简单的爬虫

 1 # Author：Winter Liu
 2 import time
 3 import urllib.request
 4 import re
 5 
 6 start_time = time.time()
 7 html_start = ‘https://yanghuanyu.com/dy‘
 8 result = []
 9 for i in range(2,31):
10     response = urllib.request.urlopen(html_start)
11     buff = response.read()
12     html = buff.decode(‘utf-8‘)
13     # with open(‘hpage.txt‘,‘w‘,encoding=‘UTF-8‘) as f:
14     #     f.write(html)
15     print(html_start)
16     data = re.findall(r‘\[.+\]\[\d\d\d\d\]\[.+\]\[.+\]‘, html)
17     data = list(set(data))
18     print(data)
19     result.extend(data)
20     html_start = "https://yanghuanyu.com/dy/page/"+str(i)
21 print(len(result))
22 print(result)
23 
24 end_time = time.time()
25 print(end_time  - start_time)