爬虫 中文编码

'''
url = 'http://pic.netbian.com/4kdongwu/'

response = requests.get(url=url,headers=headers)

手动设定编码格式

response.encoding = 'utf-8'

page_text = response.text

tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="slist"]/ul/li')

print(li_list)

import os

创建文件夹

if not os.path.exists('./img'):
os.mkdir('./img')

for li in li_list:
img_src = 'http://pic.netbian.com/'+li.xpath('./a/img/@src')[0]
img_name = li.xpath('./a/img/@alt')[0]+'.jpg'
img_name = img_name.encode('iso-8859-1').decode('gbk')

# print(img_name)

# 请求图片 存储 获取二进制文件
img_data = requests.get(url=img_src,headers=headers).content
img_path = './img/'+img_name
with open(img_path,'wb') as fp:
    fp.write(img_data)
    print('下载成功')

'''