fix(search): surface iTunes stubs and resolve feeds for delisted shows

Shows that left Apple Podcasts (e.g. Daily Wire's in 2021) come back from the iTunes Search API as metadata-only stub records with feedUrl null. mapItunesResult dropped them, so The Ben Shapiro Show — the #1 hit for 'ben shapiro' — never appeared in search while sibling shows did. - Keep feedUrl-less results (feedUrl "" + directoryUrl pointing at the Apple page) so delisted shows stay findable. - Resolve the real feed from the Apple page at subscribe time (itunes-feed-resolver: anchor on the collection's adamId, forward-scan for the embedded feedUrl; Apple serves page variants where the showOffer block sits thousands of chars after the adamId). - addFeed refuses feedless stubs whose feed can't be resolved instead of adding a broken feed; SearchPage surfaces the failure via toast. - Tests: stub mapping, extractor variants, and an end-to-end subscribe over a local HTTP server.
2026-08-10 22:38:03 -04:00
parent e73e608b9f
commit 0b0637b9dc
8 changed files with 364 additions and 11 deletions
--- a/tests/itunes-feed-resolver.test.ts
+++ b/tests/itunes-feed-resolver.test.ts
@@ -0,0 +1,70 @@
+/**
+ * Feed-resolution extraction tests.
+ *
+ * The iTunes Search API returns feedUrl null for shows delisted from Apple
+ * Podcasts. Their public Apple page still embeds the real feed URL in JSON
+ * state — alongside feedUrls of RELATED shows — so extraction must anchor on
+ * the show's adamId rather than grabbing the first feedUrl in the document.
+ */
+import { test, expect } from "bun:test";
+import { extractFeedUrlFromPage } from "../src/utils/itunes-feed-resolver";
+
+const MAIN_FEED = "https://rss.pdrl.fm/b32227/feeds.megaphone.fm/BVDWV5370667266";
+const OTHER_FEED = "https://feeds.megaphone.fm/BVDWV7762869899";
+
+/** Synthetic Apple page: related shows first, main showOffer after. */
+const pageWithNoise = `{
+  "shows":[{"showOffer":{"title":"The Matt Walsh Show","adamId":"2950206264","feedUrl":"${OTHER_FEED}","showType":"episodic"}}],
+  "pageData":{"showOffer":{"title":"The Ben Shapiro Show","adamId":"1047335260","feedUrl":"${MAIN_FEED}","showType":"episodic"}}
+}`;
+
+test("extracts the show's feed anchored on its adamId, ignoring related shows", () => {
+  const feed = extractFeedUrlFromPage(
+    pageWithNoise,
+    "https://podcasts.apple.com/us/podcast/the-ben-shapiro-show/id1047335260",
+  );
+  expect(feed).toBe(MAIN_FEED);
+});
+
+test("handles the ?uo=4 suffix Apple appends to directory URLs", () => {
+  const feed = extractFeedUrlFromPage(
+    pageWithNoise,
+    "https://podcasts.apple.com/us/podcast/the-ben-shapiro-show/id1047335260?uo=4",
+  );
+  expect(feed).toBe(MAIN_FEED);
+});
+
+test("returns null when the page has no feedUrl for the requested id", () => {
+  const feed = extractFeedUrlFromPage(
+    pageWithNoise,
+    "https://podcasts.apple.com/us/podcast/some-other-show/id9999999999",
+  );
+  expect(feed).toBeNull();
+});
+
+test("finds the feed when the showOffer sits far after the adamId reference", () => {
+  // Apple serves page variants where thousands of chars separate the first
+  // adamId reference from the showOffer block carrying the feedUrl.
+  const variant = `{"adamId":"1047335260","$kind":"ShowPageIntent"}${"x".repeat(6000)}{"showOffer":{"title":"The Ben Shapiro Show","adamId":"1047335260","feedUrl":"${MAIN_FEED}"}}`;
+  const feed = extractFeedUrlFromPage(
+    variant,
+    "https://podcasts.apple.com/us/podcast/the-ben-shapiro-show/id1047335260",
+  );
+  expect(feed).toBe(MAIN_FEED);
+});
+
+test("falls back to the first feedUrl when the URL carries no id", () => {
+  const feed = extractFeedUrlFromPage(
+    pageWithNoise,
+    "https://podcasts.apple.com/us/podcast/the-ben-shapiro-show",
+  );
+  expect(feed).toBe(OTHER_FEED);
+});
+
+test("returns null when the page contains no feedUrl at all", () => {
+  const feed = extractFeedUrlFromPage(
+    "<html><body>not found</body></html>",
+    "https://podcasts.apple.com/us/podcast/the-ben-shapiro-show/id1047335260",
+  );
+  expect(feed).toBeNull();
+});