#!/usr/bin/env python3
"""
在章节标题（h2）前插入分隔线，第一个除外
"""

import re

HTML_PATH = "/root/.openclaw/workspaces/yzr-yxl/projects/yu-zhi-ran/content/published/2026-04-14-上海阳台种菜一年/article-optimized.html"

with open(HTML_PATH, "r", encoding="utf-8") as f:
    html = f.read()

# 分隔线HTML
separator = '<div class="chapter-separator" style="margin: 40px 0 20px; border-top: 2px dashed #e0e0e0;"></div>\n'

# 找到所有 h2 标题
h2_pattern = re.compile(r'(<h2>.*?</h2>)', re.DOTALL)
matches = list(h2_pattern.finditer(html))

# 跳过第一个 h2，对其余每个插入分隔
insertions = []
for i, m in enumerate(matches[1:], start=1):  # 从第二个开始
    insert_pos = m.start()
    insertions.append((insert_pos, separator))

# 按位置逆序插入，避免影响后续位置
insertions.sort(reverse=True, key=lambda x: x[0])
html_list = list(html)
for pos, sep in insertions:
    html_list.insert(pos, sep)

new_html = ''.join(html_list)

# 写回
with open(HTML_PATH, "w", encoding="utf-8") as f:
    f.write(new_html)

print(f"✅ 已插入 {len(insertions)} 个章节分隔")
print(f"📄 文件: {HTML_PATH}")