Skip to content

Schedule Spider Crawl #1069

Schedule Spider Crawl

Schedule Spider Crawl #1069

name: Schedule Spider Crawl
on:
workflow_dispatch:
inputs:
spider_name:
description: 'Spider to be scheduled'
required: true
start_date:
description: 'Start date (YYYY-MM-DD)'
required: false
end_date:
description: 'End date (YYYY-MM-DD)'
required: false
jobs:
schedule:
runs-on: ubuntu-latest
env:
SHUB_APIKEY: ${{ secrets.SHUB_APIKEY }}
SCRAPY_CLOUD_PROJECT_ID: ${{ secrets.SCRAPY_CLOUD_PROJECT_ID }}
FILES_STORE: ${{ secrets.FILES_STORE }}
QUERIDODIARIO_DATABASE_URL: ${{ secrets.QUERIDODIARIO_DATABASE_URL }}
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
AWS_ENDPOINT_URL: ${{ secrets.AWS_ENDPOINT_URL }}
AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
SPIDERMON_DISCORD_FAKE: ${{ secrets.SPIDERMON_DISCORD_FAKE }}
SPIDERMON_DISCORD_WEBHOOK_URL: ${{ secrets.SPIDERMON_DISCORD_WEBHOOK_URL }}
ZYTE_SMARTPROXY_APIKEY: ${{ secrets.ZYTE_SMARTPROXY_APIKEY }}
steps:
- uses: actions/checkout@v2
- uses: actions/setup-python@v2
with:
python-version: '3.10'
- name: Prepare environment
run: |
python -m pip install --upgrade pip
pip install click python-decouple scrapinghub SQLAlchemy psycopg2
- name: Schedule full crawl
if: ${{ !github.event.inputs.start_date }}
run: |
cd data_collection/
python scheduler.py schedule-spider --spider_name=${{ github.event.inputs.spider_name }}
- name: Schedule partial crawl
if: ${{ github.event.inputs.start_date }}
run: |
cd data_collection/
python scheduler.py schedule-spider --spider_name=${{ github.event.inputs.spider_name }} --start_date=${{ github.event.inputs.start_date }} --end_date=${{ github.event.inputs.end_date }}