首页 > itarticle > 华理教务处爬课表 python3music

华理教务处爬课表 python3music

admin 11月 12, 2020 0

哈喽，我又来更新了呢~~马上开学了估计也没什么好更的啦T^T

今天写的是爬教务处课程的py，爬别的可以上教务处网站看，Chrome右击有
查看框架源代码，里面有具体的网址。

关门放代码！

参考资料貌似是学长的博客

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44



# -*- coding:utf-8 -*-
import requests
import re

url = "http://202.120.108.14/ecustedu/K_StudentQuery/K_StudentQueryLogin.aspx"
r = requests.Session()
html = r.get(url)
txt = html.text

str = re.findall('name="w*" id="w*" value=".*"', txt);

data = {"BtnLogin": "登录",
    "TxtPassword": "xxx",
    "TxtStudentId": "xxx"}
for x in str:
	name = x.split('"')
	data[name[1]] = name[5]


headers={
"Referer":"http://202.120.108.14/ecustedu/K_StudentQuery/K_Default.aspx",
"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36"
}
html = r.post(url,data,headers)

url = 'http://202.120.108.14/ecustedu/E_SelectCourse/ScInFormation/syllabus.aspx'
html = r.get(url)
txt = html.text

str = re.findall('name="w*" id="w*" value=".*"', txt)
data2 = {'bttn_search': '查询',
     'selyeartermflag': '下学期'}
for x in str:
	name = x.split('"')
	data2[name[1]] = name[5]
html = r.post(url, data=data2)

txt = html.text
str = re.findall('>w+<',txt)
for x in str:
	a = x.split(">")
	for y in a:
    	b = y.split("<")
    	print(b[0])