requests模塊

請求

請求方式

import requests
request = requests.get("http://httpbin.org/get")
print(request.text)

import requests
#date 以字典形式
data =https://www.cnblogs.com/jifou/p/ {
    'name':'germy',
    'age':22
}
response = requests.get("http://httpbin.org/get",params = data)
print(response.text)

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
}
response = requests.get('http://www.zhihu.com/explore',headers = headers)
print(response.text)

import requests
import json

response = requests.get("http://httpbin.org/get")
print(type(response.text))
print(response.json())
print(json.loads(response.text))
print(type(json.loads(response.text)))
print(type(response.json()))

response = requests.get("http://github.com/favicon.ico")
print(type(response.text),type(response.content))
print(response.text)
print(response.content)

import requests

#注意檔案路徑要轉義字符
#二進制資料要以b的方式寫入寫出
response = requests.get("http://github.com/favicon.ico")
with open(r'C:\Users\key\Desktop\py\favicon.ico','wb') as f:
    f.write(response.content)
    f.close()

import requests

data = {
    'name':'gemey',
    'age':'22'
}
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
}
response = requests.post("http://httpbin.org/post", data = https://www.cnblogs.com/jifou/p/data, headers = headers)
print(response.json())

import requests

response = requests.get('http://www.jianshu.com')
print(type(response.status_code), response.status_code)
print(type(response.headers), response.headers)
print(type(response.cookies), response.cookies)
print(type(response.url), response.url)
print(type(response.history), response.history)

import requests
 
response = requests.get('http://www.baidu.com')
print(response.status_code)
exit()if not response.status_code == 200  else print('Request successfully')

常見狀態碼：

• 100~199：表示服務器成功接收部分請求，要求客戶端繼續提交其余請求才能完成整個處理程序，

• 200~299：表示服務器成功接收請求并已完成整個處理程序，常用200（OK 請求成功），

• 300~399：為完成請求，客戶需進一步細化請求，例如：請求的資源已經移動一個新地址、常用302（所請求的頁面已經臨時轉移至新的url）、307和304（使用快取資源），
• 400~499：客戶端的請求有錯誤，常用404（服務器無法找到被請求的頁面）、403（服務器拒絕訪問，權限不夠），
• 500~599：服務器端出現錯誤，常用500（請求未完成，服務器遇到不可預知的情況），

編碼

import requests

response = requests.get('http://xxxxxxxxx.com')
#查看編碼方式
print(response.encoding)
#改變編碼方式
response.encoding = 'ISO-8859-1'
#處理網頁源代碼亂碼
response.encoding =  response.apparent_encoding

import requests

#上傳檔案要以二進制模式打開檔案
files ={'files':open(r'C:\Users\key\Desktop\py\favicon.ico', 'rb')}
response = requests.post('http://httpbin.org/post',files = files )
print(response.text)

import requests

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

import requests

s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456.')
response = s.get('http://httpbin.org/cookies')
print(response.text)

import requests
from requests.packages import urllib3

urllib3.disable_warnings()    #消除警告資訊
response = requests.get('http://www.12306.cn', verify = False)
print(response.status_code)

import requests

response = requests.get('http://www.12306.cn', cert = (r'/xx/crt', r'/xx/xx'))
print(response.status_code)

import requests

proxies = {
    'http': 'http://127.0.0.1:9743',
    'https': 'https://127.0.0.1:9743'
}
response =requests.get('http://www.baidu.com', proxies = proxies)

import requests

proxies = {
    'http': 'http://user:[email protected]:9743/',
}
response =requests.get('http://www.baidu.com', proxies = proxies)

import requests

proxies = {
    'http': 'socks5://127.0.0.1:9743',
    'https': 'socks5://127.0.0.1:9743'
}
response =requests.get('http://www.baidu.com', proxies = proxies)

import requests

r = requests.get('http://xxxxxxxxx.com', auth = ('user', '123'))

# 先捕捉子類例外，在捕捉父類例外
import requests
from  requests.exceptions import ReadTimeout, HTTPError, RequestException

try:
    response = requests.get('http://xxxxxxxxx.com',timeout = 1)
    print(response.status_code)
except ReadTimeout:
    print('timeout')
except HTTPError:
    print('httperror') 
except RequestException:
    print('error')

更多操作參考官方檔案：https://requests.readthedocs.io/zh_CN/latest/

標籤：Python

上一篇：歪嘴一笑百媚生，b站鬼畜無顏色，分析“歪嘴戰神”那該死的魅力

下一篇：每天一個爬蟲練習，爬取天氣資料，適合新手