Deploy in 30 seconds — Say goodbye to endless scrolling, only see the news you truly care about
中文 | English
This project is designed to be lightweight and easy to deploy
💡 Click the links below to jump to the corresponding section. Start with "Quick Start" for deployment, see "Configuration Guide" for detailed customization
| 🚀 Quick Start | AI Analysis | ⚙️ Configuration Guide |
| Docker Deployment | MCP Clients | 📝 Changelog |
| 🎯 Core Features | ☕ Support Project | 📚 Related Projects |
- Thanks to stargazers, your stars and forks are the best support for open source 😍
👉 Click to view Acknowledgments (Angel Round Honor Roll 🔥73+🔥 supporters)
💡 Special Note:
- About the List: The table below records supporters from the early stage (Angel Round) of the project. Due to the manual nature of statistics in the early days, there may be omissions or incomplete records. If anyone was missed, it was unintentional, and we ask for your kind understanding.
- Future Plan: To focus limited energy back on code development and feature iteration, this list will no longer be manually maintained as of today.
Whether your name is on the list or not, your every bit of support is the cornerstone that allows TrendRadar to be where it is today. 🙏
Thanks to GitHub for providing free infrastructure, which is the biggest prerequisite for this project to run conveniently with one-click fork.
This project uses the API from newsnow to fetch multi-platform data. Special thanks to the author for providing this service.
After communication, the author indicated no concerns about server pressure, but this is based on their goodwill and trust. Please everyone:
- Visit the newsnow project and give it a star
- When deploying with Docker, please control the frequency reasonably and avoid being overly greedy
Thanks to the following platforms and individuals for recommendations (in chronological order)
- Appinn (小众软件) - Open source software recommendation platform
- LinuxDo Community - Tech enthusiasts community
- Ruan Yifeng's Weekly - Influential tech weekly in Chinese tech circle
Thanks to financial supporters. Your generosity has transformed into snacks and drinks beside my keyboard, accompanying every iteration of this project
Return of "One-Yuan Appreciation": With the release of v5.0.0, the project enters a new phase. To support growing API costs and caffeine consumption, the "One-Yuan Appreciation" channel is now reopened. Every bit of your kindness translates into Tokens and motivation in the code world. 🚀 Support Now
| Supporter | Amount (CNY) | Date | Note |
|---|---|---|---|
| D*5 | 1.8 * 3 | 2025.11.24 | |
| *鬼 | 1 | 2025.11.17 | |
| *超 | 10 | 2025.11.17 | |
| R*w | 10 | 2025.11.17 | Great agent work! |
| J*o | 1 | 2025.11.17 | Thanks for open source |
| *晨 | 8.88 | 2025.11.16 | Nice project |
| *海 | 1 | 2025.11.15 | |
| *德 | 1.99 | 2025.11.15 | |
| *疏 | 8.8 | 2025.11.14 | Great project |
| M*e | 10 | 2025.11.14 | Open source is not easy |
| **柯 | 1 | 2025.11.14 | |
| *云 | 88 | 2025.11.13 | Good project |
| *W | 6 | 2025.11.13 | |
| *凯 | 1 | 2025.11.13 | |
| 对*. | 1 | 2025.11.13 | Thanks for TrendRadar |
| s*y | 1 | 2025.11.13 | |
| **翔 | 10 | 2025.11.13 | Wish I found it earlier |
| *韦 | 9.9 | 2025.11.13 | TrendRadar is awesome |
| h*p | 5 | 2025.11.12 | Support Chinese open source |
| c*r | 6 | 2025.11.12 | |
| a*n | 5 | 2025.11.12 | |
| 。*c | 1 | 2025.11.12 | Thanks for sharing |
| ... | ... | ... | (More 50+ supporters) |
Sponsorship Open
Seeking quality product partners.
More than features, I value your attitude towards users.
Please share your user community or feedback channels—I want to see how you support your users.
📩 Contact Me
TrendRadar is a completely free and open-source project. Your support fuels the motivation for continuous updates.
A bottle of water or a snack represents your love. Any amount is welcome; even 1 RMB is a gesture of kindness.
Your sponsorship will be used to replenish caffeine for carbon-based lifeforms ☕️ and API Tokens for silicon-based lifeforms 🤖.
| WeChat Pay | Alipay |
|---|---|
 |
 |
- Star the Repo ⭐️: It only takes 1 second. Letting more people see this project is the greatest recognition for me.
- Charity 🌻: Search for Tencent Charity (or support a local charity) to help students in need. Pass this kindness forward.
If you utilize the core code or draw inspiration from the logic of this project, it would be greatly appreciated if you could acknowledge the source in your README or documentation and include a link to this repository.
This contributes to the sustainable maintenance of the project and the growth of the community. Thank you for your respect and support! ❤️
- GitHub Issues: Best for specific technical issues. Please provide complete information (screenshots, error logs, etc.) to help locate the problem quickly.
- WeChat Official Account: It is recommended to leave comments under relevant articles. If you need to ask questions in the background, liking/recommending the article first is the best "icebreaker," and I can feel your appreciation (´▽`ʃ♡ƪ).
Friendly Reminder:
This project is for open-source sharing, not a commercial product. A lot of effort went into the documentation; most deployment issues can be answered in 🚀 Quick Start.
Please be patient and polite when asking questions. Treat the author as a friend, not customer service, for better communication efficiency!
| Follow on WeChat |
|---|
 |
📌 Check Latest Updates: Original Repository Changelog:
- Tip: Check [Changelog] to understand specific [Features]
- Added independent control for AI analysis mode, options: follow_report | daily | current | incremental
- Added time window control for AI analysis, supporting custom execution periods and daily frequency limits
- Added configuration file version management function
- Fixed several bugs
Major Refactor: AI Module Migration to LiteLLM
- Unified AI Interface: Replaced manual implementation with LiteLLM, supporting 100+ AI providers
- Simplified Configuration: Removed
providerfield, now usingmodel: "provider/model_name"format - New Features: Auto-retry (
num_retries), fallback models (fallback_models) - Configuration Changes:
ai.provider→ Removed (merged into model)ai.base_url→ai.api_baseAI_PROVIDERenvironment variable → RemovedAI_BASE_URLenvironment variable →AI_API_BASE
- Model Format Examples:
- DeepSeek:
deepseek/deepseek-chat - OpenAI:
openai/gpt-4o - Gemini:
gemini/gemini-2.5-flash - Anthropic:
anthropic/claude-3-5-sonnet
- DeepSeek:
See config.yaml for details
🌐 AI Translation
- Multi-language Translation: Translate push content to any language
- Batch Translation: Smart batch processing to reduce API calls
- Custom Prompts: Customize translation style
🔧 Configuration Optimization
- Standalone AI Model Config: Analysis and translation share model config
- Unified Region Switches: Unified management of push region display
- Custom Region Order: Customize display order of each region
✨ AI Analysis Enhancement
- AI Analysis Embedded in HTML: Analysis results directly embedded in HTML reports, used by email notifications
- Rich Style AI Section: Gradient blue card layout, clearly separating analysis dimensions
- Ranking Timeline Support: AI can access precise ranking at each crawl time point
- Section Reorganization (7→4): Consolidated into Core Trends, Sentiment & Controversy, Signals & Anomalies, Outlook & Strategy
🔧 Multi-Model Adaptation
- Universal Parameter Passthrough: Pass any advanced parameters to API
- Gemini Adaptation: Native parameter support with relaxed safety settings
🐛 Bug Fixes
- Fixed various known issues, improved system stability
- Breaking Change: All tool return values unified to
{success, summary, data, error}structure - Async Consistency: All 21 tool functions wrapped with
asyncio.to_thread()for sync calls - MCP Resources: Added 4 resources (platforms, rss-feeds, available-dates, keywords)
- RSS Enhancement:
get_latest_rsssupports multi-day queries (days param), cross-date URL deduplication - Regex Matching Fix:
get_trending_topicssupports/pattern/regex syntax anddisplay_name - Cache Optimization: Added
make_cache_key()function with param sorting + MD5 hash for consistency - New check_version Tool: Check TrendRadar and MCP Server version updates simultaneously
👉 Click to expand: Historical Updates
Dev Anecdote: A salute to a certain 'C' model provider that accompanied me for over two years, only to slap me with
"This organization has been disabled"right after I renewed my subscription.
✨ "Five Major Sections" Content Refactoring
This update refactors the push message structure into five distinct core sections:
- 📊 Trending News: Aggregated trending topics from across the web, precisely filtered by your keywords.
- 📰 RSS Feeds: Your personalized subscription content, supporting keyword-based grouping.
- 🆕 New Items: Real-time capture of brand new trending topics since the last run (marked with 🆕).
- 📋 Independent Display: Complete trending lists or RSS feeds from specified platforms, completely unaffected by keyword filtering.
- ✨ AI Analysis: Deep insights driven by AI, including trend overview, popularity trends, and critically important sentiment analysis.
✨ AI Smart Analysis Push Feature
- AI Analysis Integration: Use AI models to deeply analyze push content, automatically generate trending insights, keyword analysis, cross-platform correlation, potential impact assessment
- Sentiment Analysis: New deep sentiment recognition to accurately capture positive, negative, controversial, or concerned public opinions (v5.0.0 key enhancement)
- Multi AI Provider Support: Supports DeepSeek (default, cost-effective), OpenAI, Google Gemini, and any OpenAI-compatible API
- Two Push Modes:
only_analysis(AI analysis only),both(push both) - Custom Prompts: Customize AI analysis role and output format via
config/ai_analysis_prompt.txt - Multi-dimensional Analysis: AI can analyze ranking changes, trending duration, cross-platform performance, trend prediction
- Fix RSS HTML Display: Fixed RSS data format mismatch causing rendering issues, now displays correctly grouped by keyword
- New Regex Syntax: Keyword config supports
/pattern/regex syntax, solves English substring mismatch issues (e.g.,aimatchingtraining) 📖 View Syntax Details - New Display Name Syntax: Use
=> aliasto give complex regex a friendly name, cleaner push notifications (e.g.,/\bai\b/ => AI Related) - Can't Write Regex? README now includes AI prompt guide - just tell ChatGPT/Gemini/DeepSeek what you want to match
- Architecture Refactoring: Removed TXT support, unified to SQLite database
- RSS Query: Added
get_latest_rss,search_rss,get_rss_feeds_status - Unified Search:
search_newssupportsinclude_rssparameter to search both trending and RSS
- Fix RSS HTML Display: Merged RSS content into trending HTML page, grouped by source
- New display_mode Config: Support
keyword(group by keyword) andplatform(group by platform) display modes
- RSS Feed Support: Added RSS/Atom feed crawling, keyword-based grouping and statistics (consistent with trending format)
- Storage Structure Refactoring: Flattened directory structure
output/{type}/{date}.db - Unified Sorting Config:
sort_by_position_firstaffects both trending and RSS - Config Structure Refactoring:
config.yamlreorganized into 7 logical groups (app, report, notification, storage, platforms, rss, advanced) with clearer config paths
MCP Module Update - Optimized toolset, added aggregation & comparison features, merged redundant tools:
- Added
aggregate_newstool - Cross-platform news deduplication and aggregation - Added
compare_periodstool - Period comparison analysis (week-over-week/month-over-month) - Merged
find_similar_news+search_related_news_history→find_related_news - Enhanced
get_trending_topics- Addedauto_extractmode for automatic trending extraction - Fixed miscellaneous bugs
- Updated README-MCP-FAQ.md documentation in both Chinese and English (Q1-Q18)
- Added URL normalization to fix duplicate push issues caused by dynamic parameters (e.g., Weibo's
band_rank) - Fixed incremental mode detection logic to correctly identify historical titles
MCP Module Update:
- Adapted for v4.0.0, while maintaining compatibility with v3.x data.
- Added storage sync tools:
sync_from_remote: Pull data from remote storage to localget_storage_status: Get storage configuration and statuslist_available_dates: List available dates in local/remote storage
- StorageManager adds push record proxy methods
- S3 client switches to virtual-hosted style for better compatibility (supports Tencent Cloud COS and more services)
🎉 Major Update: Comprehensive Refactoring of Storage and Core Architecture
- Multi-Storage Backend Support: Introduced a brand new storage module supporting local SQLite and remote cloud storage (S3-compatible protocols, e.g., Cloudflare R2), adaptable to GitHub Actions, Docker, and local environments.
- Database Structure Optimization: Refactored SQLite database table structures to improve data efficiency and query performance.
