feat(sources): ajoute ohmonbento.com comme source de recettes importable #53

Merged
kyuno merged 2 commits from feat/ohmonbento-recipe-source into main 2026-09-06 02:47:33 +02:00
5 changed files with 394 additions and 6 deletions

View file

@ -2,6 +2,7 @@ import { registerRecipeSource } from "../lib/recipe-sources/recipe-source-regist
import { sevenFiftyGAdapter } from "./750g.js";
import { mangerBougerAdapter } from "./manger-bouger.js";
import { marmitonAdapter } from "./marmiton.js";
import { ohMonBentoAdapter } from "./ohmonbento.js";
import { quitoqueAdapter } from "./quitoque.js";
import { theMealDbAdapter } from "./the-meal-db.js";
@ -9,8 +10,9 @@ import { theMealDbAdapter } from "./the-meal-db.js";
* Registers every concrete, *browsable* `RecipeSourceAdapter` this app
* ships with into the shared in-memory registry (`recipe-source-registry.ts`)
* — `theMealDbAdapter`, `marmitonAdapter`, `sevenFiftyGAdapter`,
* `mangerBougerAdapter` and `quitoqueAdapter`. Called once, explicitly, by
* the two real entry points that need the registry populated:
* `mangerBougerAdapter`, `quitoqueAdapter` and `ohMonBentoAdapter`. Called
* once, explicitly, by the two real entry points that need the registry
* populated:
*
* - `server.ts` — the running API process, before it starts listening.
* - `prisma/seed.ts` — so `syncRecipeSources` has something to mirror into
@ -41,4 +43,5 @@ export function registerAllRecipeSources(): void {
registerRecipeSource(sevenFiftyGAdapter);
registerRecipeSource(mangerBougerAdapter);
registerRecipeSource(quitoqueAdapter);
registerRecipeSource(ohMonBentoAdapter);
}

