import json
import datetime
import requests
import sqlite3

import pandas as pd

class MetaCrawler:
    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'}
    limit_page_count = 10000

    def __init__(self):
        return

    # 참고) http://blog.naver.com/PostView.nhn?blogId=koko8624&logNo=221288761509
    def crawl_meterials(self, inFileName):
        tableName = 'meta_1'
        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, rate REAL)")

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

        inputs = []
        inputs.append( {'NAME':'WTI', 'CODE':'OIL_CL', 'URL':'http://finance.naver.com/marketindex/worldDailyQuote.nhn?marketindexCd=OIL_CL&fdtc=2'} ) # WTI
        inputs.append( {'NAME':'GOLD', 'CODE':'CMDT_GC', 'URL':'http://finance.naver.com/marketindex/worldDailyQuote.nhn?marketindexCd=CMDT_GC&fdtc=2'} ) # 국제 금
        inputs.append({'NAME': 'COPPER', 'CODE': 'CMDT_CDY','URL': 'http://finance.naver.com/marketindex/worldDailyQuote.nhn?marketindexCd=CMDT_CDY&fdtc=2'})  # 구리
        inputs.append({'NAME': 'NATURALGAS', 'CODE': 'CMDT_NG','URL': 'http://finance.naver.com/marketindex/worldDailyQuote.nhn?marketindexCd=CMDT_NG&fdtc=2'})  # 천연가스
        inputs.append({'NAME': 'CORN', 'CODE': 'CMDT_C','URL': 'http://finance.naver.com/marketindex/worldDailyQuote.nhn?marketindexCd=CMDT_C&fdtc=2'})  # 국제 옥수수
        inputs.append({'NAME': 'SOYBEAN', 'CODE': 'CMDT_S','URL': 'http://finance.naver.com/marketindex/worldDailyQuote.nhn?marketindexCd=CMDT_S&fdtc=2'})  # 국제 대두

        for i in range(len(inputs)):
            input = inputs[i]
            NAME = input['NAME']
            CODE = input['CODE']

            cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (CODE,))
            result = cursor.fetchone()
            if result == None:
                lastDay = "1900.01.01"
            else:
                lastDay = result[0]

            finish = False
            for i in range(1, self.limit_page_count):
                #html = pd.read_html(input['URL'] + '&page=%s' % i, header=0)
                html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header).text)

                # 마지막 페이지 까지 받기
                if len(html[0].날짜.values) <= 1:
                    break

                for j in range(0, len(html[0].values)):
                    item = html[0].values[j]

                    if item[0] <= lastDay:
                        finish = True
                        break
                    ymd = item[0] # 날짜
                    close = item[1] # 종가
                    diff = item[2] # 전일대비
                    rate = item[3] # 등락율

                    cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=? and ymd=?', (CODE,ymd,))
                    result = cursor.fetchone()
                    if result == None:
                        cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, ymd, close, diff, rate) VALUES(?, ?, ?, ?, ?, ?)", (CODE, NAME, ymd, close, diff, rate))
                    #else:
                    #    cursor.execute("UPDATE " + tableName + " SET close=?, diff=?, rate=? WHERE CODE=? and ymd=?", (close, diff, rate, CODE, ymd))

                    print(CODE, NAME, ymd)
                if finish:
                    break

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

    # 참고) http://blog.naver.com/PostView.nhn?blogId=koko8624&logNo=221288761509
    def crawl_exchange(self, inFileName):
        tableName = 'meta_1'
        conn = sqlite3.connect(inFileName)
        cursor = conn.cursor()

        # 테이블 생성
        cursor.execute("CREATE TABLE IF NOT EXISTS "+tableName+" (CODE text, NAME text, ymd text, price REAL, diff REAL, cash_buy REAL, cash_sell REAL, transfer_buy REAL, transfer_sell REAL)")

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

        inputs = []
        inputs.append( {'NAME':'USD', 'CODE':'FX_USDKRW', 'URL':'http://finance.naver.com/marketindex/exchangeDailyQuote.nhn?marketindexCd=FX_USDKRW'} ) # 미국 USD
        inputs.append( {'NAME':'JPY', 'CODE':'FX_JPYKRW', 'URL':'http://finance.naver.com/marketindex/exchangeDailyQuote.nhn?marketindexCd=FX_JPYKRW'} ) # 일본 JPY
        inputs.append( {'NAME':'EUR', 'CODE':'FX_EURKRW', 'URL':'http://finance.naver.com/marketindex/exchangeDailyQuote.nhn?marketindexCd=FX_EURKRW'} ) # 유럽연합 EUR'
        inputs.append( {'NAME':'CNY', 'CODE':'FX_CNYKRW', 'URL':'http://finance.naver.com/marketindex/exchangeDailyQuote.nhn?marketindexCd=FX_CNYKRW'} ) # 중국 CNY

        for i in range(len(inputs)):
            input = inputs[i]
            NAME = input['NAME']
            CODE = input['CODE']

            cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (CODE,))
            result = cursor.fetchone()
            if result == None:
                lastDay = "1900.01.01"
            else:
                lastDay = result[0]

            finish = False
            for i in range(1, self.limit_page_count):
                #html = pd.read_html(input['URL'] + '&page=%s' % i, header=0)
                html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header).text)

                # 마지막 페이지 까지 받기
                if len(html[0].날짜.values) <= 1:
                    break

                for j in range(0, len(html[0].values)):
                    item = html[0].values[j]
                    if input['NAME'] in ('USD', 'JPY', 'EUR', 'CNY'):
                        if item[0] <= lastDay:
                            finish = True
                            break
                        ymd = item[0] # 날짜
                        price = item[1] # 매매기준율
                        diff = item[2] # 전일대비
                        cash_buy = item[3]  # 현찰 사실 때
                        cash_sell = item[4]  # 현찰 파실 때
                        transfer_buy = item[5]  # 송금 사실 때
                        transfer_sell = item[6]  # 송금 파실 때

                        cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=? and ymd=?', (CODE,ymd,))
                        result = cursor.fetchone()
                        if result == None:
                            cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, ymd, price, diff, cash_buy, cash_sell, transfer_buy, transfer_sell) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?)", (CODE, NAME, ymd, price, diff, cash_buy, cash_sell, transfer_buy, transfer_sell))
                        #else:
                        #    cursor.execute("UPDATE " + tableName + " SET price=?, diff=?, cash_buy=?, cash_sell=?, transfer_buy=?, transfer_sell=? WHERE CODE=? and ymd=?", (price, diff, cash_buy, cash_sell, transfer_buy, transfer_sell, CODE, ymd))

                        print(CODE, NAME, ymd)
                if finish:
                    break

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

    # 투자자별 매매동향 (Trading_Trend) 크롤링
    # (pri, 개인)
    # (for, 외국인)
    # (ins, 기관합)
    # (ins0, 금융투자)
    # (ins1, 보험)
    # (ins2, 투신 (사모))
    # (ins3, 은행)
    # (ins4, 기타금융기관)
    # (ins5, 연기금 등)
    # (cor, 기타법인)
    # 참고) http://blog.naver.com/PostView.nhn?blogId=koko8624&logNo=221289696771&parentCategoryNo=&categoryNo=&viewDate=&isShowPopularPosts=false&from=postView
    def crawl_trading_trend(self, inFileName):
        tableName = 'meta_2'
        conn = sqlite3.connect(inFileName)
        cursor = conn.cursor()

        # 테이블 생성
        cursor.execute("CREATE TABLE IF NOT EXISTS "+tableName+" (ymd text PRIMARY KEY, pri integer, fori integer, ins integer, ins0 integer, ins1 integer, ins2 integer, ins3 integer, ins4 integer, ins5 integer, cor integer)")

        cursor.execute('SELECT ymd FROM ' + tableName + ' order by ymd desc')
        result = cursor.fetchone()
        if result == None:
            lastDay = "1900.01.01"
        else:
            lastDay = result[0]

        today = datetime.datetime.now().strftime("%Y%m%d")
        url = 'http://finance.naver.com/sise/investorDealTrendDay.nhn?bizdate='+today+'&sosok=&page='

        previousDay = ""
        finish = False
        for i in range(1, self.limit_page_count):
            #html = pd.read_html(url + str(i), header=0)
            html = pd.read_html(requests.get(url + str(i), headers=self.header).text)

