10.requests使用总结

1 实际案例

• 1.1 访问百度网站

# 引入Requests库
import requests
# 发起GET请求
r = requests.get('https://www.baidu.com/')
# 查看响应类型  requests.models.Response
print(type(r))
# 输出状态码  200
print(r.status_code)
# 输出响应内容类型  str
print(type(r.text))
# 输出响应内容
print(r.text)
# 输出cookies
print(r.cookies)

• 1.2 各种请求方式

import requests
# 发起POST请求
requests.post('http://httpbin.org/post')
# 发起PUT请求
requests.put('http://httpbin.org/put')
# 发起DELETE请求
requests.delete('http://httpbin.org/delete')
# 发送HEAD请求
requests.head('http://httpbin.org/get')
# 发送OPTION请求
requests.options('http://httpbin.org/get')

2 GET请求

• 2.1 无参数的GET请求

import requests
response = requests.get('http://httpbin.org/get')
print(response.text)

• 2.2 带参数的GET请求
• 2.2.1 访问url携带参数

import requests
response = requests.get('http://httpbin.org/get?name=jyx&age=18')
print(response.text)

• 2.2.2 请求体包含参数

import requests
# GET请求参数
param = {'name': 'ide', 'city': 'New York'}
# 传递参数params
response = requests.get('http://httpbin.org/get',params=param)
print(response.text)

3 POST请求

• 3.1 发送表单形式的数据

import requests
# POST请求参数
param = {'name': 'ide', 'city': 'New York'}
# 传递参数params
response = requests.post('http://httpbin.org/post',data=param)
print(response.text)

• 3.2 发送Json数据

import json
import requests
# POST请求参数
param = {'name': 'ide', 'city': 'New York'}
# 传递参数params，并格式化为json数据
response = requests.post('http://httpbin.org/post', data=json.dumps(param))
print(response.text)

• 3.3 发送文件数据

如果需要向网站发送图片、文档等，需要使用files参数

import requests
# POST请求参数
file ={'file': open('default.png', 'rb')}
# 传递参数files
response = requests.post('http://httpbin.org/post', files=file)
print(response.text)

4 获取二进制数据

import requests

response = requests.get('http://l.bst.126.net/rsc/img/loginopen/201406/appstore/quanzi.jpg?v=001')
# 输出响应的二进制内容
print(response.content)
# 下载二进制数据到本地
with open('quanzi.jpg', 'wb') as f:
    f.write(response.content)
    f.close()

5 设置headers

import requests

# 设置User-Agent浏览器信息
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36",
    # 'content-type': 'application/json'
}
# 设置请求头信息
response = requests.get('https://www.zhihu.com/question/37787004',headers=headers)
print(response.text)

6 编码类型

可以找出requests使用了什么编码，并能够进行改变

r.encoding
r.encoding = 'ISO-8859-1'

如果改变了编码，每当访问r.text时，Request都将会使用r.encoding的新值。

7 响应属性

import requests

response = requests.get('http://www.jianshu.com/')
# 获取响应状态码
print(type(response.status_code),response.status_code)
# 获取响应头信息
print(type(response.headers),response.headers)
# 获取响应头中的cookies
print(type(response.cookies),response.cookies)
# 获取访问的url
print(type(response.url),response.url)
# 获取访问的历史记录
print(type(response.history),response.history)

8 requests内置的状态字符

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', '\\'),
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', '-'),
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'),

9 获取/发送cookies

import requests

response = requests.get('https://www.baidu.com')
print(response.cookies)
for key, value in response.cookies.items():
    print(key, '=====', value)
print(response.cookies['BAIDUID'])

发送自已定义请求的COOKIES

url = 'http://httpbin.org/cookies'
cookies = {'mycookies':'working'}
response = requests.get(url, cookies = cookies)
print(response.text)

10 session会话保存

import requests

# 从requests中获取session
session = requests.session()
# 使用seesion去请求保证了请求是同一个session
session.get('http://httpbin.org/cookies/set/number/12456')
response = session.get('http://httpbin.org/cookies')
print(response.text)

11 https安全访问

• 11.1 无证书访问

import requests

response = requests.get('https://www.12306.cn')
# 在请求https时，request会进行证书的验证，如果验证失败则会抛出异常
print(response.status_code)  

• 11.2 关闭证书验证

import requests

# 关闭验证，但是仍然会报出证书警告
response = requests.get('https://www.12306.cn',verify=False)
print(response.status_code)

• 11.3 消除关闭证书验证的警告

from requests.packages import urllib3  # 可能会报错，不用担心，继续运行即可
import requests

# 关闭警告
urllib3.disable_warnings()
response = requests.get('https://www.12306.cn',verify=False)
print(response.status_code)

• 11.4 手动设置证书

import requests

# 设置本地证书
response = requests.get('https://www.12306.cn', cert=('/path/server.crt', '/path/key'))
print(response.status_code)

12 设置代理

• 12.1 普通代理

import requests

proxies = {
    "http": "http://127.0.0.1:9743",
    "https": "https://127.0.0.1:9743",
}
# 往请求中设置代理(proxies
)
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

• 12.2 需要认证的代理

import requests

proxies = {
    "http": "http://user:[email protected]:9743/",
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

• 12.3 设置socks代理

import requests

proxies = {
    'http': 'socks5://127.0.0.1:9742',
    'https': 'socks5://127.0.0.1:9742'
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

13 超时设置

import requests
from requests.exceptions import ReadTimeout

try:
   # 设置必须在500ms内收到响应，不然或抛出ReadTimeout异常
   response = requests.get("http://httpbin.org/get", timeout=0.5)
   print(response.status_code)
except ReadTimeout:
   print('Timeout')

14 json解析

requests中内置了一个JSON解码器，帮助你处理JSON数据

import requests

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

如果JSON解码失败，response .json就会抛出一个异常

15 网站认证

import requests
from requests.auth import HTTPBasicAuth

response = requests.get('http://120.27.34.24:9001', auth=HTTPBasicAuth('user', '123'))
print(response.status_code)

16 异常处理

import requests
from requests.exceptions import ReadTimeout, ConnectionError, RequestException

try:
    response = requests.get("http://httpbin.org/get", timeout=0.5)
    print(response.status_code)
except ReadTimeout:
    # 超时异常
    print('Timeout')
except ConnectionError:
    # 连接异常
    print('Connection error')
except RequestException:
    # 请求异常
    print('Error')

部分异常
异常  说明
ConnectionError 遇到网络问题（如：DNS查询失败、拒绝连接等）
HTTPError   遇到罕见的无效HTTP响应时
Timeout 请求超时
TooManyRedirects    请求超过了设定的最大重定向次数
requests.exceptions.RequestException    所有Requests显式抛出的异常的基类

17 原始响应内容

如果你想获取来自服务器的原始套接字响应，那么你可以访问r.raw，前提是需要在初始请求中设置stream=True

import requests

response = requests.get('https://github.com/timeline.json', stream=True)
print(response.raw)
print(response.raw.read(10))