import requests
from lxml import etree
import os #存储模块
if __name__ == "__main__":
url = 'http://pic.netbian.com/4kmeinv/'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
}
if not os.path.exists('./picLibs'):
os.mkdir('./picLibs') #如果没有就创建一个文件夹
response = requests.get(url=url, headers=headers)
# response.encoding = 'gbk'#通用处理中文乱码的解决方案
# response.encoding = response.apparent_encoding #通用处理中文乱码的解决方案
page_text = response.text
tree = etree.HTML(page_text)
# 数据解析:src的属性值 alt属性值
li_list = tree.xpath('//div[@class="slist"]/ul/li')
# 创建一个文件夹
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'
# 通用处理中文乱码的解决方案
img_name = img_name.encode('iso-8859-1').decode('gbk') # 需要重新赋值
# print(img_name,img_src)
# 请求图片持久化存储
img_data = requests.get(url=img_src, headers=headers).content
img_path = 'picLibs/' + img_name
with open(img_path, 'wb') as fp: # 多次打开存储
fp.write(img_data)
print(img_name, '下载成功!!')
fp.close() # 结束循环
运行结果
得到图片