- Enhanced Features: Implemented date format standardization, data retention policies, timezone configuration support, and optimized time display. Fixed remote storage data persistence issues to ensure accurate data merging.
- Cleanup and Compatibility: Removed most legacy compatibility code and unified data storage and retrieval methods.
🎉 Core Feature Enhancements
-
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)
-
Configurable Push Content Order
- Added
reverse_content_orderconfiguration option - Customize display order of trending keywords stats and new trending news
- Added
-
Global Filter Keywords
- Added
[GLOBAL_FILTER]region marker for filtering unwanted content globally - Use cases: Filter ads, marketing, low-quality content, etc.
- Added
🐳 Docker Dual-Path HTML Generation Optimization
- Bug Fix: Resolved issue where
index.htmlcould 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 accessoutput/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 for details
🌐 Web Server Support
- Added built-in web server for browser access to generated reports
- Control via
manage.pycommands:docker exec -it trendradar 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 section: report-related parameter details
- Added Push Window Configuration section: push_window configuration tutorial
- Added Execution Frequency Configuration section: Cron expression explanation and common examples
- Added Multi-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 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.ymlor set environment variablesREVERSE_CONTENT_ORDER,MAX_ACCOUNTS_PER_CHANNEL - Multi-Account Push: New feature, disabled by default, existing single-account configuration unaffected
🔧 Format Optimization
-
Bark Push Enhancement
- Bark now supports Markdown rendering
- Enabled native Markdown format: bold, links, lists, code blocks, etc.
- Removed plain text conversion to fully utilize Bark's native rendering capabilities
-
Slack Format Precision
- Use dedicated mrkdwn format for batch content processing
- Improved byte size estimation accuracy (avoid message overflow)
- Optimized link format:
<url|text>and bold syntax:*text*
-
Performance Improvement
- Format conversion completed during batching process, avoiding secondary processing
- Accurate message size estimation reduces send failure rate
🔧 Upgrade Instructions:
- GitHub Fork Users: Update
main.py，config.yaml
MCP Module Update:
- Added date parsing tool resolve_date_range to resolve AI model date calculation inconsistencies
- Support natural language date expression parsing (this week, last 7 days, last month, etc.)
- Tool count increased from 13 to 14
🎉 Added Slack Push Support
-
Team Collaboration Push Channel
- Supports Slack Incoming Webhooks (globally popular team collaboration tool)
- Centralized message management, suitable for team-shared trending news
- Supports mrkdwn format (bold, links, etc.)
-
Multiple Deployment Methods
- GitHub Actions: Configure
SLACK_WEBHOOK_URLSecret - Docker: Environment variable
SLACK_WEBHOOK_URL - Local:
config/config.yamlconfiguration file
- GitHub Actions: Configure
📖 Detailed Configuration Tutorial: Quick Start - Slack Push
- Optimized the one-click installation experience for setup-windows.bat and setup-windows-en.bat
🔧 Upgrade Instructions:
- GitHub Fork Users: Update
main.py,config/config.yaml,.github/workflows/crawler.yml
🎉 Added Bark Push Support
-
iOS Exclusive Push Channel
- Supports Bark push (based on APNs, iOS platform)
- Free, open-source, clean, efficient, ad-free
- Supports both official server and self-hosted server
-
Multiple Deployment Methods
- GitHub Actions: Configure
BARK_URLSecret - Docker: Environment variable
BARK_URL - Local:
config/config.yamlconfiguration file
- GitHub Actions: Configure
📖 Detailed Configuration Tutorial: Quick Start - Bark Push
🐛 Bug Fix
- Fixed issue where
ntfy_server_urlinconfig.yamlwas ignored (#345)
🔧 Upgrade Instructions:
- GitHub Fork Users: Update
main.py,config/config.yaml,.github/workflows/crawler.yml
🎯 New Advanced Customization Features
-
Keyword Sorting Priority Configuration
- Two sorting strategies: Popularity first vs Config order first
- For different use cases: Hot topic tracking or personalized focus
-
Display Count Precise Control
- Global config: Unified limit for all keywords
- Individual config: Use
@numbersyntax to set specific limits - Effectively control push length, highlight key content
📖 Detailed Tutorial: Keyword Configuration - Advanced Settings
🔧 Upgrade Instructions:
- GitHub Fork Users: Update
main.py,config/config.yaml
- Fixed data anomaly crash issue: Resolved
'float' object has no attribute 'lower'error encountered by some users in GitHub Actions environment - Added dual protection mechanism: Filter invalid titles (None, float, empty strings) at data acquisition stage, with type checking at function call sites
- Enhanced system stability to ensure normal operation even when data sources return abnormal formats
Upgrade Instructions (GitHub Fork Users):
- Required update:
main.py - Recommended: Use minor version upgrade method - copy and replace the file above
MCP Module Update:
- Fix issue where today's news query may return articles from past dates
- Added Personal WeChat Push Support: WeWork application can push to personal WeChat without installing WeWork APP
- Supports two message formats:
markdown(WeWork group bot) andtext(personal WeChat app) - Added
WEWORK_MSG_TYPEenvironment variable configuration, supporting GitHub Actions, Docker, docker compose and other deployment methods textmode automatically strips Markdown syntax for clean plain text push- See "Personal WeChat Push" configuration in Quick Start
Upgrade Instructions (GitHub Fork Users):
- Required updates:
main.py,config/config.yaml - Optional update:
.github/workflows/crawler.yml(if using GitHub Actions) - Recommended: Use minor version upgrade method - copy and replace the files above
- Fixed email sending SSL/TLS port configuration logic error
- Optimized email service providers (QQ/163/126) to default use port 465 (SSL)
- Added Docker environment variable support: Core config items (
enable_crawler,report_mode,push_window, etc.) support override via environment variables, solving config file modification issues for NAS users (see 🐳 Docker Deployment chapter)
MCP Module Update:
- Fixed date query parameter passing error
- Unified time parameter format for all tools
- Solved Feishu error due to overly long push content, implemented batch pushing
- Expanded ntfy error message display range
- Fixed ntfy push encoding issue
Major Update - AI Analysis Feature Launched ✨
-
Core Features:
- New MCP (Model Context Protocol) based AI analysis server
- 13 smart analysis tools: basic query, smart search, advanced analysis, system management
- Natural language interaction: Query and analyze news data through conversation
- Multi-client support: Claude Desktop, Cherry Studio, Cursor, Cline, etc.
-
Analysis Capabilities:
- Topic trend analysis (popularity tracking, lifecycle, viral detection, trend prediction)
- Data insights (platform comparison, activity stats, keyword co-occurrence)
- Sentiment analysis, similar news finding, smart summary generation
- Historical related news search, multi-mode search
-
Update Note:
- This is an independent AI analysis feature, does not affect existing push functionality
- Optional use, no need to upgrade existing deployment
-
Updates:
- Fixed ntfy push encoding issue + 1
- Fixed push time window judgment issue
-
Upgrade Note:
- Recommended minor version upgrade
Thanks to nidaye996 for discovering the UX issue
-
Updates:
- Refactored "Silent Push Mode" naming to "Push Time Window Control", improving feature comprehension
- Clarified push time window as optional additional feature, can work with three push modes
- Improved comments and documentation, making feature positioning clearer
-
Upgrade Note:
- This is just refactoring, upgrade optional
-
Updates:
- Fixed ntfy push encoding issue
- Fixed missing config file issue
- Optimized ntfy push effect
- Added GitHub Pages image segmented export feature
-
Upgrade Note:
- Recommend major version update
Added ntfy Push Notification
-
Core Features:
- Supports ntfy.sh public service and self-hosted servers
-
Use Cases:
- Suitable for privacy-conscious users (supports self-hosting)
- Cross-platform push (iOS, Android, Desktop, Web)
- No account registration needed (public servers)
- Open-source and free (MIT License)
-
Upgrade Note:
- Recommend major version update
- Fixed email notification config check being missed (#88)
Fix Description:
- Solved the issue where system still prompted "No webhook configured" even with correct email notification setup
- Added email push feature, supports sending trending news reports to email
- Smart SMTP Recognition: Auto-detects Gmail, QQ Mail, Outlook, NetEase Mail and 10+ email service providers
- Beautiful HTML Format: Email content uses same HTML format as web version, well-formatted, mobile-adapted
- Batch Sending Support: Supports multiple recipients, separated by commas
- Custom SMTP: Can customize SMTP server and port
- Fixed Docker build network connection issue
Usage Notes:
- Use cases: Suitable for users needing email archiving, team sharing, scheduled reports
- Supported emails: Gmail, QQ Mail, Outlook/Hotmail, 163/126 Mail, Sina Mail, Sohu Mail, etc.
Upgrade Note:
- This update has many changes, if upgrading, recommend major version upgrade
- Added one-click save news as image feature, easily share trending topics you care about
Usage Notes:
- Use case: After enabling web version feature (GitHub Pages)
- How to use: Open webpage on phone or PC, click "Save as Image" button at top
- Actual effect: System auto-creates beautiful image of current news report, saves to phone album or desktop
- Sharing convenience: Directly send this image to friends, Moments, or work groups, letting others see your discovered important info
- Solved DingTalk push capacity limit causing news push failure (using batch push)
- Fixed Docker unable to run properly on certain architectures
- Officially released official Docker image wantcat/trendradar, supports multi-architecture
- Optimized Docker deployment process, can use quickly without local build
Core Improvements:
- Push Logic Optimization: Changed from "push every execution" to "controllable push within time window"
- Time Window Control: Can set push time range, avoid non-work hour disturbance
- Push Frequency Options: Supports single push or multiple pushes within time window
Upgrade Note:
- This feature is disabled by default, need to manually enable push time window control in config.yaml
- Upgrade requires updating both main.py and config.yaml files
- This version is not a bug fix, but an important reminder
- Please keep webhooks properly, do not make public, do not make public, do not make public
- If you deployed this project on GitHub via fork, please put webhooks in GitHub Secret, not config.yaml
- If you already exposed webhooks or put them in config.yaml, suggest deleting and regenerating
- Optimized GitHub Pages web version effect, convenient for mobile use
- Refactored code
- Solved version number easily being missed for modification
Fixed Issues:
- Docker shell script line ending as CRLF causing execution exception issue
- frequency_words.txt being empty causing news sending also empty logic issue
- After fix, when you choose frequency_words.txt empty, will push all news, but limited by message push size, please adjust as follows
- Option 1: Turn off mobile push, only choose GitHub Pages deployment (this is the way to get most complete info, will re-sort all platform trending by your custom trending algorithm)
- Option 2: Reduce push platforms, prioritize WeWork or Telegram, these two pushes I made batch push feature (because batch push affects push experience, and only these two platforms give very little push capacity, so had to make batch push feature, but at least can ensure complete info)
- Option 3: Can combine with Option 2, mode choose current or incremental can effectively reduce one-time push content
Major Refactoring:
- Config management refactoring: All configs now managed through
config/config.yamlfile (main.py I still didn't split, convenient for you to copy and upgrade) - Run mode upgrade: Supports three modes -
daily(daily summary),current(current rankings),incremental(incremental monitoring) - Docker support: Complete Docker deployment solution, supports containerized operation
Config File Description:
config/config.yaml- Main config file (application settings, crawler config, notification config, platform config, etc.)config/frequency_words.txt- Keyword config (monitoring vocabulary settings)
New Feature: Added incremental push (configure FOCUS_NEW_ONLY at top of main.py), this switch only cares about new topics not sustained heat, only sends notification when new content appears.
Fixed Issue: Under certain circumstances, some news containing special symbols caused occasional formatting exceptions.
