Turn pages into structured data - no parsers, no selectors

1{
2  "httpResponseBody": true,
3  "pageContent": true
4}
5
6def parse(self, response):
7    http_response_body: bytes = response.body
8    with open("http_response_body.html", "wb") as fp:
9        fp.write(http_response_body)
10    page_content = response.raw_api_response["pageContent"]
11    yield page_content

1{
2  "headline": "Guide to Espresso Brewing",
3  "itemMain": "Espresso Brewing Guide. Everything you need to dial in a shot: dose, yield, time, and grind. Start with 18 g in and 36 g out in 25-30 seconds, then adjust grind until the shot tastes balanced. Water at 93°C, freshly roasted beans, and a level tamp matter more than any single variable...",
4  // ...,
5  "itemMainXPath": "//*[@id=\"main-content-wrapper\"]",
6  "metadata": {
7    "dateDownloaded": "2026-07-20T09:14:22Z"
8  }
9}