Requests库笔记

1、概览

1.1、实例引入

# 引入Requests库
import requests

# 发起GET请求
response = requests.get('https://www.baidu.com/')
# 查看响应类型  requests.models.Response
print(type(response))
# 输出状态码
print(response.status_code)
# 输出响应内容类型  text
print(type(response.text))
# 输出响应内容
print(response.text)
# 输出cookies
print(response.cookies)

1.2、各种请求方式

import requests

# 发起POST请求
requests.post('http://httpbin.org/post')
# 发起PUT请求
requests.put('http://httpbin.org/put')
# 发起DELETE请求
requests.delete('http://httpbin.org/delete')
# 发送HEAD请求
requests.head('http://httpbin.org/get')
# 发送OPTION请求
requests.options('http://httpbin.org/get')

2、请求

2.1 、基本GET请求

2.1.1、基本写法

import requests

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

2.1.2、带参数的GET请求

import requests

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

2.1.3、带参数的GET请求(2)

import requests

# 分装GET请求参数
param = {'name':'jyx','age':19}
# 设置GET请求参数(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')
# 获取响应内容
print(type(response.text))
# 如果响应内容是json,就将其转为json
print(response.json())
# 输出的是字典类型
print(type(response.json()))

2.1.5、获取二进制数据

import requests

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

# str，bytes
print(type(response.text),type(response.content))
# 输出响应的文本内容
print(response.text)
# 输出响应的二进制内容
print(response.content)
# 下载二进制数据到本地
with open('favicon.ico','wb') as f:
  f.write(response.content)
  f.close()

2.1.6、添加headers

import requests

# 设置User-Agent浏览器信息
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"
}
# 设置请求头信息
response = requests.get('https://www.zhihu.com/explore',headers=headers)
print(response.text)

2.2、基本POST请求

import requests

# 设置传入post表单信息
data= { 'name':'jyx', 'age':18}
# 设置请求头信息
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"
}
# 设置请求头信息和POST请求参数(data)
response = requests.post('http://httpbin.org/post', data=data, headers=headers)
print(response.text)

3、响应

3.1 response属性

import requests

response = requests.get('http://www.jianshu.com/')
# 获取响应状态码
print(type(response.status_code),response.status_code)
# 获取响应头信息
print(type(response.headers),response.headers)
# 获取响应头中的cookies
print(type(response.cookies),response.cookies)
# 获取访问的url
print(type(response.url),response.url)
# 获取访问的历史记录
print(type(response.history),response.history)

3.2、状态码判断

import requests

response = requests.get('http://www.jianshu.com/404.html')
# 使用request内置的字母判断状态码
if not response.status_code == requests.codes.ok:
    print('404-1')
response = requests.get('http://www.jianshu.com')
# 使用状态码数字判断
if not response.status_code == 200:
    print('404-2')

4、高级操作

4.1、文件上传

import requests

files = {'file':open('favicon.ico','rb')}
# 往POST请求头中设置文件(files)
response = requests.post('http://httpbin.org/post',files=files)
print(response.text)

4.2、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)

4.3、会话维持

4.3.1、普通请求

import requests

requests.get('http://httpbin.org/cookies/set/number/12456')
response = requests.get('http://httpbin.org/cookies')
# 本质上是两次不同的请求，session不一致
print(response.text)

4.3.2、会话维持请求

import requests

# 从Requests中获取session
session = requests.session()
# 使用seesion去请求保证了请求是同一个session
session.get('http://httpbin.org/cookies/set/number/12456')
response = session.get('http://httpbin.org/cookies')
print(response.text)

4.4、证书验证

4.4.1、无证书访问

import requests

response = requests.get('https://www.12306.cn')
# 在请求https时，request会进行证书的验证，如果验证失败则会抛出异常
print(response.status_code)

4.4.2、关闭证书验证

import requests

# 关闭验证，但是仍然会报出证书警告
response = requests.get('https://www.12306.cn',verify=False)
print(response.status_code)

4.4.3、消除关闭证书验证的警告

from requests.packages import urllib3
import requests

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

4.4.4、手动设置证书

import requests

# 设置本地证书
response = requests.get('https://www.12306.cn', cert=('/path/server.crt', '/path/key'))
print(response.status_code)

4.5、代理设置

4.5.1、设置普通代理

import requests

proxies = {
    "http": "http://127.0.0.1:9743",
    "https": "https://127.0.0.1:9743",
}
# 往请求中设置代理(proxies
)
response = requests.get("https://www.taobao.com", proxies=proxies)
print(response.status_code)

4.5.2、设置带有用户名和密码的代理

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、设置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、超时设置

import requests
from requests.exceptions import ReadTimeout

    

try:
   # 设置必须在500ms内收到响应，不然或抛出ReadTimeout异常
   response = requests.get("http://httpbin.org/get", timeout=0.5)
            print(response.status_code)
except ReadTimeout:
   print('Timeout')

4.7、认证设置

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、异常处理

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:
   # 超时异常
   print('Timeout')
except ConnectionError:
   # 连接异常
   print('Connection error')
except RequestException:
   # 请求异常
   print('Error')