feat: add Google Jobs extractor and fix scraper reliability gaps

Ship a Camoufox-backed Google Jobs source, restore Glassdoor results discarded by a python-jobspy GraphQL quirk, and fix Himalayas/Gradcracker zero-job failures. Also harden prior-skip dismiss matching and multi-profile basic-auth switching for CA/US runs.

shared/src/extractors/index.ts

@@ -26,6 +26,7 @@ export const EXTRACTOR_SOURCE_IDS = [
   "testdevjobs",
   "wellfound",
   "builtin",
+  "google-jobs",
   // --- Public ATS / career-page sources ---
   "ashby",
   "lever",
@@ -217,6 +218,12 @@ export const EXTRACTOR_SOURCE_METADATA: Record<
     category: "pipeline",
     region: "global",
   },
+  "google-jobs": {
+    label: "Google Jobs",
+    order: 199,
+    category: "pipeline",
+    region: "global",
+  },
   ashby: {
     label: "Ashby (ATS)",
     order: 210,

shared/src/job-fingerprint.test.ts

@@ -3,8 +3,11 @@ import {
   buildJobContentFingerprint,
   buildJobDescriptionFingerprint,
   collectJobDedupKeys,
+  employersMatchForDismiss,
+  jobsMatchEmployerAndTitleDismiss,
   normalizeEmployerForFingerprint,
   normalizeTitleForFingerprint,
+  titlesMatchForDismiss,
 } from "./job-fingerprint";
 
 describe("buildJobContentFingerprint", () => {
@@ -96,10 +99,58 @@ describe("buildJobContentFingerprint", () => {
       expect(normalizeEmployerForFingerprint("Acme GmbH")).toBe("acme");
     });
 
+    it("normalizeEmployerForFingerprint strips leading punctuation", () => {
+      expect(normalizeEmployerForFingerprint(". CGI IT UK Limited")).toBe(
+        "cgiituklimited",
+      );
+    });
+
     it("normalizeTitleForFingerprint drops leading repost markers", () => {
       expect(normalizeTitleForFingerprint("[Reposted] Software Engineer")).toBe(
         "softwareengineer",
       );
     });
   });
+
+  describe("prior skip dismiss matching", () => {
+    it("employersMatchForDismiss allows prefix matches", () => {
+      expect(
+        employersMatchForDismiss("cgi", normalizeEmployerForFingerprint("CGI")),
+      ).toBe(true);
+      expect(
+        employersMatchForDismiss(
+          normalizeEmployerForFingerprint("CGI IT UK Limited"),
+          normalizeEmployerForFingerprint("CGI"),
+        ),
+      ).toBe(true);
+    });
+
+    it("titlesMatchForDismiss allows plural variants", () => {
+      expect(
+        titlesMatchForDismiss(
+          normalizeTitleForFingerprint("Automation Test Engineer"),
+          normalizeTitleForFingerprint("Automation Test Engineers"),
+        ),
+      ).toBe(true);
+    });
+
+    it("jobsMatchEmployerAndTitleDismiss requires same title family", () => {
+      expect(
+        jobsMatchEmployerAndTitleDismiss({
+          employerA: "CGI IT UK Limited",
+          titleA: "Automation Test Engineers",
+          employerB: "CGI",
+          titleB: "Automation Test Engineer",
+        }),
+      ).toBe(true);
+      expect(
+        jobsMatchEmployerAndTitleDismiss({
+          employerA: "Cognizant",
+          titleA: "AI Automation Test Engineer",
+          employerB: "Cognizant",
+          titleB: "Automation Test Engineer",
+        }),
+      ).toBe(false);
+    });
+  });
 });

shared/src/job-fingerprint.ts

@@ -29,6 +29,9 @@ const TRAILING_CITY_REGION_RE = /\s+[-|–—]\s+[^,\-|–—]+,\s*[^,\-|–—]
 const COMPANY_LEGAL_SUFFIX_RE =
   /\b(?:inc|inc\.|ltd|ltd\.|llc|gmbh|s\.a\.|s\.r\.l|sa|nv|bv|plc|corp|corporation|co|company|holdings|holding)\b/g;
 
+/** Hide rediscovered roles that match a prior skip/apply within this window. */
+export const PRIOR_SKIP_DISMISS_LOOKBACK_MS = 90 * 24 * 60 * 60 * 1000;
+
 function stripDiacritics(input: string): string {
   return input.normalize("NFKD").replace(/[\u0300-\u036f]/g, "");
 }
@@ -38,6 +41,7 @@ export function normalizeEmployerForFingerprint(
 ): string {
   if (!employer) return "";
   let value = stripDiacritics(employer.toLowerCase()).trim();
+  value = value.replace(/^[^a-z0-9]+/g, "");
   value = value.replace(PARENS_RE, " ");
   value = value.replace(COMPANY_LEGAL_SUFFIX_RE, " ");
   value = value.replace(PUNCTUATION_RE, " ");
@@ -103,6 +107,69 @@ export function buildJobDescriptionFingerprint(args: {
   return `${employer}::desc::${description}`;
 }
 
