Enter keywords to search WeChat official account articles, with terminal table display + CSV export + interactive HTML report.
API Key must be configured first, passed via the environment variable REDFOX_API_KEY or the --api-key parameter. Crawl scope:Official accounts above mid-tierArticles published within the last 30 days. Keyword restrictions:No more than 10 characters, exceeding which will prompt you to simplify.
Use Cases
When you need to perform the following tasks, you should prioritize using this skill:
| Scenario | Example |
|---|---|
| Industry hotspot tracking | Search "AI" to learn what official accounts in the AI field have been discussing recently |
| Competitor content analysis | Search "large models" to crawl the article strategies of competitor official accounts |
| Material and inspiration collection | Search "Xiaohongshu operations" to get viral topic ideas and writing angles |
| Trend research reports | Search "2026 economy" and batch export CSV for data analysis |
| Finding quality accounts | Search "technology" to discover leading official accounts in related fields |
| Topic public opinion monitoring | Search "brand name" to see the discussion trends of official accounts about that brand |
If you want to searchall historical articles of a specific official account, you should use
gzh-subscribethe skill (official account article subscription), which specifically targets single-account subscription tracking.
Usage
# 基础搜索
python3 "$SKILL_PATH/assets/search.py" "关键词"
# 指定数量（多页自动翻页）
python3 "$SKILL_PATH/assets/search.py" "AI" --count 50
# 仅导出 CSV
python3 "$SKILL_PATH/assets/search.py" "大模型" --csv-only
# 不自动打开浏览器
python3 "$SKILL_PATH/assets/search.py" "AI" --no-open
Terminal output is sorted in descending order bycomposite score(keyword relevance + reading popularity + timeliness/freshness), with higher read counts prioritized for ties; when there are few results or no results, tiered prompts are automatically shown.
HTML report features: dark theme · real-time search (300ms debounce) · article cards click to jump to the original text · paginated loading · guides to hot topics when there are zero results.
CSV / HTML are saved by default in ~/Downloads/QoderGzhSearch/。
Parameter Description
| Parameter | Description | Default Value |
|---|---|---|
keyword |
Search keyword (required, positional parameter) | — |
--count |
Number of articles to retrieve | 20 |
--sort-type |
Sort method:default / time |
default |
--output-dir |
Output directory | ~/Downloads/QoderGzhSearch |
--api-key |
Specify API Key | — |
--no-open |
Do not automatically open the browser | — |
--csv-only |
Generate only CSV, not HTML | — |
--port |
HTML local service port | 8766 |
API Key Configuration
Choose any one method to configure your personal Key:
| Method | Command |
|---|---|
| Environment variable (recommended) | export REDFOX_API_KEY=ak_你的密钥 |
| Command-line parameter | --api-key ak_你的密钥 |
| Configuration file | echo '{"api_key":"ak_你的密钥"}' > ~/.qoder/apis/redfox.json |
Registration address:redfox.hk
Features
- Keyword search: real-time query of all WeChat official account articles
- Intelligent scoring and sorting: Comprehensive score based on three factors (relevance + popularity + recency); ties are sorted by read count in descending order
- Tiered response degradation: normal browsing when sufficient / guide to broad search when few / popular fallback when no results
- Terminal table: title, author, reads, likes, shares, favorites, publish time, article link
- CSV export: automatically generates a UTF-8 BOM encoded CSV
- HTML interactive report: built-in search box, supports cover image display, click a card to jump to the original article
- Local proxy service: avoids browser cross-origin restrictions
Dependencies
pip3 install requests
FAQ
Q: Search scope? A: Currently coversmid-tier and above official accountsarticles published within the last 30 days; coverage of all accounts and all history is not guaranteed.
Q: What if I want to search all articles from a specific official account?
A: Please use the gzh-subscribe skill (official account article subscription); it supports subscribing by official account ID to track all articles from a single account.
Q: How many results are returned at most?
A: 20 by default per request, adjusted via --count ; the HTML page supports pagination to load more.
Q: Where is the data saved?
A：~/Downloads/QoderGzhSearch/, file name format 公众号搜索_[关键词]_YYYY-MM-DD.csv/html。
Q: Why is a local service needed? A: Opening HTML directly in the browser has cross-origin restrictions; the built-in HTTP proxy relays API requests.
Q: What should I do when the quota runs out? A: Go to redfox.hk to register and obtain a Token.