笔记-requests详解（二）

实例引入

import requests

response = requests.get('https://www.baidu.com/')
print(type(response))
print(response.status_code)
print(type(response.text))
print(response.text)
print(response.cookies)

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

请求

基本GET请求

基本写法

import requests

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

带参数GET请求

import requests
response = requests.get("http://httpbin.org/get?name=germey&age=22")
print(response.text)

import requests

data = {
    'name': 'germey',
    'age': 22
}
response = requests.get("http://httpbin.org/get", params=data)
print(response.text)

解析json

import requests
import json

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

获取二进制数据

import requests

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

import requests

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

添加headers

import requests

response = requests.get("https://www.zhihu.com/explore")
print(response.text)

import requests

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)
print(response.text)

基本POST请求

import requests

data = {'name': 'germey', 'age': '22'}
response = requests.post("http://httpbin.org/post", data=data)
print(response.text)

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)
print(response.json())

响应

reponse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)

import requests

response = requests.get('http://www.jianshu.com/hello.html')
exit() if not response.status_code == requests.codes.not_found else print('404 Not Found')

import requests

response = requests.get('http://www.jianshu.com')
exit() if not response.status_code == 200 else print('Request Successfully')

高级操作

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

import requests

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

会话维持

模拟登录

import requests

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

import requests

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

import requests
s = requests.session()

data = {'form_email':'账户','form_password':'密码'}
#post 换成登录的地址，
s.post('https://www.douban.com/accounts/login',data)
#换成抓取的地址
response=s.get('https://movie.douban.com/top250')
print(response.text)#显示以下信息，说明已登陆成功

证书验证

import requests

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

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

import requests

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

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)

pip3 install 'requests[socks]'

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')

认证设置

import requests
from requests.auth import HTTPBasicAuth

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

import requests

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

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:
    print('Timeout')
except ConnectionError:
    print('Connection error')
except RequestException:
    print('Error')