Extract structured data from dynamic, JavaScript-heavy websites using Zyte API's proxy rotation and headless browser rendering.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install zyte-api-scraping
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 zyte-api-scraping 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 Zyte API Web Scraping?
The Zyte API Web Scraping skill enables your AI coding agent to extract high-quality structured data from any website, even those heavily protected by anti-bot measures or requiring complex dynamic JavaScript rendering. By leveraging the power of Zyte API (formerly Crawlera) coupled with the ClawLink integration, developers can execute seamless, resilient web scraping directly from their chat interface without worrying about configuring individual proxies or API keys.
This skill is built to streamline developers' data harvesting workflows by handling JavaScript rendering automatically, avoiding rate limits via smart rotation, and offering real-time health checks of the scraping infrastructure. Implementing this within your catalog of Openclaw Skills ensures a smooth, highly reliable gateway to web data aggregation.
Zyte API Web Scraping Use Cases
- Scraping highly dynamic, JavaScript-rendered single-page applications (SPAs) without configuring complex headless browser setups.
- Extracting e-commerce pricing, product catalogs, and reviews at scale with automatic proxy rotation to bypass geo-blocking or IP blocks.
- Monitoring web content, scheduled maintenance, and active service incidents of target sources or Zyte infrastructure.
- Bulk-processing data extraction across multiple target URLs using batch scraping modes directly from chat prompts.
How Zyte API Web Scraping Works
- Plugin Installation: Install the ClawLink plugin inside Openclaw using the CLI command to initialize connection flows.
- Device Pairing: Pair the OpenClaw agent with your ClawLink account securely through an approved device authorization process.
- Dashboard Connection: Access the ClawLink dashboard to link your Zyte API credentials once, storing them securely off-chat.
- Tool Discovery: Retrieve active tools via
clawlink_list_toolsto dynamically discover extraction, service health, and batch capabilities. - Execution and Extraction: Execute structured data queries using automated smart proxy routing and JS rendering, returning raw or structured website content securely.
Zyte API Web Scraping Setup
To get started with this plugin from the Openclaw Skills marketplace, run the following commands in your terminal:
openclaw plugins install clawhub:clawlink-plugin
openclaw config set tools.alsoAllow '["clawlink-plugin"]' --strict-json
openclaw gateway restart
Once restarted, run clawlink_begin_pairing to authorize the agent, then navigate to https://claw-link.dev/dashboard?add=zyte-api to link your Zyte credentials. Send /new to your chat to load the catalog.
Zyte API Web Scraping Data Schema & Taxonomy
The Zyte API integration organizes tools and data schemas into three core functional domains:
| Domain | Tools Included | Output Data Format |
|---|---|---|
| Extraction | zyte_api_extract, zyte_api_extract_batch, zyte_api_scrape |
JSON metadata containing raw HTML, structured elements, and redirected URLs |
| Service Health | zyte_api_get_status, zyte_api_list_incidents, zyte_api_list_maintenance |
Operational status objects and active incident arrays |
| Account Details | zyte_api_get_usage, zyte_api_get_account |
API usage statistics and quota consumption metrics |
Zyte API Web Scraping Advanced Features
- Automated Smart Proxy Rotation: Bypasses strict anti-scraping systems by dynamically rotating IPs through Zyte's industry-grade proxy network.
- Direct Headless Browser Rendering: Evaluates complex dynamic web elements on the fly using
browser_htmlparameters. - ClawLink Authentication Shield: Keeps sensitive API keys secure by injecting them server-side instead of exposing keys inside the chat environment.
- Batch Web Extraction: Aggregates massive target URL lists efficiently through the
zyte_api_extract_batchendpoint to optimize execution speed. - Safe State Preview Safeguards: Implements a write preview loop to prevent high-cost operations or accidental bulk calls before user confirmation.
SKILL.md
Loading
Related Openclaw Skills
WakaTime
Track developer productivity, analyze programming languages, and view daily coding statistics using this seamless WakaTime integration.
Webex Collaboration
A seamless integration that connects Webex with OpenClaw using ClawLink managed OAuth to send messages, manage spaces, configure webhooks, and coordinate teams.
Language Practice Skill
A structured, safe, and template-driven language learning skill designed to guide users through repeatable language practice workflows.
Life 101 Wisdom Companion
A digital philosophical mentor based on Peter McWilliams' Life 101, designed to deliver actionable wisdom on mindfulness, choice, and forgiveness.
YouTube Channel Management
An advanced integration skill enabling AI agents to manage YouTube channels, analyze performance metrics, moderate comments, and automate publishing workflows through the YouTube Data API v3.
Twitter Posts
A powerful integration enabling AI agents to draft, publish, search, and manage posts, timelines, and interactions on X (Twitter) using secure ClawLink OAuth authentication.
Featured*
