mirror of
https://github.com/clucraft/PriceGhost.git
synced 2026-04-26 01:06:23 +02:00
c96861fefb
When HTTP requests are blocked with 403 (e.g., B&H Photo's Cloudflare protection), the scraper now automatically retries using a headless Chrome browser via Puppeteer. Also updated Dockerfile to include Chromium dependencies for container deployment. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
76 lines
1.3 KiB
Docker
76 lines
1.3 KiB
Docker
# Build stage
|
|
FROM node:20-slim AS builder
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy package files
|
|
COPY package*.json ./
|
|
|
|
# Install dependencies
|
|
RUN npm install
|
|
|
|
# Copy source code
|
|
COPY . .
|
|
|
|
# Build TypeScript
|
|
RUN npm run build
|
|
|
|
# Production stage
|
|
FROM node:20-slim AS production
|
|
|
|
WORKDIR /app
|
|
|
|
# Install Chromium dependencies for Puppeteer
|
|
RUN apt-get update && apt-get install -y \
|
|
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 \
|
|
libxss1 \
|
|
xdg-utils \
|
|
--no-install-recommends \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Set Puppeteer to use installed Chromium
|
|
ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD=true
|
|
ENV PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium
|
|
|
|
# Copy package files
|
|
COPY package*.json ./
|
|
|
|
# Install production dependencies only
|
|
RUN npm install --omit=dev
|
|
|
|
# Copy built files from builder
|
|
COPY --from=builder /app/dist ./dist
|
|
|
|
# Create non-root user
|
|
RUN groupadd -r nodejs && useradd -r -g nodejs nodejs
|
|
|
|
# Change ownership of app directory
|
|
RUN chown -R nodejs:nodejs /app
|
|
|
|
USER nodejs
|
|
|
|
# Expose port
|
|
EXPOSE 3001
|
|
|
|
# Set environment variables
|
|
ENV NODE_ENV=production
|
|
ENV PORT=3001
|
|
|
|
# Start the application
|
|
CMD ["node", "dist/index.js"]
|