This commit is contained in:
dosangyoon
2022-04-01 23:36:29 +09:00
parent b37438f83c
commit c17140eaa1
4 changed files with 35 additions and 23 deletions

View File

@@ -7,9 +7,11 @@ import pandas as pd
class MetaCrawler:
header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'}
limit_page_count = 10000
limit_page_count = 100000
START_DATE = None
def __init__(self):
def __init__(self, START_DATE):
self.START_DATE = START_DATE
return
# 참고) http://blog.naver.com/PostView.nhn?blogId=koko8624&logNo=221288761509
@@ -39,7 +41,7 @@ class MetaCrawler:
cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (CODE,))
result = cursor.fetchone()
if result == None:
lastDay = "1900.01.01"
lastDay = self.START_DATE
else:
lastDay = result[0]
@@ -111,7 +113,7 @@ class MetaCrawler:
cursor.execute('SELECT ymd FROM ' + tableName + ' order by ymd desc')
result = cursor.fetchone()
if result == None:
lastDay = "1900.01.01"
lastDay = self.START_DATE
else:
lastDay = result[0]
@@ -153,7 +155,7 @@ class MetaCrawler:
cursor.execute("INSERT INTO " + tableName + "(ymd, pri, fori, ins, ins0, ins1, ins2, ins3, ins4, ins5, cor) VALUES(?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", (ymd, pri, fori, ins, ins0, ins1, ins2, ins3, ins4, ins5, cor))
else:
# cursor.execute("UPDATE " + tableName + " SET pri=?, fori=?, ins=?, ins0=?, ins1=?, ins2=?, ins3=?, ins4=?, ins5=?, cor=? WHERE ymd=?", (pri, fori, ins, ins0, ins1, ins2, ins3, ins4, ins5, cor, ymd))
finish
finish = True
break
print ("20"+item[0])
@@ -182,7 +184,7 @@ class MetaCrawler:
cursor.execute('SELECT ymd FROM ' + tableName + ' order by ymd desc')
result = cursor.fetchone()
if result == None:
lastDay = "1900.01.01"
lastDay = self.START_DATE
else:
lastDay = result[0]
previousDay = ""
@@ -264,7 +266,7 @@ class MetaCrawler:
cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (CODE,))
result = cursor.fetchone()
if result == None:
lastDay = "1900.01.01"
lastDay = self.START_DATE
else:
lastDay = result[0]
@@ -338,7 +340,7 @@ class MetaCrawler:
cursor.execute('SELECT ymd FROM ' + tableName + ' WHERE CODE=? order by ymd desc', (CODE,))
result = cursor.fetchone()
if result == None:
lastDay = "1900.01.01"
lastDay = self.START_DATE
else:
lastDay = result[0]