#!/usr/bin/env python3
from playwright.sync_api import sync_playwright
import json

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    context = browser.new_context(
        user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
    )
    page = context.new_page()
    
    page.goto('http://www.njls.gov.cn/lsqrmzf/214/228/index_17658.html', 
              wait_until='networkidle', timeout=30000)
    
    # Find websiteURL
    result = page.evaluate("""
        (function() {
            var info = {};
            info.websiteURL = window.websiteURL || 'NOT_FOUND';
            info.isDongJing = window.isDongJing !== undefined ? window.isDongJing : 'NOT_FOUND';
            info.classinfoids = window.classinfoids || 'NOT_FOUND';
            info.param = window.param ? JSON.stringify(window.param) : 'NOT_FOUND';
            
            // Search in scripts
            var scripts = document.querySelectorAll('script:not([src])');
            for (var i = 0; i < scripts.length; i++) {
                var t = scripts[i].textContent || '';
                if (t.indexOf('websiteURL') !== -1) {
                    var m = t.match(/websiteURL[^;]+/);
                    if (m) info.websiteURL_src = m[0];
                }
                if (t.indexOf('isDongJing') !== -1) {
                    var m = t.match(/isDongJing[^;]+/);
                    if (m) info.isDongJing_src = m[0];
                }
                if (t.indexOf('websiteCode') !== -1) {
                    var m = t.match(/websiteCode[^;]+/);
                    if (m) info.websiteCode_src = m[0];
                }
            }
            
            // Check trspage variables
            info.currIndex = window.currIndex;
            info.totalNum = window.totalNum;
            
            return JSON.stringify(info);
        })()
    """)
    print('INFO:' + result)
    
    # Try to access page 2 directly: index_17658_1.html
    page2 = context.new_page()
    page2.goto('http://www.njls.gov.cn/lsqrmzf/214/228/index_17658_1.html',
               wait_until='networkidle', timeout=30000)
    items2 = page2.query_selector_all('#result > li')
    print('PAGE2_ITEMS:' + str(len(items2)))
    
    # Try page 3: index_17658_2.html
    page3 = context.new_page()
    page3.goto('http://www.njls.gov.cn/lsqrmzf/214/228/index_17658_2.html',
               wait_until='networkidle', timeout=30000)
    items3 = page3.query_selector_all('#result > li')
    print('PAGE3_ITEMS:' + str(len(items3)))
    
    context.close()
    browser.close()