1. Overview
One-Sentence Positioning: An all-network hotspot aggregation and tracking tool that captures trending search data in real time from 7 major platforms including Douyin, Weibo, Bilibili, Kuaishou, Zhihu, Toutiao, and Baidu, for one-stop viewing of all-network hotspots.
Core Value: Solves three major pain points for content creators and marketing operators in hotspot tracking:
- Hotspots Are Scattered and Hard to Integrate: No need to check each platform one by one; aggregates hot lists from 7 major platforms at once
- Cross-Platform Comparison Is Difficult: Automatically identifies discussion differences and popularity performance of the same event across different platforms
- Trend Judgment Is Vague: Intelligently predicts hotspot trends based on dimensions such as popularity value, time on the list, and platform coverage
Target Users: Content creators, marketing operations personnel, media editors, brand planners, and hotspot tracking enthusiasts.
Not Supported: This skill does not support querying details of specific hot words; it only provides aggregated queries of all-network hotspot lists.
2. Features
Core Features
| Feature Module | Capability Description | Core Value |
|---|---|---|
| 🔍 All-Network Hot List Aggregation | Real-time capture of trending search data from 7 major platforms | Get all-network hotspots with one click, no more checking platform by platform |
| 🔗 Cross-Platform Event Identification | Intelligently identifies expressions of the same event across different platforms | Automatically merges similar topics to avoid duplicate counting |
| 📊 Popularity Trend Prediction | Predicts trends based on popularity value, duration, and platform coverage | Judge the hotspot lifecycle in advance and seize the creation window |
| 📈 TOP10 List Provision | Outputs TOP10 hotspots sorted by comprehensive popularity | Quickly locate high-value topics |
| 💬 Cross-Platform Discussion Analysis | Displays discussion focuses and differences across different platforms | Gain deep insight into the public opinion ecosystem and precisely locate audiences |
| ⏰ Subscription Push Service | Scheduled push of the latest hot list/yesterday's hot list | Continuously track hotspot dynamics and never miss key opportunities |
Highlights
- Hourly Updates: Data is updated every hour to maintain real-time performance
- Intelligent Keyword Generalization: Entering "sports" automatically expands to 10 related keywords
- Output Categorized by Platform: Baidu, Zhihu, Weibo, Douyin, Bilibili, Kuaishou, and Toutiao are displayed in order
- Full List Viewing: Each platform supports viewing up to the complete 50 entries of data
- Dynamic Intelligent Output: Platforms with no data are automatically skipped, and the number displayed is automatically adjusted when data is insufficient
3. One-Click Installation
Authentication
Get API Key
Please go to Honghu Hub to get the API KEY
Configure API Key
Option 1: Using OpenClaw as an example, add REDFOX_API_KEY to ~/.openclaw/openclaw.json. Some of the content is as follows:
{ "env": { "REDFOX_API_KEY": "ak_xxxx..." } }
Option 2: Terminal configuration:
export REDFOX_API_KEY="ak_xxxx..."
Dependency installation
pip install python-dateutil
Environment variable configuration
| Variable name | Description | Required |
|---|---|---|
REDFOX_API_KEY |
RedFox API Key | Yes |
4. Usage Guide
Basic Usage
Query the latest trending list (default)
python scripts/fetch_hotspot.py --source "全平台热点事件"
Data is updated hourly, and the previous complete hour is queried automatically. For example: if the current time is 2026-04-16 17:42:00, then query the data from 2026-04-16 16:00:00 to 2026-04-16 17:00:00 .
Query historical trending lists
# 查询昨日热榜（假设今天是2026-04-16）
python scripts/fetch_hotspot.py --source "全平台热点事件" --start-date "2026-04-15 00:00:00" --end-date "2026-04-16 00:00:00"
Date range rules：
- The time format is
YYYY-MM-DD HH:MM:SS, and it can also be abbreviated asYYYY-MM-DD(automatically completed to 00:00:00) - The date range is a
[start_date, end_date)left-closed, right-open interval - For example:
--start-date "2026-04-01 00:00:00" --end-date "2026-04-02 00:00:00"queries the data for April 1 - Maximum query range:30 days
Advanced Usage
Filter by specific platform
python scripts/fetch_hotspot.py --source "全平台热点事件" --platforms "wb,dy,bz"
Platform code mapping:
| Platform code | Platform name | API enum value |
|---|---|---|
| bd | Baidu | 7 |
| zh | Zhihu | 9 |
| wb | 5 | |
| dy | Douyin | 2 |
| bz | Bilibili | 8 |
| ks | Kuaishou | 1 |
| tt | Toutiao | 10 |
Keyword search and generalization
# 关键词筛选
python scripts/fetch_hotspot.py --source "全平台热点事件" --keywords "体育,足球"
# 关键词泛化扩展
python scripts/fetch_hotspot.py --source "全平台热点事件" --keywords "体育" --expand-keywords
Keyword generalization strategy：
- Broad terms (such as "sports", "entertainment", "technology"): automatically expanded to 10 generalized terms
- Example: "sports" -> ["sports", "football", "basketball", "athletics", "fitness", "Olympics", "World Cup", "NBA", "CBA", "table tennis"]
- Exact terms (such as "Super League", "a celebrity's name"): pass in the original term directly without expansion
- Major categories that support generalization: sports, entertainment, technology, finance, society, games, automobiles, food, travel, fashion, etc.
