#!/usr/bin/env python3
"""
生成图文混排的 HTML（图片内联为 base64），方便直接复制
"""
import os
import re
import base64
BASE_DIR = "/root/openclaw-workspace/projects/yu-zhi-ran/content/published/2026-04-14-上海阳台种菜一年"
MD_FILE = os.path.join(BASE_DIR, "final-article.md")
IMAGES_DIR = os.path.join(BASE_DIR, "images") # 使用发布目录内的 images
OUT_HTML = os.path.join(BASE_DIR, "上海阳台种菜一年_内联.html")
# 读取 Markdown
with open(MD_FILE, "r", encoding="utf-8") as f:
content = f.read()
# 预加载图片并转为 base64
image_cache = {}
for fname in os.listdir(IMAGES_DIR):
if fname.endswith('.png'):
path = os.path.join(IMAGES_DIR, fname)
with open(path, "rb") as imgf:
b64 = base64.b64encode(imgf.read()).decode('utf-8')
image_cache[fname] = b64
# 替换图片
def replace_img(match):
alt = match.group(1)
fname = match.group(2)
key = os.path.basename(fname)
if key in image_cache:
return f'
'
else:
return f'[图片缺失: {fname}]
'
content = re.sub(r'!\[(.*?)\]\((images/.*?)\)', replace_img, content)
# Markdown 转 HTML
html_lines = []
for line in content.split('\n'):
if line.startswith('# '):
html_lines.append(f'{line[2:]}
')
elif line.startswith('## '):
html_lines.append(f'{line[3:]}
')
elif line.startswith('### '):
html_lines.append(f'{line[4:]}
')
elif line.startswith('---'):
html_lines.append('
')
elif line.startswith('> '):
html_lines.append(f'{line[2:]}
')
elif re.match(r'^[-*] ', line):
html_lines.append(f'{line[2:]}')
elif re.match(r'^\d+\. ', line):
html_lines.append(f'{line[line.find(". ")+2:]}')
elif line.strip() == '':
html_lines.append('
')
else:
tmp = re.sub(r'\*\*(.*?)\*\*', r'\1', line)
tmp = re.sub(r'\*(.*?)\*', r'\1', tmp)
html_lines.append(f'{tmp}
')
html = f'''
上海阳台种菜一年
{chr(10).join(html_lines)}
'''
with open(OUT_HTML, "w", encoding="utf-8") as f:
f.write(html)
print(f"✅ HTML 已生成: {OUT_HTML}")
print(f"📊 字符数: {len(content)}")
print(f"🖼️ 内嵌图片: {len(image_cache)} 张")