Claude Code has ~85 "approved" websites that get full content extraction. Everyone else gets almost nothing. Does ChatGPT have something similar?

Found this digging through Claude Code's actual source after the leak. When it searches the web, there's a literal list of domains (Stack Overflow, MDN, GitHub, major docs sites) that get full content pulled. If your site isn't on that list, you get truncated to what looks like roughly a sentence or two worth of content. So there's a two-tier web emerging. Approved sites get their full content fed to the AI. Everyone else is almost invisible. This made me realize I have no idea how ChatGPT decides which sites to actually read vs barely glance at.