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

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