可正常使用，如需个性化调整，可参考以下选项
+    > 💡 **默认配置已可正常使用**，如需个性化调整，了解以下三个文件即可
 
-    - **推送设置**：在 [config/config.yaml](config/config.yaml) 中配置推送模式和通知选项 → [推送模式详解](#3-推送模式详解)
-    - **关键词设置**：在 [config/frequency_words.txt](config/frequency_words.txt) 中添加你关心的关键词 → [关键词配置教程](#2-关键词配置)
-    - **推送频率调整**：在 [.github/workflows/crawler.yml](.github/workflows/crawler.yml) 请谨慎调整，别贪心
+    | 文件 | 作用 |
+    |------|------|
+    | `config/config.yaml` | 主配置文件：推送模式、时间窗口、平台列表、热点权重等 |
+    | `config/frequency_words.txt` | 关键词文件：设置你关心的词汇，筛选推送内容 |
+    | `.github/workflows/crawler.yml` | 执行频率：控制多久运行一次（⚠️ 谨慎修改） |
 
-    **注意**：建议只调整文档中明确说明的配置项,其他选项主要供作者开发时测试使用
+    👉 **详细配置教程**：[配置详解](#配置详解)
 
 5. **🎉 部署成功！分享你的使用体验**
 
@@ -1413,6 +1513,8 @@ frequency_words.txt 文件增加了一个【必须词】功能，使用 + 号
 <summary>👉 点击展开：<strong>自定义监控平台</strong></summary>
 <br>
 
+**配置位置：** `config/config.yaml` 的 `platforms` 部分
+
 本项目的资讯数据来源于 [newsnow](https://github.com/ourongxing/newsnow) ，你可以点击[网站](https://newsnow.busiyi.world/)，点击[更多]，查看是否有你想要的平台。
 
 具体添加可访问 [项目源代码](https://github.com/ourongxing/newsnow/tree/main/server/sources)，根据里面的文件名，在 `config/config.yaml` 文件中修改 `platforms` 配置：
@@ -1427,15 +1529,16 @@ platforms:
     name: "华尔街见闻"
   # 添加更多平台...
 ```
-如果不会看的话，可以有选择的复制他人整理好的部分[平台配置](https://github.com/sansan0/TrendRadar/issues/95)
 
-> 💡 平台不是越多越好，别贪心大量信息，你要进行筛选，否则依然只会被大量信息淹没。
+> 💡 **快捷方式**：如果不会看源代码，可以复制他人整理好的 [平台配置汇总](https://github.com/sansan0/TrendRadar/issues/95)
+
+> ⚠️ **注意**：平台不是越多越好，建议选择 10-15 个核心平台。过多平台会导致信息过载，反而降低使用体验。
 
 </details>
 
 ### 2. 关键词配置
 
-在 `frequency_words.txt` 文件中配置监控的关键词，支持四种语法和词组功能。
+在 `frequency_words.txt` 文件中配置监控的关键词，支持五种语法、区域标记和词组功能。
 
 | 语法类型 | 符号 | 作用 | 示例 | 匹配逻辑 |
 |---------|------|------|------|---------|
@@ -1443,6 +1546,7 @@ platforms:
 | **必须词** | `+` | 限定范围 | `+手机` | 必须同时包含 |
 | **过滤词** | `!` | 排除干扰 | `!广告` | 包含则直接排除 |
 | **数量限制** | `@` | 控制显示数量 | `@10` | 最多显示10条新闻（v3.2.0新增） |
+| **全局过滤** | `[GLOBAL_FILTER]` | 全局排除指定内容 | 见下方示例 | 任何情况下都过滤（v3.5.0新增） |
 
 #### 2.1 基础语法
 
@@ -1452,6 +1556,8 @@ platforms:
 <summary>👉 点击展开：<strong>基础语法教程</strong></summary>
 <br>
 
+**配置位置：** `config/frequency_words.txt`
+
 ##### 1. **普通关键词** - 基础匹配
 ```txt
 华为
@@ -1487,6 +1593,55 @@ OPPO
 
 **配置优先级：** `@数字` > 全局配置 > 不限制
 
+##### 5. **全局过滤** `[GLOBAL_FILTER]` - 全局排除指定内容（v3.5.0 新增）
+```txt
+[GLOBAL_FILTER]
+广告
+推广
+营销
+震惊
+标题党
+
+[WORD_GROUPS]
+科技
+AI
+
+华为
+鸿蒙
+!车
+```
+**作用：** 在任何情况下过滤包含指定词的新闻，**优先级最高**
+
+**使用场景：**
+- 过滤低质内容：震惊、标题党、爆料等
+- 过滤营销内容：广告、推广、赞助等
+- 过滤特定主题：娱乐、八卦（根据需求）
+
+**过滤优先级：** 全局过滤 > 词组内过滤(`!`) > 词组匹配
+
+**区域说明：**
+- `[GLOBAL_FILTER]`：全局过滤区，包含的词在任何情况下都会被过滤
+- `[WORD_GROUPS]`：词组区，保持现有语法（`!`、`+`、`@`）
+- 如果不使用区域标记，默认全部作为词组处理（向后兼容）
+
+**匹配示例：**
+```txt
+[GLOBAL_FILTER]
+广告
+
+[WORD_GROUPS]
+科技
+AI
+```
+- ❌ "广告：最新科技产品发布" ← 包含全局过滤词"广告"，直接拒绝
+- ✅ "科技公司发布AI新产品" ← 不包含全局过滤词，匹配"科技"词组
+- ✅ "AI技术突破引发关注" ← 不包含全局过滤词，匹配"科技"词组中的"AI"
+
+**注意事项：**
+- 全局过滤词应谨慎使用，避免过度过滤导致遗漏有价值内容
+- 建议全局过滤词控制在 5-15 个以内
+- 对于特定词组的过滤，优先使用词组内过滤词（`!` 前缀）
+
 ---
 
 #### 🔗 词组功能 - 空行分隔的重要作用
@@ -1672,6 +1827,15 @@ report:
 <summary>👉 点击展开：<strong>三种推送模式详细对比</strong></summary>
 <br>
 
+**配置位置：** `config/config.yaml` 的 `report.mode`
+
+```yaml
+report:
+  mode: "daily"  # 可选: "daily" | "incremental" | "current"
+```
+
+**Docker 环境变量：** `REPORT_MODE=incremental`
+
 #### 详细对比表格
 
 | 模式 | 适用人群 | 推送时机 | 显示内容 | 典型使用场景 |
@@ -1725,6 +1889,15 @@ report:
 <summary>👉 点击展开：<strong>热点权重调整</strong></summary>
 <br>
 
+**配置位置：** `config/config.yaml` 的 `weight` 部分
+
+```yaml
+weight:
+  rank_weight: 0.6       # 排名权重
+  frequency_weight: 0.3  # 频次权重
+  hotness_weight: 0.1    # 热度权重
+```
+
 当前默认的配置是平衡性配置
 
 #### 两个核心场景
@@ -1822,50 +1995,33 @@ weight:
 <summary>👉 点击展开：<strong>Docker 部署完整指南</strong></summary>
 <br>
 
-#### 方式一：快速体验（一行命令）
+**镜像说明：**
 
-**Linux/macOS 系统：**
-```bash
-# 创建配置目录并下载配置文件
-mkdir -p config output
-wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/config.yaml -P config/
-wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/frequency_words.txt -P config/
-```
-或者**手动创建**：
-1. 在当前目录创建 `config` 文件夹
-2. 下载配置文件：
-   - 访问 https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/config.yaml → 右键"另存为" → 保存到 `config\config.yaml`
-   - 访问 https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/frequency_words.txt → 右键"另存为" → 保存到 `config\frequency_words.txt`
+TrendRadar 提供两个独立的 Docker 镜像，可根据需求选择部署：
 
-完成后的目录结构应该是：
-```
-当前目录/
-└── config/
-    ├── config.yaml
-    └── frequency_words.txt
-```
+| 镜像名称 | 用途 | 说明 |
+|---------|------|------|
+| `wantcat/trendradar` | 新闻推送服务 | 定时抓取新闻、推送通知（必选） |
+| `wantcat/trendradar-mcp` | AI 分析服务 | MCP 协议支持、AI 对话分析（可选） |
 
-```bash
-docker run -d --name trend-radar \
-  -v ./config:/app/config:ro \
-  -v ./output:/app/output \
-  -e FEISHU_WEBHOOK_URL="你的飞书webhook" \
-  -e DINGTALK_WEBHOOK_URL="你的钉钉webhook" \
-  -e WEWORK_WEBHOOK_URL="你的企业微信webhook" \
-  -e TELEGRAM_BOT_TOKEN="你的telegram_bot_token" \
-  -e TELEGRAM_CHAT_ID="你的telegram_chat_id" \
-  -e EMAIL_FROM="你的发件邮箱" \
-  -e EMAIL_PASSWORD="你的邮箱密码或授权码" \
-  -e EMAIL_TO="收件人邮箱" \
-  -e CRON_SCHEDULE="*/30 * * * *" \
-  -e RUN_MODE="cron" \
-  -e IMMEDIATE_RUN="true" \
-  wantcat/trendradar:latest
-```
+> 💡 **建议**：
+> - 只需要推送功能：仅部署 `wantcat/trendradar` 镜像
+> - 需要 AI 分析功能：同时部署两个镜像
 
-#### 方式二：使用 docker-compose（推荐）
+---
+
+#### 方式一：使用 docker-compose（推荐）
 
 1. **创建项目目录和配置**:
+
+   **方式 1-A：使用 git clone（推荐，最简单）**
+   ```bash
+   # 克隆项目到本地
+   git clone https://github.com/sansan0/TrendRadar.git
+   cd TrendRadar
+   ```
+
+   **方式 1-B：使用 wget 下载配置文件**
    ```bash
    # 创建目录结构
    mkdir -p trendradar/{config,docker}
@@ -1876,11 +2032,11 @@ docker run -d --name trend-radar \
    wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/frequency_words.txt -P config/
 
    # 下载 docker-compose 配置
-   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/.env
-   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/docker-compose.yml
+   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/.env  -P docker/
+   wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/docker-compose.yml  -P docker/
    ```
 
-完成后的目录结构应该是：
+   > 💡 **说明**：Docker 部署需要的关键目录结构如下：
 ```
 当前目录/
 ├── config/
@@ -1905,10 +2061,13 @@ docker run -d --name trend-radar \
    | `ENABLE_CRAWLER` | `crawler.enable_crawler` | `true` / `false` | 是否启用爬虫 |
    | `ENABLE_NOTIFICATION` | `notification.enable_notification` | `true` / `false` | 是否启用通知 |
    | `REPORT_MODE` | `report.mode` | `daily` / `incremental` / `current`| 报告模式 |
+   | `MAX_ACCOUNTS_PER_CHANNEL` | `notification.max_accounts_per_channel` | `3` | 每个渠道最大账号数 |
    | `PUSH_WINDOW_ENABLED` | `notification.push_window.enabled` | `true` / `false` | 推送时间窗口开关 |
    | `PUSH_WINDOW_START` | `notification.push_window.time_range.start` | `08:00` | 推送开始时间 |
    | `PUSH_WINDOW_END` | `notification.push_window.time_range.end` | `22:00` | 推送结束时间 |
-   | `FEISHU_WEBHOOK_URL` | `notification.webhooks.feishu_url` | `https://...` | 飞书 Webhook |
+   | `ENABLE_WEBSERVER` | - | `true` / `false` | 是否自动启动 Web 服务器 |
+   | `WEBSERVER_PORT` | - | `8080` | Web 服务器端口（默认 8080） |
+   | `FEISHU_WEBHOOK_URL` | `notification.webhooks.feishu_url` | `https://...` | 飞书 Webhook（支持多账号，用 `;` 分隔） |
 
    **配置优先级**：环境变量 > config.yaml
 
@@ -1919,22 +2078,52 @@ docker run -d --name trend-radar \
 
 
 3. **启动服务**:
+
+   **选项 A：启动所有服务（推送 + AI 分析）**
    ```bash
-   # 拉取最新镜像并启动
+   # 拉取最新镜像
    docker-compose pull
+
+   # 启动所有服务（trend-radar + trend-radar-mcp）
    docker-compose up -d
    ```
 
-4. **查看运行状态**:
+   **选项 B：仅启动新闻推送服务**
    ```bash
-   # 查看日志
-   docker logs -f trend-radar
-
-   # 查看容器状态
-   docker ps | grep trend-radar
+   # 只启动 trend-radar（定时抓取和推送）
+   docker-compose pull trend-radar
+   docker-compose up -d trend-radar
    ```
 
-#### 方式三：本地构建（开发者选项）
+   **选项 C：仅启动 MCP AI 分析服务**
+   ```bash
+   # 只启动 trend-radar-mcp（提供 AI 分析接口）
+   docker-compose pull trend-radar-mcp
+   docker-compose up -d trend-radar-mcp
+   ```
+
+   > 💡 **提示**：
+   > - 大多数用户只需启动 `trend-radar` 即可实现新闻推送功能
+   > - 只有需要使用 Claude/ChatGPT 进行 AI 对话分析时，才需启动 `trend-radar-mcp`
+   > - 两个服务相互独立，可根据需求灵活组合
+
+4. **查看运行状态**:
+   ```bash
+   # 查看新闻推送服务日志
+   docker logs -f trend-radar
+
+   # 查看 MCP AI 分析服务日志
+   docker logs -f trend-radar-mcp
+
+   # 查看所有容器状态
+   docker ps | grep trend-radar
+
+   # 停止特定服务
+   docker-compose stop trend-radar      # 停止推送服务
+   docker-compose stop trend-radar-mcp  # 停止 MCP 服务
+   ```
+
+#### 方式二：本地构建（开发者选项）
 
 如果需要自定义修改代码或构建自己的镜像：
 
@@ -1950,17 +2139,38 @@ vim config/frequency_words.txt
 # 使用构建版本的 docker-compose
 cd docker
 cp docker-compose-build.yml docker-compose.yml
+```
 
-# 构建并启动
+**构建并启动服务**：
+
+```bash
+# 选项 A：构建并启动所有服务
 docker-compose build
 docker-compose up -d
+
+# 选项 B：仅构建并启动新闻推送服务
+docker-compose build trend-radar
+docker-compose up -d trend-radar
+
+# 选项 C：仅构建并启动 MCP AI 分析服务
+docker-compose build trend-radar-mcp
+docker-compose up -d trend-radar-mcp
 ```
 
+> 💡 **架构参数说明**：
+> - 默认构建 `amd64` 架构镜像（适用于大多数 x86_64 服务器）
+> - 如需构建 `arm64` 架构（Apple Silicon、树莓派等），设置环境变量：
+>   ```bash
+>   export DOCKER_ARCH=arm64
+>   docker-compose build
+>   ```
+
 #### 镜像更新
 
 ```bash
-# 方式一：手动更新
+# 方式一：手动更新（爬虫 + MCP 镜像）
 docker pull wantcat/trendradar:latest
+docker pull wantcat/trendradar-mcp:latest
 docker-compose down
 docker-compose up -d
 
@@ -1969,6 +2179,13 @@ docker-compose pull
 docker-compose up -d
 ```
 
+**可用镜像**：
+
+| 镜像名称 | 用途 | 说明 |
+|---------|------|------|
+| `wantcat/trendradar` | 新闻推送服务 | 定时抓取新闻、推送通知 |
+| `wantcat/trendradar-mcp` | MCP 服务 | AI 分析功能（可选） |
+
 #### 服务管理命令
 
 ```bash
@@ -1987,6 +2204,11 @@ docker exec -it trend-radar python manage.py config
 # 显示输出文件
 docker exec -it trend-radar python manage.py files
 
+# Web 服务器管理（用于浏览器访问生成的报告）
+docker exec -it trend-radar python manage.py start_webserver   # 启动 Web 服务器
+docker exec -it trend-radar python manage.py stop_webserver    # 停止 Web 服务器
+docker exec -it trend-radar python manage.py webserver_status  # 查看 Web 服务器状态
+
 # 查看帮助信息
 docker exec -it trend-radar python manage.py help
 
@@ -2000,10 +2222,52 @@ docker stop trend-radar
 docker rm trend-radar
 ```
 
+> 💡 **Web 服务器说明**：
+> - 启动后可通过浏览器访问 `http://localhost:8080` 查看最新报告
+> - 通过目录导航访问历史报告（如：`http://localhost:8080/2025年xx月xx日/`）
+> - 端口可在 `.env` 文件中配置 `WEBSERVER_PORT` 参数
+> - 自动启动：在 `.env` 中设置 `ENABLE_WEBSERVER=true`
+> - 安全提示：仅提供静态文件访问，限制在 output 目录，只绑定本地访问
+
 #### 数据持久化
 
 生成的报告和数据默认保存在 `./output` 目录下，即使容器重启或删除，数据也会保留。
 
+**📊 网页版报告访问路径**：
+
+TrendRadar 生成的当日汇总 HTML 报告会同时保存到两个位置：
+
+| 文件位置 | 访问方式 | 适用场景 |
+|---------|---------|---------|
+| `output/index.html` | 宿主机直接访问 | **Docker 部署**（通过 Volume 挂载，宿主机可见） |
+| `index.html` | 根目录访问 | **GitHub Pages**（仓库根目录，Pages 自动识别） |
+| `output/YYYY年MM月DD日/html/当日汇总.html` | 历史报告访问 | 所有环境（按日期归档） |
+
+**本地访问示例**：
+```bash
+# 方式 1：通过 Web 服务器访问（推荐，Docker 环境）
+# 1. 启动 Web 服务器
+docker exec -it trend-radar python manage.py start_webserver
+# 2. 在浏览器访问
+http://localhost:8080                           # 访问最新报告（默认 index.html）
+http://localhost:8080/2025年xx月xx日/            # 访问指定日期的报告
+http://localhost:8080/2025年xx月xx日/html/       # 浏览该日期下的所有 HTML 文件
+
+# 方式 2：直接打开文件（本地环境）
+open ./output/index.html             # macOS
+start ./output/index.html            # Windows
+xdg-open ./output/index.html         # Linux
+
+# 方式 3：访问历史归档
+open ./output/2025年xx月xx日/html/当日汇总.html
+```
+
+**为什么有两个 index.html？**
+- `output/index.html`：Docker Volume 挂载到宿主机，本地可直接打开
+- `index.html`：GitHub Actions 推送到仓库，GitHub Pages 自动部署
+
+> 💡 **提示**：两个文件内容完全相同，选择任意一个访问即可。
+
 #### 故障排查
 
 ```bash
@@ -2020,6 +2284,513 @@ docker exec -it trend-radar /bin/bash
 docker exec -it trend-radar ls -la /app/config/
 ```
 
+#### MCP 服务部署（AI 分析功能）
+
+如果需要使用 AI 分析功能，可以部署独立的 MCP 服务容器。
+
+**架构说明**：
+
+```mermaid
+flowchart TB
+    subgraph trend-radar["trend-radar"]
+        A1[定时抓取新闻]
+        A2[推送通知]
+    end
+    
+    subgraph trend-radar-mcp["trend-radar-mcp"]
+        B1[127.0.0.1:3333]
+        B2[AI 分析接口]
+    end
+    
+    subgraph shared["共享卷"]
+        C1["config/ (ro)"]
+        C2["output/ (ro)"]
+    end
+    
+    trend-radar --> shared
+    trend-radar-mcp --> shared
+```
+
+**快速启动**：
+
+使用 docker-compose 同时启动新闻推送和 MCP 服务：
+
+```bash
+# 下载最新的 docker-compose.yml（已包含 MCP 服务配置）
+wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/docker-compose.yml
+
+# 启动所有服务
+docker-compose up -d
+
+# 查看运行状态
+docker ps | grep trend-radar
+```
+
+**单独启动 MCP 服务**：
+
+```bash
+docker run -d --name trend-radar-mcp \
+  -p 127.0.0.1:3333:3333 \
+  -v ./config:/app/config:ro \
+  -v ./output:/app/output:ro \
+  -e TZ=Asia/Shanghai \
+  wantcat/trendradar-mcp:latest
+```
+
+**验证服务**：
+
+```bash
+# 检查 MCP 服务是否正常运行
+curl http://127.0.0.1:3333/mcp
+
+# 查看 MCP 服务日志
+docker logs -f trend-radar-mcp
+```
+
+**在 AI 客户端中配置**：
+
+MCP 服务启动后，在 Claude Desktop、Cherry Studio、Cursor 等客户端中配置：
+
+```json
+{
+  "mcpServers": {
+    "trendradar": {
+      "url": "http://127.0.0.1:3333/mcp",
+      "description": "TrendRadar 新闻热点分析"
+    }
+  }
+}
+```
+
+> 💡 **提示**：MCP 服务仅监听本地端口（127.0.0.1），确保安全性。如需远程访问，请自行配置反向代理和认证。
+
+</details>
+
+### 7. 报告配置
+
+<details>
+<summary>👉 点击展开：<strong>报告相关参数配置</strong></summary>
+<br>
+
+**配置位置：** `config/config.yaml` 的 `report` 部分
+
+```yaml
+report:
+  mode: "daily"                    # 推送模式
+  rank_threshold: 5                # 排名高亮阈值
+  sort_by_position_first: false    # 排序优先级
+  max_news_per_keyword: 0          # 每个关键词最大显示数量
+  reverse_content_order: false     # 内容顺序配置
+```
+
+#### 配置项详解
+
+| 配置项 | 类型 | 默认值 | 说明 |
+|-------|------|-------|------|
+| `mode` | string | `daily` | 推送模式，可选 `daily`/`incremental`/`current`，详见 [推送模式详解](#3-推送模式详解) |
+| `rank_threshold` | int | `5` | 排名高亮阈值，排名 ≤ 该值的新闻会加粗显示 |
+| `sort_by_position_first` | bool | `false` | 排序优先级：`false`=按热点条数排序，`true`=按配置位置排序 |
+| `max_news_per_keyword` | int | `0` | 每个关键词最大显示数量，`0`=不限制 |
+| `reverse_content_order` | bool | `false` | 内容顺序：`false`=热点词汇统计在前，`true`=新增热点新闻在前 |
+
+#### 内容顺序配置（v3.5.0 新增）
+
+控制推送消息和 HTML 报告中两部分内容的显示顺序：
+
+| 配置值 | 显示顺序 |
+|-------|---------|
+| `false`（默认） | ① 热点词汇统计 → ② 新增热点新闻 |
+| `true` | ① 新增热点新闻 → ② 热点词汇统计 |
+
+**适用场景：**
+- `false`（默认）：适合关注关键词匹配结果的用户，先看分类统计
+- `true`：适合关注最新动态的用户，优先查看新增热点
+
+**Docker 环境变量：**
+```bash
+REVERSE_CONTENT_ORDER=true
+```
+
+#### 排序优先级配置
+
+**示例场景：** 配置顺序 A、B、C，热点数 A(3条)、B(10条)、C(5条)
+
+| 配置值 | 显示顺序 | 适用场景 |
+|-------|---------|---------|
+| `false`（默认） | B(10条) → C(5条) → A(3条) | 关注热度趋势 |
+| `true` | A(3条) → B(10条) → C(5条) | 关注个人优先级 |
+
+**Docker 环境变量：**
+```bash
+SORT_BY_POSITION_FIRST=true
+MAX_NEWS_PER_KEYWORD=10
+```
+
+</details>
+
+### 8. 推送时间窗口配置
+
+<details>
+<summary>👉 点击展开：<strong>推送时间窗口控制详解</strong></summary>
+<br>
+
+**配置位置：** `config/config.yaml` 的 `notification.push_window` 部分
+
+```yaml
+notification:
+  push_window:
+    enabled: false                    # 是否启用
+    time_range:
+      start: "20:00"                  # 开始时间（北京时间）
+      end: "22:00"                    # 结束时间（北京时间）
+    once_per_day: true                # 每天只推送一次
+    push_record_retention_days: 7     # 推送记录保留天数
+```
+
+#### 配置项详解
+
+| 配置项 | 类型 | 默认值 | 说明 |
+|-------|------|-------|------|
+| `enabled` | bool | `false` | 是否启用推送时间窗口控制 |
+| `time_range.start` | string | `"20:00"` | 推送时间窗口开始时间（北京时间，HH:MM 格式） |
+| `time_range.end` | string | `"22:00"` | 推送时间窗口结束时间（北京时间，HH:MM 格式） |
+| `once_per_day` | bool | `true` | `true`=每天在窗口内只推送一次，`false`=窗口内每次执行都推送 |
+| `push_record_retention_days` | int | `7` | 推送记录保留天数（用于判断是否已推送） |
+
+#### 使用场景
+
+| 场景 | 配置示例 |
+|------|---------|
+| **工作时间推送** | `start: "09:00"`, `end: "18:00"`, `once_per_day: false` |
+| **晚间汇总推送** | `start: "20:00"`, `end: "22:00"`, `once_per_day: true` |
+| **午休时间推送** | `start: "12:00"`, `end: "13:00"`, `once_per_day: true` |
+
+#### 重要提示
+
+> ⚠️ **GitHub Actions 用户注意：**
+> - GitHub Actions 执行时间不稳定，可能有 ±15 分钟的偏差
+> - 时间范围建议至少留足 **2 小时**
+> - 如果想要精准的定时推送，建议使用 **Docker 部署**在个人服务器上
+
+#### Docker 环境变量
+
+```bash
+PUSH_WINDOW_ENABLED=true
+PUSH_WINDOW_START=09:00
+PUSH_WINDOW_END=18:00
+PUSH_WINDOW_ONCE_PER_DAY=false
+PUSH_WINDOW_RETENTION_DAYS=7
+```
+
+#### 完整配置示例
+
+**场景：每天晚上 8-10 点只推送一次汇总**
+
+```yaml
+notification:
+  push_window:
+    enabled: true
+    time_range:
+      start: "20:00"
+      end: "22:00"
+    once_per_day: true
+    push_record_retention_days: 7
+```
+
+**场景：工作时间内每小时推送**
+
+```yaml
+notification:
+  push_window:
+    enabled: true
+    time_range:
+      start: "09:00"
+      end: "18:00"
+    once_per_day: false
+    push_record_retention_days: 7
+```
+
+</details>
+
+### 9. 执行频率配置
+
+<details>
+<summary>👉 点击展开：<strong>自动运行频率设置</strong></summary>
+<br>
+
+**配置位置：** `.github/workflows/crawler.yml` 的 `schedule` 部分
+
+```yaml
+on:
+  schedule:
+    - cron: "0 * * * *"  # 每小时运行一次
+```
+
+#### 什么是 Cron 表达式？
+
+Cron 是一种定时任务格式，由 5 个部分组成：`分 时 日 月 周`
+
+```
+┌───────────── 分钟 (0-59)
+│ ┌───────────── 小时 (0-23)
+│ │ ┌───────────── 日期 (1-31)
+│ │ │ ┌───────────── 月份 (1-12)
+│ │ │ │ ┌───────────── 星期 (0-6，0=周日)
+│ │ │ │ │
+* * * * *
+```
+
+#### 常用配置示例
+
+| 想要的效果 | Cron 表达式 | 说明 |
+|-----------|------------|------|
+| 每小时运行 | `0 * * * *` | 每小时的第 0 分钟运行（默认） |
+| 每 30 分钟运行 | `*/30 * * * *` | 每隔 30 分钟运行一次 |
+| 每天早 8 点运行 | `0 0 * * *` | UTC 0:00 = 北京时间 8:00 |
+| 工作时间运行 | `*/30 0-14 * * *` | 北京 8:00-22:00，每 30 分钟 |
+| 每天 3 次 | `0 0,6,12 * * *` | 北京 8:00、14:00、20:00 |
+
+#### 重要提示
+
+> ⚠️ **时区注意**：GitHub Actions 使用 **UTC 时间**，北京时间需要 **减 8 小时**
+> - 想要北京时间 8:00 运行 → 设置 UTC 0:00
+> - 想要北京时间 20:00 运行 → 设置 UTC 12:00
+
+> ⚠️ **频率限制**：GitHub 对每个账号的 Actions 运行次数有限额
+> - **建议**：不要设置比 30 分钟更短的间隔
+> - **原因**：过于频繁可能被判定为滥用，面临封号风险
+> - **实际情况**：GitHub Actions 执行时间本身就有偏差，设置太精确意义不大
+
+#### 修改方法
+
+1. 打开你 fork 的仓库
+2. 找到 `.github/workflows/crawler.yml` 文件
+3. 点击编辑（铅笔图标）
+4. 修改 `cron: "0 * * * *"` 中的表达式
+5. 点击 "Commit changes" 保存
+
+</details>
+
+### 10. 多账号推送配置
+
+<details>
+<summary>👉 点击展开：<strong>多账号推送配置详解</strong></summary>
+
+> ### ⚠️ **安全警告**
+> **GitHub Fork 用户请勿在 `config.yaml` 中配置推送信息！**
+>
+> - **风险说明**：`config.yaml` 会被提交到公开的 Git 仓库，配置推送信息（Webhook URL、Token 等）会泄露敏感数据
+> - **推荐方式**：
+>   - **GitHub Actions 用户** → 使用 GitHub Secrets 环境变量
+>   - **Docker 用户** → 使用 [`.env` 文件配置](#6-docker-部署)（`.env` 已在 `.gitignore` 中，不会被提交）
+> - **本地开发用户**：可以在 `config.yaml` 中配置（确保不会 push 到公开仓库）
+
+#### 支持的渠道
+
+| 渠道 | 配置项 | 是否需要配对 | 说明 |
+|------|--------|-------------|------|
+| **飞书** | `feishu_url` | 否 | 多个 webhook URL |
+| **钉钉** | `dingtalk_url` | 否 | 多个 webhook URL |
+| **企业微信** | `wework_url` | 否 | 多个 webhook URL |
+| **Telegram** | `telegram_bot_token` + `telegram_chat_id` | ✅ 是 | token 和 chat_id 数量必须一致 |
+| **ntfy** | `ntfy_topic` + `ntfy_token` | ✅ 是 | topic 和 token 数量必须一致（token 可选） |
+| **Bark** | `bark_url` | 否 | 多个推送 URL |
+| **Slack** | `slack_webhook_url` | 否 | 多个 webhook URL |
+| **邮件** | `email_to` | - | 已支持多收件人（逗号分隔），无需修改 |
+
+#### 推荐配置方式 1：GitHub Actions 环境变量
+
+**配置位置**：GitHub Repo → Settings → Secrets and variables → Actions → Repository secrets
+
+**基础配置示例**：
+```bash
+# 多账号数量限制
+MAX_ACCOUNTS_PER_CHANNEL=3
+
+# 飞书多账号（3个群组）
+FEISHU_WEBHOOK_URL=https://hook1.feishu.cn/xxx;https://hook2.feishu.cn/yyy;https://hook3.feishu.cn/zzz
+
+# 钉钉多账号（2个群组）
+DINGTALK_WEBHOOK_URL=https://oapi.dingtalk.com/xxx;https://oapi.dingtalk.com/yyy
+
+# 企业微信多账号（2个群组）
+WEWORK_WEBHOOK_URL=https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=xxx;https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=yyy
+
+# Bark多账号（2个设备）
+BARK_URL=https://api.day.app/key1;https://api.day.app/key2
+
+# Slack多账号（2个频道）
+SLACK_WEBHOOK_URL=https://hooks.slack.com/xxx;https://hooks.slack.com/yyy
+```
+
+**配对配置示例（Telegram 和 ntfy）**：
+
+<details>
+<summary><strong>Telegram 配对配置</strong></summary>
+
+```bash
+# ✅ 正确配置：2个token对应2个chat_id
+TELEGRAM_BOT_TOKEN=123456:AAA-BBB;789012:CCC-DDD
+TELEGRAM_CHAT_ID=-100111;-100222
+
+# ❌ 错误配置：数量不一致，将跳过推送
+TELEGRAM_BOT_TOKEN=token1;token2;token3
+TELEGRAM_CHAT_ID=id1;id2
+```
+
+**说明**：`token` 和 `chat_id` 的数量必须完全一致，否则该渠道推送会被跳过。
+
+</details>
+
+<details>
+<summary><strong>ntfy 配对配置</strong></summary>
+
+```bash
+# ✅ 正确配置：3个topic，只有第2个需要token
+NTFY_TOPIC=topic1;topic2;topic3
+NTFY_TOKEN=;token_for_topic2;
+
+# ✅ 正确配置：2个topic都需要token
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2
+
+# ❌ 错误配置：topic和token数量不匹配
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2;token3
+```
+
+**说明**：
+- 如果某个 topic 不需要 token，在对应位置留空（两个分号之间）
+- `topic` 和 `token` 的数量必须一致
+
+</details>
+
+---
+
+#### 推荐配置方式 2：Docker 环境变量（.env）
+
+**配置位置**：项目根目录 `docker/.env` 文件
+
+**基础配置示例**：
+```bash
+# 多账号数量限制
+MAX_ACCOUNTS_PER_CHANNEL=3
+
+# 飞书多账号（3个群组）
+FEISHU_WEBHOOK_URL=https://hook1.feishu.cn/xxx;https://hook2.feishu.cn/yyy;https://hook3.feishu.cn/zzz
+
+# 钉钉多账号（2个群组）
+DINGTALK_WEBHOOK_URL=https://oapi.dingtalk.com/xxx;https://oapi.dingtalk.com/yyy
+
+# 企业微信多账号（2个群组）
+WEWORK_WEBHOOK_URL=https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=xxx;https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=yyy
+
+# Bark多账号（2个设备）
+BARK_URL=https://api.day.app/key1;https://api.day.app/key2
+
+# Slack多账号（2个频道）
+SLACK_WEBHOOK_URL=https://hooks.slack.com/xxx;https://hooks.slack.com/yyy
+```
+
+**配对配置示例（Telegram 和 ntfy）**：
+
+<details>
+<summary><strong>Telegram 配对配置</strong></summary>
+
+```bash
+# ✅ 正确配置：2个token对应2个chat_id
+TELEGRAM_BOT_TOKEN=123456:AAA-BBB;789012:CCC-DDD
+TELEGRAM_CHAT_ID=-100111;-100222
+
+# ❌ 错误配置：数量不一致，将跳过推送
+TELEGRAM_BOT_TOKEN=token1;token2;token3
+TELEGRAM_CHAT_ID=id1;id2
+```
+
+**说明**：`token` 和 `chat_id` 的数量必须完全一致，否则该渠道推送会被跳过。
+
+</details>
+
+<details>
+<summary><strong>ntfy 配对配置</strong></summary>
+
+```bash
+# ✅ 正确配置：3个topic，只有第2个需要token
+NTFY_TOPIC=topic1;topic2;topic3
+NTFY_TOKEN=;token_for_topic2;
+
+# ✅ 正确配置：2个topic都需要token
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2
+
+# ❌ 错误配置：topic和token数量不匹配
+NTFY_TOPIC=topic1;topic2
+NTFY_TOKEN=token1;token2;token3
+```
+
+**说明**：
+- 如果某个 topic 不需要 token，在对应位置留空（两个分号之间）
+- `topic` 和 `token` 的数量必须一致
+
+</details>
+
+---
+
+#### 推送行为说明
+
+1. **独立推送**：每个账号独立发送，一个失败不影响其他账号
+2. **部分成功判定**：只要有一个账号发送成功，整体视为成功
+3. **日志区分**：多账号时日志会显示"账号1"、"账号2"等标签
+4. **批次间隔**：多账号会增加总发送时间（每个账号独立计算批次间隔）
+
+---
+
+#### 常见问题
+
+<details>
+<summary><strong>Q1: 超过 3 个账号会怎样？</strong></summary>
+<br>
+
+系统会自动截断到配置的最大数量，并输出警告日志。可通过 `max_accounts_per_channel` 调整限制。
+
+**⚠️ GitHub Actions 用户特别注意**：
+- **不建议配置过多账号**（建议不超过 3 个），可能导致：
+  - **触发 GitHub Actions 速率限制**：频繁的网络请求可能被识别为异常行为
+  - **潜在账号风险**：过度使用 GitHub Actions 资源可能影响账号状态
+
+</details>
+
+<details>
+<summary><strong>Q2: 多账号会影响推送速度吗？</strong></summary>
+<br>
+
+会。每个账号独立发送，总时间 = 账号数 × 单账号发送时间。建议控制账号数量。
+
+</details>
+
+<details>
+<summary><strong>Q3: 本地开发用户如何在 config.yaml 中配置？</strong></summary>
+<br>
+
+如果你是本地开发且**不会将代码推送到公开仓库**，可以直接在 `config/config.yaml` 中配置：
+
+```yaml
+notification:
+  enable_notification: true
+  max_accounts_per_channel: 3
+
+  webhooks:
+    feishu_url: "https://hook1.feishu.cn/xxx;https://hook2.feishu.cn/yyy"
+    telegram_bot_token: "token1;token2"
+    telegram_chat_id: "id1;id2"
+```
+
+**⚠️ 重要提醒**：
+- 确保 `config/config.yaml` 在 `.gitignore` 中（如果会提交代码）
+- 或者只在本地开发环境使用，**绝不提交到公开仓库**
+
+</details>
+
 </details>
 
