google-image-crawler

Extract original image URLs from Google Image search results using Playwright.

1|Updated Jan 30, 2026

Search Tags:#Playwright #web scraping #download #asynchronous #crawl #Google Images #image URL extraction

Ready to run

npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill google-image-crawler

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: google-image-crawler
Source: https://github.com/xdrshjr/JR-Agent-Skills/tree/main/google-images-crawler
Command: npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill google-image-crawler

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the discovery of high-quality image URLs from Google Image search, enabling rapid data collection without manual scraping.

Core Features & Use Cases

Automated image discovery: searches Google Images, scrolls to load more results, and returns original image URLs ready for download.
Flexible workflows: suitable for dataset building, design asset sourcing, or competitive research requiring batch URL extraction.
Use Case: quickly assemble a list of original image URLs for a design dataset or training data procurement.

Quick Start

To start crawling, run the script with a keyword, e.g. python crawl.py -k "cats" -c 10 and inspect the resulting JSON array containing fields like url, thumbnail_url, source_url, title, width and height.

Frequently Asked Questions about google-image-crawler

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

FAQPage Schema

How do I extract original image URLs from Google Image search results?▼

You can extract original image URLs from Google Image search results by running a Playwright-based crawler script with a target keyword. It automates browser scrolling to load more results and returns a JSON array containing fields like url, source_url, width, and height for batch collection.

Can I use Playwright to scrape Google Images asynchronously for a dataset?▼

Yes, you can use Playwright to scrape Google Images asynchronously for dataset building. The crawler requires installing Python dependencies and running playwright install chromium, supporting keyword-driven searches with optional page scrolling to fetch original image URLs.

How do I download images from Google search using a Python script?▼

To download images from Google search using a Python script, execute the crawler with a keyword and count argument, such as python crawl.py -k "cats" -c 10. This returns a JSON array of original image URLs, thumbnail URLs, and metadata ready for batch downloading.

Does this Google Images crawler require a specific browser environment?▼

Yes, the Google Images crawler requires a specific browser environment. You must install Python dependencies and execute playwright install chromium to set up the required Chromium browser before running the asynchronous web scraping script.

What is the best way to collect bulk image URLs for design asset sourcing?▼

The best way to collect bulk image URLs for design asset sourcing is using an automated Playwright crawler. It performs keyword-driven searches on Google Images, scrolls to load additional results, and outputs a JSON array of original image URLs with associated metadata like title and dimensions.

What limitations should I expect when crawling Google Images for original URLs?▼

When crawling Google Images for original URLs, expect limitations related to basic filtering and page scrolling dependencies. The crawler relies on Playwright and a Chromium browser, meaning execution requires a suitable environment and may face constraints from dynamic search result loading.