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
refactor: make the last resort timeout much larger
Martin Adámek9f46835a971a
diff --git a/src/crawlers/basic_crawler.js b/src/crawlers/basic_crawler.jsindex 382a9519b..ce8d72ce2 100644--- a/src/crawlers/basic_crawler.js+++ b/src/crawlers/basic_crawler.js@@ -475,10 +475,11 @@ export class BasicCrawler {* @private*/async timeoutForRunTaskFunction() {+ const timeout = 600e3; // 10 min last resort timeout for stuck runsawait addTimeoutToPromise(() => this._runTaskFunction(),- this.handleRequestTimeoutMillis * 2,- `_runTaskFunction timed out after ${(this.handleRequestTimeoutMillis * 2) / 1000} seconds.`,+ timeout,+ `_runTaskFunction timed out after ${(timeout) / 1000} seconds.`,);}