day5-requests的post方法

1.初步接触post

1.requests的POST请求

'''
# 1.访问login页面获取token信息

Request URL:
            https://github.com/login



Request Method: GET



#服务端告诉客户端需要设置的Cookies
响应头(response headers)：
    Set-Cookies

请求头(request headers)：
    Cookie
    User-Agent
'''

headers ={'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36'
          }
import requests
import  re

url1='https://github.com/login'
response = requests.get(url1,headers=headers)

#把login页返回的cookie信息转换为字典
login_cookies =response.cookies.get_dict()
#print(login_cookies)


"""
正则：<input type="hidden" name="authenticity_token" value="uL0puwy/WXwQGy8lfuaAGUPAKd21SSXvVpDkTL1knnqB/quwOgpTNqAxWTK46vQQ1V/l+vbiJPJfLme/sE4IQg==">

<input type="hidden" name="authenticity_token" value="(.*?)">
"""


token = re.findall('<input type="hidden" name="authenticity_token" value="(.*?)">',response.text,re.S)

print(token[0])

#token = re.findall('<input type="hidden" name="authenticity_token" value="(.*?)" />', response.text, re.S)
# print(token[0])

"""
2.往session页面发送post请求

(sesson) 的 network

Request URL: https://github.com/session
Request Method: POST

请求头：
    Cookie: _ga=GA1.2.2136829516.1560742337; _octo=GH1.1.872698775.1560742337; tz=Asia%2FShanghai; has_recent_activity=1; _device_id=f5631dc46d2624aa16f4da6fd575faec; logged_in=no; _gh_sess=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%3D--c73c325ede2287adaf39d672c39b4135bc467328
    User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36
    
Form Data:
    commit: Sign in
    utf8: ✓
    authenticity_token: uL0puwy/WXwQGy8lfuaAGUPAKd21SSXvVpDkTL1knnqB/quwOgpTNqAxWTK46vQQ1V/l+vbiJPJfLme/sE4IQg==
    login: evan0925
    password: bombardfox#0131
    webauthn-support: supported


"""

url2 = 'https://github.com/session'

# 拼接请求体信息

form_data = {
    'commit':'Sign in',
     'utf8': '✓',
     'authenticity_token': 'uL0puwy/WXwQGy8lfuaAGUPAKd21SSXvVpDkTL1knnqB/quwOgpTNqAxWTK46vQQ1V/l+vbiJPJfLme/sE4IQg==',
     'login': '********',
     'password': '***************',
      'webauthn-support': 'supported'
}

"""
Referer: https://github.com/login
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36
"""


headers1 = {
    'Referer': 'https://github.com/login',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36'
}

# 携带请求头、请求体、login页的cookies信息

response2 = requests.post(url2,data= form_data,headers=headers1,cookies=login_cookies)



# print(response2.status_code)
# print(response2.text)
with open('github.html','w',encoding='utf-8') as f :
    f.write(response2.text)

　　说明：

    '''
    post请求登录github

    Request URL:
        https://github.com/session

    Request
        Method: POST

    #Referer表示上一个请求的页面
    Referer:
        https://github.com/login

    User-Agent:
        Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36

    请求体：
        只有POST请求才有
        commit: Sign in
        utf8: ✓
        authenticity_token: COh/MDoDDUVauDtPbZ2A6pjf4pEA4pV8jwRO8PjHPzbXiLJiwtCXRQ7Ik3kXWxJOOF+i5/1r9twxUqaUnXe5TA==
        login: HS1
        password: ***********
        webauthn-support: unsupported
'''
   

2.response响应　　

import  requests
response = requests.get('https://www.baidu.com')

print(response.status_code) #获取响应状态吗
print(response.url)  #获取url地址
print(response.text) #获取文本
print(response.content) #获取二进制流
print(response.headers)#获取页面请求头信息
print(response.history) #获取上一次的请求地址
print(response.cookies)#返回cookie对象
print(response.cookies.get_dict()) #获取cookies信息转换成字典
print(response.cookies.items) #同上
print(response.encoding) #字符编码
print(response.elapsed)#访问时间

#一点一点写入二进制流
import requests


#一点一点写入二进制流
import requests

# 往音频地址发送get请求

url = 'https://vd3.bdstatic.com/mda-ic4pfhh3ex32svqi/hd/mda-ic4pfhh3ex32svqi.mp4?auth_key=1557973824-0-0-bfb2e69bb5198ff65e18065d91b2b8c8&bcevod_channel=searchbox_feed&pd=wisenatural&abtest=all.mp4'
response = requests.get(url, stream=True)     # stream=True 把content设置为一个迭代器对象
print(response.content)

with open('love_for_GD.mp4', 'wb') as f:
    for content in response.iter_content():
        f.write(content)

