requests模块

requests模块

 

requests

Python标准库中提供了：urllib、urllib2、httplib等模块以供Http请求，但是，它的 API 太渣了。它是为另一个时代、另一个互联网所创建的。它需要巨量的工作，甚至包括各种方法覆盖，来完成最简单的任务。

Requests 是使用 Apache2 Licensed 许可证的 基于Python开发的HTTP 库，其在Python内置模块的基础上进行了高度的封装，从而使得Pythoner进行网络请求时，变得美好了许多，使用Requests可以轻而易举的完成浏览器可有的任何操作。

安装

pip3 install requests 

1、GET请求

# 1、无参数实例

import requests

ret = requests.get('https://github.com/timeline.json')

print(ret.content)  # 获取收到的字节内容，bytes类型
print(ret.apparent_encoding)  # 获取当前网站的编码格式
ret.encoding = ret.apparent_encoding  # 设置编码格式
print(ret.url)
print(ret.text)  # 获取解码后的结果

# 2、有参数实例

import requests

payload = {'key1': 'value1', 'key2': 'value2'}  
ret = requests.get("http://httpbin.org/get", params=payload)  # params为url上？后的参数

print(ret.url)
print(ret.text)

带参数的GET请求->headers

#通常我们在发送请求时都需要带上请求头，请求头是将自身伪装成浏览器的关键，常见的有用的请求头如下
Host
Referer #大型网站通常都会根据该参数判断请求的来源
User-Agent #客户端
Cookie #Cookie信息虽然包含在请求头里，但requests模块有单独的参数来处理他，headers={}内就不要放它了


#添加headers(浏览器会识别请求头,不加可能会被拒绝访问,比如访问https://www.zhihu.com/explore)
import requests
response=requests.get('https://www.zhihu.com/explore')
response.status_code #500


#自己定制headers
headers={
    'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36',

}
respone=requests.get('https://www.zhihu.com/explore',
                     headers=headers)
print(respone.status_code) #200

带参数的GET请求->cookies

#登录github，然后从浏览器中获取cookies，以后就可以直接拿着cookie登录了，无需输入用户名密码
#用户名:egonlin 邮箱378533872@qq.com 密码lhf@123

import requests

Cookies={   'user_session':'wGMHFJKgDcmRIVvcA14_Wrt_3xaUyJNsBnPbYzEL6L0bHcfc',
}

response=requests.get('https://github.com/settings/emails',
             cookies=Cookies) #github对请求头没有什么限制，我们无需定制user-agent，对于其他网站可能还需要定制


print('378533872@qq.com' in response.text) #True

2、POST请求

介绍

#GET请求
HTTP默认的请求方法就是GET
     * 没有请求体
     * 数据必须在1K之内！
     * GET请求数据会暴露在浏览器的地址栏中

GET请求常用的操作：
       1. 在浏览器的地址栏中直接给出URL，那么就一定是GET请求
       2. 点击页面上的超链接也一定是GET请求
       3. 提交表单时，表单默认使用GET请求，但可以设置为POST


#POST请求
(1). 数据不会出现在地址栏中
(2). 数据的大小没有上限
(3). 有请求体
(4). 请求体中如果存在中文，会使用URL编码！


#！！！requests.post()用法与requests.get()完全一致，特殊的是requests.post()有一个data参数，用来存放请求体数据

使用

# 1、基本POST实例

import requests

payload = {'key1': 'value1', 'key2': 'value2'}
ret = requests.post("http://httpbin.org/post", data=payload)  # data发送字典时发送的是urlencoding形式的数据

print(ret.text)

