fulvia/modules/tld.py

#!/usr/bin/env python3
"""
Scrapes and shows information about Top Level Domains.
"""
import bs4
import requests

from module import commands, example

URI = 'https://en.wikipedia.org/wiki/List_of_Internet_top-level_domains'

@commands('tld')
@example('.tld me')
def gettld(bot, trigger):
	"""Show information about the given Top Level Domain."""
	if len(trigger.args) < 2:
		return bot.reply("What TLD?")
	word = trigger.args[1]
	if not word.startswith("."):
		word = "." + word

	res = requests.get(URI, verify=True)
	res.raise_for_status()
	soup = bs4.BeautifulSoup(res.text, "html.parser")

	td = soup.find("td", string=word)
	if not td:
		return bot.msg(f"Unable to find data for TLD: {word}")

	table_headers = []
	for th in td.parent.parent.find_all("th"):
		header = th.string
		if not header:
			header = th.a.string
		table_headers.append(header)

	if None in table_headers:
		n = table_headers.index(None)
		table_headers[n] = "Administrator"
		# this should be the only header on the page where th.string fails

	table_entries = []
	for td in td.parent.find_all("td"):
		string = td.text.strip()
		if not string:
			try:
				string = td.a.string
			except AttributeError:
				string = ""
		table_entries.append(string)

	msg = "[\x0304TLD\x03] "
	for n in range(len(table_headers)):
		msg += f"\x0310{table_headers[n]}\x03: "
		msg += f"\x0312{table_entries[n]}\x03 | "
	msg = msg[:-3].replace("\n","")
	bot.msg(msg)