scarsdale.py

import bs4
from collections import defaultdict

#counts = defaultdict(int)
counts = {}

f = open("scarsdale.html", encoding="utf-8",)
html = f.read()

soup = bs4.BeautifulSoup(html, features='html.parser')
spans = soup.find_all('span')

for span in spans:
    text = span.get_text(strip=True)
    if ' - ' in text:
        #the 1 is max splits, so do not split if dash is in univ. name
        res = text.split(' - ',1)
        student = res[0]
        college = res[1]

        #don't need to initialize if you use defaultdict.
        if college not in counts:
            counts[college] = 0

        counts[college] += 1

#sorted by college
for college, count in sorted(counts.items()):
    print(college, count)

#sorted by count
for college, count in sorted(counts.items(),
                             key=lambda x: x[1],
                             reverse=True):
    print(f"{count:3} {college}")