# https://bigdata-sk.tistory.com/10
from datetime import datetime, timedelta
import os
import pandas as pd
import re
import json
import sqlite3
import requests
from time import sleep
import time
from pandas_datareader import data as pdr

# 닐짜 형식으로 바뀐 this_date값을 확인 가능
# 읽어온 날짜 정보를 date형식으로 바꿀 일이 계속 생기므로 이 기능을 함수로 정의해줌.
# 함수명은 date_format()

class StockCrawler:
	header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'}

	historical_prices = None
	special_pattern = None
	fnGuideCrawler = None

	limit_page_count = 1000000
	START_DATE = None

	def __init__(self, START_DATE):
		self.historical_prices = dict()
		self.special_pattern = (
		'[', '!', '@', '#', '$', '%', '^', '&', '*', '(', ')', ',', '.', '?', '"', ':', ';', '{', '}', '|', '<', '>',
		']', '+', '-', '/', '=', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9')
		self.START_DATE = START_DATE
		return

	def clean_str(self, string):
		string = re.sub(r"\\", " ", string)
		string = re.sub(r"\'", " ", string)
		string = re.sub(r"\"", " ", string)
		string = re.sub(r"`", " ", string)
		string = re.sub(r"-", " ", string)
		string = re.sub(r"\(.*?\)", " ", string)
		string = re.sub(r"  ", " ", string)

		return string.strip().lower()

	def getStockInfo(self):
		#code_df = pd.read_html('http://kind.krx.co.kr/corpgeneral/corpList.do?method=download&searchType=13', header=0)[0]
		code_df = pd.read_html(requests.get('http://kind.krx.co.kr/corpgeneral/corpList.do?method=download&searchType=13', headers=self.header, timeout=30).text)[0]
		# code_df = pd.read_excel('../resources/stock/상장법인목록.xls')

		# 종목코드가 6자리이기 때문에 6자리를 맞춰주기 위해 설정해줌
		code_df.종목코드 = code_df.종목코드.map('{:06d}'.format)

		# 우리가 필요한 것은 회사명과 종목코드이기 때문에 필요없는 column들은 제외해준다.
		code_df = code_df[['회사명', '종목코드']]

		# 한글로된 컬럼명을 영어로 바꿔준다.
		code_df = code_df.rename(columns={'회사명': 'name', '종목코드': 'code'})
		###print (code_df.head())

		return code_df

	# 종목 이름을 입력하면 종목에 해당하는 코드를 불러와
	# 네이버 금융(http://finance.naver.com)에 넣어줌
	def get_url(self, item_name, code_df):
		code = code_df.query("name=='{}'".format(item_name))['code'].to_string(index=False).strip()
		url = 'http://finance.naver.com/item/sise_day.nhn?code={code}'.format(code=code.strip())

		return code, url

	def date_format(slef, d):
		d = str(d).replace('-', '.')
		#yyyy = int(d.split('.')[0])
		#mm = int(d.split('.')[1])
		#dd = int(d.split('.')[2])
		#this_date = dt.date(yyyy, mm, dd)
		return d

	def getCodeIndex(self, stocks, item_code):
		for i, stock in enumerate(stocks):
			if item_code == stock['CODE']:
				return i
		return -1

	def crawl_etf_stocks(self, inFileName):
		tableName = 'stock'
		conn = sqlite3.connect(inFileName)
		cursor = conn.cursor()

		# 테이블 생성
		cursor.execute("CREATE TABLE IF NOT EXISTS " + tableName + " (CODE text, NAME text, ymd text, close REAL, diff REAL, open REAL, high REAL, low REAL, volume REAL)")

		# 키 생성
		create_key = "CREATE INDEX IF NOT EXISTS " + tableName + "_idx on " + tableName + " (CODE, ymd) "
		cursor.execute(create_key)

		stocks = []
		stocks.append({"NAME": 'KODEX 코스닥150선물인버스', "CODE": "251340"})
		stocks.append({"NAME": 'KODEX 코스닥150 레버리지', "CODE": "233740"})
		stocks.append({"NAME": 'KODEX 200선물인버스2X', "CODE": "252670"})
		stocks.append({"NAME": 'KODEX 레버리지', "CODE": "122630"})
		stocks.append({"NAME": 'KODEX 인버스', "CODE": "114800"})
		stocks.append({"NAME": 'KODEX 중국본토CSI300', "CODE": "283580"})
		stocks.append({"NAME": 'KODEX 심천ChiNext(합성)', "CODE": "256750"})
		stocks.append({"NAME": 'KINDEX 블룸버그베트남VN30선물레버리지(H)', "CODE": "371130"})
		stocks.append({"NAME": 'KODEX 미국S&P바이오(합성)', "CODE": "185680"})
		stocks.append({"NAME": 'KODEX 미국S&P에너지(합성)', "CODE": "218420"})
		stocks.append({"NAME": 'KODEX 골드선물(H)', "CODE": "132030"})
		stocks.append({"NAME": 'KODEX 콩선물(H)', "CODE": "138920"})
		stocks.append({"NAME": 'KODEX 3대농산물선물(H)', "CODE": "271060"})
		stocks.append({"NAME": 'KODEX 건설', "CODE": "117700"})
		stocks.append({"NAME": 'KODEX 헬스케어', "CODE": "266420"})
		stocks.append({"NAME": 'KODEX 글로벌4차산업로보틱스(합성)', "CODE": "276990"})
		stocks.append({"NAME": 'KODEX 바이오', "CODE": "244580"})
		stocks.append({"NAME": 'KODEX 반도체', "CODE": "091160"})
		stocks.append({"NAME": 'KODEX 보험', "CODE": "140700"})
		stocks.append({"NAME": 'KODEX 필수소비재', "CODE": "266410"})
		stocks.append({"NAME": 'KODEX 2차전지산업', "CODE": "305720"})
		stocks.append({"NAME": 'KODEX 경기소비재', "CODE": "266390"})
		stocks.append({"NAME": 'KODEX 철강', "CODE": "117680"})
		stocks.append({"NAME": 'KODEX 에너지화학', "CODE": "117460"})
		stocks.append({"NAME": 'KODEX 은행', "CODE": "091170"})
		stocks.append({"NAME": 'TIGER 탄소효율그린뉴딜', "CODE": "376410"})

		start_time = time.time()
		for i, stock in enumerate(stocks):
			print (i, stock["NAME"], stock["CODE"], (time.time()-start_time), "s")
			start_time = time.time()
			cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (stock["CODE"],))
			result = cursor.fetchone()
			ymd = self.START_DATE
			if result is not None:
				ymd = result[0]

			stock_data = self.crawl_specific_stock(stock["CODE"], ymd)

			for item in stock_data:
				cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=? and ymd=?', (stock["CODE"],item['ymd'],))
				result = cursor.fetchone()
				if result == None:
					cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, ymd, close, diff, open, high, low, volume) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?)", (stock["CODE"], stock["NAME"], item['ymd'], item['close'], item['diff'], item['open'], item['high'], item['low'], item['volume']))
				#else:
				#	cursor.execute("UPDATE " + tableName + " SET close=?, diff=?, open=?, high=?, low=?, volume=? WHERE CODE=? and ymd=?", (item['close'], item['diff'], item['open'], item['high'], item['low'], item['volume'], stock["CODE"], item['ymd']))

			sleep(0.05)
		conn.commit()
		cursor.close()
		conn.close()
		return

	def crawl_stocks(self, inFileName):
		tableName = 'stock'
		conn = sqlite3.connect(inFileName)
		cursor = conn.cursor()

		# 테이블 생성
		cursor.execute("CREATE TABLE IF NOT EXISTS " + tableName + " (CODE text, NAME text, ymd text, close REAL, diff REAL, open REAL, high REAL, low REAL, volume REAL)")

		# 키 생성
		create_key = "CREATE INDEX IF NOT EXISTS " + tableName + "_idx on " + tableName + " (CODE, ymd) "
		cursor.execute(create_key)

		conn.commit()
		cursor.close()
		conn.close()

		code_df = self.getStockInfo()
		items = code_df.values

		start_time = time.time()
		idx = 0
		for item in items:
			idx += 1

			conn = sqlite3.connect(inFileName)
			cursor = conn.cursor()

			item_name = item[0]
			item_code = item[1]

			cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (item_code,))
			result = cursor.fetchone()
			stock = {"CODE": item_code, "NAME": item_name}

			#ymd = (datetime.today() - timedelta(days=300)).strftime('%Y-%m-%d')
			ymd = self.START_DATE.replace(".", "-")
			if result is not None:
				ymd = result[0]

			stock_data = self.crawl_specific_stock(item_code, ymd)

			for item in stock_data:
				cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=? and ymd=?', (stock["CODE"],item['ymd'],))
				result = cursor.fetchone()
				if result == None:
					cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, ymd, close, diff, open, high, low, volume) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?)", (stock["CODE"], stock["NAME"], item['ymd'], item['close'], item['diff'], item['open'], item['high'], item['low'], item['volume']))
				#else:
				#	cursor.execute("UPDATE " + tableName + " SET close=?, diff=?, open=?, high=?, low=?, volume=? WHERE CODE=? and ymd=?", (item['close'], item['diff'], item['open'], item['high'], item['low'], item['volume'], stock["CODE"], item['ymd']))

			conn.commit()
			cursor.close()
			conn.close()
			print(idx, item_name, item_code, (time.time() - start_time), "s")

			start_time = time.time()
			sleep(0.05)

		return

	def crawl_special_stocks(self, inFileName):
		tableName = 'stock'
		conn = sqlite3.connect(inFileName)
		cursor = conn.cursor()

