Skip to content

Free, open-source Google Maps scraper for lead generation (Python, no API key, no Docker). Exports name, phone, email, website, rating and Instagram/Facebook/LinkedIn/TikTok/YouTube/X links to CSV. 100 places with emails in 44 s; --grid beats Google's 120 cap. MX email check, ad-pixel detection. Skill for Claude Code, Codex and Cursor.

3.6 KB
Raw Blame

Scrape Google Maps leads with Claude Code

The Google Maps Scraper Kit lets you scrape Google Maps leads with Claude Code by asking in plain English, and get back a clean table plus a CSV. It is free and runs locally: the agent drives the kit's own scraping engine on your machine, with no API key and no SaaS credits.

Set it up

Install Python 3.9 or newer and Google Chrome (or Chromium, Edge or Brave), then pick one option. Docker Desktop works too, instead of the local Chrome.

Option A: open the kit folder in Claude Code. The skill and four slash commands load automatically.

git clone https://github.com/Mahanaicoach/google-maps-scraper-kit.git
cd google-maps-scraper-kit
claude

Option B: install the skill into an agent you already use.

npx skills add mahanaicoach/google-maps-scraper-kit

The skill works with Claude Code, Codex, Cursor and any other Agent Skills-compatible tool. The slash commands are Claude Code only. The engine ships with the kit, so the agent still needs the kit folder to start it.

Ask in plain language

Scrape gyms in Miami and give me phones, emails and websites.

Or use a slash command in Claude Code:

Slash command Action
/scrape <business> in <city, ST> [depth] Run one scrape, return a clean table and CSV
/scrape-batch <keywords-file> [--city "City, ST"] Run many queries as one job
/scrape-setup Start the engine and run a health check
/scrape-jobs [list | delete <id>] List or delete jobs

What the agent does

  1. Runs python3 scripts/engine.py status, which prints the engine's URL (localhost:8080 unless you changed SCRAPER_PORT) only when the kit's own engine answers, and starts it with python3 scripts/engine.py start (or docker compose up -d if you run Docker) if it is down.
  2. Runs python3 scripts/scrape.py "<business type> in <City, ST>" --city "<City, ST>" as a background command. The script geocodes the city, creates the job, waits for it and collects its rows, with emails and social profiles on by default. It skips the social profiles only if you say you do not want them.
  3. Keeps the 8 lead fields (name, phone, email, website, category, address, rating and review count), then the six social columns: Instagram, Facebook, LinkedIn, TikTok, YouTube and X.
  4. Saves the file, then presents a short table and the CSV path instead of dumping every row into chat.

The kit's own scripts, the exact docker compose forms SETUP.md uses are pre-approved in .claude/settings.json; everything else asks as usual.

Example output

Illustrative rows only:

title phone emails website category
Example Fitness Club +1 305-555-0101 [email protected] example.com Gym
Sample Strength Studio +1 305-555-0102 [email protected] example.org Gym
Demo Boxing Gym +1 305-555-0103 example.net Boxing gym

What to expect

  • Google Maps returns about 120 listings per search. Ask for the whole city and the agent runs --grid 3, which splits it into 9 tiles and dedupes the results.
  • Emails come back only when a business publishes one on its website. Expect some empty cells.
  • For large jobs, the agent prints one short warning about temporary IP rate limits and suggests proxies, then proceeds.
  • The skill scrapes Google Maps business listings only. It does not scrape social platforms directly.
  • Scraping Google Maps is against Google's Terms of Service, so read Responsible use before outreach.

Related