timeout 5초 추가

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

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:
@@ -125,7 +125,7 @@ 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:
@@ -190,7 +190,7 @@ 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:
@@ -264,7 +264,7 @@ 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: