#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""查看服务器HTML中content链接的li结构"""
import re, time
from playwright.sync_api import sync_playwright

IP = "171.221.172.137"
UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
LIST_URL = "http://www.pujiang.gov.cn/pjxrmzf/c160163/nav_list.shtml"

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True, args=[
        "--disable-blink-features=AutomationControlled", "--no-sandbox",
        f"--host-resolver-rules=MAP www.pujiang.gov.cn {IP}, MAP pujiang.gov.cn {IP}",
    ])
    ctx = browser.new_context(user_agent=UA, locale="zh-CN", viewport={"width": 1920, "height": 1080})
    page = ctx.new_page()
    try:
        page.goto(LIST_URL, timeout=10000, wait_until="domcontentloaded")
    except Exception:
        pass
    for i in range(10):
        time.sleep(2)
        try:
            html = page.content()
        except Exception:
            continue
        if "_ts" not in html and len(html) > 5000:
            break
    # 找 content_ 链接的上下文
    idx = html.find("content_")
    print("第一个 content_ 位置:", idx)
    if idx > 0:
        seg = html[idx-400:idx+400]
        print("上下文:")
        print(seg)
    # 保存HTML供分析
    open("/tmp/pj_srv_list.html", "w", encoding="utf-8").write(html)
    print("\n已保存 /tmp/pj_srv_list.html, 总长", len(html))
    browser.close()