🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
ops: improve the layering of the docker image
Karim shoair0cf3bcf3aa16
diff --git a/Dockerfile b/Dockerfileindex 3524d3e..5515bf3 100644--- a/Dockerfile+++ b/Dockerfile@@ -1,31 +1,34 @@-FROM python:3.12-slim-trixie AS builder+FROM python:3.12-slim-trixieCOPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/# Set environment variables-ENV DEBIAN_FRONTEND=noninteractive-ENV PYTHONUNBUFFERED=1-ENV PYTHONDONTWRITEBYTECODE=1--ADD . /app+ENV DEBIAN_FRONTEND=noninteractive \+ PYTHONUNBUFFERED=1 \+ PYTHONDONTWRITEBYTECODE=1WORKDIR /app-# Install dependencies+# Copy dependency file first for better layer caching+COPY pyproject.toml ./++# Install dependencies onlyRUN --mount=type=cache,target=/root/.cache/uv \- --mount=type=bind,source=pyproject.toml,target=pyproject.toml \uv sync --no-install-project --all-extras --compile-bytecode-# Install all browsers and their deps-RUN uv run playwright install-deps chromium firefox-RUN uv run playwright install chromium-RUN uv run camoufox fetch --browserforge+# Copy source code+COPY . .-# Sync the project+# Install browsers and project in one optimized layerRUN --mount=type=cache,target=/root/.cache/uv \- uv sync --all-extras --compile-bytecode--# Clean up to save space-RUN rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*+ --mount=type=cache,target=/var/cache/apt \+ --mount=type=cache,target=/var/lib/apt \+ apt-get update && \+ uv run playwright install-deps chromium firefox && \+ uv run playwright install chromium && \+ uv run camoufox fetch --browserforge && \+ uv sync --all-extras --compile-bytecode && \+ apt-get clean && \+ rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*# Expose port for MCP server HTTP transportEXPOSE 8000diff --git a/pyproject.toml b/pyproject.tomlindex 64a36a7..8b2a555 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,8 @@ build-backend = "setuptools.build_meta"[project]name = "scrapling"-dynamic = ["version"]+# Static version instead of dynamic version so we can get better layer caching while building docker, check the docker file to understand+version = "0.3.6"description = "Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!"readme = {file = "README.md", content-type = "text/markdown"}license = {file = "LICENSE"}@@ -99,9 +100,6 @@ scrapling = "scrapling.cli:main"zip-safe = falseinclude-package-data = true-[tool.setuptools.dynamic]-version = {attr = "scrapling.__version__"}-[tool.setuptools.packages.find]where = ["."]include = ["scrapling*"]\ No newline at end of file