Skip to content

sort-scraped-data

sort-scraped-data #825

# This is a basic workflow to help you get started with Actions
name: sort-scraped-data
# Controls when the workflow will run
on:
schedule:
- cron: 55 05 * * * # Runs once daily at 05:55 UTC
workflow_dispatch:
concurrency:
group: scrape-and-schedule
cancel-in-progress: false
# A workflow run is made up of one or more jobs that can run sequentially or in parallel
jobs:
# This workflow contains a single job called "scrape"
sort:
# The type of runner that the job will run on
runs-on: ubuntu-latest
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
- name: checkout repo content
uses: actions/checkout@v3 # checkout the repository content to github runner.
- name: setup python
uses: actions/setup-python@v4
# with:
# python-version: 3.8.2
- name: execute py script # run sort-scraped-data.py to sort csv files into folders
run: |
python sort-scraped-data.py
- name: Commit and push if it changed
run: |
git config user.name "${GITHUB_ACTOR}"
git config user.email "${GITHUB_ACTOR}@users.noreply.github.com"
git pull
git add -A
timestamp=$(date -u)
if ! git diff-index --quiet HEAD; then
git commit -m "Sorted on [${timestamp}]"
git push "https://${GITHUB_ACTOR}:${TOKEN}@github.com/${GITHUB_REPOSITORY}.git" HEAD || exit 0
fi
#EOF