1. 程式人生 > 實用技巧 >轉 requests庫 學習筆記

轉 requests庫 學習筆記

1、概覽

1.1、例項引入

# 引入Requests庫
import requests

# 發起GET請求
response = requests.get('https://www.baidu.com/')
# 檢視響應型別  requests.models.Response
print(type(response))
# 輸出狀態碼
print(response.status_code)
# 輸出響應內容型別  text
print(type(response.text))
# 輸出響應內容
print(response.text)
# 輸出cookies
print(response.cookies)



1.2、各種請求方式

import requests

# 發起POST請求
requests.post('http://httpbin.org/post')
# 發起PUT請求
requests.put('http://httpbin.org/put')
# 發起DELETE請求
requests.delete('http://httpbin.org/delete')
# 傳送HEAD請求
requests.head('http://httpbin.org/get')
# 傳送OPTION請求
requests.options('http://httpbin.org/get')


2、請求

2.1 、基本GET請求

2.1.1、基本寫法

import requests

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

2.1.2、帶引數的GET請求

import requests

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

2.1.3、帶引數的GET請求(2)

import requests

# 分裝GET請求引數
param = {'name':'jyx','age':19}
# 設定GET請求引數(Params)
response = requests.get('http://httpbin.org/get',params=param)
print(response.text)

2.1.4、解析json

import requests

response = requests.get('http://httpbin.org/get')
# 獲取響應內容
print(type(response.text))
# 如果響應內容是json,就將其轉為json
print(response.json())
# 輸出的是字典型別
print(type(response.json()))

2.1.5、獲取二進位制資料

import requests

response = requests.get('http://github.com/favicon.ico')

# str,bytes
print(type(response.text),type(response.content))
# 輸出響應的文字內容
print(response.text)
# 輸出響應的二進位制內容
print(response.content)
# 下載二進位制資料到本地
with open('favicon.ico','wb') as f:
  f.write(response.content)
  f.close()

2.1.6、新增headers

import requests

# 設定User-Agent瀏覽器資訊
headers = {
      "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36"
}
# 設定請求頭資訊
response = requests.get('https://www.zhihu.com/explore',headers=headers)
print(response.text)

2.2、基本POST請求

import requests

# 設定傳入post表單資訊
data= { 'name':'jyx', 'age':18}
# 設定請求頭資訊
headers = {
      "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36"
}
# 設定請求頭資訊和POST請求引數(data)
response = requests.post('http://httpbin.org/post', data=data, headers=headers)
print(response.text)

3、響應

3.1 response屬性

import requests

response = requests.get('http://www.jianshu.com/')
# 獲取響應狀態碼
print(type(response.status_code),response.status_code)
# 獲取響應頭資訊
 print(type(response.headers),response.headers)
# 獲取響應頭中的cookies
print(type(response.cookies),response.cookies)
# 獲取訪問的url
 print(type(response.url),response.url)
# 獲取訪問的歷史記錄
 print(type(response.history),response.history)

3.2、 狀態碼判斷

import requests

response = requests.get('http://www.jianshu.com/404.html')
# 使用request內建的字母判斷狀態碼
if not response.status_code == requests.codes.ok:
    print('404-1')
response = requests.get('http://www.jianshu.com')
# 使用狀態碼數字判斷
if not response.status_code == 200:
    print('404-2')

3.3 requests內建的狀態字元

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'),

4、高階操作

4.1、檔案上傳

import requests

files = {'file':open('favicon.ico','rb')}
# 往POST請求頭中設定檔案(files)
response = requests.post('http://httpbin.org/post',files=files)
print(response.text)

4.2、獲取cookies

import requests

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

4.3、會話維持

4.3.1、普通請求

import requests

requests.get('http://httpbin.org/cookies/set/number/12456')
response = requests.get('http://httpbin.org/cookies')
# 本質上是兩次不同的請求,session不一致
print(response.text)

4.3.2、會話維持請求

import requests

# 從Requests中獲取session
session = requests.session()
# 使用seesion去請求保證了請求是同一個session
session.get('http://httpbin.org/cookies/set/number/12456')
response = session.get('http://httpbin.org/cookies')
print(response.text)

4.4、證書驗證

4.4.1、無證書訪問

import requests

response = requests.get('https://www.12306.cn')
# 在請求https時,request會進行證書的驗證,如果驗證失敗則會丟擲異常
print(response.status_code)  

4.4.2、關閉證書驗證

import requests

# 關閉驗證,但是仍然會報出證書警告
response = requests.get('https://www.12306.cn',verify=False)
print(response.status_code)

4.4.3、消除關閉證書驗證的警告

from requests.packages import urllib3
import requests

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

4.4.4、手動設定證書

import requests

# 設定本地證書
response = requests.get('https://www.12306.cn', cert=('/path/server.crt', '/path/key'))
print(response.status_code)  

4.5、代理設定

4.5.1、設定普通代理

import requests

proxies = {
    "http": "http://127.0.0.1:9743",
    "https": "https://127.0.0.1:9743",
}
# 往請求中設定代理(proxies
)
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

4.5.2、設定帶有使用者名稱和密碼的代理

import requests

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

4.5.3、設定socks代理

pip3 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)

4.6、超時設定

import requests
from requests.exceptions import ReadTimeout

    

try:
   # 設定必須在500ms內收到響應,不然或丟擲ReadTimeout異常
   response = requests.get("http://httpbin.org/get", timeout=0.5)
            print(response.status_code)
except ReadTimeout:
   print('Timeout')

4.7、認證設定

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)

4.8、異常處理

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:
   # 超時異常
   print('Timeout')
except ConnectionError:
   # 連線異常
   print('Connection error')
except RequestException:
   # 請求異常
   print('Error')