WeWork and Telegram push messages have length limits, I adopted splitting messages for pushing. Development docs see WeWork and Telegram
Before this version, not only main.py needs copy replacement, crawler.yml also needs you to copy replacement https://github.com/sansan0/TrendRadar/blob/master/.github/workflows/crawler.yml
Thanks to Claude Research for organizing various platform APIs, helping me quickly complete platform adaptation (although code is more redundant~
- Supports Telegram, WeWork, DingTalk push channels, supports multi-channel config and simultaneous push
200 stars⭐ reached, continue celebrating with everyone~
- Important update, added weight, news you see now is hottest most concerned appearing at top
- Updated documentation usage, because recently updated many features, and previous usage docs I was lazy wrote simple (see ⚙️ frequency_words.txt complete configuration tutorial below)
- Added project new version update reminder, default on, if want to turn off, can change "FEISHU_SHOW_VERSION_UPDATE": True to False in main.py
- Removed compatibility code, students who forked before, directly copying code will show exception on same day (will recover normal next day)
- Feishu and html bottom added new news display
100 stars⭐ reached, writing small feature to celebrate
frequency_words.txt file added required word feature, using + sign
- Required word syntax as follows: Tang Monk or Pig must both appear in title, will be included in push news
+Tang Monk
+Pig
- Filter word priority higher: If title filter word matches Tang Monk reciting sutras, then even if required word has Tang Monk, also not display
+Tang Monk
!Tang Monk reciting sutras
- Webpage and Feishu messages support phone directly jumping to detailed news
- Optimized display effect + 1
- Feishu message display effect optimized
- Zhihu (知乎)
- Douyin (抖音)
- Bilibili Hot Search
- Wallstreetcn (华尔街见闻)
- Tieba (贴吧)
- Baidu Hot Search
- Yicai (财联社)
- Thepaper (澎湃新闻)
- Ifeng (凤凰网)
- Toutiao (今日头条)
- Weibo (微博)
Default monitoring of 11 mainstream platforms, with support for adding custom platforms.
💡 For detailed configuration, see Configuration Guide - Platform Configuration
Supports RSS/Atom feed crawling, keyword-based grouping and statistics (consistent with trending format):
- Unified Format: RSS and trending use the same keyword matching and display format
- Simple Config: Add RSS sources directly in
config.yaml - Merged Push: Trending and RSS are merged into a single notification
💡 RSS uses the same
frequency_words.txtfor keyword filtering as trending
Three Push Modes:
| Mode | Target Users | Push Feature |
|---|---|---|
| Daily Summary (daily) | Managers/Regular Users | Push all matched news of the day (includes previously pushed) |
| Current Rankings (current) | Content Creators | Push current ranking matches (continuously ranked news appear each time) |
| Incremental Monitor (incremental) | Traders/Investors | Push only new content, zero duplication |
💡 Quick Selection Guide:
- Don't want duplicate news → Use
incremental- Want complete ranking trends → Use
current- Need daily summary reports → Use
dailyFor detailed comparison and configuration, see Configuration Guide - Push Mode Details
Additional Features (Optional):
| 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 |
| Display Mode Switch | keyword=group by keyword, platform=group by platform (v4.6.0 new) |
keyword |
💡 For detailed configuration, see Configuration Guide - Report Configuration and Configuration Guide - Push Window
Set personal keywords (e.g., AI, BYD, Education Policy) to receive only relevant trending news, filtering out noise.
💡 Basic Configuration: Keyword Configuration - Basic Syntax
💡 Advanced Configuration: Keyword Configuration - Advanced Settings
💡 You can also skip filtering and receive all trending news (leave frequency_words.txt empty)
Real-time tracking of news popularity changes helps you understand not just "what's trending" but "how trends evolve."
- Timeline Tracking: Records complete time span from first to last appearance
- Popularity Changes: Tracks ranking changes and appearance frequency across time periods
- New Detection: Real-time identification of emerging topics, marked with 🆕
- Continuity Analysis: Distinguishes between one-time hot topics and continuously developing news
- Cross-Platform Comparison: Same news across different platforms, showing media attention differences
💡 Push format reference: Configuration Guide - Push Format Reference
No longer controlled by platform algorithms, TrendRadar reorganizes all trending searches
💡 Weight adjustment guide: Configuration Guide - Advanced Configuration
Supports WeWork (+ WeChat push solution), Feishu, DingTalk, Telegram, Email, ntfy, Bark, Slack — messages delivered directly to phone and email.
💡 For detailed configuration, see Configuration Guide - Multi-Account Push Configuration
Translate push content into any language, breaking language barriers — whether reading domestic trends or subscribing to international news via RSS, access everything in your native language
- One-Click Translation: Set
ai_translation.enabled: trueand target language inconfig.yaml - Multi-Language Support: Supports English, Korean, Japanese, French, and any other language
- Smart Batch Processing: Automatically batches translations to reduce API calls and save costs
- Custom Style: Customize translation style and terminology via
ai_translation_prompt.txt - Shared Model Config: Shares the
aiconfig section with AI analysis feature
# config.yaml quick enable example
ai_translation:
enabled: true
language: "English" # Target translation language💡 Translation shares model config with AI analysis — just configure
ai.api_keyonce to use both features
RSS Source References: Here are some RSS feed collections for your reference
- awesome-tech-rss - Tech, startup, and programming blogs & media
- awesome-rss-feeds - Mainstream news media RSS from countries worldwide
⚠️ Some international media content may involve sensitive topics that AI models might refuse to translate. Please filter subscription sources based on your actual needs
Multi-Backend Support:
- Remote Cloud Storage: GitHub Actions environment default, supports S3-compatible protocols (R2/OSS/COS, etc.), data stored in cloud, keeping repository clean
- Local SQLite: Traditional SQLite database, stable and efficient (Docker/local deployment)
- Auto Selection: Auto-selects appropriate backend based on runtime environment
💡 For storage configuration details, see Configuration Details - Storage Configuration
- GitHub Actions: Cloud automated operations (7-day check-in cycle + remote cloud storage)
- Docker Deployment: Supports multi-architecture containerized operation
- Local Running: Python environment direct execution
Use AI models to deeply analyze push content, automatically generate trending insights report
- Smart Analysis: Automatically analyze trending topics, keyword popularity, cross-platform correlation, potential impact
- Multi Provider: Supports DeepSeek, OpenAI, Gemini, and OpenAI-compatible APIs
- Flexible Push: Choose original content only, AI analysis only, or both
- Custom Prompts: Customize analysis perspective via
config/ai_analysis_prompt.txt
💡 Detailed configuration tutorial: Let AI help me analyze hot topics
Provide complete trending display for specified platforms, unaffected by keyword filtering
- Full Trending: Specified platforms show complete trending list, for users who want to see full rankings
- RSS Independent Display: RSS source content can be fully displayed, not limited by keywords
- Flexible Configuration: Support configuring display platforms, RSS sources, max count
💡 Detailed configuration tutorial: Report Configuration - Independent Display
AI conversational analysis system based on MCP (Model Context Protocol), enabling deep data mining with natural language.
💡 Usage Tip: AI features require local news data support
- Project includes test data for immediate feature experience
- Recommend deploying the project yourself to get more real-time data
See AI Analysis for details
After running, the index.html generated in the root directory is the complete news report page.
Deployment: Click Use this template to create your repository, then deploy to Cloudflare Pages or GitHub Pages.
💡 Tip: Enable GitHub Pages for an online URL. Go to Settings → Pages to enable. Preview Effect
⚠️ The GitHub Actions auto-storage feature has been discontinued (this approach caused excessive load on GitHub servers, affecting platform stability).
Transform from "algorithm recommendation captivity" to "actively getting the information you want"
Target Users: Investors, content creators, PR professionals, news-conscious general users
Typical Scenarios: Stock investment monitoring, brand sentiment tracking, industry trend watching, lifestyle news gathering
| Web Effect (Email Push) | Feishu Push Effect | AI Analysis Push Effect |
|---|---|---|
 |
 |
 |
Reminder: You should first check the latest official documentation to ensure the configuration steps are up to date.
- Features: More stable than GitHub Actions
- Best for: Users with their own server, NAS, or an always-on PC
👉 Jump to Docker Deployment Tutorial
- Features: Data is stored in Remote Cloud Storage (no longer written to Git repo)
- Storage: Configure cloud storage service (e.g. Cloudflare R2, Alibaba Cloud OSS, Tencent Cloud COS, etc.)
- Note: Requires periodic check-in renewal (every 7 days)
Click the green [Use this template] button in the upper right corner of this repository → select "Create a new repository".
⚠️ Note:
- Any mention of "Fork" in this document can be understood as "Use this template"
- Using Fork may cause runtime issues, see Issue #606
In your Forked repository, go to Settings > Secrets and variables > Actions > New repository secret
📌 Important Instructions (Please Read Carefully):
- One Name for One Secret: For each configuration item, click the "New repository secret" button once and fill in a pair of "Name" and "Secret"
- Cannot See Value After Saving is Normal: For security reasons, after saving, you can only see the Name when re-editing, but not the Secret value
- 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
Configuration Example:
As shown above, each row is a configuration item:
- Name: Must use the fixed names listed in the expanded sections below (e.g.,
WEWORK_WEBHOOK_URL) - Secret (Value): Fill in the actual content obtained from the corresponding platform (e.g., Webhook URL, Token, etc.)
👉 Click to expand: WeWork Bot (Simplest and fastest configuration)
GitHub Secret Configuration (
- Name:
WEWORK_WEBHOOK_URL(Please copy and paste this name, do not type manually to avoid typos) - Secret (Value): Your WeWork bot Webhook address
Bot Setup Steps:
- Open WeWork App → Enter target internal group chat
- Click "…" button at top right → Select "Message Push"
- Click "Add" → Name input "TrendRadar"
- Copy Webhook address, click save, paste the copied content into GitHub Secret above
👉 Click to expand: Personal WeChat Push (Based on WeWork app, push to personal WeChat)
This solution is based on WeWork's plugin mechanism. The push style is plain text (no markdown format), but it can push directly to personal WeChat without installing WeWork App.
GitHub Secret Configuration (
-
Name:
WEWORK_WEBHOOK_URL(Please copy and paste this name, do not type manually) -
Secret (Value): Your WeWork app Webhook address
-
Name:
WEWORK_MSG_TYPE(Please copy and paste this name, do not type manually) -
Secret (Value):
text
Setup Steps:
- Complete the WeWork bot Webhook setup above
- Add
WEWORK_MSG_TYPESecret with valuetext - Follow the image below to link personal WeChat
- After configuration, WeWork App can be deleted from phone
Notes:
- Uses the same Webhook address as WeWork bot
- Difference is message format:
textfor plain text,markdownfor rich text (default) - Plain text format will automatically remove all markdown syntax (bold, links, etc.)
👉 Click to expand: Feishu Bot (Message display is relatively friendly)
Note: If AI Analysis is enabled, Feishu push notifications may occasionally (approx. 5% probability) experience a few minutes of delay. This is likely due to the platform's internal compliance auditing for AI-generated content.
GitHub Secret Configuration (
- Name:
FEISHU_WEBHOOK_URL(Please copy and paste this name, do not type manually) - Secret (Value): Your Feishu bot Webhook address (link starts with https://www.feishu.cn/flow/api/trigger-webhook/********)
Two methods available, Method 1 is simpler, Method 2 is more complex (but stable push)
Method 1 discovered and suggested by ziventian, thanks to them. Default is personal push, group push can be configured via #97
Method 1:
For some users, additional operations needed to avoid "System Error". Need to search for the bot on mobile and enable Feishu bot application (suggestion from community, can refer)
-
Open in PC browser https://botbuilder.feishu.cn/home/my-command
-
Click "New Bot Command"
-
Click "Select Trigger", scroll down, click "Webhook Trigger"
-
Now you'll see "Webhook Address", copy this link to local notepad temporarily, continue with next steps
-
In "Parameters" put the following content, then click "Done"
{
"message_type": "text",
"content": {
"text": "{{Content}}"
}
}-
Click "Select Action" > "Send via Official Bot"
-
Message title fill "TrendRadar Trending Monitor"
-
Most critical part, click + button, select "Webhook Trigger", then arrange as shown in image
- After configuration, put Webhook address from step 4 into GitHub Secrets
FEISHU_WEBHOOK_URL
Method 2:
-
Open in PC browser https://botbuilder.feishu.cn/home/my-app
-
Click "New Bot Application"
-
After entering the created application, click "Process Design" > "Create Process" > "Select Trigger"
-
Scroll down, click "Webhook Trigger"
-
Now you'll see "Webhook Address", copy this link to local notepad temporarily, continue with next steps
-
In "Parameters" put the following content, then click "Done"
{
"message_type": "text",
"content": {
"text": "{{Content}}"
}
}-
Click "Select Action" > "Send Feishu Message", check "Group Message", then click the input box below, click "Groups I Manage" (if no group, you can create one in Feishu app)
-
Message title fill "TrendRadar Trending Monitor"
-
Most critical part, click + button, select "Webhook Trigger", then arrange as shown in image
- After configuration, put Webhook address from step 5 into GitHub Secrets
FEISHU_WEBHOOK_URL
👉 Click to expand: DingTalk Bot
GitHub Secret Configuration (
- Name:
DINGTALK_WEBHOOK_URL(Please copy and paste this name, do not type manually) - Secret (Value): Your DingTalk bot Webhook address
Bot Setup Steps:
-
Create Bot (PC Only):
- Open DingTalk PC client, enter target group chat
- Click group settings icon (⚙️) → Scroll down to find "Bot" and click
- Select "Add Bot" → "Custom"
-
Configure Bot:
- Set bot name
- Security Settings:
- Custom Keywords: Set "Trending" or "热点"
-
Complete Setup:
- Check service terms agreement → Click "Done"
- Copy the obtained Webhook URL
- Put URL into GitHub Secrets
DINGTALK_WEBHOOK_URL
Note: Mobile can only receive messages, cannot create new bots.
