Anansi：可自愈选择器、伪装真实用户的网页数据采集工具

🕷️ anansi - Gather data from difficult websites easily

Anansi helps you collect information from websites that block standard tools. It fixes broken parts on its own and acts like a real person to avoid detection. You can connect it to AI models to perform searches through simple chat.

📋 What this tool does

Many websites prevent automated tools from reading their data. These sites check how you connect and block software that looks like a robot. Anansi solves this through several features:

Self-healing selectors: When a website changes its layout, the tool finds the new location of your information automatically.
Browser rendering: Anansi loads pages just like a normal web browser. This catches data that stays hidden from basic tools.
TLS fingerprinting: The tool hides the fact that it is a script. Websites see these requests as typical connections from a personal laptop.
AI integration: It uses the Model Context Protocol to talk to AI assistants. You ask the AI to find facts, and it uses Anansi to gather that data from the web.

💻 System requirements

Windows 10 or Windows 11.
4 GB of free RAM.
An internet connection that remains stable.
Your standard Chrome or Edge web browser updated to the latest version.

📥 How to get started

Visit the official download page.
Locate the section labeled Assets.
Click the file ending in .exe to start your download.
Save the file to your desktop or downloads folder.

⚙️ Running the application

Find the file you just downloaded.
Double-click the file to open the installer.
Follow the prompts on your screen.
Select "Install for everyone" if you share this computer with others.
Click "Finish" once the progress bar completes.
Look for the Anansi icon on your desktop and double-click it.

🤖 Using the AI connection

Anansi works with popular AI tools. If you use a chat application that supports external tools, you can connect Anansi to it.

Open the settings menu within your preferred AI tool.
Find the section for external connections or MCP servers.
Select the option to add a new connection.
Point the tool to the Anansi install folder on your C drive.
Save your settings.
Open your AI chat window and type a request like "Find the product price on this website."
The AI will command Anansi to fetch the page and read the info for you.

🛠️ Handling issues

Sometimes a website might block even sophisticated tools. If Anansi fails to load a page, try the following fixes:

Restart the application.
Check your internet connection.
Verify that your firewall allows the app to communicate with the web.
Wait for a few minutes before you try the request again.

🛡️ Privacy and safety

Anansi keeps your data on your computer. It does not send your search history to any third-party servers. Your information stays private. The tool only connects to the websites you ask it to visit. It does not store your passwords or your personal login details.

📈 Improving your success rate

Web scraping requires patience. If you want to gather large amounts of data, run the program during off-peak hours. This lowers the chance of encountering protection measures on the target website. Use clear instructions when talking to your AI assistant. Tell it exactly which pieces of information you need, such as an item name or a specific date. This helps the tool focus on the right parts of the page.

If you find that a page loads slowly, wait for the browser window to render the visual elements. Anansi needs these elements to read the text correctly. Do not close the browser window while the tool processes the page. Once the tool reports the finished status, it will safely close the browser session itself.

🔑 Common terms

Selector: A hidden address that tells the software where to find specific text on a webpage.
TLS Fingerprint: The unique signature your computer leaves when it talks to a web server.
MCP: A standard method that allows AI models to use software on your computer.
Browser Rendering: The process of drawing a webpage so that it behaves like a normal site in your browser.