crawling

+import json
+
+with open('water.json', 'r', encoding='utf-8') as make_file:
+    a = json.load(make_file)
+    print(aa)
\ No newline at end of file

+{}
\ No newline at end of file

+ Subproject commit 12d49c195cc74e4ed59ccc44029a6fc4cafd5f6c

+from selenium import webdriver
+from bs4 import BeautifulSoup
+import requests
+import urllib.request
+import time
+
+
+def name_preprocessing(a):
+    if a[0] == ' ':
+        a = a[1:]
+    num = a.count('_')
+    for i in range(num):
+        a = a.replace('_', '')
+    if a.find('G') != -1:
+        temp = a.find('G')
+        if temp > 3:
+            for i in range(temp - 1, 0, -1):
+                if ord(a[i]) < 48 or ord(a[i]) > 57:
+                    end = i
+                    break
+            a = a[:end + 1]
+
+
+    if a.find('L') != -1:
+        if a.find('M') != -1:
+            temp = a.find("M")
+            for i in range(temp - 1, 0, -1):
+                if ord(a[i]) < 48 or ord(a[i]) > 57:
+                    end = i
+                    break
+        else:
+            temp = a.find('L')
+            for i in range(temp - 1, 0, -1):
+                if ord(a[i]) < 48 or ord(a[i]) > 57:
+                    end = i
+                    break
+        a = a[:end + 1]
+    if a[-1] == '.':
+        a = a[:-2]
+    temp1 = a.find('(')
+    temp2 = a.find(')')
+    if temp1 == 0:
+        a = a[temp2+1:]
+    return a
+
+
+def unit_preprocessing(a, b):
+    if a[0] == ' ':
+        a = a[1:]
+    unit = a.find(b)
+    b = a[:unit]
+    temp = a.find('당')
+    won = a.find('원')
+    a = a[temp + 2:won]
+    if a.find('.') != -1:
+        won = a.find('.')
+        a = a[:won]
+    a = a.replace(',', '')
+    unit = int(int(a) / int(b) * 100)
+    return unit
+
+
+def home_water(H):
+    page_num = 3
+    path = 'C:\chromedriver'
+    driver = webdriver.Chrome(path)
+    driver.get(
+        'http://www.homeplus.co.kr/app.exhibition.category.Category.ghs?comm=category.list&cid=60386&WT.ac=GNBctg_2dep_ctg')
+
+    for i in range(page_num-1):
+        driver.find_element_by_xpath("//a[@class='more']").click()
+        time.sleep(10)
+
+    html = driver.page_source
+    soup = BeautifulSoup(html, 'html.parser')
+    table = soup.find_all('ul', {'class' : 'fix-ty2'})
+    for five in table:
+        one = five.find_all('li')
+        for i in one:
+            temp_dict = {}
+            a = i.find('div', {'class' : 'exh-comtxt w-ty4'})
+            if type(a) == type(None):
+                continue
+
+            price = a.find('span', {'class' : 'price'})
+            unit = price.find('span', {'class' : 'unit-area'})
+            if type(unit) == type(None):
+                continue
+            price = price.find('strong', {'class' : 'buy'})
+            name = a.find('a', {'class' : 'name'})
+            if type(name) == type(None):
+                continue
+
+            name = name_preprocessing(name.text)
+            price = price.text
+            price = price.replace(',', '')
+            unit = unit_preprocessing(unit.text, 'ML')
+
+            overlap = False
+            change = 0
+            for qw in range(len(H)):
+                if H[qw]['name'] == name and H[qw]['mart'] == 'homeplus':
+                    change = qw
+                    overlap = True
+
+            if overlap == False:
+                soup = i.find('a', {'class': 'thumb'})
+                if type(soup) == type(None):
+                    continue
+                imgUrl = soup.find('img')['src']
+                imgUrl = 'http:' + imgUrl
+                temp_dict['mart'] = 'homeplus'
+                temp_dict['name'] = name
+                temp_dict['price'] = price
+                temp_dict['unit'] = unit
+                temp_dict['img'] = imgUrl
+                H.append(temp_dict)
+
+            else:
+                if H[change]['unit'] > unit:
+                    H[change]['price'] = price
+                    H[change]['unit'] = unit
+                continue
+    print('홈플러스 물')
+    print(H)
+    print(len(H))
+
+
+def home_snack(H):
+    page_num = 17
+    path = 'C:\chromedriver'
+    driver = webdriver.Chrome(path)
+    driver.get(
+        'http://www.homeplus.co.kr/app.exhibition.category.Category.ghs?comm=category.list&cid=60343&WT.ac=GNBctg_2dep_ctg')
+
+    for i in range(page_num - 1):
+        driver.find_element_by_xpath("//a[@class='more']").click()
+        time.sleep(10)
+    html = driver.page_source
+    soup = BeautifulSoup(html, 'html.parser')
