爬虫_初步（爬取豆瓣图片）

from urllib.request import urlopen
import urllib.request,urllib.error
import re

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0'}

url = 'https://movie.douban.com/top250'
request = urllib.request.Request(url, headers=headers)#发送请求
response = urllib.request.urlopen(request)
get_1 = response.read().decode('utf-8')
get_1



imginfo = re.findall(r'<img width="100" alt="(.*?)" src="(.*?)" class="">',get_1)
imginfo
for i in range(0,20):
    imgurl = imginfo[i]
    imginfo[0]
    imgreq = urlopen(imgurl[1])
    imgc = imgreq.read()
    imgf = open(r'D:\\A-lesson work\\CCUT\\img2\\'+ imgurl[0]+'.jpg','wb')
    imgf.write(imgc)
    imgf.close()