Skip to content

RSS Source Pipeline #16

RSS Source Pipeline

RSS Source Pipeline #16

name: RSS Source Pipeline
on:
workflow_dispatch:
inputs:
feeds_path:
description: "RSS feed config CSV path."
required: false
default: "config/free_rss_feeds.csv"
type: string
aliases_path:
description: "Symbol alias CSV path."
required: false
default: "config/core_us_equity_aliases.csv"
type: string
watchlist_path:
description: "Watchlist CSV path."
required: false
default: "data/live/political_watchlist.csv"
type: string
max_items_per_feed:
description: "Maximum feed items per configured RSS/Atom feed."
required: false
default: "50"
type: string
commit_outputs:
description: "Commit generated live CSV outputs back to data/live."
required: false
default: "false"
type: choice
options:
- "false"
- "true"
schedule:
- cron: "15 12 * * 6"
permissions:
contents: write
concurrency:
group: ${{ github.workflow }}-${{ github.ref_name }}
cancel-in-progress: false
jobs:
build-rss-source-events:
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- uses: actions/checkout@v6
- uses: actions/setup-python@v6
with:
python-version: "3.11"
- name: Install package
run: python -m pip install -e .
- name: Fetch RSS sources and extract mentions
env:
FEEDS_PATH: ${{ github.event.inputs.feeds_path || 'config/free_rss_feeds.csv' }}
ALIASES_PATH: ${{ github.event.inputs.aliases_path || 'config/core_us_equity_aliases.csv' }}
WATCHLIST_PATH: ${{ github.event.inputs.watchlist_path || 'data/live/political_watchlist.csv' }}
MAX_ITEMS_PER_FEED: ${{ github.event.inputs.max_items_per_feed || '50' }}
run: |
set -euo pipefail
mkdir -p data/output/rss_source_pipeline
python scripts/fetch_rss_sources.py \
--feeds "${FEEDS_PATH}" \
--output data/output/rss_source_pipeline/source_items.csv \
--max-items-per-feed "${MAX_ITEMS_PER_FEED}" \
--continue-on-feed-error \
--status-output data/output/rss_source_pipeline/source_fetch_status.json
python scripts/extract_source_mentions.py \
--raw-items data/output/rss_source_pipeline/source_items.csv \
--aliases "${ALIASES_PATH}" \
--output data/output/rss_source_pipeline/source_events.csv
python scripts/build_tracker.py \
--watchlist "${WATCHLIST_PATH}" \
--events data/output/rss_source_pipeline/source_events.csv \
--output data/output/rss_source_pipeline/source_tracker.csv
- name: Publish live CSV outputs to repository
env:
COMMIT_OUTPUTS: ${{ github.event_name == 'schedule' && 'true' || github.event.inputs.commit_outputs || 'false' }}
run: |
set -euo pipefail
if [ "${COMMIT_OUTPUTS}" != "true" ]; then
echo "Live output commit disabled."
exit 0
fi
mkdir -p data/live
cp data/output/rss_source_pipeline/source_items.csv data/live/source_items.csv
cp data/output/rss_source_pipeline/source_events.csv data/live/source_events.csv
cp data/output/rss_source_pipeline/source_events.csv data/live/political_events.csv
cp data/output/rss_source_pipeline/source_tracker.csv data/live/source_tracker.csv
cp data/output/rss_source_pipeline/source_fetch_status.json data/live/source_fetch_status.json
python scripts/write_live_manifest.py \
--base-dir . \
--output data/live/source_manifest.json \
data/live/source_fetch_status.json \
data/live/source_items.csv \
data/live/source_events.csv \
data/live/political_events.csv \
data/live/source_tracker.csv
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git add data/live/source_items.csv data/live/source_events.csv data/live/political_events.csv data/live/source_tracker.csv data/live/source_fetch_status.json data/live/source_manifest.json
if git diff --cached --quiet; then
echo "No live RSS output changes to commit."
else
git commit -m "Update live RSS source events [skip ci]"
git push
fi
- name: Upload RSS source artifact
uses: actions/upload-artifact@v7
with:
name: rss-source-pipeline
path: data/output/rss_source_pipeline/
if-no-files-found: error