Python3中的Requests库

Requests库——基于Urllib的，简单易用的HTTP库

一，基本GET请求

1.实例引入

import requests

response = requests.get("https://www.baidu.com")  #获取百度网页信息
print(type(response))
print(response.status_code)  #输出状态码 200
print(type(response.text))  
print(response.text)  #输出内容
print(response.cookies)  #输出cookies内容

 

2.带参数的GET请求

import requests

data = {
    'name': 'jack',
    'age': 20
}
response = requests.get("http://httpbin.org/get", params=data)  #带参数的get请求
'''
    也可写为：
    response = requests.get("http://httpbin.org/get?name=jack&age=20")
'''
print(response.text)

 

3.解析json

import requests

response = requests.get("http://httpbin.org/get")
print(type(response.text))
print(response.json())
'''
    相当于：
    import json
    print(json.loads(response.text))
'''
print(type(response.json()))

输出结果为：

<class 'str'>
{'args': {}, 'headers': {'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate', 'Host': 'httpbin.org', 'User-Agent': 'python-requests/2.22.0', 'X-Amzn-Trace-Id': 'Root=1-5e467444-697bbfa202d8d6e88ccdea42'}, 'origin': '223.88.90.83', 'url': 'http://httpbin.org/get'}
<class 'dict'>

 

4.获取二进制数据

import requests
 
#爬取百度图片
response = requests.get("https://dss0.bdstatic.com/5aV1bjqh_Q23odCf/static/superman/img/logo_top-e3b63a0b1b.png") 
print(type(response.text),type(response.content))  #输出为<class 'str'> <class 'bytes'>
print(response.text)  # 输出为乱码
print(response.content)  #二进制内容

保存二进制文件：

import requests
  
#获取百度图片
response = requests.get("https://dss0.bdstatic.com/5aV1bjqh_Q23odCf/static/superman/img/logo_top-e3b63a0b1b.png") 
with open('baidu.png', 'wb') as f:  
    f.write(response.content)  #将二进制内容写入文件
    f.close()

 

5.添加headers

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}  #设置headers
response = requests.get('https://www.zhihu.com/explore', headers=headers)
print(response.text)

 

二，基本POST请求

import requests

data = {'name': 'jack', 'age': '20'}  #添加form data部分数据
response = requests.post('http://httpbin.org/post', data=data)  #post请求
print(response.text)

#添加headers信息
import requests

data = {'name': 'jack', 'age': '20'}
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}  #headers信息
response = requests.post('http://httpbin.org/post', data=data, headers=headers)
print(response.json())  #输出为json格式

 

三，响应

1.response属性

import requests

response = requests.get('http://www.jianshu.com')
print(type(response.status_code), response.status_code)  #状态码
print(type(response.headers), response.headers)  #headers信息
print(type(response.cookies), response.cookies)  #cookies信息
print(type(response.url), response.url)  #访问的url
print(type(response.history), response.history)  #访问的历史记录

 

2.状态码判断

100:{'continue',},
200:{'ok', 'okay', 'all_ok', 'all_okay'},
201:{'created',},

#重定向
300:{'multiple choices',},
301:{'moved_permanently', 'moved'},

#客户端错误
401:{'unauthorized',},
403:{'forbidden',},
404:{'not found',},
405:{'method not allowed',}

import requests

response = requests.get('http://www.jianshu.com')
exit() if not response.status_code==requests.codes.ok else print('Request Successfully')  #可用requests.codes.ok代替状态码200

''' 6  也可写为： 7  exit() if not response.status_code==200 else print('Request Successfully') 8 '''

 

四，高级操作

1.文件上传

import requests

files = {'file': open('baidu.png', 'rb')}  #打开文件
response = requests.post('http://httpbin.org/post', files=files)   #通过post讲文件上传

 

2.获取cookies

import requests

response = requests.get('https://www.baidu.com')
print(response.cookies)  #不需要再声明handler
for key, value in response.cookies.items():  #输出cookies各项信息
    print(key + '=' + value)

 

3.会话维持

模拟登录，维持登录状态

import requests

s = requests.Session()  #声明Session对象，用Session对象发起两次get请求，相当于在一个浏览器访问
                        #若不声明Session对象，则是在两个浏览器中操作，设置和访问分别在两个不同的网站，无法维持会话
s.get('http://httpbin.org/cookies/set/number/123456789')  #访问网站设置cookies
response = s.get('http://httpbin.org/cookies')  #访问cookies
print(response.text)  #若没有声明Session对象，等到的cookies为空

 

4.证书验证

#爬取证书不合法，即不安全的网站
import requests
from requests import urllib3
urllib3.disable_warnings()  #消除不进行证书验证的警告信息
response = requests.get('https://www.12306.cn', verify=False)  #设置verify=False，不进行证书验证
print(response.status_code)