Skip to main content

Documentation Index

Fetch the complete documentation index at: https://sourcetable.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

Sourcetable’s AI can browse the web, extract structured data from websites, and automate browser interactions — all powered by Playwright under the hood. Ask in natural language, and the AI handles the technical details.

​
Web scraping

Extract data from web pages and import it directly into your spreadsheet:
  • “Scrape the product listings from this URL and put them in a table”
  • “Extract all the pricing information from this competitor’s website”
  • “Pull the table of contents from this Wikipedia page”
  • “Get the top 100 results from this search query and list them with titles and URLs”
The AI uses playwright_browser and computer_use tools to navigate pages, extract content, and structure it into spreadsheet-ready data.

​
Browser automation

The AI can interact with web pages like a human user:
  • Navigate to specific URLs
  • Click buttons and links
  • Fill forms and input fields
  • Scroll through pages
  • Wait for content to load
  • Extract text, tables, images, and structured data

​
Screenshots

Capture visual snapshots of web pages:
  • “Take a screenshot of this dashboard URL”
  • “Capture the pricing page of competitor.com”
The AI uses the screenshot tool to render the page and return the image.

​
MCP integration (Apify)

For large-scale or recurring web scraping, Sourcetable integrates with Apify through MCP:
  • Run pre-built Apify actors for common scraping tasks
  • Scrape at scale with rate limiting and proxy rotation
  • Schedule recurring scraping jobs
  • Extract data from JavaScript-heavy single-page applications
Connect Apify from the MCP connectors settings.

​
Example workflows

​
Price monitoring

“Every week, scrape competitor pricing from these 5 URLs and add the results to my tracking spreadsheet”

​
Lead generation

“Extract company names, emails, and phone numbers from this directory page”

​
Content aggregation

“Pull the latest headlines and summaries from these 10 news sites”

​
Data collection

“Scrape the results table from this government statistics page and import it”

​
Limitations

Web scraping must comply with website terms of service and robots.txt directives. Some sites block automated access. The AI respects rate limits and will inform you if a site cannot be scraped.
  • JavaScript-heavy sites may require Apify for reliable extraction
  • Login-protected content requires valid credentials
  • Some sites actively block scraping tools
  • Large-scale scraping is better handled through the Apify MCP connector