python爬虫類入門requestsモジュール

22064 ワード

Requests
Python標準ライブラリでは、urllib、urllib 2、httplibなどのモジュールがHttp要求のために提供されていますが、APIはあまりにも不完全です.別の時代、もう一つのインターネットのために作られました.それは膨大な量の仕事を必要としています.さらに様々な方法でカバーして、最も簡単な任務を達成します.
RequestsはApache 2 Licensedライセンスを使用してPythonに基づいて開発されたHTTPライブラリであり、Python内蔵モジュールをベースに高度なパッケージを行い、Pythonerがネットワーク要求を行う時には、多くの美しくなり、Requestsを使用して簡単にブラウザーに操作できるようになりました.
概要
インストール:
    pip install requests
requestsの一般的な属性:
    response = requests.get(url)
    response.text
    response.content
    response.encoding
    response.apparent_encoding
    response.status_code
            301      
            302      
    response.cookies.get_dict()
1、GET要求
1、パラメータなしの例
    import requests

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

    print ret.url
    print ret.text
2、パラメータの例があります
    import requests

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

    print ret.url
    print ret.text
2、POSTリクエスト
1、基本POST例
    import requests

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

    print ret.text
2、送信要求ヘッダとデータの例
    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、その他の要求
    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)

    #                 
    requests.request(method, url, **kwargs)
4、より多くのパラメータ
    def request(method, url, **kwargs):
        """Constructs and sends a :class:`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) ` 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 ` object
        :rtype: requests.Response

        Usage::

          >>> import requests
          >>> req = requests.request('GET', 'http://httpbin.org/get')
          
        """


    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/')


    def param_param():
        # -      
        # -       
        # -      (ascii    )

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

        requests.request(method='get',
        url='http://127.0.0.1:8000/test/',
        params="k1=v1&k2=   &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'))

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


    def param_data():
        #      
        #       
        #      
        #        

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

        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'),
        #      :k1=v1;k2=v2;k3=v3;k3=v4
        headers={'Content-Type': 'application/x-www-form-urlencoded'})


    def param_json():
        #  json                 ,json.dumps(...)
        #           body ,  Content-Type 
        # {'Content-Type': 'application/json'}
        requests.request(method='POST',
                 url='http://127.0.0.1:8000/test/',
                 json={'k1': 'v1', 'k2': '   '})


    def param_headers():
        #           
        requests.request(method='POST',
                 url='http://127.0.0.1:8000/test/',
                 json={'k1': 'v1', 'k2': '   '},
                 headers={'Content-Type': 'application/x-www-form-urlencoded'}
                 )


    def param_cookies():
        #   Cookie     
        requests.request(method='POST',
             url='http://127.0.0.1:8000/test/',
             data={'k1': 'v1', 'k2': 'v2'},
             cookies={'cook1': 'value1'},
             )

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

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

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

        #     ,     
        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)


    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)



    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)




    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:
            #       。
            for i in r.iter_content():
                print(i)


    def requests_session():
        import requests

        session = requests.Session()

        # 1、        ,  cookie

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

        # 2、    ,      cookie,   cookie   gpsd     
        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)
参考:
武沛斉:http://www.cnblogs.com/wupeiqi/articles/6283017.html
公式文書:http://cn.python-requests.org/zh_CN/latest/