juxtapoandClaude Opus 5
a58a61b98c
A South African men's apparel store on Spree 5.6 + Next.js 15. 160 products
live, three markets, live Malaysian courier rates, customer-owned carts.
What is here:
storefront/ the Next.js app
backend/ ONLY the custom Spree code. Spree itself is a prebuilt image
that mounts no app code, so every file here needs an explicit
volume entry in docker-compose.yml or it is silently ignored.
catalogue/ the scripts that loaded and maintain the products
docs/ manifest, mock registry, napkins
Real .env files are committed deliberately. This lives on the house's private
Gitea, and a clone that runs beats a clone that needs a secrets handover.
LANDMINE.md maps every key, what it opens, and what must be rotated before this
repo goes anywhere less private.
The admin API key used to be a literal in six catalogue scripts. They now read
SPREE_ADMIN_KEY from the environment and refuse to run without it.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
66 lines
2.1 KiB
Python
66 lines
2.1 KiB
Python
#!/usr/bin/env python3
|
|
"""Download images for batch2 + batch3 products."""
|
|
import json, os, re, urllib.request, time, sys
|
|
|
|
base = os.path.dirname(os.path.abspath(__file__))
|
|
out_root = os.path.join(base, "products")
|
|
os.makedirs(out_root, exist_ok=True)
|
|
|
|
def slugify(name):
|
|
s = re.sub(r'[^a-zA-Z0-9]+', '-', name).strip('-').lower()
|
|
return s[:60]
|
|
|
|
def load_jsonl(path):
|
|
items = []
|
|
with open(path) as f:
|
|
for line in f:
|
|
line = line.strip()
|
|
if line:
|
|
items.append(json.loads(line))
|
|
return items
|
|
|
|
existing = load_jsonl(os.path.join(base, "products.jsonl"))
|
|
offset = len(existing)
|
|
|
|
batches = []
|
|
for fname in ["products-batch2.jsonl", "products-batch3.jsonl"]:
|
|
path = os.path.join(base, fname)
|
|
if os.path.exists(path):
|
|
batches.extend(load_jsonl(path))
|
|
|
|
print(f"Existing: {offset} products, new: {len(batches)} to download")
|
|
|
|
ok, fail = 0, 0
|
|
for i, p in enumerate(batches, 1):
|
|
idx = offset + i
|
|
dirname = f"{idx:03d}-{slugify(p['brand'])}-{slugify(p['name'])}"
|
|
pdir = os.path.join(out_root, dirname)
|
|
os.makedirs(pdir, exist_ok=True)
|
|
|
|
info = {"name": p["name"], "brand": p["brand"], "price_myr": p["price"], "source_code": p["code"]}
|
|
if "category" in p:
|
|
info["category"] = p["category"]
|
|
with open(os.path.join(pdir, "info.json"), "w") as f:
|
|
json.dump(info, f, indent=2)
|
|
|
|
img_ok = 0
|
|
for j, url in enumerate(p["imgs"], 1):
|
|
dest = os.path.join(pdir, f"image-{j}.jpg")
|
|
if os.path.exists(dest) and os.path.getsize(dest) > 1000:
|
|
img_ok += 1
|
|
continue
|
|
try:
|
|
req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36"})
|
|
with urllib.request.urlopen(req, timeout=15) as r, open(dest, "wb") as out:
|
|
out.write(r.read())
|
|
img_ok += 1
|
|
except Exception as e:
|
|
print(f" FAIL {url}: {e}")
|
|
fail += 1
|
|
time.sleep(0.2)
|
|
|
|
ok += img_ok
|
|
print(f"[{i}/{len(batches)}] {p['brand']} - {p['name'][:40]} -> {img_ok}/{len(p['imgs'])} imgs")
|
|
|
|
print(f"\nDone: {ok} images downloaded, {fail} failed")
|