generated from City-Bureau/city-scrapers-template
-
-
Notifications
You must be signed in to change notification settings - Fork 2
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #9 from City-Bureau/batch-update-workflow
🔧 Clean up: Github workflows
- Loading branch information
Showing
3 changed files
with
37 additions
and
34 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -2,58 +2,51 @@ name: Cron | |
|
||
on: | ||
schedule: | ||
# Set any time that you'd like scrapers to run (in UTC) | ||
- cron: "27 6 * * *" | ||
- cron: "1 6 * * *" | ||
workflow_dispatch: | ||
|
||
env: | ||
CI: true | ||
PYTHON_VERSION: 3.9 | ||
PIPENV_VENV_IN_PROJECT: true | ||
SCRAPY_SETTINGS_MODULE: city_scrapers.settings.prod | ||
WAYBACK_ENABLED: true | ||
AUTOTHROTTLE_MAX_DELAY: 30.0 | ||
AUTOTHROTTLE_START_DELAY: 1.5 | ||
AUTOTHROTTLE_TARGET_CONCURRENCY: 3.0 | ||
# Add secrets for the platform you're using and uncomment here | ||
# AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} | ||
# AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} | ||
# S3_BUCKET: ${{ secrets.S3_BUCKET }} | ||
AZURE_ACCOUNT_KEY: ${{ secrets.AZURE_ACCOUNT_KEY }} | ||
AZURE_ACCOUNT_NAME: ${{ secrets.AZURE_ACCOUNT_NAME }} | ||
AZURE_CONTAINER: ${{ secrets.AZURE_CONTAINER }} | ||
AZURE_STATUS_CONTAINER: ${{ secrets.AZURE_STATUS_CONTAINER }} | ||
# GOOGLE_APPLICATION_CREDENTIALS = os.getenv("GOOGLE_APPLICATION_CREDENTIALS") | ||
# GCS_BUCKET = os.getenv("GCS_BUCKET") | ||
# Setup Sentry, add the DSN to secrets and uncomment here | ||
# SENTRY_DSN: ${{ secrets.SENTRY_DSN }} | ||
SENTRY_DSN: ${{ secrets.SENTRY_DSN }} | ||
|
||
jobs: | ||
crawl: | ||
runs-on: ubuntu-latest | ||
steps: | ||
- uses: actions/checkout@v2 | ||
- uses: actions/checkout@v4 | ||
|
||
- name: Set up Python 3.9 | ||
uses: actions/setup-python@v1 | ||
- name: Set up Python ${{ env.PYTHON_VERSION }} | ||
uses: actions/setup-python@v5 | ||
with: | ||
python-version: 3.9 | ||
python-version: ${{ env.PYTHON_VERSION }} | ||
|
||
- name: Install Pipenv | ||
uses: dschep/install-pipenv-action@v1 | ||
run: pip install --user pipenv | ||
|
||
- name: Cache Python dependencies | ||
uses: actions/cache@v1 | ||
uses: actions/cache@v4 | ||
with: | ||
path: .venv | ||
key: pip-3.9-${{ hashFiles('**/Pipfile.lock') }} | ||
key: ${{ env.PYTHON_VERSION }}-${{ hashFiles('**/Pipfile.lock') }} | ||
restore-keys: | | ||
pip-3.9- | ||
${{ env.PYTHON_VERSION }}- | ||
pip- | ||
- name: Install dependencies | ||
run: pipenv sync | ||
env: | ||
PIPENV_DEFAULT_PYTHON_VERSION: 3.9 | ||
PIPENV_DEFAULT_PYTHON_VERSION: ${{ env.PYTHON_VERSION }} | ||
|
||
- name: Run scrapers | ||
run: | | ||
|
@@ -63,4 +56,10 @@ jobs: | |
- name: Combine output feeds | ||
run: | | ||
export PYTHONPATH=$(pwd):$PYTHONPATH | ||
pipenv run scrapy combinefeeds -s LOG_ENABLED=True | ||
pipenv run scrapy combinefeeds -s LOG_ENABLED=False | ||
- name: Prevent workflow deactivation | ||
uses: gautamkrishnar/keepalive-workflow@v1 | ||
with: | ||
committer_username: "citybureau-bot" | ||
committer_email: "[email protected]" |