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
docs: fix code examples for pre/post navigation hooks
Martin Adámekd0d7d80392e0
diff --git a/src/crawlers/browser_crawler.js b/src/crawlers/browser_crawler.jsindex 30db8d2b6..53383353d 100644--- a/src/crawlers/browser_crawler.js+++ b/src/crawlers/browser_crawler.js@@ -125,7 +125,7 @@ import { AutoscaledPoolOptions } from '../autoscaling/autoscaled_pool';* async (crawlingContext, gotoOptions) => {* const { page } = crawlingContext;* await page.evaluate((attr) => { window.foo = attr; }, 'bar');- * }+ * },* ]* ```* @property {Array<Hook>} [postNavigationHooks]@@ -139,7 +139,7 @@ import { AutoscaledPoolOptions } from '../autoscaling/autoscaled_pool';* if (hasCaptcha(page)) {* await solveCaptcha (page);* }- * };+ * },* ]* ```* @property {RequestList} [requestList]diff --git a/src/crawlers/cheerio_crawler.js b/src/crawlers/cheerio_crawler.jsindex 5384209b8..210750b58 100644--- a/src/crawlers/cheerio_crawler.js+++ b/src/crawlers/cheerio_crawler.js@@ -205,7 +205,7 @@ const CHEERIO_OPTIMIZED_AUTOSCALED_POOL_OPTIONS = {* preNavigationHooks: [* async (crawlingContext, requestAsBrowserOptions) => {* requestAsBrowserOptions.forceUrlEncoding = true;- * }+ * },* ]* ```* @property {Array<Hook>} [postNavigationHooks]@@ -216,7 +216,7 @@ const CHEERIO_OPTIMIZED_AUTOSCALED_POOL_OPTIONS = {* postNavigationHooks: [* async (crawlingContext) => {* // ...- * };+ * },* ]* ```* @property {string[]} [additionalMimeTypes]@@ -313,7 +313,7 @@ const CHEERIO_OPTIMIZED_AUTOSCALED_POOL_OPTIONS = {* preNavigationHooks: [* (crawlingContext, requestAsBrowserOptions) => {* requestAsBrowserOptions.forceUrlEncoding = true;- * }+ * },* ]* ```*diff --git a/src/crawlers/playwright_crawler.js b/src/crawlers/playwright_crawler.jsindex 09bf87b3a..605723e51 100644--- a/src/crawlers/playwright_crawler.js+++ b/src/crawlers/playwright_crawler.js@@ -112,7 +112,7 @@ import { gotoExtended } from '../playwright_utils';* preNavigationHooks: [* async (crawlingContext, gotoOptions) => {* await page.evaluate((attr) => { window.foo = attr; }, 'bar');- * }+ * },* ]* ```* @property {Array<PlaywrightHook>} [postNavigationHooks]@@ -126,7 +126,7 @@ import { gotoExtended } from '../playwright_utils';* if (hasCaptcha(page)) {* await solveCaptcha (page);* }- * };+ * },* ]* ```* @property {PlaywrightLaunchContext} [launchContext]diff --git a/src/crawlers/puppeteer_crawler.js b/src/crawlers/puppeteer_crawler.jsindex a08990458..7188f2e50 100644--- a/src/crawlers/puppeteer_crawler.js+++ b/src/crawlers/puppeteer_crawler.js@@ -113,7 +113,7 @@ import { BrowserPoolOptions } from 'browser-pool';* async (crawlingContext, gotoOptions) => {* const { page } = crawlingContext;* await page.evaluate((attr) => { window.foo = attr; }, 'bar');- * }+ * },* ]* ```* @property {Array<PuppeteerHook>} [postNavigationHooks]@@ -127,7 +127,7 @@ import { BrowserPoolOptions } from 'browser-pool';* if (hasCaptcha(page)) {* await solveCaptcha (page);* }- * };+ * },* ]* ```* @property {RequestList} [requestList]