# -*- coding: utf-8 -*-
"""提取 A7 页面清单（pages dict 的 key = 页面名.html）+ sitemap 归属"""
import json, io, sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

doc = json.load(open(r'e:\code\crm-backend-matt\.scratch\lanhu-latest\axure-v29.json', encoding='utf-8'))
pages = doc['pages']

# ---- A7 页面（按 key 过滤，key = 页面名.html）----
a7 = {k: v for k, v in pages.items() if k.upper().startswith('A7')}
print('=== A7 pages:', len(a7), '===')
for k, v in a7.items():
    print(f"{k} | mapping={v['mapping_md5']}")

# ---- sitemap walk：输出每个叶子页的路径（区分正式树与草稿箱）----
def walk(node, path, out):
    name = node.get('pageName', '')
    cur = path + [name] if node.get('type') != 'Axure:Page' else path
    url = node.get('url')
    if url:
        out.append(('/'.join(cur), url))
    for ch in node.get('children') or []:
        walk(ch, cur, out)

leaves = []
for rn in doc['sitemap']['rootNodes']:
    walk(rn, [], leaves)

a7_tree = [(p, u) for p, u in leaves if u.upper().startswith('A7')]
print('=== A7 in sitemap tree:', len(a7_tree), '===')
for p, u in a7_tree:
    print(f'{u}  <-  {p}')