View the full ranking
When the user replies "View the full {platform name} ranking":
python scripts/fetch_hotspot.py --source "全平台热点事件" --platforms wb --output markdown
Agent time determination logic
Automatically select the query method based on user intent (assuming today's date is T):
| User intent | Query method | Script parameters |
|---|---|---|
| "Today's hot topics" / "Today's trending list" | Query from 0:00 today to the current hour | --start-date "T 00:00:00" --end-date "T {当前小时}:00:00" |
| "Latest trending list" / "Hot topics list" | Query the previous complete hour | No time parameter needs to be specified |
| "Yesterday's trending list" / "Yesterday's hot list" | Query from 0:00 to 24:00 yesterday | --start-date "T-1 00:00:00" --end-date "T 00:00:00" |
| "This week's trending list" / "This week's hot list" | Query from 0:00 Monday of this week to the current hour | --start-date "{本周一日期} 00:00:00" --end-date "T {当前小时}:00:00" |
Calculation rule for this week's Monday：
- Calculation formula: this week's Monday = today's date - (today's day of the week - 1) days
- Example: today is 2026-05-09 (Saturday), this week's Monday = 2026-05-04
Comparison query scenarios: when the user needs to compare data across multiple days, the trending lists for multiple days need to be queried separately:
# 对比昨天和今天的热榜（假设今天是2026-04-16）
python scripts/fetch_hotspot.py --source "全平台热点事件" --start-date "2026-04-15 00:00:00" --end-date "2026-04-16 00:00:00" # 昨日
python scripts/fetch_hotspot.py --source "全平台热点事件" --start-date "2026-04-16 00:00:00" --end-date "2026-04-17 00:00:00" # 今日实时
Output format description
compact mode (default): Output minimal structured data (metadata + platform TOP3 overview), with the complete data file path appended at the end dataFile: {path}. The agent should use compact mode to retrieve data, from dataFile path to read the complete JSON data. Only 1 API call is allowed.
Output Format Template: Output by platform category, showing TOP10 hot topics for each platform. Smart output rules:
- If a platform has no hot topic data, do not display that platform
- If a platform has fewer than 10 items, display the actual number
- When data > 10 items, display "This platform has {N} more items not shown"
- Platform order: Baidu → Zhihu → Weibo → Douyin → Bilibili → Kuaishou → Toutiao
See the output format template for details references/output-templates.md。
Heat Value Processing
- If the heat value already includes a unit (such as "wan", "yi"), use the original value directly
- If the heat value is a pure number, convert it to the "number + wan" format (
hotCount // 10000integer division)- Example: Baidu heat
7904508→790万
- Example: Baidu heat
- The heat value format must be "number + wan"; other characters are prohibited
Subscription Push Service
- Daily Push: Push the latest hot lists on a scheduled daily basis (such as 8 AM and 8 PM)
- Weekly Push: Push a popular summary on a scheduled weekly basis (such as Monday morning)
- Push format: streamlined TOP10 table + brief summary (TOP3 for each platform + brief summary of network-wide hot topics)
Command Quick Reference
| Scenario | Command |
|---|---|
| Latest Hot List | python scripts/fetch_hotspot.py --source "全平台热点事件" |
| Today's Hot List | python scripts/fetch_hotspot.py --source "全平台热点事件" --start-date "T 00:00:00" --end-date "T HH:00:00" |
| Yesterday's Hot List | python scripts/fetch_hotspot.py --source "全平台热点事件" --start-date "T-1 00:00:00" --end-date "T 00:00:00" |
| Specified Platform | python scripts/fetch_hotspot.py --platforms "wb,dy" |
| Keyword Filtering | python scripts/fetch_hotspot.py --keywords "体育,足球" |
| Keyword Generalization | python scripts/fetch_hotspot.py --keywords "体育" --expand-keywords |
Data Structure Description
{
"status": "success",
"stat_time": "2026-05-08 07:35:15",
"total_count": 330,
"hotspots": [
{
"title": "热点标题",
"url": "https://...",
"hotCount": 7904508,
"index": 1,
"gmtCreate": "2026-05-08 06:00:14",
"platCode": "bd",
"platName": "百度"
}
],
"query_range": {
"type": "realtime",
"start_date": "2026-05-08 06:00:00",
"end_date": "2026-05-08 07:00:00"
}
}
| Field | Description |
|---|---|
| hotspots | Hot topic list, containing hot topic data from all platforms |
| title | Hot topic title (spaces already processed) |
| url | Hot topic link (spaces converted to %20) |
| hotCount | Heat value (pure number, characters such as "wan re du" already removed) |
| index | Rank within platform |
| gmtCreate | Creation time |
| platCode | Platform code: bd/bz/dy/ks/tt/wb/zh |
