Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
TypeScript apifyautomationcrawlercrawlingheadlessheadless-chromejavascriptnodejsnpmplaywrightpuppeteerscraperscrapingtypescriptweb-crawlerweb-crawlingweb-scraping
docs: improve warning message on empty RequestList (#2232)
Jindřich Bärf6b7e288df0d
diff --git a/packages/core/src/storages/request_list.ts b/packages/core/src/storages/request_list.tsindex 9b7848392..9eeb4f80e 100644--- a/packages/core/src/storages/request_list.ts+++ b/packages/core/src/storages/request_list.ts@@ -681,7 +681,7 @@ export class RequestList {// Skip if resource contained no URLs.if (!urlsArr.length) {- this.log.warning('list fetched, but it is empty.', { requestsFromUrl, regex });+ this.log.warning('The fetched list contains no valid URLs.', { requestsFromUrl, regex });return [];}diff --git a/packages/core/src/storages/request_provider.ts b/packages/core/src/storages/request_provider.tsindex b53202c4d..64995532c 100644--- a/packages/core/src/storages/request_provider.ts+++ b/packages/core/src/storages/request_provider.ts@@ -576,7 +576,7 @@ export abstract class RequestProvider implements IStorage {// Skip if resource contained no URLs.if (!urlsArr.length) {- this.log.warning('list fetched, but it is empty.', { requestsFromUrl, regex });+ this.log.warning('The fetched list contains no valid URLs.', { requestsFromUrl, regex });return [];}