# how stripe's custom docs framework broke me (and what i learned) > stripe doesn't use mintlify, docusaurus, or gitbook. they built their own. extracting it took days. here's what i found. stripe has the most popular api documentation on the internet. they also have one of the most custom docs frameworks i've encountered. extracting it was not a "paste url and wait" operation. it was days of work. back-and-forth. wrong assumptions. dead ends. here's what made it hard, and exactly how i got through it. ## it's not mintlify. it's not docusaurus. it's not gitbook. i have extractors for the common frameworks. mintlify? `.md` endpoints, done. docusaurus? structure in `docusaurus.config.js`, raw markdown in `docs/` folder. gitbook? partially supported. stripe uses none of these. they built their own. this is the first thing that hits you when you try to extract stripe. your framework detector returns "unknown." your tier 1-4 ladder methods fail. your html purification pulls rendered pages, but the navigation is empty, the content is fragmented, and you're looking at a shell instead of a site. ## content was in redux state, not the page html stripe's docs are server-side rendered with javascript hydration. but here's the catch: the actual documentation content isn't in the html. it's in a preloaded redux state object that's embedded in the page as a massive json blob. the html you fetch contains the shell: header, sidebar skeleton, maybe a title. but the actual paragraphs, code examples, parameter tables. all of that is in `window.__PRELOADED_STATE__` or injected via inline script. this means: **headless js dom (jsdom) sees the html. great.** **but the content is in a script tag. jsdom doesn't run scripts.** **so jsdom sees an empty page.** i tried running jsdom with `runScripts: 'dangerously'`. still didn't work. the preloaded state uses `JSON.parse()` inside the script, but the initial injection might happen before dom ready in a way jsdom can't replicate. ## strategy: extract json from the script tag when standard html purification failed, i switched to raw text extraction. step 1: fetch the html with a simple `GET` request. no jsdom. just raw text. step 2: find the preloaded redux state. this is a massive json object inside a `