import requests
#UA :User-Agent(请求载体的身份标识)
#UA检测:门户网站的服务器会检测对应请求的载体身份标识,
# 如果检测到请求的载体身份标识为某一浏览器,说明该请求是一个正常请求
# 但是如果检测到请求的载体身份标识不是某一浏览器,则认为是不正常请求,被拒绝
# User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36
if __name__ == '__main__':
#UA 伪装
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
}
url = 'https://www.baidu.com/s'
# url = 'https://www.baidu.com/s?wd=%E6%88%98%E7%8B%BC2'
#处理url 携带的参数:封装到字典
kw = input('输入要爬取的网页关键词:')
param = {
'wd': kw
}
#对指定的url 发起的请求对应的url 是携带参数的,并且求情过程中处理了参数
response = requests.get(url=url,params=param,headers=headers)
page_text = response.text
fileName = kw+'.html'
with open(fileName,'w',encoding='utf-8') as pf:
pf.write(page_text)
print(fileName,'保存成功!')