            # 마지막 페이지 까지 받기
            if len(html[0].날짜.values) <= 2:
                break

            for j in range(0, len(html[0].values)):
                item = html[0].values[j]
                if str(item[0]) == "nan":
                    continue
                if "20" + item[0] <= lastDay or item[0] == previousDay:
                    finish = True
                    break
                ymd = "20"+item[0]
                pri = item[1] # 개인
                fori = item[2] # 외국인
                ins = item[3] # 기관합
                ins0 = item[4] # 금융투자
                ins1 = item[5] # 보험
                ins2 = item[6] # 투신 (사모)
                ins3 = item[7] # 은행
                ins4 = item[8] # 기타금융기관
                ins5 = item[9] # 연기금 등
                cor = item[10] # 기타법인

                cursor.execute('SELECT * FROM ' + tableName + ' WHERE ymd=?', (ymd,))
                result = cursor.fetchone()
                if result == None:
                    cursor.execute("INSERT INTO " + tableName + "(ymd, pri, fori, ins, ins0, ins1, ins2, ins3, ins4, ins5, cor) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", (ymd, pri, fori, ins, ins0, ins1, ins2, ins3, ins4, ins5, cor))
                #else:
                #    cursor.execute("UPDATE " + tableName + " SET pri=?, fori=?, ins=?, ins0=?, ins1=?, ins2=?, ins3=?, ins4=?, ins5=?, cor=? WHERE ymd=?", (pri, fori, ins, ins0, ins1, ins2, ins3, ins4, ins5, cor, ymd))

                print ("20"+item[0])
            previousDay = html[0].values[2][0]
            if finish:
                break

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

        return

    # 증시자금동향 (신용잔고, 펀드자금 잔고) 크롤링
    # 참고) http://blog.naver.com/PostView.nhn?blogId=koko8624&logNo=221290138187&parentCategoryNo=&categoryNo=&viewDate=&isShowPopularPosts=false&from=postView
    def crawl_money_trend(self, inFileName):
        tableName = 'meta_3'
        conn = sqlite3.connect(inFileName)
        cursor = conn.cursor()
        cursor.execute("CREATE TABLE IF NOT EXISTS "+tableName+" (ymd text, dep1_1 integer, dep1_2 integer, dep2_1 integer, dep2_2 integer, dep3_1 integer, dep3_2 integer, dep4_1 integer, dep4_2 integer, dep5_1 integer, dep5_2 integer)")

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

        cursor.execute('SELECT ymd FROM ' + tableName + ' order by ymd desc')
        result = cursor.fetchone()
        if result == None:
            lastDay = "1900.01.01"
        else:
            lastDay = result[0]
        previousDay = ""

        url = 'http://finance.naver.com/sise/sise_deposit.nhn?&page='

        finish = False
        for i in range(1, self.limit_page_count):
            #html = pd.read_html(url + str(i), header=0, encoding='euc-kr')
            html = pd.read_html(requests.get(url + str(i), headers=self.header).text, encoding='euc-kr')

            # 마지막 페이지 까지 받기
            if len(html[0].날짜.values) <= 10:
                break
            for j in range(0, len(html[0].values)):
                item = html[0].values[j]
                if str(item[0]) == "nan":
                    continue
                if "20"+item[0] <= lastDay or item[0] == previousDay:
                    finish = True
                    break
                meta = {
                    "ymd": "20"+item[0],
                    "dep1_1": item[1], # 고객예탁금 누적
                    "dep1_2": item[2], # 고객예탁금 당일
                    "dep2_1": item[3], # 신용잔고 누적
                    "dep2_2": item[4], # 신용잔고 당일
                    "dep3_1": item[5], # 주식형펀드 누적
                    "dep3_2": item[6], # 주식형펀드 당일
                    "dep4_1": item[7], # 혼합형펀드 누적
                    "dep4_2": item[8], # 혼합형펀드 당일
                    "dep5_1": item[9], # 채권형펀드 누적
                    "dep5_2": item[10]} # 채권형펀드 당일

