Pricing

Pay per usage

Go to Store

Website Content Crawler

Try for free

Developed by

Apify

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.

3.7 (41)

Pricing

Pay per usage

1501

Total users

58K

Monthly users

8.1K

Runs succeeded

>99%

Issues response

7.6 days

Last modified

3 hours ago

Developer tools

Back to issues Create new issue

Feature Request: Automatic Recrawling Within Same Task Run for RAG System Integration

Closed

sprouto_net opened this issue

I'm currently utilizing the Website Content Crawler in my Retrieval-Augmented Generation (RAG) system to extract and process website content. My objective is to automatically recrawl pages after fix duration of time like 30 days, all within the same task run, to ensure my system remains up-to-date with the latest information. Could you please advise if such a feature is currently supported or if there are recommended approaches to achieve this functionality? If not, I would like to suggest this as a feature request for future development.

Jakub Kopecký (jakub.kopecky)

Hi,

Thank you for using Website Content Crawler!

For your use case, you can use Apify Schedules (https://docs.apify.com/platform/schedules) to schedule monthly task runs. Additionally, you can set up a webhook integration in the task (https://docs.apify.com/platform/integrations) to receive notifications when the task completes, and then retrieve the results.

Let me know if this works for you,

Jakub

Jiří Spilka (jiri.spilka)

I'll go ahead and close this issue for now, but let me add information about Apify's vector database support.

To support automatic content updates in vector databases like Pinecone, Apify provides a dedicated integration: 👉 Pinecone Integration

This integration automates the transfer of datasets (e.g., from Website Content Crawler) into Pinecone — or other supported vector DBs — with options for:

Chunking long text for embedding
Custom metadata mapping
Delta updates (only changed/new records)
Efficient document identification using url or other fields

After a crawl, you get a dataset like:

{
  "url": "https://example.com",
  "text": "...long page content...",
  "metadata": { "title": "Example Page" }
}

Then configure the integration like this:

{
  "datasetFields": ["text"],
  "metadataDatasetFields": {"title": "metadata.title"},
  "performChunking": true,
  "chunkSize": 1000,
  "chunkOverlap": 0,
  "dataUpdatesStrategy": "deltaUpdates",
  "dataUpdatePrimaryDatasetFields": ["url"],
  "usePineconeIdPrefix": true
}

This ensures:

Only updated content is re-indexed
Records are uniquely identified (e.g., by URL)
No duplicates or wasteful reprocessing

Besides Pinecone, Apify also supports similar integrations with: Qdrant, Milvus, PGVector and other database

You can find these in the Apify Store.

Add comment

Fast Website Content Crawler

6sigmag/fast-website-content-crawler

A high-performance web scraper that rapidly extracts and analyzes content from multiple websites simultaneously. Perfect for competitive research, content aggregation, and website structure analysis.

David Deng

1.1K

4.4

AI Website Content Markdown Scraper

quaking_pail/ai-website-content-markdown-scraper

This Apify Actor, "Website Content Crawler with Markdown Extraction," is designed to perform a comprehensive crawl of specified websites, extract their text content, convert it into Markdown format, and store it in a structured dataset. The extracted content is suitable for feeding LLMs.

AI_Builder

585

3.8

Website Content to Markdown for LLM Training

easyapi/website-content-to-markdown-for-llm-training

🚀 Transform web content into clean, LLM-ready Markdown! 📘 Scrape multiple pages, extract main content, and convert to Markdown format. Perfect for AI researchers, data scientists, and LLM developers. Fast, efficient, and customizable. Supercharge your AI training data today! 🌐📝🧠

EasyApi

5.0

🔥 FireScrape AI Website Content Markdown Scraper

mohamedgb00714/fireScraper-AI-Website-Content-Markdown-Scraper

Advanced web scraper powered by Crawlee and Puppeteer — extracts website content, converts it to Markdown, and structures it for LLM training datasets.

mohamed el hadi msaid

5.0

Extract-any-webpage-content-for-llm

ai-developer/extract-any-webpage-content-for-llm

Fast and easy way to extract data from any webpage and are LLM friendly. The tool lets you easily extract content from any website. Ideal for researchers, marketers, and developers.

aideveloper

471

AI-Powered Web Content & Link Extractor

scrapercoder/ai-powered-web-content-link-extractor

Crawls websites to extract clean, structured content for AI/LLM use, ideal for training datasets, knowledge bases, and RAG systems. Json output includes: * text: Normalized page content * links: Extracted sub-URLs

wallnut.ai

Deep Website Content Crawler

6sigmag/deep-website-content-crawler

Scrape Failed Killer! A high-performance web scraper that rapidly extracts and analyzes content from multiple websites simultaneously. Perfect for competitive research, content aggregation, and website structure analysis.

David Deng

412

4.1

RAG Web Browser

apify/rag-web-browser

Web browser for OpenAI Assistants, RAG pipelines, or AI agents, similar to a web browser in ChatGPT. It queries Google Search, scrapes the top N pages, and returns their content as Markdown for further processing by an LLM. It can also scrape individual URLs. Supports Model Context Protocol (MCP).

Apify

3.6K

4.3

Article Content Extractor 📄

easyapi/article-content-extractor

Extract clean article content, metadata and structured information from any web page. Supports multiple URLs and returns well-formatted JSON with title, description, content, author, publish date and more. 🔍📄

EasyApi

Dynamic Markdown Scraper

louisdeconinck/dynamic-markdown-scraper

Effortlessly feed LLM AIs with clean Markdown using our advanced web scraper. Seamlessly scrape dynamic, JavaScript-rendered websites while preserving original formatting. Ideal for AI training, documentation, and content migration.