{"id":"cmp071zs1000how4bw3sxa1vd","slug":"importing-recipes-from-any-cooking-site","title":"Importing recipes from any cooking site","excerpt":"Most recipe sites already publish their recipes in machine-readable format. We just read the structured data — no AI guessing required.","body":"## How it actually works\n\nWhen you paste a recipe URL into NestBoard's meal planner, we don't send it to an LLM to \"extract\" the ingredients and steps. We just read the structured data that's already there.\n\nMost major cooking sites — Bon Appétit, NYT Cooking, AllRecipes, individual food blogs running WordPress — embed schema.org/Recipe markup in every recipe page. It's invisible to you, but it's sitting in the HTML: the ingredient list, the instructions, cook time, yield, everything.\n\nWe parse that structured data, pull out the fields we need, and show you the recipe. No round-trip to a language model. No latency. No hallucination risk.\n\n## What works well\n\nFood blogs using plugins like WP Recipe Maker or Tasty Recipes are perfect. The metadata is clean and consistent.\n\nRecipe aggregators like AllRecipes and Food Network work beautifully. They've been publishing schema.org data for years.\n\nEven smaller independent sites often use the same WordPress plugins, so they work just as well as the big names.\n\n## What doesn't work\n\nRestaurant menus don't publish recipe metadata — they're not recipes, they're listings. If you want to save \"pad thai from the place on 5th,\" you'll need to add it manually or ask Robin to help you build a recipe card from a photo.\n\nSome older or minimal food blogs skip the structured data entirely. If the site doesn't have the markup, we can't import it.\n\nAnd sometimes a site will have the schema.org tags but fill them incorrectly — missing units, ingredients buried in the instructions, that kind of thing. We can't fix bad data.\n\n## Why we like this approach\n\nIt's fast. There's no API call to wait on, no token budget to manage.\n\nIt's honest. If the data isn't there, we tell you. We don't try to guess what the recipe might be.\n\nAnd it respects the work that recipe publishers have already done. They've marked up their content in a standard format specifically so tools like ours can use it. We're just reading what they intended to share.\n\nThis is the same philosophy we take with Robin: we're [clear about what it reads and what it doesn't](/blog/what-robin-actually-reads-and-what-it-never-will). We'd rather give you a reliable tool with known boundaries than promise magic and deliver guesswork.\n\nIf you've found a recipe site that should work but doesn't, let us know. We're always refining the parser.","category":"Behind the scenes","ogImage":null,"metaTitle":null,"metaDescription":null,"authorName":null,"authorAvatarUrl":null,"status":"published","generatedBy":"claude","topicId":"cmoxfejbn0002twzg1yvgh4zk","publishedAt":"2026-05-18T13:01:34.601Z","scheduledFor":"2026-05-18T13:00:00.000Z","createdAt":"2026-05-10T19:56:58.850Z","updatedAt":"2026-05-18T13:01:34.780Z"}