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
chore: backport https://github.com/apify/apify-ts/pull/57 (#1312)
Vlad Frangu121ec85ba345
diff --git a/src/enqueue_links/click_elements.js b/src/enqueue_links/click_elements.jsindex ab65964a2..4d1f6c3e0 100644--- a/src/enqueue_links/click_elements.js+++ b/src/enqueue_links/click_elements.js@@ -409,6 +409,7 @@ async function waitForPageIdle({ page, waitForPageIdleMillis, maxWaitForPageIdlereturn new Promise((resolve) => {let timeout;let maxTimeout;+ const context = page.browserContext();function newTabTracker(target) {if (isTargetRelevant(page, target)) activityHandler();@@ -431,7 +432,7 @@ async function waitForPageIdle({ page, waitForPageIdleMillis, maxWaitForPageIdlefunction finish() {page.removeListener('request', activityHandler);page.removeListener('framenavigated', activityHandler);- page.removeListener('targetcreated', newTabTracker);+ context.removeListener('targetcreated', newTabTracker);resolve();}@@ -439,7 +440,7 @@ async function waitForPageIdle({ page, waitForPageIdleMillis, maxWaitForPageIdletimeout = activityHandler(); // We call this once manually in case there would be no requests at all.page.on('request', activityHandler);page.on('framenavigated', activityHandler);- page.on('targetcreated', newTabTracker);+ context.on('targetcreated', newTabTracker);});}