fix(discovery): block countries in vague locations via job description

QAJobsBoard and similar feeds often store Worldwide/Remote while the real
country is only in the description. Scan title and description when location
is vague, and prefer concrete locations from QAJobsBoard postings.

Co-authored-by: Cursor <cursoragent@cursor.com>

extractors/qajobsboard/manifest.ts

@@ -81,14 +81,47 @@ function salaryLabel(raw: SalaryBand | undefined): string | undefined {
   return schedule.trim() || undefined;
 }
 
+const VAGUE_LOCATION_LABELS = new Set([
+  "worldwide",
+  "global",
+  "anywhere",
+  "remote",
+  "unknown",
+]);
+
+function isVagueLocationLabel(value: string): boolean {
+  return VAGUE_LOCATION_LABELS.has(value.trim().toLowerCase());
+}
+
+function extractJobLocationFromDescription(
+  html: string | undefined,
+): string | undefined {
+  if (!html) return undefined;
+  const text = stripHtml(html);
+  const match = text.match(
+    /\bjob\s+location\s*:\s*([^\n.]{2,120})/i,
+  );
+  if (!match?.[1]) return undefined;
+  const extracted = match[1].trim();
+  return extracted || undefined;
+}
+
 function locationLabel(job: QaJobBoardlyJob): string {
   const limits = Array.isArray(job.location_limits)
-    ? job.location_limits.filter(
-        (v): v is string => typeof v === "string" && v.trim().length > 0,
-      )
+    ? job.location_limits
+        .map((v) => (typeof v === "string" ? v.trim() : ""))
+        .filter((v) => v.length > 0 && !isVagueLocationLabel(v))
     : [];
   if (limits.length > 0) return limits.join(", ");
+
   const loc = asString(job.location);
+  if (loc && !isVagueLocationLabel(loc)) return loc;
+
+  const fromDescription = extractJobLocationFromDescription(
+    job.description?.html,
+  );
+  if (fromDescription) return fromDescription;
+
   if (loc) return loc;
   return "Unknown";
 }