add Google News integration and enhance crawler capabilities

Dockerfile

@@ -1,35 +1,11 @@
-FROM node:22-bookworm-slim
+FROM duriin-api-base:latest
 
 ENV NODE_ENV=production
-ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-  chromium \
-  fonts-liberation \
-  libasound2 \
-  libatk-bridge2.0-0 \
-  libatk1.0-0 \
-  libcups2 \
-  libdbus-1-3 \
-  libdrm2 \
-  libgbm1 \
-  libgtk-3-0 \
-  libnspr4 \
-  libnss3 \
-  libx11-xcb1 \
-  libxcomposite1 \
-  libxdamage1 \
-  libxfixes3 \
-  libxrandr2 \
-  libxshmfence1 \
-  xdg-utils \
-  && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
 COPY package.json package-lock.json ./
 RUN npm ci --omit=dev \
-  && npx playwright install chromium \
   && npm cache clean --force \
   && mkdir -p /data \
   && ln -s /data/archive.sqlite /app/archive.sqlite

Dockerfile.base

@@ -0,0 +1,31 @@
+FROM node:22-bookworm-slim
+
+ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  chromium \
+  fonts-liberation \
+  libasound2 \
+  libatk-bridge2.0-0 \
+  libatk1.0-0 \
+  libcups2 \
+  libdbus-1-3 \
+  libdrm2 \
+  libgbm1 \
+  libgtk-3-0 \
+  libnspr4 \
+  libnss3 \
+  libx11-xcb1 \
+  libxcomposite1 \
+  libxdamage1 \
+  libxfixes3 \
+  libxrandr2 \
+  libxshmfence1 \
+  xdg-utils \
+  && rm -rf /var/lib/apt/lists/*
+
+COPY package.json package-lock.json /tmp/playwright-install/
+RUN cd /tmp/playwright-install \
+  && npm ci --omit=dev \
+  && npx playwright install chromium \
+  && rm -rf /tmp/playwright-install

rebuild-api.sh

@@ -3,6 +3,11 @@ set -euo pipefail
 
 cd "$(dirname "$0")"
 
+if [[ "${1:-}" == "--base" ]]; then
+  echo "Rebuilding base image (chromium + system deps)..."
+  sudo docker build -f Dockerfile.base -t duriin-api-base:latest .
+fi
+
 sudo docker compose down
 sudo env DOCKER_BUILDKIT=0 COMPOSE_DOCKER_CLI_BUILD=0 docker compose build --no-cache
 sudo docker compose up -d --no-build