+    table = soup.find_all('ul', {'class': 'fix-ty2'})
+    for five in table:
+        one = five.find_all('li')
+        for i in one:
+            temp_dict = {}
+            a = i.find('div', {'class': 'exh-comtxt w-ty4'})
+            if type(a) == type(None):
+                continue
+
+            price = a.find('span', {'class': 'price'})
+            unit = price.find('span', {'class': 'unit-area'})
+
+            if type(unit) == type(None):
+                continue
+            price = price.find('strong', {'class': 'buy'})
+            name = a.find('a', {'class': 'name'})
+            if type(name) == type(None):
+                continue
+            unit = unit.text
+            if unit.find('ML') != -1:
+                continue
+            if unit.find('개') != -1:
+                continue
+            name = name_preprocessing(name.text)
+            price = price.text
+            price = price.replace(',', '')
+            unit = unit_preprocessing(unit, 'G')
+
+            overlap = False
+            change = 0
+            for qw in range(len(H)):
+                if H[qw]['name'] == name and H[qw]['mart'] == 'homeplus':
+                    change = qw
+                    overlap = True
+
+            if overlap == False:
+                soup = i.find('a', {'class': 'thumb'})
+                if type(soup) == type(None):
+                    continue
+                imgUrl = soup.find('img')['src']
+                imgUrl = 'http:' + imgUrl
+                temp_dict['mart'] = 'homeplus'
+                temp_dict['name'] = name
+                temp_dict['price'] = price
+                temp_dict['unit'] = unit
+                temp_dict['img'] = imgUrl
+                H.append(temp_dict)
+
+            else:
+                if H[change]['unit'] > unit:
+                    H[change]['price'] = price
+                    H[change]['unit'] = unit
+                continue
+
+    print('홈플러스 과자')
+    print(H)
+    print(len(H))
+
+
+
+def home_coffee(H):
+    page_num = 2
+    path = 'C:\chromedriver'
+    driver = webdriver.Chrome(path)
+    driver.get(
+        'http://www.homeplus.co.kr/app.exhibition.category.Category.ghs?comm=category.list&cid=60406&WT.ac=GNBctg_3dep_ctg')
+
+    for i in range(page_num - 1):
+        driver.find_element_by_xpath("//a[@class='more']").click()
+        time.sleep(10)
+    html = driver.page_source
+    soup = BeautifulSoup(html, 'html.parser')
+    table = soup.find_all('ul', {'class': 'fix-ty2'})
+    for five in table:
+        one = five.find_all('li')
+        for i in one:
+            temp_dict = {}
+            a = i.find('div', {'class': 'exh-comtxt w-ty4'})
+            if type(a) == type(None):
+                continue
+
+            price = a.find('span', {'class': 'price'})
+            unit = price.find('span', {'class': 'unit-area'})
+
+            if type(unit) == type(None):
+                continue
+            price = price.find('strong', {'class': 'buy'})
+            name = a.find('a', {'class': 'name'})
+            if type(name) == type(None):
+                continue
+            unit = unit.text
+            if unit.find('G') != -1:
+                continue
+
+            name = name_preprocessing(name.text)
+            price = price.text
+            price = price.replace(',', '')
+            unit = unit_preprocessing(unit, 'ML')
+
+            overlap = False
+            change = 0
+            for qw in range(len(H)):
+                if H[qw]['name'] == name and H[qw]['mart'] == 'homeplus':
+                    change = qw
+                    overlap = True
+
+            if overlap == False:
+                soup = i.find('a', {'class': 'thumb'})
+                if type(soup) == type(None):
+                    continue
+                imgUrl = soup.find('img')['src']
+                imgUrl = 'http:' + imgUrl
+                temp_dict['mart'] = 'homeplus'
+                temp_dict['name'] = name
+                temp_dict['price'] = price
+                temp_dict['unit'] = unit
+                temp_dict['img'] = imgUrl
+                H.append(temp_dict)
+
+            else:
+                if H[change]['unit'] > unit:
+                    H[change]['price'] = price
+                    H[change]['unit'] = unit
+                continue
+
+    print('홈플러스 커피')
+    print(H)
+    print(len(H))
+
+
+H_water = {}
+H_snack = {}
+H_coffee = {}
+#home_water(H_water)
+#home_snack(H_snack)
+#home_coffee(H_coffee)
\ No newline at end of file

