Skip to content

Scrape

Scrape #172

Workflow file for this run

name: Scrape
on:
schedule:
- cron: "0 12 * * 0"
workflow_dispatch:
jobs:
scrape:
runs-on: ubuntu-latest
steps:
- name: Checkout repo
uses: actions/checkout@v2
- name: Set up R
uses: r-lib/actions/setup-r@v2
with:
r-version: '4.4.2'
- name: Install system dependencies
run: |
sudo apt-get update
sudo apt-get install -y \
libcurl4-openssl-dev \
libssl-dev \
libxml2-dev \
libfontconfig1-dev \
libfreetype6-dev \
libpng-dev \
libtiff5-dev \
libjpeg-dev \
libharfbuzz-dev \
libfribidi-dev \
libgit2-dev \
libcairo2-dev \
libglpk-dev \
libudunits2-dev \
libmagick++-dev
- name: Cache R packages
uses: actions/cache@v3
with:
path: ~/R/
key: ${{ runner.os }}-r-${{ hashFiles('Scraper.R') }}
restore-keys: |
${{ runner.os }}-r-
- name: Install R packages with pak
run: |
Rscript -e 'install.packages("pak", repos = "https://cloud.r-project.org")'
Rscript -e 'pak::pkg_install(c("tidyverse", "rvest"))'
- name: Run scraper script
run: Rscript Scraper.R
- name: Commit and push scraped data
run: |
git config --local user.name github-actions
git config --local user.email "actions@github.com"
if git status --porcelain | grep .; then
git add Data/*
git add logs.txt
git commit -am "GH ACTION Autorun $(date)"
git push origin main
else
echo "No changes to commit"
fi
env:
REPO_KEY: ${{secrets.GITHUB_TOKEN}}
username: github-actions