Yellow Pages Business Scraper

Extract comprehensive business listings from Yellow Pages including contact information, ratings, reviews, categories, and location data. Get phone numbers, addresses, websites, business hours, and customer ratings from the largest US business directory.

AI-Ready Output: Every result includes structured fields optimized for LLM prompts, vector databases, and RAG pipelines — feed directly into ChatGPT, Claude, or your AI workflow.

What data do you get from Yellow Pages?

Yellow Pages Business Scraper returns complete business directory data organized into structured fields:

Field Group	What's Included
Identity	Business name, profile URL
Contact Info	Phone number, email address, website
Location	Street address, city, state, ZIP code, latitude/longitude coordinates
Reputation	Star rating (0-5), review count
Categories	Business categories and classifications
Operations	Opening hours, years in business
AI-Ready Output	llm_context (markdown for LLM prompts), ai_summary (natural language brief), searchable_text (dense text for vector DB/RAG), data_quality score (0-100)

How to use Yellow Pages Business Scraper

1. Open Yellow Pages Business Scraper on Apify
2. Enter a business category (e.g., "roofing contractors", "plumbers", "dentists")
3. Enter a location (e.g., "Dallas, TX" or "dallas-tx")
4. Set max pages (30 businesses per page)
5. Configure residential proxies (required for reliable access)
6. Click Start and download results in JSON, CSV, or Excel

Input

| Parameter | Type | Required | Description | |---|---|---| | query | string | Yes | Business category or name (e.g., "roofing contractors", "plumbers", "dentists") | | location | string | Yes | City and state (e.g., "Dallas, TX" or "dallas-tx") | | maxPages | integer | No | Number of search pages to scrape (30 businesses per page, default: 1) | | proxyConfiguration | object | Yes | Residential proxies required for access |

Example input

{
    "query": "roofing contractors",
    "location": "Dallas, TX",
    "maxPages": 2,
    "proxyConfiguration": {
        "useApifyProxy": true,
        "apifyProxyGroups": ["RESIDENTIAL"]
    }
}

Example output

{
    "url": "https://www.yellowpages.com/dallas-tx/mip/abc-roofing-123456",
    "name": "ABC Roofing Contractors",
    "phone": "(214) 555-0123",
    "email": "info@abcroofing.com",
    "address": "123 Main St",
    "city": "Dallas",
    "state": "TX",
    "zip": "75201",
    "full_address": "123 Main St, Dallas, TX, 75201",
    "website": "https://abcroofing.com",
    "rating": 4.8,
    "review_count": 127,
    "categories": ["Roofing Contractors", "Roof Repair"],
    "years_in_business": 15,
    "description": "Professional roofing services...",
    "hours": ["Mo-Fr 08:00-17:00", "Sa 09:00-15:00"],
    "latitude": 32.7767,
    "longitude": -96.7970,
    "llm_context": "# ABC Roofing Contractors\nPhone: (214) 555-0123\nAddress: 123 Main St, Dallas, TX, 75201\nWebsite: https://abcroofing.com\nRating: 4.8/5 (127 reviews)...",
    "ai_summary": "ABC Roofing Contractors in Dallas, TX has a 4.8/5 star rating from 127 reviews.",
    "searchable_text": "ABC Roofing Contractors Roofing Contractors Roof Repair Dallas TX Professional roofing services...",
    "data_quality": 95
}

Use cases

• B2B lead generation — Build targeted contact lists with phone numbers, emails, and websites for sales outreach
• Market research — Analyze business density, category distribution, and competitive landscapes by location
• Data enrichment — Add verified contact information and location data to existing business records
• Competitor analysis — Track businesses in your industry with ratings, review counts, and contact details
• Directory building — Create curated business directories with complete, verified information
• AI workflows — Feed structured business data into ChatGPT, Claude, or RAG pipelines using AI-ready output fields

Output format

Results can be exported in JSON, CSV, Excel, XML, or accessed programmatically via the Apify API.

AI-ready fields

Every result includes fields designed for AI, LLM, and RAG workflows:

Field	Format	Purpose
llm_context	Markdown	Structured business summary for LLM prompts — includes name, contact info, rating, categories, and description
ai_summary	Plain text	Natural language 1-2 sentence summary for embeddings and search snippets
searchable_text	Dense plain text	Combined searchable content for vector databases and full-text search
data_quality	Integer (0-100)	Completeness score based on key fields (name, phone, address, website, rating, categories)

Proxy requirements

Yellow Pages requires residential proxies to bypass anti-bot protection. Without proxies, requests will be blocked immediately.

On Apify: Select "Residential proxies" in proxy configuration when starting the actor.

FAQ

How to get data from Yellow Pages?

Yellow Pages Business Scraper collects publicly available business listings from YellowPages.com. Enter a business category and location — the tool returns structured data for every matching business including contact information, ratings, and location details.

What data can you extract from Yellow Pages?

Yellow Pages Business Scraper extracts complete business profiles: name, phone, email, website, full address with coordinates, star ratings, review counts, business categories, operating hours, and years in business. Every field is structured and ready for analysis or AI workflows.

Why are residential proxies required?

Yellow Pages uses anti-bot protection that blocks datacenter IPs. Residential proxies are required for reliable access. Configure residential proxies in the Apify proxy settings.

How many businesses can I collect per run?

Each search page returns approximately 30 businesses. With multiple pages configured, you can collect hundreds of businesses per run. For larger datasets, run multiple searches across different categories or locations.

Can I use Yellow Pages data with ChatGPT or other LLMs?

Yes. Every result includes AI-ready fields: llm_context (structured markdown), ai_summary (natural language brief), searchable_text (dense text for vector DBs), and data_quality (completeness score). Feed directly into ChatGPT, Claude, or any RAG pipeline without additional processing.

Limitations

• Data is limited to what is publicly available on YellowPages.com
• Residential proxies are required for access (included in Apify proxy configuration)
• Results vary by search query and location availability
• Some business fields may be incomplete depending on listing quality

Other business data tools

Looking for business data from other sources? Check out our other data collection tools on the Apify Store.