+import requests
+import time
+from bs4 import BeautifulSoup
+import json
+from selenium import webdriver
+
+from crawling import emart_water, emart_snack, emart_coffee
+from lottemart import lotte_water, lotte_snack, lotte_coffee
+from homeplus import home_coffee, home_snack, home_water
+
+
+water = []
+snack = []
+coffee = []
+
+temp_dict = {}
+
+with open('coffee.json', 'r', encoding='utf-8') as read_file:
+    temp_dict = json.load(read_file)
+
+coffee = temp_dict['product']
+
+#emart_water(water)
+#emart_snack(snack)
+#emart_coffee(coffee)
+
+#lotte_water(water)
+#lotte_snack(snack)
+lotte_coffee(coffee)
+
+#home_water(water)
+#home_snack(snack)
+#home_coffee(coffee)
+
+#water_dict = {}
+#water_dict['product'] = water
+#snack_dict = {}
+#snack_dict['product'] = snack
+coffee_dict = {}
+coffee_dict['product'] = coffee
+
+with open('coffee.json', 'w', encoding='utf-8') as make_file:
+    json.dump(coffee_dict, make_file, ensure_ascii=False, indent='\t')
+
+
+'''
+with open('water.json', 'w', encoding='utf-8') as make_file:
+    json.dump(water_dict, make_file, ensure_ascii=False, indent='\t')
+
+with open('snack.json', 'w', encoding='utf-8') as make_file:
+    json.dump(snack_dict, make_file, ensure_ascii=False, indent='\t')
+
+
+with open('coffee.json', 'w', encoding='utf-8') as make_file:
+    json.dump(coffee_dict, make_file, ensure_ascii=False, indent='\t')
+'''
\ No newline at end of file

-a = '[노브랜드] 미네랄 워터 생수 (2L x 6개입)'
-while True:
-    b = a.find('[')
-    c = a.find(']')
-    if b == -1:
-        break
-    elif b == 0:
-        a = a[c + 1:-1]
-    else:
-        break
-while True:
-    d = a.find('(')
-    e = a.find(')')
-    if d == -1:
-        break
-    elif d == 0:
-        a = a[e + 1:-1]
-    else:
-        break
-
-result = ''
-b = list(a)
-for i in b:
-    if (ord(i) < 48) or (ord(i) > 57):
-        if i == ' ':
-            continue
-        result += i
-    else:
-        break
-while True:
-    if (result[-1] == '(') or (result[-1] == '[') or (result[-1] == ' '):
-        result = result[0:-1]
-    else:
-        break
+import requests
+import time
+from bs4 import BeautifulSoup
+import json
+from selenium import webdriver
+
+
+def qweq(a):
+    b = {}
+    b['mart'] = 'emart'
+    b['name'] = '삼다수'
+    b['price'] = 12
+
+    c = {}
+    c['mart'] = 'emart'
+    c['name'] = '삼다수'
+    c['price'] = 22
+
+    a.append(b)
+    a.append(c)
+    print(len(a))
+
+a = ['asas', 'asas']
+qweq(a)
+print(a)
+
+
+
 

+import pymysql
+import mysql.connector as mysql
+
+
+
+db = pymysql.connect(
+    host='localhost',
+    user='root',
+    passwd='111111'
+)
+
+print(db)
+
+cursor = db.cursor()
+cursor.execute("SHOW DATABASES")
+
+databases = cursor.fetchall()
+
+print(databases)
+
+for database in databases:
+    print(database)
\ No newline at end of file