#!/usr/bin/env python3
"""检查吉安CMS站点的catid"""
import requests, re, sys

url = sys.argv[1]
r = requests.get(url, headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}, timeout=15)
r.encoding = "utf-8"
html = r.text

print(f"URL: {url}")
print(f"HTML: {len(html)} chars")

# 1. Look for catid in JS variables
for m in re.finditer(r'catid[\s\"\'=:]+(\d+)', html):
    print(f"  catid={m.group(1)}")

# 2. Look in script tags
scripts = re.findall(r'<script[^>]*>(.*?)</script>', html, re.DOTALL)
for s in scripts:
    for m in re.finditer(r'ajax_type[\s\"\'=:]+([^\"\'&\s,;\]]+)', s):
        print(f"  ajax_type={m.group(1)}")
    for m in re.finditer(r'catid[\s\"\'=:]+(\d+)', s):
        print(f"  catid(c)= {m.group(1)}")
    for m in re.finditer(r'data\s*[:=]\s*\{([^}]+)\}', s):
        print(f"  data_block={m.group(1)[:200]}")

# 3. Look for api-ajax_list references
for m in re.finditer(r'api-ajax_list', html):
    print(f"  Found: api-ajax_list at pos {m.start()}")

# 4. Look for form data
fds = re.findall(r'ajax_type[^<]{10,200}', html)
for fd in fds[:5]:
    print(f"  ajax_type_ref: {fd[:150]}")

# 5. Print page title
title = re.search(r'<title>(.*?)<', html)
if title:
    print(f"  Title: {title.group(1)}")