 <br>
diff --git a/config/config.yaml b/config/config.yaml
index 333bedf..81d7cbf 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -29,6 +29,7 @@ report:
   rank_threshold: 5 # 排名高亮阈值
   sort_by_position_first: false # 排序优先级：true=先按配置位置排序，false=先按热点条数排序
   max_news_per_keyword: 0 # 每个关键词最大显示数量，0=不限制
+  reverse_content_order: false # 内容顺序：false=热点词汇统计在前，true=新增热点新闻在前
 
 notification:
   enable_notification: true # 是否启用通知功能，如果 false，则不发送手机通知
@@ -39,6 +40,7 @@ notification:
   slack_batch_size: 4000 # Slack消息分批大小（字节）
   batch_send_interval: 3 # 批次发送间隔（秒）
   feishu_message_separator: "━━━━━━━━━━━━━━━━━━━" # feishu 消息分割线
+  max_accounts_per_channel: 3 # 每个渠道最大账号数量，建议不超过 3
 
   # 🕐 推送时间窗口控制（可选功能）
   # 用途：限制推送的时间范围，避免非工作时间打扰
@@ -71,23 +73,39 @@ notification:
   #    - Minor: Spam notifications flooding your devices
   #    - Severe: Webhook abuse leading to security incidents (malicious messages, phishing links, etc.)
   #
+  # ⚠️⚠️⚠️ 多账号推送说明 / MULTI-ACCOUNT PUSH NOTICE ⚠️⚠️⚠️
+  #
+  # 🔸 多账号支持：
+  #   • 请使用分号(;)分隔多个账号，如："url1;url2;url3"
+  #   • 示例：telegram_bot_token: "token1;token2" 对应 telegram_chat_id: "id1;id2"
+  #   • 对于需要配对的配置（如 Telegram 的 token 和 chat_id），数量必须一致
+  #   • 每个渠道最多支持 max_accounts_per_channel 个账号（见上方配置）
+  #   • 邮箱已支持多收件人（逗号分隔），保持不变
+  #
+  # 🔸 Multi-Account Support:
+  #   • Use semicolon(;) to separate multiple accounts, e.g., "url1;url2;url3"
+  #   • Example: telegram_bot_token: "token1;token2" with telegram_chat_id: "id1;id2"
+  #   • For paired configs (e.g., Telegram token and chat_id), quantities must match
+  #   • Each channel supports up to max_accounts_per_channel accounts (see above config)
+  #   • Email already supports multiple recipients (comma-separated), unchanged
+  #
   webhooks:
-    feishu_url: "" # 飞书机器人的 webhook URL
-    dingtalk_url: "" # 钉钉机器人的 webhook URL
-    wework_url: "" # 企业微信机器人的 webhook URL
+    feishu_url: "" # 飞书机器人的 webhook URL（多账号用 ; 分隔）
+    dingtalk_url: "" # 钉钉机器人的 webhook URL（多账号用 ; 分隔）
+    wework_url: "" # 企业微信机器人的 webhook URL（多账号用 ; 分隔）
     wework_msg_type: "markdown" # 企业微信消息类型：markdown(群机器人) 或 text(个人微信应用)
-    telegram_bot_token: "" # Telegram Bot Token
-    telegram_chat_id: "" # Telegram Chat ID
+    telegram_bot_token: "" # Telegram Bot Token（多账号用 ; 分隔，需与 chat_id 数量一致）
+    telegram_chat_id: "" # Telegram Chat ID（多账号用 ; 分隔，需与 bot_token 数量一致）
     email_from: "" # 发件人邮箱地址
     email_password: "" # 发件人邮箱密码或授权码
     email_to: "" # 收件人邮箱地址，多个收件人用逗号分隔
     email_smtp_server: "" # SMTP服务器地址（可选，留空自动识别）
     email_smtp_port: "" # SMTP端口（可选，留空自动识别）
     ntfy_server_url: "https://ntfy.sh" # ntfy服务器地址，默认使用公共服务，可改为自托管地址
-    ntfy_topic: "" # ntfy主题名称
-    ntfy_token: "" # ntfy访问令牌（可选，用于私有主题）
-    bark_url: "" # Bark推送URL（格式：https://api.day.app/your_device_key 或自建服务器地址）
-    slack_webhook_url: "" # Slack Incoming Webhook URL（格式：https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX）
+    ntfy_topic: "" # ntfy主题名称（多账号用 ; 分隔）
+    ntfy_token: "" # ntfy访问令牌（可选，用于私有主题，多账号用 ; 分隔）
+    bark_url: "" # Bark推送URL（多账号用 ; 分隔，格式：https://api.day.app/your_device_key 或自建服务器地址）
+    slack_webhook_url: "" # Slack Incoming Webhook URL（多账号用 ; 分隔，格式：https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX）
 
 # 用于让关注度更高的新闻在更前面显示，即用算法重新组合不同平台的热搜排序形成你侧重的热搜，合起来是 1 就行
 weight:
diff --git a/docker/.env b/docker/.env
index 2c73e17..9946b30 100644
--- a/docker/.env
+++ b/docker/.env
@@ -12,6 +12,21 @@ REPORT_MODE=
 SORT_BY_POSITION_FIRST=
 # 每个关键词最大显示数量 (0=不限制，>0=限制数量)
 MAX_NEWS_PER_KEYWORD=
+# 内容顺序：false=热点词汇统计在前，true=新增热点新闻在前
+REVERSE_CONTENT_ORDER=
+
+# ============================================
+# Web 服务器配置
+# ============================================
+
+# 是否自动启动 Web 服务器托管 output 目录 (true/false)
+# 启用后可通过 http://localhost:{WEBSERVER_PORT} 访问生成的报告
+# 手动控制：docker exec -it trend-radar python manage.py start_webserver
+ENABLE_WEBSERVER=false
+
+# Web 服务器端口（默认 8080，可自定义避免冲突）
+# 注意：修改后需要重启容器生效
+WEBSERVER_PORT=8080
 
 # ============================================
 # 推送时间窗口配置
@@ -29,36 +44,47 @@ PUSH_WINDOW_ONCE_PER_DAY=
 PUSH_WINDOW_RETENTION_DAYS=
 
 # ============================================
-# 通知渠道配置
+# 多账号配置
 # ============================================
 
-# 推送配置
+# 每个渠道最大账号数量（建议不超过 3，避免fork用户触发账号风险）
+MAX_ACCOUNTS_PER_CHANNEL=
+
+# ============================================
+# 通知渠道配置（多账号用 ; 分隔）
+# ============================================
+
+# 飞书机器人 webhook URL（多账号用 ; 分隔）
 FEISHU_WEBHOOK_URL=
+# Telegram Bot Token（多账号用 ; 分隔，需与 chat_id 数量一致）
 TELEGRAM_BOT_TOKEN=
+# Telegram Chat ID（多账号用 ; 分隔，需与 bot_token 数量一致）
 TELEGRAM_CHAT_ID=
+# 钉钉机器人 webhook URL（多账号用 ; 分隔）
 DINGTALK_WEBHOOK_URL=
+# 企业微信机器人 webhook URL（多账号用 ; 分隔）
 WEWORK_WEBHOOK_URL=
+# 企业微信消息类型（markdown 或 text）
 WEWORK_MSG_TYPE=
 
+# 邮件配置（邮箱已支持多收件人，逗号分隔）
 EMAIL_FROM=
 EMAIL_PASSWORD=
 EMAIL_TO=
 EMAIL_SMTP_SERVER=
 EMAIL_SMTP_PORT=
 
-# ntfy 推送配置
+# ntfy 推送配置（多账号用 ; 分隔，topic 和 token 数量需一致）
 NTFY_SERVER_URL=https://ntfy.sh
-# ntfy主题名称
+# ntfy主题名称（多账号用 ; 分隔）
 NTFY_TOPIC=
-# 可选：访问令牌(用于私有主题)
+# 可选：访问令牌(用于私有主题，多账号用 ; 分隔，无令牌的留空占位如 ";token2")
 NTFY_TOKEN=
 
-# Bark 推送配置
-# Bark推送URL（格式：https://api.day.app/your_device_key 或自建服务器地址）
+# Bark 推送配置（多账号用 ; 分隔）
 BARK_URL=
 
-# Slack 推送配置
-# Slack Incoming Webhook URL（格式：https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX）
+# Slack 推送配置（多账号用 ; 分隔）
 SLACK_WEBHOOK_URL=
 
 # ============================================
diff --git a/docker/Dockerfile b/docker/Dockerfile
index f86f65c..574eb11 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,9 +2,9 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
-# https://github.com/aptible/supercronic
+# Latest releases available at https://github.com/aptible/supercronic/releases
 ARG TARGETARCH
-ENV SUPERCRONIC_VERSION=v0.2.34
+ENV SUPERCRONIC_VERSION=v0.2.39
 
 RUN set -ex && \
     apt-get update && \
@@ -12,12 +12,12 @@ RUN set -ex && \
     case ${TARGETARCH} in \
     amd64) \
     export SUPERCRONIC_URL=https://github.com/aptible/supercronic/releases/download/${SUPERCRONIC_VERSION}/supercronic-linux-amd64; \
-    export SUPERCRONIC_SHA1SUM=e8631edc1775000d119b70fd40339a7238eece14; \
+    export SUPERCRONIC_SHA1SUM=c98bbf82c5f648aaac8708c182cc83046fe48423; \
     export SUPERCRONIC=supercronic-linux-amd64; \
     ;; \
     arm64) \
     export SUPERCRONIC_URL=https://github.com/aptible/supercronic/releases/download/${SUPERCRONIC_VERSION}/supercronic-linux-arm64; \
-    export SUPERCRONIC_SHA1SUM=4ab6343b52bf9da592e8b4bb7ae6eb5a8e21b71e; \
+    export SUPERCRONIC_SHA1SUM=5ef4ccc3d43f12d0f6c3763758bc37cc4e5af76e; \
     export SUPERCRONIC=supercronic-linux-arm64; \
     ;; \
     *) \
@@ -26,26 +26,25 @@ RUN set -ex && \
     ;; \
     esac && \
     echo "Downloading supercronic for ${TARGETARCH} from ${SUPERCRONIC_URL}" && \
-    # 添加重试机制和超时设置
-    for i in 1 2 3 4 5; do \
-    echo "Download attempt $i/5"; \
-    if curl --fail --silent --show-error --location --retry 3 --retry-delay 2 --connect-timeout 30 --max-time 120 -o "$SUPERCRONIC" "$SUPERCRONIC_URL"; then \
-    echo "Download successful"; \
-    break; \
-    else \
-    echo "Download attempt $i failed, exit code: $?"; \
-    if [ $i -eq 5 ]; then \
-    echo "All download attempts failed"; \
-    exit 1; \
-    fi; \
-    sleep $((i * 2)); \
-    fi; \
+    # 重试机制：最多3次，每次超时30秒
+    for i in 1 2 3; do \
+        echo "Download attempt $i/3"; \
+        if curl -fsSL --connect-timeout 30 --max-time 60 -o "$SUPERCRONIC" "$SUPERCRONIC_URL"; then \
+            echo "Download successful"; \
+            break; \
+        else \
+            echo "Download attempt $i failed"; \
+            if [ $i -eq 3 ]; then \
+                echo "All download attempts failed"; \
+                exit 1; \
+            fi; \
+            sleep 2; \
+        fi; \
     done && \
     echo "${SUPERCRONIC_SHA1SUM}  ${SUPERCRONIC}" | sha1sum -c - && \
     chmod +x "$SUPERCRONIC" && \
     mv "$SUPERCRONIC" "/usr/local/bin/${SUPERCRONIC}" && \
     ln -s "/usr/local/bin/${SUPERCRONIC}" /usr/local/bin/supercronic && \
-    # 验证安装
     supercronic -version && \
     apt-get remove -y curl && \
     apt-get clean && \
diff --git a/docker/Dockerfile.mcp b/docker/Dockerfile.mcp
new file mode 100644
index 0000000..6aacfb6
--- /dev/null
+++ b/docker/Dockerfile.mcp
@@ -0,0 +1,23 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# 安装依赖
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 复制 MCP 服务器代码
+COPY mcp_server/ ./mcp_server/
+
+# 创建必要目录
+RUN mkdir -p /app/config /app/output
+
+ENV PYTHONUNBUFFERED=1 \
+    CONFIG_PATH=/app/config/config.yaml \
+    FREQUENCY_WORDS_PATH=/app/config/frequency_words.txt
+
+# MCP HTTP 服务端口
+EXPOSE 3333
+
+# 启动 MCP 服务器（HTTP 模式）
+CMD ["python", "-m", "mcp_server.server", "--transport", "http", "--host", "0.0.0.0", "--port", "3333"]
diff --git a/docker/docker-compose-build.yml b/docker/docker-compose-build.yml
index 804e12d..955c4c9 100644
--- a/docker/docker-compose-build.yml
+++ b/docker/docker-compose-build.yml
@@ -6,6 +6,9 @@ services:
     container_name: trend-radar
     restart: unless-stopped
 
