Skip to content

Scrape Routescanner and MSC daily (v2) #396

Scrape Routescanner and MSC daily (v2)

Scrape Routescanner and MSC daily (v2) #396

Workflow file for this run

# This workflows starts scraping Routescanner and MSC each day at 05:00 UTC,
# using the v2 scrapers, and opens a PR to merge the gathered data.
name: Scrape Routescanner and MSC daily (v2)
on:
schedule:
- cron: '0 5 * * *'
push:
paths:
- ".github/workflows/daily_run_v2.yml"
- "webscrapers/routescanner_automated_v2.py"
- "webscrapers/msc_automated_v2.py"
workflow_dispatch:
jobs:
routescanner-v2:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
with:
python-version: "3.11"
- run: pip install -U pandas requests fake_useragent
- run: python routescanner_automated_v2.py
working-directory: ./webscrapers
- uses: stefanzweifel/git-auto-commit-action@v5
with:
branch: "data_staging"
commit_options: '--signoff'
commit_message: "Add Routescanner v2 data"
msc-v2:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v4
with:
python-version: "3.11"
- run: pip install -U pandas requests
- run: python msc_automated_v2.py
working-directory: ./webscrapers
- uses: stefanzweifel/git-auto-commit-action@v5
with:
branch: "data_staging"
commit_options: '--signoff'
commit_message: "Add MSC v2 data"