pryscraper/commerce_sync.py
cryptorugmunch 0200bf3e16 refactor(exceptions): add ruff BLE001; convert 103 broad except Exception
Per CONVENTIONS.md Part 2 ("Never bare except") and CONVENTIONS.md
Part 7 (pre-commit hooks: ruff), blind `except Exception` is now a
lint failure. Pre-existing sites are marked `# noqa: BLE001` for
later manual review; new code must use specific exception types.

Changes:
- pyproject.toml: added "BLE" to ruff lint select. BLE001 is now enforced
- 103 of 166 `except Exception` sites were auto-converted to specific
  types based on context (httpx, json, OSError, subprocess, etc.)
- 62 remaining sites marked with `# noqa: BLE001` for later review
  (mostly generic try/except wrappers that legitimately need broad catch
  for graceful degradation: e.g. compliance LLM fallback must catch
  any error to preserve the regex result)
- 1 manual fix: reverted compliance.py LLM fallback to broad except
  with explicit "must catch all errors" comment + noqa
- 2 files (commerce_sync.py, crm_sync.py) needed `import httpx` added
  so the auto-converted exception references would resolve
- 5 source files (agency, monitor, pipelines, auth_connector,
  llm_providers/registry) renamed "name" -> "<scope>_name" in
  extra={...} dicts because "name" is a reserved LogRecord field

Test impact:
- 14 failing tests -> 1 (the SSE subprocess test is a sandbox limitation,
  pre-existing and unrelated)
- New `test_ble_temp.py` verifies BLE001 catches new violations

Follow-up:
- Each `# noqa: BLE001` site should be reviewed and replaced with a
  specific exception type where possible. The most common legitimate
  broad-catch case is the LLM fallback path; everything else probably
  can be narrowed.
2026-07-02 21:04:53 +02:00

199 lines
6.6 KiB
Python

import httpx
"""Pry — Commerce Platform Sync Engine.
Unified interface for WooCommerce, Shopify, and generic API sync."""
from paths import PRY_DATA_DIR
# SPDX-License-Identifier: MIT
# Copyright (c) 2026 Rug Munch Media LLC
#
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
# Licensed under MIT. See LICENSE.
import logging
import os
from pathlib import Path
from typing import Any
logger = logging.getLogger(__name__)
# ── Record sync operation ──
COMMERCE_DIR = PRY_DATA_DIR / "commerce"
COMMERCE_DIR.mkdir(parents=True, exist_ok=True)
async def sync_to_woocommerce(
products: list[dict[str, Any]],
wp_url: str,
consumer_key: str,
consumer_secret: str,
category_id: int = 0,
status: str = "draft",
) -> dict[str, Any]:
"""Sync products to WooCommerce via REST API.
Args:
products: List of product dicts with name, price, description, image_url
wp_url: WordPress site URL (e.g., https://mystore.com)
consumer_key: WooCommerce REST API consumer key
consumer_secret: WooCommerce REST API consumer secret
category_id: Product category ID to assign
status: Product status (draft, publish, pending)
"""
from client import get_client
client = await get_client()
base_url = wp_url.rstrip("/")
auth = (consumer_key, consumer_secret)
results = []
for product in products:
wc_product = {
"name": product.get("name", "Unnamed Product")[:255],
"regular_price": str(product.get("price", 0)),
"description": (product.get("description") or product.get("content", ""))[:5000],
"short_description": (product.get("short_description") or "")[:500],
"images": [{"src": product["image_url"]}] if product.get("image_url") else [],
"categories": [{"id": category_id}] if category_id else [],
"status": status,
"meta_data": [
{"key": "_pry_source_url", "value": product.get("url", "")},
{
"key": "_pry_imported_at",
"value": __import__("datetime")
.datetime.now(__import__("datetime").timezone.utc)
.isoformat(),
},
],
}
try:
resp = await client.post(
f"{base_url}/wp-json/wc/v3/products",
json=wc_product,
auth=auth,
timeout=30,
)
if resp.is_success:
data = resp.json()
results.append(
{
"success": True,
"woo_id": data.get("id"),
"name": data.get("name"),
"edit_url": f"{base_url}/wp-admin/post.php?post={data.get('id')}&action=edit",
}
)
else:
results.append(
{
"success": False,
"name": product.get("name", "Unknown"),
"error": f"WooCommerce error {resp.status_code}: {resp.text[:200]}",
}
)
except (httpx.HTTPError, httpx.RequestError) as e:
results.append(
{
"success": False,
"name": product.get("name", "Unknown"),
"error": str(e)[:200],
}
)
success_count = sum(1 for r in results if r["success"])
return {
"success": success_count > 0,
"total": len(products),
"synced": success_count,
"failed": len(products) - success_count,
"results": results,
}
async def sync_to_shopify(
products: list[dict[str, Any]],
shop_url: str,
access_token: str,
) -> dict[str, Any]:
"""Sync products to Shopify via REST API.
Args:
products: List of product dicts with name, price, description, image_url
shop_url: Shopify store URL (e.g., https://mystore.myshopify.com)
access_token: Shopify admin API access token
"""
from client import get_client
client = await get_client()
base_url = shop_url.rstrip("/")
results = []
for product in products:
shopify_product = {
"product": {
"title": (product.get("name") or "Unnamed Product")[:255],
"body_html": f"<div>{(product.get('description') or product.get('content', ''))[:5000]}</div>",
"vendor": "Pry Import",
"product_type": "Reference",
"status": "draft",
"variants": [
{
"price": str(product.get("price", 0)),
"inventory_management": "shopify",
}
],
"metafields": [
{
"key": "pry_source_url",
"value": product.get("url", ""),
"type": "single_line_text_field",
"namespace": "pry",
}
],
}
}
try:
resp = await client.post(
f"{base_url}/admin/api/2024-01/products.json",
json=shopify_product,
headers={"X-Shopify-Access-Token": access_token},
timeout=30,
)
if resp.is_success:
data = resp.json()
pid = data.get("product", {}).get("id")
results.append(
{
"success": True,
"shopify_id": pid,
"name": data.get("product", {}).get("title"),
"edit_url": f"{base_url}/admin/products/{pid}",
}
)
else:
results.append(
{
"success": False,
"name": product.get("name", "Unknown"),
"error": f"Shopify error {resp.status_code}: {resp.text[:200]}",
}
)
except (httpx.HTTPError, httpx.RequestError) as e:
results.append(
{
"success": False,
"name": product.get("name", "Unknown"),
"error": str(e)[:200],
}
)
success_count = sum(1 for r in results if r["success"])
return {
"success": success_count > 0,
"total": len(products),
"synced": success_count,
"failed": len(products) - success_count,
"results": results,
}