#guide
3 posts tagged #guide.
What is structured data extraction?
Structured data extraction turns a web page into schema-validated JSON by naming the fields you want, not the CSS selectors that break when a site redesigns.
▸guide5 min
JSON Schema or a plain-language prompt: which to hand the extractor
Plain-language prompt or JSON Schema for AI extraction? You always send a prompt; an output_schema optionally pins field names and types. When to add one.
▸guide4 min
How to scrape a site that keeps blocking you
A 403, a 429, or a blank page usually means a site blocked your scraper. How to read the failure and get the page back, from a retry to a stealth browser.
▸guide6 min