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: ensure `PlaywrightGotoOptions` won't result in `unknown` when playwright is not installed (#2995)
Martin Adámek93eba38b9cd8
diff --git a/packages/playwright-crawler/src/internals/playwright-crawler.ts b/packages/playwright-crawler/src/internals/playwright-crawler.tsindex d18668ade..686f540c3 100644--- a/packages/playwright-crawler/src/internals/playwright-crawler.ts+++ b/packages/playwright-crawler/src/internals/playwright-crawler.ts@@ -23,7 +23,7 @@ export interface PlaywrightCrawlingContext<UserData extends Dictionary = DictionPlaywrightContextUtils {}export interface PlaywrightHook extends BrowserHook<PlaywrightCrawlingContext, PlaywrightGotoOptions> {}export interface PlaywrightRequestHandler extends BrowserRequestHandler<LoadedContext<PlaywrightCrawlingContext>> {}-export type PlaywrightGotoOptions = Parameters<Page['goto']>[1];+export type PlaywrightGotoOptions = Dictionary & Parameters<Page['goto']>[1];export interface PlaywrightCrawlerOptionsextends BrowserCrawlerOptions<PlaywrightCrawlingContext, { browserPlugins: [PlaywrightPlugin] }> {diff --git a/renovate.json b/renovate.jsonindex 833c7f5f7..a9b7d05f5 100644--- a/renovate.json+++ b/renovate.json@@ -24,5 +24,5 @@}],"schedule": ["every weekday"],- "ignoreDeps": ["crawlee", "cheerio", "playwright", "yarn"]+ "ignoreDeps": ["crawlee", "cheerio", "playwright"]}