Skip to content

scraper

scraper #535

Workflow file for this run

name: scraper
on:
workflow_dispatch:
schedule:
- cron: "0 12 * * *" # runs at 12:00 UTC everyday
jobs:
generate_list:
runs-on: ubuntu-latest
steps:
- name: checkout repo content
uses: actions/checkout@v4
- name: setup python
uses: actions/setup-python@v5
with:
python-version: "3.12"
- name: install Python packages
run: |
python -m pip install --upgrade pip
pip install tldextract aiohttp
- name: Download URLs
run: python scraper.py
- name: create adblocking lists
run: |
sed 's/^/\|\|/;s/$/\^/' urls.txt > urls_ABP.txt
sed 's/^/\|\|/;s/$/\^$all/' urls.txt > urls_UBO.txt
- name: commit files
run: |
git config --local user.email "action@github.com"
git config --local user.name "GitHub Action"
git add -A
git diff --name-only --cached --exit-code || ( git commit -am "update lists" && git push )