requests 模块笔记

导入模块

import requests

请求方式：

    requests.get("https://www.baidu.com")
    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")

获取数据：

    r = requests.get('http://www.baidu.com') #像目标url地址发送get请求，返回一个response对象
    
    response.text返回的是Unicode格式，通常需要转换为utf-8格式。
    response.content是二进制模式，可以下载视频之类的，如果想看的话需要decode成utf-8格式。
    # response.content.decode("utf-8) 或 response.encoding="utf-8" 转码
    
    print(r.text)            # 返回响应的内容
    print(r.content)        # 这样获取的数据是二进制数据
    print(r.url)            # 打印请求网址的地址
    print(r.status_code)    # 打印请求页面的状态（状态码）# r.ok的布尔值便可以知道是否登陆成功
    print(r.cookies)        # 打印请求网址的cookies信息
    print(r.headers)        # 打印请求网址的headers所有信息
    print(r.encoding)        # 获取/修改网页编码
    print(r.json())            # 返回json数据
    
    print(r.history)        # 打印请求的历史记录（以列表的形式显示）

下载图片

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

例子：往请求链接中添加一些数据(data、headers、cookies、proxies...)：

    import requests
    
    data = {'name': 'germey', 'age': '22'}
    cookie = {'key':'value'}
    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'}
    proxies = {"http": "http://127.0.0.1:9743}
    
    requests.get(url='https://www.baidu.com/baidu', params={'wd': 'python',})
    # 为url传递参数 https://www.baidu.com/baidu?wd=python     

    response = requests.post(
        "https://www.zhihu.com/explore",
        data=data,  # 如果传递的是string而不是dict，需要先调用dumps方法格式化一下
        cookies=cookie,
        headers=headers, 
        proxies=proxies)
    print (response.headers.get('content-type')) #访问响应头部分内容
补：    requests.get(url, allow_redirects=False)    # 不允许重定向，默认True    # verify=False    # 关闭证书验证

其他操作

会话维持

cookie的一个作用就是可以用于模拟登陆，做会话维持

            import requests

            session = requests.session()
            session.get('http://httpbin.org/cookies/set/number/12456')
            response = session.get('http://httpbin.org/cookies')
            print(response.text)

代理设置

        import requests

        proxies = {
          "http": "http://127.0.0.1:9743",                    # 设置普通代理
          "https": "https://127.0.0.1:9743",                # 设置普通代理
          "http": "http://user:password@127.0.0.1:9743/",    # 设置用户名和密码代理
        }

        response = requests.get("https://www.taobao.com", proxies=proxies)
        print(response.status_code)

设置socks代理

安装socks模块 pip3 install 'requests[socks]'

                import requests
                proxies = {
                    'http': 'socks5://127.0.0.1:9742',
                    'https': 'socks5://127.0.0.1:9742'
                }
                response = requests.get("https://www.taobao.com", proxies=proxies)
                print(response.status_code)

超时设置

        import requests

        from requests.exceptions import ReadTimeout
        try:
            response = requests.get("http://httpbin.org/get", timeout = 0.5)#设置秒数超时，仅对于连接有效
            print(response.status_code)
        except ReadTimeout:
            print('Timeout')

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)

文件上传

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

认证设置

        import requests
        from requests.auth import HTTPBasicAuth

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

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

关闭证书验证

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

消除验证证书的警报

        from requests.packages import urllib3
        import requests

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

手动设置证书

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

异常处理

        # RequestException继承IOError,
　　    # HTTPError，ConnectionError,Timeout继承RequestionException
　　    # ProxyError，SSLError继承ConnectionError
　　    # ReadTimeout继承Timeout异常

        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')
            
        # RequestException    # 发送一个模糊的异常
        # ConnectionError    # 发生连接错误时的异常
        # HTTPError            # 发生HTTP错误时的异常
        # URLRequired        # URL错误时的异常
        # ConnectTimeout    # 连接服务器是请求超时
        # ReadTimeout        # 服务器没有在指定的时间内发送数据
        # Timeout            # 请求超时

原文出处： requests 模块笔记