爬虫获取网站美女图片
import requests
from lxml import html
import os
if __name__=="__main__":
etree = html.etree
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/80.0.3987.163 Safari/537.36'
}
response = requests.get(url=url,headers=headers)
page_text = response.text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="slist"]/ul/li')
if not os.path.exists('./picLibs'):
os.mkdir('./picLibs')
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')
img_data = requests.get(url=img_src,headers=headers).content
img_path = 'picLibs/'+img_name
with open(img_path,'wb') as fp:
fp.write(img_data)
print('over...')