python爬虫 基于requests模块的get请求实现详解

import requests# 1.指定urlurl = 'https://www.sogou.com/'# 2.发起get请求:get方法会返回请求成功的响应对象response = requests.get(url=url)# 3.获取响应中的数据：text属性作用是可以获取响应对象中字符串形式的页面数据page_data = response.text# 4.持久化数据with open("sougou.html","w",encoding="utf-8") as f:  f.write(page_data)  f.close()print("ok")

def get(url, params=None, **kwargs):  r"""Sends a GET request.  :param url: URL for the new :class:`Request` object.  :param params: (optional) Dictionary, list of tuples or bytes to send    in the body of the :class:`Request`.  :param /*/*kwargs: Optional arguments that ``request`` takes.  :return: :class:`Response <Response>` object  :rtype: requests.Response

import requests# 指定urlurl = 'https://www.sogou.com/web'# 封装get请求参数prams = {  'query':'周杰伦',  'ie':'utf-8'}response = requests.get(url=url,params=prams)page_text = response.textwith open("周杰伦.html","w",encoding="utf-8") as f:  f.write(page_text)  f.close()print("ok")

import requests# 指定urlurl = 'https://www.sogou.com/web'# 封装get请求参数prams = {  'query':'周杰伦',  'ie':'utf-8'}# 自定义请求头信息headers={  'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',  }response = requests.get(url=url,params=prams,headers=headers)page_text = response.textwith open("周杰伦.html","w",encoding="utf-8") as f:  f.write(page_text)  f.close()print("ok")