weibo-post-search

Weibo Account Post Retrieval

📝 Introduction

A Weibo user post query tool. Enter a Weibo user's homepage link or uid to query that user's latest posts, with paginated browsing supported.

✨ Features

Feature Module	Capability Description	Core Value
User Query	Enter a Weibo homepage link or uid to query posts	View any user's latest updates with one click
Paginated Browsing	Supports browsing results across multiple pages	Explore a user's historical posts page by page

🔑 Authentication

Get API Key

Please go to Redfox Hub to get the API KEY

Configure API Key

Option 1: Using Qoder as an example, add REDFOX_API_KEY to ~/.openclaw/openclaw.json :

{ "env": { "REDFOX_API_KEY": "ak_xxxx..." } }

Option 2: Terminal configuration

export REDFOX_API_KEY="ak_xxxx..."

🔄 Workflow

Step 1: Understand the user's intent and extract the uid

1. Extract the user uid

• If the user provides a Weibo homepage link (such as https://weibo.com/1784473157), extract the uid from it
• If the user directly provides a numeric uid, use it directly
• If the user's intent is vague (such as "help me look up a Weibo user"), proactively ask: "Please provide the Weibo user's homepage link or uid"
• Do not guess on your own and call the script when the user has not provided a uid

2. Identify the page number parameter

• If the user mentions "next page" or "page 2" → the corresponding page number
• If the user mentions "previous page" → current page - 1
• If no page number is mentioned → default to page 1

Step 2: Call the query script

python3 ~/.agents/skills/weibo-post-search/scripts/user_work_list.py "<uid或主页链接>" [--page 页码]

Parameter description:

Parameter	Description
input	User uid or Weibo homepage link (such as https://weibo.com/1784473157）
--page	Page number, starting from 1 (default 1)

The script outputs in JSON format:

Field	Description
uid	User uid
user_name	User nickname (taken from the nickname field in the posts; falls back to uid when there is no nickname)
articles	User post list
page	Current page number
has_next	Whether there is a next page (true/false)

Fields for each post:

Field	Description
content	Post content
forward_num	Repost count
comment_num	Comment count
like_num	Like count
publish_time	Publish time (including hours, minutes, and seconds, such as 2025-07-10 14:30:25）
work_url	Post link (https://weibo.com/{uid}/{mblogId}）

Step 3: Determine the result and display it

Case A: articles count > 0 (matching results found)

A1. Inform the user of the query scope

📊 {user_name} Found Nposts (page {page}), the detailed data is as follows:

A2. Render a Markdown table (display all)

| # | 博文内容 | 转发数 | 评论数 | 点赞数 | 发布时间 |
|---|----------|--------|--------|--------|----------|
| 1 | [博文内容](链接) | 305 | 120 | 1.2w | 2025-07-10 14:30:25 |

Number formatting rules:

• < 10000: raw number (such as 320）
• ≥ 10000：x.xw format (such as 1.2w）

Content rules: [博文内容](work_url); if exceeding 30 characters, truncate and add ...; when the content is empty, display -

A3. Pagination prompt (⚠️ immediately after A2, cannot be omitted, must be output every time)

• If has_next is true:

📄 Currently page {page} . Reply "next page" to continue viewing.

• If has_next is false (the current page has fewer than 9 items or is empty, and is already the last page):

📄 Currently page {page} , no more data.

⚠️ A1~A3 are all indispensable and must be completed consecutively in the same round of output.

Case B: number of articles = 0 (no matching results)

B1. Apology prompt

😔 {user_name} has no blog post data yet, or this user has enabled privacy protection.