# -*- coding: utf-8 -*-
"""校验 index.html 合规性"""
import re, sys

html = open('index.html', encoding='utf-8').read()

PRODUCT_IMGS = [
    "Image260914185828073177.jpg",
    "Image260914185825479878.jpg",
    "Image2609141858254798df.jpg",
    "Image260914185827307941.jpg",
    "Image2609141858286671fe.jpg",
    "Image2609141858264178bf.jpg",
    "Image260914185828010d52.jpg",
    "Image260914185827120258.jpg",
]
BANNER = "Image260916111139706c0d.png"
ABOUT = "Image260916110252046a67.png"

CITY_LINKS = [
    "https://uyogr.qianyin168.com","https://mcueh.szbla.com","https://bqdwm.773588.com",
    "https://vvwzv.xmotp.com","https://pwniv.yuanyince1688.com","https://zyint.zhfmgc.com",
    "https://vygwe.jntfw.com","https://eiarf.bfcmgg.com","https://unmtj.qianyin168.com",
    "https://plonb.buhuihua.com",
]
FRIEND_LINKS = [
    "https://qcbsf.51mplg.com","https://pzvza.yuanyince1688.com","https://sludj.layouwei.com",
    "https://cemtf.51mplg.com","https://nunlz.jntfw.com","https://qbkhi.hgesf.com",
    "https://dccof.wggjl.com","https://ctqre.yu68999.com","https://ypslk.buhuihua.com",
    "https://zyscx.836188.com",
]

errors = []
warns = []

# 1. 图片检查：是否只用指定链接，无额外图片
used_imgs = re.findall(r'https?://cdn\.qiancipai\.com/([^\s"\'<>]+)', html)
allowed = set(PRODUCT_IMGS + [BANNER, ABOUT])
for u in used_imgs:
    if u not in allowed:
        errors.append(f"使用了未授权的图片: {u}")
# 确认所有指定图片都被用到（可选，至少检查关键）
for a in allowed:
    if a not in html:
        warns.append(f"指定图片未使用: {a}")

# 2. form / input 检查（禁止用户输入模块）
if re.search(r'<(form|input|textarea)\b', html, re.I):
    errors.append("页面包含 form/input/textarea，违反无用户输入模块约束")

# 3. 三要素
for tag in ['title', 'keywords', 'description']:
    if f'name="{tag}"' not in html and f'<{tag}' not in html:
        errors.append(f"缺少 {tag}")
if '安徽亳州' not in html:
    warns.append("三要素/内容未体现安徽亳州地区")

# 4. 资质证书板块检查：规则说没提供则不写 -> 确认无资质证书板块
if '资质' in html or '证书' in html:
    warns.append("页面出现资质/证书内容，素材未提供，建议移除")

# 5. ICP 备案检查
if 'ICP' in html or 'icp' in html or '备案号' in html:
    errors.append("底部出现 ICP 备案信息，违反约束")

# 6. Banner 比例检查
if 'aspect-ratio: 1920 / 1000' not in html:
    errors.append("Banner 未设置 1920:1000 比例")
if BANNER not in html:
    errors.append("Banner 图未使用指定链接")
if ABOUT not in html:
    errors.append("关于我们配图未使用指定链接")

# 7. 板块完整性
for sec, kw in [
    ('首页Banner', 'banner'), ('产品展示', 'products'), ('关于我们', 'about'),
    ('应用场景', 'scenarios'), ('合作案例', 'cases'), ('售后服务', 'service'),
    ('FAQ', 'faq'), ('城市分站', 'cities'), ('友情链接', 'links'),
]:
    if f'id="{kw}"' not in html:
        errors.append(f"缺少板块: {sec}")

# 8. 分站链接齐全
for c in CITY_LINKS:
    if c not in html:
        errors.append(f"缺少城市分站: {c}")
if len(CITY_LINKS) != 10:
    errors.append("城市分站数量非10个")
for f in FRIEND_LINKS:
    if f not in html:
        errors.append(f"缺少友情链接: {f}")
if len(FRIEND_LINKS) != 10:
    errors.append("友情链接数量非10个")

# 9. 绝对化用语检查（广告法）
banned = ['最', '第一', '顶级', '全网最优', '最好', '唯一', '国家级', '极致']
for b in banned:
    # 在中文语境下检查（忽略代码/注释）
    text_part = re.sub(r'<[^>]+>', '', html)
    if b in text_part:
        warns.append(f"文案可能含绝对化用语: 「{b}」")

print("=== 错误 (必须修复) ===")
for e in errors: print("  ✗", e)
print("\n=== 警告 (建议确认) ===")
for w in warns: print("  !", w)

print("\n=== 用到的图片清单 ===")
for u in used_imgs: print("  ✓", u)

print("\n图片叠加文字检查：搜索 banner-overlay 文字...")
overlay_text = re.findall(r'class="banner-overlay">(.*?)</div>', html, re.S)
if overlay_text:
    print("  Banner 叠加内容:", overlay_text[0].strip()[:100])
else:
    print("  ✓ Banner 无文字叠加（仅 img）")

sys.exit(1 if errors else 0)