+/**
+ * Whether two normalized employers refer to the same company for dismiss matching.
+ * Allows prefix matches so `cgi` matches `cgiituklimited`.
+ */
+export function employersMatchForDismiss(
+  normalizedEmployerA: string,
+  normalizedEmployerB: string,
+): boolean {
+  if (!normalizedEmployerA || !normalizedEmployerB) return false;
+  if (normalizedEmployerA === normalizedEmployerB) return true;
+  const [short, long] =
+    normalizedEmployerA.length <= normalizedEmployerB.length
+      ? [normalizedEmployerA, normalizedEmployerB]
+      : [normalizedEmployerB, normalizedEmployerA];
+  if (short.length < 3) return false;
+  return long.startsWith(short);
+}
+
+/**
+ * Whether two normalized titles are the same role for dismiss matching.
+ * Allows a trailing plural `s` variant (`engineer` vs `engineers`).
+ */
+export function titlesMatchForDismiss(
+  normalizedTitleA: string,
+  normalizedTitleB: string,
+): boolean {
+  if (!normalizedTitleA || !normalizedTitleB) return false;
+  if (normalizedTitleA === normalizedTitleB) return true;
+  if (
+    normalizedTitleA.length > 4 &&
+    normalizedTitleA.endsWith("s") &&
+    normalizedTitleA.slice(0, -1) === normalizedTitleB
+  ) {
+    return true;
+  }
+  if (
+    normalizedTitleB.length > 4 &&
+    normalizedTitleB.endsWith("s") &&
+    normalizedTitleB.slice(0, -1) === normalizedTitleA
+  ) {
+    return true;
+  }
+  return false;
+}
+
+/** Same company + same job title (normalized), for prior-skip hide rules. */
+export function jobsMatchEmployerAndTitleDismiss(args: {
+  employerA: string | null | undefined;
+  titleA: string | null | undefined;
+  employerB: string | null | undefined;
+  titleB: string | null | undefined;
+}): boolean {
+  const employerA = normalizeEmployerForFingerprint(args.employerA);
+  const employerB = normalizeEmployerForFingerprint(args.employerB);
+  const titleA = normalizeTitleForFingerprint(args.titleA);
+  const titleB = normalizeTitleForFingerprint(args.titleB);
+  if (!employerA || !employerB || !titleA || !titleB) return false;
+  return (
+    employersMatchForDismiss(employerA, employerB) &&
+    titlesMatchForDismiss(titleA, titleB)
+  );
+}
+
 export function collectJobDedupKeys(args: {
   employer: string | null | undefined;
   title: string | null | undefined;

shared/src/settings-registry.ts

@@ -480,6 +480,13 @@ export const settingsRegistry = {
     parse: parseIntOrNull,
     serialize: serializeNullableNumber,
   },
+  googleJobsMaxJobsPerTerm: {
+    kind: "typed" as const,
+    schema: z.number().int().min(1).max(150),
+    default: (): number => 30,
+    parse: parseIntOrNull,
+    serialize: serializeNullableNumber,
+  },
   fourdayweekMaxJobsPerTerm: {
     kind: "typed" as const,
     schema: z.number().int().min(1).max(1000),
@@ -965,6 +972,10 @@ export const settingsRegistry = {
     kind: "string" as const,
     schema: z.string().trim().max(200),
   },
+  basicAuthActiveProfileByUser: {
+    kind: "string" as const,
+    schema: z.string().trim().max(10000),
+  },
   rxresumeBaseResumeId: {
     kind: "string" as const,
     schema: z.string().trim().max(200),

shared/src/testing/factories.ts

@@ -182,6 +182,7 @@ export const createAppSettings = (
     override: null,
   },
   activeProfileId: null,
+  basicAuthActiveProfileByUser: null,
   rxresumeBaseResumeId: null,
   rxresumeBaseResumeIdV4: null,
   rxresumeBaseResumeIdV5: null,
@@ -206,6 +207,7 @@ export const createAppSettings = (
   builtinMaxJobsPerTerm: { value: 100, default: 100, override: null },
   builtinMaxPagesPerTerm: { value: 3, default: 3, override: null },
   wellfoundMaxJobsPerTerm: { value: 50, default: 50, override: null },
+  googleJobsMaxJobsPerTerm: { value: 30, default: 30, override: null },
   fourdayweekMaxJobsPerTerm: { value: 50, default: 50, override: null },
   qajobsboardMaxJobsPerTerm: { value: 100, default: 100, override: null },
   arcRemoteJobsPaths: {

shared/src/types/settings.ts

@@ -218,6 +218,7 @@ export interface AppSettings {
   builtinMaxJobsPerTerm: Resolved<number>;
   builtinMaxPagesPerTerm: Resolved<number>;
   wellfoundMaxJobsPerTerm: Resolved<number>;
+  googleJobsMaxJobsPerTerm: Resolved<number>;
   fourdayweekMaxJobsPerTerm: Resolved<number>;
   qajobsboardMaxJobsPerTerm: Resolved<number>;
   arcRemoteJobsPaths: Resolved<string[]>;
@@ -270,6 +271,8 @@ export interface AppSettings {
 
   // Simple strings:
   activeProfileId: string | null;
+  /** JSON map of basic-auth username → search profile id when one login has multiple profiles. */
+  basicAuthActiveProfileByUser: string | null;
   rxresumeBaseResumeId: string | null;
   rxresumeBaseResumeIdV4: string | null;
   rxresumeBaseResumeIdV5: string | null;