python的requests模块

get没有参数请求

    # -*-coding:utf-8 -*-
    import requests
    url="https://www.baidu.com/"
    reponse = requests.get(url=url)
    print(reponse.text)

    # -*-coding:utf-8 -*-
    import requests
    url="https://www.baidu.com/"
    reponse = requests.request(method="GET",url=url)
    print(reponse.text)

Post没有参数的请求

    # -*-coding:utf-8 -*-
    import requests
    url="https://www.baidu.com/"
    reponse = requests.request(method="POST",url=url)
    print(reponse.text)

   # -*-coding:utf-8 -*-
    import requests
    url="https://www.baidu.com/"
    reponse = requests.post(url=url)
    print(reponse.text)

get、post有请求参数几个统一形式:

params:是get的请求数据拼接在url后面的

data,json是post的不能类型的数据，解释如下：


    # -*-coding:utf-8 -*-
    import requests
    import json
    url="https://www.baidu.com/"
    #https://www.baidu.com/s?wd=
    params ={"wd":"江可爱"}
    #这种类型的数据，请求的时候Content-Type= application/x-www-form-urlencoded会把数据
    #传给requests.body,然后再转成dict，让request.POST.get()获取
    data = {"usename":"1234","password":"1233"} #如果是post方式是变成这种格式请求"usename=1234;password=1233"
    #这个形式Content-Type= application/json是传给了requests.body,但是没有转成字典所以request.POST.get()是没有值的
    jsons=json.dumps({"usename":"1234","password":"1233"}) #json(str)
    reponse = requests.get(url=url,params=params,data=data,json=jsons)
    print(reponse.text)

请求头headers、登陆返回的cookie,浏览器模拟user-agent，referer的作用是记录你访问一个目标网站时，在访问前你的原网站的地址:

    #cookie
    r = requests.get(url=url,
                 cookies={".CNBlogsCookie":"005E5D62C333893955F050B6B5A3ACCCEAB4FC6A1D6"})
print(r.text)

    #headers
    headers = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36",
            "referer":"https://www.zhihu.com/",
           "Host":"www.zhihu.com",
           "cookie":""
           }

将文本流保存到文件,iter_content可以迭代获取内容

import requests
import os
url = "https://www.cnblogs.com/venvive/p/11530684.html"
r = requests.get(url=url,
                 cookies={".CNBlogsCookie":"005E5D62C333893955F050B6B5A2D544319D412F1C111E3ACCCEAB4FC6A1D6"})
base_path = os.path.dirname(os.path.abspath(__file__))
with open(base_path+"/reportss.txt","wb") as fd:
    for chunk in r.iter_content(chunk_size=9):
        fd.write(chunk)

重定向与请求历史

例如Github将所有的HTTP请求重定向到HTTPS:

    r = requests.get("http://github.com")
    #重定向
    r.url = "https://github.com/"
    print(r.status_code)
    print(r.history)
    
    #输出：
    200
    [<Response [301]>]

如果是使用GET、OPTIONS、POST、PUT、PATCH或者DELETE、 HEAD,那么可以使用allow_redirects参数禁止重定向处理，False是禁止，True是允许

r = requests.get("http://github.com",allow_redirects=False)
#重定向
r.url = "https://github.com/"
print(r.status_code)
print(r.history)
#输出：
301
[]

超时

requests在经过以timeout参数设定的秒数时间之后停止等待响应，基本上所有的生产代码都应该使用这一参数，如果不使用，程序可能会永远失去响应

r = requests.get("https://www.zhihu.com/",timeout=0.001)
#输出报错：
#requests.exceptions.ConnectTimeout: HTTPSConnectionPool(host='www.zhihu.com', port=443): Max retries exceeded