google-maps-contact-extract
Extracts business contact details from Google Maps search results and place detail pages, then visits each business website to collect emails, phone numbers, and social media profiles (Facebook, Instagram, Twitter/X, LinkedIn, YouTube, TikTok, Pinterest, Discord)
Install / Use
npx skills add browser-act/skills --skill google-maps-contact-extractInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
CommunicationSupported Platforms
Our assessment of google-maps-contact-extract
google-maps-contact-extract scores 95/100 on our quality scale, 54th of 394 Communication skills we index (top 14%).
Its SKILL.md is 11 KB long, well organised into 16 sections with 9 code examples: a thorough specification that gives an agent plenty to work with.
With 6,001 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 3 months ago, so google-maps-contact-extract is actively maintained.
- Our last check on 2026-11-15 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-03. Automated pattern scan on 2026-10-02. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
google-maps-contact-extract compared with similar skills
All 4 of these similar skills score higher than google-maps-contact-extract; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| google-maps-contact-extract (this skill)by browser-act | 95 | 6.0k | 3mo ago | SKILL.md |
| Scraplingby D4Vinci | 100 | 103.6k | 2d ago | MCP Server |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
Frequently asked questions
- How do I install google-maps-contact-extract?
- Run
npx skills add browser-act/skills --skill google-maps-contact-extract. The install tabs above show the steps for each supported agent. - Which AI agents does google-maps-contact-extract work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is google-maps-contact-extract safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is google-maps-contact-extract still maintained?
- The repository was last updated about 3 months ago, so google-maps-contact-extract is actively maintained.
Skill content
View source on GitHubname: google-maps-contact-extract description: "Extracts business contact details from Google Maps search results and place detail pages, then visits each business website to collect emails, phone numbers, and social media profiles (Facebook, Instagram, Twitter/X, LinkedIn, YouTube, TikTok, Pinterest, Discord). Use when user mentions Google Maps contact extraction, maps email scraper, business lead generation from Google Maps, find emails from maps, scrape Google Maps businesses, maps business contacts, get phone from Google Maps, social media from maps listing, competitor research from maps, local business contact list, maps data export, google maps scraper, extract contacts from google maps, find business email google, gmaps leads, maps email finder, or wants to replicate Google Maps business data extraction."
Google Maps — Contact Extractor
keyword + location → business list with name/address/phone/website + email/social media/contacts from each business's website
Language
All process output to user (progress updates, process notifications) follows the user's language.
Objective
Search Google Maps by keyword and location, collect place details from each result, visit each business's website to extract emails and social media profiles, and return a merged dataset replicating Google Maps Email Extractor functionality.
Prerequisites
- For search: navigate to
https://www.google.com/maps/search/{keyword}/@{lat},{lng},{zoom}z— the search results sidebar (feed) must be visible - For place detail: navigate to the individual place URL
https://www.google.com/maps/place/?q=place_id:{place_id}— the place sidebar with name, address, phone must be visible - For website contact extraction: navigate to the business's website homepage
- No login required for Google Maps or most business websites
Pre-execution Checks
1. Tool Readiness
If browser-act has been confirmed available in the current session → skip this step.
Invoke browser-act via Skill tool to load usage. If installation or configuration issues arise, follow its guidance to resolve then retry.
Capability Components
This Skill's operational boundary = what the user can manually do in their browser. It only reads data already displayed to the user on the page, never bypassing authentication or access controls. JS code is encapsulated in Python files under the
scripts/directory, invoked viaeval "$(python scripts/xxx.py {params})". It is recommended to use the bash tool for execution. Working directory: allpython scripts/commands must be run from the Skill's root directory (the directory containingSKILL.mdandscripts/). Usecd {skill-directory}before running batch scripts, or use absolute paths:python {absolute-path-to-scripts}/xxx.py.
