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: remove invalid example
Martin Adámekfedc25490ba9
diff --git a/docs/examples/puppeteer_with_proxy.mdx b/docs/examples/puppeteer_with_proxy.mdxdeleted file mode 100644index 4b88b1d1a..000000000--- a/docs/examples/puppeteer_with_proxy.mdx+++ /dev/null@@ -1,29 +0,0 @@-----id: puppeteer-with-proxy-title: Puppeteer with proxy------import CodeBlock from '@theme/CodeBlock';--import CrawlSource from '!!raw-loader!./puppeteer_with_proxy.ts';--:::danger--FIXME: is this staying?--:::--This example demonstrates how to load pages in headless Chrome / Puppeteer over [Apify Proxy](https://docs.crawlee.dev/proxy).--To make it work, you'll need an Apify account with access to the proxy. Visit the [Apify platform introduction](/docs/guides/apify-platform) to find-how to log into your account from the SDK.--:::tip--To run this example on the Apify Platform, select the `apify/actor-node-puppeteer-chrome` image for your Dockerfile.--:::--<CodeBlock className="language-js">- {CrawlSource}-</CodeBlock>diff --git a/docs/examples/puppeteer_with_proxy.ts b/docs/examples/puppeteer_with_proxy.tsdeleted file mode 100644index 90e0dabb7..000000000--- a/docs/examples/puppeteer_with_proxy.ts+++ /dev/null@@ -1,20 +0,0 @@-import { PuppeteerCrawler, ProxyConfiguration } from 'crawlee';--// Proxy connection is automatically established in the Crawler-const proxyConfiguration = new ProxyConfiguration();--const crawler = new PuppeteerCrawler({- proxyConfiguration,- async requestHandler({ page, log }) {- const status = await page.$eval('td.status', (el) => el.textContent);- log.info(`Proxy Status: ${status}`);- },-});--await crawler.addRequests(['http://proxy.crawlee.dev']);--console.log('Running Puppeteer script...');--await crawler.run();--console.log('Puppeteer closed.');diff --git a/website/versioned_docs/version-3.0/examples/puppeteer_with_proxy.mdx b/website/versioned_docs/version-3.0/examples/puppeteer_with_proxy.mdxdeleted file mode 100644index 4b88b1d1a..000000000--- a/website/versioned_docs/version-3.0/examples/puppeteer_with_proxy.mdx+++ /dev/null@@ -1,29 +0,0 @@-----id: puppeteer-with-proxy-title: Puppeteer with proxy------import CodeBlock from '@theme/CodeBlock';--import CrawlSource from '!!raw-loader!./puppeteer_with_proxy.ts';--:::danger--FIXME: is this staying?--:::--This example demonstrates how to load pages in headless Chrome / Puppeteer over [Apify Proxy](https://docs.crawlee.dev/proxy).--To make it work, you'll need an Apify account with access to the proxy. Visit the [Apify platform introduction](/docs/guides/apify-platform) to find-how to log into your account from the SDK.--:::tip--To run this example on the Apify Platform, select the `apify/actor-node-puppeteer-chrome` image for your Dockerfile.--:::--<CodeBlock className="language-js">- {CrawlSource}-</CodeBlock>diff --git a/website/versioned_docs/version-3.0/examples/puppeteer_with_proxy.ts b/website/versioned_docs/version-3.0/examples/puppeteer_with_proxy.tsdeleted file mode 100644index 90e0dabb7..000000000--- a/website/versioned_docs/version-3.0/examples/puppeteer_with_proxy.ts+++ /dev/null@@ -1,20 +0,0 @@-import { PuppeteerCrawler, ProxyConfiguration } from 'crawlee';--// Proxy connection is automatically established in the Crawler-const proxyConfiguration = new ProxyConfiguration();--const crawler = new PuppeteerCrawler({- proxyConfiguration,- async requestHandler({ page, log }) {- const status = await page.$eval('td.status', (el) => el.textContent);- log.info(`Proxy Status: ${status}`);- },-});--await crawler.addRequests(['http://proxy.crawlee.dev']);--console.log('Running Puppeteer script...');--await crawler.run();--console.log('Puppeteer closed.');