wechat-article-search

WeChat Official Account article search instructions

Applicable scenarios

• The user says "help me search for official account articles/recent articles with a certain keyword"
• Need to quickly obtain: title, summary, publication time, official account name, accessible link

Workflow

Step 1: Confirm that dependency packages are installed

This script depends on the NodeJS dependency package cheerio, enter the skill directory to install:

cd skills/wechat-article-search && npm install

Step 2: Confirm the number of search terms

1. Confirm keywords and quantity

Step 3: Execute the search command

1. Execute the search command (by default it will automatically try to resolve the real WeChat article link)

node scripts/search_wechat.js "关键词"

Special workflow (optional)

1. Execute the search command including a quantity limit

node scripts/search_wechat.js "关键词" -n 15

1. If the user needs to save the results to a file, execute the command

node scripts/search_wechat.js "关键词" -n 20 -o result.json

1. If the user needs JSON format output, execute the command

node scripts/search_wechat.js "关键词" json

Parameter description

• query: Search keyword (required)
• -n, --num: Number of results to return (default 10, maximum 50)
• -o, --output: Output JSON file path (optional)
• -r, --resolve-url: Resolve the real WeChat article URL (enabled by default)
• --no-resolve-url: Skip real link resolution and directly return the Sogou redirect link
• json, --json: Directly output JSON format data, convenient for program processing

Output format

Formatted output (default)

Output search results in an easy-to-read text format; each article contains the following information:

序号. 文章标题
📌 来源: 公众号名称 | ⏰ 时间信息
💡 文章内容概要
🔗 [查看详情](<完整链接>)

Time information format：

• If there is a complete timestamp:HH:MM (相对时间描述), for example:23:45 (1小时前)
• If there is only relative time: display directly, for example:2小时前

Output characteristics：

• There is a blank line separating each article
• Source and time are displayed on the same line
• Links display the complete URL address, using the [查看详情](<链接>) format

JSON output (using the json parameter)

{
  "query": "搜索关键词",
  "total": 10,
  "articles": [
    {
      "title": "文章标题",
      "source": "公众号名称",
      "datetime": "2026-03-08 10:30:00",
      "date_text": "2026年03月08日",
      "date_description": "2小时前",
      "summary": "文章摘要",
      "url": "https://mp.weixin.qq.com/s/...",
      "url_resolved": true
    }
  ]
}

JSON field description：

• title: Article title
• source: Source official account name
• datetime: Article publication time (China time zone, format: YYYY-MM-DD HH:mm:ss)
• date_text: Date description (format: YYYY年MM月DD日)
• date_description: Relative time description (such as "2 hours ago", "1 day ago", "just now")
• summary: Article summary
• url: Article link (may be a real WeChat link or a Sogou redirect link)
• url_resolved: Whether it was successfully resolved to a real WeChat link (true/false）

Output description

• All links use the [查看详情](<链接>) format, special characters can be handled correctly
• Articles are sorted in descending order by publication time (newest first)
• Only articles from the last 60 days are displayed; older content is automatically filtered out
• Time is preferentially parsed from the timestamp in the page script tag; if there is no timestamp, then try to extract it from the text

Common issue handling

• Empty results: try changing the keyword, using fewer special characters, or retrying later
• Failed to resolve the real URL: this is normal (anti-crawling restrictions); you can prompt the user to open the intermediate link in a browser

Notes

• This tool is for learning and research purposes only; please do not use it for commercial purposes or large-scale crawling.
• When using this tool, please comply with the terms of use and regulations of the relevant websites.
• Excessive use may result in IP bans, so please use it with caution.