410 lines
13 KiB
Python
410 lines
13 KiB
Python
# https://bigdata-sk.tistory.com/10
|
|
|
|
import pandas as pd
|
|
import re
|
|
import json
|
|
import sqlite3
|
|
import requests
|
|
|
|
class Queue(object):
|
|
def __init__(self, max):
|
|
self.queue = []
|
|
self.max = max
|
|
|
|
def dequeue(self):
|
|
length = len(self.queue)
|
|
if length == 0 or length < self.max:
|
|
return -1
|
|
return self.queue.pop(0)
|
|
|
|
def enqueue(self, n):
|
|
length = len(self.queue)
|
|
if length == self.max:
|
|
self.dequeue()
|
|
|
|
self.queue.append(n)
|
|
pass
|
|
|
|
def sum(self):
|
|
sum = 0
|
|
for item in self.queue:
|
|
sum += item
|
|
return sum
|
|
|
|
def avg(self):
|
|
length = len(self.queue)
|
|
total = self.sum()
|
|
return round(total / length)
|
|
|
|
def print(self):
|
|
print(self.sum(), self.queue)
|
|
|
|
# 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 = 10000
|
|
|
|
def __init__(self):
|
|
self.historical_prices = dict()
|
|
self.special_pattern = (
|
|
'[', '!', '@', '#', '$', '%', '^', '&', '*', '(', ')', ',', '.', '?', '"', ':', ';', '{', '}', '|', '<', '>',
|
|
']', '+', '-', '/', '=', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9')
|
|
|
|
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).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()
|
|
cursor.execute("CREATE TABLE IF NOT EXISTS " + tableName + " (CODE text PRIMARY KEY, NAME text, PRICE text)")
|
|
|
|
stocks = []
|
|
stocks.append({"NAME": 'KODEX 코스닥150선물인버스', "CODE": "251340", "PRICE": []})
|
|
stocks.append({"NAME": 'KODEX 코스닥150 레버리지', "CODE": "233740", "PRICE": []})
|
|
stocks.append({"NAME": 'KODEX 200선물인버스2X', "CODE": "252670", "PRICE": []})
|
|
stocks.append({"NAME": 'KODEX 레버리지', "CODE": "122630", "PRICE": []})
|
|
stocks.append({"NAME": 'KODEX 골드선물(H)', "CODE": "132030", "PRICE": []})
|
|
|
|
for stock in stocks:
|
|
cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=?', (stock["CODE"],))
|
|
result = cursor.fetchone()
|
|
if result != None:
|
|
stock["PRICE"] = json.loads(result[2])
|
|
|
|
self.crawl_specific_stock(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) VALUES(?, ?, ?)", (stock["CODE"], stock["NAME"], text))
|
|
else:
|
|
cursor.execute("UPDATE " + tableName + " SET PRICE=? WHERE CODE=?", (text, stock["CODE"]))
|
|
|
|
conn.commit()
|
|
cursor.close()
|
|
conn.close()
|
|
return
|
|
|
|
def crawl_stocks(self, inFileName):
|
|
tableName = 'stock'
|
|
conn = sqlite3.connect(inFileName)
|
|
cursor = conn.cursor()
|
|
cursor.execute("CREATE TABLE IF NOT EXISTS " + tableName + " (CODE text PRIMARY KEY, NAME text, PRICE text)")
|
|
|
|
code_df = self.getStockInfo()
|
|
items = code_df.values
|
|
|
|
idx = 0
|
|
for item in items:
|
|
idx += 1
|
|
|
|
item_name = item[0]
|
|
item_code = item[1]
|
|
print(idx, item_name, item_code)
|
|
|
|
cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=?', (item_code,))
|
|
result = cursor.fetchone()
|
|
stock = {"CODE": item_code, "NAME": item_name, "PRICE": []}
|
|
if result != None:
|
|
stock["PRICE"] = json.loads(result[2])
|
|
|
|
self.crawl_specific_stock(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) VALUES(?, ?, ?)", (stock["CODE"], stock["NAME"], text))
|
|
else:
|
|
cursor.execute("UPDATE " + tableName + " SET PRICE=? WHERE CODE=?", (text, stock["CODE"]))
|
|
|
|
conn.commit()
|
|
cursor.close()
|
|
conn.close()
|
|
return
|
|
|
|
|
|
def get_data(self, stock):
|
|
url = 'http://finance.naver.com/item/sise_day.nhn?code={code}'.format(code=stock['CODE'].strip())
|
|
|
|
# 일자 데이터를 담을 df라는 DataFrame 정의
|
|
df = pd.DataFrame()
|
|
|
|
lastDay = ""
|
|
if len(stock) > 0 and len(stock["PRICE"]) - 1 > 0:
|
|
lastDay = stock["PRICE"][len(stock["PRICE"]) - 1]["DATE"].replace("-", ".")
