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
# using multistage build, as we need dev deps to build the TS source code
FROM apify/actor-node:24-beta AS builder
# copy all files, install all dependencies (including dev deps) and build the project
COPY . ./
RUN rm -rf node_modules package-lock.json
RUN npm install --include=dev \
&& npm run build
# create final image
FROM apify/actor-node:24-beta
# copy only necessary files
COPY --from=builder /usr/src/app/packages ./packages
COPY --from=builder /usr/src/app/package.json ./
COPY --from=builder /usr/src/app/main.js ./
# install only prod deps
RUN rm -rf node_modules package-lock.json
RUN npm --quiet set progress=false \
&& npm install --only=prod --no-audit \
&& npm update --no-audit \
&& echo "Installed NPM packages:" \
&& (npm list --only=prod --all || true) \
&& echo "Node.js version:" \
&& node --version \
&& echo "NPM version:" \
&& npm --version
# run compiled code
CMD npm run start:prod