华为交换机学习

crawler 简单的爬取百度图片,并保存图片

Crawler 爬虫——爬取百度图片

import urllib
from urllib import request, parse
import re

# keyword = "阿狸"
# keyword = urllib.parse.quote(keyword)
# print(keyword)    #%E9%98%BF%E7%8B%B8

url = "https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1600852001400_R&pv=&ic=0&nc=1&z=&hd=&latest=&copyright=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&sid=&word=%E9%98%BF%E7%8B%B8"
result = request.urlopen(url=url).read().decode('utf-8')
# print(result)
# 写入html
# with open("picture.html", 'w', encoding='utf-8') as w:
#     w.write(result)

#正则匹配规则,列表存储符合的图片链接
rule = '"thumbURL":"(.*?)"'
pic_list = re.findall(rule, result)

#遍历列表,然后保存图片
a = 1
for i in pic_list:
    print(i)
    res = request.urlopen(i).read()
    string = str(a) + '.jpg'
    a = int(a)+1
    with open(string, 'wb') as w:
        w.write(res)