Python requests模块详解

#发送请求
response = requests.get(url)

#response的常用属性：
response.text    # 根据HTTP 头部对响应的编码作出有根据的推测，推测的文本编码
response.encoding=”gbk”   # 修改编码方式

respones.content   # bytes类型
response.content.deocde(“utf8”)   # 解码

response.status_code   # 获取状态码
response.request.headers   # 获取请求头
response.headers     # 获取响应头

# 携带header的请求
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
requests.get(url,headers=headers)

# 携带带参数的请求
dic = {‘name‘:‘python‘}
requests.get(url,params=dic)

# 发送请求 
response = requests.post("http://www.baidu.com/", data = data,headers=headers)

data 的形式：字典


# 代理的使用
requests.get("http://www.baidu.com", proxies = proxies)
proxies的形式：字典
proxies = { 
    "http": "http://192.11.11.22:2222", 
    "https": "https://12.34.56.79:2222", 
    }

# cookies的形式：字典
cookies = {"cookie的name":"cookie的value"}
# 使用方法：
resp = requests.get(url,headers=headers,cookies=cookies}

# requests.utils.dict_from_cookiejar:把cookiejar对象转化为字典
import requests

url = "http://www.baidu.com"
response = requests.get(url)
print(type(response.cookies))

cookies = requests.utils.dict_from_cookiejar(response.cookies)
print(cookies)

# requests 提供了一个叫做session类，来实现客户端和服务端的会话保持

# 会话保持有两个内涵：

# 保存cookie
# 实现和服务端的长连接
# 使用方法

session = requests.session()
response = session.get(url,headers)
# session实例在请求了一个网站后，对方服务器设置在本地的cookie会保存在session中，下一次再使用session请求对方服务器的时候，会带上前一次的cookie

class Login():
    def __init__(self, loginName, password):
        # 用户名和密码
        self.loginName = loginName
        self.password = password
        # 接口地址
        self.login_url = ‘‘

        self.headers = {
            "Origin": "*",
            "Referer": "*
            ‘User-Agent‘: ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36‘
        }

        # spider session
        self.session = requests.session()

    def parse_get(self, url, params):
        ‘‘‘
        发送get请求
        :param url:
        :param params:
        :return:
        ‘‘‘
        resp = self.session.get(url=url, params=params, headers=self.headers)
        return resp.content.decode()

# ssl的证书不安全导致,添加verify=False参数


import requests

url = "https://www.12306.cn/mormhweb/"
response = requests.get(url,verify=False)

# 添加timeout参数，能够保证在3秒钟内返回响应，否则会报错

response = requests.get(url,timeout=3)

# parse.py
import requests
from retrying import retry

headers = {}


@retry(stop_max_attempt_number=3) #最大重试3次，3次全部报错，才会报错
def _parse_url(url)
    response = requests.get(url, headers=headers, timeout=3) #超时的时候回报错并重试
    assert response.status_code == 200 #状态码不是200，也会报错
    return response


def parse_url(url)
    try: #进行异常捕获
        response = _parse_url(url)
    except Exception as e:
        print(e)
        response = None
    return response