V.AISTUDIO / generate_seo_stubs.py
bep40's picture
Upload generate_seo_stubs.py
f7d7f1f verified
Raw
History Blame
3.8 kB
#!/usr/bin/env python3
"""
SEO STUB GENERATOR cho V.AISTUDIO Static Space
Tạo 1979 file HTML cho mỗi sản phẩm để fix 404 và hỗ tr�n SEO URL sharing.
Cài đặt: pip install huggingface_hub requests
Chạy: python3 generate_seo_stubs.py
Yêu cầu: BIẾT_TOKEN trong environment hoặc ~/.huggingface/token
"""
import json
import re
import unicodedata
import time
import urllib.request
try:
from huggingface_hub import HfApi
except ImportError:
import subprocess
subprocess.check_call(["pip", "install", "-q", "huggingface_hub"])
from huggingface_hub import HfApi
SPACE_ID = "bep40/V.AISTUDIO"
BASE = "https://bep40-v-aistudio.static.hf.space"
def slugify(name):
s = unicodedata.normalize('NFKD', name)
s = s.encode('ascii', 'ignore').decode('ascii').lower()
s = re.sub(r'[^a-z0-9]+', '-', s).strip('-')
s = re.sub(r'-+', '-', s)
return s
def html_stub(slug, name, brand, price, img, desc):
title = f"{name} | {brand} - V.AISTUDIO" if brand else f"{name} - V.AISTUDIO"
desc = re.sub(r'<[^>]+>', '', str(desc))[:160]
img = img or f"{BASE}/logo/logo_600.png"
return f'''<!DOCTYPE html>
<html lang="vi">
<head>
<meta charset="UTF-8">
<title>{title}</title>
<meta name="description" content="{desc}">
<meta name="robots" content="noindex,follow">
<link rel="canonical" href="{BASE}/san-pham/{slug}/">
<meta property="og:type" content="product">
<meta property="og:title" content="{title}">
<meta property="og:description" content="{desc}">
<meta property="og:image" content="{img}">
<meta property="og:url" content="{BASE}/san-pham/{slug}/">
<meta property="og:site_name" content="V.AISTUDIO">
<meta name="twitter:card" content="summary_large_image">
<script>window.location.replace("/?product={slug}");</script>
</head>
<body><h1><a href="/?product={slug}">{title}</a></h1></body>
</html>'''
def main():
api = HfApi()
# Download index.html
print("Downloading index.html...")
with urllib.request.urlopen(f"https://huggingface.co/spaces/{SPACE_ID}/resolve/main/index.html") as r:
html = r.read().decode()
# Extract products JSON
m = re.search(r'var products\s*=\s*(\[[\s\S]*?\]);', html)
if not m:
print("ERROR: Khong tim thay products array")
return
# Parse
products_json = m.group(1)
products_json = re.sub(r'\\x([0-9a-f]{2})', lambda x: chr(int(x.group(1),16)), products_json)
products_json = re.sub(r',\s*([}\]])', r'\1', products_json)
products = json.loads(products_json)
print(f"Found {len(products)} products")
# Upload stubs
uploaded = 0
seen = {}
for p in products:
name = p.get('name', '')
slug = p.get('slug') or slugify(name)
if slug in seen:
seen[slug] += 1
slug = f"{slug}-{seen[slug]}"
seen[slug] = 0
stub = html_stub(
slug,
name[:200],
p.get('brand', ''),
p.get('price', ''),
p.get('image', ''),
p.get('description', '')
)
try:
api.upload_file(
path_or_fileobj=stub.encode(),
path_in_repo=f"san-pham/{slug}/index.html",
repo_id=SPACE_ID,
repo_type="space",
commit_message=f"SEO stub: {name[:40]}"
)
uploaded += 1
except Exception as e:
print(f" Error: {e}")
if uploaded % 100 == 0:
print(f" {uploaded}...")
time.sleep(0.5)
print(f"Done! {uploaded} stubs uploaded to {SPACE_ID}")
# Xoa file nay sau khi chay xong
print("\nKiem tra: curl -sI https://bep40-v-aistudio.static.hf.space/san-pham/<slug>/")
if __name__ == "__main__":
main()