|
|
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 = pd.read_html(requests.get(pg_url, headers=self.header).text)
|
|
count = 0
|
|
for date in html[0].날짜.values:
|
|
if type(date) is str:
|
|
count += 1
|
|
if date == lastDay:
|
|
lastPage = True
|
|
df = df.append(html[0], ignore_index=True)
|
|
break
|
|
if count == 10:
|
|
df = df.append(html[0], ignore_index=True)
|
|
else:
|
|
if lastPage == False:
|
|
df = df.append(html[0], ignore_index=True)
|
|
lastPage = True
|
|
else:
|
|
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)
|
|
|
|
# 컬럼명 'date'의 타입을 date로 바꿔줌
|
|
df['date'] = pd.to_datetime(df['date'])
|
|
|
|
# 일자(date)를 기준으로 오름차순 정렬
|
|
# df = df.sort_values(by=['date'], ascending=True)
|
|
|
|
# 상위 5개 데이터 확인
|
|
###print (df.head())
|
|
|
|
if len(stock) > 0 and len(stock["PRICE"]) - 1 > 0:
|
|
lastDay = stock["PRICE"][len(stock["PRICE"]) - 1]["DATE"]
|
|
for values in df.values:
|
|
day = str(values[0]).split(' ')[0]
|
|
if lastDay == day:
|
|
break
|
|
stock["PRICE"].append({
|
|
"DATE": 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["PRICE"] = sorted(stock["PRICE"], key=lambda x: x['DATE'], reverse=True)
|
|
stock["PRICE"] = sorted(stock["PRICE"], key=lambda x: x['DATE'])
|
|
return
|
|
|
|
def get_moving_avg(self, stock):
|
|
q_3 = Queue(3)
|
|
q_5 = Queue(5)
|
|
q_7 = Queue(7)
|
|
q_10 = Queue(10)
|
|
q_20 = Queue(20)
|
|
q_30 = Queue(30)
|
|
q_60 = Queue(60)
|
|
q_90 = Queue(90)
|
|
q_100 = Queue(100)
|
|
q_120 = Queue(120)
|
|
q_150 = Queue(150)
|
|
q_180 = Queue(180)
|
|
q_200 = Queue(200)
|
|
q_240 = Queue(240)
|
|
|
|
for i in range(len(stock['PRICE'])):
|
|
q_3.enqueue(stock['PRICE'][i]['close'])
|
|
q_5.enqueue(stock['PRICE'][i]['close'])
|
|
q_7.enqueue(stock['PRICE'][i]['close'])
|
|
q_10.enqueue(stock['PRICE'][i]['close'])
|
|
q_20.enqueue(stock['PRICE'][i]['close'])
|
|
q_30.enqueue(stock['PRICE'][i]['close'])
|
|
q_60.enqueue(stock['PRICE'][i]['close'])
|
|
q_90.enqueue(stock['PRICE'][i]['close'])
|
|
q_100.enqueue(stock['PRICE'][i]['close'])
|
|
q_120.enqueue(stock['PRICE'][i]['close'])
|
|
q_150.enqueue(stock['PRICE'][i]['close'])
|
|
q_180.enqueue(stock['PRICE'][i]['close'])
|
|
q_200.enqueue(stock['PRICE'][i]['close'])
|
|
q_240.enqueue(stock['PRICE'][i]['close'])
|
|
|
|
stock['PRICE'][i]['avg3'] = q_3.avg()
|
|
stock['PRICE'][i]['avg5'] = q_5.avg()
|
|
stock['PRICE'][i]['avg7'] = q_7.avg()
|
|
stock['PRICE'][i]['avg10'] = q_10.avg()
|
|
stock['PRICE'][i]['avg20'] = q_20.avg()
|
|
stock['PRICE'][i]['avg30'] = q_30.avg()
|
|
stock['PRICE'][i]['avg60'] = q_60.avg()
|
|
stock['PRICE'][i]['avg90'] = q_90.avg()
|
|
stock['PRICE'][i]['avg100'] = q_100.avg()
|
|
stock['PRICE'][i]['avg120'] = q_120.avg()
|
|
stock['PRICE'][i]['avg150'] = q_150.avg()
|
|
stock['PRICE'][i]['avg180'] = q_180.avg()
|
|
stock['PRICE'][i]['avg200'] = q_200.avg()
|
|
stock['PRICE'][i]['avg240'] = q_240.avg()
|
|
|
|
return
|
|
|
|
def crawl_specific_stock(self, stock):
|
|
# 데이터 수집
|
|
self.get_data(stock)
|
|
# 이동 평균 계산
|
|
self.get_moving_avg(stock)
|
|
return
|
|
|
|
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)")
|
|
|
|
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)")
|
|
|
|
stock = {"NAME": code, "CODE": code, "PRICE": []}
|
|
|
|
lastDay = ""
|
|
cursor.execute('SELECT * FROM ' + tableName + ' WHERE CODE=?', (stock["CODE"],))
|
|
result = cursor.fetchone()
|
|
if result != 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 |