Dockerize the puppeteer-parse service and add to docker-compose

docker-compose.yml

@@ -57,7 +57,7 @@ services:
       - SSO_JWT_SECRET=some_sso_secret
       - CLIENT_URL=http://localhost:3000
       - GATEWAY_URL=http://localhost:8080/api
-      - PUPPETEER_TASK_HANDLER_URL=http://host.docker.internal:9090/
+      - PUPPETEER_TASK_HANDLER_URL=http://content-fetch:9090/
       - REMINDER_TASK_HANDLER_URL=/svc/reminders/trigger
     depends_on:
       migrate:
@@ -84,19 +84,16 @@ services:
       api:
         condition: service_healthy
 
-  # TODO: Needs some work to get this running on M1
+  content-fetch:
-  # content-fetch:
+    build:
-  #   platform: linux/amd64
+      context: .
-  #   build:
+      dockerfile: ./packages/puppeteer-parse/Dockerfile
-  #     context: .
+    container_name: "omnivore-content-fetch"
-  #     dockerfile: ./packages/puppeteer-parse/Dockerfile
+    expose:
-  #   container_name: "omnivore-content-fetch"
+      - 9090
-  #   ports:
+    environment:
-  #     - "9090:8080"
+      - JWT_SECRET=some_secret
-  #   environment:
+      - REST_BACKEND_ENDPOINT=http://api:8080/api
-  #     - JWT_SECRET=some_secret
+    depends_on:
-  #     - PREVIEW_IMAGE_BUCKET='fake-bucket'
+      api:
-  #     - REST_BACKEND_ENDPOINT=http://api:4000/api
+        condition: service_healthy
-  #     - CHROMIUM_PATH=/usr/bin/google-chrome-stable
-  #     - IS_LOCAL=true
-  #     - ALLOWED_ORIGINS=http://localhost:8080

packages/puppeteer-parse/Dockerfile

@@ -0,0 +1,112 @@
+# FROM node:14-slim
+
+# # Taken from pu
+
+# # Install latest chrome dev package and fonts to support major charsets (Chinese, Japanese, Arabic, Hebrew, Thai and a few others)
+# # Note: this installs the necessary libs to make the bundled version of Chromium that Puppeteer
+# # installs, work.
+# RUN apt-get update \
+#     && apt-get install -y wget gnupg \
+#     && wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | apt-key add - \
+#     && sh -c 'echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/google.list' \
+#     && apt-get update \
+#     && apt-get install -y google-chrome-stable fonts-ipafont-gothic fonts-wqy-zenhei fonts-thai-tlwg fonts-kacst fonts-freefont-ttf libxss1 \
+#       --no-install-recommends \
+#     && rm -rf /var/lib/apt/lists/*
+
+# ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD true
+# ENV CHROMIUM_PATH "/usr/bin/google-chrome-stable"
+
+# ------------------------
+
+# FROM --platform=linux/arm64 node:14.18
+
+# RUN apt-get update \
+#   && apt-get install -y chromium \
+#   && apt-get install -y ca-certificates \
+#   fonts-liberation \
+#   libappindicator3-1 \
+#   libasound2 \
+#   libatk-bridge2.0-0 \
+#   libatk1.0-0 \
+#   libc6 \
+#   libcairo2 \
+#   libcups2 \
+#   libdbus-1-3 \
+#   libexpat1 \
+#   libfontconfig1 \
+#   libgbm1 \
+#   libgcc1 \
+#   libglib2.0-0 \
+#   libgtk-3-0 \
+#   libnspr4 \
+#   libnss3 \
+#   libpango-1.0-0 \
+#   libpangocairo-1.0-0 \
+#   libstdc++6 \
+#   libx11-6 \
+#   libx11-xcb1 \
+#   libxcb1 \
+#   libxcomposite1 \
+#   libxcursor1 \
+#   libxdamage1 \
+#   libxext6 \
+#   libxfixes3 \
+#   libxi6 \
+#   libxrandr2 \
+#   libxrender1 \
+#   libxss1 \
+#   libxtst6 \
+#   lsb-release \
+#   wget \
+#   xdg-utils
+
+FROM node:14.18-alpine
+
+# Installs latest Chromium (92) package.
+RUN apk add --no-cache \
+      chromium \
+      nss \
+      freetype \
+      harfbuzz \
+      ca-certificates \
+      ttf-freefont \
+      nodejs \
+      yarn
+
+# Tell Puppeteer to skip installing Chrome. We'll be using the installed package.
+ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD=true \
+    PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium-browser
+
+# Puppeteer v10.0.0 works with Chromium 92.
+RUN yarn add puppeteer@10.0.0
+
+# Add user so we don't need --no-sandbox.
+RUN addgroup -S pptruser && adduser -S -g pptruser pptruser \
+    && mkdir -p /home/pptruser/Downloads /app \
+    && chown -R pptruser:pptruser /home/pptruser \
+    && chown -R pptruser:pptruser /app
+
+# Run everything after as non-privileged user.
+WORKDIR /app
+
+ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD true
+ENV CHROMIUM_PATH /usr/bin/chromium-browser
+ENV LAUNCH_HEADLESS=true
+
+COPY package.json .
+COPY yarn.lock .
+COPY tsconfig.json .
+COPY .prettierrc .
+COPY .eslintrc .
+
+COPY /packages/puppeteer-parse/package.json ./packages/puppeteer-parse/package.json
+
+RUN yarn install --pure-lockfile
+
+ADD /packages/puppeteer-parse ./packages/puppeteer-parse
+
+EXPOSE 8080
+
+# USER pptruser
+ENTRYPOINT ["yarn", "workspace", "@omnivore/puppeteer-parse", "start"]

packages/puppeteer-parse/index.js

@@ -122,7 +122,7 @@ const getBrowserPromise = (async () => {
     args: chromium.args,
     defaultViewport: { height: 1080, width: 1920 },
     executablePath: process.env.CHROMIUM_PATH || (await chromium.executablePath),
-    headless: process.env.IS_LOCAL ? false : chromium.headless,
+    headless: process.env.LAUNCH_HEADLESS ? true : chromium.headless,
     timeout: 0,
   });
 })();