如何用Wget或Python批量下载指定网站的.zip与.utu文件？

我来帮你搞定批量下载这些AI涂装文件的问题！你的原始代码只做了最基础的链接提取，没处理Archive.org的链接结构、页面嵌套层级、超时重试和异常捕获这些关键问题，所以才会失败。下面分两部分给你提供更健壮的Python实现：

一、批量下载Project AI的.zip涂装文件 #

Project AI的文件需要经过分类页→子分类页→涂装详情页→下载链接的多层嵌套，我们需要逐层解析，同时处理Archive.org的链接重定向问题：

改进后的代码（Python 3.x） #

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import os
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry

# 配置会话和重试机制，解决超时和连接问题
def create_session():
    session = requests.Session()
    retry_strategy = Retry(
        total=3,
        backoff_factor=1,
        status_forcelist=[429, 500, 502, 503, 504]
    )
    adapter = HTTPAdapter(max_retries=retry_strategy)
    session.mount("http://", adapter)
    session.mount("https://", adapter)
    return session

# 解析分类页面，获取子分类链接
def get_subcategory_links(session, base_url):
    sub_links = []
    try:
        response = session.get(base_url, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, "html.parser")
        # 找到子分类的飞机图片链接（根据页面结构调整选择器）
        for link in soup.select("a[href*='acfiles.php?cat=']"):
            full_link = urljoin(base_url, link["href"])
            if full_link not in sub_links:
                sub_links.append(full_link)
        return sub_links
    except Exception as e:
        print(f"获取子分类链接失败: {e}")
        return []

# 解析子分类页面，获取涂装详情页链接
def get_repaint_links(session, sub_url):
    repaint_links = []
    try:
        response = session.get(sub_url, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, "html.parser")
        # 找到跳转到涂装详情页的链接（匹配repaints.php格式）
        for link in soup.select("a[href*='repaints.php?ac=']"):
            full_link = urljoin(sub_url, link["href"])
            repaint_links.append(full_link)
        return repaint_links
    except Exception as e:
        print(f"获取涂装详情页链接失败: {e}")
        return []

# 解析涂装详情页，获取下载链接
def get_download_link(session, repaint_url):
    try:
        response = session.get(repaint_url, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, "html.parser")
        # 找到download.php的下载链接
        download_link = soup.find("a", href=lambda x: x and "download.php?fileid=" in x)
        if download_link:
            return urljoin(repaint_url, download_link["href"])
        return None
    except Exception as e:
        print(f"获取下载链接失败: {e}")
        return None

# 下载文件到指定目录
def download_file(session, download_url, save_dir="project_ai_paints"):
    os.makedirs(save_dir, exist_ok=True)
    try:
        # 先获取文件名，从响应头或者链接解析
        filename = download_url.split("fileid=")[-1] + ".zip"
        save_path = os.path.join(save_dir, filename)
        
        # 跳过已下载的文件
        if os.path.exists(save_path):
            print(f"文件 {filename} 已存在，跳过下载")
            return
        
        response = session.get(download_url, timeout=15, stream=True)
        response.raise_for_status()
        with open(save_path, "wb") as f:
            for chunk in response.iter_content(chunk_size=8192):
                f.write(chunk)
        print(f"成功下载: {filename}")
    except Exception as e:
        print(f"下载文件失败 {download_url}: {e}")

# 主函数：批量处理两个分类页面
def main_project_ai():
    session = create_session()
    base_urls = [
        "http://web.archive.org/web/20050315112710/http://www.projectai.com:80/libraries/acfiles.php?cat=6",
        "http://web.archive.org/web/20050315112940/http://www.projectai.com:80/libraries/acfiles.php?cat=1"
    ]
    
    for base_url in base_urls:
        print(f"开始处理分类页面: {base_url}")
        sub_cats = get_subcategory_links(session, base_url)
        for sub_cat in sub_cats:
            print(f"处理子分类: {sub_cat}")
            repaint_pages = get_repaint_links(session, sub_cat)
            for repaint_page in repaint_pages:
                dl_link = get_download_link(session, repaint_page)
                if dl_link:
                    download_file(session, dl_link)

if __name__ == "__main__":
    # 先运行Project AI的下载
    main_project_ai()

二、批量下载Flight 1 Ultimate Traffic的.utu文件 #

这个页面的下载链接是相对路径，我们只需要提取所有.utu格式的下载链接，直接批量下载即可：

对应的代码（可以追加到上面的脚本中） #

def main_ultimate_traffic():
    session = create_session()
    base_url = "http://web.archive.org/web/20060512161232/http://ultimatetraffic.flight1.net:80/utfiles.asp?mode=1&index=0"
    save_dir = "ultimate_traffic_paints"
    os.makedirs(save_dir, exist_ok=True)
    
    try:
        response = session.get(base_url, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, "html.parser")
        
        # 提取所有.utu的下载链接
        for link in soup.select("a[href*='.utu']"):
            relative_link = link["href"]
            # 补全完整的Archive.org链接
            full_download_link = urljoin(base_url, relative_link)
            # 解析文件名
            filename = relative_link.split("id=")[-1]
            save_path = os.path.join(save_dir, filename)
            
            if os.path.exists(save_path):
                print(f"文件 {filename} 已存在，跳过")
                continue
            
            try:
                response = session.get(full_download_link, timeout=15, stream=True)
                response.raise_for_status()
                with open(save_path, "wb") as f:
                    for chunk in response.iter_content(chunk_size=8192):
                        f.write(chunk)
                print(f"成功下载: {filename}")
            except Exception as e:
                print(f"下载失败 {full_download_link}: {e}")
    except Exception as e:
        print(f"获取Ultimate Traffic页面失败: {e}")

# 调用Ultimate Traffic的下载函数
if __name__ == "__main__":
    # main_project_ai()  # 取消注释可运行Project AI下载
    main_ultimate_traffic()

关键改进点说明 #

• 会话与重试机制：用requests.Session()保持连接，配合重试策略解决超时、5xx错误等问题
• 链接补全：用urljoin处理相对链接，确保生成完整的Archive.org可访问链接
• 异常捕获：每个步骤都加了异常处理，避免单个链接失败导致整个程序崩溃
• 增量下载：检查文件是否已存在，跳过重复下载
• 流式下载：用stream=True分块下载大文件，避免内存溢出

注意：运行代码前需要先安装依赖：pip install requests beautifulsoup4 urllib3

内容的提问来源于stack exchange，提问作者Edward Winch