Compare commits
6
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
7eac9afad1 | ||
|
|
274ad5b5d5 | ||
|
|
bc68f8a752 | ||
|
|
648d5ac742 | ||
|
|
8dd354c7c5 | ||
|
|
31c656d66f |
+1
-2
@@ -45,7 +45,6 @@ logs/
|
|||||||
.DS_Store
|
.DS_Store
|
||||||
Thumbs.db
|
Thumbs.db
|
||||||
|
|
||||||
# Docs (optional - include if you want them in container)
|
# Docs (keep README.md — required by pyproject.toml / Docker build)
|
||||||
docs/
|
docs/
|
||||||
*.md
|
|
||||||
|
|
||||||
|
|||||||
+21
-38
@@ -9,8 +9,7 @@ on:
|
|||||||
jobs:
|
jobs:
|
||||||
lint-and-test:
|
lint-and-test:
|
||||||
runs-on: ubuntu-latest
|
runs-on: ubuntu-latest
|
||||||
container:
|
# No job container: actions/checkout@v4 needs Node (act_runner fails in python-only images)
|
||||||
image: python:3.11-bullseye
|
|
||||||
|
|
||||||
services:
|
services:
|
||||||
postgres:
|
postgres:
|
||||||
@@ -29,24 +28,20 @@ jobs:
|
|||||||
- name: Check out code
|
- name: Check out code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
|
|
||||||
- name: Install system dependencies
|
- name: Set up Python venv
|
||||||
run: |
|
run: |
|
||||||
apt-get update
|
python3 -m venv .venv
|
||||||
apt-get install -y postgresql-client
|
.venv/bin/pip install --upgrade pip
|
||||||
|
.venv/bin/pip install -e ".[dev]"
|
||||||
- name: Install Python dependencies
|
|
||||||
run: |
|
|
||||||
pip install --upgrade pip
|
|
||||||
pip install -e ".[dev]"
|
|
||||||
|
|
||||||
- name: Run linters
|
- name: Run linters
|
||||||
run: |
|
run: |
|
||||||
echo "Running ruff..."
|
echo "Running ruff..."
|
||||||
ruff check src/ tests/ || true
|
.venv/bin/ruff check src/ tests/ || true
|
||||||
echo "Running black check..."
|
echo "Running black check..."
|
||||||
black --check src/ tests/ || true
|
.venv/bin/black --check src/ tests/ || true
|
||||||
echo "Running mypy..."
|
echo "Running mypy..."
|
||||||
mypy src/ --install-types --non-interactive || true
|
.venv/bin/mypy src/ --install-types --non-interactive || true
|
||||||
|
|
||||||
- name: Run tests with coverage
|
- name: Run tests with coverage
|
||||||
env:
|
env:
|
||||||
@@ -57,40 +52,38 @@ jobs:
|
|||||||
SMTP_PASSWORD: ${{ secrets.SMTP_PASSWORD || 'dummy' }}
|
SMTP_PASSWORD: ${{ secrets.SMTP_PASSWORD || 'dummy' }}
|
||||||
FROM_EMAIL: ${{ secrets.FROM_EMAIL || 'test@example.com' }}
|
FROM_EMAIL: ${{ secrets.FROM_EMAIL || 'test@example.com' }}
|
||||||
run: |
|
run: |
|
||||||
pytest tests/ -v --cov=src/pote --cov-report=term --cov-report=xml
|
.venv/bin/pytest tests/ -v --cov=src/pote --cov-report=term --cov-report=xml
|
||||||
|
|
||||||
- name: Test scripts
|
- name: Test scripts
|
||||||
env:
|
env:
|
||||||
DATABASE_URL: postgresql://poteuser:${{ secrets.DB_PASSWORD || 'testpass123' }}@postgres:5432/potedb_test
|
DATABASE_URL: postgresql://poteuser:${{ secrets.DB_PASSWORD || 'testpass123' }}@postgres:5432/potedb_test
|
||||||
run: |
|
run: |
|
||||||
echo "Testing database migrations..."
|
echo "Testing database migrations..."
|
||||||
alembic upgrade head
|
.venv/bin/alembic upgrade head
|
||||||
echo "Testing price loader..."
|
echo "Testing price loader..."
|
||||||
python scripts/fetch_sample_prices.py || true
|
.venv/bin/python scripts/fetch_sample_prices.py || true
|
||||||
|
|
||||||
security-scan:
|
security-scan:
|
||||||
runs-on: ubuntu-latest
|
runs-on: ubuntu-latest
|
||||||
container:
|
|
||||||
image: python:3.11-bullseye
|
|
||||||
steps:
|
steps:
|
||||||
- name: Check out code
|
- name: Check out code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
|
|
||||||
- name: Install dependencies
|
- name: Set up Python venv
|
||||||
run: |
|
run: |
|
||||||
pip install --upgrade pip
|
python3 -m venv .venv
|
||||||
pip install safety bandit
|
.venv/bin/pip install --upgrade pip
|
||||||
|
.venv/bin/pip install -e ".[dev]" safety bandit
|
||||||
|
|
||||||
- name: Run safety check
|
- name: Run safety check
|
||||||
run: |
|
run: |
|
||||||
pip install -e .
|
.venv/bin/safety check --json || true
|
||||||
safety check --json || true
|
|
||||||
continue-on-error: true
|
continue-on-error: true
|
||||||
|
|
||||||
- name: Run bandit security scan
|
- name: Run bandit security scan
|
||||||
run: |
|
run: |
|
||||||
bandit -r src/ -f json -o bandit-report.json || true
|
.venv/bin/bandit -r src/ -f json -o bandit-report.json || true
|
||||||
bandit -r src/ -f screen
|
.venv/bin/bandit -r src/ -f screen
|
||||||
continue-on-error: true
|
continue-on-error: true
|
||||||
|
|
||||||
dependency-scan:
|
dependency-scan:
|
||||||
@@ -114,20 +107,10 @@ jobs:
|
|||||||
- name: Check out code
|
- name: Check out code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
|
|
||||||
- name: Set up Docker Buildx
|
- name: Build and test Docker image
|
||||||
uses: docker/setup-buildx-action@v3
|
|
||||||
|
|
||||||
- name: Build Docker image
|
|
||||||
uses: docker/build-push-action@v5
|
|
||||||
with:
|
|
||||||
context: .
|
|
||||||
push: false
|
|
||||||
tags: pote:test
|
|
||||||
cache-from: type=gha
|
|
||||||
cache-to: type=gha,mode=max
|
|
||||||
|
|
||||||
- name: Test Docker image
|
|
||||||
run: |
|
run: |
|
||||||
|
# Plain docker build — buildx images are not visible to act_runner's docker run
|
||||||
|
docker build -t pote:test .
|
||||||
docker run --rm pote:test python -c "import pote; print('POTE import successful')"
|
docker run --rm pote:test python -c "import pote; print('POTE import successful')"
|
||||||
|
|
||||||
workflow-summary:
|
workflow-summary:
|
||||||
|
|||||||
+6
-6
@@ -1,18 +1,18 @@
|
|||||||
# Email Setup for levkin.ca
|
# Email Setup for levkine.ca (Mailcow)
|
||||||
|
|
||||||
Your POTE system is configured to use `test@levkin.ca` for sending reports.
|
Homelab POTE sends via Mailcow **`mail.levkine.ca`** using the shared **`alerts@levkine.ca`** mailbox (same as Kuma/Beszel). See ansible `docs/guides/smtp-inventory.md`.
|
||||||
|
|
||||||
## ✅ Configuration Done
|
## ✅ Configuration Done
|
||||||
|
|
||||||
The `.env` file has been created with these settings:
|
The `.env` file has been created with these settings:
|
||||||
|
|
||||||
```env
|
```env
|
||||||
SMTP_HOST=mail.levkin.ca
|
SMTP_HOST=10.0.10.132
|
||||||
SMTP_PORT=587
|
SMTP_PORT=587
|
||||||
SMTP_USER=test@levkin.ca
|
SMTP_USER=alerts@levkine.ca
|
||||||
SMTP_PASSWORD=YOUR_MAILBOX_PASSWORD_HERE
|
SMTP_PASSWORD=YOUR_MAILBOX_PASSWORD_HERE
|
||||||
FROM_EMAIL=test@levkin.ca
|
FROM_EMAIL=alerts@levkine.ca
|
||||||
REPORT_RECIPIENTS=test@levkin.ca
|
REPORT_RECIPIENTS=idobkin@gmail.com
|
||||||
```
|
```
|
||||||
|
|
||||||
## 🔑 Next Steps
|
## 🔑 Next Steps
|
||||||
|
|||||||
@@ -30,6 +30,8 @@ POTE tracks stock trading activity of government officials (starting with U.S. C
|
|||||||
|
|
||||||
**📧 Want automated reports?** See **[AUTOMATION_QUICKSTART.md](AUTOMATION_QUICKSTART.md)** for email reporting setup!
|
**📧 Want automated reports?** See **[AUTOMATION_QUICKSTART.md](AUTOMATION_QUICKSTART.md)** for email reporting setup!
|
||||||
|
|
||||||
|
**🏠 Homelab deploy (LXC 236)?** See **[docs/HANDOFF-2026-05-27.md](docs/HANDOFF-2026-05-27.md)** for ops handoff and next steps.
|
||||||
|
|
||||||
### Local Development
|
### Local Development
|
||||||
```bash
|
```bash
|
||||||
# Install
|
# Install
|
||||||
|
|||||||
@@ -0,0 +1,166 @@
|
|||||||
|
# POTE homelab handoff — 2026-05-27
|
||||||
|
|
||||||
|
**Status:** Production LXC running; PR #1 merged to `main`; CI green on Gitea Actions.
|
||||||
|
**Research only — not investment advice.**
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## What’s live
|
||||||
|
|
||||||
|
| Item | Value |
|
||||||
|
|------|--------|
|
||||||
|
| Host | LXC **236** `pote` @ **10.0.10.48** (pve10) |
|
||||||
|
| App | `/home/poteapp/pote` (venv, **no git clone** — deploy via rsync) |
|
||||||
|
| DB | PostgreSQL `pote` / `poteuser` (password rotated; in Ansible vault) |
|
||||||
|
| Data | ~55 officials, ~329 trades (30-day live ingest, May 2026) |
|
||||||
|
| SMTP | `10.0.10.132` (Mailcow), send as **`alerts@levkine.ca`** |
|
||||||
|
| Reports | **`idobkin@gmail.com`** daily 07:00, weekly Sun 08:00 |
|
||||||
|
|
||||||
|
### Cron (`crontab -u poteapp -l`)
|
||||||
|
|
||||||
|
| Time | Script |
|
||||||
|
|------|--------|
|
||||||
|
| 06:00 | `fetch_congressional_trades.py --days 7` |
|
||||||
|
| 06:15 | `enrich_securities.py` |
|
||||||
|
| 06:30 | `monitor_market.py --scan` |
|
||||||
|
| 07:00 | `send_daily_report.py --to idobkin@gmail.com` |
|
||||||
|
| Sun 08:00 | `send_weekly_report.py --to idobkin@gmail.com` |
|
||||||
|
|
||||||
|
### Data source (important)
|
||||||
|
|
||||||
|
Legacy **housestockwatcher.com** and S3 buckets are dead/blocked. Ingest uses public JSON from [congress-trading-monitor](https://github.com/kadoa-org/congress-trading-monitor) (~5000 rows cap). Override with env `POTE_HOUSE_DATA_URL` if you add another feed.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Repos & branches
|
||||||
|
|
||||||
|
| Repo | Branch | Notes |
|
||||||
|
|------|--------|--------|
|
||||||
|
| **POTE** | `main` @ `git.levkin.ca/ilia/POTE` | Merged PR #1 — ingest, email, CI, deps |
|
||||||
|
| **ansible** | `feature/outline-setup-api` (or `master`) | Inventory, `deploy-pote.sh`, vault — may need merge to homelab default branch |
|
||||||
|
|
||||||
|
Local:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd ~/Documents/code/POTE && git checkout main && git pull
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Quick access
|
||||||
|
|
||||||
|
```bash
|
||||||
|
ssh root@10.0.10.48
|
||||||
|
su - poteapp
|
||||||
|
cd pote && source venv/bin/activate
|
||||||
|
|
||||||
|
# Logs
|
||||||
|
tail -f ~/logs/daily_report.log
|
||||||
|
tail -f ~/logs/trades.log
|
||||||
|
|
||||||
|
# Manual run
|
||||||
|
python scripts/fetch_congressional_trades.py --days 30
|
||||||
|
python scripts/send_daily_report.py --to idobkin@gmail.com --test-smtp
|
||||||
|
```
|
||||||
|
|
||||||
|
Deploy code from laptop (preserves server `.env`):
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd ~/Documents/code/ansible
|
||||||
|
make deploy-pote
|
||||||
|
# or: RUN_FETCH=1 make deploy-pote
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Ansible / homelab inventory
|
||||||
|
|
||||||
|
Already wired (ansible repo):
|
||||||
|
|
||||||
|
- `inventories/production/hosts` — `pote` @ `.48`, VMID 236
|
||||||
|
- `docs/guides/host-list.md` — LXC 236 row
|
||||||
|
- `scripts/beszel-install-agents.sh` — `pote-236`
|
||||||
|
- `scripts/deploy-pote.sh`, `make deploy-pote`
|
||||||
|
- `scripts/vault-update-pote.py`, `make vault-update-pote`
|
||||||
|
- `docs/guides/smtp-inventory.md` — POTE uses `alerts@levkine.ca`
|
||||||
|
- Vault: `vault_pote_db_password_prod`, `vault_pote_smtp_password`
|
||||||
|
|
||||||
|
```bash
|
||||||
|
make vault-export-env
|
||||||
|
make beszel-install-agents BESZEL_ONLY=pote-236 # if agent not yet installed
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Verify after first automated day
|
||||||
|
|
||||||
|
1. **07:00+** — Email in Gmail (From: `alerts@levkine.ca`, subject `POTE Daily Report - YYYY-MM-DD`). Check spam once.
|
||||||
|
2. **Logs** — `~/logs/daily_report.log`, `trades.log` — no tracebacks.
|
||||||
|
3. **DB growth** — trade count should tick up on weekdays:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
su - poteapp -c 'cd pote && source venv/bin/activate && python -c "
|
||||||
|
from sqlalchemy import func, select
|
||||||
|
from pote.db import SessionLocal
|
||||||
|
from pote.db.models import Trade, Official
|
||||||
|
with SessionLocal() as s:
|
||||||
|
print(\"trades\", s.scalar(select(func.count(Trade.id))))
|
||||||
|
print(\"officials\", s.scalar(select(func.count(Official.id))))
|
||||||
|
"'
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Next steps (priority order)
|
||||||
|
|
||||||
|
### Soon
|
||||||
|
|
||||||
|
- [ ] **Sync server to `main`** — `make deploy-pote` from laptop (server was rsync’d pre-merge; safe to refresh).
|
||||||
|
- [ ] **Confirm first cron email** — tomorrow 07:00 server time; fix via `crontab -e` / `.env` `REPORT_RECIPIENTS` if needed.
|
||||||
|
- [ ] **Beszel agent** — `make beszel-install-agents BESZEL_ONLY=pote-236` if not done.
|
||||||
|
- [ ] **Proxmox backup** — schedule backup for LXC 236 on pve10.
|
||||||
|
- [ ] **Merge ansible branch** — homelab inventory/deploy scripts if still on `feature/outline-setup-api`.
|
||||||
|
|
||||||
|
### Optional enhancements
|
||||||
|
|
||||||
|
- [ ] **Dedicated mailbox** — e.g. `pote@levkine.ca` in Mailcow instead of shared `alerts@` ([smtp-inventory.md](https://git.levkin.ca/ilia/ansible/src/branch/master/docs/guides/smtp-inventory.md) in ansible repo).
|
||||||
|
- [ ] **Git deploy on LXC** — clone `gitea@git.levkin.ca:ilia/POTE.git` + deploy key; replace rsync-only workflow.
|
||||||
|
- [ ] **UniFi DNS** — `mail.levkine.ca` → `10.0.10.132` so `.env` can use hostname instead of raw IP ([unifi-static-dhcp.md](https://git.levkin.ca/ilia/ansible/src/branch/master/docs/guides/unifi-static-dhcp.md)).
|
||||||
|
- [ ] **Full history ingest** — kadoa JSON is capped; add second source (capitol-api, Clerk scrape) for backfill.
|
||||||
|
- [ ] **Kuma monitor** — LAN HTTP health script or SSH check (no public URL).
|
||||||
|
- [ ] **Mattermost / webhook alerts** — not implemented; email only today.
|
||||||
|
|
||||||
|
### Not planned (unless you want them)
|
||||||
|
|
||||||
|
- Public URL / Caddy vhost (LAN-only by design)
|
||||||
|
- Investment signals exposed as advice (research descriptors only)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Known issues / caveats
|
||||||
|
|
||||||
|
| Topic | Detail |
|
||||||
|
|-------|--------|
|
||||||
|
| **Disclosure lag** | STOCK Act filings appear weeks after trades; reports are descriptive, not timely trading signals. |
|
||||||
|
| **Amount ranges** | Disclosure buckets only ($1k–$15k, etc.), not exact sizes. |
|
||||||
|
| **Empty tickers** | Some filings skipped when ticker missing. |
|
||||||
|
| **CI vs prod** | CI uses venv + Postgres service; prod uses host Postgres — both should pass after merge. |
|
||||||
|
| **Gitea deploy workflow** | `.github/workflows/deploy.yml` still references `git pull` on Proxmox; prod uses **rsync** via ansible `deploy-pote.sh`. |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Related docs
|
||||||
|
|
||||||
|
| Doc | Purpose |
|
||||||
|
|-----|---------|
|
||||||
|
| [EMAIL_SETUP.md](../EMAIL_SETUP.md) | SMTP / Mailcow / levkine.ca |
|
||||||
|
| [AUTOMATION_QUICKSTART.md](../AUTOMATION_QUICKSTART.md) | Cron + reports |
|
||||||
|
| [PROXMOX_QUICKSTART.md](../PROXMOX_QUICKSTART.md) | Original LXC provisioning |
|
||||||
|
| Ansible `docs/guides/projects-handoff-2026-05-26.md` | Multi-project homelab context |
|
||||||
|
| Ansible `docs/guides/smtp-inventory.md` | Mailboxes |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## One-line summary
|
||||||
|
|
||||||
|
**POTE on 10.0.10.48 ingests public congressional trades daily, emails a research summary to Gmail at 07:00, and is maintained via `main` + `make deploy-pote` — verify tomorrow’s cron email, then Beszel, backups, and optional data-source expansion.**
|
||||||
@@ -18,8 +18,10 @@ dependencies = [
|
|||||||
"pydantic-settings>=2.0",
|
"pydantic-settings>=2.0",
|
||||||
"python-dotenv>=1.0",
|
"python-dotenv>=1.0",
|
||||||
"requests>=2.31",
|
"requests>=2.31",
|
||||||
|
"httpx>=0.27",
|
||||||
"pandas>=2.0",
|
"pandas>=2.0",
|
||||||
"numpy>=1.24",
|
"numpy>=1.24",
|
||||||
|
"scikit-learn>=1.3",
|
||||||
"yfinance>=0.2",
|
"yfinance>=0.2",
|
||||||
"psycopg2-binary>=2.9",
|
"psycopg2-binary>=2.9",
|
||||||
]
|
]
|
||||||
|
|||||||
@@ -28,8 +28,8 @@ def main():
|
|||||||
|
|
||||||
args = parser.parse_args()
|
args = parser.parse_args()
|
||||||
|
|
||||||
logger.info("=== Fetching Congressional Trades from House Stock Watcher ===")
|
logger.info("=== Fetching Congressional Trades (public STOCK Act data) ===")
|
||||||
logger.info("Source: https://housestockwatcher.com (free, no API key)")
|
logger.info("Source: public JSON feeds (see HouseWatcherClient.data_urls)")
|
||||||
|
|
||||||
try:
|
try:
|
||||||
with HouseWatcherClient() as client:
|
with HouseWatcherClient() as client:
|
||||||
|
|||||||
@@ -30,6 +30,16 @@ class Settings(BaseSettings):
|
|||||||
# Logging
|
# Logging
|
||||||
log_level: str = Field(default="INFO", description="Log level (DEBUG, INFO, WARNING, ERROR)")
|
log_level: str = Field(default="INFO", description="Log level (DEBUG, INFO, WARNING, ERROR)")
|
||||||
|
|
||||||
|
# Email (Mailcow @ mail.levkine.ca — use LAN IP from app LXCs if DNS points public)
|
||||||
|
smtp_host: str = Field(default="mail.levkine.ca", description="SMTP server hostname")
|
||||||
|
smtp_port: int = Field(default=587, description="SMTP port (587 STARTTLS)")
|
||||||
|
smtp_user: str = Field(default="", description="SMTP auth username")
|
||||||
|
smtp_password: str = Field(default="", description="SMTP auth password")
|
||||||
|
from_email: str = Field(default="", description="From address for reports")
|
||||||
|
report_recipients: str = Field(
|
||||||
|
default="", description="Default report recipients (comma-separated)"
|
||||||
|
)
|
||||||
|
|
||||||
# Application
|
# Application
|
||||||
app_name: str = "POTE"
|
app_name: str = "POTE"
|
||||||
app_version: str = "0.1.0"
|
app_version: str = "0.1.0"
|
||||||
|
|||||||
@@ -3,6 +3,7 @@ Database layer: engine, session factory, and base model.
|
|||||||
"""
|
"""
|
||||||
|
|
||||||
from collections.abc import Generator
|
from collections.abc import Generator
|
||||||
|
from contextlib import contextmanager
|
||||||
|
|
||||||
from sqlalchemy import create_engine
|
from sqlalchemy import create_engine
|
||||||
from sqlalchemy.orm import DeclarativeBase, Session, sessionmaker
|
from sqlalchemy.orm import DeclarativeBase, Session, sessionmaker
|
||||||
@@ -26,8 +27,9 @@ class Base(DeclarativeBase):
|
|||||||
pass
|
pass
|
||||||
|
|
||||||
|
|
||||||
|
@contextmanager
|
||||||
def get_session() -> Generator[Session, None, None]:
|
def get_session() -> Generator[Session, None, None]:
|
||||||
"""Get a database session (use as a context manager or dependency)."""
|
"""Get a database session (context manager or FastAPI-style dependency)."""
|
||||||
session = SessionLocal()
|
session = SessionLocal()
|
||||||
try:
|
try:
|
||||||
yield session
|
yield session
|
||||||
|
|||||||
@@ -1,9 +1,12 @@
|
|||||||
"""
|
"""
|
||||||
House Stock Watcher client for fetching congressional trade data.
|
House Stock Watcher client for fetching congressional trade data.
|
||||||
Free, no API key required - scrapes from housestockwatcher.com
|
|
||||||
|
Uses public STOCK Act disclosure datasets (no API key). The legacy
|
||||||
|
housestockwatcher.com host is often unavailable; we try several mirrors.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
import logging
|
import logging
|
||||||
|
import os
|
||||||
from datetime import date, datetime
|
from datetime import date, datetime
|
||||||
from typing import Any
|
from typing import Any
|
||||||
|
|
||||||
@@ -11,16 +14,69 @@ import httpx
|
|||||||
|
|
||||||
logger = logging.getLogger(__name__)
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
def _default_data_urls() -> tuple[str, ...]:
|
||||||
|
override = os.environ.get("POTE_HOUSE_DATA_URL", "").strip()
|
||||||
|
if override:
|
||||||
|
return (override,)
|
||||||
|
return (
|
||||||
|
"https://raw.githubusercontent.com/kadoa-org/congress-trading-monitor/main/public/data/trades.json",
|
||||||
|
"https://housestockwatcher.com/api/all_transactions",
|
||||||
|
"https://house-stock-watcher-data.s3-us-west-2.amazonaws.com/data/all_transactions.json",
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
DEFAULT_DATA_URLS: tuple[str, ...] = _default_data_urls()
|
||||||
|
|
||||||
|
|
||||||
|
def _ascii_safe(text: str | None) -> str:
|
||||||
|
"""Normalize text for DB fields that may use ASCII-only client encoding."""
|
||||||
|
if not text:
|
||||||
|
return ""
|
||||||
|
return text.replace("\u00b7", "-").replace("·", "-").strip()
|
||||||
|
|
||||||
|
|
||||||
|
def _party_label(code: str | None) -> str:
|
||||||
|
if not code:
|
||||||
|
return ""
|
||||||
|
mapping = {"D": "Democrat", "R": "Republican", "I": "Independent"}
|
||||||
|
return mapping.get(code.strip().upper(), code.strip())
|
||||||
|
|
||||||
|
|
||||||
|
def normalize_transaction_record(raw: dict[str, Any]) -> dict[str, Any]:
|
||||||
|
"""
|
||||||
|
Map a raw disclosure record to the House Stock Watcher field names
|
||||||
|
expected by TradeLoader.
|
||||||
|
"""
|
||||||
|
if "representative" in raw and "disclosure_date" in raw:
|
||||||
|
return raw
|
||||||
|
|
||||||
|
# Kadoa congress-trading-monitor export
|
||||||
|
if "filer_name" in raw:
|
||||||
|
chamber = (raw.get("chamber") or "").strip().lower()
|
||||||
|
house = "Senate" if chamber == "senate" else "House"
|
||||||
|
return {
|
||||||
|
"representative": raw.get("filer_name", "").strip(),
|
||||||
|
"ticker": (raw.get("ticker") or "").strip(),
|
||||||
|
"transaction_date": raw.get("transaction_date", ""),
|
||||||
|
"disclosure_date": raw.get("filing_date", ""),
|
||||||
|
"transaction": raw.get("transaction_type", ""),
|
||||||
|
"amount": raw.get("amount_range_label", ""),
|
||||||
|
"house": house,
|
||||||
|
"district": _ascii_safe(raw.get("office")),
|
||||||
|
"party": _party_label(raw.get("party")),
|
||||||
|
}
|
||||||
|
|
||||||
|
return raw
|
||||||
|
|
||||||
|
|
||||||
class HouseWatcherClient:
|
class HouseWatcherClient:
|
||||||
"""
|
"""
|
||||||
Client for House Stock Watcher API (free, community-maintained).
|
Client for congressional trade JSON feeds (free, community-maintained).
|
||||||
|
|
||||||
Data source: https://housestockwatcher.com/
|
Primary source: congress-trading-monitor public dataset on GitHub.
|
||||||
No authentication required.
