feat(apify): add LinkedIn profile scraping (harvestapi)

lib/apify/__tests__/scrapeProfileUrl.test.ts

@@ -0,0 +1,37 @@
+import { describe, it, expect, vi, beforeEach } from "vitest";
+
+import { scrapeProfileUrl } from "@/lib/apify/scrapeProfileUrl";
+
+const li = vi.fn();
+vi.mock("@/lib/apify/linkedin/startLinkedinProfileScraping", () => ({
+  default: (...a: unknown[]) => li(...a),
+}));
+vi.mock("@/lib/apify/tiktok/startTiktokProfileScraping", () => ({ default: vi.fn() }));
+vi.mock("@/lib/apify/instagram/startInstagramProfileScraping", () => ({
+  startInstagramProfileScraping: vi.fn(),
+}));
+vi.mock("@/lib/apify/twitter/startTwitterProfileScraping", () => ({ default: vi.fn() }));
+vi.mock("@/lib/apify/threads/startThreadsProfileScraping", () => ({ default: vi.fn() }));
+vi.mock("@/lib/apify/youtube/startYoutubeProfileScraping", () => ({ default: vi.fn() }));
+vi.mock("@/lib/apify/facebook/startFacebookProfileScraping", () => ({ default: vi.fn() }));
+vi.mock("@/lib/socials/getUsernameFromProfileUrl", () => ({
+  getUsernameFromProfileUrl: () => "drew-thurlow",
+}));
+
+beforeEach(() => {
+  vi.clearAllMocks();
+  li.mockResolvedValue({ runId: "li-run", datasetId: "li-ds" });
+});
+
+describe("scrapeProfileUrl", () => {
+  it("dispatches linkedin.com to the LinkedIn scraper", async () => {
+    const r = await scrapeProfileUrl("https://www.linkedin.com/in/drew-thurlow", "drew-thurlow");
+    expect(li).toHaveBeenCalledWith("drew-thurlow");
+    expect(r).toMatchObject({ supported: true, runId: "li-run", datasetId: "li-ds" });
+  });
+  it("returns null for an unsupported platform (spotify)", async () => {
+    const r = await scrapeProfileUrl("https://open.spotify.com/artist/x", "x");
+    expect(r).toBeNull();
+    expect(li).not.toHaveBeenCalled();
+  });
+});

lib/apify/__tests__/startLinkedinProfileScraping.test.ts

@@ -0,0 +1,32 @@
+import { describe, it, expect, vi, beforeEach } from "vitest";
+import apifyClient from "@/lib/apify/client";
+import startLinkedinProfileScraping from "@/lib/apify/linkedin/startLinkedinProfileScraping";
+
+const start = vi.fn();
+vi.mock("@/lib/apify/client", () => ({ default: { actor: vi.fn(() => ({ start })) } }));
+
+beforeEach(() => {
+  vi.clearAllMocks();
+  start.mockResolvedValue({ id: "run-1", defaultDatasetId: "ds-1", status: "RUNNING" });
+});
+
+describe("startLinkedinProfileScraping", () => {
+  it("starts the harvestapi actor with `urls` (the actor's real input key), building the /in/ URL from a handle", async () => {
+    const r = await startLinkedinProfileScraping("sweetmaneth");
+    expect(apifyClient.actor).toHaveBeenCalledWith("harvestapi/linkedin-profile-scraper");
+    expect(start).toHaveBeenCalledWith({ urls: ["https://www.linkedin.com/in/sweetmaneth"] });
+    expect(r).toEqual({ runId: "run-1", datasetId: "ds-1" });
+  });
+
+  it("passes a full profile URL through unchanged", async () => {
+    await startLinkedinProfileScraping("https://www.linkedin.com/in/drew-thurlow");
+    expect(start).toHaveBeenCalledWith({ urls: ["https://www.linkedin.com/in/drew-thurlow"] });
+  });
+  it("rejects LinkedIn path prefixes as handles (legacy rows stored 'in') instead of scraping the wrong profile", async () => {
+    await expect(startLinkedinProfileScraping("in")).rejects.toThrow(/Invalid LinkedIn handle/);
+    await expect(startLinkedinProfileScraping("company")).rejects.toThrow(
+      /Invalid LinkedIn handle/,
+    );
+    expect(start).not.toHaveBeenCalled();
+  });
+});

lib/apify/linkedin/startLinkedinProfileScraping.ts

@@ -0,0 +1,46 @@
+import apifyClient from "@/lib/apify/client";
+import { OUTSTANDING_ERROR } from "@/lib/apify/errors";
+import { ApifyRunInfo } from "@/lib/apify/types";
+
+/**
+ * Starts a LinkedIn profile scrape via the harvestapi actor.
+ * Mirrors the other `start<Platform>ProfileScraping` modules.
+ *
+ * @param handle - A LinkedIn vanity slug (e.g. `drew-thurlow`) or full profile URL.
+ * @returns Apify run info, or null if the run failed to start.
+ * @see https://apify.com/harvestapi/linkedin-profile-scraper
+ */
+const startLinkedinProfileScraping = async (handle: string): Promise<ApifyRunInfo | null> => {
+  const cleanHandle = handle.trim().replace(/^@/, "");
+  // Legacy rows stored the LinkedIn path prefix ("in") as the username — never
+  // scrape those (linkedin.com/in/in is a real, wrong profile URL); fail loudly.
+  if (!cleanHandle || ["in", "company", "school"].includes(cleanHandle.toLowerCase())) {
+    throw new Error(`Invalid LinkedIn handle: "${handle}"`);
+  }
+
+  const targetUrl = cleanHandle.startsWith("http")
+    ? cleanHandle
+    : `https://www.linkedin.com/in/${cleanHandle}`;
+
+  const input = { urls: [targetUrl] };
+
+  try {
+    const run = await apifyClient.actor("harvestapi/linkedin-profile-scraper").start(input);
+
+    if (!run?.id || !run?.defaultDatasetId) {
+      console.error("Failed to start LinkedIn profile scraping for handle:", handle);
+      return null;
+    }
+
+    if (run.status === "FAILED" || run.status === "ABORTED") {
+      throw new Error(OUTSTANDING_ERROR);
+    }
+
+    return { runId: run.id, datasetId: run.defaultDatasetId };
+  } catch (error) {
+    console.error("Error in startLinkedinProfileScraping:", error);
+    throw error;
+  }
+};
+
+export default startLinkedinProfileScraping;

lib/apify/scrapeProfileUrl.ts

@@ -4,6 +4,7 @@ import startTwitterProfileScraping from "@/lib/apify/twitter/startTwitterProfile
 import startThreadsProfileScraping from "@/lib/apify/threads/startThreadsProfileScraping";
 import startYoutubeProfileScraping from "@/lib/apify/youtube/startYoutubeProfileScraping";
 import startFacebookProfileScraping from "@/lib/apify/facebook/startFacebookProfileScraping";
+import startLinkedinProfileScraping from "@/lib/apify/linkedin/startLinkedinProfileScraping";
 import { getUsernameFromProfileUrl } from "@/lib/socials/getUsernameFromProfileUrl";
 
 type ScrapeRunner = (handle: string) => Promise<{
@@ -51,6 +52,10 @@ const PLATFORM_SCRAPERS: Array<{
     match: (url: string) => url.includes("facebook.com"),
     scraper: startFacebookProfileScraping,
   },
+  {
+    match: (url: string) => url.includes("linkedin.com"),
+    scraper: startLinkedinProfileScraping,
+  },
 ];
 
 export const scrapeProfileUrl = async (

lib/artists/__tests__/getSocialPlatformByLink.test.ts

@@ -0,0 +1,14 @@
+import { describe, it, expect } from "vitest";
+import { getSocialPlatformByLink } from "@/lib/artists/getSocialPlatformByLink";
+
+describe("getSocialPlatformByLink", () => {
+  it("maps linkedin.com to LINKEDIN", () => {
+    expect(getSocialPlatformByLink("https://linkedin.com/in/drew-thurlow")).toBe("LINKEDIN");
+    expect(getSocialPlatformByLink("linkedin.com/company/recoup")).toBe("LINKEDIN");
+  });
+  it("still maps the existing platforms", () => {
+    expect(getSocialPlatformByLink("x.com/theasf")).toBe("TWITTER");
+    expect(getSocialPlatformByLink("tiktok.com/@apache_207")).toBe("TIKTOK");
+    expect(getSocialPlatformByLink("")).toBe("NONE");
+  });
+});

lib/artists/getSocialPlatformByLink.ts

@@ -10,6 +10,7 @@ export function getSocialPlatformByLink(link: string): string {
   if (link.includes("instagram.com")) return "INSTAGRAM";
   if (link.includes("spotify.com")) return "SPOTIFY";
   if (link.includes("tiktok.com")) return "TIKTOK";
+  if (link.includes("linkedin.com")) return "LINKEDIN";
   if (link.includes("apple.com")) return "APPLE";
   if (link.includes("youtube.")) return "YOUTUBE";
   if (link.includes("facebook.com")) return "FACEBOOK";

lib/socials/__tests__/getUsernameFromProfileUrl.test.ts

@@ -0,0 +1,20 @@
+import { describe, it, expect } from "vitest";
+import { getUsernameFromProfileUrl } from "@/lib/socials/getUsernameFromProfileUrl";
+
+describe("getUsernameFromProfileUrl", () => {
+  it("extracts the first path segment for standard platforms", () => {
+    expect(getUsernameFromProfileUrl("https://instagram.com/apacheoficial")).toBe("apacheoficial");
+    expect(getUsernameFromProfileUrl("x.com/theasf")).toBe("theasf");
+    expect(getUsernameFromProfileUrl("")).toBe("");
+  });
+
+  it("extracts the handle from LinkedIn /in/, /company/, /school/ URLs (not the path prefix)", () => {
+    expect(getUsernameFromProfileUrl("https://www.linkedin.com/in/sweetmaneth/")).toBe(
+      "sweetmaneth",
+    );
+    expect(getUsernameFromProfileUrl("linkedin.com/in/drew-thurlow-3a354311")).toBe(
+      "drew-thurlow-3a354311",
+    );
+    expect(getUsernameFromProfileUrl("https://linkedin.com/company/recoupable")).toBe("recoupable");
+  });
+});

lib/socials/getUsernameFromProfileUrl.ts

@@ -11,6 +11,12 @@ export const getUsernameFromProfileUrl = (profileUrl: string | null | undefined)
 
   try {
     const normalizedUrl = profileUrl.toLowerCase().trim();
+    // LinkedIn nests the handle under a path prefix (/in/, /company/, /school/) —
+    // the generic first-segment rule would return the prefix itself (e.g. "in").
+    const linkedin = normalizedUrl.match(/linkedin\.com\/(?:in|company|school)\/([^/?]+)/);
+    if (linkedin) {
+      return linkedin[1];
+    }
     const match = normalizedUrl.match(/(?:\.com|\.net)\/([^/?]+)/);
     return match ? match[1] : "";
   } catch (error) {