本章节需要掌握的知识点:
urllib中的parse
parse.quote() # 对带中文的参数进行编码
parse.unquote() # 解码
from urllib import request, parse
# 请求的url
url = 'https://baike.baidu.com/item/'
name = input('请输入需要查询的名字:')
# 对中文进行编码
params = parse.quote(name)
# 拼接url
url += params
# print(url)
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36'
' (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
}
# 构建请求对象
req = request.Request(headers=headers, url=url)
# 发送请求
res = request.urlopen(req)
# 将请求到的页面下载到本地
with open('%s.html' % name, 'w') as fp:
fp.write(res.read().decode('utf-8'))