Add file-type and host filters with a 4chan default

media-scrape/src/store.ts

@@ -108,6 +108,8 @@ export interface MediaFilterOptions {
     authorId?: string;
     authorIds?: string[];
     cachedOnly?: boolean;
+    exts?: string[];
+    excludeHosts?: string[];
     aspect?: string;
     resolution?: string;
     after?: string;
@@ -493,6 +495,17 @@ export class ScrapeStore {
         if (options.cachedOnly) {
             conditions.push("preview_hash IS NOT NULL");
         }
+        if (options.exts?.length) {
+            const clauses = options.exts.map(() => "(lower(url) LIKE ? OR lower(content_type) LIKE ?)");
+            conditions.push(`(${clauses.join(" OR ")})`);
+            for (const ext of options.exts) {
+                values.push(`%.${ext.toLowerCase()}%`, `%/${ext.toLowerCase()}%`);
+            }
+        }
+        for (const host of options.excludeHosts ?? []) {
+            conditions.push("lower(url) NOT LIKE ?");
+            values.push(`%${host.toLowerCase()}%`);
+        }
         if (options.after) {
             conditions.push("posted_at >= ?");
             values.push(options.after);