python3简单使用requests 用户代理，cookie池

　　官方文档：http://docs.python-requests.org/en/master/

　　参考文档：http://www.cnblogs.com/zhaof/p/6915127.html#undefined

　　我这里使用的是当前最新的python3.6。

　　安装

　　　　pip3 install requests

　　使用requests模块完成各种操作

　　1、get请求

import requests

url='https://www.baidu.com'

r = requests.get(url)

print(r.status_code)

　　2、post请求

　　　　url = 'https://www.baidu.com'

        data1 = {

            "name": "zhaofan",

            "age": 23

        }

        r = requests.post(url, data=data1, verify=True)

        print(r.status_code)

　　3、使用代理

import requests

url='http://docs.python-requests.org/en/master/'

proxies={

    'http':'127.0.0.1:8080',

    'https':'127.0.0.1:8080'

}

r = requests.get(url,proxies=proxies)

print(r.status_code)

　　如果代理需要设置账户名和密码,只需要将字典更改为如下：
　　proxies = {
　　　　　　"http":"http://user:password@127.0.0.1:9999"
　　　　}
　　如果你的代理是通过sokces这种方式则需要pip install "requests[socks]"
　　proxies= {
　　　　"http":"socks5://127.0.0.1:9999",
　　　　"https":"sockes5://127.0.0.1:8888"
　　}

　　4、自定义header和cookie,获取cookie

 url = 'https://weixin.sogou.com/weixin?type=1&s_from=input&query=python&ie=utf8&_sug_=n&_sug_type_='

        headers = {

            'User-Agent': 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36',

            'Cookie': 'name=JSESSIONID;value=aaaUrhXY8CzPBgs1eXUFw;domain=weixin.sogou.com'

        }

        r = requests.get(url, headers=headers)

        # 获取cookie

        print(r.cookies)

        print(r.status_code)

        # print(r.text)

　　cookie的一个作用就是可以用于模拟登陆，做会话维持

s = requests.Session()

s.get("http://httpbin.org/cookies/set/number/123456")

response = s.get("http://httpbin.org/cookies")

print(response.text)

　　　5、用户代理池，cookie 池测试代码

import sys

import requests

import os

import random

sys.path.append(os.path.abspath('{bastpath}{sep}..'.format(bastpath=sys.path[0],sep=os.path.sep)))

class test:

    def __init__(self,logPath):

        self.mycookies = [

                {'name': 'amet non sint', 'value': 'nulla occaecat dolore', 'domain': 'Excepteur labore est proident',

                 'path': 'dolor laborum consectetur', 'sameSite': 'amet ea Lorem', 'storeId': 'ex nulla nostrud'},

                {'name': 'velit consectetur in', 'value': None, 'domain': 'sit',

                 'path': 'nostrud', 'sameSite': 'et laborum',

                 'storeId': 'labore commodo elit reprehenderit occaecat'}]

        self.user_agent_list = ['Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36',

            'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36',

            'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36',

            'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36',

            'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',

            'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36',

            'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0) Gecko/20100101 Firefox/17.0.6',

            'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1468.0 Safari/537.36',

            'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36',

            'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36'

        ]

    # 首先根据关键字获取对应微信公众号的url

    def test(self,url):

        try:

            cookie1 = random.choice(self.mycookies)

            print(cookie1)

            UserAgent = random.choice(self.user_agent_list)

            header = {'User-Agent': UserAgent}

            print(header)

            txt = requests.get(url, cookies=cookie1,headers=header).text

            print(txt)

        except Exception as ex:

            print(ex)

　 6、证书验证

　　现在的很多网站都是https的方式访问，所以这个时候就涉及到证书的问题

　　为了避免这种情况的发生可以通过verify=False，但是这样是可以访问到页面，但是会提示：

InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs

　　解决方法为：

import requests

from requests.packages import urllib3

urllib3.disable_warnings()

response = requests.get("https://www.12306.cn",verify=False)

print(response.status_code)

　　7、认证设置

　　如果碰到需要认证的网站可以通过requests.auth模块实现

import requests

from requests.auth import HTTPBasicAuth

response = requests.get("http://120.27.34.24:9001/",auth=HTTPBasicAuth("user",""))

print(response.status_code)

　　当然这里还有一种方式

import requests

response = requests.get("http://120.27.34.24:9001/",auth=("user",""))

print(response.status_code)

　　8、异常处理

　　关于reqeusts的异常在这里可以看到详细内容：http://www.python-requests.org/en/master/api/#exceptions

