Count Spotlight PA articles over time

count.py

import csv
from collections import defaultdict
from pathlib import Path


def count_files_by_month(filenames):
    counts = defaultdict(lambda: defaultdict(int))

    for filename in filenames:
        path = Path(filename)
        folder = path.parent.name
        date_part = path.stem.split("-")[0:2]  # Get YYYY-MM from filename

        if len(date_part) == 2 and date_part[0].isdigit() and date_part[1].isdigit():
            year_month = f"{date_part[0]}-{date_part[1]}"
            counts[folder][year_month] += 1

    return counts


def write_csv(counts, output_file="output.csv"):
    running_totals = {}

    folders = ["news", "statecollege", "berks"]
    for folder in folders:
        running_totals[folder] = 0

    all_months = sorted(
        set(month for months in counts.values() for month in months.keys())
    )

    rows = []
    for folder in folders:
        row = [folder]
        for month in all_months:
            if month in counts[folder]:
                running_totals[folder] += counts[folder][month]
            row.append(running_totals[folder])
        rows.append(row)

    with open(output_file, "w", newline="") as f:
        writer = csv.writer(f)
        writer.writerow(["folder"] + all_months)
        writer.writerows(rows)


# Read filenames from file or stdin
with open("filenames.txt", "r") as f:
    filenames = [line.strip() for line in f if line.strip()]

counts = count_files_by_month(filenames)
write_csv(counts)

Instructions.md

• Run find ./content -iname '*-*-*.md' | tee filenames.txt
• Remove newsletters and other folders you don't care about
• Run counts.py over it
• Make stacked bar chart in DataWrapper

spotlight-pa-articles-published-over-time.png