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
repaired validation
Petr Patekaabf2bf61b25
diff --git a/src/cheerio_crawler.js b/src/cheerio_crawler.jsindex cd19fde29..edf2abb8d 100644--- a/src/cheerio_crawler.js+++ b/src/cheerio_crawler.js@@ -238,7 +238,7 @@ class CheerioCrawler {checkParamOrThrow(apifyProxyGroups, 'options.apifyProxyGroups', 'Maybe [String]');checkParamOrThrow(apifyProxySession, 'options.apifyProxySession', 'Maybe String');checkParamOrThrow(proxyUrls, 'options.proxyUrls', 'Maybe [String]');- checkParamOrThrow(handlePageFunction, 'options.prepareRequestFunction', 'Maybe Function');+ checkParamOrThrow(prepareRequestFunction, 'options.prepareRequestFunction', 'Maybe Function');// Enforce valid proxy configurationif (proxyUrls && !proxyUrls.length) throw new Error('Parameter "options.proxyUrls" of type Array must not be empty');if (useApifyProxy && proxyUrls) throw new Error('Cannot combine "options.useApifyProxy" with "options.proxyUrls"!');