# 2、发送请求头和数据实例

import requests
import json

url = 'https://api.github.com/some/endpoint'
payload = {'some': 'data'}
headers = {'content-type': 'application/json'}

ret = requests.post(url, data=json.dumps(payload), headers=headers)  # 此时data发送的json格式的数据

print(ret.text)
print(ret.cookies)  # 获取网站返回的cookie

发送post请求，模拟浏览器的登录行为

注意：
　1、对于登录来说，应该输错用户名或密码然后分析抓包流程，用脑子想一想，输对了浏览器就跳转了，
    还分析个毛线，累死你也找不到包

　　2、要做登录的时候一定记得要把cookie先清除； 
　　3、requests.session():中间的cookie都不用自己分析了，有用的没用的都给放进来了、
　　4、response.cookie.get_dict()    #获取cookie

自动登录github

''' 一 目标站点分析
浏览器输入https://github.com/login
然后输入错误的账号密码，抓包
发现登录行为是post提交到：https://github.com/session
而且请求头包含cookie
而且请求体包含：
commit:Sign in
utf8:✓
authenticity_token:lbI8IJCwGslZS8qJPnof5e7ZkCoSoMn6jmDTsL1r/m06NLyIbw7vCrpwrFAPzHMep3Tmf/TSJVoXWrvDZaVwxQ==
login:egonlin
password:123


二 流程分析
先GET：https://github.com/login拿到初始cookie与authenticity_token
返回POST：https://github.com/session， 带上初始cookie，带上请求体（authenticity_token，用户名，密码等）
最后拿到登录cookie

ps：如果密码时密文形式，则可以先输错账号，输对密码，然后到浏览器中拿到加密后的密码，github的密码是明文
'''

import requests
import re
#第一次请求
r1=requests.get('https://github.com/login')
r1_cookie=r1.cookies.get_dict() #拿到初始cookie(未被授权)
authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] #从页面中拿到CSRF TOKEN

#第二次请求：带着初始cookie和TOKEN发送POST请求给登录页面，带上账号密码
data={
'commit':'Sign in',
'utf8':'✓',
'authenticity_token':authenticity_token,
'login':'317828332@qq.com',
'password':'alex3714'
}
r2=requests.post('https://github.com/session',
data=data,
cookies=r1_cookie
)

login_cookie=r2.cookies.get_dict()

#第三次请求：以后的登录，拿着login_cookie就可以,比如访问一些个人配置
r3=requests.get('https://github.com/settings/emails',
cookies=login_cookie)

print('317828332@qq.com' in r3.text) #True

这里要注意先要使用get请求访问，获取一个未授权的cookie，发送post请求时要带着这个cookie，且这里用的form表单形式提交的，我们要到页面上找到token的内容并发送

import requests
import re

session = requests.session()
# 第一次请求
r1 = session.get('https://github.com/login')
authenticity_token = re.findall(r'name="authenticity_token".*?value="(.*?)"', r1.text)[0]  # 从页面中拿到CSRF TOKEN

# 第二次请求
data = {
    'commit': 'Sign in',
    'utf8': '✓',
    'authenticity_token': authenticity_token,
    'login': '317828332@qq.com',
    'password': 'alex3714'
}
r2 = session.post('https://github.com/session',
                  data=data,
                  )

# 第三次请求
r3 = session.get('https://github.com/settings/emails')

print('317828332@qq.com' in r3.text)  # True

requests.session()自动帮我们保存cookie信息

登录github小应用

import requests
import re
#第一次请求
# GET请求
# 请求头
# - 获取token和
# - User-agent
# - cookie
# 第二次请求
#POST请求
#请求头
# referer
# User-agent
#请求体
#获取data
# 第三次请求，登录成功之后
#- 请求之前自己先登录一下，看一下有没有referer
#- 请求新的url，进行其他操作
#- 查看用户名在不在里面
#第一次请求
response1 = requests.get(
"https://github.com/login",
headers = {
"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36",
},
)
authenticity_token = re.findall('name="authenticity_token".*?value="(.*?)"',response1.text,re.S)
r1_cookies = response1.cookies.get_dict()
# print(r1_cookies,"cookie") #获取到的cookie

