|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
import requests
from lxml import etree
import os
#url
ulr = 'https://movie.douban.com/top250'
#UA伪装
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36'
}
#发起请求
response = requests.get(url=ulr,headers=headers)
page_text = response.text
#数据解析
tree = etree.HTML(page_text)
li_list = tree.xpath('//ol[@class="grid_view"]/li')
#保存图片文件创建
if not os.path.exists('./doubanTOP250'):
os.mkdir('./doubanTOP250')
#循环抓取
for li in li_list:
movie_name = li.xpath('div/div[2]/div[@class="hd"]/a/span[1]/text()')[0]
movie_img = li.xpath('div/div[1]/a/img/@src')[0]
movie_data = requests.get(url=movie_img,headers=headers).content
movie_path = 'doubanTOP250/'+movie_name
#文件保存
with open(movie_path,'wb') as fp:
fp.write(movie_data)
print(movie_name+'下载成功!!!') |
|