find-emails
Crawl websites locally with crawl4ai to extract contact emails. Accepts multiple URLs and outputs domain-grouped results for clear attribution. Uses deep crawling with URL filters (contact, about, support) to find emails on relevant pages. Use when extracting emails from websites, finding contact information, or crawling for email addresses.
Why use this skill?
Use the find-emails skill for OpenClaw to crawl websites, discover contact information, and extract emails into structured JSON or text files.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/lukem121/find-emailsWhat This Skill Does
The find-emails skill is a powerful automation tool designed to extract contact information from websites with precision. Leveraging the crawl4ai library, it performs deep local crawls of target domains, intelligently filtering for relevant pages such as 'contact', 'about', and 'support' to maximize the discovery of email addresses. The skill simplifies data gathering by grouping extracted emails by their domain and providing clear attribution for where each address was found. It supports both raw console output for quick checks and structured JSON output for integration into larger AI-driven workflows.
Installation
To begin using this skill, ensure you have the OpenClaw environment configured. Install the necessary dependencies by running the following command in your terminal:
pip install crawl4ai
Once the environment is prepared, you can add the skill to your agent's library using the ClawHub CLI:
clawhub install openclaw/skills/skills/lukem121/find-emails
After installation, you can verify the setup by running the help command for the script to ensure all dependencies are resolved correctly.
Use Cases
This skill is ideal for lead generation, market research, and automated administrative tasks. Use it when:
- You need to build a contact list for a list of potential B2B partners.
- You are auditing your own website to ensure contact links are correctly identified.
- You are performing automated site reconnaissance to identify support channels for specific domains.
- You need to aggregate public-facing contact information across large batches of URLs efficiently.
Example Prompts
- "Find all contact emails for https://openai.com and https://anthropic.com and save the results to a file named leads.json."
- "Crawl the website https://tech-startup.io to find support and inquiry email addresses using a max depth of 3."
- "Extract emails from the provided local markdown documentation file and format the output as JSON."
Tips & Limitations
- Efficiency: The tool uses a configurable URL pattern list (
scripts/url_patterns.json). If you aren't finding results, check if your target site uses unconventional naming for its contact pages and add those to the patterns. - Depth/Pages: Be mindful of the
--max-depthand--max-pagesflags to avoid excessive resource usage when crawling large websites. - Limitations: The tool relies on crawl4ai's capability to render content; heavily obfuscated websites or those behind aggressive CAPTCHAs may not yield results. It is best suited for standard business websites and documentation portals.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-lukem121-find-emails": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read