How to parse the entire table?

Question

Python

I need to parse a table with the class schedule of my university . Here is a link from which I need to parse. I tried the classic method using beautifulsoup and output through a loop, but it turns out some kind of mess, maybe someone knows how to completely parse this table without a loop?

Answer 1

from bs4 import BeautifulSoup
from urllib.request import urlopen
from json import dumps

url = "https://rozklad.ztu.edu.ua/schedule/group/%D0%86%D0%9F%D0%97-21-3?new"

bs=BeautifulSoup(urlopen(url).read(), features="lxml")

schedule = []
schedule_table = bs.find("table", attrs={"class":"schedule"})
for tr in schedule_table.findAll("tr"):
    if str(tr.th.text).strip() == "":
        continue
    tds = tr.findAll("td")
    for td in tds:
        newitem = {
            "day": td.get("day")[0:-2],
            "hour": td.get("hour")
        }
        if len(td.get("class")) > 0:
            newitem.update({
                "content": {
                    "variative": {
                        "subject": td.find("div", attrs={"class":"subject"}).text.strip(),
                        "room": td.find("span", attrs={"class":"room"}).parent.text.strip(),
                        "room_span": td.find("span", attrs={"class":"room"}).text.strip(),
                        "room_changed": "changed" in td.find("span", attrs={"class":"room"}).get("class"),
                        "teacher": td.find("div", attrs={"class":"teacher"}).text.strip(),
                    }
                }
            })
        schedule.append(newitem)

print(dumps(schedule, indent = 4, ensure_ascii = False))

# так можно фильтровать
wednesdays = [d for d in schedule if d["day"] == "Середа"]
print(dumps(wednesdays, indent = 4, ensure_ascii = False))
# и так по любому из параметров