Pricing

Pay per usage

Go to Store

Crawl4AI

Try for free

Developed by

Jan Buchar

Wraps the Crawl4AI open-source library for retrieving text content from websites.

0.0 (0)

Pricing

Pay per usage

Total users

230

Monthly users

158

Runs succeeded

98%

Last modified

a month ago

Start URLs

startUrlsarrayRequired

URLs to start with

Maximum crawl depth

maxCrawlDepthintegerOptional

How many levels of links should the crawler follow. The Start URLs have a depth of 0, all links found there have a depth of 1, and so on.

Default value of this property is 2

Proxy configuration

proxyConfigurationobjectOptional

Select proxies to be used by your crawler.

Use magic mode

magicModebooleanOptional

Masks browser automation signals, Simulates human-like behavior, Overrides navigator properties, Handles cookie consent popups, Manages browser fingerprinting, Randomizes timing patterns

Default value of this property is true

Save screenshots

saveScreenshotsbooleanOptional

Should the crawler save screenshots?

Default value of this property is false

CSS selector

cssSelectorstringOptional

Ensures only a part of the website is processed

Wait for

waitForstringOptional

CSS selector or JS function to wait for before processing a page

Javascript code to execute on each page

jsCodestringOptional

Function executed for each request

Extraction strategy

extractionStrategyEnumOptional

Specifies how data is extracted from each page

Value options:

"llm": string"jsonCss": string"cosine": string

LLM provider

llmProviderstringOptional

Specifies the LLM used to extract data

API token

llmApiTokenstringOptional

Token used for authentication with the LLM provider

Instruction

llmInstructionstringOptional

Instructions (prompt) for the LLM

JsonCss schema

jsonCssSchemastringOptional

Description of the data to be extracted

Semantic filter

cosineSemanticFilterstringOptional

Specifies the semantic filter

Word count threshold

cosineWordCountThresholdintegerOptional

Specifies the word count threshold

Linkage method

cosineLinkageMethodstringOptional

Specifies the linkage method

Top K

cosineTopKintegerOptional

Specifies top K

Model name

cosineModelNamestringOptional

Specifies the model

Debug logging

debugLogbooleanOptional

Print debug-level log messages

Default value of this property is false

AI Web Scraper - Powered by Crawl4AI

raizen/ai-web-scraper

A blazing-fast AI web scraper powered by Crawl4AI. Perfect for LLMs, AI agents, AI automation, model training, sentiment analysis, and content generation. Supports deep crawling, multiple extraction strategies and flexible output (Markdown/JSON). Seamlessly integrates with Make.com, n8n, and Zapier.

Raizen Technology

Le Monde Scraper

david.lukac/le-monde-scraper

Scrape news data from lemonde.fr with this unofficial API. Extract articles, monitor their popularity and performance and automate the fight against fake news. Filter the results by authors, topics, categories, or publication dates. Preview or download the results in your preferred format.

David Lukáč

AP News Scraper

theo/ap-news-scraper

Scrape news data from apnews.com with this unofficial API. Extract articles, monitor their popularity and performance and automate the fight against fake news. Filter the results by authors, topics, categories, or publication dates. Preview or download the results in your preferred format.

Theo Vasilis

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

47.1k

Ulta Review Crawler

webscrapewizard/my-actor

WebScraperWizard

Example Website Screenshot Crawler

dz_omar/example-website-screenshot-crawler

Automated website screenshot crawler using Pyppeteer and Apify. This open-source actor captures screenshots from specified URLs, uploads them to the Apify Key-Value Store, and provides easy access to the results, making it ideal for monitoring website changes and archiving web content.

Abdlhakim hefaia

Scraper Api

zfcsoftware/scraper-api

This api allows you to scrape sites such as websites with rate limits, websites with protection such as Cloudflare. It is cheap and fast. It uses trusted proxies and works for most sites. The ip address used is not used again, a reliable ip is used for each request.