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
Fix loadedUrl crashing validations
Ondra Urban677903da8a06
diff --git a/package.json b/package.jsonindex ebcbe5bcc..a0dce556e 100644--- a/package.json+++ b/package.json@@ -60,7 +60,7 @@"@types/puppeteer": "^3.0.2","@types/socket.io": "^2.1.11","@types/tough-cookie": "^4.0.0",- "apify-client": "1.0.0-beta.11",+ "apify-client": "1.0.0-beta.12","apify-shared": "^0.5.0","cheerio": "^1.0.0-rc.3","content-type": "^1.0.4",diff --git a/src/crawlers/basic_crawler.js b/src/crawlers/basic_crawler.jsindex 2a0854918..1d4e46143 100644--- a/src/crawlers/basic_crawler.js+++ b/src/crawlers/basic_crawler.js@@ -421,7 +421,7 @@ class BasicCrawler {if (!request) return;// Reset loadedUrl so an old one is not carried over to retries.- request.loadedUrl = null;+ request.loadedUrl = undefined;const statisticsId = request.id || request.uniqueKey;this.stats.startJob(statisticsId);