爬虫必备—requests

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。

1. GET请求

 # 1、无参数实例

 import requests

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

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

 # 2、有参数实例

 import requests

 payload = {'key1': 'value1', 'key2': 'value2'}
 ret = requests.get("http://httpbin.org/get", params=payload)

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

2. POST请求

 # 1、基本POST实例

 import requests

 payload = {'key1': 'value1', 'key2': 'value2'}
 ret = requests.post("http://httpbin.org/post", data=payload)

 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)

 print(ret.text)
 print(ret.cookies)

3. 其它请求

 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. 请求参数

 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

5. 参数示例

 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': "",
             'password': "xxxxxx",
             'oneMonth': ""
         }
     )

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

参数示例

6. requests模拟登陆GitHub

 import requests
 from bs4 import BeautifulSoup

 def login_github():
     """
     通过requests模块模拟浏览器登陆GitHub
     :return:
     """
     # 获取csrf_token
     r1 = requests.get('https://github.com/login')   # 获得get请求的对象
     s1 = BeautifulSoup(r1.text, 'html.parser')      # 使用bs4解析HTML对象
     token = s1.find('input', attrs={'name': 'authenticity_token'}).get('value')     # 获取登陆授权码，即csrf_token
     get_cookies = r1.cookies.get_dict()     # 获取get请求的cookies，post请求时必须携带

     # 发送post登陆请求
     '''
     post登陆参数
     commit    Sign+in
     utf8    ✓
     authenticity_token    E961jQMIyC9NPwL54YPj70gv2hbXWJ…fTUd+e4lT5RAizKbfzQo4eRHsfg==
     login    JackUpDown（用户名）
     password    **********（密码）
     '''
     r2 = requests.post(
         'https://github.com/session',
         data={
             'commit': 'Sign+in',
             'utf8': '✓',
             'authenticity_token': token,
             'login': 'JackUpDown',
             'password': '**********'
         },
         cookies=get_cookies     # 携带get请求的cookies
                        )
     login_cookies = r2.cookies.get_dict()   # 获得登陆成功的cookies，携带此cookies就可以访问任意GitHub页面

     # 携带post cookies跳转任意页面
     r3 = requests.get('https://github.com/settings/emails', cookies=login_cookies)
     print(r3.text)

转载自：

1. http://www.cnblogs.com/wupeiqi/articles/6283017.html