pip install -i https://pypi.tuna.tsinghua.edu.cn/simple some-package lxml
from urllib.request import urlopen
from lxml import etree
import os
html = urlopen('http://gp.qq.com/cp/a20190522gamedata/pc_list.shtml')
html_lxml = etree.HTML(html.read().decode('GBK'))
list_index = html_lxml.xpath('//div[@id="section-container"]/ul')
for list in list_index:
file_title = list.xpath('preceding-sibling::h3')[-1].xpath('string()')
print('正在下载' + file_title + '文件')
if not os.path.exists(file_title):
os.mkdir(file_title)
for href in list.xpath('./li/a'):
img_src = urlopen('https:'+href.xpath('./img/@src')[0]).read()
img_title = href.xpath('./p/text()')[0]
print('下载文件:' + img_title)
with open(file_title+'/'+img_title+'.png', mode='wb') as ret:
ret.write(img_src)
print('下载成功')
![在这里插入图片描述](https://i-blog.csdnimg.cn/blog_migrate/71fa99eb4fd88264e4c35573acbe9b37.png#pic_center)