NMU

parse_learn_credits.py

#!/usr/bin/python
 # -*- coding: utf-8 -*-

import json
import re
import time
from functools import reduce
import pyperclip 


try:
    from HTMLParser import HTMLParser
except ImportError:
    # Python 3
    from html.parser import HTMLParser


parser = HTMLParser()


def parse_results(table_html):
	table_html_decoded = parser.unescape(table_html)
    # <td class="cell c3" style="text-align:center;">'90 / 3.0'</td>
	# to '90 / 3.0'
	hours_credits     = re.findall(r'(?<=\"cell c5\").*?(?<=>)(.*)(?=<\/td>)', table_html_decoded)
	courses_semesters = re.findall(r'(?<=\"cell c0\").*?(?<=>)(.*)(?=<\/td>)', table_html_decoded)
	if len(hours_credits) == 0:
		print('Не удалось ничего найти в ')
		print('"%s"' % table_html)
		return
	assert(len(hours_credits) == len(courses_semesters), 'Invalid courses and credits count!')
	courses = {}
	credits_sum = 0.0
	for i in range(len(hours_credits)):
		hc = hours_credits[i]
		cs = courses_semesters[i]
		course  = cs.split('/')[0].replace(" ", "")
		num_str = hc.split('/')[1].replace(" ", "")
		credit_num = float(num_str)
		credits_sum += credit_num
		if not course in courses:
			courses[course] = []
		courses[course].append(credit_num)
		
	print('Общая сумма кредитов: %s' % credits_sum)
	for course in courses:
		print('Курс %s:' % course)
		credits = courses[course]
		sum = reduce(lambda a,b: a+b, credits)
		print('   %s кредитов' % sum)


user_resp = input("Скопируете html c http://do.nmu.org.ua в буфер обмена\n(yes/no):")

if user_resp != "yes" and user_resp != "y":
	print('Выход...')
	exit(0)

input_html =  pyperclip.paste() 

try:
	parse_results(input_html)
except Exception as e:
	print('Что-то пошло не так....\n%s' % e)