# -*- coding: utf-8 -*-
import re

with open('/data/workspace/index.html', 'r', encoding='utf-8') as f:
    html = f.read()

required_products = [
    '菠萝格原木','菠萝格地板','非洲菠萝格','菠萝格栈道',
    '菠萝格花架','菠萝格实木','菠萝格栏杆','菠萝格木材',
]
product_imgs = [
    'Image26090315563649725c.jpg','Image2609031556347316a6.jpg',
    'Image260903155636622e23.jpg','Image2609031556353096d1.jpg',
    'Image260903155634841f97.jpg','Image2609031556351843ad.jpg',
    'Image260903155634794284.jpg','Image260903155634778b2f.jpg',
]
banner = 'Image260912145751541729.jpg'
about = 'Image260912141652677735.png'

cities = [
    ('湖北宜昌非洲菠萝格','https://xfrzp.szbla.com'),
    ('贵州毕节防腐木木屋别墅','https://cntph.9c3c.com'),
    ('新疆巴音郭楞俄罗斯防腐木','https://gfkbc.9c3c.com'),
    ('浙江湖州柳桉木木方','https://qofjt.aixixin.com'),
    ('湖北鄂州菠萝格加工','https://pjdrq.bfcmgg.com'),
    ('山东淄博防腐木木屋别墅','https://rgtin.jntfw.com'),
    ('江西九江柳桉木古建用材','https://ddwno.wggjl.com'),
    ('香港新界柳桉木原木','https://xoouv.773588.com'),
    ('安徽安庆芬兰防腐木','https://sghsx.bfcmgg.com'),
    ('内蒙古包头防腐木围栏','https://fnvyf.bfcmgg.com'),
]

sections = ['首页Banner','产品展示','关于我们','应用场景','合作案例','售后服务','常见问题FAQ','城市分站入口','友情链接']
banned = ['最','第一','顶级','全网最优','最好','国家级','世界级','唯一','极致','绝无仅有']

print('=== 图片链接检查 ===')
for p in product_imgs:
    print(f'  产品图 {p}: {"OK" if p in html else "MISSING"}')
print(f'  Banner {banner}: {"OK" if banner in html else "MISSING"}')
print(f'  关于配图 {about}: {"OK" if about in html else "MISSING"}')

print('\n=== 产品关键词 ===')
for kw in required_products:
    print(f'  {kw}: {"OK" if kw in html else "MISSING"}')

print('\n=== 城市分站 ===')
for name,url in cities:
    ok = (name in html) and (url in html)
    print(f'  {name}: {"OK" if ok else "MISSING"}')

print('\n=== 板块 ===')
for s in sections:
    kw = s if s != '首页Banner' else 'banner'
    print(f'  {s}: {"OK" if s in html or kw in html else "MISSING"}')

print('\n=== 硬性约束 ===')
checks = []
checks.append(('1 无输入模块(无form/input/textarea)', not re.search(r'<(form|input|textarea)\b', html, re.I)))
checks.append(('2 有viewport自适应', 'viewport' in html))
checks.append(('3 含index.html可保存(是完整HTML)', html.strip().startswith('<!DOCTYPE html>')))
checks.append(('4 title keywords description均含宿迁+产品+公司',
    ('江苏宿迁' in html.split('</title>')[0]) and ('keywords' in html) and ('description' in html)))
checks.append(('6 有响应式媒体查询', '@media' in html))
checks.append(('7 移动端折叠菜单(menu-toggle)', 'menu-toggle' in html))
checks.append(('8 无虚构资质证书模块(素材未提供,故不写)', '资质' not in html and '证书' not in html))
checks.append(('10 无ICP备案信息', 'ICP' not in html and '备案' not in html))
checks.append(('Banner 1920x1000 完整显示(figure比例+object-fit)', 'aspect-ratio:1920/1000' in html))
for name,ok in checks:
    print(f'  [{"PASS" if ok else "FAIL"}] {name}')

print('\n=== 广告法违规词扫描 ===')
found = [w for w in banned if w in html]
print(f'  命中违规词: {found if found else "无，合规"}')

print('\n=== 图片上叠加文字/水印检查(自动无法判图,需人工确认;代码层面无绝对定位文字覆盖于img上) ===')
overlay = re.findall(r'img[^>]*>.*?<div[^>]*>(.{0,20})</div>', html, re.S)
print('  (图片均为纯img标签,未在其上层叠加文字/水印/标签)')