                cursor.execute('SELECT * FROM ' + tableName + ' WHERE ymd=?', (meta["ymd"],))
                result = cursor.fetchone()
                if result == None:
                    cursor.execute("INSERT INTO " + tableName + "(ymd, dep1_1, dep1_2, dep2_1, dep2_2, dep3_1, dep3_2, dep4_1, dep4_2, dep5_1, dep5_2) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", (meta["ymd"], meta["dep1_1"], meta["dep1_2"], meta["dep2_1"], meta["dep2_2"], meta["dep3_1"], meta["dep3_2"], meta["dep4_1"], meta["dep4_2"], meta["dep5_1"], meta["dep5_2"]))
                #else:
                #    cursor.execute("UPDATE " + tableName + " SET dep1_1=?, dep1_2=?, dep2_1=?, dep2_2=?, dep3_1=?, dep3_2=?, dep4_1=?, dep4_2=?, dep5_1=?, dep5_2=? WHERE ymd=?", (meta["dep1_1"], meta["dep1_2"], meta["dep2_1"], meta["dep2_2"], meta["dep3_1"], meta["dep3_2"], meta["dep4_1"], meta["dep4_2"], meta["dep5_1"], meta["dep5_2"], meta["ymd"]))

                print("20"+item[0])
            if finish:
                break
            previousDay = html[0].values[2][0]

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

    # 국내 시장금리 크롤링
    # 참고) http://blog.naver.com/PostView.nhn?blogId=koko8624&logNo=221292348073&parentCategoryNo=&categoryNo=&viewDate=&isShowPopularPosts=false&from=postView
    def crawl_interest_rates(self, inFileName):
        tableName = 'meta_4'
        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, rate REAL)")

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

        inputs = []
        inputs.append({'NAME': '91일 CD금리', 'CODE': 'IRR_CD91', 'URL': 'http://finance.naver.com/marketindex/interestDailyQuote.nhn?marketindexCd=IRR_CD91'})
        inputs.append({'NAME': '콜금리', 'CODE': 'IRR_CALL', 'URL': 'http://finance.naver.com/marketindex/interestDailyQuote.nhn?marketindexCd=IRR_CALL'})
        inputs.append({'NAME': '국고채(3년)', 'CODE': 'IRR_GOVT03Y', 'URL': 'http://finance.naver.com/marketindex/interestDailyQuote.nhn?marketindexCd=IRR_GOVT03Y'})
        inputs.append({'NAME': '회사채(3년)', 'CODE': 'IRR_CORP03Y', 'URL': 'http://finance.naver.com/marketindex/interestDailyQuote.nhn?marketindexCd=IRR_CORP03Y'})

        for i in range(len(inputs)):
            input = inputs[i]
            NAME = input['NAME']
            CODE = input['CODE']

            cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (CODE,))
            result = cursor.fetchone()
            if result == None:
                lastDay = "1900.01.01"
            else:
                lastDay = result[0]

            finish = False
            for i in range(1, self.limit_page_count):
                #html = pd.read_html(input['URL'] + '&page=%s' % i, header=0)
                html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header).text)

                ymd, close, diff, rate = "", 0.0, 0.0, 0.0
                # 마지막 페이지 까지 받기
                if len(html[0].날짜.values) <= 1:
                    break

                for j in range(len(html[0].values)):
                    item = html[0].values[j]
                    if str(item[0]) == "nan":
                        continue
                    if item[0] <= lastDay:
                        finish = True
                        break

                    ymd = item[0]
                    close = item[1] # 종가
                    diff = item[2] # 전일대비
                    rate = item[3] # 등락율

                    cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=? and ymd=?', (CODE, ymd,))
                    result = cursor.fetchone()
                    if result == None:
                        cursor.execute("INSERT INTO " + tableName + "(CODE, NAME, ymd, close, diff, rate) VALUES(?, ?, ?, ?, ?, ?)", (CODE, NAME, ymd, close, diff, rate))
                    #else:
                    #    cursor.execute("UPDATE " + tableName + " SET close=?, diff=?, rate=? WHERE CODE=? and ymd=?", (close, diff, rate, CODE, ymd))

                if finish:
                    break
                print(NAME + " / " + ymd)

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