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

timeout 5초 추가

Browse Source
This commit is contained in:
dosang.yoon
2022-06-03 12:28:58 +09:00
parent c5848ebadc
commit 5774a6eaf0
8 changed files with 87 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
stockpredictor/crawler/toJsonFile/StockCrawler.py
View File

@@ -74,7 +74,7 @@ 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).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=5).text)[0]
# code_df = pd.read_excel('../resources/stock/상장법인목록.xls')
# 종목코드가 6자리이기 때문에 6자리를 맞춰주기 위해 설정해줌
@@ -255,7 +255,7 @@ 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).text)
html = pd.read_html(requests.get(pg_url, headers=self.header, timeout=5).text)
count = 0
for date in html[0].날짜.values:
@@ -378,7 +378,7 @@ 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).text)
html = pd.read_html(requests.get(pg_url, headers=self.header, timeout=5).text)
count = 0
for date in html[0].날짜.values:
if type(date) is str:
@@ -600,7 +600,7 @@ 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).text)
html = pd.read_html(requests.get(pg_url, headers=self.header, timeout=5).text)
count = 0
for date in html[0].날짜.values:
if type(date) is str: