From 4de5890c605b2236a4d7bb775b3d1fedf0eca7d3 Mon Sep 17 00:00:00 2001 From: Marian Steinbach Date: Thu, 3 May 2018 10:22:10 +0200 Subject: [PATCH] Change to run spider in Docker container --- .dockerignore | 6 ++++++ Dockerfile | 9 +++++++++ Makefile | 12 +++++------- spider.py | 2 +- 4 files changed, 21 insertions(+), 8 deletions(-) create mode 100644 .dockerignore diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 0000000..ae2f869 --- /dev/null +++ b/.dockerignore @@ -0,0 +1,6 @@ +.git +webapp +docs +secrets +temp +venv diff --git a/Dockerfile b/Dockerfile index 1061afd..e3fdbe4 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1 +1,10 @@ FROM python:3.6-alpine3.7 + +ADD requirements.txt / +RUN pip install -r requirements.txt + +RUN apk add --no-cache git + +ADD spider.py / + +ENTRYPOINT ["python", "spider.py"] diff --git a/Makefile b/Makefile index 34c9edd..0b30d63 100644 --- a/Makefile +++ b/Makefile @@ -2,13 +2,11 @@ .PHONY: webapp -# Python venv for running the spider locally -venv: - virtualenv -p python3 venv - venv/bin/pip3 install -r requirements.txt - -spider: venv - venv/bin/python ./spider.py +# Build docker image and run spider in Docker container +spider: + docker pull python:3.6-alpine3.7 + docker build -t spider . + docker run --rm -ti -v $(PWD):/out spider screenshots: venv docker pull netzbegruenung/green-spider-screenshotter:latest diff --git a/spider.py b/spider.py index 6900a5e..feb1337 100644 --- a/spider.py +++ b/spider.py @@ -37,7 +37,7 @@ green_directory_repo = 'https://github.com/netzbegruenung/green-directory.git' green_direcory_data_path = 'data/countries/de' green_directory_local_path = './cache/green-directory' -result_path = './webapp/dist/data' +result_path = '/out' # IP address of the newthinking GCMS server gcms_ip = "91.102.13.20"