urllib.request 模拟游览器发送get请求，往请求头里面添加参数

• 模拟浏览器发送get请求

import urllib.request
response = urllib.request.urlopen("http://www.baidu.com")

• 往请求头里面进行添加数据

import urllib.request
 self.heads = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.100 Safari/537.36"
        }
# 让UA包含在请求里面，更像浏览器请求
request = urllib.request.Request(url=url,headers=self.heads)
content = urllib.request.urlopen(request)

urllib.parse url的解析，合并，编码，解码

• 对参数进行编码

# 以字典的方法进行编码
kw = {
    'kw': '帅哥'
}
result = urllib.parse.urlencode(kw)
url = 'https://tieba.baidu.com/f?' + result
# 以字符串进行编码

kw = '帅哥'
result = urllib.parse.quote(kw)
print(result)

• 对参数进行解码

urllib.parse.unquote(result)

• 对路由进行拼接

baseurl = 'https://book.qidian.com/info/1017777013#Catalog'
suburl = 'info/1018368514'
result = urllib.parse.urljoin(baseurl,suburl)
print(result)

• 把路由进行分割

import urllib.parse
url = 'https://book.qidian.com/info/1017777013#Catalog'
result = urllib.parse.urlparse(url=url,allow_fragments=False)

• 把切割好的路由进行拼接

# 必须传入七个参数
url = ('https','book.qidian.com','/info/1017777013','','','Catalog')
result = urllib.parse.urlunparse(url)