#!/bin/bash
# 生成最终 HTML（内联图片，跳过广告相关图片）
python3 - << 'PYEOF'
import os, re, 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-optimized.md")
IMAGES_DIR = os.path.join(BASE_DIR, "images")
OUT_HTML = os.path.join(BASE_DIR, "上海阳台种菜一年_发布版.html")
SKIP_IMAGES = ["08-App截图.png"]
with open(MD_FILE, "r", encoding="utf-8") as f:
content = f.read()
# 预加载图片 base64（排除跳过的）
image_cache = {}
for fname in os.listdir(IMAGES_DIR):
if fname.endswith('.png') and fname not in SKIP_IMAGES:
path = os.path.join(IMAGES_DIR, fname)
with open(path, "rb") as fimg:
image_cache[fname] = base64.b64encode(fimg.read()).decode('utf-8')
# 替换图片
def replace_img(match):
alt, fname = match.groups()
key = os.path.basename(fname)
if key in image_cache:
return f'
'
else:
return f'[图片已省略: {alt}]
'
content = re.sub(r'!\[(.*?)\]\((images/.*?)\)', replace_img, content)
# MD → 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"✅ 最终发布 HTML: {OUT_HTML}")
print(f"📊 字符数: {len(content)}")
print(f"🖼️ 内嵌图片: {len(image_cache)} 张（跳过 {len(SKIP_IMAGES)} 张）")
print(f"💾 文件大小: {os.path.getsize(OUT_HTML)/1024:.1f} KB")
PYEOF