+    ports:
+      - "127.0.0.1:${WEBSERVER_PORT:-8080}:${WEBSERVER_PORT:-8080}"
+
     volumes:
       - ../config:/app/config:ro
       - ../output:/app/output
@@ -18,6 +21,12 @@ services:
       - REPORT_MODE=${REPORT_MODE:-}
       - SORT_BY_POSITION_FIRST=${SORT_BY_POSITION_FIRST:-}
       - MAX_NEWS_PER_KEYWORD=${MAX_NEWS_PER_KEYWORD:-}
+      - REVERSE_CONTENT_ORDER=${REVERSE_CONTENT_ORDER:-}
+      # Web 服务器
+      - ENABLE_WEBSERVER=${ENABLE_WEBSERVER:-false}
+      - WEBSERVER_PORT=${WEBSERVER_PORT:-8080}
+      # 多账号配置
+      - MAX_ACCOUNTS_PER_CHANNEL=${MAX_ACCOUNTS_PER_CHANNEL:-}
       # 推送时间窗口
       - PUSH_WINDOW_ENABLED=${PUSH_WINDOW_ENABLED:-}
       - PUSH_WINDOW_START=${PUSH_WINDOW_START:-}
@@ -49,3 +58,20 @@ services:
       - CRON_SCHEDULE=${CRON_SCHEDULE:-*/5 * * * *}
       - RUN_MODE=${RUN_MODE:-cron}
       - IMMEDIATE_RUN=${IMMEDIATE_RUN:-true}
+
+  trend-radar-mcp:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile.mcp
+    container_name: trend-radar-mcp
+    restart: unless-stopped
+
+    ports:
+      - "127.0.0.1:3333:3333"
+
+    volumes:
+      - ../config:/app/config:ro
+      - ../output:/app/output:ro
+
+    environment:
+      - TZ=Asia/Shanghai
diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
index 206d7d3..c7115b3 100644
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@@ -4,6 +4,9 @@ services:
     container_name: trend-radar
     restart: unless-stopped
 
+    ports:
+      - "127.0.0.1:${WEBSERVER_PORT:-8080}:${WEBSERVER_PORT:-8080}"
+
     volumes:
       - ../config:/app/config:ro
       - ../output:/app/output
@@ -16,6 +19,12 @@ services:
       - REPORT_MODE=${REPORT_MODE:-}
       - SORT_BY_POSITION_FIRST=${SORT_BY_POSITION_FIRST:-}
       - MAX_NEWS_PER_KEYWORD=${MAX_NEWS_PER_KEYWORD:-}
+      - REVERSE_CONTENT_ORDER=${REVERSE_CONTENT_ORDER:-}
+      # Web 服务器
+      - ENABLE_WEBSERVER=${ENABLE_WEBSERVER:-false}
+      - WEBSERVER_PORT=${WEBSERVER_PORT:-8080}
+      # 多账号配置
+      - MAX_ACCOUNTS_PER_CHANNEL=${MAX_ACCOUNTS_PER_CHANNEL:-}
       # 推送时间窗口
       - PUSH_WINDOW_ENABLED=${PUSH_WINDOW_ENABLED:-}
       - PUSH_WINDOW_START=${PUSH_WINDOW_START:-}
@@ -47,3 +56,18 @@ services:
       - CRON_SCHEDULE=${CRON_SCHEDULE:-*/5 * * * *}
       - RUN_MODE=${RUN_MODE:-cron}
       - IMMEDIATE_RUN=${IMMEDIATE_RUN:-true}
+
+  trend-radar-mcp:
+    image: wantcat/trendradar-mcp:latest
+    container_name: trend-radar-mcp
+    restart: unless-stopped
+
+    ports:
+      - "127.0.0.1:3333:3333"
+
+    volumes:
+      - ../config:/app/config:ro
+      - ../output:/app/output:ro
+
+    environment:
+      - TZ=Asia/Shanghai
diff --git a/docker/entrypoint.sh b/docker/entrypoint.sh
index 01d489d..d33bb1c 100644
--- a/docker/entrypoint.sh
+++ b/docker/entrypoint.sh
@@ -33,9 +33,15 @@ case "${RUN_MODE:-cron}" in
         /usr/local/bin/python main.py
     fi
 
+    # 启动 Web 服务器（如果配置了）
+    if [ "${ENABLE_WEBSERVER:-false}" = "true" ]; then
+        echo "🌐 启动 Web 服务器..."
+        /usr/local/bin/python manage.py start_webserver
+    fi
+
     echo "⏰ 启动supercronic: ${CRON_SCHEDULE:-*/30 * * * *}"
     echo "🎯 supercronic 将作为 PID 1 运行"
-    
+
     exec /usr/local/bin/supercronic -passthrough-logs /tmp/crontab
     ;;
 *)
diff --git a/docker/manage.py b/docker/manage.py
index e72d553..944cccf 100644
--- a/docker/manage.py
+++ b/docker/manage.py
@@ -8,8 +8,14 @@ import os
 import sys
 import subprocess
 import time
+import signal
 from pathlib import Path
 
+# Web 服务器配置
+WEBSERVER_PORT = int(os.environ.get("WEBSERVER_PORT", "8080"))
+WEBSERVER_DIR = "/app/output"
+WEBSERVER_PID_FILE = "/tmp/webserver.pid"
+
 
 def run_command(cmd, shell=True, capture_output=True):
     """执行系统命令"""
@@ -374,13 +380,13 @@ def restart_supercronic():
     """重启supercronic进程"""
     print("🔄 重启supercronic...")
     print("⚠️ 注意: supercronic 是 PID 1，无法直接重启")
-    
+
     # 检查当前 PID 1
     try:
         with open('/proc/1/cmdline', 'r') as f:
             pid1_cmdline = f.read().replace('\x00', ' ').strip()
         print(f"  🔍 当前 PID 1: {pid1_cmdline}")
-        
+
         if "supercronic" in pid1_cmdline.lower():
             print("  ✅ PID 1 是 supercronic")
             print("  💡 要重启 supercronic，需要重启整个容器:")
@@ -394,29 +400,167 @@ def restart_supercronic():
         print("  💡 建议重启容器: docker restart trend-radar")
 
 
+def start_webserver():
+    """启动 Web 服务器托管 output 目录"""
+    print(f"🌐 启动 Web 服务器 (端口: {WEBSERVER_PORT})...")
+    print(f"  🔒 安全提示：仅提供静态文件访问，限制在 {WEBSERVER_DIR} 目录")
+
+    # 检查是否已经运行
+    if Path(WEBSERVER_PID_FILE).exists():
+        try:
+            with open(WEBSERVER_PID_FILE, 'r') as f:
+                old_pid = int(f.read().strip())
+            try:
+                os.kill(old_pid, 0)  # 检查进程是否存在
+                print(f"  ⚠️ Web 服务器已在运行 (PID: {old_pid})")
+                print(f"  💡 访问: http://localhost:{WEBSERVER_PORT}")
+                print("  💡 停止服务: python manage.py stop_webserver")
+                return
+            except OSError:
+                # 进程不存在，删除旧的 PID 文件
+                os.remove(WEBSERVER_PID_FILE)
+        except Exception as e:
+            print(f"  ⚠️ 清理旧的 PID 文件: {e}")
+            try:
+                os.remove(WEBSERVER_PID_FILE)
+            except:
+                pass
+
+    # 检查目录是否存在
+    if not Path(WEBSERVER_DIR).exists():
+        print(f"  ❌ 目录不存在: {WEBSERVER_DIR}")
+        return
+
+    try:
+        # 启动 HTTP 服务器
+        # 使用 --bind 绑定到 0.0.0.0 使容器内部可访问
+        # 工作目录限制在 WEBSERVER_DIR，防止访问其他目录
+        process = subprocess.Popen(
+            [sys.executable, '-m', 'http.server', str(WEBSERVER_PORT), '--bind', '0.0.0.0'],
+            cwd=WEBSERVER_DIR,
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.DEVNULL,
+            start_new_session=True
+        )
+
+        # 等待一下确保服务器启动
+        time.sleep(1)
+
+        # 检查进程是否还在运行
+        if process.poll() is None:
+            # 保存 PID
+            with open(WEBSERVER_PID_FILE, 'w') as f:
+                f.write(str(process.pid))
+
+            print(f"  ✅ Web 服务器已启动 (PID: {process.pid})")
+            print(f"  📁 服务目录: {WEBSERVER_DIR} (只读，仅静态文件)")
+            print(f"  🌐 访问地址: http://localhost:{WEBSERVER_PORT}")
+            print(f"  📄 首页: http://localhost:{WEBSERVER_PORT}/index.html")
+            print("  💡 停止服务: python manage.py stop_webserver")
+        else:
+            print(f"  ❌ Web 服务器启动失败")
+    except Exception as e:
+        print(f"  ❌ 启动失败: {e}")
+
+
+def stop_webserver():
+    """停止 Web 服务器"""
+    print("🛑 停止 Web 服务器...")
+
+    if not Path(WEBSERVER_PID_FILE).exists():
+        print("  ℹ️ Web 服务器未运行")
+        return
+
+    try:
+        with open(WEBSERVER_PID_FILE, 'r') as f:
+            pid = int(f.read().strip())
+
+        try:
+            # 尝试终止进程
+            os.kill(pid, signal.SIGTERM)
+            time.sleep(0.5)
+
+            # 检查进程是否已终止
+            try:
+                os.kill(pid, 0)
+                # 进程还在，强制杀死
+                os.kill(pid, signal.SIGKILL)
+                print(f"  ⚠️ 强制停止 Web 服务器 (PID: {pid})")
+            except OSError:
+                print(f"  ✅ Web 服务器已停止 (PID: {pid})")
+        except OSError as e:
+            if e.errno == 3:  # No such process
+                print(f"  ℹ️ 进程已不存在 (PID: {pid})")
+            else:
+                raise
+
+        # 删除 PID 文件
+        os.remove(WEBSERVER_PID_FILE)
+    except Exception as e:
+        print(f"  ❌ 停止失败: {e}")
+        # 尝试清理 PID 文件
+        try:
+            os.remove(WEBSERVER_PID_FILE)
+        except:
+            pass
+
+
+def webserver_status():
+    """查看 Web 服务器状态"""
+    print("🌐 Web 服务器状态:")
+
+    if not Path(WEBSERVER_PID_FILE).exists():
+        print("  ⭕ 未运行")
+        print(f"  💡 启动服务: python manage.py start_webserver")
+        return
+
+    try:
+        with open(WEBSERVER_PID_FILE, 'r') as f:
+            pid = int(f.read().strip())
+
+        try:
+            os.kill(pid, 0)  # 检查进程是否存在
+            print(f"  ✅ 运行中 (PID: {pid})")
+            print(f"  📁 服务目录: {WEBSERVER_DIR}")
+            print(f"  🌐 访问地址: http://localhost:{WEBSERVER_PORT}")
+            print(f"  📄 首页: http://localhost:{WEBSERVER_PORT}/index.html")
+            print("  💡 停止服务: python manage.py stop_webserver")
+        except OSError:
+            print(f"  ⭕ 未运行 (PID 文件存在但进程不存在)")
+            os.remove(WEBSERVER_PID_FILE)
+            print("  💡 启动服务: python manage.py start_webserver")
+    except Exception as e:
+        print(f"  ❌ 状态检查失败: {e}")
+
+
 def show_help():
     """显示帮助信息"""
     help_text = """
 🐳 TrendRadar 容器管理工具
 
 📋 命令列表:
-  run         - 手动执行一次爬虫
-  status      - 显示容器运行状态
-  config      - 显示当前配置
-  files       - 显示输出文件
-  logs        - 实时查看日志
-  restart     - 重启说明
-  help        - 显示此帮助
+  run              - 手动执行一次爬虫
+  status           - 显示容器运行状态
+  config           - 显示当前配置
+  files            - 显示输出文件
+  logs             - 实时查看日志
+  restart          - 重启说明
+  start_webserver  - 启动 Web 服务器托管 output 目录
+  stop_webserver   - 停止 Web 服务器
+  webserver_status - 查看 Web 服务器状态
+  help             - 显示此帮助
 
 📖 使用示例:
   # 在容器中执行
   python manage.py run
   python manage.py status
   python manage.py logs
-  
+  python manage.py start_webserver
+
   # 在宿主机执行
   docker exec -it trend-radar python manage.py run
   docker exec -it trend-radar python manage.py status
+  docker exec -it trend-radar python manage.py start_webserver
   docker logs trend-radar
 
 💡 常用操作指南:
@@ -424,18 +568,24 @@ def show_help():
      - 查看 supercronic 是否为 PID 1
      - 检查配置文件和关键文件
      - 查看 cron 调度设置
-  
-  2. 手动执行测试: run  
+
+  2. 手动执行测试: run
      - 立即执行一次新闻爬取
      - 测试程序是否正常工作
-  
+
   3. 查看日志: logs
      - 实时监控运行情况
      - 也可使用: docker logs trend-radar
-  
+
   4. 重启服务: restart
      - 由于 supercronic 是 PID 1，需要重启整个容器
      - 使用: docker restart trend-radar
+
+  5. Web 服务器管理:
+     - 启动: start_webserver
+     - 停止: stop_webserver
+     - 状态: webserver_status
+     - 访问: http://localhost:8080
 """
     print(help_text)
 
@@ -453,6 +603,9 @@ def main():
         "files": show_files,
         "logs": show_logs,
         "restart": restart_supercronic,
+        "start_webserver": start_webserver,
+        "stop_webserver": stop_webserver,
+        "webserver_status": webserver_status,
         "help": show_help,
     }
 
diff --git a/main.py b/main.py
index b90a519..df9f73a 100644
--- a/main.py
+++ b/main.py
@@ -20,7 +20,7 @@ import requests
 import yaml
 
 
-VERSION = "3.4.1"
+VERSION = "3.5.0"
 
 
 # === SMTP邮件配置 ===
@@ -55,6 +55,109 @@ SMTP_CONFIGS = {
 }
 
 
+# === 多账号推送工具函数 ===
+def parse_multi_account_config(config_value: str, separator: str = ";") -> List[str]:
+    """
+    解析多账号配置，返回账号列表
+
+    Args:
+        config_value: 配置值字符串，多个账号用分隔符分隔
+        separator: 分隔符，默认为 ;
+
+    Returns:
+        账号列表，空字符串会被保留（用于占位）
+    """
+    if not config_value:
+        return []
+    # 保留空字符串用于占位（如 ";token2" 表示第一个账号无token）
+    accounts = [acc.strip() for acc in config_value.split(separator)]
+    # 过滤掉全部为空的情况
+    if all(not acc for acc in accounts):
+        return []
+    return accounts
+
+
+def validate_paired_configs(
+    configs: Dict[str, List[str]],
+    channel_name: str,
+    required_keys: Optional[List[str]] = None
+) -> Tuple[bool, int]:
+    """
+    验证配对配置的数量是否一致
+
+    Args:
+        configs: 配置字典，key 为配置名，value 为账号列表
+        channel_name: 渠道名称，用于日志输出
+        required_keys: 必须有值的配置项列表
+
+    Returns:
+        (是否验证通过, 账号数量)
+    """
+    # 过滤掉空列表
+    non_empty_configs = {k: v for k, v in configs.items() if v}
+
+    if not non_empty_configs:
+        return True, 0
+
+    # 检查必须项
+    if required_keys:
+        for key in required_keys:
+            if key not in non_empty_configs or not non_empty_configs[key]:
+                return True, 0  # 必须项为空，视为未配置
+
+    # 获取所有非空配置的长度
+    lengths = {k: len(v) for k, v in non_empty_configs.items()}
+    unique_lengths = set(lengths.values())
+
+    if len(unique_lengths) > 1:
+        print(f"❌ {channel_name} 配置错误：配对配置数量不一致，将跳过该渠道推送")
+        for key, length in lengths.items():
+            print(f"   - {key}: {length} 个")
+        return False, 0
+
+    return True, list(unique_lengths)[0] if unique_lengths else 0
+
+
+def limit_accounts(
+    accounts: List[str],
+    max_count: int,
+    channel_name: str
+) -> List[str]:
+    """
+    限制账号数量
+
+    Args:
+        accounts: 账号列表
+        max_count: 最大账号数量
+        channel_name: 渠道名称，用于日志输出
+
+    Returns:
+        限制后的账号列表
+    """
+    if len(accounts) > max_count:
+        print(f"⚠️ {channel_name} 配置了 {len(accounts)} 个账号，超过最大限制 {max_count}，只使用前 {max_count} 个")
+        print(f"   ⚠️ 警告：如果您是 fork 用户，过多账号可能导致 GitHub Actions 运行时间过长，存在账号风险")
+        return accounts[:max_count]
+    return accounts
+
+
+def get_account_at_index(accounts: List[str], index: int, default: str = "") -> str:
+    """
+    安全获取指定索引的账号值
+
+    Args:
+        accounts: 账号列表
+        index: 索引
+        default: 默认值
+
+    Returns:
+        账号值或默认值
+    """
+    if index < len(accounts):
+        return accounts[index] if accounts[index] else default
+    return default
+
+
 # === 配置管理 ===
 def load_config():
     """加载配置文件"""
@@ -84,6 +187,10 @@ def load_config():
             os.environ.get("MAX_NEWS_PER_KEYWORD", "").strip() or "0"
         )
         or config_data["report"].get("max_news_per_keyword", 0),
+        "REVERSE_CONTENT_ORDER": os.environ.get("REVERSE_CONTENT_ORDER", "").strip().lower()
+        in ("true", "1")
+        if os.environ.get("REVERSE_CONTENT_ORDER", "").strip()
+        else config_data["report"].get("reverse_content_order", False),
         "USE_PROXY": config_data["crawler"]["use_proxy"],
         "DEFAULT_PROXY": config_data["crawler"]["default_proxy"],
         "ENABLE_CRAWLER": os.environ.get("ENABLE_CRAWLER", "").strip().lower()
@@ -105,6 +212,11 @@ def load_config():
         "FEISHU_MESSAGE_SEPARATOR": config_data["notification"][
             "feishu_message_separator"
         ],
+        # 多账号配置
+        "MAX_ACCOUNTS_PER_CHANNEL": int(
+            os.environ.get("MAX_ACCOUNTS_PER_CHANNEL", "").strip() or "0"
+        )
+        or config_data["notification"].get("max_accounts_per_channel", 3),
         "PUSH_WINDOW": {
             "ENABLED": os.environ.get("PUSH_WINDOW_ENABLED", "").strip().lower()
             in ("true", "1")
@@ -210,39 +322,73 @@ def load_config():
 
