magister filter

from bs4 import BeautifulSoup
import re
import linecache

#                  | r   r+   w   w+   a   a+
#------------------|--------------------------
#read              | +   +        +        +
#write             |     +    +   +    +   +
#write after seek  |     +    +   +
#create            |          +   +    +   +
#truncate          |          +   +
#position at start | +   +    +   +
#position at end   |                   +   +

# https://regexr.com/
#text = re.sub("<.*?>", "", text)


SourcecodeFile = "C:\\Users\\Thomas\\Documents\\VSCode\\motdfile\\schedule\\sourcecode2.txt"
ResultsFile ="C:\\Users\\Thomas\\Documents\\VSCode\\motdfile\\schedule\\results.txt"
ResultsFormattedFile = "C:\\Users\\Thomas\\Documents\\VSCode\\motdfile\\schedule\\resultsedited.txt"
f = open(SourcecodeFile, "r+")
html = f.read()
f.close()
html = html.replace("   ", "")
html = html.replace("&nbsp;", "")
html = re.sub("<!--.*?-->", "", html)
f = open(SourcecodeFile, "w")
f.write(html)
f.close()
soup = BeautifulSoup(html, 'html.parser')

f = open("results.txt", "w+")
for item in soup.find_all("td"):
    f.write(item.get_text())
f.seek(0)
with open('resultsedited.txt','w') as f2:
    for line in f:
        if not line.isspace() and line != "pw\n" and line != "tt\n" and line != "hw\n":
            f2.write(line)
f.close()

"""
alles [
    [
        datum,
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
    ]
    [
        datum,
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
    ]
    [
        datum,
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
    ]
    [
        datum,
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
        lesuur[vak, tijd, docent, locatie]
    ]
]
"""
schedule = []


with open('resultsedited.txt','r+') as f:
    f.seek(0, 0)
    lineNumber = 0
    for line in f:
        lineNumber += 1
        if re.match(r"\w+ \d+ \w+", line):
            schedule.append([line[:-2]])
        elif re.match(r".*? - \w*? - .*", line):
            itemList = line.split(" - ")
            subject = itemList[0]
            schedule[-1].append([subject])
            hour = linecache.getline("resultsedited.txt", lineNumber - 1)[:-1]
            schedule[-1][-1].insert(0, int(hour))
        elif line == "hele dag\n":
            schedule[-1].append([0])
            schedule[-1][-1].append(linecache.getline("resultsedited.txt", (lineNumber + 1))[:-1])
        elif re.match(r"  .*\n", line):
            schedule[-1][-1].append(line[2:-1])
        elif re.match(r"\(.*?\)", line):
            location = line[:-1]
            if location == "( )":
                location = "(MHP)"
            if isinstance(schedule[-1][-1], str):
                schedule[-1].append([0])
                schedule[-1][-1].append(linecache.getline("resultsedited.txt", (lineNumber + 1))[2:-1])
                schedule[-1][-1].append(location[1:-1])
            else:
                schedule[-1][-1].append(location[1:-1])





for a in schedule:
    print(str(a[0]) + "\n")
    count = 1
    while (count < len(a)):
        countNested = 1
        print("\t" + str(a[count][0]))
        while (countNested < len(a[count])):
            print("\t\t" + str(a[count][countNested]))
            countNested += 1
        count += 1


#datum : "\w* \d+ \w*"
#vak/docent/klas: ".*? - \w*? - .*"
#lokaal: "\(\d*?\)"


#Nog om te doen: commenten wat alles is en fucking veel andere shit lmao