dsyoon/DeepStock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
dosangyoon
2022-07-29 14:28:27 +09:00
parent b06a89eb2f
commit 794e2ea5f7
1082 changed files with 4441 additions and 446000 deletions
Download Patch File Download Diff File Expand all files Collapse all files

319
stockpredictor_back/crawler/toJsonFile/MetaCrawler.py Normal file
View File

@@ -0,0 +1,319 @@
import json
import datetime
import requests
import pandas as pd
from time import sleep
import os
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_stocks(self, inFileName):
stocks = []
if os.path.isfile(inFileName):
inFp = open(inFileName, 'r', encoding='utf-8')
for line in inFp.readlines():
line = line.strip()
if line:
stocks.append(json.loads(line))
inFp.close()
outFp = open(inFileName, 'w', encoding='utf-8')
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
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
for i in range(len(inputs)):
input = inputs[i]
if len(stocks) == 0:
meta = {}
meta["NAME"] = input['NAME']
meta["CODE"] = input['CODE']
meta["PRICE"] = []
lastDay = "1900.01.01"
else:
meta = stocks[i]
lastDay = meta['PRICE'][0]['DATE']
finish = False
for i in range(1, self.limit_page_count):
#html = pd.read_html(input['URL'] + '&page=%s' % i, header=0)
html = None
while True:
try:
html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header, timeout=30).text)
sleep(0.5)
break
except:
print(i)
if i > 200:
break
continue
# 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 j == 0:
continue
if item[0] <= lastDay:
finish = True
break
meta["PRICE"].append({
"DATE": item[0], # 날짜
"close": item[1], # 매매기준율
"diff": item[2] # 전일대비
})
elif input['NAME'] in ('WTI', 'GOLD'):
if item[0] <= lastDay:
finish = True
break
meta["PRICE"].append({
"DATE": item[0], # 날짜
"close": item[1], # 종가
"diff": item[2], # 전일대비
"rate": item[3] # 등락율
})
if finish:
break
meta["PRICE"] = sorted(meta["PRICE"], key=lambda x: x['DATE'], reverse=True)
outFp.write(json.dumps(meta, ensure_ascii=False) + "\n")
outFp.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):
stocks = []
if os.path.isfile(inFileName):
inFp = open(inFileName, 'r', encoding='utf-8')
for line in inFp.readlines():
line = line.strip()
if line:
stocks.append(json.loads(line))
inFp.close()
outFp = open(inFileName, 'w', encoding='utf-8')
today = datetime.datetime.now().strftime("%Y%m%d")
url = 'http://finance.naver.com/sise/investorDealTrendDay.nhn?bizdate='+today+'&sosok=&page='
if len(stocks) == 0:
lastDay = "1900.01.01"
else:
lastDay = stocks[0]['DATE']
previousDay = ""
finish = False
for i in range(1, self.limit_page_count):
#html = pd.read_html(url + str(i), header=0)
html = None
while True:
try:
html = pd.read_html(requests.get(url + str(i), headers=self.header, timeout=30).text)
sleep(0.5)
break
except:
print(i)
if i > 200:
break
continue
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 2:
break
for j in range(1, 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 = {
"DATE": "20"+item[0],
"pri": item[1], # 개인
"for": 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
outFp.write(json.dumps(meta, ensure_ascii=False) + "\n")
print ("20"+item[0])
previousDay = html[0].values[2][0]
if finish:
break
if len(stocks) > 0:
for stock in stocks:
outFp.write(json.dumps(stock, ensure_ascii=False) + "\n")
outFp.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):
stocks = []
if os.path.isfile(inFileName):
inFp = open(inFileName, 'r', encoding='utf-8')
for line in inFp.readlines():
line = line.strip()
if line:
stocks.append(json.loads(line))
inFp.close()
outFp = open(inFileName, 'w', encoding='utf-8')
url = 'http://finance.naver.com/sise/sise_deposit.nhn?&page='
if len(stocks) == 0:
lastDay = "1900.01.01"
else:
lastDay = stocks[0]['DATE']
previousDay = ""
finish = False
for i in range(1, self.limit_page_count):
#html = pd.read_html(url + str(i), header=0, encoding='euc-kr')
html = None
while True:
try:
html = pd.read_html(requests.get(url + str(i), headers=self.header, timeout=30).text, encoding='euc-kr')
sleep(0.5)
break
except:
print(url + str(i))
if i > 200:
break
continue
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 10:
break
for j in range(1, 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 = {
"DATE": "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
outFp.write(json.dumps(meta, ensure_ascii=False) + "\n")
print("20"+item[0])
if finish:
break
previousDay = html[0].values[2][0]
if len(stocks) > 0:
for stock in stocks:
outFp.write(json.dumps(stock, ensure_ascii=False) + "\n")
outFp.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):
stocks = []
if os.path.isfile(inFileName):
inFp = open(inFileName, 'r', encoding='utf-8')
for line in inFp.readlines():
line = line.strip()
if line:
stocks.append(json.loads(line))
inFp.close()
outFp = open(inFileName, 'w', encoding='utf-8')
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]
if len(stocks) == 0:
meta = {}
meta["NAME"] = input['NAME']
meta["CODE"] = input['CODE']
meta["PRICE"] = []
lastDay = "1900.01.01"
else:
meta = stocks[i]
lastDay = meta['PRICE'][0]['DATE']
finish = False
for i in range(1, self.limit_page_count):
#html = pd.read_html(input['URL'] + '&page=%s' % i, header=0)
html = None
while True:
try:
html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header, timeout=30).text)
sleep(0.5)
break
except:
print(i)
if i > 200:
break
continue
# 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
meta["PRICE"].append({
"DATE": item[0],
"close": item[1], # 종가
"diff": item[2], # 전일대비
"rate": item[3]}) # 등락율
if finish:
break
print(meta["NAME"] + " / " + item[0])
meta["PRICE"] = sorted(meta["PRICE"], key=lambda x: x['DATE'], reverse=True)
outFp.write(json.dumps(meta, ensure_ascii=False) + "\n")
outFp.close()
return