版权声明:沃斯里德小浩浩啊 https://blog.csdn.net/Healer66/article/details/86602292
目标:
Python3爬取https://www.imooc.com/course/list的所有图片
# coding=gbk
import re
from urllib import request
url = 'https://www.imooc.com/course/list'
html = request.urlopen(url).read().decode('utf-8')
listurl = re.findall(r'src=.+\.jpg',html)
for i in range(len(listurl)):
listurl[i] = re.sub(r'src="','',listurl[i]) #把src="去掉
i = 1
for url in listurl:
f = open(str(i)+'.jpg','wb+')
html = request.urlopen('https:'+url).read() #必须要加上https:
f.write(html)
f.close()
i += 1