From c70d64d4cde2bf2acc5c4164eef79c40fd58aa42 Mon Sep 17 00:00:00 2001 From: Mael Date: Sun, 22 Jun 2025 19:08:21 +0200 Subject: feat(workers): migrate from puppeteer to playwright (#1296) * feat: convert to playwright Convert crawling to use Playwright instead of Chrome. - Update Dockerfile to include Playwright - Update crawler worker to use Playwright API - Update dependencies * feat: convert from Puppeteer to Playwright for crawling * feat: update docker-compose * use separate browser context for better isolation * skip chrome download in linux script * readd the stealth plugin --------- Co-authored-by: Mohamed Bassem --- docker/Dockerfile | 2 +- docker/Dockerfile.dev | 2 +- docker/docker-compose.dev.yml | 2 ++ 3 files changed, 4 insertions(+), 2 deletions(-) (limited to 'docker') diff --git a/docker/Dockerfile b/docker/Dockerfile index 54e337f5..7a3f4cb2 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -13,7 +13,7 @@ RUN apk add --no-cache libc6-compat make g++ py3-pip linux-headers COPY . . ENV NEXT_TELEMETRY_DISABLED 1 -ENV PUPPETEER_SKIP_DOWNLOAD true +ENV PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1 RUN pnpm install --frozen-lockfile # Build the db migration script diff --git a/docker/Dockerfile.dev b/docker/Dockerfile.dev index 50048a6d..d4051cc5 100644 --- a/docker/Dockerfile.dev +++ b/docker/Dockerfile.dev @@ -11,4 +11,4 @@ RUN corepack enable COPY . . ENV NEXT_TELEMETRY_DISABLED 1 -ENV PUPPETEER_SKIP_DOWNLOAD true +ENV PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1 diff --git a/docker/docker-compose.dev.yml b/docker/docker-compose.dev.yml index 0384ced5..3eb62030 100644 --- a/docker/docker-compose.dev.yml +++ b/docker/docker-compose.dev.yml @@ -20,6 +20,8 @@ services: chrome: image: gcr.io/zenika-hub/alpine-chrome:123 restart: unless-stopped + ports: + - 9222:9222 command: - --no-sandbox - --disable-gpu -- cgit v1.2.3-70-g09d2