Requests库整理

基于urllib库实现，简单易用

---

#简单好用
import requests

res = requests.get('http://www.baidu.com')
print(res)
print(res.text)
print(res.status_code)
print(res.cookies)

一、基本get请求

1.普通请求直接get

2.带参数的

import requests

data = {
    'name':'germey',
    'age':22
}
res = requests.get('http://httpbin.org/get',data)   #直接传进去
#相当于response = requests.get("http://httpbin.org/get?name=germey&age=22")
print(res)

3.解析json

import requests

res = requests.get('http://httpbin.org/get')
print(res.json())

4.获取二进制数据

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

5.添加headers

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.get("https://www.zhihu.com/explore", headers=headers)

---

二、基本post请求

import requests

data = {'name': 'germey', 'age': '22'}
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}
response = requests.post("http://httpbin.org/post", data=data, headers=headers)

三、响应

1.response的属性

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)

2.状态码的判定

response = requests.get("https://github.com/favicon.ico")
if response.status_code==200:
    print(response.content)

四、高级操作

1.文件上传

import requests

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

2.获取cookies

import requests

response = requests.get("https://www.baidu.com")
print(response.cookies)
for i in response.cookies.items():
    print(i)

3.会话维持，session操作，模拟登陆用

#再次请求该网站时是同一个会话，可以模拟登陆
import requests

s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123456789')
response = s.get('http://httpbin.org/cookies')
print(response.text)

4.证书验证，好像就12306用到？

#第一种方法，不让他报错
import requests

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

#第二种方法，规规矩矩加入证书
import requests

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

5.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)

#--------------------------------------------------------------------------------
#socks5代理
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)

6.超时设置

import requests
from requests.exceptions import ReadTimeout
try:
    response = requests.get("http://httpbin.org/get", timeout = 0.5)
    print(response.status_code)
except ReadTimeout:
    print('Timeout')