#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""把选题档案 md 转成可直接打开的公网 html（只支持本文用到的几种结构）。"""
import re, html, sys
SRC = '/root/media-hub/topics/2026-11-04-下一条视频-WorkBuddy最好上手的PersonalAgent.md'
OUT = '/root/media-hub/export/拍摄/topic-next-video-1104.html'
lines = open(SRC, encoding='utf-8').read().split('\n')
out, i = [], 0
in_ul = in_ol = False
def close_lists():
global in_ul, in_ol
if in_ul:
out.append(''); in_ul = False
if in_ol:
out.append(''); in_ol = False
def inline(s):
s = html.escape(s)
s = re.sub(r'\*\*(.+?)\*\*', r'\1', s)
return s
while i < len(lines):
ln = lines[i]
s = ln.strip()
if not s:
close_lists(); i += 1; continue
if s == '---':
close_lists(); out.append('
'); i += 1; continue
if s.startswith('|'):
close_lists()
rows = []
while i < len(lines) and lines[i].strip().startswith('|'):
cells = [c.strip() for c in lines[i].strip().strip('|').split('|')]
if not re.fullmatch(r'[-: ]+', ''.join(cells)):
rows.append(cells)
i += 1
out.append('')
out.append('' + ''.join('| %s | ' % inline(c) for c in rows[0]) + '
')
out.append('')
for r in rows[1:]:
out.append('' + ''.join('| %s | ' % inline(c) for c in r) + '
')
out.append('
')
continue
if s.startswith('### '):
close_lists(); out.append('%s
' % inline(s[4:])); i += 1; continue
if s.startswith('## '):
close_lists(); out.append('%s
' % inline(s[3:])); i += 1; continue
if s.startswith('# '):
close_lists(); out.append('%s
' % inline(s[2:])); i += 1; continue
if s.startswith('> '):
close_lists(); out.append('%s
' % inline(s[2:])); i += 1; continue
if s.startswith('- '):
if not in_ul:
close_lists(); out.append(''); in_ul = True
out.append('- %s
' % inline(s[2:])); i += 1; continue
if re.match(r'^\d+\. ', s):
if not in_ol:
close_lists(); out.append(''); in_ol = True
out.append('- %s
' % inline(re.sub(r'^\d+\. ', '', s))); i += 1; continue
close_lists(); out.append('%s
' % inline(s)); i += 1
body = '\n'.join(out)
page = '''
下一条视频 · 选题档案（Jeanna 原话照录）
@@BODY@@
'''.replace('@@BODY@@', body)
open(OUT, 'w', encoding='utf-8').write(page)
print('ok', len(page.encode()))