From 8e4801f3d3a6b43b7bc9dcd505fbd735e9da40b2 Mon Sep 17 00:00:00 2001
From: Lilia Kai <liliakai@gmail.com>
Date: Tue, 12 Sep 2023 16:03:11 +0200
Subject: [PATCH] Run browsertrix in docker on the host

Install docker in the container

Add a named volume called `browsertrix`

Mount the named volume in the worker at /crawls

Expose the host docker socket

Override the environment variable from auto-archiver's Dockerfile so
that it will call docker.

This will require setting new configs in orchestration.yaml:

 wacz_archiver_enricher:
  browsertrix_home: auto-archiver-api_browsertrix
  wacz_collections: /crawls
---
 docker-compose.yml | 8 ++++++++
 src/Dockerfile     | 2 ++
 2 files changed, 10 insertions(+)

diff --git a/docker-compose.yml b/docker-compose.yml
index fa99160..43892a3 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,5 +1,8 @@
 version: '3.8'
 
+volumes:
+  browsertrix:
+
 services:
 
   web:
@@ -23,10 +26,15 @@ services:
     command: celery worker --app=worker.celery --loglevel=info --logfile=logs/celery.log
     volumes:
       - ./src:/app
+      - /var/run/docker.sock:/var/run/docker.sock
+      - browsertrix:/crawls
+
     env_file: src/.env
     environment:
       - CELERY_BROKER_URL=redis://:${REDIS_PASSWORD}@redis:6379/0
       - CELERY_RESULT_BACKEND=redis://:${REDIS_PASSWORD}@redis:6379/0
+      - RUNNING_IN_DOCKER= # Override env from auto-archiver Dockerfile
+
     depends_on:
       - web
       - redis
diff --git a/src/Dockerfile b/src/Dockerfile
index 7e01b7e..bd44d70 100644
--- a/src/Dockerfile
+++ b/src/Dockerfile
@@ -4,6 +4,8 @@ FROM bellingcat/auto-archiver
 # set work directory
 WORKDIR /app
 
+RUN curl -fsSL https://get.docker.com -o get-docker.sh && \
+    sh get-docker.sh
 # set environment variables
 ENV PYTHONUNBUFFERED 1
 ENV PYTHONDONTWRITEBYTECODE 1