View file

@ -0,0 +1,170 @@
import type {
ParsedRecipe,
RecipeSourceAdapter,
RecipeSourceListItem,
RecipeSourceListParams,
RecipeSourceListResult,
} from "../lib/recipe-sources/recipe-source-adapter.js";
import {
RecipeSourceFetchError,
RecipeSourceParseError,
} from "../lib/recipe-sources/recipe-source-errors.js";
import { jsonLdRecipeAdapter } from "./json-ld-recipe.js";
const SOURCE_KEY = "ohMonBento";
const SITE_ORIGIN = "https://ohmonbento.com";
/** One recipe card scraped off an ohmonbento.com search page — see {@link extractRecipeCards}. */
interface OhMonBentoCard {
url: string;
title: string;
image: string | null;
}
/**
* Scrapes every recipe card out of an ohmonbento.com search results page.
* Each card is a `<div class="entry-thumb">` wrapping a single
* `<a href="/<slug>/">` with one `<img>` inside — no `ItemList` JSON-LD
* (unlike marmiton.ts) and no lazy-load `data-src` dance (unlike
* quitoque.ts): the real image is just the `<img>`'s `src`. `href` is a
* root-relative path, resolved against {@link SITE_ORIGIN} here.
* Attribute-order-agnostic.
*/
function extractRecipeCards(html: string): OhMonBentoCard[] {
const cards: OhMonBentoCard[] = [];
const thumbPattern = /<div\s+[^>]*class="[^"]*\bentry-thumb\b[^"]*"[^>]*>([\s\S]*?)<\/div>/g;
for (const match of html.matchAll(thumbPattern)) {
const block = match[1] ?? "";
const href = /<a\s+[^>]*\bhref="([^"]+)"/.exec(block)?.[1];
if (href === undefined) continue;
const title = /\balt="([^"]*)"/.exec(block)?.[1] ?? "";
if (title.length === 0) continue;
const url = href.startsWith("http") ? href : `${SITE_ORIGIN}${href}`;
cards.push({ url, title, image: /\bsrc="([^"]+)"/.exec(block)?.[1] ?? null });
}
return cards;
}
/**
* Re-labels a `RecipeSourceFetchError`/`RecipeSourceParseError` thrown by
* the generic `jsonLdRecipeAdapter` (`sourceKey` `"jsonLdRecipe"`) as this
* adapter's (`sourceKey` `"ohMonBento"`) — same reasoning as marmiton.ts's
* identically-named helper. (Not factored out into a shared helper —
* marmiton/750g/manger-bouger/quitoque each keep their own copy; the
* near-identical five-liner isn't worth a module.)
*/
function rekeySourceError(err: unknown): unknown {
if (err instanceof RecipeSourceFetchError) {
return new RecipeSourceFetchError(SOURCE_KEY, err.message, { cause: err.cause });
}
if (err instanceof RecipeSourceParseError) {
return new RecipeSourceParseError(SOURCE_KEY, err.message, { cause: err.cause });
}
return err;
}
/**
* ohmonbento.com — a French Japanese-cuisine / bento cooking blog
* (WordPress). Unofficial (`official: false`, same reasoning as every
* other scraped adapter): no published API, this reads ordinary pages and
* the schema.org JSON-LD they embed. `robots.txt` allows everything except
* `/wp-admin/`.
*
* The simplest of the scraped adapters: like marmiton.ts, `fetchDetail`/
* `parse` delegate straight to {@link jsonLdRecipeAdapter} — a recipe page
* carries a WP Recipe Maker `Recipe` inside a Yoast `@graph`, which
* `findRecipeNode` already handles (recurses into the array). Only `list()`
* is site-specific: WordPress search at `/?s={query}&paged={page}` — the
* **same URL whether `query` is empty (whole catalogue) or not** (no
* branching, unlike 750g.ts) — with a `<div class="entry-thumb">` card
* scrape (see {@link extractRecipeCards}). A page past the last one 404s,
* the same clean end-of-list signal as marmiton.ts.
*/
export const ohMonBentoAdapter: RecipeSourceAdapter<{ html: string; url: string }> = {
key: SOURCE_KEY,
name: "Oh mon Bento",
official: false,
iconUrl: `${SITE_ORIGIN}/favicon.ico`,
// Le contenu d'ohmonbento.com (noms, ingrédients, instructions) est en
// français — détermine contre quel modèle/locale d'étiquettes
// d'ingrédients translateRecipe (recipe-translation.ts) résout les
// recettes de cette source lors d'une prévisualisation/d'un import.
locale: "fr",
async list(params: RecipeSourceListParams): Promise<RecipeSourceListResult> {
try {
// Curseur opaque = numéro de page suivant ; WordPress pagine via
// `&paged=N` (page 1 implicite quand le paramètre est absent). Le
// paramètre `?s=` est toujours présent, même vide — c'est ce qui
// liste tout le catalogue (vérifié sur le ticket).
const page = params.cursor ? Number(params.cursor) : 1;
const query = params.query ?? "";
const listUrl = `${SITE_ORIGIN}/?s=${encodeURIComponent(query)}${
page > 1 ? `&paged=${page}` : ""
}`;
let response: Response;
try {
response = await fetch(listUrl);
} catch (cause) {
throw new RecipeSourceFetchError(
SOURCE_KEY,
`Network error listing Oh mon Bento recipes (${listUrl})`,
{ cause },
);
}
// Une page au-delà de la dernière renvoie une vraie 404 — pas un
// échec, juste « il n'y a plus rien » (même signal que marmiton.ts).
if (response.status === 404) {
return { items: [], nextCursor: null };
}
if (!response.ok) {
throw new RecipeSourceFetchError(
SOURCE_KEY,
`Oh mon Bento responded ${response.status} (${listUrl})`,
);
}
const html = await response.text();
const items: RecipeSourceListItem[] = extractRecipeCards(html).map((card) => ({
externalId: card.url,
title: card.title,
picture: card.image,
url: card.url,
}));
// La 404 ci-dessus est le vrai signal de fin ; on ne propose une page
// suivante que si celle-ci a renvoyé au moins une carte (même logique
// que marmiton.ts).
const nextCursor = items.length > 0 ? String(page + 1) : null;
return { items, nextCursor };
} catch (err) {
// Rethrown as-is (already keyed "ohMonBento" by whichever branch
// above threw it) — same reasoning as `marmiton.ts`/`quitoque.ts`.
throw err;
}
},
// `externalId` est directement l'URL canonique de la recette sur
// ohmonbento.com (renvoyée telle quelle par `list()` ci-dessus) — même
// convention que `jsonLdRecipeAdapter.fetchDetail`, à qui cette méthode
// délègue entièrement.
async fetchDetail(externalId: string): Promise<{ html: string; url: string }> {
try {
return await jsonLdRecipeAdapter.fetchDetail(externalId);
} catch (err) {
// `rekeySourceError` est le traitement utile de l'erreur à ce point
// d'appel (relabelliser sa `sourceKey`), pas un simple re-throw.
throw rekeySourceError(err);
}
},
parse(raw: { html: string; url: string }): ParsedRecipe {
try {
return jsonLdRecipeAdapter.parse(raw);
} catch (err) {
throw rekeySourceError(err);
}
},
};

