requests库使用

Requests是用python语言编写的，基于urllib，采用Apache2 Licensed开源协议的HTTP库。它比utllib更加方便，可以节约我们大量的工作，完全满足HTTP测试需求。一句话，它是python实现的简单易用的HTTP库。
安装：

pip install requests

各种请求方式

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')
r = requests.options('http://httpbin.org/get')

请求

基本GET请求

基本写法

# 基本写法

import requests

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

带参数的GET请求

# 带参数的GET请求:拼接在url后面
import requests

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

# 带参数的GET请求：作为参数传入

import requests

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

解析json

# 解析json

import requests
import json

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

下载文件

# 获取二进制数据

import requests

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

# 将二进制流写入到文件

import requests

response = requests.get('http://github.com/favicon.ico')
with open('favicon.ico','wb') as f:
    f.write(response.content)
    f.close()

添加headers

# 添加headers
import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 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':'nic',
    'age':23
}
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'
}
response = requests.post('http://httpbin.org/post',data=data,headers=headers)
print(response.json())

{'args': {}, 'data': '', 'files': {}, 'form': {'age': '23', 'name': 'nic'}, 'headers': {'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate', 'Content-Length': '15', 'Content-Type': 'application/x-www-form-urlencoded', 'Host': 'httpbin.org', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36', 'X-Amzn-Trace-Id': 'Root=1-5ecdead9-ecfd9b34abf7f7053e279758'}, 'json': None, 'origin': '49.52.99.230', 'url': 'http://httpbin.org/post'}

response属性

# 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)

<class 'int'> 403
<class 'requests.structures.CaseInsensitiveDict'> {'Server': 'Tengine', 'Date': 'Wed, 27 May 2020 04:25:44 GMT', 'Content-Type': 'text/html', 'Transfer-Encoding': 'chunked', 'Connection': 'keep-alive', 'Vary': 'Accept-Encoding', 'Strict-Transport-Security': 'max-age=31536000; includeSubDomains; preload', 'Content-Encoding': 'gzip'}
<class 'requests.cookies.RequestsCookieJar'> <RequestsCookieJar[]>
<class 'str'> https://www.jianshu.com/
<class 'list'> [<Response [301]>]

文件上传

# 文件上传

import requests

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

获取cookie

# 获取cookie

import requests

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

<class 'requests.cookies.RequestsCookieJar'>
BDORZ=27315

会话维持

# 会话维持，可以用来模拟登录
# 如果不使用Session方法，两次get请求是独立的，相当于使用两个浏览器发起了两个不一样的请求

import requests
session = requests.Session()
session.get('http://httpbin.org/cookies/set/number/123456')  # 设置cookie
response = session.get('http://httpbin.org/cookies') # 获取cookie
print(response.text)

{
  "cookies": {
    "number": "123456"
  }
}

证书验证

# 证书验证：不进行验证，会报warning

import requests

response = requests.get('https://www.12306.cn',verify=False)
print(response.status_code)

# 证书验证：本地有证书
import requests

response = requests.get('https://www.12306.cn',cert=('/path/server.crt','/path/key'))
print(response.status_code)

代理设置

# 代理设置

import requests

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

import requests

proxies = {
    "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

import requests
from requests.exceptions import ReadTimeout

try:
    response = requests.get("https://nicahead.github.io/",timeout=0.001)
    print(response.status_code)
except ReadTimeout:
    print("timeout")

timeout

认证设置

import requests

response = requests.get('http:/120.27.34.24:9001',auth=('user','123'))
print(response.status_code)

异常处理

官网文档

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

# 先捕捉子类额异常，再捕捉父类的异常

try:
    response = requests.get("https://nicahead.github.io/",timeout=0.001)
    print(response.status_code)
except ReadTimeout:
    print("ReadTimeout")
except ConnectionError:
    print("ConnectionError")
except RequestException:
    print("RequestException")

ReadTimeout