requests模块 - python学习网

请求

请求方式

get请求

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

带参数get请求

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

添加Headers

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)

解析json

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()))

获取二进制数据

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

import requests

#注意文件路径要转义字符
#二进制数据要以b的方式写入写出
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()

基本post请求

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 = data, headers = headers)
print(response.json())

响应

response属性

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)

状态码判断

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

常见状态码：

100~199：表示服务器成功接收部分请求，要求客户端继续提交其余请求才能完成整个处理过程。
200~299：表示服务器成功接收请求并已完成整个处理过程。常用200（OK 请求成功）。
300~399：为完成请求，客户需进一步细化请求。例如：请求的资源已经移动一个新地址、常用302（所请求的页面已经临时转移至新的url）、307和304（使用缓存资源）。
400~499：客户端的请求有错误，常用404（服务器无法找到被请求的页面）、403（服务器拒绝访问，权限不够）。
500~599：服务器端出现错误，常用500（请求未完成。服务器遇到不可预知的情况）。

编码

import requests

response = requests.get('http://xxxxxxxxx.com')
#查看编码方式
print(response.encoding)
#改变编码方式
response.encoding = 'ISO-8859-1'
#处理网页源代码乱码
response.encoding =  response.apparent_encoding

高级操作

文件上传

import requests

#上传文件要以二进制模式打开文件
files ={'files':open(r'C:\Users\key\Desktop\py\favicon.ico', 'rb')}
response = requests.post('http://httpbin.org/post',files = files )
print(response.text)

获取cookies

import requests

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

会话维持，用来模拟登陆

import requests

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

证书验证

import requests
from requests.packages import urllib3

urllib3.disable_warnings()    #消除警告信息
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)

代理设置

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:password@127.0.0.1:9743/',
}
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)

认证设置

import requests

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

异常处理

# 先捕捉子类异常，在捕捉父类异常
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')

更多操作参考官方文档：https://requests.readthedocs.io/zh_CN/latest/

python学习网

分类

常见状态码：