#第二次请求
response2 = requests.post(
"https://github.com/session",
headers = {
"Referer": "https://github.com/",
"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36",
},
data={
"commit":"Sign in",
"utf8":"✓",
"authenticity_token":authenticity_token,
"login":"haiyanzzz",
"password":"xxxx",
zhy..azjash1234
},
cookies = r1_cookies
)
print(response2.status_code)
print(response2.history) #跳转的历史状态码

#第三次请求，登录成功之后，访问其他页面
r2_cookies = response2.cookies.get_dict() #拿上cookie，知道是你登录了，就开始访问页面
response3 = requests.get(
"https://github.com/settings/emails",
headers = {
"Referer": "https://github.com/",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36",
},
cookies = r2_cookies,
)
print(response3.text)
print("haiyanzzz" in response3.text) #True返回True说明就成功了

3、其他请求

requests.get(url, params=None, **kwargs)
requests.post(url, data=None, json=None, **kwargs)
requests.put(url, data=None, **kwargs)
requests.head(url, **kwargs)
requests.delete(url, **kwargs)
requests.patch(url, data=None, **kwargs)
requests.options(url, **kwargs)
  
# 以上方法均是在此方法的基础上构建
requests.request(method, url, **kwargs)

4、更多参数

def request(method, url, **kwargs):
"""Constructs and sends a :class:`Request <Request>`.

:param method: method for the new :class:`Request` object.
:param url: URL for the new :class:`Request` object.
:param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`.
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param json: (optional) json data to send in the body of the :class:`Request`.
:param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.
:param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
:param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload.
``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')``
or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string
defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers
to add for the file.
:param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
:param timeout: (optional) How long to wait for the server to send data
before giving up, as a float, or a :ref:`(connect timeout, read
timeout) <timeouts>` tuple.
:type timeout: float or tuple
:param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.
:type allow_redirects: bool
:param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
:param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``.
:param stream: (optional) if ``False``, the response content will be immediately downloaded.
:param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
:return: :class:`Response <Response>` object
:rtype: requests.Response

Usage::

>>> import requests
>>> req = requests.request('GET', 'http://httpbin.org/get')
<Response [200]>
"""

参数列表

def param_method_url():
    # requests.request(method='get', url='http://127.0.0.1:8000/test/')
    # requests.request(method='post', url='http://127.0.0.1:8000/test/')
    pass


def param_param():
    # - 可以是字典
    # - 可以是字符串
    # - 可以是字节（ascii编码以内）

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params={'k1': 'v1', 'k2': '水电费'})

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params="k1=v1&k2=水电费&k3=v3&k3=vv3")

    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8'))

    # 错误
    # requests.request(method='get',
    # url='http://127.0.0.1:8000/test/',
    # params=bytes("k1=v1&k2=水电费&k3=v3&k3=vv3", encoding='utf8'))
    pass


def param_data():
    # 可以是字典
    # 可以是字符串
    # 可以是字节
    # 可以是文件对象

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data={'k1': 'v1', 'k2': '水电费'})

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data="k1=v1; k2=v2; k3=v3; k3=v4"
    # )

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data="k1=v1;k2=v2;k3=v3;k3=v4",
    # headers={'Content-Type': 'application/x-www-form-urlencoded'}
    # )

    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # data=open('data_file.py', mode='r', encoding='utf-8'), # 文件内容是：k1=v1;k2=v2;k3=v3;k3=v4
    # headers={'Content-Type': 'application/x-www-form-urlencoded'}
    # )
    pass


def param_json():
    # 将json中对应的数据进行序列化成一个字符串，json.dumps(...)
    # 然后发送到服务器端的body中，并且Content-Type是 {'Content-Type': 'application/json'}
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     json={'k1': 'v1', 'k2': '水电费'})


def param_headers():
    # 发送请求头到服务器端
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     json={'k1': 'v1', 'k2': '水电费'},
                     headers={'Content-Type': 'application/x-www-form-urlencoded'}
                     )