		# 테이블 생성
		cursor.execute("CREATE TABLE IF NOT EXISTS " + tableName + " (CODE text, NAME text, ymd text, close REAL, diff REAL, open REAL, high REAL, low REAL, volume REAL)")

		# 키 생성
		create_key = "CREATE INDEX IF NOT EXISTS " + tableName + "_idx on " + tableName + " (CODE, ymd) "
		cursor.execute(create_key)

		conn.commit()
		cursor.close()
		conn.close()

		start_time = time.time()

		pd.options.display.float_format = '{:.4f}'.format
		pd.set_option('display.max_columns', None)

		special_stocks = {
			'^KS11': 'Kospi',
			'^KQ11': 'Kosdak',
			'^DJI': 'Dow Johns',
			'^GSPC': 'S&P 500',
			'^IXIC': 'Nasdaq',
			'^NDX': 'NASDAQ 100',

			'SQQQ': 'ProShares UltraPro Short QQQ',
			'TQQQ': 'ProShares UltraPro QQQ',
			'SCO': 'ProShares UltraShort Bloomberg Crude Oil',
			'UCO': 'ProShares Ultra Bloomberg Crude Oil',
			'GLL': 'ProShares UltraShort Gold',
			'UGL': 'ProShares Ultra Gold',
			'SOXS': 'Direxion Daily Semiconductor Bear -3X Shares',
			'SOXL': 'Direxion Daily Semiconductor Bull 3X Shares',
			'FNGD': 'MicroSectors™ FANG+™ Index -3X Inverse Leveraged ETN',
			'FNGU': 'MicroSectors™ FANG+™ Index 3X Leveraged ETN',

			'AAPL': 'Apple',
			'MSFT': 'Microsoft',
			'GOOG': 'Alphabet C',
			'AMZN': 'Amazon.com',
			'AVGO': 'Broadcom',
			'FB': 'Meta Platforms',
			'NVDA': 'NVIDIA',
			'UNH': 'UnitedHealth',
			'TSM': 'Taiwan Semiconductor',
			'JNJ': 'Johnson & Johnson (JNJ)',
			'TCTZF': 'Tencent Holdings',
			'V': 'Visa A',
			'WMT': 'Walmart',
			'XOM': 'Exxon Mobil',
			'JPM': 'JPMorgan',
			'MA': 'Mastercard',
			'CVX': 'Chevron Corp',
			'HD': 'Home Depot',
			'BAC': 'Bank of America',
			'KO': 'Coca-Cola',
			'COST': 'Costco',
			'DIS': 'Walt Disney',
			'VZ': 'Verizon',
			'CSCO':	'Cisco',
			'ORCL': 'Oracle',
			'NKE': 'Nike',
			'ACN': 'Accenture',
			'ADBE': 'Adobe',
			'CRM': 'Salesforce.com',
			'INTC': 'Intel',
			'QCOM': 'Qualcomm',
			'AMD': 'AMD',
			'MS': 'Morgan Stanley',
			'T': 'AT&T',
			'HON': 'Honeywell',
			'IBM': 'IBM',
			'DQ': 'Daqo New Energy Corp ADR',
			'EBAY': 'eBay Inc',
			'NTAP': 'NetApp Inc',
			'ASML': 'ASML Holding NV ADR',
			'BABA': 'Alibaba Group Holdings Ltd ADR'}

		conn = sqlite3.connect(inFileName)
		cursor = conn.cursor()

		us_sotck_data = {}
		for ticker in special_stocks:

			cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (ticker,))

			result = cursor.fetchone()
			if result is not None:
				start_day = result[0].replace(".", "-")
				end_day = datetime.today().strftime('%Y-%m-%d')
			else:
				#start_day = pd.to_datetime('2017-01-01')
				start_day = self.START_DATE.replace(".", "-")
				end_day = datetime.today().strftime('%Y-%m-%d')

			try:
				data = pdr.get_data_yahoo(ticker, start_day, end_day)
				us_sotck_data[ticker] = {
					'close': data['Close'].to_dict(),
					'open': data['Open'].to_dict(),
					'high': data['High'].to_dict(),
					'low': data['Low'].to_dict(),
					'volume': data['Volume'].to_dict()
				}
			except:
				print(ticker)
				continue

