Requests库的使用

Requests库的使用

1 请求方式

import requests
requests.post('http://httpbin.org/post')
requests.put('http://httpbin.org/put')
requests.delete('http://httpbin.org/delete')
requests.head('http://httpbin.org/get')
requests.options('http://httpbin.org/get')

2 Get请求

2.1 基本方式

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

---

response = requests.get("http://httpbin.org/get?name=germey&age=22")

---

data = {
'name': 'germey',
'age': 22
}
response = requests.get("http://httpbin.org/get", params=data)

2.2 添加Headers

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.get("https://www.zhihu.com/explore", headers=headers)

3 Post请求

import requests

data = {'name': 'germey', 'age': '22'}
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.post("http://httpbin.org/post", data=data, headers=headers)

4 响应的属性

print(response.status_code)
print(response.headers)
print(response.cookies)
print(response.url)
print(response.history)
print(response.text)        #str类型
print(response.content)     #byte类型

response.json()         #相当于json.loads(response.text)  ，转换为字典形式

5 状态码

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',),


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

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',),


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'),

6 文件下载和上传

6.1 下载

import requests

response = requests.get("https://github.com/favicon.ico")
with open('favicon.ico', 'wb') as f:
    f.write(response.content)
    f.close()

6.2 上传

import requests

files = {'file': open('favicon.ico', 'rb')}
response = requests.post("http://httpbin.org/post", files=files)
print(response.text)

7 Cookie

7.1 获取Cookie

import requests

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

7.2 会话维持（模拟登陆）

import requests

s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

8 证书

8.1 不进行证书认证

import requests
from requests.packages import urllib3

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

8.2 用本地证书来验证

import requests

response = requests.get('https://www.12306.cn', cert=('/path/server.crt', '/path/key'))
print(response.status_code)

9 代理

9.1 一般代理

import requests

proxies = {
  "http": "http://127.0.0.1:9743",
  "https": "https://127.0.0.1:9743",
}

response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

9.2 有用户名和密码的代理

import requests

proxies = {
    "http": "http://user:password@127.0.0.1:9743/",
}
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

9.3 socks代理

pip install ‘requests[socks]’

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)

10 超时设置

import requests
from requests.exceptions import ReadTimeout

try:
    response = requests.get("http://httpbin.org/get", timeout = 0.5)  #单位秒
    print(response.status_code)
except ReadTimeout:
    print('Timeout')

11 登陆认证（先登录才能访问）

import requests
from requests.auth import HTTPBasicAuth

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

12 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:
    print('Timeout')
except ConnectionError:
    print('Connection error')
except RequestException:
    print('Error')