python爬取漂亮小姐姐图片

import osimport requestsfrom lxml import etreeimport reheaders = {    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36 Edg/91.0.864.59',}# 保存文件def xzwj(xz, head, path):    w_na = xz.split("/")[-1]    w_rar = requests.get(xz, headers=head).content    with open(path + f'//{w_na}', 'wb') as f:        f.write(w_rar)        print("正在下载，请耐心等待。。。")        print(w_na, "下载完成")# 解释压缩文件网址def rar_xz(rar_url, head):    xz_res = requests.get(rar_url, headers=head).text    xz_rar = re.compile(r'window.location='(.*?)'')    xz = xz_rar.findall(xz_res)[0]    return xzdef xzxz(xx):    print("要下载的内容和网址是：", pna[xx - 1], pli[xx - 1])    print("---------开始下载展示图片------------")    r_resp = requests.get(pli[xx - 1], headers=headers)    r_tree = etree.HTML(r_resp.text)    r_imgs = r_tree.xpath('//div/div/p/img/@src')    r_nas = r_tree.xpath('//div/div/p/img/@title')    rar_url = r_tree.xpath('//div/div[@class="pay-box"]/a/@href')[0]    n = 1    gg=input('请输入保存的路径(默认c://,注意:需改为://):')    if gg =='':        gg='c://'    path = f"{gg+r_nas[0]}"    if not os.path.exists(path):        os.mkdir(path)    head = {        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36 Edg/91.0.864.59',        'referer': pli[xx - 1]    }    for img in r_imgs:        xzwj(img, head, path)        print(f"{r_nas[0][:-2]},第{n}张下载完成---")        n += 1    print("共", len(r_imgs), "张下载完成")    print("==============开始下载压缩文件============")    xz = rar_xz(rar_url, head)    xzwj(xz, head, path)def main_xz():    print("1.性感美女 2.清纯可爱 3.性感御姐 4.制服诱惑")    ms = input("请选择分类：")    url1 = "https://dimgw.us/xinggan"    url2 = "https://dimgw.us/qc"    url3 = "https://dimgw.us/yj"    url4 = "https://dimgw.us/zf"    if int(ms) == 1:        url = url1    elif int(ms) == 2:        url = url2    elif int(ms) == 3:        url = url3    elif int(ms) == 4:        url = url4    resp = requests.get(url, headers=headers)    pages = re.findall(r'<a class="page-numbers" href="(.*?)</a>', resp.text)[-1]    page = pages.split(">")[-1]    print("此类共", page, "页！")    print("*" * 50)    pna = []    pli = []    for p in range(1, int(page) + 1):        purl = url + f"/page/{p}"        presp = requests.get(purl, headers=headers)        tree = etree.HTML(presp.text)        rw_li = tree.xpath('//div[@class="row posts-wrapper"]//div/a[@target="_blank"]/@href')        rw_na = tree.xpath('//div[@class="row posts-wrapper"]//div/a[@target="_blank"]/img/@alt')        pna.extend(rw_na)        pli.extend(rw_li)    print("-" * 50, "n", "共有以下美女可选：")    for na in pna:        print(pna.index(na) + 1, na)    return pna, plipna, pli = main_xz()var = 1while var != len(pna):    xx = int(input("请输入要下载的序号(0退出):"))    if xx != 0:        xzxz(xx)    else:        print("退出")        break    var += 1