		cursor.close()
		conn.close()

		dateList = list(us_sotck_data['SQQQ']['close'])
		for idx, item_code in enumerate(us_sotck_data):
			stock_data = []
			stock = us_sotck_data[item_code]
			for i, ymd in enumerate(dateList):
				if i > 0:
					if ymd in stock['close'] and dateList[i-1] in stock['close']:
						diff = stock['close'][ymd] - stock['close'][dateList[i-1]]
					else:
						continue
				else:
					if ymd in stock['close']:
						diff = stock['close'][ymd]
					else:
						continue

				stock_data.append({
					'CODE':item_code, 'NAME':special_stocks[item_code], 'ymd': ymd.strftime('%Y.%m.%d'),
					'close': round(stock['close'][ymd], 2), 'diff': round(diff, 2), 'open': round(stock['open'][ymd], 2),
					'high': round(stock['high'][ymd], 2), 'low': round(stock['low'][ymd], 2), 'volume': stock['volume'][ymd]
				})

			stock_data = reversed(stock_data)

			conn = sqlite3.connect(inFileName)
			cursor = conn.cursor()
			for item in stock_data:
				cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=? and ymd=?', (item["CODE"],item['ymd'],))
				result = cursor.fetchone()
				if result == None:
					cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, ymd, close, diff, open, high, low, volume) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?)", (item["CODE"], item["NAME"], item['ymd'], item['close'], item['diff'], item['open'], item['high'], item['low'], item['volume']))
				#else:
				#	cursor.execute("UPDATE " + tableName + " SET close=?, diff=?, open=?, high=?, low=?, volume=? WHERE CODE=? and ymd=?", (item['close'], item['diff'], item['open'], item['high'], item['low'], item['volume'], stock["CODE"], item['ymd']))

			conn.commit()
			cursor.close()
			conn.close()
			print(idx, item_code, special_stocks[item_code], (time.time() - start_time), "s")

			start_time = time.time()
			sleep(0.05)
		return


	def get_data(self, code, lastDay):
		url = 'http://finance.naver.com/item/sise_day.nhn?code={code}'.format(code=code.strip())

		stock = []
		# 일자 데이터를 담을 df라는 DataFrame 정의
		df = pd.DataFrame()

		date_set = set()
		lastPage = False
		# 1페이지에서 1000페이지의 데이터만 가져오기
		for page in range(1, self.limit_page_count):
			# 최근 상장 기업의 마지막 반복되는 페이지를 제외시킨다.
			pg_url = '{url}&page={page}'.format(url=url, page=page)
			#html = pd.read_html(pg_url, header=0)
			html = None
			while True:
				try:
					html = pd.read_html(requests.get(pg_url, headers=self.header, timeout=30).text)
					sleep(0.5)
					break
				except:
					print(pg_url)
					if page > 200:
						break
					continue

			for date in html[0].날짜.values:
				if type(date) is str:
					if date in date_set:
						lastPage = True
						break
					date_set.add(date)

					if date == lastDay:
						lastPage = True
						df = pd.concat((df, html[0]), ignore_index=True)
						break
			df = pd.concat((df, html[0]), ignore_index=True)
			df = df.dropna()
			if (lastPage) or (len(df) < 1) or ("날짜" not in df) or (df.날짜[1]==''):
				print("\t- lastpage:", page)
				break

		# df.dropna()를 이용해 결측값 있는 행 제거
		df = df.dropna()

		# 상위 5개 데이터 확인하기
		###print (df.head())

		# 한글로 된 컬럼명을 영어로 바꿔줌
		df = df.rename(columns={'날짜': 'date', '종가': 'close', '전일비': 'diff', '시가': 'open', '고가': 'high', '저가': 'low', '거래량': 'volume'})

		# 데이터의 타입을 int형으로 바꿔줌
		df[['close', 'diff', 'open', 'high', 'low', 'volume']] = df[['close', 'diff', 'open', 'high', 'low', 'volume']].astype(int)

		for values in df.values:
			day = str(values[0]).split(' ')[0]
			if lastDay == day:
				break
			stock.append({
				"ymd": day,
				df.columns[1]: values[1],
				df.columns[2]: values[2],
				df.columns[3]: values[3],
				df.columns[4]: values[4],
				df.columns[5]: values[5],
				df.columns[6]: values[6],
			})