👉 Click to expand: Telegram Bot
GitHub Secret Configuration (
-
Name:
TELEGRAM_BOT_TOKEN(Please copy and paste this name, do not type manually) -
Secret (Value): Your Telegram Bot Token
-
Name:
TELEGRAM_CHAT_ID(Please copy and paste this name, do not type manually) -
Secret (Value): Your Telegram Chat ID
Note: Telegram requires two Secrets, please click "New repository secret" button twice to add them separately
Bot Setup Steps:
-
Create Bot:
- Search
@BotFatherin Telegram (note case, has blue verification checkmark, shows ~37849827 monthly users, this is official, beware of fake accounts) - Send
/newbotcommand to create new bot - Set bot name (must end with "bot", easily runs into duplicate names, so think creatively)
- Get Bot Token (format like:
123456789:AAHfiqksKZ8WmR2zSjiQ7_v4TMAKdiHm9T0)
- Search
-
Get Chat ID:
Method 1: Via Official API
- First send a message to your bot
- Visit:
https://api.telegram.org/bot<Your Bot Token>/getUpdates - Find the number in
"chat":{"id":number}in returned JSON
Method 2: Using Third-Party Tool
- Search
@userinfobotand send/start - Get your user ID as Chat ID
-
Configure to GitHub:
TELEGRAM_BOT_TOKEN: Fill in Bot Token from step 1TELEGRAM_CHAT_ID: Fill in Chat ID from step 2
👉 Click to expand: Email Push (Supports all mainstream email providers)
- Note: To prevent email bulk sending abuse, current bulk sending allows all recipients to see each other's email addresses.
- If you haven't configured email sending before, not recommended to try
⚠️ Important Configuration Dependency: Email push requires HTML report file. Make surestorage.formats.htmlis set totrueinconfig/config.yaml:storage: formats: sqlite: true txt: false html: true # Must be enabled, otherwise email push will failIf set to
false, email push will report error:Error: HTML file does not exist or not provided: None
GitHub Secret Configuration (
-
Name:
EMAIL_FROM(Please copy and paste this name, do not type manually) -
Secret (Value): Sender email address
-
Name:
EMAIL_PASSWORD(Please copy and paste this name, do not type manually) -
Secret (Value): Email password or authorization code
-
Name:
EMAIL_TO(Please copy and paste this name, do not type manually) -
Secret (Value): Recipient email address (multiple separated by comma, or can be same as EMAIL_FROM to send to yourself)
-
Name:
EMAIL_SMTP_SERVER(Optional, please copy and paste this name) -
Secret (Value): SMTP server address (leave empty for auto-detection)
-
Name:
EMAIL_SMTP_PORT(Optional, please copy and paste this name) -
Secret (Value): SMTP port (leave empty for auto-detection)
Note: Email push requires at least 3 required Secrets (EMAIL_FROM, EMAIL_PASSWORD, EMAIL_TO), the last two are optional
Supported Email Providers (Auto-detect SMTP config):
| Provider | Domain | SMTP Server | Port | Encryption |
|---|---|---|---|---|
| Gmail | gmail.com | smtp.gmail.com | 587 | TLS |
| QQ Mail | qq.com | smtp.qq.com | 465 | SSL |
| Outlook | outlook.com | smtp-mail.outlook.com | 587 | TLS |
| Hotmail | hotmail.com | smtp-mail.outlook.com | 587 | TLS |
| Live | live.com | smtp-mail.outlook.com | 587 | TLS |
| 163 Mail | 163.com | smtp.163.com | 465 | SSL |
| 126 Mail | 126.com | smtp.126.com | 465 | SSL |
| Sina Mail | sina.com | smtp.sina.com | 465 | SSL |
| Sohu Mail | sohu.com | smtp.sohu.com | 465 | SSL |
| 189 Mail | 189.cn | smtp.189.cn | 465 | SSL |
| Aliyun Mail | aliyun.com | smtp.aliyun.com | 465 | TLS |
| Yandex Mail | yandex.com | smtp.yandex.com | 465 | TLS |
| iCloud Mail | icloud.com | smtp.mail.me.com | 587 | SSL |
Auto-detect: When using above emails, no need to manually configure
EMAIL_SMTP_SERVERandEMAIL_SMTP_PORT, system auto-detects.Feedback Notice:
- If you successfully test with other email providers, please open an Issue to let us know, we'll add to support list
- If above email configurations are incorrect or unusable, please also open an Issue for feedback to help improve the project
Special Thanks:
- Thanks to @DYZYD for contributing 189 Mail (189.cn) configuration and completing self-send-receive testing (#291)
- Thanks to @longzhenren for contributing Aliyun Mail (aliyun.com) configuration and completing testing (#344)
- Thanks to @ACANX for contributing Yandex Mail (yandex.com) configuration and completing testing (#663)
- Thanks to @Sleepy-Tianhao for contributing iCloud Mail (icloud.com) configuration and completing testing (#728)
Common Email Settings:
- Login QQ Mail web version → Settings → Account
- Enable POP3/SMTP service
- Generate authorization code (16-letter code)
EMAIL_PASSWORDfill authorization code, not QQ password
- Enable two-step verification
- Generate app-specific password
EMAIL_PASSWORDfill app-specific password
- Login web version → Settings → POP3/SMTP/IMAP
- Enable SMTP service
- Set client authorization code
EMAIL_PASSWORDfill authorization code
Advanced Configuration: If auto-detect fails, manually configure SMTP:
EMAIL_SMTP_SERVER: Like smtp.gmail.comEMAIL_SMTP_PORT: Like 587 (TLS) or 465 (SSL)
Multiple Recipients (note: English comma separator):
- EMAIL_TO="user1@example.com,user2@example.com,user3@example.com"
👉 Click to expand: ntfy Push (Open-source, free, self-hostable)
Two Usage Methods:
Features:
- ✅ No account registration, use immediately
- ✅ 250 messages/day (enough for 90% users)
- ✅ Topic name is "password" (need to choose hard-to-guess name)
⚠️ Messages unencrypted, not for sensitive info, but suitable for our non-sensitive project info
Quick Start:
-
Download ntfy App:
- Android: Google Play / F-Droid
- iOS: App Store
- Desktop: Visit ntfy.sh
-
Subscribe to Topic (choose a hard-to-guess name):
Suggested format: trendradar-{your initials}-{random numbers} Cannot use Chinese ✅ Good example: trendradar-zs-8492 ❌ Bad example: news, alerts (too easy to guess) -
Configure GitHub Secret (
⚠️ Name must match exactly):-
Name:
NTFY_TOPIC(Please copy and paste this name, do not type manually) -
Secret (Value): Fill in your subscribed topic name
-
Name:
NTFY_SERVER_URL(Optional, please copy and paste this name) -
Secret (Value): Leave empty (default uses ntfy.sh)
-
Name:
NTFY_TOKEN(Optional, please copy and paste this name) -
Secret (Value): Leave empty
Note: ntfy requires at least 1 required Secret (NTFY_TOPIC), the last two are optional
-
-
Test:
curl -d "Test message" ntfy.sh/your-topic-name
Target Users: Have server, pursue complete privacy, strong technical ability
Advantages:
- ✅ Completely open-source (Apache 2.0 + GPLv2)
- ✅ Complete data self-control
- ✅ No restrictions
- ✅ Zero cost
Docker One-Click Deploy:
docker run -d \
--name ntfy \
-p 80:80 \
-v /var/cache/ntfy:/var/cache/ntfy \
binwiederhier/ntfy \
serve --cache-file /var/cache/ntfy/cache.dbConfigure TrendRadar:
NTFY_SERVER_URL: https://ntfy.yourdomain.com
NTFY_TOPIC: trendradar-alerts # Self-hosting can use simple name
NTFY_TOKEN: tk_your_token # Optional: Enable access controlSubscribe in App:
- Click "Use another server"
- Enter your server address
- Enter topic name
- (Optional) Enter login credentials
FAQ:
Q1: Is the free version enough?
250 messages/day is enough for most users. With 30-minute crawl intervals, about 48 pushes/day, completely sufficient.
Q2: Is the Topic name really secure?
If you choose a random, sufficiently long name (like trendradar-zs-8492-news), brute force is nearly impossible:
- ntfy has strict rate limiting (1 request/second)
- 64 character choices (A-Z, a-z, 0-9, _, -)
- 10 random characters have 64^10 possibilities (would take years to crack)
Recommended Choice:
| User Type | Recommended | Reason |
|---|---|---|
| Regular Users | Method 1 (Free) | Simple, fast, enough |
| Technical Users | Method 2 (Self-Host) | Complete control, unlimited |
| High-Frequency Users | Method 3 (Paid) | Check official website |
Related Links:
👉 Click to expand: Bark Push (iOS exclusive, clean & efficient)
GitHub Secret Configuration (
- Name:
BARK_URL(copy and paste this name, don't type manually) - Secret: Your Bark push URL
Bark Introduction:
Bark is a free open-source push tool for iOS platform, featuring simplicity, speed, and no ads.
Usage Methods:
-
Download Bark App:
- iOS: App Store
-
Get Push URL:
- Open Bark App
- Copy the push URL displayed on the home page (format:
https://api.day.app/your_device_key) - Configure the URL to GitHub Secrets as
BARK_URL
Suitable for: Users with servers, pursuing complete privacy, strong technical skills
Docker One-Click Deployment:
docker run -d \
--name bark-server \
-p 8080:8080 \
finab/bark-serverConfigure TrendRadar:
BARK_URL: http://your-server-ip:8080/your_device_keyNotes:
- ✅ Bark uses APNs push, max 4KB per message
- ✅ Supports automatic batch sending, no worry about long messages
- ✅ Push format is plain text (automatically removes Markdown syntax)
⚠️ Only supports iOS platform
Related Links:
👉 Click to expand: Slack Push
GitHub Secret Configuration (
- Name:
SLACK_WEBHOOK_URL(copy and paste this name, don't type manually) - Secret: Your Slack Incoming Webhook URL
Slack Introduction:
Slack is a team collaboration tool, Incoming Webhooks can push messages to Slack channels.
Setup Steps:
-
Visit Slack API Page:
- Open https://api.slack.com/apps?new_app=1
- Login to your Slack workspace if not logged in
-
Choose Creation Method:
- Click "From scratch"
-
Fill in App Information:
- App Name: Enter app name (e.g.,
TrendRadarorHot News Monitor) - Workspace: Select your workspace from dropdown
- Click "Create App" button
- App Name: Enter app name (e.g.,
-
Navigate to Incoming Webhooks:
- Find and click "Incoming Webhooks" in left menu
-
Enable Feature:
- Find "Activate Incoming Webhooks" toggle
- Switch from
OFFtoON - Page will auto-refresh showing new configuration options
-
Add New Webhook:
- Scroll to page bottom
- Click "Add New Webhook to Workspace" button
-
Select Target Channel:
- System will show authorization page
- Select channel to receive messages from dropdown (e.g.,
#hot-news) ⚠️ For private channels, must join the channel first
-
Authorize App:
- Click "Allow" button to complete authorization
- System will auto-redirect back to config page
-
View Generated URL:
- In "Webhook URLs for Your Workspace" section
- You'll see the newly generated Webhook URL
- Format:
https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX
-
Copy URL:
- Click "Copy" button on the right of URL
- Or manually select and copy URL
-
Configure to TrendRadar:
- GitHub Actions: Add URL to GitHub Secrets as
SLACK_WEBHOOK_URL - Local Testing: Fill URL in
config/config.yamlslack_webhook_urlfield - Docker Deployment: Add URL to
docker/.envfile asSLACK_WEBHOOK_URLvariable
- GitHub Actions: Add URL to GitHub Secrets as
Notes:
- ✅ Supports Markdown format (auto-converts to Slack mrkdwn)
- ✅ Supports automatic batch sending (4KB per batch)
- ✅ Suitable for team collaboration, centralized message management
⚠️ Webhook URL contains secret key, never make it public
Message Format Preview:
*[Batch 1/2]*
📊 *Trending Topics Statistics*
🔥 *[1/3] AI ChatGPT* : 2 articles
1. [Baidu Hot] 🆕 ChatGPT-5 Official Release *[1]* - 09:15 (1 time)
2. [Toutiao] AI Chip Stocks Surge *[3]* - [08:30 ~ 10:45] (3 times)
Related Links:
👉 Click to expand: Generic Webhook Push (Supports Discord, Matrix, IFTTT, etc.)