DOM: Search results list — extract business cards from Google Maps search feed
Prerequisite: navigate to and wait for Google Maps search results to load, then extract all visible business cards.
navigate https://www.google.com/maps/search/{keyword}/@{lat},{lng},{zoom}z
wait stable
eval "$(python scripts/search-places.py '{keyword}' --max {max_count})"
Parameters:
{keyword}: search term, e.g.coffee shops--max: maximum number of places to extract, default20{lat},{lng}: center coordinates, e.g.40.7580,-73.9855{zoom}: zoom level, e.g.14
Output example:
{
"keyword": "coffee shops",
"count": 20,
"places": [
{
"name": "Blue Dove Coffee",
"rating": 4.8,
"review_count": "292",
"category": "Coffee shop",
"price_range": null,
"phone": null,
"open_status": "Closed · Opens 7 AM",
"place_id": "0xa5922b78cc420fb1:0x535506dc9cdb2cec",
"lat": 40.7368708,
"lng": -73.9909297,
"maps_url": "https://www.google.com/maps/place/Blue+Dove+Coffee/data=..."
}
]
}
Pagination: Google Maps loads ~20 results per view. Scroll down in the results panel to trigger loading of additional results, then re-run the extraction script. Repeat until desired count is reached.
scroll down --amount 3000
wait stable
eval "$(python scripts/search-places.py '{keyword}' --max {total_count})"
DOM: Place detail — extract full business info from a Google Maps place page
Prerequisite: navigate to the place page and wait for the sidebar to load with name, address, and phone visible.
navigate https://www.google.com/maps/place/?q=place_id:{place_id}
wait stable
wait --selector "h1" --state visible --timeout 15000
eval "$(python scripts/place-detail.py)"
Alternatively, navigate directly using the maps_url returned from the search results component.
Output example:
{
"place_id": "0xa5922b78cc420fb1:0x535506dc9cdb2cec",
"name": "Blue Dove Coffee",
"rating": 4.8,
"review_count": 292,
"category": "Coffee shop",
"address": "33 Union Square W, New York, NY 10003",
"located_in": null,
"phone": "(646) 939-0937",
"website": "https://www.bluedovecoffee.com/",
"menu_url": "https://order.dripos.com/Blue-Dove-Coffee",
"price_range": "$1–10",
"coordinates": { "lat": 40.7368708, "lng": -73.9909297 },
"hours": [
"Monday7 AM–5 PM",
"Tuesday7 AM–5 PM",
"Wednesday7 AM–5 PM",
"Thursday7 AM–5 PM",
"Friday7 AM–5 PM",
"Saturday7 AM–5 PM",
"Sunday7 AM–4 PM"
],
"service_options": ["Serves dine-in", "Offers takeout", "Offers delivery"],
"amenities": ["Has wheelchair accessible entrance", "Accepts credit cards", "Accepts NFC mobile payments"],
"maps_url": "https://www.google.com/maps/place/..."
}
DOM: Website contacts — extract emails, phones, social media from a business website
Prerequisite: navigate to the business website homepage.