		# stock = sorted(stock, key=lambda x: x['ymd'], reverse=True)
		stock = sorted(stock, key=lambda x: x['ymd'])
		return stock

	def crawl_specific_stock(self, code, ymd):
		# 데이터 수집
		stock = self.get_data(code, ymd)

		# 이동 평균 계산
		#self.get_moving_avg(stock)

		return stock

	def update(self, inFileName, outFileName):
		"""
		Full json 데이터를 db에 import 시킴
		inFileName = PROJECT_HOME + '/resources/stock.json.full'
		outFileName = PROJECT_HOME + '/resources/stock.db'
		crawler = StockCrawler()
		crawler.update(inFileName, outFileName)

		:param inFileName:
		:param outFileName:
		:return:
		"""
		tableName = 'stock'
		conn = sqlite3.connect(outFileName, isolation_level=None)
		cursor = conn.cursor()
		cursor.execute("CREATE TABLE IF NOT EXISTS " + tableName + " (CODE text PRIMARY KEY, NAME text, PRICE text, MACD text, STOCHASTIC text, ICHIMOKU text, RSI text, BOLINGERBAND text)")

		idx = 0
		inFp = open(inFileName, 'r')
		for line in inFp.readlines():
			if line:
				idx += 1
				stock = json.loads(line)
				print(idx, stock["CODE"], stock["NAME"])

				text = json.dumps(stock["PRICE"], ensure_ascii=False)

				cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=?', (stock["CODE"],))
				result = cursor.fetchone()
				if result == None:
					cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, PRICE) VALUES(?, ?, ?)", (stock["CODE"], stock["NAME"], text))
				else:
					cursor.execute("UPDATE " + tableName + " SET PRICE=? WHERE CODE=?", (text, stock["CODE"]))

		return


	def saveIndex(self, code, inFileName, outFileName):
		tableName = 'stock'
		conn = sqlite3.connect(outFileName)
		cursor = conn.cursor()
		cursor.execute("CREATE TABLE IF NOT EXISTS " + tableName + " (CODE text PRIMARY KEY, NAME text, PRICE text, MACD text, STOCHASTIC text, ICHIMOKU text, RSI text, BOLINGERBAND text)")

		stock = {"NAME": code, "CODE": code}

		lastDay = ""
		cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=?', (stock["CODE"],))
		result = cursor.fetchone()
		if result is not None:
			stock["PRICE"] = json.loads(result[2])
			lastDay = stock["PRICE"][len(stock["PRICE"]) - 1]["DATE"]

		with open(inFileName, "r", encoding="utf-8") as inFp:
			for line in inFp:
				line = line.strip()
				if line[0] == "#":
					continue

				arr = line.split("\t")
				if arr[0] == lastDay:
					break

				price = {"DATE": arr[0], "close": float(arr[1]), "diff": float(arr[6].replace("%", "")), "open": float(arr[2]), "high": float(arr[3]), "low": float(arr[4]), "volume": 0}
				price['avg3'] = 0
				price['avg5'] = 0
				price['avg7'] = 0
				price['avg10'] = 0
				price['avg20'] = 0
				price['avg30'] = 0
				price['avg60'] = 0
				price['avg90'] = 0
				price['avg100'] = 0
				price['avg120'] = 0
				price['avg150'] = 0
				price['avg180'] = 0
				price['avg200'] = 0
				price['avg240'] = 0
				stock["PRICE"].append(price)

		stock["PRICE"] = sorted(stock["PRICE"], key=lambda x: x['DATE'])
		# self.get_moving_avg(stock)

		text = json.dumps(stock['PRICE'], ensure_ascii=False)

		cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=?', (stock["CODE"],))
		result = cursor.fetchone()
		if result == None:
			cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, PRICE, MACD, STOCHASTIC, ICHIMOKU, RSI) VALUES(?, ?, ?, ?, ?, ?, ?)", (stock["CODE"], stock["NAME"], text, "[{}]", "[{}]", "[{}]", "[{}]"))
		else:
			cursor.execute("UPDATE " + tableName + " SET PRICE=?, MACD=?, STOCHASTIC=?, ICHIMOKU=?, RSI=? WHERE CODE=?", (text, "[{}]", "[{}]", "[{}]", "[{}]", stock["CODE"]))

		conn.commit()
		cursor.close()
		conn.close()
		return

if __name__ == "__main__":
	stockCrawler = StockCrawler()

	PROJECT_HOME = os.path.join(os.path.dirname(os.path.join(os.path.dirname(os.path.join(os.path.dirname(os.path.join(os.path.dirname(__file__))))))))
	stockFileName = PROJECT_HOME + '/resources/stock.db'
	stockCrawler.crawl_us_sotck_datas(stockFileName)