GitHub Secret Configuration (
-
Name:
GENERIC_WEBHOOK_URL(copy and paste this name, don't type manually) -
Secret: Your Webhook URL
-
Name:
GENERIC_WEBHOOK_TEMPLATE(optional, copy and paste this name) -
Secret: JSON template string, supports
{title}and{content}placeholders
Generic Webhook Introduction:
Generic Webhook supports any platform that accepts HTTP POST requests, including but not limited to:
- Discord: Push to channels via Webhook
- Matrix: Push via Webhook bridge
- IFTTT: Trigger automation workflows
- Custom Services: Any custom service supporting Webhooks
Configuration Examples:
-
Get Webhook URL:
- Go to Discord Server Settings → Integrations → Webhooks
- Create new Webhook, copy URL
-
Configure Template:
{"content": "{content}"} -
GitHub Secret Configuration:
GENERIC_WEBHOOK_URL: Discord Webhook URLGENERIC_WEBHOOK_TEMPLATE:{"content": "{content}"}
Templates support two placeholders:
{title}- Message title{content}- Message content
Template Examples:
# Default format (used when empty)
{"title": "{title}", "content": "{content}"}
# Discord format
{"content": "{content}"}
# Custom format
{"text": "{content}", "username": "TrendRadar"}Notes:
- ✅ Supports Markdown format (same as WeWork format)
- ✅ Supports automatic batch sending
- ✅ Supports multi-account configuration (use
;separator) ⚠️ Template must be valid JSON format⚠️ Different platforms have different message format requirements, please refer to target platform documentation
⚠️ Note:
- For first deployment, suggest completing GitHub Secrets configuration first (choose one push platform), then jump to [Step 3] to test push success.
- Don't modify
config/config.yamlandfrequency_words.txttemporarily, adjust these configs after push test succeeds as needed.
⚠️ Reminder:
- Complete Step 1-2 first, then test immediately! Test success first, then adjust configuration (Step 4) as needed.
- IMPORTANT: Enter your own forked project, not this project!
How to find your Actions page:
- Method 1: Open your forked project homepage, click the Actions tab at the top
- Method 2: Direct access
https://github.com/YourUsername/TrendRadar/actions
Example comparison:
- ❌ Author's project:
https://github.com/sansan0/TrendRadar/actions - ✅ Your project:
https://github.com/YourUsername/TrendRadar/actions
Testing steps:
- Enter your project's Actions page
- Find "Hot News Crawler" and click in
- If you don't see this text, refer to #109 to solve
- Click "Run workflow" button on the right to run
- Wait about 1 minute, messages will be pushed to your configured platform
⚠️ Note:
- 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
The default configuration is ready to use. If you need personalized adjustments, just understand the following files:
| 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 ( |
👉 Detailed Configuration Tutorial: Configuration Guide
v4.0.0 Important Change: Introduced the "Activity Detection" mechanism; GitHub Actions need periodic check-ins to maintain operation.
- Running Cycle: Valid for 7 days—service will automatically suspend when countdown ends.
- Renewal Method: Manually trigger the "Check In" workflow on the Actions page to reset the 7-day validity period.
- Operation Path:
Actions→Check In→Run workflow - Design Philosophy:
- If you forget for 7 days, maybe you don't really need it. Letting it stop is a digital detox, freeing you from the constant impact.
- GitHub Actions is a valuable public computing resource. The check-in mechanism aims to prevent wasted computing cycles, ensuring resources are allocated to truly active users who need them. Thank you for your understanding and support.
You can also choose NOT to configure remote cloud storage, but then you will be in Lite Mode with some advanced features unavailable.
Two Deployment Modes Comparison:
| Mode | Configuration Required | Features |
|---|---|---|
| Lite Mode | No storage configuration needed | Real-time crawling + Keyword filtering + Multi-channel push |
| Full Mode | Configure remote cloud storage | Lite Mode + New detection + Trend tracking + Incremental push + AI analysis |
Lite Mode Description:
- ✅ Available: Real-time news crawling, keyword filtering, hotspot weight ranking, current list push
- ❌ Not Available: New news detection (🆕), trend tracking, incremental mode, daily summary accumulation, MCP AI analysis
Full Mode Description: Configure remote cloud storage to unlock all features. Continue with the configuration below.
👉 Click to expand: Remote Cloud Storage Configuration (Determines Feature Completeness) (Optional)
According to Cloudflare platform rules, enabling R2 requires binding a payment method.
- Purpose: Verify identity only, no charges will be incurred.
- Payment: Supports dual-currency credit cards or regional PayPal.
- Usage: R2's free tier (10GB storage/month) is sufficient for this project's daily operation, no need to worry about costs.
GitHub Secret Configuration:
Required Configuration (4 items):
| Name | Secret (Value) Description |
|---|---|
S3_BUCKET_NAME |
Bucket name (e.g., trendradar-data) |
S3_ACCESS_KEY_ID |
Access key ID |
S3_SECRET_ACCESS_KEY |
Access key |
S3_ENDPOINT_URL |
S3 API endpoint (e.g., R2: https://<account-id>.r2.cloudflarestorage.com) |
Optional Configuration:
| Name | Secret (Value) Description |
|---|---|
S3_REGION |
Region (default auto, some providers may require specification) |
💡 More storage configuration options: See Storage Configuration Details
How to Get Credentials (Using Cloudflare R2 as Example):
- Visit Cloudflare Dashboard and log in
- Select
R2in left menu → ClickCreate Bucket→ Enter name (e.g.,trendradar-data) - Click
Manage R2 API Tokensat top right →Create API Token - Select
Object Read & Writepermission → After creation, it will displayAccess Key IDandSecret Access Key - Endpoint URL can be found in bucket details page (format:
https://<account-id>.r2.cloudflarestorage.com)
This is a core feature of v5.0.0, letting AI summarize and analyze news for you. Highly recommended.
Configuration Method:
Add the following to GitHub Secrets (or .env / config.yaml):
AI_API_KEY: Your API Key (Supports DeepSeek, OpenAI, etc.)AI_PROVIDER: Provider name (e.g.,deepseek,openai)
That's it! No complex deployment needed. You'll see the smart analysis report in the next push.
Congratulations! Now you can start enjoying the efficient information flow brought by TrendRadar.
💬 Many users are sharing their experiences on the official account, we look forward to your insights~
- Want to learn more tips and advanced techniques?
- Need quick answers to problems?
- Have great ideas to share?
👉 Follow the WeChat Official Account「Silicon Tea Room」, your likes and comments are the motivation for continuous updates.
TrendRadar provides two ways to use AI to meet different needs:
| Feature | ✨ AI Analysis Push (Step 6) | 🧠 AI Smart Analysis |
|---|---|---|
| Mode | Passive Receipt (Daily Report) | Active Conversation (Deep Research) |
| Scenario | "What's big today?" | "Analyze AI industry changes over the past week" |
| Deployment | Minimalist (Just add Key) | Advanced (Requires Local/Docker) |
| Client | Mobile | PC |
👉 Conclusion: Start with AI Analysis Push for daily needs; if you are a data analyst or need deep mining, try MCP Smart Analysis.
📖 Reminder: This chapter provides detailed configuration explanations. Suggest completing Quick Start basic configuration first, then refer to detailed options here as needed.
👉 Click to expand: Custom Monitoring Platforms
Configuration Location: platforms section in config/config.yaml
This project's news data comes from newsnow. You can click the website, click [More], to see if there are platforms you want.
For specific additions, visit project source code, based on the file names there, modify the platforms configuration in config/config.yaml file:
platforms:
enabled: true # Enable trending platform crawling
sources:
- id: "toutiao"
name: "Toutiao"
- id: "baidu"
name: "Baidu Hot Search"
- id: "wallstreetcn-hot"
name: "Wallstreetcn"
# Add more platforms...💡 Shortcut: If you don't know how to read source code, you can copy from others' organized Platform Configuration Summary
⚠️ 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.
Configuration Location: config/frequency_words.txt
Configure monitoring keywords in frequency_words.txt with seven syntax types, region markers, and grouping features.
| Syntax Type | Symbol | Purpose | Example | Matching Logic |
|---|---|---|---|---|
| Normal | None | Basic matching | Huawei |
Match any one |
| 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) |
| Regex | /pattern/ |
Precise matching | /\bai\b/ |
Match using regex (v4.7.0 new) |
| Display Name | => alias |
Custom display text | /\bai\b/ => AI Related |
Show alias in push/HTML (v4.7.0 new) |
👉 Click to expand: Basic Syntax Tutorial
Huawei
OPPO
AppleEffect: News containing any one of these words will be captured
Huawei
OPPO
+phoneEffect: Must include both normal word and required word to be captured
Apple
Huawei
!fruit
!priceEffect: News containing filter words will be excluded, even if it contains keywords
Tesla
Musk
@5Effect: Limit maximum news count for this keyword group
Priority: @number > Global config > Unlimited
[GLOBAL_FILTER]
advertisement
promotion
marketing
shocking
clickbait
[WORD_GROUPS]
technology
AI
Huawei
HarmonyOS
!carEffect: 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:
[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)
Normal keywords use substring matching, which is convenient for Chinese but may cause false matches in English. For example, ai would match the ai in training.
Use regex syntax /pattern/ to achieve precise matching:
/(?<![a-z])ai(?![a-z])/
artificial intelligenceEffect: Match using regular expressions, supports all Python regex syntax
Common Regex Patterns:
| Need | Regex | Description |
|---|---|---|
| Word boundary | /\bword\b/ |
Match standalone word, e.g., /\bai\b/ matches "AI" but not "training" |
| Non-letter boundary | /(?<![a-z])ai(?![a-z])/ |
Looser boundary, suitable for mixed Chinese-English |
| Start match | /^breaking/ |
Only match titles starting with "breaking" |
| End match | /release$/ |
Only match titles ending with "release" |
| Multiple options | /apple|huawei|xiaomi/ |
Match any one (note escaped |) |
Matching Examples:
# Config
/(?<![a-z])ai(?![a-z])/
artificial intelligence- ✅ "AI is the future" ← Matches standalone "AI"
- ✅ "Hello ai here" ← Non-letter boundaries, matches "ai"
- ✅ "Artificial intelligence grows rapidly" ← Matches "artificial intelligence"
- ❌ "Resistance training is important" ← "ai" in "training" doesn't match
- ❌ "The maid cleaned the room" ← "ai" in "maid" doesn't match
Combined Usage:
# Regex + Normal + Filter
/\bai\b/
artificial intelligence
machine learning
!advertisementNotes:
- Regex automatically enables case-insensitive matching (
re.IGNORECASE) - Supports JavaScript-style
/pattern/isyntax (flags are ignored since case-insensitive is always enabled) - Invalid regex syntax will be treated as normal words
- Regex can be used for normal words, required words(
+), and filter words(!)
💡 Can't Write Regex? Let AI Help!
If you're not familiar with regular expressions, just ask ChatGPT / Gemini / DeepSeek to generate one:
I need a Python regex to match the word "ai" but not match "ai" in "training". Please give me the regex in
/pattern/format without extra explanation.
AI will give you something like: /(?<![a-zA-Z])ai(?![a-zA-Z])/
Regex patterns can look unfriendly in push notifications and HTML pages. Use => alias syntax to set a display name:
/(?<![a-zA-Z])ai(?![a-zA-Z])/ => AI Related
artificial intelligenceEffect: Push notifications and HTML pages show "AI Related" instead of the complex regex
Syntax Format:
# Regex + Display Name
/pattern/ => Display Name
/pattern/i => Display Name # Supports flags syntax (flags are ignored)
/pattern/=>Display Name # Spaces around => are optional
# Normal Word + Display Name
deepseek => DeepSeek NewsExample:
# Config
/(?<![a-zA-Z])ai(?![a-zA-Z])/ => AI Related
artificial intelligence| Original Config | Push/HTML Display |
|---|---|
/(?<![a-z])ai(?![a-z])/ + artificial intelligence |
(?<![a-z])ai(?![a-z]) artificial intelligence |
/(?<![a-z])ai(?![a-z])/ => AI Related + artificial intelligence |
AI Related |
Notes:
- Display name only needs to be set on the first word of a group
- If multiple words have display names, the first one is used
- Without display name, all words in the group are concatenated
Core Rule: Use empty lines to separate different groups, each group is independently counted
iPhone
Huawei
OPPO
+launch
A-shares
Shanghai Index
Shenzhen Index
+fluctuation
!prediction
World Cup
Euro Cup
Asian Cup
+matchGroup 1 - Phone Launches:
- Keywords: iPhone, Huawei, OPPO
- Required: launch
- Effect: Must include phone brand name and "launch"
Matching Examples:
- ✅ "iPhone 15 officially launched with pricing" ← Has "iPhone" + "launch"
- ✅ "Huawei Mate60 series launch livestream" ← Has "Huawei" + "launch"
- ✅ "OPPO Find X7 launch date confirmed" ← Has "OPPO" + "launch"
- ❌ "iPhone sales hit record high" ← Has "iPhone" but missing "launch"
Group 2 - Stock Market:
- Keywords: A-shares, Shanghai Index, Shenzhen Index
- Required: fluctuation
- Filter: prediction
- Effect: Include stock-related words and "fluctuation", but exclude "prediction"
Matching Examples:
- ✅ "A-shares major fluctuation analysis today" ← Has "A-shares" + "fluctuation"
- ✅ "Shanghai Index fluctuation reasons explained" ← Has "Shanghai Index" + "fluctuation"
- ❌ "Experts predict A-shares fluctuation trends" ← Has "A-shares" + "fluctuation" but contains "prediction"
- ❌ "A-shares trading volume hits new high" ← Has "A-shares" but missing "fluctuation"
Group 3 - Football Events:
- Keywords: World Cup, Euro Cup, Asian Cup
- Required: match
- Effect: Must include cup name and "match"
Matching Examples:
- ✅ "World Cup group stage match results" ← Has "World Cup" + "match"
- ✅ "Euro Cup final match time" ← Has "Euro Cup" + "match"
- ❌ "World Cup tickets on sale" ← Has "World Cup" but missing "match"
# Step 1: Start with broad keywords for testing
Artificial Intelligence
AI
ChatGPT
# Step 2: After finding mismatches, add required words
Artificial Intelligence
AI
ChatGPT
+technology
# Step 3: After finding noise, add filter words
Artificial Intelligence
AI
ChatGPT
+technology
!advertisement
!training❌ Not Recommended: Too many words in one group
Huawei
OPPO
Apple
Samsung
vivo
OnePlus
Meizu
+phone
+launch
+sales
!fake
!repair
!second-handRecommended: Split into precise groups
Huawei
OPPO
+new product
Apple
Samsung
+launch
phone
sales
+market👉 Click to expand: Advanced Settings Tutorial
Config Location: config/config.yaml
report:
sort_by_position_first: false # Sorting priority config| Value | Sorting Rule | Use Case |
|---|---|---|
false (default) |
News count ↓ → Config position ↑ | Focus on popularity trends |
true |
Config position ↑ → News count ↓ | Focus on personal priority |
Example: Config order A, B, C, news count A(3), B(10), C(5)
false: B(10) → C(5) → A(3)true: A(3) → B(10) → C(5)
report:
max_news_per_keyword: 10 # Max 10 per keyword (0=unlimited)Docker Environment Variables:
SORT_BY_POSITION_FIRST=true
MAX_NEWS_PER_KEYWORD=10Combined Example:
# config.yaml
report:
sort_by_position_first: true # Config order priority
max_news_per_keyword: 10 # Global default max 10 per keyword# frequency_words.txt
Tesla
Musk
@20 # Key focus, show 20 (override global)
Huawei # Use global config, show 10
BYD
@5 # Limit to 5Final Effect: Display in config order: Tesla(20) → Huawei(10) → BYD(5)
👉 Click to expand: Detailed Comparison of 3 Modes
Configuration Location: report.mode in config/config.yaml
report:
mode: "daily" # Options: "daily" | "incremental" | "current"| Mode | Target Users | Push Timing | Display Content | Typical Use Case |
|---|---|---|---|---|
Daily Summarydaily |
📋 Managers/Regular Users | Scheduled push (default hourly) | All matched news of the day + New news section |
Example: Check all important news of the day at 6 PM Feature: See full-day trend, don't miss any hot topic Note: Will include previously pushed news |
Current Rankingscurrent |
📰 Content Creators | Scheduled push (default hourly) | Current ranking matches + New news section |
Example: Track "which topics are hottest now" hourly Feature: Real-time understanding of current popularity ranking changes Note: Continuously ranked news appear each time |
Incremental Monitorincremental |
📈 Traders/Investors | Push only when new | Newly appeared frequency word matches | Example: Monitor "Tesla", only notify when new news appears Feature: Zero duplication, only see first-time news Suitable for: High-frequency monitoring, avoid information disturbance |
Assume you monitor "Apple" keyword, execute once per hour:
| Time | daily Mode Push | current Mode Push | incremental Mode Push |
|---|---|---|---|
| 10:00 | News A, News B | News A, News B | News A, News B |
| 11:00 | News A, News B, News C | News B, News C, News D | Only News C |
| 12:00 | News A, News B, News C | News C, News D, News E | Only News D, News E |
Explanation:
daily: Cumulative display of all news of the day (A, B, C all retained)current: Display current ranking news (ranking changed, News D on list, News A off list)incremental: Only push newly appeared news (avoid duplicate disturbance)
💡 Encountered this problem? 👉 "Execute once per hour, news output in first execution still appears in next hour execution"
- Reason: You might have selected
daily(Daily Summary) orcurrent(Current Rankings) mode- Solution: Change to
incremental(Incremental Monitor) mode, only push new content
Users who selected
incremental(Incremental Monitor) mode, please note:📌 Incremental mode only pushes when there are new matching news
If you haven't received push notifications for a long time, it may be because:
- No new hot topics matching your keywords in current time period
- Keyword configuration is too strict or too broad
- Too few monitoring platforms
Solutions:
- Solution 1: 👉 Optimize Keyword Configuration - Adjust keyword precision, add or modify monitoring keywords
- Solution 2: Switch push mode - Change to
currentordailymode for scheduled push notifications- Solution 3: 👉 Add More Platforms - Add more news platforms to expand information sources
👉 Click to expand: Customize Hotspot Weights
Configuration Location: advanced.weight section in config/config.yaml
advanced:
weight:
rank: 0.6 # Ranking weight
frequency: 0.3 # Frequency weight
hotness: 0.1 # Hotness weightCurrent default configuration is balanced.
Real-Time Trending Type:
advanced:
weight:
rank: 0.8 # Mainly focus on ranking
frequency: 0.1 # Less concern about continuity
hotness: 0.1Target Users: Content creators, marketers, users wanting to quickly understand current hot topics
In-Depth Topic Type:
advanced:
weight:
rank: 0.4 # Moderate ranking focus
frequency: 0.5 # Emphasize sustained heat within the day
hotness: 0.1Target Users: Investors, researchers, journalists, users needing deep trend analysis
- Three numbers must sum to 1.0
- Increase what's important: Increase
rankfor rankings,frequencyfor continuity - Suggest adjusting 0.1-0.2 at a time, observe effects
Core idea: Users pursuing speed and timeliness increase ranking weight, users pursuing depth and stability increase frequency weight.
👉 Click to expand: Message Style Preview
📊 Trending Keywords Stats
🔥 [1/3] AI ChatGPT : 2 items
-
[Baidu Hot] 🆕 ChatGPT-5 officially launched [1] - 09:15 (1 time)
-
[Toutiao] AI chip concept stocks surge [3] - [08:30 ~ 10:45] (3 times)
━━━━━━━━━━━━━━━━━━━
📈 [2/3] BYD Tesla : 2 items
-
[Weibo] 🆕 BYD monthly sales break record [2] - 10:20 (1 time)
-
[Douyin] Tesla price reduction promotion [4] - [07:45 ~ 09:15] (2 times)
━━━━━━━━━━━━━━━━━━━
📌 [3/3] A-shares Stock Market : 1 item
- [Wallstreetcn] A-shares midday review [5] - [11:30 ~ 12:00] (2 times)
🆕 New Trending News (Total 2 items)
Baidu Hot (1 item):
- ChatGPT-5 officially launched [1]
Weibo (1 item):
- BYD monthly sales break record [2]
Updated: 2025-01-15 12:30:15
| Format Element | Example | Meaning | Description |
|---|---|---|---|
| 🔥📈📌 | 🔥 [1/3] AI ChatGPT | Popularity Level | 🔥 High (≥10) 📈 Medium (5-9) 📌 Normal (<5) |
| [Number/Total] | [1/3] | Rank Position | Current group rank among all matches |
| Keyword Group | AI ChatGPT | Keyword Group | Group from config, title must contain words |
| : N items | : 2 items | Match Count | Total news matching this group |
| [Platform] | [Baidu Hot] | Source Platform | Platform name of the news |
| 🆕 | 🆕 ChatGPT-5 officially launched | New Mark | First appearance in this round |
| [number] | [1] | High Rank | Rank ≤ threshold, bold red display |
| [number] | [7] | Normal Rank | Rank > threshold, normal display |
| - time | - 09:15 | First Time | Time when news was first discovered |
| [time~time] | [08:30 ~ 10:45] | Duration | Time range from first to last appearance |
| (N times) | (3 times) | Frequency | Total appearances during monitoring |
| New Section | 🆕 New Trending News | New Topic Summary | Separately shows newly appeared topics |
👉 Click to expand: Complete Docker Deployment Guide
Image Description:
TrendRadar provides two independent Docker images, deploy according to your needs:
| 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) |
💡 Recommendations:
- Only need push functionality: Deploy
wantcat/trendradarimage only- Need AI analysis: Deploy both images
-
Create Project Directory and Config:
Method 1-A: Using git clone (Recommended, Simplest)
# Clone project to local git clone https://github.com/sansan0/TrendRadar.git cd TrendRadar
Method 1-B: Using wget to download config files
# Create directory structure mkdir -p trendradar/{config,docker} cd trendradar # Download config file templates 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/ wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/config/ai_analysis_prompt.txt -P config/ # Download docker compose config 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/
💡 Note: Key directory structure required for Docker deployment:
current directory/
├── config/
│ ├── config.yaml
│ ├── frequency_words.txt
│ └── ai_analysis_prompt.txt # AI analysis prompt (v5.0.0 new, optional)
└── docker/
├── .env
└── docker-compose.yml
-
Config File Description:
config/config.yaml- Application main config (report mode, push settings, AI analysis, etc.)config/frequency_words.txt- Keyword config (set your interested trending keywords)config/ai_analysis_prompt.txt- AI prompt config (customize AI analysis role and output format, v5.0.0 new).env- Environment variable config (webhook URLs, API Keys, scheduled tasks)
⚙️ Environment Variable Override Mechanism (v3.0.5+)
If you encounter config.yaml modifications not taking effect in NAS or other Docker environments, you can directly override configs via environment variables:
Environment Variable Corresponding Config Example Value Description ENABLE_WEBSERVER- true/falseAuto-start web server WEBSERVER_PORT- 8080Web server port FEISHU_WEBHOOK_URLnotification.channels.feishu.webhook_urlhttps://...Feishu Webhook (multi-account use ;separator)AI_ANALYSIS_ENABLEDai_analysis.enabledtrue/falseEnable AI analysis (v5.0.0 new) AI_API_KEYai.api_keysk-xxx...AI API Key (shared by ai_analysis and ai_translation) AI_PROVIDERai.providerdeepseek/openai/geminiAI provider (v5.0.0 new) S3_*storage.remote.*- Remote storage config (5 params) Config Priority: Environment Variables > config.yaml
Usage Method:
- Modify
.envfile, uncomment and fill in needed configs - Or add directly in NAS/Synology Docker management interface's "Environment Variables"
- Restart container to take effect:
docker compose up -d
-
Start Service:
Option A: Start All Services (Push + AI Analysis)
# Pull latest images docker compose pull # Start all services (trendradar + trendradar-mcp) docker compose up -d
Option B: Start News Push Service Only
# Start trendradar only (scheduled crawling and push) docker compose pull trendradar docker compose up -d trendradarOption C: Start MCP AI Analysis Service Only
# Start trendradar-mcp only (AI analysis interface) docker compose pull trendradar-mcp docker compose up -d trendradar-mcp💡 Tips:
- Most users only need to start
trendradarfor news push functionality - Only need to start
trendradar-mcpwhen using ChatGPT/Gemini for AI dialogue analysis - Both services are independent and can be flexibly combined
- Most users only need to start
-
Check Running Status:
# View news push service logs docker logs -f trendradar # View MCP AI analysis service logs docker logs -f trendradar-mcp # View all container status docker ps | grep trendradar # Stop specific service docker compose stop trendradar # Stop push service docker compose stop trendradar-mcp # Stop MCP service
If you need custom code modifications or build your own image:
# Clone project
git clone https://github.com/sansan0/TrendRadar.git
cd TrendRadar
# Modify config files
vim config/config.yaml
vim config/frequency_words.txt
# Use build version docker compose
cd docker
cp docker-compose-build.yml docker-compose.ymlBuild and Start Services:
# 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 trendradar
docker compose up -d trendradar
# Option C: Build and start MCP AI analysis service only
docker compose build trendradar-mcp
docker compose up -d trendradar-mcp💡 Architecture Parameter Notes:
- Default builds
amd64architecture images (suitable for most x86_64 servers)- To build
arm64architecture (Apple Silicon, Raspberry Pi, etc.), set environment variable:export DOCKER_ARCH=arm64 docker compose build
# 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
# Method 2: Using docker compose update
docker compose pull
docker compose up -dAvailable Images:
| Image Name | Purpose | Description |
|---|---|---|
wantcat/trendradar |
News Push Service | Scheduled news crawling, push notifications |
wantcat/trendradar-mcp |
MCP Service | AI analysis features (optional) |
# View running status
docker exec -it trendradar python manage.py status
# Manually execute crawler once
docker exec -it trendradar python manage.py run
# View real-time logs
docker exec -it trendradar python manage.py logs
# Display current config
docker exec -it trendradar python manage.py config
# Display output files
docker exec -it trendradar python manage.py files
# Web server management (for browser access to generated reports)
docker exec -it trendradar python manage.py start_webserver # Start web server
docker exec -it trendradar python manage.py stop_webserver # Stop web server
docker exec -it trendradar python manage.py webserver_status # Check web server status
# View help info
docker exec -it trendradar python manage.py help
# Restart container
docker restart trendradar
# Stop container
docker stop trendradar
# Remove container (keep data)
docker rm trendradar💡 Web Server Notes:
- After starting, access latest report at
http://localhost:8080- Access historical reports via directory navigation (e.g.,
http://localhost:8080/2025-xx-xx/)- Port can be configured in
.envfile withWEBSERVER_PORTparameter- Auto-start: Set
ENABLE_WEBSERVER=truein.env- Security: Static files only, limited to output directory, localhost binding only
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/html/YYYY-MM-DD/当日汇总.html |
Historical reports | All environments (archived by date) |
Local Access Examples:
# Method 1: Via Web Server (recommended, Docker environment)
# 1. Start web server
docker exec -it trendradar python manage.py start_webserver
# 2. Access in browser
http://localhost:8080 # Access latest report (default index.html)
http://localhost:8080/html/2025-xx-xx/ # Access reports for specific 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/html/2025-xx-xx/当日汇总.htmlWhy two index.html files?
