code

analyze.py

import requests, json, re

def main():
	states = [l.split(",") for l in open("states.txt", "r").read().split("\n")]
	state_codes = {l.split(",")[0].lower(): l.split(",")[1].lower() for l in open("state_codes.csv", "r").read().split("\n")}
	pops = {l.split(",")[0].lower(): int(l.split(",")[1]) for l in open("pops.csv", "r").read().split("\n")}
	styling = ""
	lengths = {}
	ratios = []
	for state in states:
		length = page_length(state[0], True)
		lengths[state[0]] = length / pops[state[1]]
		ratios.append(length / pops[state[1]])
		print(f"{state[1].title()}: {length}")
	max_rat = 1.2
	for state in states:
		styling += f".{state_codes[state[1]]} {{fill: {get_color(lengths[state[0]], max_rat)};}}\n"

	print(styling)

def page_length(title, recursive=False):
	req = requests.get(f"https://en.wikipedia.org/w/api.php?action=parse&page={title}&format=json")
	content = json.loads(req.content)["parse"]["text"]["*"]
	sum_len = len(content)

	if not recursive:
		return sum_len

	#print(f"{title.replace('_', ' ')}: {len(content)}")

	links = get_links(content, title)
	for link in links:
		link_len = page_length(link)
		#print(f"\t{link.replace('_', ' ')}: {link_len}")
		sum_len += link_len
	
	return sum_len

def get_links(content, title):
	regex = r"Main articles?: (?:<a href=\"\/wiki\/(.+?)\".+?>.+?</a> ?a?n?d? ?)?(?:<a href=\"\/wiki\/(.+?)\".+?>.+?</a> ?a?n?d? ?){1,}"
	matches = re.findall(regex, content)
	new_matches = []
	for match in matches:
		for rm in match:
			if len(rm) > 0 and title.split(" ")[0].lower() in rm.lower():
				new_matches.append(rm.split("#")[0])
	return new_matches

def get_color(length, max_rat):
	ratio = max(min(length / max_rat, 1), 0)
	r = round(255 - ratio * 128)
	gb = round(255 - ratio * 255)
	return f"rgba({gb}, {gb}, {r}, 1)"

if __name__ == "__main__":
	main()