sleep 추가

This commit is contained in:
dosang.yoon
2022-06-03 12:33:10 +09:00
parent 5774a6eaf0
commit 80294296f8
6 changed files with 22 additions and 0 deletions

View File

@@ -47,6 +47,7 @@ class MetaCrawler:
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)
sleep(0.5)
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 1:
@@ -120,6 +121,7 @@ class MetaCrawler:
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)
sleep(0.5)
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 2:
@@ -180,6 +182,7 @@ class MetaCrawler:
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')
sleep(0.5)
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 10:
@@ -251,6 +254,7 @@ class MetaCrawler:
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)
sleep(0.5)
# 마지막 페이지 까지 받기
if len(html[0].날짜.values) <= 1: