Last active
September 4, 2023 03:07
-
-
Save 0x1d107/b37ff974e493668af35263f8f3786058 to your computer and use it in GitHub Desktop.
USATU schedule parser
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| beautifulsoup4==4.11.1 | |
| certifi==2022.12.7 | |
| charset-normalizer==3.0.1 | |
| icalendar==5.0.4 | |
| idna==3.4 | |
| lxml==4.9.2 | |
| python-dateutil==2.8.2 | |
| pytz==2022.7.1 | |
| requests==2.28.2 | |
| six==1.16.0 | |
| soupsieve==2.3.2.post1 | |
| urllib3==1.26.14 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/bin/env python | |
| import datetime as dt | |
| import requests as rq | |
| from bs4 import BeautifulSoup | |
| import uuid | |
| import icalendar | |
| UUID_NS=uuid.UUID('d7440a20-0018-4292-bb37-0a6ae62e61c3') | |
| API_URL =\ | |
| "https://isu.ugatu.su/api/new_schedule_api/?schedule_semestr_id=231&WhatShow=1&student_group_id=2384&weeks=0" | |
| soup = BeautifulSoup(rq.get(API_URL).text,features='lxml') | |
| def get_week_day(weeknum,weekday=0): | |
| semester_start_year = 2023 | |
| first_sept = dt.datetime(semester_start_year,9,1) | |
| first_week_monday = first_sept - dt.timedelta(days=first_sept.weekday()) | |
| return (first_week_monday + dt.timedelta(weeks=weeknum-1,days=weekday)).date() | |
| day_of_week=-1 | |
| cal = icalendar.Calendar() | |
| cal.add('prodid','-//USATU Schedule//NONSGML v1.0//RU') | |
| cal.add('version','2.0') | |
| for row in soup.tbody.find_all('tr'): | |
| if 'dayheader' in row['class']: | |
| day_of_week+=1 | |
| if 'noinfo' in row['class']: | |
| continue | |
| dow_name,time,weeks,subject,class_type,prof,lecture_hall,comments,*_=row.find_all('td') | |
| for week_str in weeks.get_text().split(): | |
| weeknum = int(week_str) | |
| start_str,end_str = time.get_text().split('-') | |
| day = get_week_day(weeknum,day_of_week) | |
| start_time = dt.time.fromisoformat(start_str) | |
| end_time = dt.time.fromisoformat(end_str) | |
| start_dt = dt.datetime.combine(day,start_time) | |
| end_dt = dt.datetime.combine(day,end_time) | |
| lesson_evt = icalendar.Event() | |
| subj_name = subject.get_text() | |
| if not subj_name: | |
| subj_name = class_type.get_text() | |
| summary = f"{subj_name} {class_type.get_text()} {lecture_hall.get_text()}" | |
| lesson_evt.add('summary',summary) | |
| lesson_evt.add('dtstart',start_dt) | |
| lesson_evt.add('dtend',end_dt) | |
| lesson_evt.add('uid',uuid.uuid3(UUID_NS,f"{subj_name} {start_dt}")) | |
| cal.add_component(lesson_evt) | |
| #print(summary) | |
| with open('schedule.ics','wb') as f: | |
| f.write(cal.to_ical()) | |
| print(cal.to_ical().decode('utf-8')) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment