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
README - fixing typo
Marek Trunkat1b00cf158682
diff --git a/README.md b/README.mdindex c8e28b895..7ae6b4f58 100644--- a/README.md+++ b/README.md@@ -364,7 +364,7 @@ Apify.main(async () => {// Fetch the page HTMLconst html = await requestPromise(request.url);- // Store the HTML and URL to the default dataset+ // Store the HTML and URL to the default dataset.await Apify.pushData({url: request.url,html,@@ -478,7 +478,7 @@ The results are stored to the default dataset. In local configuration, the resulconst Apify = require('apify');Apify.main(async () => {- // Create and initialize an instance of the RequestList class that contains the start URL+ // Create and initialize an instance of the RequestList class that contains the start URL.const requestList = new Apify.RequestList({sources: [{ url: 'http://www.ycombinator.com/' },@@ -530,7 +530,7 @@ Apify.main(async () => {// Store the results to the default dataset.await Apify.pushData(data);- // Find the link to the next page using Puppeteer functions+ // Find the link to the next page using Puppeteer functions.let nextHref;try {nextHref = await page.$eval('.morelink', el => el.href);diff --git a/examples/basic_crawler.js b/examples/basic_crawler.jsindex 500b88c1c..c615e585b 100644--- a/examples/basic_crawler.js+++ b/examples/basic_crawler.js@@ -42,7 +42,7 @@ Apify.main(async () => {// Fetch the page HTMLconst html = await requestPromise(request.url);- // Store the HTML and URL to the default dataset+ // Store the HTML and URL to the default dataset.await Apify.pushData({url: request.url,html,diff --git a/examples/puppeteer_crawler.js b/examples/puppeteer_crawler.jsindex 155bca9fd..9a8991312 100644--- a/examples/puppeteer_crawler.js+++ b/examples/puppeteer_crawler.js@@ -11,7 +11,7 @@const Apify = require('apify');Apify.main(async () => {- // Create and initialize an instance of the RequestList class that contains the start URL+ // Create and initialize an instance of the RequestList class that contains the start URL.const requestList = new Apify.RequestList({sources: [{ url: 'http://www.ycombinator.com/' },@@ -63,7 +63,7 @@ Apify.main(async () => {// Store the results to the default dataset.await Apify.pushData(data);- // Find the link to the next page using Puppeteer functions+ // Find the link to the next page using Puppeteer functions.let nextHref;try {nextHref = await page.$eval('.morelink', el => el.href);