requests库

python实现的简单易用的HTTP库。基于urllib，采用Apache2 Licensed开源协议的HTTP库，比urllib更方便，可以节约我们大量的工作，完全满足HTTP测试需求。

　#示例

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)

'''各种请求方法'''
#print('*'*100)
#requests.post("http://httpbin.org/post")
#requests.put("http://httpbin.org/put")
#requests.delete("http://httpbin.org/delete")
#requests.head("http://httpbin.org/head")
#requests.options("http://httpbin.org/options")

'''GET请求'''
#基本GET请求
print("*基本GET*"*20)
response = requests.get("http://httpbin.org/get")
print(response.text)
print("*json*"*20)
print(response.json())
#带参数的GET请求
print("*带参数GET*"*20)
response = requests.get("http://httpbin.org/get?name=zhangsan&age=15")
print(response.text)
data = {
    'name':'lisi',
    'age':19
}
response = requests.get("http://httpbin.org/get",params=data)
print(response.text)
#获取二进制数据
print("*获取二进制数据*"*20)
response = requests.get("https://github.com/favicon.ico")
print(type(response.text),type(response.content))
print(response.text)
print(response.content)
with open("faviconn.ico","wb") as f:
    f.write(response.content)
    f.close()


#爬虫的时候，如果没有header，服务器会把你禁掉或出现服务器错误等。
print("*添加header*"*20)
response = requests.get("https://www.zhihu.com/explore")    #直接请求，不加header
print(response.text)
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)

'''POST请求'''
#基本POST请求
print("-基本POST请求-"*20)
data = {"name":"xiaoming","age":"22"}
response = requests.post("http://httpbin.org/post",data=data)
print(response.text)
response = requests.post("http://httpbin.org/post",data=data,headers=headers)
print(response.json())

'''状态码判断'''
print("-状态码判断-"*20)
response = requests.get("http://httpbin.org")
exit() if not response.status_code == requests.codes.ok else print("Request Successfully")
#或者exit() if not response.status_code == 200 else print("Request Successfully")

'''文件上传'''
print("-文件上传-"*20)
files = {"file":open("faviconn.ico","rb")}
response = requests.post("http://httpbin.org/post",files = files)
print(response.text)

'''cookies'''
print("-cookies-"*20)
response = requests.get("https://www.baidu.com")
print(response.cookies)
for key,value in response.cookies.items():
    print(key + "=" +value)

'''会话维持'''
print("-会话维持-"*20)
requests.get("http://httpbin.org/cookies/set/number/112232")
response = requests.get("http://httpbin.org/cookies/")
print(response.text)

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

'''证书验证'''
print("-证书验证-"*20)
response = requests.get("https://www.12306.cn")
print(response.status_code)
from requests.packages import urllib3
urllib3.disable_warnings()
response = requests.get("https://www.12306.cn",verify=False)
print(response.status_code)
# response = requests.get("https://www.12306.cn",cert=('/path/server/crt','/path/key'))
# print(response.status_code)

'''超时设置、异常处理'''
print("-超时设置、异常处理-"*20)
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")

'''认证设置'''
print("-认证设置-"*20)
from requests.auth import HTTPBasicAuth
r = requests.get("http://120.27.34.24:9001",auth=HTTPBasicAuth('user','123'))
# 或r = requests.get("http://120.27.34.24:9001",auth=('user','123'))
print(r.status_code)

## requests得到的内容乱码问题：
参考：https://jingyan.baidu.com/article/2c8c281dbb969d0008252a80.html

html = requests.get("http://********",headers=headers)
html.encoding = 'utf-8'
print(html.text)