还未完善的某小说网爬虫

 1 import urllib.request
 2 import urllib.error
 3 import re
 4 import os
 5 
 6 url = input(‘请输入要获取的网页(quanshu网)：‘)
 7 def get(url):
 8     try:
 9         headers = {‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36‘}
10         urls = urllib.request.Request(url,headers = headers)
11         html = urllib.request.urlopen(urls).read()
12         html = html.decode(‘gbk‘)
13 
14         reg = r‘<li><a href="(.*?)" title=".*?">(.*?)</a></li>‘
15         regs = re.findall(reg,html)
16 
17         for i in regs:
18             url_data = i[0]
19     except urllib.error.HTTPError as reason:
20         print(‘出错了！错误的原因是：‘,reason)
21         input(‘‘)
22 
23     urls_2 = urllib.request.Request(url_data,headers = headers)
24     urls_2_open = urllib.request.urlopen(urls_2).read()
25     urls_2_open = urls_2_open.decode(‘gbk‘)
26 
27     reg_2 = r‘</script>&nbsp;&nbsp;&nbsp;&nbsp;(.*?)<script type="text/javascript">
28     regs_2 = re.findall(reg_2,urls_2_open)
29     print(regs_2)
30 
31     ‘‘‘
32     with open(‘盗墓笔记.TXT‘,‘w‘) as g:
33         g.write(regs_2)
34     ‘‘‘
35         
36         
37 if __name__==‘__main__‘:
38     get(url)