執行截圖：

 1 import requests
 2 from lxml import etree
 3 from urllib import request
 4 
 5 # 全域性變數（請求頭+檔案IO物件）
 6 headers = {
 7     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36 Edg/85.0.564.44'}
 8 file=open('./古詩名句.txt','w',encoding='
 
utf-8')
 9 
10 
11 # 採集前端原始碼
12 def index():
13     for num in range(1, 12):
14         base_url = 'https://so.gushiwen.cn/mingju/default.aspx?p={}&c=&t='.format(num)  # 網站翻頁
15         print('正在寫入', base_url, '中的資料資訊...')
16         response = requests.get(base_url, headers=headers)  # 模擬訪問+請求頭
17
 
         response.encoding = 'utf-8'  # 解碼
18         html = response.text  # 獲取原始碼
19         clean(html)  # 清洗資料
20 
21 
22 # 清洗資料
23 def clean(html):
24     htmls=etree.HTML(html)#預處理
25     #xpath守則
26     Mingjus_urls=htmls.xpath('//div[@class="cont"]/a[1]/@href')#名句網址（待處理）
27     #print(Mingjus_urls)
 

28     Mingjus=htmls.xpath('//div[@class="cont"]/a[1]/text()')#名句
29     #print(Mingjus)
30     Poem_titles=htmls.xpath('//div[@class="cont"]/a[2]/text()')
31     #print(Poem_titles)
32     sto(Mingjus_urls,Mingjus,Poem_titles)
33 
34 # 列印資料
35 def sto(Mingjus_urls,Mingjus,Poem_titles):
36     for M,Mingju,Poem_title in zip(Mingjus_urls,Mingjus,Poem_titles):
37         #拼接網址
38         Mingju_url='https://so.gushiwen.cn/'+M
39         #整合資料資訊
40         full_info=Mingju+'\t'+Poem_title+'\n'+'名句網址：'+Mingju_url
41         #寫入檔案
42         file.write(full_info+'\n')
43 
44 if __name__ == '__main__':
45     index()
46     file.close()