#!/usr/bin/env python3
"""测试分页URL格式"""
from playwright.sync_api import sync_playwright
from bs4 import BeautifulSoup
import re

def test_pagination(menu_id=7):
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page(viewport={'width': 1920, 'height': 1080})

        # 先打开第1页
        url1 = f"https://niaodaifu.cn/health-information?menu_id={menu_id}"
        print(f"[第1页] GET {url1}")
        page.goto(url1, wait_until='networkidle', timeout=30000)
        page.wait_for_timeout(3000)
        soup1 = BeautifulSoup(page.content(), 'html.parser')
        medias1 = soup1.find_all('div', class_='media')
        ids1 = []
        for m in medias1:
            a = m.find('a', class_='media-heading')
            if a:
                href = a.get('href', '')
                match = re.search(r'article_id=(\d+)', href)
                if match:
                    ids1.append(match.group(1))
        print(f"  第1页 article_ids: {ids1}")

        # 尝试几种分页URL格式
        formats = [
            f"https://niaodaifu.cn/health-information?menu_id={menu_id}&page=2",
            f"https://niaodaifu.cn/health-information?menu_id={menu_id}&pageNo=2",
            f"https://niaodaifu.cn/health-information?menu_id={menu_id}&pageIndex=2",
        ]

        for url2 in formats:
            print(f"\n[第2页] GET {url2}")
            page.goto(url2, wait_until='networkidle', timeout=30000)
            page.wait_for_timeout(3000)
            soup2 = BeautifulSoup(page.content(), 'html.parser')
            medias2 = soup2.find_all('div', class_='media')
            ids2 = []
            for m in medias2:
                a = m.find('a', class_='media-heading')
                if a:
                    href = a.get('href', '')
                    match = re.search(r'article_id=(\d+)', href)
                    if match:
                        ids2.append(match.group(1))
            print(f"  第2页 article_ids: {ids2}")
            if ids2 != ids1:
                print(f"  *** 分页有效！与第1页不同 ***")
                break
            else:
                print(f"  !!! 分页无效，与第1页相同 !!!")

        # 查看分页组件HTML
        print("\n\n[分页组件HTML]")
        pager = soup1.find(class_=re.compile('el-pagination'))
        if pager:
            print(pager.prettify()[:1000])
        else:
            print("未找到 el-pagination")

        browser.close()

if __name__ == '__main__':
    test_pagination()