　　所有的异常都是在requests.excepitons中

　　　　从源码我们可以看出RequestException继承IOError,
　　　　HTTPError，ConnectionError,Timeout继承RequestionException
　　　　ProxyError，SSLError继承ConnectionError
　　　　ReadTimeout继承Timeout异常
　　　　这里列举了一些常用的异常继承关系，详细的可以看：http://cn.python-requests.org/zh_CN/latest/_modules/requests/exceptions.html#RequestException

　　　　简单测试

import requests

from requests.exceptions import ReadTimeout,ConnectionError,RequestException

try:

    response = requests.get("http://httpbin.org/get",timout=0.1)

    print(response.status_code)

except ReadTimeout:

    print("timeout")

except ConnectionError:

    print("connection Error")

except RequestException:

    print("error")

　　　　其实最后测试可以发现，首先被捕捉的异常是timeout,当把网络断掉的haul就会捕捉到ConnectionError，如果前面异常都没有捕捉到，最后也可以通过RequestExctption捕捉到

　　9、状态码

状态码判断

Requests还附带了一个内置的状态码查询对象

主要有如下内容：

100: ('continue',),

101: ('switching_protocols',),

102: ('processing',),

103: ('checkpoint',),

122: ('uri_too_long', 'request_uri_too_long'),

200: ('ok', 'okay', 'all_ok', 'all_okay', 'all_good', '\o/', '✓'),

201: ('created',),

202: ('accepted',),

203: ('non_authoritative_info', 'non_authoritative_information'),

204: ('no_content',),

205: ('reset_content', 'reset'),

206: ('partial_content', 'partial'),

207: ('multi_status', 'multiple_status', 'multi_stati', 'multiple_stati'),

208: ('already_reported',),

226: ('im_used',),

Redirection.

300: ('multiple_choices',),

301: ('moved_permanently', 'moved', '\o-'),

302: ('found',),

303: ('see_other', 'other'),

304: ('not_modified',),

305: ('use_proxy',),

306: ('switch_proxy',),

307: ('temporary_redirect', 'temporary_moved', 'temporary'),

308: ('permanent_redirect',

'resume_incomplete', 'resume',), # These 2 to be removed in 3.0

Client Error.

400: ('bad_request', 'bad'),

401: ('unauthorized',),

402: ('payment_required', 'payment'),

403: ('forbidden',),

404: ('not_found', '-o-'),

405: ('method_not_allowed', 'not_allowed'),

406: ('not_acceptable',),

407: ('proxy_authentication_required', 'proxy_auth', 'proxy_authentication'),

408: ('request_timeout', 'timeout'),

409: ('conflict',),

410: ('gone',),

411: ('length_required',),

412: ('precondition_failed', 'precondition'),

413: ('request_entity_too_large',),

414: ('request_uri_too_large',),

415: ('unsupported_media_type', 'unsupported_media', 'media_type'),

416: ('requested_range_not_satisfiable', 'requested_range', 'range_not_satisfiable'),

417: ('expectation_failed',),

418: ('im_a_teapot', 'teapot', 'i_am_a_teapot'),

421: ('misdirected_request',),

422: ('unprocessable_entity', 'unprocessable'),

423: ('locked',),

424: ('failed_dependency', 'dependency'),

425: ('unordered_collection', 'unordered'),

426: ('upgrade_required', 'upgrade'),

428: ('precondition_required', 'precondition'),

429: ('too_many_requests', 'too_many'),

431: ('header_fields_too_large', 'fields_too_large'),

444: ('no_response', 'none'),

449: ('retry_with', 'retry'),

450: ('blocked_by_windows_parental_controls', 'parental_controls'),

451: ('unavailable_for_legal_reasons', 'legal_reasons'),

499: ('client_closed_request',),

Server Error.

500: ('internal_server_error', 'server_error', '/o\', '✗'),

501: ('not_implemented',),

502: ('bad_gateway',),

503: ('service_unavailable', 'unavailable'),

504: ('gateway_timeout',),

505: ('http_version_not_supported', 'http_version'),

506: ('variant_also_negotiates',),

507: ('insufficient_storage',),

509: ('bandwidth_limit_exceeded', 'bandwidth'),

510: ('not_extended',),

511: ('network_authentication_required', 'network_auth', 'network_authentication'),

通过下面例子测试：（不过通常还是通过状态码判断更方便）

import requests

response= requests.get("http://www.baidu.com")

if response.status_code == requests.codes.ok:

    print("访问成功")

　　10、文件上传

　　实现方法和其他参数类似，也是构造一个字典然后通过files参数传递

import requests

files= {"files":open("git.jpeg","rb")}

response = requests.post("http://httpbin.org/post",files=files)

print(response.text)