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

init

Browse Source
This commit is contained in:
dosang.yoon
2022-06-03 13:44:37 +09:00
parent 0b49e88adf
commit 617db82e60
11 changed files with 34 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
stockpredictor/crawler/toSQLite/MetaCrawler.py
View File

@@ -46,7 +46,7 @@ class MetaCrawler:
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, timeout=5).text)
html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header, timeout=30).text)
sleep(0.5)
# 마지막 페이지 까지 받기
@@ -126,7 +126,7 @@ class MetaCrawler:
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, timeout=5).text)
html = pd.read_html(requests.get(url + str(i), headers=self.header, timeout=30).text)
sleep(0.5)
# 마지막 페이지 까지 받기
@@ -192,7 +192,7 @@ class MetaCrawler:
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, timeout=5).text, encoding='euc-kr')
html = pd.read_html(requests.get(url + str(i), headers=self.header, timeout=30).text, encoding='euc-kr')
sleep(0.5)
# 마지막 페이지 까지 받기
@@ -267,7 +267,7 @@ class MetaCrawler:
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, timeout=5).text)
html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header, timeout=30).text)
sleep(0.5)
# 마지막 페이지 까지 받기

4
stockpredictor/crawler/toSQLite/StockCrawler.py
View File

@@ -75,7 +75,7 @@ class StockCrawler:
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=5).text)[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
@@ -228,7 +228,7 @@ class StockCrawler:
# 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, timeout=5).text)
html = pd.read_html(requests.get(pg_url, headers=self.header, timeout=30).text)
sleep(0.5)
for date in html[0].날짜.values: