#!/usr/bin/env python3
"""对 index.html 做结构与约束自检"""
from pathlib import Path
import re

html = Path('/data/workspace/index.html').read_text(encoding='utf-8')

checks = []

# 1. 基础结构
checks.append(("DOCTYPE 声明", "<!DOCTYPE html>" in html))
checks.append(("html lang=zh-CN", 'lang="zh-CN"' in html))
checks.append(("viewport 移动端", "viewport" in html))
checks.append(("title 非空", bool(re.search(r'<title>(.+?)</title>', html, re.S))))
checks.append(("keywords 非空", bool(re.search(r'name="keywords"[^>]*content="[^"]+', html))))
checks.append(("description 非空", bool(re.search(r'name="description"[^>]*content="[^"]+', html))))

# title 含更新时间
title_m = re.search(r'<title>(.+?)</title>', html, re.S)
checks.append(("title 含 更新时间 格式", title_m and "（更新时间：2026-09-16 22:01:37）" in title_m.group(1)))
checks.append(("title 优先马鞍山", title_m and title_m.group(1).startswith("安徽马鞍山")))

# 2. 无输入模块
checks.append(("无 form 表单", "<form" not in html.lower() and "form>" not in html.lower()))
checks.append(("无 input", "<input" not in html.lower()))
checks.append(("无 textarea", "<textarea" not in html.lower()))

# 3. 图片：只用提供的链接，无叠加文字水印（已用alt描述但不叠加在图上，属正常）
imgs = re.findall(r'<img[^>]+src="([^"]+)"', html)
provided = [
    "http://cdn.qiancipai.com/Image26091610463149272c.jpg",
    "http://cdn.qiancipai.com/Image260916104631289d36.jpg",
    "http://cdn.qiancipai.com/Image260916104633007e22.jpg",
    "http://cdn.qiancipai.com/Image2609161046322893b3.jpg",
    "http://cdn.qiancipai.com/Image2609161046322732ee.jpg",
    "http://cdn.qiancipai.com/Image260916104632726db6.jpg",
    "http://cdn.qiancipai.com/Image2609161046318043d2.jpg",
    "http://cdn.qiancipai.com/Image260916104631257ad9.jpg",
    "http://cdn.qiancipai.com/Image260916115601596220.png",
    "http://cdn.qiancipai.com/Image26091611510265267f.png",
]
allowed = set(provided)
img_ok = all(src in allowed for src in imgs)
checks.append(("图片全部来自提供清单（无自生成/替换）", img_ok))
checks.append(("去重图片 = 10 张全部使用", len(set(imgs)) == 10))

# Banner 用 115601596220.png
checks.append(("Banner 使用指定Banner图", "Image260916115601596220.png" in html))
# 关于配图
checks.append(("关于我们使用指定配图", "Image26091611510265267f.png" in html))

# 4. Banner 宽高比 1920x1000
checks.append(("Banner aspect-ratio 1920/1000", "aspect-ratio: 1920 / 1000" in html))

# 5. 板块齐全
for sec, kid in [
    ("首页Banner", 'class="banner"'),
    ("产品展示", 'id="products"'),
    ("关于我们", 'id="about"'),
    ("应用场景", 'id="scene"'),
    ("合作案例", 'id="cases"'),
    ("售后服务", 'id="service"'),
    ("FAQ", 'id="faq"'),
    ("城市分站入口", 'id="cities"'),
    ("友情链接", 'id="links"'),
]:
    checks.append((f"板块存在：{sec}", kid in html))

# 6. 响应式断点（7个）
for bp in [1920, 1440, 1280, 1100, 1024, 768, 375]:
    checks.append((f"响应式断点 {bp}px", f"max-width: {bp}px" in html))

# 7. 资质证书（未提供资料 → 不写该部分）
checks.append(("无资质证书板块（未提供资料）", 'id="qualification"' not in html and "资质证书" not in html))

# 8. 无 ICP 备案
checks.append(("无 ICP 备案信息", "ICP" not in html and "icp" not in html and "备案号" not in html))

# 9. 广告法：禁止绝对化用语
forbidden = ["最", "第一", "顶级", "全网最优", "国家级", "唯一", "极致"]
bad = [w for w in forbidden if w in html]
checks.append(("无绝对化用语（广告法）", len(bad) == 0))

# 10. 城市分站 & 友情链接完整性
for url in [
    "https://rtpnu.zhfmgc.com", "https://xotim.836188.com", "https://xzjnn.szbla.com",
    "https://ztsyk.9c3c.com", "https://aodnb.layouwei.com", "https://hjghd.szbla.com",
    "https://tavop.buhuihua.com", "https://llbko.wggjl.com", "https://znrhg.szbla.com",
    "https://rfccx.zhfmgc.com",
]:
    checks.append((f"城市分站链接 {url.split('//')[1]}", url in html))

for url in [
    "https://lgnbw.wggjl.com", "https://xgnvu.szbla.com", "https://hpesv.9c3c.com",
    "https://ajels.773588.com", "https://ivdhl.jntfw.com", "https://nigvf.aixixin.com",
    "https://llosg.836188.com", "https://xtlvu.aixixin.com", "https://mxjom.bfcmgg.com",
    "https://doypi.wggjl.com",
]:
    checks.append((f"友情链接 {url.split('//')[1]}", url in html))

# 公司信息
for info in ["鑫久正节能", "董先生", "18515896788", "安徽马鞍山"]:
    checks.append((f"公司信息含「{info}」", info in html))

# 产品关键词覆盖
kw = ["工业窑炉陶瓷纤维垫片", "燃气设备陶瓷纤维垫片", "陶瓷纤维方形垫片",
      "法兰耐高温垫片", "蒸汽管道垫片", "坩埚升液管法兰垫片",
      "陶瓷纤维密封垫片", "柔性耐高温垫片"]
for k in kw:
    checks.append((f"产品关键词「{k}」", k in html))

print("=" * 70)
ok = 0
for name, res in checks:
    print(f"  [{'✓' if res else '✗'}] {name}")
    ok += res
print("=" * 70)
print(f"通过: {ok}/{len(checks)}")