from PyPDF2 import PdfReader
import re

reader = PdfReader("2020-2021+Undergraduate+Catalog.pdf")
text = ""
class_titles = set()

page_num = 0
for page in reader.pages:
    page_num = page_num + 1
    if page_num >= 701:
        text += page.extract_text() + "\n"
        lines = text.splitlines()
        for line in lines:
            match = re.match(".+ \d{4} - (.+)", line)
            if match != None:
                #print("Found")
                class_titles.add(match.group(1).strip())

#print(class_titles)
with open("classes.txt", "w") as file1:
    for item in class_titles:
        file1.write(item)
        file1.write('\n')
    file1.close()