output/index.html: Docker Volume mounted to host, can be opened locallyindex.html: Pushed to repository by GitHub Actions, auto-deployed by GitHub Pages
💡 Tip: Both files have identical content, choose either one to access.
# Check container status
docker inspect trendradar
# View container logs
docker logs --tail 100 trendradar
# Enter container for debugging
docker exec -it trendradar /bin/bash
# Verify config files
docker exec -it trendradar ls -la /app/config/If you need to use AI analysis features, you can deploy the standalone MCP service container.
Architecture Description:
flowchart TB
subgraph trendradar["trendradar"]
A1[Scheduled News Fetching]
A2[Push Notifications]
end
subgraph trendradar-mcp["trendradar-mcp"]
B1[127.0.0.1:3333]
B2[AI Analysis API]
end
subgraph shared["Shared Volume"]
C1["config/ (ro)"]
C2["output/ (ro)"]
end
trendradar --> shared
trendradar-mcp --> shared
Quick Start:
Use docker compose to start both news push and MCP services:
# Method 1: Clone project (Recommended)
git clone https://github.com/sansan0/TrendRadar.git
cd TrendRadar/docker
docker compose up -d
# Method 2: Download docker-compose.yml separately
mkdir trendradar && cd trendradar
wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/docker-compose.yml
wget https://raw.githubusercontent.com/sansan0/TrendRadar/master/docker/.env
mkdir -p config output
# Download config files
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/
# Modify volume paths in docker-compose.yml: ../config -> ./config, ../output -> ./output
docker compose up -d
# Check running status
docker ps | grep trendradarStart MCP Service Separately:
# Linux/Mac
docker run -d --name trendradar-mcp \
-p 127.0.0.1:3333:3333 \
-v $(pwd)/config:/app/config:ro \
-v $(pwd)/output:/app/output:ro \
-e TZ=Asia/Shanghai \
wantcat/trendradar-mcp:latest
# Windows PowerShell
docker run -d --name trendradar-mcp `
-p 127.0.0.1:3333:3333 `
-v ${PWD}/config:/app/config:ro `
-v ${PWD}/output:/app/output:ro `
-e TZ=Asia/Shanghai `
wantcat/trendradar-mcp:latest
⚠️ Note: Ensureconfig/andoutput/folders exist in current directory with config files and news data before running.
Verify Service:
# Check MCP service health
curl http://127.0.0.1:3333/mcp
# View MCP service logs
docker logs -f trendradar-mcpConfigure in AI Clients:
After MCP service starts, configure based on your client:
Cherry Studio (Recommended, GUI config):
- Settings → MCP Server → Add
- Type:
streamableHttp - URL:
http://127.0.0.1:3333/mcp
Claude Desktop / Cline (JSON config):
{
"mcpServers": {
"trendradar": {
"url": "http://127.0.0.1:3333/mcp",
"type": "streamableHttp"
}
}
}💡 Tip: MCP service only listens on local port (127.0.0.1) for security. For remote access, configure reverse proxy and authentication yourself.
👉 Click to expand: Customize Push Style and Content
Configuration Location: report and display sections in config/config.yaml
report:
mode: "daily" # Push mode
display_mode: "keyword" # Display mode (v4.6.0 new)
rank_threshold: 5 # Ranking highlight threshold
sort_by_position_first: false # Sorting priority
max_news_per_keyword: 0 # Maximum display count per keyword
display:
region_order: # Region display order (v5.2.0 new)
- new_items # New trending section
- hotlist # Hotlist section
- rss # RSS subscription section
- standalone # Independent display section
- ai_analysis # AI analysis section| Config Item | Type | Default | Description |
|---|---|---|---|
mode |
string | daily |
Push mode, options: daily/incremental/current, see Push Mode Details |
display_mode |
string | keyword |
Display mode, options: keyword/platform, see below |
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 |
display.region_order |
list | See config above | Adjust list order to control region display positions |
Controls how news is grouped in push messages and HTML reports:
| Mode | Grouping | Title Prefix | Use Case |
|---|---|---|---|
keyword (default) |
Group by keyword | [Platform] |
Users focusing on specific topics |
platform |
Group by platform | [Keyword] |
Users focusing on specific platforms |
Example Comparison:
# keyword mode (group by keyword)
📊 Trending Keywords Stats
🔥 [1/3] AI : 12 items
1. [Weibo] OpenAI releases GPT-5 #1-#3 - 08:30 (5 times)
2. [Zhihu] How to view AI replacing programmers #2 - 09:15 (3 times)
# platform mode (group by platform)
📊 Trending News Stats
🔥 [1/4] Weibo : 12 items
1. [AI] OpenAI releases GPT-5 #1-#3 - 08:30 (5 times)
2. [Trump] Trump announces major policy #2 - 09:15 (3 times)
Control the display position of each section in push messages by adjusting the order of display.region_order list.
Default Order: New Items → Hotlist → RSS → Standalone → AI Analysis
Custom Example: Want AI analysis at the top?
display:
region_order:
- ai_analysis # Move to first line
- new_items
- hotlist
- rss
- standaloneNote: A region will only be displayed when both conditions are met:
- Listed in
region_order - Corresponding switch in
display.regionsistrue
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:
SORT_BY_POSITION_FIRST=true
MAX_NEWS_PER_KEYWORD=10Provides full trending list display for specified platforms, unaffected by frequency_words.txt keyword filtering.
Configuration Location: display section in config/config.yaml
display:
regions:
standalone: true # Enable independent display section
standalone:
platforms: ["zhihu", "weibo"] # Trending platform ID list
rss_feeds: ["hacker-news"] # RSS feed ID list
max_items: 20 # Max display count per source (0=unlimited)Use Cases:
- Want to view the complete trending ranking of a platform (like Zhihu) instead of just keyword-matched content
- Subscribed to RSS feeds with few updates (like personal blogs) and want full push every time
Effect Example:
📋 Independent Display Section (Total 15 items)
Zhihu Trending (10 items):
1. [Zhihu] How to view OpenAI releasing Sora?
2. [Zhihu] 2024 postgraduate entrance exam scores released...
...
Hacker News (5 items):
1. [Hacker News] Launch HN: TrendRadar...
...
👉 Click to expand: Set Push Time Window
Configuration Location: notification.push_window section in config/config.yaml
notification:
push_window:
enabled: false # Whether to enable
start: "20:00" # Start time (Beijing time)
end: "22:00" # End time (Beijing time)
once_per_day: true # Push only once per day| Config Item | Type | Default | Description |
|---|---|---|---|
enabled |
bool | false |
Whether to enable push time window control |
start |
string | "20:00" |
Push window start time (Beijing time, HH:MM format) |
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 |
| 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 |
⚠️ 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
PUSH_WINDOW_ENABLED=true
PUSH_WINDOW_START=09:00
PUSH_WINDOW_END=18:00
PUSH_WINDOW_ONCE_PER_DAY=falseScenario: Push once between 8-10 PM daily
notification:
push_window:
enabled: true
start: "20:00"
end: "22:00"
once_per_day: trueScenario: Push every hour during working hours
notification:
push_window:
enabled: true
start: "09:00"
end: "18:00"
once_per_day: false👉 Click to expand: Set Auto-Run Frequency
Configuration Location: schedule section in .github/workflows/crawler.yml
on:
schedule:
- cron: "0 * * * *" # Run every hourGitHub Actions uses a time format called "Cron". You don't need to understand it deeply; just copy and replace the code below.
Configuration Location: schedule section in .github/workflows/crawler.yml
| I want... | Copy this line | Note |
|---|---|---|
| Every Hour | - cron: "0 * * * *" |
Default, runs at minute 0 |
| Every 30 Mins | - cron: "*/30 * * * *" |
Runs every 30 minutes |
| Daily at 8 AM | - cron: "0 0 * * *" |
0 because UTC 0:00 = Beijing 8:00 AM |
| Work Hours (30m) | - cron: "*/30 0-14 * * *" |
Beijing 8:00 - 22:00 |
| 3 Times Daily | - cron: "0 0,6,12 * * *" |
Beijing 8:00, 14:00, 20:00 |
-
Time Zone: GitHub servers use UTC time.
- Math: Your desired Beijing time minus 8 hours = value to fill.
- Example: For Beijing 20:00, fill in 12:00.
-
Don't run too often: Suggest intervals no shorter than 30 minutes.
- GitHub free resources are limited; running too frequently might get flagged.
- Actions have startup delays, so precise timing isn't guaranteed anyway.
- In your GitHub repository, find
.github/workflows/crawler.yml. - Click the ✏️ (Edit) button top right.
- Find the line
cron: "..."and replace the content inside quotes with the code above. - Click the green Commit changes button to save.
👉 Click to expand: Send to Multiple Recipients
Configuration Location: notification section in config/config.yaml
DO NOT write passwords/Tokens directly in
config.yaml! If you upload a file containing passwords to GitHub, the whole world can see it.Correct Method:
- GitHub Actions Users: Add in Settings -> Secrets
- Docker Users: Write in
.envfile (this file won't be uploaded)
Simple, just separate multiple addresses with a semicolon ;.
