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

2
stockpredictor/crawler/toJsonFile/FnGuideCrawler.py
View File

@@ -10,7 +10,7 @@ class FnGuideCrawler:
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

8
stockpredictor/crawler/toJsonFile/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).text)
html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header, timeout=5).text)
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 1:
@@ -119,7 +119,7 @@ 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).text)
html = pd.read_html(requests.get(url + str(i), headers=self.header, timeout=5).text)
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 2:
@@ -179,7 +179,7 @@ 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).text, encoding='euc-kr')
html = pd.read_html(requests.get(url + str(i), headers=self.header, timeout=5).text, encoding='euc-kr')
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 10:
@@ -250,7 +250,7 @@ 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).text)
html = pd.read_html(requests.get(input['URL'] + '&page=%s' % i, headers=self.header, timeout=5).text)
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 1:

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: