requests库

GET请求

• 基本实例

  import requestsresponse = requests.get('https://www.httpbin.org/get')
  print(response.text)
  

  
• params参数

  import requests
  data = {"name":"Bileton","age":"21"
  }
  response = requests.get('https://www.httpbin.org/get',params=data)
  print(response.text)
  

  
• json格式
  网页响应的类型是字符串类型的，但这里也是JSON格式的，可以直接调用json方法

  import requests
  data = {"name":"Bileton","age":"21"
  }
  response = requests.get('https://www.httpbin.org/get',params=data)
  print(response.json())
  # {'args': {'age': '21', 'name': 'Bileton'}, 'headers': {'Accept': '*/*', 'Accept-Encoding': 'gzip, deflate, br, zstd', 'Host': 'www.httpbin.org', 'User-Agent': 'python-requests/2.32.3', 'X-Amzn-Trace-Id': 'Root=1-672a4784-12ddc86a16dd0f3d4001ec86'}, 'origin': '125.45.126.225', 'url': 'https://www.httpbin.org/get?name=Bileton&age=21'}
  

• 请求头（Request Headers）
  添加请求头信息，设置headers参数

  import requests
  data = {"name":"Bileton","age":"21"
  }
  headers = {
  "user-agent":
  "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36 Edg/130.0.0.0"
  }
  response = requests.get('https://www.httpbin.org/get',params=data,headers=headers)
  print(response.json())
  

  

POST请求

• 基本实例

  params = {"name":"Bileton","age":"21"
  }
  headers = {
  "user-agent":
  "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36 Edg/130.0.0.0"
  }data = {"name":"Bileton","age":"21"
  }response = requests.post('https://www.httpbin.org/post',params=params,headers=headers,data=data)
  print(response.text)
  

  {"args": {"age": "21", "name": "Bileton"}, "data": "", "files": {}, "form": {"age": "21", "name": "Bileton"}, "headers": {"Accept": "*/*", "Accept-Encoding": "gzip, deflate, br, zstd", "Content-Length": "19", "Content-Type": "application/x-www-form-urlencoded", "Host": "www.httpbin.org", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36 Edg/130.0.0.0", "X-Amzn-Trace-Id": "Root=1-672a4adb-4a7a532f3ebb47d17b9d45da"}, "json": null, "origin": "125.45.126.229", "url": "https://www.httpbin.org/post?name=Bileton&age=21"
  }
  

  form是提交的数据

Cookie

• 获取Cookie

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

  <RequestsCookieJar[<Cookie BAIDUID=B66399BCCEE18461B7577D4F034E25E0:FG=1 for .baidu.com/>, <Cookie BAIDUID_BFESS=B66399BCCEE18461B7577D4F034E25E0:FG=1 for .baidu.com/>, <Cookie BIDUPSID=B66399BCCEE18461B7577D4F034E25E0 for .baidu.com/>, <Cookie H_PS_PSSID=61004_61027_61035_61078 for .baidu.com/>, <Cookie PSTM=1730825523 for .baidu.com/>, <Cookie BDSVRTM=6 for www.baidu.com/>, <Cookie BD_HOME=1 for www.baidu.com/>]>
  BAIDUID=B66399BCCEE18461B7577D4F034E25E0:FG=1
  BAIDUID_BFESS=B66399BCCEE18461B7577D4F034E25E0:FG=1
  BIDUPSID=B66399BCCEE18461B7577D4F034E25E0
  H_PS_PSSID=61004_61027_61035_61078
  PSTM=1730825523
  BDSVRTM=6
  BD_HOME=1
  

• 维持登录状态
  Cookie
  登录github，把请求头中的Cookie内容复制下来
  
  然后把Cookie内容取出放到请求头里

  url = 'https://github.com/'headers = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36","Cookie":"_octo=GH1.1.1248862582.1728219778; _device_id=64df60ce376c117249233fa8cfeadec3; saved_user_sessions=184353984%3A0OccUYxxcXaTR-83X8DhQWyUdrI5fjj7uqY0ELmpfxJ_PtQL; user_session=0OccUYxxcXaTR-83X8DhQWyUdrI5fjj7uqY0ELmpfxJ_PtQL; __Host-user_session_same_site=0OccUYxxcXaTR-83X8DhQWyUdrI5fjj7uqY0ELmpfxJ_PtQL; logged_in=yes; dotcom_user=Bileton; color_mode=%7B%22color_modEgGDB9310wz%2FQ2D9UrGflA%3D%3D"
  }
  response = requests.get(url,headers=headers)
  print(response.text)
  

• SSL证书验证
  访问https://ssr2.scrape.center/，会出现“您的连接不是私密连接”
  
  如果直接使用requests请求这个网站，会出现SSLError的错误。
  我们可以通过设置verify参数来控制是否验证证书，它的默认值是true。

  url = "https://ssr2.scrape.center/"
  response = requests.get(url,verify=False)
  print(response.status_code) # 200
  

• 身份认证
  访问https://ssr3.scrape.center/，会有认证窗口
  
  requests库自带有身份认证功能，通过auth参数即可设置。

  url = "https://ssr3.scrape.center/"
  response = requests.get(url,auth=('admin','admin'))
  print(response.status_code) # 200