View file

@ -0,0 +1,195 @@
import { expect } from "chai";
import {
RecipeSourceFetchError,
RecipeSourceParseError,
} from "../../src/lib/recipe-sources/recipe-source-errors.js";
import { ohMonBentoAdapter } from "../../src/sources/ohmonbento.js";
/** Stubs `globalThis.fetch` to return `html` — same pattern as `marmiton.test.ts`/`quitoque.test.ts`. */
function stubFetchHtml(html: string, status = 200) {
globalThis.fetch = (async () => new Response(html, { status })) as typeof fetch;
}
/** Like {@link stubFetchHtml} but records the URL each call was made with — for asserting `list()`'s search/pagination URL. */
function stubFetchHtmlCapturing(html: string): { calls: string[] } {
const calls: string[] = [];
globalThis.fetch = (async (input: string | URL | Request) => {
calls.push(typeof input === "string" ? input : input.toString());
return new Response(html, { status: 200 });
}) as typeof fetch;
return { calls };
}
/** A search-results page with `cards` `<div class="entry-thumb">` blocks, each an `<a href="/<slug>/">` wrapping one `<img alt src>`. */
function searchHtml(cards: { slug: string; title: string; image: string }[]): string {
const blocks = cards
.map(
(card) =>
`<div class="entry-thumb"><a href="/${card.slug}/">` +
`<img alt="${card.title}" src="${card.image}" /></a></div>`,
)
.join("\n");
return `<!doctype html><html><body><div class="search-results">${blocks}</div></body></html>`;
}
/** A recipe page: a WP Recipe Maker `Recipe` inside a Yoast `@graph` array. */
function detailHtml(): string {
const payload = {
"@context": "https://schema.org",
"@graph": [
{ "@type": "WebSite", name: "Oh mon Bento" },
{ "@type": "BreadcrumbList" },
{
"@type": "Recipe",
name: "Kamameshi",
description: "Riz japonais mijoté en cocotte.",
image: "https://ohmonbento.com/wp-content/uploads/kamameshi.jpg",
recipeYield: ["2", "2 portions"],
recipeIngredient: ["300 g de riz rond japonais (Japonica)", "1 c. à soupe de sauce soja"],
recipeInstructions: [
{ "@type": "HowToStep", name: "Rincer le riz", text: "Rincez le riz à l'eau claire." },
{ "@type": "HowToStep", name: "Cuire", text: "Faites cuire à couvert 12 minutes." },
],
},
],
};
return `<!doctype html><html><head><script type="application/ld+json">${JSON.stringify(
payload,
)}</script></head><body></body></html>`;
}
describe("ohMonBentoAdapter", () => {
let originalFetch: typeof fetch;
beforeEach(() => {
originalFetch = globalThis.fetch;
});
afterEach(() => {
globalThis.fetch = originalFetch;
});
it("declares itself as an unofficial, French-locale source with an icon", () => {
expect(ohMonBentoAdapter.key).to.equal("ohMonBento");
expect(ohMonBentoAdapter.name).to.equal("Oh mon Bento");
expect(ohMonBentoAdapter.official).to.equal(false);
expect(ohMonBentoAdapter.iconUrl).to.be.a("string");
expect(ohMonBentoAdapter.locale).to.equal("fr");
});
describe("list", () => {
it("scrapes each entry-thumb card into a RecipeSourceListItem and offers a next page", async () => {
stubFetchHtml(
searchHtml([
{ slug: "kamameshi", title: "Kamameshi", image: "https://img.test/1.jpg" },
{ slug: "onigiri", title: "Onigiri", image: "https://img.test/2.jpg" },
]),
);
const result = await ohMonBentoAdapter.list({});