     # 输出配置来源信息
     notification_sources = []
+    max_accounts = config["MAX_ACCOUNTS_PER_CHANNEL"]
+
     if config["FEISHU_WEBHOOK_URL"]:
+        accounts = parse_multi_account_config(config["FEISHU_WEBHOOK_URL"])
+        count = min(len(accounts), max_accounts)
         source = "环境变量" if os.environ.get("FEISHU_WEBHOOK_URL") else "配置文件"
-        notification_sources.append(f"飞书({source})")
+        notification_sources.append(f"飞书({source}, {count}个账号)")
     if config["DINGTALK_WEBHOOK_URL"]:
+        accounts = parse_multi_account_config(config["DINGTALK_WEBHOOK_URL"])
+        count = min(len(accounts), max_accounts)
         source = "环境变量" if os.environ.get("DINGTALK_WEBHOOK_URL") else "配置文件"
-        notification_sources.append(f"钉钉({source})")
+        notification_sources.append(f"钉钉({source}, {count}个账号)")
     if config["WEWORK_WEBHOOK_URL"]:
+        accounts = parse_multi_account_config(config["WEWORK_WEBHOOK_URL"])
+        count = min(len(accounts), max_accounts)
         source = "环境变量" if os.environ.get("WEWORK_WEBHOOK_URL") else "配置文件"
-        notification_sources.append(f"企业微信({source})")
+        notification_sources.append(f"企业微信({source}, {count}个账号)")
     if config["TELEGRAM_BOT_TOKEN"] and config["TELEGRAM_CHAT_ID"]:
-        token_source = (
-            "环境变量" if os.environ.get("TELEGRAM_BOT_TOKEN") else "配置文件"
+        tokens = parse_multi_account_config(config["TELEGRAM_BOT_TOKEN"])
+        chat_ids = parse_multi_account_config(config["TELEGRAM_CHAT_ID"])
+        # 验证数量一致性
+        valid, count = validate_paired_configs(
+            {"bot_token": tokens, "chat_id": chat_ids},
+            "Telegram",
+            required_keys=["bot_token", "chat_id"]
         )
-        chat_source = "环境变量" if os.environ.get("TELEGRAM_CHAT_ID") else "配置文件"
-        notification_sources.append(f"Telegram({token_source}/{chat_source})")
+        if valid and count > 0:
+            count = min(count, max_accounts)
+            token_source = "环境变量" if os.environ.get("TELEGRAM_BOT_TOKEN") else "配置文件"
+            notification_sources.append(f"Telegram({token_source}, {count}个账号)")
     if config["EMAIL_FROM"] and config["EMAIL_PASSWORD"] and config["EMAIL_TO"]:
         from_source = "环境变量" if os.environ.get("EMAIL_FROM") else "配置文件"
         notification_sources.append(f"邮件({from_source})")
 
     if config["NTFY_SERVER_URL"] and config["NTFY_TOPIC"]:
-        server_source = "环境变量" if os.environ.get("NTFY_SERVER_URL") else "配置文件"
-        notification_sources.append(f"ntfy({server_source})")
+        topics = parse_multi_account_config(config["NTFY_TOPIC"])
+        tokens = parse_multi_account_config(config["NTFY_TOKEN"])
+        # ntfy 的 token 是可选的，但如果配置了，数量必须与 topic 一致
+        if tokens:
+            valid, count = validate_paired_configs(
+                {"topic": topics, "token": tokens},
+                "ntfy"
+            )
+            if valid and count > 0:
+                count = min(count, max_accounts)
+                server_source = "环境变量" if os.environ.get("NTFY_SERVER_URL") else "配置文件"
+                notification_sources.append(f"ntfy({server_source}, {count}个账号)")
+        else:
+            count = min(len(topics), max_accounts)
+            server_source = "环境变量" if os.environ.get("NTFY_SERVER_URL") else "配置文件"
+            notification_sources.append(f"ntfy({server_source}, {count}个账号)")
 
     if config["BARK_URL"]:
+        accounts = parse_multi_account_config(config["BARK_URL"])
+        count = min(len(accounts), max_accounts)
         bark_source = "环境变量" if os.environ.get("BARK_URL") else "配置文件"
-        notification_sources.append(f"Bark({bark_source})")
+        notification_sources.append(f"Bark({bark_source}, {count}个账号)")
 
     if config["SLACK_WEBHOOK_URL"]:
+        accounts = parse_multi_account_config(config["SLACK_WEBHOOK_URL"])
+        count = min(len(accounts), max_accounts)
         slack_source = "环境变量" if os.environ.get("SLACK_WEBHOOK_URL") else "配置文件"
-        notification_sources.append(f"Slack({slack_source})")
+        notification_sources.append(f"Slack({slack_source}, {count}个账号)")
 
     if notification_sources:
         print(f"通知渠道配置来源: {', '.join(notification_sources)}")
+        print(f"每个渠道最大账号数: {max_accounts}")
     else:
         print("未配置任何通知渠道")
 
@@ -646,8 +792,13 @@ def save_titles_to_file(results: Dict, id_to_name: Dict, failed_ids: List) -> st
 
 def load_frequency_words(
     frequency_file: Optional[str] = None,
-) -> Tuple[List[Dict], List[str]]:
-    """加载频率词配置"""
+) -> Tuple[List[Dict], List[str], List[str]]:
+    """
+    加载频率词配置
+
+    Returns:
+        (词组列表, 词组内过滤词, 全局过滤词)
+    """
     if frequency_file is None:
         frequency_file = os.environ.get(
             "FREQUENCY_WORDS_PATH", "config/frequency_words.txt"
@@ -664,9 +815,37 @@ def load_frequency_words(
 
     processed_groups = []
     filter_words = []
+    global_filters = []  # 新增：全局过滤词列表
+
+    # 默认区域（向后兼容）
+    current_section = "WORD_GROUPS"
 
     for group in word_groups:
-        words = [word.strip() for word in group.split("\n") if word.strip()]
+        lines = [line.strip() for line in group.split("\n") if line.strip()]
+
+        if not lines:
+            continue
+
+        # 检查是否为区域标记
+        if lines[0].startswith("[") and lines[0].endswith("]"):
+            section_name = lines[0][1:-1].upper()
+            if section_name in ("GLOBAL_FILTER", "WORD_GROUPS"):
+                current_section = section_name
+                lines = lines[1:]  # 移除标记行
+
+        # 处理全局过滤区域
+        if current_section == "GLOBAL_FILTER":
+            # 直接添加所有非空行到全局过滤列表
+            for line in lines:
+                # 忽略特殊语法前缀，只提取纯文本
+                if line.startswith(("!", "+", "@")):
+                    continue  # 全局过滤区不支持特殊语法
+                if line:
+                    global_filters.append(line)
+            continue
+
+        # 处理词组区域（保持现有逻辑）
+        words = lines
 
         group_required_words = []
         group_normal_words = []
@@ -705,7 +884,7 @@ def load_frequency_words(
                 }
             )
 
-    return processed_groups, filter_words
+    return processed_groups, filter_words, global_filters
 
 
 def parse_file_titles(file_path: Path) -> Tuple[Dict, Dict]:
@@ -992,7 +1171,7 @@ def calculate_news_weight(
 
 
 def matches_word_groups(
-    title: str, word_groups: List[Dict], filter_words: List[str]
+    title: str, word_groups: List[Dict], filter_words: List[str], global_filters: Optional[List[str]] = None
 ) -> bool:
     """检查标题是否匹配词组规则"""
     # 防御性类型检查：确保 title 是有效字符串
@@ -1001,12 +1180,17 @@ def matches_word_groups(
     if not title.strip():
         return False
 
+    title_lower = title.lower()
+
+    # 全局过滤检查（优先级最高）
+    if global_filters:
+        if any(global_word.lower() in title_lower for global_word in global_filters):
+            return False
+
     # 如果没有配置词组，则匹配所有标题（支持显示全部新闻）
     if not word_groups:
         return True
 
-    title_lower = title.lower()
-
     # 过滤词检查
     if any(filter_word.lower() in title_lower for filter_word in filter_words):
         return False
@@ -1099,8 +1283,9 @@ def count_word_frequency(
     rank_threshold: int = CONFIG["RANK_THRESHOLD"],
     new_titles: Optional[Dict] = None,
     mode: str = "daily",
+    global_filters: Optional[List[str]] = None,
 ) -> Tuple[List[Dict], int]:
-    """统计词频，支持必须词、频率词、过滤词，并标记新增标题"""
+    """统计词频，支持必须词、频率词、过滤词、全局过滤词，并标记新增标题"""
 
     # 如果没有配置词组，创建一个包含所有新闻的虚拟词组
     if not word_groups:
@@ -1191,7 +1376,7 @@ def count_word_frequency(
 
             # 使用统一的匹配逻辑
             matches_frequency_words = matches_word_groups(
-                title, word_groups, filter_words
+                title, word_groups, filter_words, global_filters
             )
 
             if not matches_frequency_words:
@@ -1443,11 +1628,11 @@ def prepare_report_data(
     if not hide_new_section:
         filtered_new_titles = {}
         if new_titles and id_to_name:
-            word_groups, filter_words = load_frequency_words()
+            word_groups, filter_words, global_filters = load_frequency_words()
             for source_id, titles_data in new_titles.items():
                 filtered_titles = {}
                 for title, title_data in titles_data.items():
-                    if matches_word_groups(title, word_groups, filter_words):
+                    if matches_word_groups(title, word_groups, filter_words, global_filters):
                         filtered_titles[title] = title_data
                 if filtered_titles:
                     filtered_new_titles[source_id] = filtered_titles
@@ -1742,8 +1927,15 @@ def generate_html_report(
         f.write(html_content)
 
     if is_daily_summary:
-        root_file_path = Path("index.html")
-        with open(root_file_path, "w", encoding="utf-8") as f:
+        # 生成到根目录（供 GitHub Pages 访问）
+        root_index_path = Path("index.html")
+        with open(root_index_path, "w", encoding="utf-8") as f:
+            f.write(html_content)
+
+        # 同时生成到 output 目录（供 Docker Volume 挂载访问）
+        output_index_path = Path("output") / "index.html"
+        ensure_directory_exists("output")
+        with open(output_index_path, "w", encoding="utf-8") as f:
             f.write(html_content)
 
     return file_path
@@ -2259,7 +2451,8 @@ def render_html_content(
                     </ul>
                 </div>"""
 
-    # 处理主要统计数据
+    # 生成热点词汇统计部分的HTML
+    stats_html = ""
     if report_data["stats"]:
         total_count = len(report_data["stats"])
 
@@ -2276,7 +2469,7 @@ def render_html_content(
 
             escaped_word = html_escape(stat["word"])
 
-            html += f"""
+            stats_html += f"""
                 <div class="word-group">
                     <div class="word-header">
                         <div class="word-info">
@@ -2291,7 +2484,7 @@ def render_html_content(
                 is_new = title_data.get("is_new", False)
                 new_class = "new" if is_new else ""
 
-                html += f"""
+                stats_html += f"""
                     <div class="news-item {new_class}">
                         <div class="news-number">{j}</div>
                         <div class="news-content">
@@ -2318,7 +2511,7 @@ def render_html_content(
                     else:
                         rank_text = f"{min_rank}-{max_rank}"
 
-                    html += f'<span class="rank-num {rank_class}">{rank_text}</span>'
+                    stats_html += f'<span class="rank-num {rank_class}">{rank_text}</span>'
 
                 # 处理时间显示
                 time_display = title_data.get("time_display", "")
@@ -2329,16 +2522,16 @@ def render_html_content(
                         .replace("[", "")
                         .replace("]", "")
                     )
-                    html += (
+                    stats_html += (
                         f'<span class="time-info">{html_escape(simplified_time)}</span>'
                     )
 
                 # 处理出现次数
                 count_info = title_data.get("count", 1)
                 if count_info > 1:
-                    html += f'<span class="count-info">{count_info}次</span>'
+                    stats_html += f'<span class="count-info">{count_info}次</span>'
 
-                html += """
+                stats_html += """
                             </div>
                             <div class="news-title">"""
 
@@ -2348,21 +2541,22 @@ def render_html_content(
 
                 if link_url:
                     escaped_url = html_escape(link_url)
-                    html += f'<a href="{escaped_url}" target="_blank" class="news-link">{escaped_title}</a>'
+                    stats_html += f'<a href="{escaped_url}" target="_blank" class="news-link">{escaped_title}</a>'
                 else:
-                    html += escaped_title
+                    stats_html += escaped_title
 
-                html += """
+                stats_html += """
                             </div>
                         </div>
                     </div>"""
 
-            html += """
+            stats_html += """
                 </div>"""
 
-    # 处理新增新闻区域
+    # 生成新增新闻区域的HTML
+    new_titles_html = ""
     if report_data["new_titles"]:
-        html += f"""
+        new_titles_html += f"""
                 <div class="new-section">
                     <div class="new-section-title">本次新增热点 (共 {report_data['total_new_count']} 条)</div>"""
 
@@ -2370,7 +2564,7 @@ def render_html_content(
             escaped_source = html_escape(source_data["source_name"])
             titles_count = len(source_data["titles"])
 
-            html += f"""
+            new_titles_html += f"""
                     <div class="new-source-group">
                         <div class="new-source-title">{escaped_source} · {titles_count}条</div>"""
 
@@ -2394,7 +2588,7 @@ def render_html_content(
                 else:
                     rank_text = "?"
 