navigate {website_url}
wait stable
eval "$(python scripts/extract-contacts.py --depth shallow)"
For deeper extraction (also scans contact/about subpages), use --depth deep. After running with --depth deep, check contact_subpages in the output, then navigate to each and re-run:
navigate {subpage_url}
wait stable
eval "$(python scripts/extract-contacts.py --depth shallow)"
Parameters:
--depth:shallow(homepage only, default) ordeep(also discovers and lists contact/about subpage URLs)
Output example:
{
"source_url": "https://www.bluedovecoffee.com/",
"emails": ["support@bluedovecoffee.com", "careers@bluedovecoffee.com", "orders@bluedovecoffee.com"],
"phone_numbers": [],
"social_media": {
"facebook": ["https://www.facebook.com/people/Blue-Dove-Coffee/100094867009022"],
"instagram": ["https://www.instagram.com/bluedovecoffee"],
"tiktok": ["https://www.tiktok.com/@bluedovecoffee"]
},
"contact_subpages": []
}
Composite: Full pipeline — search + place details + website contacts
Complete flow replicating Google Maps Email Extractor:
-
Navigate to Google Maps search:
navigate https://www.google.com/maps/search/{keyword}/@{lat},{lng},{zoom}z wait stable eval "$(python scripts/search-places.py '{keyword}' --max {max_count})"Save list of places (especially
name,maps_url,place_id). -
For each place: navigate to place detail page and extract full info:
navigate {maps_url} wait stable wait --selector "h1" --state visible --timeout 15000 eval "$(python scripts/place-detail.py)"Collect
website,phone,address,hours,rating, etc. -
For each place with a
websitevalue: extract contacts from the website:navigate {website} wait stable eval "$(python scripts/extract-contacts.py --depth deep)"For each URL in
contact_subpages, navigate and extract again to find additional emails. -
Merge results: join by
place_idorname. Final record per business:{ "name": "Blue Dove Coffee", "address": "33 Union Square W, New York, NY 10003", "phone": "(646) 939-0937", "website": "https://www.bluedovecoffee.com/", "rating": 4.8, "review_count": 292, "category": "Coffee shop", "coordinates": { "lat": 40.7368708, "lng": -73.9909297 }, "hours": ["Monday7 AM–5 PM", "..."], "service_options": ["Serves dine-in", "Offers takeout"], "emails": ["support@bluedovecoffee.com"], "social_media": { "instagram": ["https://www.instagram.com/bluedovecoffee"], "tiktok": ["https://www.tiktok.com/@bluedovecoffee"] } }
Pagination
DOM Pagination: Google Maps search loads ~20 results initially. Scroll down in the sidebar:
scroll down --amount 3000
wait stable
eval "$(python scripts/search-places.py '{keyword}' --max {total_count})"
Repeat until the desired number of results is reached. Termination: Google Maps typically shows up to ~120 results per search; the sidebar will show "You've reached the end of the results" or stop loading new items.
Success Criteria
places.count >= 1from search results extraction- Place detail returns
name != null AND (address != null OR phone != null) - Website contact extraction returns
emails.length + phone_numbers.length + Object.keys(social_media).length >= 0(no contacts = valid result for businesses without public contact info)
Known Limitations
- Google Maps search results are limited to approximately 120 businesses per search query; to get more, use more specific sub-area searches
- Phone numbers on the Google Maps search list card are not always shown;
place-detail.pyon the individual place page is more reliable - Website contact extraction depends on the business's website structure; sites using image-based emails or obfuscated text will return no emails
- Some businesses do not have a website listed on Google Maps; those cannot be enriched with contact data
- Google Maps may throttle requests if too many place pages are navigated in rapid succession; add 1–2 second delays between place navigations in batch scripts
Execution Efficiency
- Batch orchestration: Write a bash script that loops through the pipeline steps in a single session. Add a 1–2 second sleep between each place detail navigation to avoid triggering anti-scraping. Example:
for place_url in "${place_urls[@]}"; do browser-act --session gmaps-s1 navigate "$place_url" browser-act --session gmaps-s1 wait stable browser-act --session gmaps-s1 eval "$(python scripts/place-detail.py)" sleep 1.5 done - Test before batch execution: Test with 2–3 places before running the full batch
- Error resumption: Save each place's result to a JSON file immediately after extraction; on failure, skip already-saved places by checking if the file exists
- Multiple sessions for throughput: Open 2–3 parallel stealth browser sessions and distribute places across them; each session has an independent fingerprint
Experience Notes
Path: {working-directory}/browser-act-skill-forge-memories/google-maps-contact-extract.memory.md
Before execution: If the file exists, read it first — it records unexpected situations encountered during past executions (e.g., a strategy has become ineffective); adjust strategy order accordingly.
After execution: If an unexpected situation is encountered (strategy became ineffective, page redesigned, anti-scraping upgraded, better path discovered), append a line:
{YYYY-MM-DD}: {what happened} → {conclusion}
Normal execution does not write to the file.
Related Skills
Scrapling
103.6k🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
