We’re excited to announce a powerful new feature in Revise that makes content creation even more effortless: URL Fetching. Now you can ask Revise to fetch, analyze, and incorporate content from any URL directly into your WordPress posts—all with a simple conversational prompt.
What Is URL Fetching?
URL Fetching allows Revise to access external web pages, extract their content, and use that information to help you create, enhance, or research your WordPress content. It’s like having a research assistant built right into your editor.
How It Works
The magic happens through natural conversation. Simply include a URL in your prompt, and Revise handles the rest:
"Can you summarize https://example.com/article and incorporate it into an article?"Behind the scenes:
- Revise recognizes the URL in your request
- Safely fetches the content from the web
- Processes and cleans the HTML into readable text
- Analyzes the content using AI
- Creates or updates your WordPress blocks with the result
Real-World Use Cases
📰 Content Curation
Transform external articles into your own unique content:
"Fetch https://techcrunch.com/article/latest-ai-news and write a blog post
with my perspective on these developments"📊 Research Compilation
Gather information from multiple sources:
"Read https://wikipedia.org/wiki/Machine_Learning and create an
introductory guide for beginners"🔄 Content Repurposing
Turn web content into different formats:
"Summarize https://example.com/long-report and create 5 social media
posts highlighting the key points"💡 Idea Generation
Get inspired by existing content:
"Analyze https://competitor.com/blog-post and suggest 3 related article
ideas I could write about"📝 Fact-Checking & References
Incorporate accurate information from authoritative sources:
"Fetch https://research-paper.edu/study and summarize the key findings
in my article about health trends"Security First
We built URL Fetching with security as a top priority:
🛡️ Protection Against Malicious URLs
- Private IP blocking prevents access to internal networks
- Protocol validation only allows HTTP and HTTPS
- SSRF protection blocks attempts to access local resources
⚡ Performance Safeguards
- 5MB download limit prevents excessive bandwidth usage
- 30-second timeout ensures requests don’t hang indefinitely
- 50,000 character limit on processed text keeps responses manageable
🧹 Content Sanitization
- Script removal strips all JavaScript from fetched pages
- Style cleanup removes CSS and formatting noise
- HTML parsing converts messy markup into clean, readable text
How to Use URL Fetching
Using this feature is as simple as having a conversation:
Basic Syntax
Just include a URL in any Revise chat prompt:
"Summarize https://example.com for me"Advanced Requests
Be specific about what you want:
"Fetch https://news-site.com/article-123, extract the main points,
and write a 500-word response article with my counterarguments"Multiple Operations
Combine URL fetching with other Revise capabilities:
"Read https://research.org/paper.pdf and update my Introduction block
to include these statistics"Works With Major LLM Providers
Whether you prefer Claude (Anthropic), GPT-4 (OpenAI), or Gemini (Google), URL Fetching works seamlessly across all supported providers. Your AI assistant of choice can now access the entire web to help you create better content.
Technical Deep Dive
For the technically curious, here’s how it works under the hood:
- Marker Detection: When the LLM recognizes a URL request, it outputs a special
---FETCH_URL---marker with JSON instructions - URL Validation: Our server validates the URL for security issues
- Content Retrieval: WordPress’s HTTP API safely fetches the content
- HTML Processing: Content is converted from HTML to clean markdown-style text
- Context Augmentation: The fetched content is added to the conversation context
- AI Processing: The LLM processes both your original request and the fetched content
- Block Operations: Results are formatted as WordPress block operations
All of this happens transparently in seconds, giving you a seamless experience.
Privacy & Ethics
What We Don’t Do
- ❌ We don’t store fetched content
- ❌ We don’t cache external pages
- ❌ We don’t share your requests with third parties
- ❌ We don’t bypass paywalls or authentication
What We Encourage
- ✅ Always respect copyright and fair use guidelines
- ✅ Add your own analysis and perspective
- ✅ Cite sources when using external content
- ✅ Create transformative, original work
Examples to Try Right Now
Copy and paste these prompts into Revise:
Quick Summaries
"Summarize the key points from https://wikipedia.org/wiki/Artificial_intelligence"Content Creation
"Fetch https://github.com/trending and write a blog post about the top 5
trending repositories this week"Comparison Articles
"Read https://product-a.com/features and https://product-b.com/features,
then create a comparison table"News Aggregation
"Get the latest from https://news.ycombinator.com and write a tech news
roundup with my commentary"What’s Next?
URL Fetching is just the beginning. We’re exploring additional capabilities like:
- 📄 PDF fetching for academic papers and reports
- 🔐 Authenticated requests for content behind logins (with your credentials)
- 🌐 Multi-URL fetching to aggregate content from multiple sources
- 🖼️ Image extraction to pull relevant visuals from web pages
Get Started Today
URL Fetching is available now in Revise for all users. Simply update to the latest version and start experimenting with your favorite URLs.
Installation
If you haven’t installed Revise yet:
- Download from useRevise.com
- Install the plugin in WordPress
- Configure your preferred AI provider (Anthropic, OpenAI, or Gemini)
- Start chatting with URLs!
Need Help?
Your Feedback Matters
We built URL Fetching based on user feedback requesting better research capabilities. What other features would make Revise more useful for your workflow? Let us know!
About Revise: Revise is an AI-powered writing assistant built directly into WordPress’s Gutenberg editor. Write, edit, and enhance your content through natural conversation—no context switching required.