Quick and dirty "rank Texas death row media witnesses by frequency" script.

tx-death-row-witnesses.py

from collections import Counter

import requests
from bs4 import BeautifulSoup


def j_formatter(reporter):
    name, affil = [x.strip() for x in reporter.split(',', 1)]

    # if this were a real thing, would obv want more rigorous cleaning
    if name == 'Michael Graczyk':
        name = 'Mike Graczyk'

    if affil == 'Huntsville Item':
        affil = 'The Hunstville Item'

    return name + ' - ' + affil


URL = 'https://www.tdcj.state.tx.us/death_row/dr_media_witness_list.html'
page = requests.get(URL)
soup = BeautifulSoup(page.text, 'html.parser')
table = soup.find('table')
rows = table.find_all('tr')

journos = Counter()

for row in rows[1:]:
    reporters = row.find_all('td')[6].text.split(';')

    for human in [x for x in reporters if x.strip()]:
        journos[j_formatter(human)] += 1

for i, journo in enumerate(journos.most_common(20)):
    print(str(i+1) + '.', journo[0] + ': ', journo[1])