Python3 Requests库基础使用

此文为学习笔记

实例引入

各种请求方式

import requests

response = requests.get('https://www.baidu.com')
print(type(response))
print(response.status_code)
print(type(response.text))
print(response.text)
print(response.cookies)

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')

请求

基本GET请求

基本写法

import requests

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

带参数的GET请求

import requests

response = requests.get('http://httpbin.org/get?name=MQS&age=23')
print(response.text)

import requests

data = {
    'name': 'MQS',
    'age': 23
}
response = requests.get('http://httpbin.org/get', params = data)
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(response.json()))

获取二进制数据

import requests

response = requests.get('https://www.baidu.com/img/bd_logo1.png')
print(type(response.text), type(response.content))
print(response.text)
print(response.content)

import requests

response = requests.get('https://www.baidu.com/img/bd_logo1.png')
# 保存图片
with open('bd_logo.png', 'wb') as f:
    f.write(response.content)
    f.close()

添加Headers

import requests

response = requests.get('https://www.zhihu.com/explore')
print(response.text)

import requests

headers = {
    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36"
}
response = requests.get('https://www.zhihu.com/explore', headers = headers)
print(response.text)

基本POST请求

import requests

data = {
    'name': 'MQS',
    'age': 23
}
response = requests.post('http://httpbin.org/post', data=data)
print(response.text)

import requests

headers = {
    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36"
}
data = {
    'name': 'MQS',
    'age': 23
}
response = requests.post('http://httpbin.org/post', data=data, headers = headers)
print(response.text)

响应

response属性

import requests

headers = {
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'
}
response = requests.get('https://www.jianshu.com/', headers = headers)
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://httpbin.org/get')
print(response.status_code)
if response.status_code == 200:
    print('Request Successfully')

高级操作

文件上传

import requests

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

获取cookie

import requests

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

会话维持

模拟登陆

import requests
# 这是两个请求,所有没有cookies
requests.get('http://httpbin.org/cookies/set/number/12345')
response = requests.get('http://httpbin.org/cookies')
print(response.text)

import requests

session = requests.Session()
session.get('http://httpbin.org/cookies/set/number/12345')
response = session.get('http://httpbin.org/cookies')
print(response.text)

证书验证

import requests
from requests.packages import urllib3
#  消除警告
urllib3.disable_warnings()
response = requests.get('https://www.12306.cn/index/', verify = False)
print(response.status_code)

import requests
# 指定证书
response = requests.get('https://www.12306.cn/index/', cert=('/path/server.crt', '/path/key'))
print(response.status_code)

代理设置

import requests

# http代理
proxies = {
    'http': 'http://127.0.0.1:1080',
    'https': 'https://127.0.0.1:1080'
}
response = requests.get('https://www.taobao.com', proxies = proxies)
print(response.status_code)

import requests

# http代理传入账号密码
proxies = {
    'http': 'http://user:password@127.0.0.1:1080'
}
response = requests.get('https://www.taobao.com', proxies = proxies)
print(response.status_code)

import requests

# socks代理
proxies = {
    'http': 'socks5://127.0.0.1:1086',
    'https': 'socks5://127.0.0.1:1086'
}
response = requests.get('https://www.taobao.com', proxies = proxies)
print(response.status_code)

超时设置

import requests
from requests.exceptions import ConnectTimeout

try:
    response = requests.get('https://httpbin.org/get', timeout=1)
    print(response.status_code)
except ConnectTimeout:
    print('Timeout')
    

认证设置

import requests
from requests.auth import HTTPBasicAuth

r = requests.get('http://127.0.0.1:9001', auth = HTTPBasicAuth('user', '123'))
print(r.status_code)

import requests

r = requests.get('http://127.0.0.1:9001', auth = ('user', '123'))
print(r.status_code)

异常处理

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

try:
    response = requests.get('https://httpbin.org/get', timeout=0.5)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')
except ConnectionError:
    print('ConnectionError')
except RequestException:
    print('RequestException')