　　

3.requests高级应用（了解）

'''
证书验证(大部分网站都是https)
'''
import requests


# https = http + ssl
response = requests.get('https://www.xiaohuar.com')
print(response.status_code)


# 改进1:去掉报错,但是会报警告
import requests
response = requests.get('https://www.xiaohuar.com', verify=False)
# 不验证证书,报警告,返回200
print(response.status_code)

# 改进2:去掉报错,并且去掉警报信息
import requests
import urllib3
urllib3.disable_warnings()  # 关闭警告
response = requests.get('https://www.xiaohuar.com', verify=False)
print(response.status_code)

# 改进3:加上证书(伪代码)
# 很多网站都是https,但是不用证书也可以访问,大多数情况都是可以携带也可以不携带证书
# 知乎\百度等都是可带可不带
# 有硬性要求的,则必须带，比如对于定向的用户,拿到证书后才有权限访问某个特定网站
import requests
response = requests.get(
    'https://www.xiaohuar.com',
    cert=('/path/server.crt', '/path/key'))
print(response.status_code)


'''
超时设置

# 两种超时:float or tuple
# timeout=0.1  # 代表接收数据的超时时间
# timeout=(0.1,0.2)  # 0.1代表链接超时  0.2代表接收数据的超时时间
'''

import requests

response = requests.get('https://www.baidu.com',
                        timeout=0.0001)
print(response.status_code)


'''
使用代理（重要指数*******）

# 代理设置:先发送请求给代理,然后由代理帮忙发送(封ip是常见的事情)
# 西刺代理
'''

import requests
proxies={
    # 带用户名密码的代理,@符号前是用户名与密码
    'http': 'http://tank:123@localhost:9527',
    'http': 'http://localhost:9527',
    'https': 'https://localhost:9527',
}
response = requests.get('https://www.12306.cn', proxies=proxies)
print(response.status_code)


# 支持socks代理,安装:pip install requests[socks]
import requests
proxies = {
    'http': 'socks5://user:pass@host:port',
    'https': 'socks5://user:pass@host:port'
}
respone = requests.get('https://www.12306.cn', proxies=proxies)

print(respone.status_code)


'''
# 认证设置
登录网站时，会弹出一个框，要求你输入用户名与密码（类似于alert），此时无法进入html页面，待授权通过后才能进入html页面。

Requests模块为我们提供了多种身份认证方式，包括基本身份认证等...

其原理指的是通过输入用户名与密码获取用户的凭证来识别用户，然后通过token对用户进行授权。
基本身份认证:
    HTTP Basic Auth是HTTP1.0提出的认证方式。客户端对于每一个realm，通过提供用户名和密码来进行认证的方式当认证失败时，服务器收到客户端请求，返回401。

'''
import requests
# 通过访问github的api来测试
url = 'https://api.github.com/user'
HEADERS = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
}

# 测试1，失败返回401
response = requests.get(url, headers=HEADERS)
print(response.status_code)  # 401
print(response.text)


# 测试2，通过requests.auth内的HTTPBasicAuth进行认证，认证成功返回用户信息
from requests.auth import HTTPBasicAuth
response = requests.get(url, headers=HEADERS, auth=HTTPBasicAuth('uesrname', 'pwd'))
print(response.text)


# 测试3，通过requests.get请求内的auth参数默认就是HTTPBasicAuth，认证成功返回用户信息
response = requests.get(url, headers=HEADERS, auth=('*******', '**********'))
print(response.text)


'''
上传文件
'''
import requests

# 上传文本文件
files1 = {'file': open('user.txt', 'rb')}
response = requests.post('http://httpbin.org/post', files=files1)
print(response.status_code)  # 200
print(response.text)  # 200

# 上传图片文件
files2 = {'jpg': open('小狗.jpg', 'rb')}
response = requests.post('http://httpbin.org/post', files=files2)
print(response.status_code)  # 200
print(response.text)  # 200

# 上传视频文件
files3 = {'movie': open('love_for_GD.mp4', 'rb')}
response = requests.post('http://httpbin.org/post', files=files3)
print(response.status_code)  # 200
print(response.text)  # 200