Requests库的使用

请求

基本GET请求

# 导入Requests模块
import requests

response = requests.get("https://www.baidu.com") 
# 现在我们就有了一个名为response的Response对象。我们可以从这个对象中获取所有我们想要的信息

# 用text获取响应内容
print(response.text)

带参数的GET请求

# 直接把参数加到到网址后面，用?分隔，用&拼接
response = requests.get("https://www.baidu.com?name=Bob&age=22")

# 以字典形式传值
data = {
    'name':'Bob',
    'age': 22
}

response = requests.get("https://www.baidu.com", params = data)
print(response.text)

解析Json

import json
# 当返回结果为json格式的字符串时，可以直接调用json()方法将其转化为json对象
response.json()

json.loads(response.text) # 可以得到相同的结果

获取二进制数据

response.content

添加headers

import requests
headers = {
    "User-Agent":'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.106 Safari/537.36'
}

response = requests.get("https://www.zhihu.com", headers=headers)

print(response.text)

基本POST请求

import requests

data = {
    'name': "Bob",
    'age': 22
}

# 数据字典在发出请求时会自动编码为表单形式

response = requests.post("https://www.zhihu.com", data=data)
print(response.text)

响应

response属性

import requests

response = requests.get('http://www.jianshu.com')
# 状态码
response.status_code
# cookies
response.cookies
# headers
response.headers
# url
response.url
# history
response.history

状态码判断

exit() if not response.status_code == requests.codes.ok else print("Request Successfuly!")

exit() if not response.status_code == 200 else print("Request Successfuly!")

高级操作

文件上传

import requests

files = {'file': open('favicon.ico', 'rb')}
response = requests.post("http://httpbin.org/post", files=files, timeout=1)
print(response.text)

获取cookies

import requests

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

会话维持

import requests

requests.get("http://httpbin.org/cookies/set/number/123456789")
response = requests.get("http://httpbin.org/cookies")
print(response.text)
# cookies为空是因为发起了两次请求，而这两个请求是两个独立的过程，相当于用一个浏览器设置了cookie，然后用另一个浏览器获取cookies这个页面，即在
# 两个互不关联的浏览器中进行操作

# 如何在同一个浏览器中实现set和get？
# 设置Session对象，再发起两次请求
s = requests.Session()
s.get("http://httpbin.org/cookies/set/number/123456789")
response = s.get("http://httpbin.org/cookies")
print(response.text)

代理设置

import requests

proxies = {
#     添加一些代理IP
    "http": "http://127.0.0.1:9743",
    "https": "https://127.0.0.1:9743"
}

# 如果代理是有用户名和密码的
proxies = {
#     添加一些代理IP, 传入用户名和密码信息
    "http": "http://user:password@127.0.0.1:9743/",
}

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

超时设置和异常处理

import requests
from requests.exceptions import ReadTimeout, ConnectTimeout

try:
    response = requests.get("http://httpbin.org/get", timeout=0.1)
    print(response.status_code)
except ReadTimeout:
    print("ReadTimeout")
except ConnectTimeout:
    print("ConnectTimeout")