1. 请求方式

• requests.get(url)
• requests.post(url)
• requests.put(url)
• requests.delete(url)
• requests.head(url)
• requests.options(url)

1.1 requests.get()

• 基本用法

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

• 带参数的get用法

  import requests
  data = {
      'name': 'yindf',
      'age': 24
  }
  resp = requests.get('http://httpbin.org/get', params=data)
  print(resp.text)
  

• 解析json

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

  resp.json()其实就是调用了json.loads(resp.text)，所以二者结果一致

• 获取二进制数据（下载图片、视频等常用）

  import requests
  resp = requests.get('https://github.com/favicon.ico')
  print(type(resp.text), type(resp.content))
  print(resp.text)
  print(resp.content)
  

  保存二进制数据

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

• 添加headers

  import requests
  headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1'
  }
  resp = requests.get('https://www.zhihu.com/explore', headers=headers)
  print(resp.text)
  

1.2 request.post()

• 添加数据与headers

  import requests
  data = {
      'name' : 'yindf',
      'age' : 24
  }
  headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1'
  }
  resp = requests.post('http://httpbin.org/post', data=data, headers=headers)
  print(resp.text)
  

2. 响应

2.1 response属性

import requests

resp = requests.get('http://www.jianshu.com')
print(type(resp.status_code), resp.status_code)
print(type(resp.headers), resp.headers)
print(type(resp.cookies), resp.cookies)
print(type(resp.url), resp.url)
print(type(resp.history), resp.history)

>> <class 'int'> 200
>> <class 'requests.structures.CaseInsensitiveDict'> {'Date': 'Wed, 20 Dec 2017 01:35:32 GMT', 'Server': 'Tengine', 'Content-Type': 'text/html; charset=utf-8', 'Transfer-Encoding': 'chunked', 'X-Frame-Options': 'DENY', 'X-XSS-Protection': '1; mode=block', 'X-Content-Type-Options': 'nosniff', 'ETag': 'W/"75c89fd881f59b584e1023df6a772ebd"', 'Cache-Control': 'max-age=0, private, must-revalidate', 'Set-Cookie': 'locale=zh-CN; path=/', 'X-Request-Id': 'cd5c79bc-c9e3-4eb6-9c9b-f40a7f4b7c6e', 'X-Runtime': '0.006088', 'Content-Encoding': 'gzip', 'X-Via': '1.1 PShbwhjyw5dx20:1 (Cdn Cache Server V2.0)', 'Connection': 'keep-alive'}
>> <class 'requests.cookies.RequestsCookieJar'> <RequestsCookieJar[<Cookie locale=zh-CN for www.jianshu.com/>]>
>> <class 'str'> http://www.jianshu.com/
>> <class 'list'> []

3. 高级操作

3.1 文件上传

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

3.2 获取cookie

import requests
resp = requests.get('https://www.baidu.com')
print(resp.cookies)
for key, val in resp.cookies.items():
    print(key+'='+val)

3.3 会话维持，模拟登录

import requests
s = requests.Session()
s.get('http://httpbin.org/cookies/set/number/123')
resp = s.get('http://httpbin.org/cookies')
print(resp.text)

3.4 证书验证

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

• 这里指定verify参数为False取消证书验证

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

• 这里通过cert参数指定证书路径

3.5 超时设置

import requests
from requests.exceptions import Timeout
try:
    resp = requests.get('https://www.taobao.com',timeout=1)
    print(resp.status_code)
except Timeout:
    print('Time out')

3.6 认证设置

import requests
from requests.auth import HTTPBasicAuth
resp = requests.get(url, auth=HTTPBasicAuth('user', 'passwd'))
print(resp.status_code)

import requests
resp = requests.get(url, auth=('user', 'passwd'))
print(resp.status_code)

3.7 异常处理

import requests
from requests.exceptions import Timeout, HTTPError, RequestException
try:
    resp = requests.get('http://httpbin.org/get', timeout=0.1)
    print(resp.status_code)
except Timeout:
    print('time out')
except HTTPError:
    print('http error')
except RequestException:
    print('error')