expect(result.items).to.deep.equal([
{
externalId: "https://ohmonbento.com/kamameshi/",
title: "Kamameshi",
picture: "https://img.test/1.jpg",
url: "https://ohmonbento.com/kamameshi/",
},
{
externalId: "https://ohmonbento.com/onigiri/",
title: "Onigiri",
picture: "https://img.test/2.jpg",
url: "https://ohmonbento.com/onigiri/",
},
]);
expect(result.nextCursor).to.equal("2");
});
it("treats a 404 (past the last page) as the clean end of the list", async () => {
stubFetchHtml("", 404);
const result = await ohMonBentoAdapter.list({ cursor: "99" });
expect(result.items).to.deep.equal([]);
expect(result.nextCursor).to.be.null;
});
it("uses the same `/?s=` search URL for an empty query, with no `paged` on page 1", async () => {
const { calls } = stubFetchHtmlCapturing(
searchHtml([{ slug: "x", title: "X", image: "https://img.test/x.jpg" }]),
);
await ohMonBentoAdapter.list({});
expect(calls).to.deep.equal(["https://ohmonbento.com/?s="]);
});
it("passes the query and page through to `/?s={query}&paged={n}`", async () => {
const { calls } = stubFetchHtmlCapturing(
searchHtml([{ slug: "x", title: "X", image: "https://img.test/x.jpg" }]),
);
await ohMonBentoAdapter.list({ query: "bento box", cursor: "3" });
expect(calls).to.deep.equal(["https://ohmonbento.com/?s=bento%20box&paged=3"]);
});
it("throws RecipeSourceFetchError keyed 'ohMonBento' on a non-404 non-2xx response", async () => {
stubFetchHtml("", 500);
try {
await ohMonBentoAdapter.list({});
expect.fail("expected list to throw");
} catch (err) {
expect(err).to.be.instanceOf(RecipeSourceFetchError);
expect((err as RecipeSourceFetchError).sourceKey).to.equal("ohMonBento");
}
});
});
describe("fetchDetail / parse", () => {
it("parses a Yoast @graph-wrapped WPRM Recipe into a ParsedRecipe", async () => {
stubFetchHtml(detailHtml());
const raw = await ohMonBentoAdapter.fetchDetail("https://ohmonbento.com/kamameshi/");
const parsed = ohMonBentoAdapter.parse(raw);
expect(parsed.name).to.equal("Kamameshi");
// recipeYield: ["2", "2 portions"] -> first element, regex \d+ -> 2.
expect(parsed.portions).to.equal(2);
expect(parsed.ingredients.map((i) => i.rawText)).to.deep.equal([
"300 g de riz rond japonais (Japonica)",
"1 c. à soupe de sauce soja",
]);
expect(parsed.steps.map((s) => s.description)).to.deep.equal([
"Rincez le riz à l'eau claire.",
"Faites cuire à couvert 12 minutes.",
]);
});
it("re-keys a delegated RecipeSourceFetchError to 'ohMonBento' when the detail page 404s", async () => {
stubFetchHtml("", 404);
try {
await ohMonBentoAdapter.fetchDetail("https://ohmonbento.com/gone/");
expect.fail("expected fetchDetail to throw");
} catch (err) {
expect(err).to.be.instanceOf(RecipeSourceFetchError);
expect((err as RecipeSourceFetchError).sourceKey).to.equal("ohMonBento");
}
});
it("re-keys a delegated RecipeSourceParseError to 'ohMonBento' when a page has no Recipe JSON-LD", () => {
try {
ohMonBentoAdapter.parse({
html: "<!doctype html><html><body>rien</body></html>",
url: "https://ohmonbento.com/vide/",
});
expect.fail("expected parse to throw");
} catch (err) {
expect(err).to.be.instanceOf(RecipeSourceParseError);
expect((err as RecipeSourceParseError).sourceKey).to.equal("ohMonBento");
}
});
});
});

