使用 Python 自动化爬取并下载 APK 文件：以游戏巴士为例

import os
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin, urlparse
import time

# 配置项
BASE_URL = "https://www.youxibashi.cn/"
DOWNLOAD_DIR = "apks"
HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0 Safari/537.36"
}

# 创建下载目录
os.makedirs(DOWNLOAD_DIR, exist_ok=True)

def extract_apk_link(page_url):
    """
    从游戏巴士的软件详情页提取 APK 下载链接
    示例页面：
      - https://www.youxibashi.cn/download/9727.html （乐学喵）
      - https://www.youxibashi.cn/download/3082.html （奥北体能）
      - https://www.youxibashi.cn/download/654.html  （护眼大师）
    """
    try:
        resp = requests.get(page_url, headers=HEADERS, timeout=10)
        resp.raise_for_status()
        soup = BeautifulSoup(resp.text, 'html.parser')

        # 查找包含 "APK下载" 的 <a> 标签（普通下载）
        download_link = soup.find('a', string=lambda text: text and 'APK下载' in text)
        if download_link and download_link.get('href'):
            apk_url = urljoin(BASE_URL, download_link['href'])
            return apk_url
        else:
            print(f"[!] 未在 {page_url} 找到 APK 下载链接")
            return None
    except Exception as e:
        print(f"[ERROR] 解析 {page_url} 失败: {e}")
        return None

def download_apk(apk_url, save_dir):
    """下载 APK 并保存"""
    try:
        resp = requests.get(apk_url, headers=HEADERS, stream=True, timeout=30)
        resp.raise_for_status()

        # 从 URL 中提取文件名
        filename = os.path.basename(urlparse(apk_url).path)
        if not filename.endswith('.apk'):
            filename += '.apk'

        filepath = os.path.join(save_dir, filename)
        with open(filepath, 'wb') as f:
            for chunk in resp.iter_content(chunk_size=8192):
                f.write(chunk)
        print(f"[✓] 已保存: {filepath}")
    except Exception as e:
        print(f"[ERROR] 下载失败 {apk_url}: {e}")

def main():
    # 待爬取的软件详情页列表（可扩展）
    target_pages = [
        "https://www.youxibashi.cn/download/9727.html",  # 乐学喵 - MBA备考平台
        "https://www.youxibashi.cn/download/3082.html",  # 奥北体能 - 校园体测助手
        "https://www.youxibashi.cn/download/654.html",   # 护眼大师 - 蓝光过滤工具
    ]

    for page in target_pages:
        print(f"\n[+] 正在处理: {page}")
        apk_link = extract_apk_link(page)
        if apk_link:
            print(f"  → 发现 APK 链接: {apk_link}")
            download_apk(apk_link, DOWNLOAD_DIR)
        else:
            print("  → 跳过")
        time.sleep(1)  # 礼貌性延迟

    print(f"\n[INFO] 所有任务完成！APK 保存至: ./{DOWNLOAD_DIR}/")

if __name__ == "__main__":
    main()