import requests
import urllib
import bs4
import re
import os

from .Setting import Setting
from .ProxyHandler import ProxyHandler
from .Logger import Logger
from .Util import Util
from .DataType import PageLink, TorrentFile

from .WorkerTorrentKim import WorkerTorrentKim
from .WorkerTfreeca import WorkerTfreeca
from .WorkerTocops import  WorkerTocops


class Crawler:
	def __init__(self):
		self.setting = Setting()
		self.session = requests.session()
		self.proxy_handler = ProxyHandler()
		self.worker = None

		if len(self.setting.settings['urls']) > 0:
			urlinfo = urllib.parse.urlparse(self.setting.settings['urls'][0])
			top_url = urllib.parse.urlunparse((urlinfo.scheme, urlinfo.netloc, '', '', '', ''))
			self.proxy_handler.check_url = top_url

		if 'torrentkim' in top_url:
			self.worker = WorkerTorrentKim()
		elif 'tfreeca' in top_url:
			self.worker = WorkerTfreeca()
		elif 'tcorea' in top_url:
			self.worker = WorkerTocops()

	@staticmethod
	def print_log(files):
		f = open('output/log.txt', 'at')
		for file in files:
			f.write(file.file_name+'\n')
		f.close()

	def request_get(self, url):
		headers = {
			'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36',
			'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
			'Accept-Charset': 'utf-8,euc-kr;q=0.7,*;q=0.3',
			'Accept-Language': 'ko-KR,ko;q=0.9,en-US;q=0.8,en;q=0.7',
			'Connection': 'keep-alive',
		}

		proxy = self.proxy_handler.get_proxy()
		while True:
			try:
				resp = self.session.get(url, proxies=proxy, headers=headers, timeout=3)
			except Exception as e:
				self.proxy_handler.set_proxy_dead(proxy)
				proxy = self.proxy_handler.get_proxy()
				continue
			else:
				if resp.status_code != 200:
					self.proxy_handler.set_proxy_dead(proxy)
					proxy = self.proxy_handler.get_proxy()
					continue
				else:
					break

		return resp

	def crawl_list(self, url):
		Logger.log('checking page {}'.format(url))

		resp = self.request_get(url)
		soup = bs4.BeautifulSoup(resp.content.decode('utf8'), 'lxml')

		re_title = re.compile('|'.join(['(?P<key' + str(i) + '>' + video['keyword'] + ')' for i, video in enumerate(self.setting.settings['video'])]), re.I)
		re_episode = re.compile(r'[ .,]E([0-9]+)[ .,]', re.I)

		links = self.worker.crawl_list(url, soup, re_title, re_episode, self.setting)
		return links

	def crawl_downlink(self, page_link):
		Logger.log('searching content page : {}({}) : {}'.format(page_link.title, page_link.episode, page_link.url))

		resp = self.request_get(page_link.url)
		soup = bs4.BeautifulSoup(resp.content.decode('utf8'), 'lxml')

		links = self.worker.crawl_downlink(page_link, soup)
		return links

	def download_files(self, file_link):
		if file_link.episode in self.setting.downloaded[file_link.title]:
			return

		Logger.log("start download {}".format(file_link.file_name))

		try:
			resp = self.request_get(file_link.url)
			file_name = file_link.file_name
			with open(self.setting.settings['download_path'] + file_name, 'wb') as f:
				f.write(resp.content)

			self.setting.downloaded[file_link.title].append(file_link.episode)
			self.setting.save()

			Logger.log("downloaded {}".format(file_name))

		except Exception as e:
			Logger.log(e)

	def crawl_torrent(self):
		page_links = []
		for org_url in self.setting.settings['urls']:
			page = 1
			while page <= self.setting.settings['max_page']:
				url = org_url.replace('<page>', str(page))
				page_links += self.crawl_list(url)
				page += 1

		files = []
		for link in page_links:
			files += self.crawl_downlink(link)

		for file in files:
			self.download_files(file)

	def crawl(self):
		if Util.get_free_space() < 4*1024*1024:
			Logger.log('Disk space is less than 4GB. Aborted')
			return

		# self.test()

		Logger.log('Crawling start')
		self.crawl_torrent()
		Logger.log('Crawling finished')


class Sorter:
	@staticmethod
	def move_files():
		setting = Setting()
		if not 'file_download_path' in setting.settings or not 'file_move_path' in setting.settings:
			return

		file_list = os.listdir(setting.settings['file_download_path'])
		for filename in file_list:
			for video in setting.settings['video']:
				if video['title'] in filename:
					old_path = os.path.join(setting.settings['file_download_path'], filename)
					new_path = os.path.join(setting.settings['file_move_path'], video['title'] + '/' + filename)
					os.rename(old_path, new_path)