View file

@ -61,6 +61,15 @@ describe("registerAllRecipeSources", () => {
expect(listRecipeSources().map((adapter) => adapter.key)).to.include("quitoque");
});
it("registers Oh mon Bento into the shared registry", () => {
registerAllRecipeSources();
const ohMonBento = getRecipeSource("ohMonBento");
expect(ohMonBento).to.not.be.undefined;
expect(ohMonBento?.name).to.equal("Oh mon Bento");
expect(listRecipeSources().map((adapter) => adapter.key)).to.include("ohMonBento");
});
it("does not register the generic JSON-LD adapter — it's not a household-toggleable source in its own right", () => {
registerAllRecipeSources();

View file

@ -620,12 +620,23 @@ pas encore de ligne `Source` — jamais une erreur).
lacune assumée que `750g.ts`). Fin de liste = page sans aucune carte.
Les copies privées de `rekeySourceError` (marmiton/750g/manger-bouger
en ont chacune une) ne sont pas factorisées.
- **`ohmonbento.ts`** — `key: "ohMonBento"`, `official: false`,
`locale: "fr"`. Le plus simple des adaptateurs scrapés : `fetchDetail`/
`parse` délèguent tels quels à `jsonLdRecipeAdapter` (une page recette
porte un `Recipe` WP Recipe Maker dans un `@graph` Yoast, géré
nativement par `findRecipeNode`). `list()` : recherche WordPress
`GET /?s={query}&paged={N}` — **même URL que la requête soit vide (tout
le catalogue) ou non**, pas de branchement (contrairement à `750g.ts`) —
scrape de cartes `<div class="entry-thumb"><a href="/<slug>/"><img
alt src>` (image dans `src`, pas de lazy-load `data-src` ; `href`
relatif résolu contre l'origine). Une page au-delà de la dernière **404**
(signal de fin propre, comme `marmiton.ts`).
`apps/api/src/sources/index.ts`'s `registerAllRecipeSources()` enregistre
`theMealDb`, `marmiton`, `750g`, `mangerBouger` et `quitoque` — appelé
explicitement par `server.ts`/`seed*`, **jamais** par `app.ts` (que chaque
test récupère via supertest ; y enregistrer un adaptateur réel ferait
dépendre sa présence de l'ordre des tests).
`theMealDb`, `marmiton`, `750g`, `mangerBouger`, `quitoque` et
`ohMonBento` — appelé explicitement par `server.ts`/`seed*`, **jamais**
par `app.ts` (que chaque test récupère via supertest ; y enregistrer un
adaptateur réel ferait dépendre sa présence de l'ordre des tests).
### Endpoints (`apps/api/src/modules/sources/`, `/sources`, `requireAuth`)