| platName | Platform name: Baidu/Bilibili/Douyin/Kuaishou/Toutiao/Weibo/Zhihu |
5. Use Cases
Scenario 1: Content creators tracking hot topics
Role: Self-media creator Need: Quickly understand network-wide hot topics every morning and determine the topic direction for the day How to use: Enter "today's hot topics" to get the real-time TOP10 hot lists from 7 major platforms Expected benefit: Grasp network-wide hot topic trends within 5 minutes and precisely identify high-value topics
Scenario 2: Market operations competitive analysis
Role: Brand market operations Need: Compare discussion differences for the same event across different platforms and understand the public opinion ecosystem How to use: Query hot topics for specified keywords and observe cross-platform discussion focus Expected benefit: Gain deep insight into user discussion differences across platforms and formulate differentiated operational strategies
Scenario 3: PR crisis monitoring
Role: Public Relations Manager Requirement: Real-time monitoring of popularity changes for specific brands or events across multiple platforms How to Use: Through keyword filtering + subscription push, continuously track related hot topics Expected Benefits: Discover public opinion signals at the earliest opportunity and seize the window for crisis response
Scenario 4: Hot Topic Trend Research
Role: Data Analyst Requirement: Compare hot topic data across multiple days and analyze hot topic evolution trends How to Use: Use comparative queries to query data for multiple days separately and analyze popularity changes Expected Benefits: Determine the hot topic lifecycle based on data and output trend analysis reports
6. Project Architecture
Directory Structure
trending-hub/
├── SKILL.md # 技能描述文件
├── scripts/
│ └── fetch_hotspot.py # 热点数据获取脚本
└── references/
└── output-templates.md # 输出格式模板参考
Tech Stack
| Component | Technology | Description |
|---|---|---|
| Scripting Language | Python 3 | Use the standard library urllib.request |
| External Dependencies | python-dateutil | Date Handling |
| Data Interface | Redfox API | Multi-platform hot topic data aggregation |
| Output Format | JSON / Markdown | Structured and visualized output |
Core Module Description
| Module | Function |
|---|---|
fetch_hotspot.py |
Fetch multi-platform hot topic data from the API, supporting platform filtering, keyword search, time range queries, and keyword generalization |
output-templates.md |
Define the dialogue output format template and standardize the TOP10 table and summary format for each platform |
Resource Index
- Script: see scripts/fetch_hotspot.py(Purpose and parameters: fetch hot topic data from the API, supporting platform filtering)
- Reference: see references/output-templates.md(When to read: refer to the format template when outputting dialogue)
7. FAQ
Installation-related
Q: The script reports an error when running: "ModuleNotFoundError: No module named 'dateutil'"
A: Please install the dependency:pip install python-dateutil
Q: It shows "REDFOX_API_KEY not found"
A: Please ensure the environment variable has been configured REDFOX_API_KEY, and refer to the authentication section above for configuration.
Usage-related
Q: Why does querying "Today's Hot Topics" show data that is not from today?
A: The data is updated hourly, and the latest hot list query returns data from the previous complete hour. To query today's data, use the --start-date and --end-date parameters to specify today from 0:00 to the current hour.
Q: How far back can data be queried? A: The maximum query range is 30 days.
Q: How can I view the complete 50-item list for a platform?
A: Reply "View {platform name} complete list", and the system will use the --platforms parameter to filter that platform and output the complete 50 items of data.
Q: Hot topic titles cannot be clicked?
A: Titles are output in Markdown hyperlink format [标题](url) , and hot topics without URLs display only text.
Troubleshooting
Q: The API returns empty data? A: Possible reasons: 1) Network connection issues; 2) The API Key is invalid or expired; 3) The query time range exceeds the limit. Please check the network and API Key configuration.
Q: The output is truncated?
A: By default, compact mode is used to avoid truncation. If it is still truncated, read the complete JSON data from the dataFile path at the end of the compact output.
Q: No results for keyword search?
A: Try using the --expand-keywords parameter to generalize and expand the keywords, broadening the search scope.