File size: 3,671 Bytes
201164a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | #!/usr/bin/env python3
"""
SEO Stub Generator - Phiên bản đơn giản cho Static Space
Tạo file HTML stub cho mỗi sản phẩm để xử lý URL /san-pham/{slug}/
CÁCH CHẠY:
1. Trên UI Space: Settings → Build → Trigger Rebuild
(Build sẽ tự động chạy build.sh → python3 app/run_seo_generation.py)
2. Hoặc manually: python3 app/run_seo_generation.py
YÊU CẦU:
- huggingface_hub (được cài trong build.sh)
"""
import json
import re
import unicodedata
import urllib.request
try:
from huggingface_hub import HfApi
except ImportError:
import subprocess
subprocess.run(["pip", "install", "huggingface_hub", "-q"])
from huggingface_hub import HfApi
SPACE_ID = "bep40/V.AISTUDIO"
BASE_URL = "https://bep40-v-aistudio.static.hf.space"
def slugify(name):
s = unicodedata.normalize('NFKD', name or '').lower()
s = re.sub(r'[^a-z0-9]+', '-', s).strip('-')
return s or str(hash(name) % 100000)
def create_stub(p):
slug = p.get('slug') or slugify(p.get('name', 'product'))
name = str(p.get('name', 'Product'))[:200]
brand = str(p.get('brand', ''))
img = p.get('image') or f"{BASE_URL}/logo/logo_600.png"
desc = re.sub(r'<[^>]+>', '', str(p.get('description', '')))[:160]
title = f"{name} | {brand} - V.AISTUDIO" if brand else f"{name} - V.AISTUDIO"
return f'''<!DOCTYPE html>
<html lang="vi">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>{name} | {brand} - V.AISTUDIO</title>
<meta name="description" content="{desc}">
<meta name="robots" content="noindex,follow">
<link rel="canonical" href="{BASE_URL}/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_URL}/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():
# Tải index.html
url = f"https://huggingface.co/spaces/{SPACE_ID}/resolve/main/index.html"
try:
with urllib.request.urlopen(url, timeout=30) as r:
html = r.read().decode('utf-8')
except Exception as e:
print(f"LỖI tải index: {e}")
return
# Trích xuất products
match = re.search(r'var\s+products\s*=\s*(\[[\s\S]*?\]);', html)
if not match:
print("KHÔNG TÌM THẤY products array!")
return
products = json.loads(match.group(1))
print(f"Tìm thấy {len(products)} sản phẩm")
api = HfApi()
uploaded = 0
errors = 0
for i, p in enumerate(products):
slug = p.get('slug') or slugify(p.get('name', 'product'))
stub = create_stub(p)
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: {slug}"
)
uploaded += 1
if uploaded % 100 == 0:
print(f"✓ Đã tạo {uploaded}/{len(products)} stubs...")
except Exception as e:
errors += 1
if errors < 5:
print(f"Lỗi {slug}: {e}")
print(f"\n=== HOÀN THÀNH ===")
print(f"Thành công: {uploaded}")
print(f"Lỗi: {errors}")
if __name__ == "__main__":
main() |