import json, re

for fname, label in [('taixing_api.json','p1'),('taixing_p2.json','p2')]:
    with open(f'/root/gov_crawler/{fname}') as f:
        data = json.load(f)
    html = data['data']['html']
    titles = re.findall(r'title="([^"]+)"', html)
    print(f'\n=== {label} ===')
    for t in titles[:5]:
        print(f'  {t}')
    # Check pagination
    pagi = re.search(r'pageNo="(\d+)"\s+count="(\d+)"', html)
    if pagi:
        print(f'  pageNo={pagi.group(1)}, count={pagi.group(2)}')