import requests
from lxml import etree
from concurrent.futures import ThreadPoolExecutor

# 使用 session 来复用连接
session = requests.Session()

cookies = {
}

headers = {
}
params = {
  
}


# 爬取页面并获取链接
def get_page_urls(page):
    xhurl = f'https://xhcya.com/category/acg/page/{page}'   #分区链接
    try:
        resp = session.get(url=xhurl, headers=headers).text
        tree = etree.HTML(resp)
        urls = tree.xpath('//div[@class="inn-archive__item__container inn-card_post-thumbnail__item__container"]/a/@href')
        print(urls)
        return [url.split('/')[-1] for url in urls]
    except Exception as e:
        print(f"Error fetching page {page}: {e}")
        return []

# 发送 POST 请求
def post_data(post_id):
    try:
        data = f'------WebKitFormBoundaryZpZ0W9jNRUM2lSFt\r\nContent-Disposition: form-data; name="postId"\r\n\r\n{post_id}\r\n------WebKitFormBoundaryZpZ0W9jNRUM2lSFt--\r\n'
        response = session.post(url='https://xhcya.com/wp-admin/admin-ajax.php', headers=headers, data=data, params=params,cookies=cookies)
        print(f"Response for {post_id}: {response.text}")
    except Exception as e:
        print(f"Error posting data for {post_id}: {e}")

# 主函数，使用多线程并发
def main():
    with ThreadPoolExecutor(max_workers=20) as executor:
        # 获取所有页面的链接
        futures = [executor.submit(get_page_urls, page) for page in range(1, 5)]    #爬取页码数
        post_ids = []
        for future in futures:
            post_ids.extend(future.result())

        # 对每个链接的ID进行并发POST请求
        post_futures = [executor.submit(post_data, post_id) for post_id in post_ids]
        for future in post_futures:
            future.result()  # 等待所有请求完成

if __name__ == "__main__":
    main()