SCOTUS_Analysis

parseCsv.py

# SCRIPT FOR SCRAPING SCOTUS HEARING TRANSCRIPT
# DATA COMPILED BY R STREET INSTITUTE: https://www.rstreet.org/2019/04/04/supreme-court-confirmation-hearing-transcripts-as-data/
# This script parses the data and searches for key terms, and outputs another (results.csv) file, along with printing a summary

import csv
import sys
import re

def print_inventory(dct):
    print("Mentions:")
    for item, amount in dct.items():  # dct.iteritems() in Python 2
        print("{} ({})".format(item, amount))

args = sys.argv

if len(args) < 3:
    print("USAGE: python3 readCsv.py <FILENAME> <SEARCHTERM>")
    raise Exception("Must provide file name, then search term.")

fileName = args[1]
term = args[2]

# Times mentioned by party
total = 0
totalR = 0
totalD = 0

# Times mentioned per justice
justices = {
   "Neil M. Gorsuch": 0,
   "Elena Kagan":  0,
   "Sonia Sotomayor": 0,
   "Samuel A. Alito, Jr.": 0,
   "John G. Roberts, Jr.": 0,
   "Stephen G. Breyer": 0,
   "Ruth Bader Ginsburg": 0,
   "Clarence Thomas": 0,
   "David H. Souter": 0,
   "Anthony M. Kennedy": 0,
   "William H. Rehnquist (to be Associate Justice) and Lewis F. Powell Jr.": 0,
   "William H. Rehnquist (to be chief)": 0,
   "Antonin Scalia": 0,
   "Sandra Day O'Connor": 0,
   "John Paul Stevens": 0,
   "Judge Robert Bork": 0
}

results = open('results.csv', 'w')
writer = csv.writer(results, delimiter=',', quotechar='"')
writer.writerow(['HEARING', 'SPEAKER', 'PARTY', 'COMMENT'])

with open(fileName, newline='', encoding="utf8", errors="ignore") as csvfile:
    data = csv.reader(csvfile, delimiter=',', quotechar='"')
    for row in data:
        title = row[4]
        comments = row[7]
        if title == 'Senator' or title == 'Chairman':
            x = re.findall(term, comments, re.IGNORECASE)
            # If term is mentioned...
            num = len(x)
            if num > 0:
                # Get the hearing, and add one to the appropriate key
                hearing = row[3]
                for key, value in justices.items():
                    if key == hearing:
                        justices[key] = justices[key] + len(x)

                # Log the party values
                party = row[5]
                name = row[6]
                total = total + len(x)
                values = [hearing, name, party, comments]
                writer.writerow(values)
                if party == 'D':
                    totalD = totalD + len(x)
                else:
                     totalR = totalR + len(x)

print("-- SUMMARY --")
print("\n")
print(str(total) + ' mentions of ' + '"' + term + '"')
print("\n")
print("Total Dem Instances: " + str(totalD))
print("Total GOP Instances: " + str(totalR))
print("\n")
print_inventory(justices)