网页采集器练习-requests 

 1 import requests
 2 if __name__ == "__main__":
 3     header = {
 4         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3868.400 QQBrowser/10.8.4394.400"
 5     }
 6 # UA伪装，将对应的User-Agent封装到一个字典中
 7     url = "https://www.baidu.com/s"
 8 # 指定url
 9     kw = input("请输入您要搜索的内容：")
10     param = {
11         "wd": kw
12     }
13 # 对指定的url发起的请求对应的url是携带参数的，并且请求过程中处理了参数
14     response = requests.get(url=url, params=param, headers=header)
15     page_text = response.text
16     fileName = kw+".html"
17     with open(fileName, "w", encoding="utf-8") as fp:
18         fp.write(page_text)
19     print(fileName, "保存成功！！！")

 

posted @ 2021-08-21 22:20  likl-  阅读(51)  评论(0)    收藏  举报