skills.rest
AgentComputerAI
AgentComputerAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

yelp

Scrape Yelp search pages via Chrome CDP to extract business listings.

5|Updated Apr 9, 2026
Search Tags:#search#puppeteer#scraping#cheerio#datadome#yelp#business listings
One-click install
npx skills add https://github.com/AgentComputerAI/torch --skill yelp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: yelp
Source: https://github.com/AgentComputerAI/torch/tree/main/skills/sites/yelp
Command: npx skills add https://github.com/AgentComputerAI/torch --skill yelp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extracting structured business data from Yelp search pages is blocked by DataDome anti‑bot defenses, making traditional HTTP requests fail.

Core Features & Use Cases

  • Connect to a real Chrome instance via CDP to inherit a trusted DataDome cookie.
  • Bypass DataDome without captcha solving or proxy.
  • Parse up to 24 pages of search results, extracting name, URL, rating, review count, neighborhood, status, categories, snippet, and photo.
  • Ideal for market research, competitor analysis, and local business listings aggregation.

Quick Start

Ask the yelp skill to scrape the Yelp search URL for pizza in New York.

Frequently Asked Questions about yelp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scrape Yelp search results when DataDome anti-bot protection blocks my requests?▼

Scraping Yelp search results blocked by DataDome requires connecting to a real Chrome instance via the Chrome DevTools Protocol to inherit a trusted DataDome cookie, bypassing defenses without captcha solving or proxies.

What business listing data fields can I extract from Yelp search pages?▼

Yelp search page scraping extracts structured business listing data including name, URL, rating, review count, neighborhood, status, categories, snippet, and photo for up to 24 pages of results.

How do I set up puppeteer-core to bypass DataDome on Yelp?▼

To bypass DataDome on Yelp, launch a live Chrome instance reachable via CDP at http://127.0.0.1:9222, then use puppeteer-core with cheerio to connect, parse, and extract the search results.

Does Yelp scraping with a real Chrome instance require proxies or captcha solving?▼

Yelp scraping via a real Chrome instance uses puppeteer-core to inherit an existing trusted DataDome cookie, bypassing anti-bot protection without requiring proxies or captcha solving services.

What's the best way to aggregate local business listings from Yelp for market research?▼

Aggregating local business listings from Yelp for market research involves scraping up to 24 pages of search results to extract names, ratings, review counts, and categories while bypassing anti-bot defenses via real Chrome.

Why do traditional HTTP requests fail when scraping Yelp business listings?▼

Traditional HTTP requests fail scraping Yelp business listings because DataDome anti-bot defenses block them, requiring a real Chrome instance via CDP to inherit a trusted cookie for successful data extraction.

Related Skills

Explore More Data & Analytics Skills→
AgentComputerAIAgentComputerAI
5

booking

Scrape Booking.com hotel listings and prices via a Chrome debugger connection.

Official
Advanced
cryptopaficryptopafi

apify-market-research

Extract structured listings, reviews, pricing, and contact data using Apify Actors.

Community
Intermediate
AgentComputerAIAgentComputerAI
5

stackoverflow

Scrape StackOverflow tag pages with Puppeteer and Cheerio.

Official
Advanced
pynbj1001pynbj1001
2

scrapling-official

Scrapes JavaScript-rendered and anti-bot protected websites using adaptive parsing and stealth browser automation.

Community
Advanced