A powerful automation tool that extracts structured article details and full body content from Zhihu using the BrowserAct API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install zhihu-search-api-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install zhihu-search-api-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Zhihu Search API Automated Extraction?
The Zhihu Search API Automated Extraction skill is a specialized tool designed for the Openclaw Skills ecosystem to streamline the retrieval of high-quality data from one of China's largest knowledge-sharing platforms. By leveraging the BrowserAct API, it bypasses common web scraping hurdles such as CAPTCHAs, IP rotations, and geo-fencing, providing a stable stream of data for researchers and developers.
This skill is particularly valuable for those needing reliable, hallucination-free data extraction. Unlike standard LLM-based web browsing, this skill uses pre-set workflows to ensure that the article titles, author names, publication dates, and full body content are captured with structural integrity, making it an essential component for any automated research pipeline.
Zhihu Search API Automated Extraction Use Cases
- Industry Trend Tracking: Monitor emerging topics like generative AI or market shifts within the past 7 to 30 days.
- Public Relations & Brand Monitoring: Track brand sentiment and media exposure across Zhihu to manage corporate reputation.
- Competitor Intelligence: Automatically collect updates on competitor product launches and market positioning.
- Content Aggregation: Fetch full article bodies for AI agents to summarize daily industry news or weekly hot events.
- Market Research: Gather structured data including publication dates and author info for quantitative analysis.
How Zhihu Search API Automated Extraction Works
- Input Configuration: The agent receives a search keyword and optional filters for date range (e.g., 7d, 30d, 1y) and result limits.
- Authentication Check: The system verifies the BROWSERACT_API_KEY environment variable before initiating the request.
- API Request Dispatch: A Python script calls the BrowserAct Zhihu Search API template to begin the automated browsing task.
- Status Monitoring: The skill outputs real-time logs with timestamps, allowing the agent to track the task's progress during long-running operations.
- Data Parsing: Upon completion, the raw API response is parsed into a clean, structured format containing titles, body content, image URLs, and source links.
- Error Handling: The skill identifies authorization errors versus network flickers, triggering a single automatic retry if necessary.
Zhihu Search API Automated Extraction Setup
To integrate this into your Openclaw Skills library, ensure you have Python installed and a valid API key from the BrowserAct Console.
# Set your API Key
export BROWSERACT_API_KEY='your_api_key_here'
# Run the extraction script
python -u ./scripts/zhihu_search_api.py "your keyword" "7d" 10
Zhihu Search API Automated Extraction Data Schema & Taxonomy
The skill returns a structured JSON-like output for each article found, organized as follows:
| Field | Description | Type |
|---|---|---|
title |
The full headline of the Zhihu article | String |
body_content |
The complete text content of the article body | String |
author |
The name of the publishing user or organization | String |
publication_date |
Date the article was published | String |
image_url |
URL for the article's main cover image | String (URL) |
url_link |
The permanent direct link to the original post | String (URL) |
Zhihu Search API Automated Extraction Advanced Features
- No-Hallucination Guarantee: Uses deterministic extraction patterns rather than generative AI to ensure data accuracy.
- Automated Retry Logic: Built-in intelligence to automatically retry failed tasks once if the error is non-terminal.
- Real-time Status Heartbeat: Continuous timestamped logging to prevent agent timeouts during complex browser automation tasks.
- Anti-Bot Bypass: Native handling of reCAPTCHA and regional IP restrictions, ensuring high success rates for Openclaw Skills users.
SKILL.md
Loading
Related Openclaw Skills
China Social Policy Public Data
A specialized assistant for querying and organizing official Chinese social security, medical insurance, and housing provident fund policies.
jetson-info
A specialized diagnostic utility for retrieving comprehensive hardware specifications and SDK versions from NVIDIA Jetson devices.
PLC Programming Helper
A specialized command-line utility designed to assist AI agents and developers in managing programmable logic controller programming tasks and data.
XHS Writer: Professional Xiaohongshu Content Creation Suite
A comprehensive offline content creation suite designed to transform any topic into a viral Xiaohongshu publishing package including copy, hooks, and image layouts.
Y Combinator Ecosystem Navigator
A comprehensive guide to navigating the Y Combinator ecosystem, focusing on its operational model, cultural philosophy, and strategic networking value.
Gear Ratio & Mechanical Drive Calculator
A comprehensive mechanical engineering suite for calculating gear ratios, shaft speeds, torque output, and drivetrain configurations via your AI agent.
Featured*