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
BASE_URL = "https://housestockwatcher.com/api"
|
data_urls: tuple[str, ...] = DEFAULT_DATA_URLS
|
||||||
|
|
||||||
def __init__(self, timeout: float = 30.0):
|
def __init__(self, timeout: float = 30.0):
|
||||||
"""
|
"""
|
||||||
@@ -65,30 +121,31 @@ class HouseWatcherClient:
|
|||||||
Raises:
|
Raises:
|
||||||
httpx.HTTPError: If request fails
|
httpx.HTTPError: If request fails
|
||||||
"""
|
"""
|
||||||
url = f"{self.BASE_URL}/all_transactions"
|
last_error: Exception | None = None
|
||||||
logger.info(f"Fetching transactions from {url}")
|
for url in self.data_urls:
|
||||||
|
if not url:
|
||||||
|
continue
|
||||||
|
logger.info(f"Fetching transactions from {url}")
|
||||||
|
try:
|
||||||
|
response = self._client.get(url)
|
||||||
|
response.raise_for_status()
|
||||||
|
data = response.json()
|
||||||
|
if not isinstance(data, list):
|
||||||
|
raise ValueError(f"Expected list response, got {type(data)}")
|
||||||
|
data = [normalize_transaction_record(item) for item in data]
|
||||||
|
logger.info(f"Fetched {len(data)} transactions from {url}")
|
||||||
|
if limit:
|
||||||
|
data = data[:limit]
|
||||||
|
return data
|
||||||
|
except Exception as e:
|
||||||
|
last_error = e
|
||||||
|
logger.warning(f"Failed to fetch from {url}: {e}")
|
||||||
|
continue
|
||||||
|
|
||||||
try:
|
logger.error("Failed to fetch congressional trades from all configured URLs")
|
||||||
response = self._client.get(url)
|
if last_error:
|
||||||
response.raise_for_status()
|
raise last_error
|
||||||
data = response.json()
|
raise RuntimeError("No data URLs configured")
|
||||||
|
|
||||||
if not isinstance(data, list):
|
|
||||||
raise ValueError(f"Expected list response, got {type(data)}")
|
|
||||||
|
|
||||||
logger.info(f"Fetched {len(data)} transactions from House Stock Watcher")
|
|
||||||
|
|
||||||
if limit:
|
|
||||||
data = data[:limit]
|
|
||||||
|
|
||||||
return data
|
|
||||||
|
|
||||||
except httpx.HTTPError as e:
|
|
||||||
logger.error(f"Failed to fetch from House Stock Watcher: {e}")
|
|
||||||
raise
|
|
||||||
except Exception as e:
|
|
||||||
logger.error(f"Unexpected error fetching transactions: {e}")
|
|
||||||
raise
|
|
||||||
|
|
||||||
def fetch_recent_transactions(self, days: int = 30) -> list[dict[str, Any]]:
|
def fetch_recent_transactions(self, days: int = 30) -> list[dict[str, Any]]:
|
||||||
"""
|
"""
|
||||||
|
|||||||
@@ -45,27 +45,25 @@ class TradeLoader:
|
|||||||
|
|
||||||
for txn in transactions:
|
for txn in transactions:
|
||||||
try:
|
try:
|
||||||
# Get or create official
|
with self.session.begin_nested():
|
||||||
official, is_new_official = self._get_or_create_official(txn)
|
official, is_new_official = self._get_or_create_official(txn)
|
||||||
if is_new_official:
|
if is_new_official:
|
||||||
officials_created += 1
|
officials_created += 1
|
||||||
|
|
||||||
# Get or create security
|
ticker = txn.get("ticker", "").strip().upper()
|
||||||
ticker = txn.get("ticker", "").strip().upper()
|
if not ticker or ticker in ("N/A", "--", ""):
|
||||||
if not ticker or ticker in ("N/A", "--", ""):
|
logger.debug(
|
||||||
logger.debug(
|
f"Skipping transaction with no ticker: {txn.get('representative')}"
|
||||||
f"Skipping transaction with no ticker: {txn.get('representative')}"
|
)
|
||||||
)
|
continue
|
||||||
continue
|
|
||||||
|
|
||||||
security, is_new_security = self._get_or_create_security(ticker)
|
security, is_new_security = self._get_or_create_security(ticker)
|
||||||
if is_new_security:
|
if is_new_security:
|
||||||
securities_created += 1
|
securities_created += 1
|
||||||
|
|
||||||
# Create trade (upsert)
|
trade_created = self._upsert_trade(txn, official.id, security.id, source)
|
||||||
trade_created = self._upsert_trade(txn, official.id, security.id, source)
|
if trade_created:
|
||||||
if trade_created:
|
trades_created += 1
|
||||||
trades_created += 1
|
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.error(f"Failed to ingest transaction {txn}: {e}")
|
logger.error(f"Failed to ingest transaction {txn}: {e}")
|
||||||
|
|||||||
Reference in New Issue
Block a user