From f272f9338091733fe2f1f725d26d0c5646332111 Mon Sep 17 00:00:00 2001
From: Adityaaa <144815351+addydude@users.noreply.github.com>
Date: Mon, 9 Nov 2026 08:39:45 +0530
Subject: [PATCH] build: add Docker image for scrape mode

Slim python:3.12 image with WebVac installed from source and Patchright
Chromium ready to launch. /data is the working directory so scan output
can be volume-mounted. The optional De-Caffeinator VAPT task is left out
on purpose (submodule + Node.js) to keep the image lean.

Closes #4
---
 .dockerignore | 16 ++++++++++++++++
 Dockerfile    | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)
 create mode 100644 .dockerignore
 create mode 100644 Dockerfile

diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..3b2a1ee
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,16 @@
+.git
+.github
+.venv
+__pycache__
+*.pyc
+.pytest_cache
+scraped_data
+decaffeinator
+docs
+examples
+tests
+.env
+capsolver.key
+proxies.txt
+auth_creds.json
+sessions
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..f538b2f
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,32 @@
+# WebVac — asyncio dynamic web scraper (scrape/crawl mode).
+#
+# Build:  docker build -t webvac .
+# Doctor: docker run --rm webvac --doctor
+# Scrape: docker run --rm -v webvac-data:/data webvac --url https://example.com --mode single
+#
+# Scan output is written under /data/scraped_data (the working directory),
+# so mount a volume at /data to keep it. The optional De-Caffeinator VAPT
+# task is not included: it needs the decaffeinator submodule and Node.js,
+# which are deliberately left out to keep this image lean.
+FROM python:3.12-slim
+
+ENV PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1
+
+WORKDIR /app
+
+# Install the package first (README is referenced by pyproject metadata).
+COPY pyproject.toml README.md ./
+COPY webvac ./webvac
+COPY run.py ./
+
+RUN pip install --upgrade pip \
+    && pip install . \
+    && python -m patchright install --with-deps chromium
+
+# Runtime working directory: scraped_data/ lands here.
+RUN mkdir -p /data
+WORKDIR /data
+
+ENTRYPOINT ["webvac"]
+CMD ["--help"]