2020/11/11：爬虫基础（二） 爬取图片

#爬取图片
from urllib import request, parse
import re
import json
#动态增加的文件请求
url = 'https://tieba.baidu.com/f?kw=csgo&ie=utf-8'
pge  = int(input("请输入要访问的页数"))

headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:82.0) Gecko/20100101 Firefox/82.0"
}

for page in range(pge):
    pn = page*50
    u4 = url+"&pn"+"="+"%s"%pn
    res = request.Request(url = u4,headers = headers)
    response = request.urlopen(res)
    yya = response.read().decode("utf-8")
    #正则匹配
image_list = re.findall(r"(http://.*?jpg)", yya)
    #从数组中截取图片地址
# print(image_list)

for link in image_list:
    if link.startswith("http"):
        print("开始爬取:%s"%link)
        # request.urlretrieve(url= link, filename='../images/'+link[-10:])
    else:
        pass