xpath小练习，爬取美女图片

import requests
from lxml import etree
import os
import time

dir_path = './meinv'
if not os.path.exists(dir_path):
    os.mkdir(dir_path)

# 因为第一页的url和后面的不一样，所以这段代码把url进行了处理
url_list = ['http://pic.netbian.com/4kmeinv/']
url_template = 'http://pic.netbian.com/4kmeinv/index_%d.html'
for page in range(2, 11):  # 自行设定要爬取的页码数量
    url_list.append(format(url_template % page))

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0'}
for url in url_list:
    page_text = requests.get(url=url, headers=headers).text
    tree = etree.HTML(page_text)
    a_list = tree.xpath('//div[@class="slist"]/ul/li/a')
    for a in a_list:
        img_src = 'http://pic.netbian.com' + a.xpath('./img/@src')[0]
        img_name = a.xpath('./b/text()')[0]
        img_name = img_name.encode('iso-8859-1').decode('gbk')  # 解决中文乱码
        img = requests.get(url=img_src, headers=headers).content  # content用来获取二进制内容
        img_path = dir_path + '/' + img_name + '.jpg'
        with open(img_path, 'wb') as f:
            f.write(img)
            print(img_name, '下载成功！')
    time.sleep(30)