import argparse
import json
import re
import sys
import time
from html.parser import HTMLParser

import requests

KILL_HREF = re.compile(r"/kill/(\d+)/?")
SYSTEM_AND_DATE = re.compile(r"/(\d+)/(\d+)/$")


def get_hash(kill):
	response = requests.get("https://zkillboard.com/api/killID/{}/".format(kill))
	response.raise_for_status()
	data = response.json()
	if len(data) > 1:
		raise ValueError()
	return data[0]["zkb"]["hash"]


class RelatedParser(HTMLParser):
	def __init__(self):
		super().__init__()
		self._team = 0
		self._kills = set()

	def handle_starttag(self, tag, attrs):
		attrs = dict(attrs)

		if tag == "table" and attrs.get("id", "") == "killlist":
			self._team += 1

		if tag == "a" and self._team > 0:
			match = KILL_HREF.search(attrs.get("href", ""))
			if match:
				kill = (self._team, match.group(1))
				if kill not in self._kills:
					self._kills.add(kill)

	@property
	def kills(self):
		return self._kills


def main():
	parser = argparse.ArgumentParser()
	parser.add_argument("url")
	parser.add_argument("-o", "--output")
	args = parser.parse_args()

	response = requests.get(args.url)
	response.raise_for_status()
	page = response.text

	related = RelatedParser()
	related.feed(page)

	output = []
	for team, kill in related.kills:
		time.sleep(1.05)  # Zkillboard is very sensitive.
		output.append({"id": kill, "hash": get_hash(kill), "team": team})

	if args.output:
		filename = args.output
	else:
		match = SYSTEM_AND_DATE.search(args.url)
		if match:
			filename = "{}_{}.json".format(*match.groups())
		else:
			filename = "scrapped.json"

	with open(filename, "w") as file:
		file.write(json.dumps(output))


if __name__ == "__main__":
	main()