-                html += f"""
+                new_titles_html += f"""
                         <div class="new-item">
                             <div class="new-item-number">{idx}</div>
                             <div class="new-item-rank {rank_class}">{rank_text}</div>
@@ -2407,21 +2601,29 @@ def render_html_content(
 
                 if link_url:
                     escaped_url = html_escape(link_url)
-                    html += f'<a href="{escaped_url}" target="_blank" class="news-link">{escaped_title}</a>'
+                    new_titles_html += f'<a href="{escaped_url}" target="_blank" class="news-link">{escaped_title}</a>'
                 else:
-                    html += escaped_title
+                    new_titles_html += escaped_title
 
-                html += """
+                new_titles_html += """
                                 </div>
                             </div>
                         </div>"""
 
-            html += """
+            new_titles_html += """
                     </div>"""
 
-        html += """
+        new_titles_html += """
                 </div>"""
 
+    # 根据配置决定内容顺序
+    if CONFIG.get("REVERSE_CONTENT_ORDER", False):
+        # 新增热点在前，热点词汇统计在后
+        html += new_titles_html + stats_html
+    else:
+        # 默认：热点词汇统计在前，新增热点在后
+        html += stats_html + new_titles_html
+
     html += """
             </div>
             
@@ -2762,57 +2964,47 @@ def render_feishu_content(
     report_data: Dict, update_info: Optional[Dict] = None, mode: str = "daily"
 ) -> str:
     """渲染飞书内容"""
-    text_content = ""
-
+    # 生成热点词汇统计部分
+    stats_content = ""
     if report_data["stats"]:
-        text_content += f"📊 **热点词汇统计**\n\n"
+        stats_content += f"📊 **热点词汇统计**\n\n"
 
-    total_count = len(report_data["stats"])
+        total_count = len(report_data["stats"])
 
-    for i, stat in enumerate(report_data["stats"]):
-        word = stat["word"]
-        count = stat["count"]
+        for i, stat in enumerate(report_data["stats"]):
+            word = stat["word"]
+            count = stat["count"]
 
-        sequence_display = f"<font color='grey'>[{i + 1}/{total_count}]</font>"
+            sequence_display = f"<font color='grey'>[{i + 1}/{total_count}]</font>"
 
-        if count >= 10:
-            text_content += f"🔥 {sequence_display} **{word}** : <font color='red'>{count}</font> 条\n\n"
-        elif count >= 5:
-            text_content += f"📈 {sequence_display} **{word}** : <font color='orange'>{count}</font> 条\n\n"
-        else:
-            text_content += f"📌 {sequence_display} **{word}** : {count} 条\n\n"
+            if count >= 10:
+                stats_content += f"🔥 {sequence_display} **{word}** : <font color='red'>{count}</font> 条\n\n"
+            elif count >= 5:
+                stats_content += f"📈 {sequence_display} **{word}** : <font color='orange'>{count}</font> 条\n\n"
+            else:
+                stats_content += f"📌 {sequence_display} **{word}** : {count} 条\n\n"
 
-        for j, title_data in enumerate(stat["titles"], 1):
-            formatted_title = format_title_for_platform(
-                "feishu", title_data, show_source=True
-            )
-            text_content += f"  {j}. {formatted_title}\n"
+            for j, title_data in enumerate(stat["titles"], 1):
+                formatted_title = format_title_for_platform(
+                    "feishu", title_data, show_source=True
+                )
+                stats_content += f"  {j}. {formatted_title}\n"
 
-            if j < len(stat["titles"]):
-                text_content += "\n"
+                if j < len(stat["titles"]):
+                    stats_content += "\n"
 
-        if i < len(report_data["stats"]) - 1:
-            text_content += f"\n{CONFIG['FEISHU_MESSAGE_SEPARATOR']}\n\n"
-
-    if not text_content:
-        if mode == "incremental":
-            mode_text = "增量模式下暂无新增匹配的热点词汇"
-        elif mode == "current":
-            mode_text = "当前榜单模式下暂无匹配的热点词汇"
-        else:
-            mode_text = "暂无匹配的热点词汇"
-        text_content = f"📭 {mode_text}\n\n"
+            if i < len(report_data["stats"]) - 1:
+                stats_content += f"\n{CONFIG['FEISHU_MESSAGE_SEPARATOR']}\n\n"
 
+    # 生成新增新闻部分
+    new_titles_content = ""
     if report_data["new_titles"]:
-        if text_content and "暂无匹配" not in text_content:
-            text_content += f"\n{CONFIG['FEISHU_MESSAGE_SEPARATOR']}\n\n"
-
-        text_content += (
+        new_titles_content += (
             f"🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
         )
 
         for source_data in report_data["new_titles"]:
-            text_content += (
+            new_titles_content += (
                 f"**{source_data['source_name']}** ({len(source_data['titles'])} 条):\n"
             )
 
@@ -2822,9 +3014,37 @@ def render_feishu_content(
                 formatted_title = format_title_for_platform(
                     "feishu", title_data_copy, show_source=False
                 )
-                text_content += f"  {j}. {formatted_title}\n"
+                new_titles_content += f"  {j}. {formatted_title}\n"
 
-            text_content += "\n"
+            new_titles_content += "\n"
+
+    # 根据配置决定内容顺序
+    text_content = ""
+    if CONFIG.get("REVERSE_CONTENT_ORDER", False):
+        # 新增热点在前，热点词汇统计在后
+        if new_titles_content:
+            text_content += new_titles_content
+            if stats_content:
+                text_content += f"\n{CONFIG['FEISHU_MESSAGE_SEPARATOR']}\n\n"
+        if stats_content:
+            text_content += stats_content
+    else:
+        # 默认：热点词汇统计在前，新增热点在后
+        if stats_content:
+            text_content += stats_content
+            if new_titles_content:
+                text_content += f"\n{CONFIG['FEISHU_MESSAGE_SEPARATOR']}\n\n"
+        if new_titles_content:
+            text_content += new_titles_content
+
+    if not text_content:
+        if mode == "incremental":
+            mode_text = "增量模式下暂无新增匹配的热点词汇"
+        elif mode == "current":
+            mode_text = "当前榜单模式下暂无匹配的热点词汇"
+        else:
+            mode_text = "暂无匹配的热点词汇"
+        text_content = f"📭 {mode_text}\n\n"
 
     if report_data["failed_ids"]:
         if text_content and "暂无匹配" not in text_content:
@@ -2849,21 +3069,21 @@ def render_dingtalk_content(
     report_data: Dict, update_info: Optional[Dict] = None, mode: str = "daily"
 ) -> str:
     """渲染钉钉内容"""
-    text_content = ""
-
     total_titles = sum(
         len(stat["titles"]) for stat in report_data["stats"] if stat["count"] > 0
     )
     now = get_beijing_time()
 
-    text_content += f"**总新闻数：** {total_titles}\n\n"
-    text_content += f"**时间：** {now.strftime('%Y-%m-%d %H:%M:%S')}\n\n"
-    text_content += f"**类型：** 热点分析报告\n\n"
-
-    text_content += "---\n\n"
+    # 头部信息
+    header_content = f"**总新闻数：** {total_titles}\n\n"
+    header_content += f"**时间：** {now.strftime('%Y-%m-%d %H:%M:%S')}\n\n"
+    header_content += f"**类型：** 热点分析报告\n\n"
+    header_content += "---\n\n"
 
+    # 生成热点词汇统计部分
+    stats_content = ""
     if report_data["stats"]:
-        text_content += f"📊 **热点词汇统计**\n\n"
+        stats_content += f"📊 **热点词汇统计**\n\n"
 
         total_count = len(report_data["stats"])
 
@@ -2874,25 +3094,64 @@ def render_dingtalk_content(
             sequence_display = f"[{i + 1}/{total_count}]"
 
             if count >= 10:
-                text_content += f"🔥 {sequence_display} **{word}** : **{count}** 条\n\n"
+                stats_content += f"🔥 {sequence_display} **{word}** : **{count}** 条\n\n"
             elif count >= 5:
-                text_content += f"📈 {sequence_display} **{word}** : **{count}** 条\n\n"
+                stats_content += f"📈 {sequence_display} **{word}** : **{count}** 条\n\n"
             else:
-                text_content += f"📌 {sequence_display} **{word}** : {count} 条\n\n"
+                stats_content += f"📌 {sequence_display} **{word}** : {count} 条\n\n"
 
             for j, title_data in enumerate(stat["titles"], 1):
                 formatted_title = format_title_for_platform(
                     "dingtalk", title_data, show_source=True
                 )
-                text_content += f"  {j}. {formatted_title}\n"
+                stats_content += f"  {j}. {formatted_title}\n"
 
                 if j < len(stat["titles"]):
-                    text_content += "\n"
+                    stats_content += "\n"
 
             if i < len(report_data["stats"]) - 1:
-                text_content += f"\n---\n\n"
+                stats_content += f"\n---\n\n"
 
-    if not report_data["stats"]:
+    # 生成新增新闻部分
+    new_titles_content = ""
+    if report_data["new_titles"]:
+        new_titles_content += (
+            f"🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
+        )
+
+        for source_data in report_data["new_titles"]:
+            new_titles_content += f"**{source_data['source_name']}** ({len(source_data['titles'])} 条):\n\n"
+
+            for j, title_data in enumerate(source_data["titles"], 1):
+                title_data_copy = title_data.copy()
+                title_data_copy["is_new"] = False
+                formatted_title = format_title_for_platform(
+                    "dingtalk", title_data_copy, show_source=False
+                )
+                new_titles_content += f"  {j}. {formatted_title}\n"
+
+            new_titles_content += "\n"
+
+    # 根据配置决定内容顺序
+    text_content = header_content
+    if CONFIG.get("REVERSE_CONTENT_ORDER", False):
+        # 新增热点在前，热点词汇统计在后
+        if new_titles_content:
+            text_content += new_titles_content
+            if stats_content:
+                text_content += f"\n---\n\n"
+        if stats_content:
+            text_content += stats_content
+    else:
+        # 默认：热点词汇统计在前，新增热点在后
+        if stats_content:
+            text_content += stats_content
+            if new_titles_content:
+                text_content += f"\n---\n\n"
+        if new_titles_content:
+            text_content += new_titles_content
+
+    if not stats_content and not new_titles_content:
         if mode == "incremental":
             mode_text = "增量模式下暂无新增匹配的热点词汇"
         elif mode == "current":
@@ -2901,29 +3160,8 @@ def render_dingtalk_content(
             mode_text = "暂无匹配的热点词汇"
         text_content += f"📭 {mode_text}\n\n"
 
-    if report_data["new_titles"]:
-        if text_content and "暂无匹配" not in text_content:
-            text_content += f"\n---\n\n"
-
-        text_content += (
-            f"🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
-        )
-
-        for source_data in report_data["new_titles"]:
-            text_content += f"**{source_data['source_name']}** ({len(source_data['titles'])} 条):\n\n"
-
-            for j, title_data in enumerate(source_data["titles"], 1):
-                title_data_copy = title_data.copy()
-                title_data_copy["is_new"] = False
-                formatted_title = format_title_for_platform(
-                    "dingtalk", title_data_copy, show_source=False
-                )
-                text_content += f"  {j}. {formatted_title}\n"
-
-            text_content += "\n"
-
     if report_data["failed_ids"]:
-        if text_content and "暂无匹配" not in text_content:
+        if "暂无匹配" not in text_content:
             text_content += f"\n---\n\n"
 
         text_content += "⚠️ **数据获取失败的平台：**\n\n"
@@ -3124,8 +3362,12 @@ def split_content_into_batches(
         batches.append(final_content)
         return batches
 
-    # 处理热点词汇统计
-    if report_data["stats"]:
+    # 定义处理热点词汇统计的函数
+    def process_stats_section(current_batch, current_batch_has_content, batches):
+        """处理热点词汇统计"""
+        if not report_data["stats"]:
+            return current_batch, current_batch_has_content, batches
+
         total_count = len(report_data["stats"])
 
         # 添加统计标题
@@ -3333,8 +3575,14 @@ def split_content_into_batches(
                 ):
                     current_batch = test_content
 
-    # 处理新增新闻（同样确保来源标题+第一条新闻的原子性）
-    if report_data["new_titles"]:
+        return current_batch, current_batch_has_content, batches
+
+    # 定义处理新增新闻的函数
+    def process_new_titles_section(current_batch, current_batch_has_content, batches):
+        """处理新增新闻"""
+        if not report_data["new_titles"]:
+            return current_batch, current_batch_has_content, batches
+
         new_header = ""
         if format_type in ("wework", "bark"):
             new_header = f"\n\n\n\n🆕 **本次新增热点新闻** (共 {report_data['total_new_count']} 条)\n\n"
@@ -3476,6 +3724,26 @@ def split_content_into_batches(
 
             current_batch += "\n"
 
+        return current_batch, current_batch_has_content, batches
+
+    # 根据配置决定处理顺序
+    if CONFIG.get("REVERSE_CONTENT_ORDER", False):
+        # 新增热点在前，热点词汇统计在后
+        current_batch, current_batch_has_content, batches = process_new_titles_section(
+            current_batch, current_batch_has_content, batches
+        )
+        current_batch, current_batch_has_content, batches = process_stats_section(
+            current_batch, current_batch_has_content, batches
+        )
+    else:
+        # 默认：热点词汇统计在前，新增热点在后
+        current_batch, current_batch_has_content, batches = process_stats_section(
+            current_batch, current_batch_has_content, batches
+        )
+        current_batch, current_batch_has_content, batches = process_new_titles_section(
+            current_batch, current_batch_has_content, batches
+        )
+
     if report_data["failed_ids"]:
         failed_header = ""
         if format_type == "wework":
@@ -3541,8 +3809,9 @@ def send_to_notifications(
     mode: str = "daily",
     html_file_path: Optional[str] = None,
 ) -> Dict[str, bool]:
-    """发送数据到多个通知平台"""
+    """发送数据到多个通知平台（支持多账号）"""
     results = {}
+    max_accounts = CONFIG["MAX_ACCOUNTS_PER_CHANNEL"]
 
     if CONFIG["PUSH_WINDOW"]["ENABLED"]:
         push_manager = PushRecordManager()
@@ -3565,90 +3834,133 @@ def send_to_notifications(
 
     report_data = prepare_report_data(stats, failed_ids, new_titles, id_to_name, mode)
 
-    feishu_url = CONFIG["FEISHU_WEBHOOK_URL"]
-    dingtalk_url = CONFIG["DINGTALK_WEBHOOK_URL"]
-    wework_url = CONFIG["WEWORK_WEBHOOK_URL"]
-    telegram_token = CONFIG["TELEGRAM_BOT_TOKEN"]
-    telegram_chat_id = CONFIG["TELEGRAM_CHAT_ID"]
+    update_info_to_send = update_info if CONFIG["SHOW_VERSION_UPDATE"] else None
+
+    # 发送到飞书（多账号）
+    feishu_urls = parse_multi_account_config(CONFIG["FEISHU_WEBHOOK_URL"])
+    if feishu_urls:
+        feishu_urls = limit_accounts(feishu_urls, max_accounts, "飞书")
+        feishu_results = []
+        for i, url in enumerate(feishu_urls):
+            if url:  # 跳过空值
+                account_label = f"账号{i+1}" if len(feishu_urls) > 1 else ""
+                result = send_to_feishu(
+                    url, report_data, report_type, update_info_to_send, proxy_url, mode, account_label
+                )
+                feishu_results.append(result)
+        results["feishu"] = any(feishu_results) if feishu_results else False
+
+    # 发送到钉钉（多账号）
+    dingtalk_urls = parse_multi_account_config(CONFIG["DINGTALK_WEBHOOK_URL"])
+    if dingtalk_urls:
+        dingtalk_urls = limit_accounts(dingtalk_urls, max_accounts, "钉钉")
+        dingtalk_results = []
+        for i, url in enumerate(dingtalk_urls):
+            if url:
+                account_label = f"账号{i+1}" if len(dingtalk_urls) > 1 else ""
+                result = send_to_dingtalk(
+                    url, report_data, report_type, update_info_to_send, proxy_url, mode, account_label
+                )
+                dingtalk_results.append(result)
+        results["dingtalk"] = any(dingtalk_results) if dingtalk_results else False
+
+    # 发送到企业微信（多账号）
+    wework_urls = parse_multi_account_config(CONFIG["WEWORK_WEBHOOK_URL"])
+    if wework_urls:
+        wework_urls = limit_accounts(wework_urls, max_accounts, "企业微信")
+        wework_results = []
+        for i, url in enumerate(wework_urls):
+            if url:
+                account_label = f"账号{i+1}" if len(wework_urls) > 1 else ""
+                result = send_to_wework(
+                    url, report_data, report_type, update_info_to_send, proxy_url, mode, account_label
+                )
+                wework_results.append(result)
+        results["wework"] = any(wework_results) if wework_results else False
+
+    # 发送到 Telegram（多账号，需验证配对）
+    telegram_tokens = parse_multi_account_config(CONFIG["TELEGRAM_BOT_TOKEN"])
+    telegram_chat_ids = parse_multi_account_config(CONFIG["TELEGRAM_CHAT_ID"])
+    if telegram_tokens and telegram_chat_ids:
+        valid, count = validate_paired_configs(
+            {"bot_token": telegram_tokens, "chat_id": telegram_chat_ids},
+            "Telegram",
+            required_keys=["bot_token", "chat_id"]
+        )
+        if valid and count > 0:
+            telegram_tokens = limit_accounts(telegram_tokens, max_accounts, "Telegram")
+            telegram_chat_ids = telegram_chat_ids[:len(telegram_tokens)]  # 保持数量一致
+            telegram_results = []
+            for i in range(len(telegram_tokens)):
+                token = telegram_tokens[i]
+                chat_id = telegram_chat_ids[i]
+                if token and chat_id:
+                    account_label = f"账号{i+1}" if len(telegram_tokens) > 1 else ""
+                    result = send_to_telegram(
+                        token, chat_id, report_data, report_type,
+                        update_info_to_send, proxy_url, mode, account_label
+                    )
+                    telegram_results.append(result)
+            results["telegram"] = any(telegram_results) if telegram_results else False
+
+    # 发送到 ntfy（多账号，需验证配对）
+    ntfy_server_url = CONFIG["NTFY_SERVER_URL"]
+    ntfy_topics = parse_multi_account_config(CONFIG["NTFY_TOPIC"])
+    ntfy_tokens = parse_multi_account_config(CONFIG["NTFY_TOKEN"])
+    if ntfy_server_url and ntfy_topics:
+        # 验证 token 和 topic 数量一致（如果配置了 token）
+        if ntfy_tokens and len(ntfy_tokens) != len(ntfy_topics):
+            print(f"❌ ntfy 配置错误：topic 数量({len(ntfy_topics)})与 token 数量({len(ntfy_tokens)})不一致，跳过 ntfy 推送")
+        else:
+            ntfy_topics = limit_accounts(ntfy_topics, max_accounts, "ntfy")
+            if ntfy_tokens:
+                ntfy_tokens = ntfy_tokens[:len(ntfy_topics)]
+            ntfy_results = []
+            for i, topic in enumerate(ntfy_topics):
+                if topic:
+                    token = get_account_at_index(ntfy_tokens, i, "") if ntfy_tokens else ""
+                    account_label = f"账号{i+1}" if len(ntfy_topics) > 1 else ""
+                    result = send_to_ntfy(
+                        ntfy_server_url, topic, token, report_data, report_type,
+                        update_info_to_send, proxy_url, mode, account_label
+                    )
+                    ntfy_results.append(result)
+            results["ntfy"] = any(ntfy_results) if ntfy_results else False
+
+    # 发送到 Bark（多账号）
+    bark_urls = parse_multi_account_config(CONFIG["BARK_URL"])
+    if bark_urls:
+        bark_urls = limit_accounts(bark_urls, max_accounts, "Bark")
+        bark_results = []
+        for i, url in enumerate(bark_urls):
+            if url:
+                account_label = f"账号{i+1}" if len(bark_urls) > 1 else ""
+                result = send_to_bark(
+                    url, report_data, report_type, update_info_to_send, proxy_url, mode, account_label
+                )
+                bark_results.append(result)
+        results["bark"] = any(bark_results) if bark_results else False
+
+    # 发送到 Slack（多账号）
+    slack_urls = parse_multi_account_config(CONFIG["SLACK_WEBHOOK_URL"])
+    if slack_urls:
+        slack_urls = limit_accounts(slack_urls, max_accounts, "Slack")
+        slack_results = []
+        for i, url in enumerate(slack_urls):
+            if url:
+                account_label = f"账号{i+1}" if len(slack_urls) > 1 else ""
+                result = send_to_slack(
+                    url, report_data, report_type, update_info_to_send, proxy_url, mode, account_label
+                )
+                slack_results.append(result)
+        results["slack"] = any(slack_results) if slack_results else False
+
+    # 发送邮件（保持原有逻辑，已支持多收件人）
     email_from = CONFIG["EMAIL_FROM"]
     email_password = CONFIG["EMAIL_PASSWORD"]
     email_to = CONFIG["EMAIL_TO"]
     email_smtp_server = CONFIG.get("EMAIL_SMTP_SERVER", "")
     email_smtp_port = CONFIG.get("EMAIL_SMTP_PORT", "")
-    ntfy_server_url = CONFIG["NTFY_SERVER_URL"]
-    ntfy_topic = CONFIG["NTFY_TOPIC"]
-    ntfy_token = CONFIG.get("NTFY_TOKEN", "")
-    bark_url = CONFIG["BARK_URL"]
-    slack_webhook_url = CONFIG["SLACK_WEBHOOK_URL"]
-
-    update_info_to_send = update_info if CONFIG["SHOW_VERSION_UPDATE"] else None
-
-    # 发送到飞书
-    if feishu_url:
-        results["feishu"] = send_to_feishu(
-            feishu_url, report_data, report_type, update_info_to_send, proxy_url, mode
-        )
-
-    # 发送到钉钉
-    if dingtalk_url:
-        results["dingtalk"] = send_to_dingtalk(
-            dingtalk_url, report_data, report_type, update_info_to_send, proxy_url, mode
-        )
-
-    # 发送到企业微信
-    if wework_url:
-        results["wework"] = send_to_wework(
-            wework_url, report_data, report_type, update_info_to_send, proxy_url, mode
-        )
-
-    # 发送到 Telegram
-    if telegram_token and telegram_chat_id:
-        results["telegram"] = send_to_telegram(
-            telegram_token,
-            telegram_chat_id,
-            report_data,
-            report_type,
-            update_info_to_send,
-            proxy_url,
-            mode,
-        )
-
-    # 发送到 ntfy
-    if ntfy_server_url and ntfy_topic:
-        results["ntfy"] = send_to_ntfy(
-            ntfy_server_url,
-            ntfy_topic,
-            ntfy_token,
-            report_data,
-            report_type,
-            update_info_to_send,
-            proxy_url,
-            mode,
-        )
-
-    # 发送到 Bark
-    if bark_url:
-        results["bark"] = send_to_bark(
-            bark_url,
-            report_data,
-            report_type,
-            update_info_to_send,
-            proxy_url,
-            mode,
-        )
-
-    # 发送到 Slack
-    if slack_webhook_url:
-        results["slack"] = send_to_slack(
-            slack_webhook_url,
-            report_data,
-            report_type,
-            update_info_to_send,
-            proxy_url,
-            mode,
-        )
-
-    # 发送邮件
     if email_from and email_password and email_to:
         results["email"] = send_to_email(
             email_from,
@@ -3682,6 +3994,7 @@ def send_to_feishu(
     update_info: Optional[Dict] = None,
     proxy_url: Optional[str] = None,
     mode: str = "daily",
+    account_label: str = "",
 ) -> bool:
     """发送到飞书（支持分批发送）"""
     headers = {"Content-Type": "application/json"}
@@ -3689,6 +4002,9 @@ def send_to_feishu(
     if proxy_url:
         proxies = {"http": proxy_url, "https": proxy_url}
 
+    # 日志前缀
+    log_prefix = f"飞书{account_label}" if account_label else "飞书"
+
     # 获取分批内容，使用飞书专用的批次大小
     feishu_batch_size = CONFIG.get("FEISHU_BATCH_SIZE", 29000)
     # 预留批次头部空间，避免添加头部后超限
@@ -3704,13 +4020,13 @@ def send_to_feishu(
     # 统一添加批次头部（已预留空间，不会超限）
     batches = add_batch_headers(batches, "feishu", feishu_batch_size)
 
-    print(f"飞书消息分为 {len(batches)} 批次发送 [{report_type}]")
+    print(f"{log_prefix}消息分为 {len(batches)} 批次发送 [{report_type}]")
 
     # 逐批发送
     for i, batch_content in enumerate(batches, 1):
         batch_size = len(batch_content.encode("utf-8"))
         print(
-            f"发送飞书第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
+            f"发送{log_prefix}第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
         )
 
         total_titles = sum(
@@ -3736,26 +4052,26 @@ def send_to_feishu(
                 result = response.json()
                 # 检查飞书的响应状态
                 if result.get("StatusCode") == 0 or result.get("code") == 0:
-                    print(f"飞书第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
+                    print(f"{log_prefix}第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
                     # 批次间间隔
                     if i < len(batches):
                         time.sleep(CONFIG["BATCH_SEND_INTERVAL"])
                 else:
                     error_msg = result.get("msg") or result.get("StatusMessage", "未知错误")
                     print(
-                        f"飞书第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{error_msg}"
+                        f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{error_msg}"
                     )
                     return False
             else:
                 print(
-                    f"飞书第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
+                    f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
                 )
                 return False
         except Exception as e:
-            print(f"飞书第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
             return False
 
-    print(f"飞书所有 {len(batches)} 批次发送完成 [{report_type}]")
+    print(f"{log_prefix}所有 {len(batches)} 批次发送完成 [{report_type}]")
     return True
 
 
@@ -3766,6 +4082,7 @@ def send_to_dingtalk(
     update_info: Optional[Dict] = None,
     proxy_url: Optional[str] = None,
     mode: str = "daily",
+    account_label: str = "",
 ) -> bool:
     """发送到钉钉（支持分批发送）"""
     headers = {"Content-Type": "application/json"}
@@ -3773,6 +4090,9 @@ def send_to_dingtalk(
     if proxy_url:
         proxies = {"http": proxy_url, "https": proxy_url}
 
+    # 日志前缀
+    log_prefix = f"钉钉{account_label}" if account_label else "钉钉"
+
     # 获取分批内容，使用钉钉专用的批次大小
     dingtalk_batch_size = CONFIG.get("DINGTALK_BATCH_SIZE", 20000)
     # 预留批次头部空间，避免添加头部后超限
@@ -3788,13 +4108,13 @@ def send_to_dingtalk(
     # 统一添加批次头部（已预留空间，不会超限）
     batches = add_batch_headers(batches, "dingtalk", dingtalk_batch_size)
 
-    print(f"钉钉消息分为 {len(batches)} 批次发送 [{report_type}]")
+    print(f"{log_prefix}消息分为 {len(batches)} 批次发送 [{report_type}]")
 
     # 逐批发送
     for i, batch_content in enumerate(batches, 1):
         batch_size = len(batch_content.encode("utf-8"))
         print(
-            f"发送钉钉第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
+            f"发送{log_prefix}第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
         )
 
         payload = {
@@ -3812,25 +4132,25 @@ def send_to_dingtalk(
             if response.status_code == 200:
                 result = response.json()
                 if result.get("errcode") == 0:
-                    print(f"钉钉第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
+                    print(f"{log_prefix}第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
                     # 批次间间隔
                     if i < len(batches):
                         time.sleep(CONFIG["BATCH_SEND_INTERVAL"])
                 else:
                     print(
-                        f"钉钉第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{result.get('errmsg')}"
+                        f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{result.get('errmsg')}"
                     )
                     return False
             else:
                 print(
-                    f"钉钉第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
+                    f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
                 )
                 return False
         except Exception as e:
-            print(f"钉钉第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
             return False
 
-    print(f"钉钉所有 {len(batches)} 批次发送完成 [{report_type}]")
+    print(f"{log_prefix}所有 {len(batches)} 批次发送完成 [{report_type}]")
     return True
 
 
@@ -3885,6 +4205,7 @@ def send_to_wework(
     update_info: Optional[Dict] = None,
     proxy_url: Optional[str] = None,
     mode: str = "daily",
+    account_label: str = "",
 ) -> bool:
     """发送到企业微信（支持分批发送，支持 markdown 和 text 两种格式）"""
     headers = {"Content-Type": "application/json"}
@@ -3892,14 +4213,17 @@ def send_to_wework(
     if proxy_url:
         proxies = {"http": proxy_url, "https": proxy_url}
 
+    # 日志前缀
+    log_prefix = f"企业微信{account_label}" if account_label else "企业微信"
+
     # 获取消息类型配置（markdown 或 text）
     msg_type = CONFIG.get("WEWORK_MSG_TYPE", "markdown").lower()
     is_text_mode = msg_type == "text"
 
     if is_text_mode:
-        print(f"企业微信使用 text 格式（个人微信模式）[{report_type}]")
+        print(f"{log_prefix}使用 text 格式（个人微信模式）[{report_type}]")
     else:
-        print(f"企业微信使用 markdown 格式（群机器人模式）[{report_type}]")
+        print(f"{log_prefix}使用 markdown 格式（群机器人模式）[{report_type}]")
 
     # text 模式使用 wework_text，markdown 模式使用 wework
     header_format_type = "wework_text" if is_text_mode else "wework"
@@ -3914,7 +4238,7 @@ def send_to_wework(
     # 统一添加批次头部（已预留空间，不会超限）
     batches = add_batch_headers(batches, header_format_type, wework_batch_size)
 
-    print(f"企业微信消息分为 {len(batches)} 批次发送 [{report_type}]")
+    print(f"{log_prefix}消息分为 {len(batches)} 批次发送 [{report_type}]")
 
     # 逐批发送
     for i, batch_content in enumerate(batches, 1):
@@ -3930,7 +4254,7 @@ def send_to_wework(
             batch_size = len(batch_content.encode("utf-8"))
 
         print(
-            f"发送企业微信第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
+            f"发送{log_prefix}第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
         )
 
         try:
@@ -3940,25 +4264,25 @@ def send_to_wework(
             if response.status_code == 200:
                 result = response.json()
                 if result.get("errcode") == 0:
-                    print(f"企业微信第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
+                    print(f"{log_prefix}第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
                     # 批次间间隔
                     if i < len(batches):
                         time.sleep(CONFIG["BATCH_SEND_INTERVAL"])
                 else:
                     print(
-                        f"企业微信第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{result.get('errmsg')}"
+                        f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{result.get('errmsg')}"
                     )
                     return False
             else:
                 print(
-                    f"企业微信第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
+                    f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
                 )
                 return False
         except Exception as e:
-            print(f"企业微信第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
             return False
 
-    print(f"企业微信所有 {len(batches)} 批次发送完成 [{report_type}]")
+    print(f"{log_prefix}所有 {len(batches)} 批次发送完成 [{report_type}]")
     return True
 
 
@@ -3970,6 +4294,7 @@ def send_to_telegram(
     update_info: Optional[Dict] = None,
     proxy_url: Optional[str] = None,
     mode: str = "daily",
+    account_label: str = "",
 ) -> bool:
     """发送到Telegram（支持分批发送）"""
     headers = {"Content-Type": "application/json"}
@@ -3979,6 +4304,9 @@ def send_to_telegram(
     if proxy_url:
         proxies = {"http": proxy_url, "https": proxy_url}
 
+    # 日志前缀
+    log_prefix = f"Telegram{account_label}" if account_label else "Telegram"
+
     # 获取分批内容，预留批次头部空间
     telegram_batch_size = CONFIG.get("MESSAGE_BATCH_SIZE", 4000)
     header_reserve = _get_max_batch_header_size("telegram")
@@ -3989,13 +4317,13 @@ def send_to_telegram(
     # 统一添加批次头部（已预留空间，不会超限）
     batches = add_batch_headers(batches, "telegram", telegram_batch_size)
 
-    print(f"Telegram消息分为 {len(batches)} 批次发送 [{report_type}]")
+    print(f"{log_prefix}消息分为 {len(batches)} 批次发送 [{report_type}]")
 
     # 逐批发送
     for i, batch_content in enumerate(batches, 1):
         batch_size = len(batch_content.encode("utf-8"))
         print(
-            f"发送Telegram第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
+            f"发送{log_prefix}第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
         )
 
         payload = {
@@ -4012,25 +4340,25 @@ def send_to_telegram(
             if response.status_code == 200:
                 result = response.json()
                 if result.get("ok"):
-                    print(f"Telegram第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
+                    print(f"{log_prefix}第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
                     # 批次间间隔
                     if i < len(batches):
                         time.sleep(CONFIG["BATCH_SEND_INTERVAL"])
                 else:
                     print(
-                        f"Telegram第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{result.get('description')}"
+                        f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{result.get('description')}"
                     )
                     return False
             else:
                 print(
-                    f"Telegram第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
+                    f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
                 )
                 return False
         except Exception as e:
-            print(f"Telegram第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
             return False
 
-    print(f"Telegram所有 {len(batches)} 批次发送完成 [{report_type}]")
+    print(f"{log_prefix}所有 {len(batches)} 批次发送完成 [{report_type}]")
     return True
 
 
@@ -4183,8 +4511,12 @@ def send_to_ntfy(
     update_info: Optional[Dict] = None,
     proxy_url: Optional[str] = None,
     mode: str = "daily",
+    account_label: str = "",
 ) -> bool:
     """发送到ntfy（支持分批发送，严格遵守4KB限制）"""
+    # 日志前缀
+    log_prefix = f"ntfy{account_label}" if account_label else "ntfy"
+
     # 避免 HTTP header 编码问题
     report_type_en_map = {
         "当日汇总": "Daily Summary",
@@ -4227,13 +4559,13 @@ def send_to_ntfy(
     batches = add_batch_headers(batches, "ntfy", ntfy_batch_size)
 
     total_batches = len(batches)
-    print(f"ntfy消息分为 {total_batches} 批次发送 [{report_type}]")
+    print(f"{log_prefix}消息分为 {total_batches} 批次发送 [{report_type}]")
 
