1 import urllib.request
 2 import urllib.parse
 3 from bs4 import BeautifulSoup
 4 
 5 url= ‘http://bkjw.hnist.cn/student/integratedQuery/instructionPlanQuery/detail/index‘
 6 headers={
 7 ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36‘,
 8 
 9 
10 ‘Cookie‘: ‘LOGIN=3234313732323030303837; COMPANY_ID=10122; ID=30374a53626949763944633d; PASSWORD=6f2f4f6b4d68706c7459453d; SCREEN_NAME=594b7368595246717254325668325047744a357833673d3d; JSESSIONID=abcLf7J_SGjp060VtN-9w; selectionBar=1443377‘
11 }
12 
13 request = urllib.request.Request(url=url,headers=headers)
14 
15 response = urllib.request.urlopen(request).read().decode()
16 
17 # print(response.read().decode())
18 soup =BeautifulSoup(response,‘lxml‘)
19 
20 table_list = soup.findAll(‘table‘)
21 
22 
23 file_name=‘course.txt‘
24 file=open(file_name,‘ab‘)
25 file.write((‘课程号     |    课程名      | 课程属性|  分数  |  学分 |   考试时间  |\n\n‘).encode())
26 
27 for i in table_list:
28     for body in i.findAll(‘tbody‘):
29         for tr in body.findAll(‘tr‘):
30             for td in tr.findAll(‘td‘):
31                 temp_str=td.getText()
32                 new_str=temp_str.strip()
33                 # print(new_str,end="  ")
34                 file.write((new_str+‘  |  ‘).encode())
35             file.write(‘\n‘.encode())