feat(crawl): URL deduplication

This commit is contained in:
Gergő Móricz
2024-11-08 16:22:06 +01:00
parent 25e94ffd28
commit 6ecf24b85e
4 changed files with 50 additions and 7 deletions
+3
View File
@@ -86,6 +86,9 @@ export interface CrawlScrapeOptions {
country?: string;
languages?: string[];
};
skipTlsVerification?: boolean;
removeBase64Images?: boolean;
deduplicateSimilarURLs?: boolean;
}
export type Action = {