     # 反转批次顺序，使得在ntfy客户端显示时顺序正确
     # ntfy显示最新消息在上面，所以我们从最后一批开始推送
     reversed_batches = list(reversed(batches))
 
-    print(f"ntfy将按反向顺序推送（最后批次先推送），确保客户端显示顺序正确")
+    print(f"{log_prefix}将按反向顺序推送（最后批次先推送），确保客户端显示顺序正确")
 
     # 逐批发送（反向顺序）
     success_count = 0
@@ -4243,12 +4575,12 @@ def send_to_ntfy(
 
         batch_size = len(batch_content.encode("utf-8"))
         print(
-            f"发送ntfy第 {actual_batch_num}/{total_batches} 批次（推送顺序: {idx}/{total_batches}），大小：{batch_size} 字节 [{report_type}]"
+            f"发送{log_prefix}第 {actual_batch_num}/{total_batches} 批次（推送顺序: {idx}/{total_batches}），大小：{batch_size} 字节 [{report_type}]"
         )
 
         # 检查消息大小，确保不超过4KB
         if batch_size > 4096:
-            print(f"警告：ntfy第 {actual_batch_num} 批次消息过大（{batch_size} 字节），可能被拒绝")
+            print(f"警告：{log_prefix}第 {actual_batch_num} 批次消息过大（{batch_size} 字节），可能被拒绝")
 
         # 更新 headers 的批次标识
         current_headers = headers.copy()
@@ -4267,7 +4599,7 @@ def send_to_ntfy(
             )
 
             if response.status_code == 200:
-                print(f"ntfy第 {actual_batch_num}/{total_batches} 批次发送成功 [{report_type}]")
+                print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次发送成功 [{report_type}]")
                 success_count += 1
                 if idx < total_batches:
                     # 公共服务器建议 2-3 秒，自托管可以更短
@@ -4275,7 +4607,7 @@ def send_to_ntfy(
                     time.sleep(interval)
             elif response.status_code == 429:
                 print(
-                    f"ntfy第 {actual_batch_num}/{total_batches} 批次速率限制 [{report_type}]，等待后重试"
+                    f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次速率限制 [{report_type}]，等待后重试"
                 )
                 time.sleep(10)  # 等待10秒后重试
                 # 重试一次
@@ -4287,19 +4619,19 @@ def send_to_ntfy(
                     timeout=30,
                 )
                 if retry_response.status_code == 200:
-                    print(f"ntfy第 {actual_batch_num}/{total_batches} 批次重试成功 [{report_type}]")
+                    print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次重试成功 [{report_type}]")
                     success_count += 1
                 else:
                     print(
-                        f"ntfy第 {actual_batch_num}/{total_batches} 批次重试失败，状态码：{retry_response.status_code}"
+                        f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次重试失败，状态码：{retry_response.status_code}"
                     )
             elif response.status_code == 413:
                 print(
-                    f"ntfy第 {actual_batch_num}/{total_batches} 批次消息过大被拒绝 [{report_type}]，消息大小：{batch_size} 字节"
+                    f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次消息过大被拒绝 [{report_type}]，消息大小：{batch_size} 字节"
                 )
             else:
                 print(
-                    f"ntfy第 {actual_batch_num}/{total_batches} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
+                    f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
                 )
                 try:
                     print(f"错误详情：{response.text}")
@@ -4307,23 +4639,23 @@ def send_to_ntfy(
                     pass
 
         except requests.exceptions.ConnectTimeout:
-            print(f"ntfy第 {actual_batch_num}/{total_batches} 批次连接超时 [{report_type}]")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次连接超时 [{report_type}]")
         except requests.exceptions.ReadTimeout:
-            print(f"ntfy第 {actual_batch_num}/{total_batches} 批次读取超时 [{report_type}]")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次读取超时 [{report_type}]")
         except requests.exceptions.ConnectionError as e:
-            print(f"ntfy第 {actual_batch_num}/{total_batches} 批次连接错误 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次连接错误 [{report_type}]：{e}")
         except Exception as e:
-            print(f"ntfy第 {actual_batch_num}/{total_batches} 批次发送异常 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次发送异常 [{report_type}]：{e}")
 
     # 判断整体发送是否成功
     if success_count == total_batches:
-        print(f"ntfy所有 {total_batches} 批次发送完成 [{report_type}]")
+        print(f"{log_prefix}所有 {total_batches} 批次发送完成 [{report_type}]")
         return True
     elif success_count > 0:
-        print(f"ntfy部分发送成功：{success_count}/{total_batches} 批次 [{report_type}]")
+        print(f"{log_prefix}部分发送成功：{success_count}/{total_batches} 批次 [{report_type}]")
         return True  # 部分成功也视为成功
     else:
-        print(f"ntfy发送完全失败 [{report_type}]")
+        print(f"{log_prefix}发送完全失败 [{report_type}]")
         return False
 
 
@@ -4334,8 +4666,12 @@ def send_to_bark(
     update_info: Optional[Dict] = None,
     proxy_url: Optional[str] = None,
     mode: str = "daily",
+    account_label: str = "",
 ) -> bool:
     """发送到Bark（支持分批发送，使用 markdown 格式）"""
+    # 日志前缀
+    log_prefix = f"Bark{account_label}" if account_label else "Bark"
+
     proxies = None
     if proxy_url:
         proxies = {"http": proxy_url, "https": proxy_url}
@@ -4348,7 +4684,7 @@ def send_to_bark(
     device_key = parsed_url.path.strip('/').split('/')[0] if parsed_url.path else None
 
     if not device_key:
-        print(f"Bark URL 格式错误，无法提取 device_key: {bark_url}")
+        print(f"{log_prefix} URL 格式错误，无法提取 device_key: {bark_url}")
         return False
 
     # 构建正确的 API 端点
@@ -4365,13 +4701,13 @@ def send_to_bark(
     batches = add_batch_headers(batches, "bark", bark_batch_size)
 
     total_batches = len(batches)
-    print(f"Bark消息分为 {total_batches} 批次发送 [{report_type}]")
+    print(f"{log_prefix}消息分为 {total_batches} 批次发送 [{report_type}]")
 
     # 反转批次顺序，使得在Bark客户端显示时顺序正确
     # Bark显示最新消息在上面，所以我们从最后一批开始推送
     reversed_batches = list(reversed(batches))
 
-    print(f"Bark将按反向顺序推送（最后批次先推送），确保客户端显示顺序正确")
+    print(f"{log_prefix}将按反向顺序推送（最后批次先推送），确保客户端显示顺序正确")
 
     # 逐批发送（反向顺序）
     success_count = 0
@@ -4381,13 +4717,13 @@ def send_to_bark(
 
         batch_size = len(batch_content.encode("utf-8"))
         print(
-            f"发送Bark第 {actual_batch_num}/{total_batches} 批次（推送顺序: {idx}/{total_batches}），大小：{batch_size} 字节 [{report_type}]"
+            f"发送{log_prefix}第 {actual_batch_num}/{total_batches} 批次（推送顺序: {idx}/{total_batches}），大小：{batch_size} 字节 [{report_type}]"
         )
 
         # 检查消息大小（Bark使用APNs，限制4KB）
         if batch_size > 4096:
             print(
-                f"警告：Bark第 {actual_batch_num}/{total_batches} 批次消息过大（{batch_size} 字节），可能被拒绝"
+                f"警告：{log_prefix}第 {actual_batch_num}/{total_batches} 批次消息过大（{batch_size} 字节），可能被拒绝"
             )
 
         # 构建JSON payload
@@ -4411,18 +4747,18 @@ def send_to_bark(
             if response.status_code == 200:
                 result = response.json()
                 if result.get("code") == 200:
-                    print(f"Bark第 {actual_batch_num}/{total_batches} 批次发送成功 [{report_type}]")
+                    print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次发送成功 [{report_type}]")
                     success_count += 1
                     # 批次间间隔
                     if idx < total_batches:
                         time.sleep(CONFIG["BATCH_SEND_INTERVAL"])
                 else:
                     print(
-                        f"Bark第 {actual_batch_num}/{total_batches} 批次发送失败 [{report_type}]，错误：{result.get('message', '未知错误')}"
+                        f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次发送失败 [{report_type}]，错误：{result.get('message', '未知错误')}"
                     )
             else:
                 print(
-                    f"Bark第 {actual_batch_num}/{total_batches} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
+                    f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次发送失败 [{report_type}]，状态码：{response.status_code}"
                 )
                 try:
                     print(f"错误详情：{response.text}")
@@ -4430,23 +4766,23 @@ def send_to_bark(
                     pass
 
         except requests.exceptions.ConnectTimeout:
-            print(f"Bark第 {actual_batch_num}/{total_batches} 批次连接超时 [{report_type}]")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次连接超时 [{report_type}]")
         except requests.exceptions.ReadTimeout:
-            print(f"Bark第 {actual_batch_num}/{total_batches} 批次读取超时 [{report_type}]")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次读取超时 [{report_type}]")
         except requests.exceptions.ConnectionError as e:
-            print(f"Bark第 {actual_batch_num}/{total_batches} 批次连接错误 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次连接错误 [{report_type}]：{e}")
         except Exception as e:
-            print(f"Bark第 {actual_batch_num}/{total_batches} 批次发送异常 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {actual_batch_num}/{total_batches} 批次发送异常 [{report_type}]：{e}")
 
     # 判断整体发送是否成功
     if success_count == total_batches:
-        print(f"Bark所有 {total_batches} 批次发送完成 [{report_type}]")
+        print(f"{log_prefix}所有 {total_batches} 批次发送完成 [{report_type}]")
         return True
     elif success_count > 0:
-        print(f"Bark部分发送成功：{success_count}/{total_batches} 批次 [{report_type}]")
+        print(f"{log_prefix}部分发送成功：{success_count}/{total_batches} 批次 [{report_type}]")
         return True  # 部分成功也视为成功
     else:
-        print(f"Bark发送完全失败 [{report_type}]")
+        print(f"{log_prefix}发送完全失败 [{report_type}]")
         return False
 
 
@@ -4475,6 +4811,7 @@ def send_to_slack(
     update_info: Optional[Dict] = None,
     proxy_url: Optional[str] = None,
     mode: str = "daily",
+    account_label: str = "",
 ) -> bool:
     """发送到Slack（支持分批发送，使用 mrkdwn 格式）"""
     headers = {"Content-Type": "application/json"}
@@ -4482,6 +4819,9 @@ def send_to_slack(
     if proxy_url:
         proxies = {"http": proxy_url, "https": proxy_url}
 
+    # 日志前缀
+    log_prefix = f"Slack{account_label}" if account_label else "Slack"
+
     # 获取分批内容（使用 Slack 批次大小），预留批次头部空间
     slack_batch_size = CONFIG["SLACK_BATCH_SIZE"]
     header_reserve = _get_max_batch_header_size("slack")
@@ -4492,7 +4832,7 @@ def send_to_slack(
     # 统一添加批次头部（已预留空间，不会超限）
     batches = add_batch_headers(batches, "slack", slack_batch_size)
 
-    print(f"Slack消息分为 {len(batches)} 批次发送 [{report_type}]")
+    print(f"{log_prefix}消息分为 {len(batches)} 批次发送 [{report_type}]")
 
     # 逐批发送
     for i, batch_content in enumerate(batches, 1):
@@ -4501,7 +4841,7 @@ def send_to_slack(
 
         batch_size = len(mrkdwn_content.encode("utf-8"))
         print(
-            f"发送Slack第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
+            f"发送{log_prefix}第 {i}/{len(batches)} 批次，大小：{batch_size} 字节 [{report_type}]"
         )
 
         # 构建 Slack payload（使用简单的 text 字段，支持 mrkdwn）
@@ -4516,21 +4856,21 @@ def send_to_slack(
 
             # Slack Incoming Webhooks 成功时返回 "ok" 文本
             if response.status_code == 200 and response.text == "ok":
-                print(f"Slack第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
+                print(f"{log_prefix}第 {i}/{len(batches)} 批次发送成功 [{report_type}]")
                 # 批次间间隔
                 if i < len(batches):
                     time.sleep(CONFIG["BATCH_SEND_INTERVAL"])
             else:
                 error_msg = response.text if response.text else f"状态码：{response.status_code}"
                 print(
-                    f"Slack第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{error_msg}"
+                    f"{log_prefix}第 {i}/{len(batches)} 批次发送失败 [{report_type}]，错误：{error_msg}"
                 )
                 return False
         except Exception as e:
-            print(f"Slack第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
+            print(f"{log_prefix}第 {i}/{len(batches)} 批次发送出错 [{report_type}]：{e}")
             return False
 
-    print(f"Slack所有 {len(batches)} 批次发送完成 [{report_type}]")
+    print(f"{log_prefix}所有 {len(batches)} 批次发送完成 [{report_type}]")
     return True
 
 
@@ -4690,7 +5030,7 @@ class NewsAnalyzer:
             print(f"读取到 {total_titles} 个标题（已按当前监控平台过滤）")
 
             new_titles = detect_latest_new_titles(current_platform_ids)
-            word_groups, filter_words = load_frequency_words()
+            word_groups, filter_words, global_filters = load_frequency_words()
 
             return (
                 all_results,
@@ -4699,6 +5039,7 @@ class NewsAnalyzer:
                 new_titles,
                 word_groups,
                 filter_words,
+                global_filters,
             )
         except Exception as e:
             print(f"数据加载失败: {e}")
@@ -4735,6 +5076,7 @@ class NewsAnalyzer:
         id_to_name: Dict,
         failed_ids: Optional[List] = None,
         is_daily_summary: bool = False,
+        global_filters: Optional[List[str]] = None,
     ) -> Tuple[List[Dict], str]:
         """统一的分析流水线：数据处理 → 统计计算 → HTML生成"""
 
@@ -4748,6 +5090,7 @@ class NewsAnalyzer:
             self.rank_threshold,
             new_titles,
             mode=mode,
+            global_filters=global_filters,
         )
 
         # HTML生成
@@ -4827,7 +5170,7 @@ class NewsAnalyzer:
         if not analysis_data:
             return None
 
-        all_results, id_to_name, title_info, new_titles, word_groups, filter_words = (
+        all_results, id_to_name, title_info, new_titles, word_groups, filter_words, global_filters = (
             analysis_data
         )
 
@@ -4841,6 +5184,7 @@ class NewsAnalyzer:
             filter_words,
             id_to_name,
             is_daily_summary=True,
+            global_filters=global_filters,
         )
 
         print(f"{summary_type}报告已生成: {html_file}")
@@ -4868,7 +5212,7 @@ class NewsAnalyzer:
         if not analysis_data:
             return None
 
-        all_results, id_to_name, title_info, new_titles, word_groups, filter_words = (
+        all_results, id_to_name, title_info, new_titles, word_groups, filter_words, global_filters = (
             analysis_data
         )
 
@@ -4882,6 +5226,7 @@ class NewsAnalyzer:
             filter_words,
             id_to_name,
             is_daily_summary=True,
+            global_filters=global_filters,
         )
 
         print(f"{summary_type}HTML已生成: {html_file}")
@@ -4941,7 +5286,7 @@ class NewsAnalyzer:
 
         new_titles = detect_latest_new_titles(current_platform_ids)
         time_info = Path(save_titles_to_file(results, id_to_name, failed_ids)).stem
-        word_groups, filter_words = load_frequency_words()
+        word_groups, filter_words, global_filters = load_frequency_words()
 
         # current模式下，实时推送需要使用完整的历史数据来保证统计信息的完整性
         if self.report_mode == "current":
@@ -4955,6 +5300,7 @@ class NewsAnalyzer:
                     historical_new_titles,
                     _,
                     _,
+                    _,
                 ) = analysis_data
 
                 print(
@@ -4970,6 +5316,7 @@ class NewsAnalyzer:
                     filter_words,
                     historical_id_to_name,
                     failed_ids=failed_ids,
+                    global_filters=global_filters,
                 )
 
                 combined_id_to_name = {**historical_id_to_name, **id_to_name}
@@ -5002,6 +5349,7 @@ class NewsAnalyzer:
                 filter_words,
                 id_to_name,
                 failed_ids=failed_ids,
+                global_filters=global_filters,
             )
             print(f"HTML报告已生成: {html_file}")
 
diff --git a/version b/version
index 8cf6caf..e5b8203 100644
--- a/version
+++ b/version
@@ -1 +1 @@
-3.4.1
\ No newline at end of file
+3.5.0
\ No newline at end of file