def param_cookies():
    # 发送Cookie到服务器端
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     data={'k1': 'v1', 'k2': 'v2'},
                     cookies={'cook1': 'value1'},
                     )
    # 也可以使用CookieJar（字典形式就是在此基础上封装）
    from http.cookiejar import CookieJar
    from http.cookiejar import Cookie

    obj = CookieJar()
    obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None,
                          discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False,
                          port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False)
                   )
    requests.request(method='POST',
                     url='http://127.0.0.1:8000/test/',
                     data={'k1': 'v1', 'k2': 'v2'},
                     cookies=obj)


def param_files():
    # 发送文件
    # file_dict = {
    # 'f1': open('readme', 'rb')
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 发送文件，定制文件名
    # file_dict = {
    # 'f1': ('test.txt', open('readme', 'rb'))
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 发送文件，定制文件名
    # file_dict = {
    # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf")
    # }
    # requests.request(method='POST',
    # url='http://127.0.0.1:8000/test/',
    # files=file_dict)

    # 发送文件，定制文件名
    # file_dict = {
    #     'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'})
    # }
    # requests.request(method='POST',
    #                  url='http://127.0.0.1:8000/test/',
    #                  files=file_dict)

    pass


def param_auth():
    from requests.auth import HTTPBasicAuth, HTTPDigestAuth

    ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf'))
    print(ret.text)

    # ret = requests.get('http://192.168.1.1',
    # auth=HTTPBasicAuth('admin', 'admin'))
    # ret.encoding = 'gbk'
    # print(ret.text)

    # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass'))
    # print(ret)
    #


def param_timeout():
    # ret = requests.get('http://google.com/', timeout=1)
    # print(ret)

    # ret = requests.get('http://google.com/', timeout=(5, 1))
    # print(ret)
    pass


def param_allow_redirects():
    ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False)
    print(ret.text)


def param_proxies():
    # proxies = {
    # "http": "61.172.249.96:80",
    # "https": "http://61.185.219.126:3128",
    # }

    # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'}

    # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies)
    # print(ret.headers)


    # from requests.auth import HTTPProxyAuth
    #
    # proxyDict = {
    # 'http': '77.75.105.165',
    # 'https': '77.75.105.165'
    # }
    # auth = HTTPProxyAuth('username', 'mypassword')
    #
    # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth)
    # print(r.text)

    pass


def param_stream():
    ret = requests.get('http://127.0.0.1:8000/test/', stream=True)
    print(ret.content)
    ret.close()

    # from contextlib import closing
    # with closing(requests.get('http://httpbin.org/get', stream=True)) as r:
    # # 在此处理响应。
    # for i in r.iter_content():
    # print(i)


def requests_session():
    import requests

    session = requests.Session()

    ### 1、首先登陆任何页面，获取cookie

    i1 = session.get(url="http://dig.chouti.com/help/service")

    ### 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权
    i2 = session.post(
        url="http://dig.chouti.com/login",
        data={
            'phone': "8615131255089",
            'password': "xxxxxx",
            'oneMonth': ""
        }
    )

    i3 = session.post(
        url="http://dig.chouti.com/link/vote?linksId=8589623",
    )
    print(i3.text)

参数示例

总结

requests 
    method: 请求方式
    url: 请求的url
    params: url中的参数？k1=v1&k2=v2
    data: 请求体的内容
    json: json格式的请求体的内容
    headers: 请求头
    cookies: 请求的cookie
    proxies: 封IP，用代理 
    
    
    
    files: 上传文件
    auth: 基本认证
    timeout: 超时时间
    allow_redirects: True 
    stream: 下载大文件时
        ret = requests.get('http://127.0.0.1:8000/test/', stream=True)
        for i in r.iter_content():
            # print(i)
        from contextlib import closing
        with closing(requests.get('http://httpbin.org/get', stream=True)) as r:
            # 在此处理响应。
            for i in r.iter_content():
                print(i)
                            
    cert: 证书
    verify: 确认