Example: Suppose you have two Feishu groups:
- Group 1:
https://.../webhook/aaa - Group 2:
https://.../webhook/bbb
Config value:
https://.../webhook/aaa;https://.../webhook/bbb
| Platform | Method | Note |
|---|---|---|
| Feishu/DingTalk/WeWork | Separate URLs with ; |
Just chain them up |
| Bark (iOS) | Separate URLs with ; |
Push to multiple iPhones |
| Telegram | Separate Tokens and ChatIDs with ; |
Token1 ↔ ChatID1 Token2 ↔ ChatID2 |
| ntfy | Separate Topics and Tokens with ; |
If a topic needs no token, leave empty:token1;;token3 (middle is empty) |
# Send to 3 Feishu groups
FEISHU_WEBHOOK_URL=https://hook1...;https://hook2...;https://hook3...
# Send to 2 DingTalk groups
DINGTALK_WEBHOOK_URL=https://oapi...;https://oapi...
# Send to 2 Telegram users (Match one-to-one)
TELEGRAM_BOT_TOKEN=tokenA;tokenB
TELEGRAM_CHAT_ID=userA;userBTip: Default limit is 3 accounts per platform to prevent abuse. Adjust
MAX_ACCOUNTS_PER_CHANNELif needed.
👉 Click to expand: Choose Data Storage Location
The system automatically selects the best location for you, so you usually don't need to worry about it:
| Your Environment | Data Location | Description |
|---|---|---|
| Docker / Local | Local Disk | Saved in the output/ folder within the project directory. |
| GitHub Actions | Cloud Storage | Since GitHub Actions environments are destroyed after running, cloud storage (e.g., Cloudflare R2) is required. |
If you run on GitHub Actions, you need a "cloud drive" to save data. For example, Cloudflare R2 (free tier is generous).
Add these 5 variables to GitHub Secrets:
| Variable Name | Value |
|---|---|
STORAGE_BACKEND |
remote |
S3_BUCKET_NAME |
Your bucket name |
S3_ACCESS_KEY_ID |
Your Access Key |
S3_SECRET_ACCESS_KEY |
Your Secret Key |
S3_ENDPOINT_URL |
Your R2 endpoint URL |
💡 Tutorial: How to apply for R2? See Quick Start - Remote Storage Configuration
By default, we never delete your data. If you want to save space, you can enable "Auto Cleanup".
Config Location: config/config.yaml
storage:
local:
retention_days: 30 # Keep local data for 30 days (0 = forever)
remote:
retention_days: 30 # Keep cloud data for 30 daysIf you are overseas or find the push time doesn't match your local time, you can change the timezone.
Config Location: config/config.yaml
app:
timezone: "Asia/Shanghai" # Default is China Standard Time- Example for Los Angeles:
America/Los_Angeles - Example for London:
Europe/London
👉 Click to expand: Enable AI Smart Analysis
After enabling this feature, AI acts as a professional analyst. When pushing a batch of news, it will:
- Auto-Read: Read all matched trending news.
- Deep Think: Analyze connections between seemingly isolated news items.
- Write Report: Append a concise and profound "Insight Report" at the end of the push message.
Includes: Trending topic summary, public opinion direction, cross-platform correlation, potential impact assessment, etc.
The simplest way is via environment variables (Recommended for GitHub Secrets or .env).
Required Configurations:
| Variable Name | Value | Description |
|---|---|---|
AI_ANALYSIS_ENABLED |
true |
Enable switch |
AI_API_KEY |
sk-xxxxxx |
Your API Key |
AI_MODEL |
deepseek/deepseek-chat |
Model identifier (format: provider/model) |
Supported AI Providers (Based on LiteLLM, supports 100+ providers):
| Provider | AI_MODEL Value | Description |
|---|---|---|
| DeepSeek (Recommended) | deepseek/deepseek-chat |
Excellent cost-performance ratio for high-frequency analysis |
| OpenAI | openai/gpt-4oopenai/gpt-4o-mini |
GPT-4o series |
| Google Gemini | gemini/gemini-1.5-flashgemini/gemini-1.5-pro |
Gemini series |
| Custom API | Any format | Use with AI_API_BASE |
💡 New Feature: Now based on LiteLLM unified interface, supporting 100+ AI providers with simpler configuration and better error handling.
Optional Configurations:
| Variable Name | Default | Description |
|---|---|---|
AI_API_BASE |
(auto) | Custom API endpoint (e.g., OneAPI, local models) |
AI_TEMPERATURE |
1.0 |
Sampling temperature (0-2, higher = more random) |
AI_MAX_TOKENS |
5000 |
Maximum tokens to generate |
AI_TIMEOUT |
120 |
Request timeout (seconds) |
AI_NUM_RETRIES |
2 |
Number of retries on failure |
If you subscribe to foreign RSS feeds (like Hacker News), AI can translate the content into your native language.
Configuration Location: config/config.yaml
ai_translation:
enabled: true # Enable translation
language: "Chinese" # Target language (Chinese, English, Japanese...)Think the AI sounds too official? You can modify its prompt to change its style (e.g., "Sarcastic Commentator", "Senior Investment Advisor").
- File:
config/ai_analysis_prompt.txt - Method: Edit with a text editor, tell AI what analysis style you want.
TrendRadar v3.0.0 added MCP (Model Context Protocol) based AI analysis feature, allowing natural language conversations with news data for deep analysis.
Critical: AI features require local news data support
AI analysis does not query real-time online data directly, but analyzes locally accumulated news data (stored in the output folder)
-
Built-in Test Data: The
outputdirectory includes one week of trending news data from December 21-27, 2025 for quick feature testing -
Query Limitations:
- ✅ Only query data within available date range (Dec 21-27, 7 days total)
- ❌ Cannot query real-time news or future dates
-
Getting Latest Data:
- Test data is for quick experience only, recommend deploying the project yourself to get real-time data
- Follow Quick Start to deploy and run the project
- After accumulating news data for at least 1 day, you can query the latest trending topics
Cherry Studio provides GUI config interface, 5-minute quick deployment, complex parts are one-click install.
Illustrated Deployment Tutorial: Now updated to my WeChat Official Account (see Support Project), reply "mcp" to get
Detailed Deployment Tutorial: README-Cherry-Studio.md
Deployment Mode Description:
- STDIO Mode (Recommended): One-time configuration, no need to reconfigure later. The illustrated deployment tutorial only demonstrates this mode's configuration.
- HTTP Mode (Alternative): If STDIO mode configuration encounters issues, you can use HTTP mode. This mode's configuration is basically the same as STDIO, but only requires copy-pasting one line, less error-prone. The only thing to note is that you need to manually start the service before each use. For details, refer to the HTTP mode section at the bottom of README-Cherry-Studio.md.
Detailed Conversation Tutorial: README-MCP-FAQ.md
Question Effect:
💡 Tip: Actually not recommended to ask multiple questions at once. If your chosen AI model cannot even sequentially call as shown below, suggest switching models.
TrendRadar MCP service supports standard Model Context Protocol (MCP), can connect to various AI clients supporting MCP for smart analysis.
Note:
- Replace
/path/to/TrendRadarwith your actual project path - Windows paths use double backslashes:
C:\\Users\\YourName\\TrendRadar - Remember to restart after saving
👉 Click to expand: Cursor
-
Start HTTP Service:
# Windows start-http.bat # Mac/Linux ./start-http.sh
-
Configure Cursor:
Project Level Config (Recommended): Create
.cursor/mcp.jsonin project root:{ "mcpServers": { "trendradar": { "url": "http://localhost:3333/mcp", "description": "TrendRadar News Trending Aggregation Analysis" } } }Global Config: Create
~/.cursor/mcp.jsonin user directory (same content) -
Usage Steps:
- Restart Cursor after saving config
- Check connected tools in chat interface "Available Tools"
- Start using:
Search today's "AI" related news
Create .cursor/mcp.json:
{
"mcpServers": {
"trendradar": {
"command": "uv",
"args": [
"--directory",
"/path/to/TrendRadar",
"run",
"python",
"-m",
"mcp_server.server"
]
}
}
}👉 Click to expand: VSCode (Cline/Continue)
Add in Cline's MCP settings:
HTTP Mode:
{
"trendradar": {
"url": "http://localhost:3333/mcp",
"type": "streamableHttp",
"autoApprove": [],
"disabled": false
}
}STDIO Mode (Recommended):
{
"trendradar": {
"command": "uv",
"args": [
"--directory",
"/path/to/TrendRadar",
"run",
"python",
"-m",
"mcp_server.server"
],
"type": "stdio",
"disabled": false
}
}Edit ~/.continue/config.json:
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"/path/to/TrendRadar",
"run",
"python",
"-m",
"mcp_server.server"
]
}
}
]
}
}Usage Examples:
Analyze recent 7 days "Tesla" popularity trend
Generate today's trending summary report
Search "Bitcoin" related news and analyze sentiment
👉 Click to expand: MCP Inspector (Debug Tool)
MCP Inspector is the official debug tool for testing MCP connections:
-
Start TrendRadar HTTP Service:
# Windows start-http.bat # Mac/Linux ./start-http.sh
-
Start MCP Inspector:
npx @modelcontextprotocol/inspector
-
Connect in Browser:
- Visit:
http://localhost:3333/mcp - Test "Ping Server" function to verify connection
- Check "List Tools" returns 14 tools:
- Date Parsing: resolve_date_range
- Basic Query: get_latest_news, get_news_by_date, get_trending_topics
- Smart Search: search_news, search_related_news_history
- Advanced Analysis: analyze_topic_trend, analyze_data_insights, analyze_sentiment, find_similar_news, generate_summary_report
- System Management: get_current_config, get_system_status, trigger_crawl
- Visit:
👉 Click to expand: Other MCP-Compatible Clients
Any client supporting Model Context Protocol can connect to TrendRadar:
Service Address: http://localhost:3333/mcp
Basic Config Template:
{
"name": "trendradar",
"url": "http://localhost:3333/mcp",
"type": "http",
"description": "News Trending Aggregation Analysis"
}Basic Config Template:
{
"name": "trendradar",
"command": "uv",
"args": [
"--directory",
"/path/to/TrendRadar",
"run",
"python",
"-m",
"mcp_server.server"
],
"type": "stdio"
}Notes:
- Replace
/path/to/TrendRadarwith actual project path - Windows paths use backslash escape:
C:\\Users\\... - Ensure project dependencies installed (ran setup script)
👉 Click to expand: Q1: HTTP Service Cannot Start?
Check Steps:
-
Confirm port 3333 is not occupied:
# Windows netstat -ano | findstr :3333 # Mac/Linux lsof -i :3333
-
Check if project dependencies installed:
# Re-run install script # Windows: setup-windows.bat or setup-windows-en.bat # Mac/Linux: ./setup-mac.sh
-
View detailed error logs:
uv run python -m mcp_server.server --transport http --port 3333
-
Try custom port:
uv run python -m mcp_server.server --transport http --port 33333
👉 Click to expand: Q2: Client Cannot Connect to MCP Service?
Solutions:
-
STDIO Mode:
- Confirm UV path correct (run
which uvorwhere uv) - Confirm project path correct and no Chinese characters
- Check client error logs
- Confirm UV path correct (run
-
HTTP Mode:
- Confirm service started (visit
http://localhost:3333/mcp) - Check firewall settings
- Try using 127.0.0.1 instead of localhost
- Confirm service started (visit
-
General Checks:
- Restart client application
- Check MCP service logs
- Use MCP Inspector to test connection
👉 Click to expand: Q3: Tool Call Failed or Returns Error?
Possible Reasons:
-
Data Does Not Exist:
- Confirm crawler has run (have output directory data)
- Check query date range has data
- Check available dates in output directory
-
Parameter Error:
- Check date format:
YYYY-MM-DD - Confirm correct platform ID:
zhihu,weibo, etc. - See parameter descriptions in tool docs
- Check date format:
-
Config Issues:
- Confirm
config/config.yamlexists - Confirm
config/frequency_words.txtexists - Check config file format is correct
- Confirm
4 Related Articles (Chinese):
- Comment here for mobile Q&A by project author
- Breaking 1000 stars in 2 months - My GitHub project promotion experience
- Important notes for running this project via GitHub fork
- How to write WeChat Official Account or news articles based on this project
AI Development:
- If you have niche requirements, you can develop based on my project yourself, even with zero programming experience
- All my open-source projects use my own AI-assisted software to improve development efficiency, this tool is now open-source
- Core Function: Quickly filter project code to feed AI, you just need to add personal requirements
- Project Address: https://github.com/sansan0/ai-code-context-helper
📍 Chairman Mao's Footprint Map - Interactive dynamic display of complete trajectory 1893-1976. Welcome comrades to contribute data
Bilibili Comment Data Visualization Analysis Software
GPL-3.0 License