mdbq 1.8.0__py3-none-any.whl → 1.8.2__py3-none-any.whl

mdbq/other/sku_picture.py

@@ -5,6 +5,7 @@ import json
 import os
 import platform
 import random
+from dateutil.relativedelta import relativedelta
 import re
 import time
 import warnings
@@ -18,6 +19,14 @@ from selenium.webdriver.chrome.service import Service
 from mdbq.config import set_support
 from mdbq.config import get_myconf
 from mdbq.mysql import mysql
+from mdbq.mysql import s_query
+import ua_sj
+import requests
+
+import io
+from openpyxl import load_workbook
+from openpyxl.drawing.image import Image
+from openpyxl.utils import get_column_letter
 
 warnings.filterwarnings('ignore')
 
@@ -444,16 +453,86 @@ class SkuPicture:
 
         if results:
             self.df = pd.concat(results)
+            self.df = self.df[['sku图片链接'] != '0']
 
     def read_df(self):
         path = os.path.join(self.path, self.filename)
         df = pd.read_excel(path, header=0)
         df = df[['商品id', '商家编码', '是否新增']]
+        df['是否新增'].fillna(0, inplace=True)
         df = df.astype({'是否新增': int})
         df = df[df['是否新增'] == 1]
         self.urls = df.to_dict('records')
 
 
+class DownloadPicture():
+    """
+    从数据库中下载数据
+    """
+    def __init__(self, service_name):
+        # target_service 从哪个服务器下载数据
+        self.months = 0  # 下载几个月数据, 0 表示当月, 1 是上月 1 号至今
+        # 实例化一个下载类
+        username, password, host, port = get_myconf.select_config_values(target_service=service_name,
+                                                                         database='mysql')
+        self.download = s_query.QueryDatas(username=username, password=password, host=host, port=port)
+        self.df = pd.DataFrame()
+        self.headers = {'User-Agent': ua_sj.get_ua()}
+        self.save_path = '/Users/xigua/Downloads/sku图片链接'
+        self.filename = ''
+        if not os.path.exists(self.save_path):
+            os.mkdir(self.save_path)
+
+    def get_df_from_service(self):
+        start_date, end_date = self.months_data(num=self.months)
+        projection = {
+            '商品id': 1,
+            '商家编码': 1,
+            'sku编码': 1,
+            'sku名称': 1,
+            'sku图片链接': 1
+        }
+        self.df = self.download.data_to_df(
+            db_name='属性设置2',
+            table_name='天猫商品sku信息',
+            start_date=start_date,
+            end_date=end_date,
+            projection=projection,
+        )
+
+    def download_data(self):
+        dict_data = self.df.to_dict('records')
+        num = len(dict_data)
+        i = 0
+        for data in dict_data:
+            url = data['sku图片链接']
+            sku_name = re.sub('/', '_', data['sku名称'])
+            self.filename = f'{data['商品id']}_{data['商家编码']}_{data['sku编码']}_{sku_name}.jpg'
+            if os.path.isfile(os.path.join(self.save_path, self.filename)):
+                i += 1
+                continue
+            if 'https' not in url:
+                i += 1
+                continue
+
+            print(f'正在下载: {i}/{num},   {data['sku编码']}')
+            self.headers.update({'User-Agent': ua_sj.get_ua()})
+            res = requests.get(url, headers=self.headers)  # 下载图片到内存
+            # 保存图片到本地文件夹
+            with open(os.path.join(self.save_path, self.filename), 'wb') as f:
+                f.write(res.content)
+            i += 1
+            time.sleep(0.5)
+
+    @staticmethod
+    def months_data(num=0, end_date=None):
+        """ 读取近 num 个月的数据, 0 表示读取当月的数据 """
+        if not end_date:
+            end_date = datetime.datetime.now()
+        start_date = end_date - relativedelta(months=num)  # n 月以前的今天
+        start_date = f'{start_date.year}-{start_date.month}-01'  # 替换为 n 月以前的第一天
+        return pd.to_datetime(start_date), pd.to_datetime(end_date)
+
 def main(service_name, database):
     if not os.path.exists(Share_Path):
         print(f'当前系统环境不支持')
@@ -483,5 +562,159 @@ def main(service_name, database):
         )  # 3. 回传数据库
 
 
+def main2(service_name, database):
+    d = DownloadPicture(service_name=service_name)
+    d.get_df_from_service()
+    d.download_data()
+
+
+class InsertPicture():
+    def __init__(self):
+        self.filename = 'test.xlsx'
+        self.path = '/Users/xigua/Downloads'
+        self.pic_datas = []
+        self.header = 0  # sku 的标题栏起始行数
+
+    def insert_data(self):
+        self.get_filename()
+
+        workbook = load_workbook(os.path.join(self.path, self.filename))
+        sheet = workbook.active
+        rows = sheet.max_row  # 总行数
+        columns = sheet.max_column  # 总列数
+        sheet.insert_cols(0, 1)  # 在第0列开始插入1列空白列
+        # sheet['A1'] = '商品图片'
+
+        is_trange = False
+        for col in range(1, columns+1):  # 遍历每一列
+            # if is_trange == True:
+            #     break
+            for row in range(1, rows+1):  # 遍历每一行
+                # print(f'第{col}列, 第{row}行...')
+                value = sheet.cell(row=row, column=col).value
+                if value:
+                    for data in self.pic_datas:
+                        if str(value) == data['sku'] or (len(str(value)) > 16 and str(value) in data['sku']):
+                            # print(value, data['sku'])
+                            print(f'转换: 第{col}列, 第{row}行, sku: {data['sku']} ...')
+                            image_path = os.path.join(data['文件路径'], data['文件名称'])
+                            with open(image_path, 'rb') as f:
+                                img_data = f.read()
+                            img = Image(io.BytesIO(img_data))
+                            width, height = self.img_resize(img.width, img.height)  # 等比例缩放图片
+                            col_letter = 'A'
+                            # col_letter = get_column_letter(col)  # 将数字索引转换为列标签 A、B、C、D...
+                            sheet.column_dimensions[col_letter].width = 13
+                            sheet.row_dimensions[row].height = 80
+                            img.width = width
+                            img.height = height
+                            sheet.add_image(img, f'{col_letter}{row}')
+                            is_trange = True
+
+        if is_trange == False:  # 如果 sku 没有匹配到任何值，则使用 商家编码
+            for col in range(1, columns + 1):  # 遍历每一列
+                # if is_trange == True:
+                #     break
+                for row in range(1, rows + 1):  # 遍历每一行
+                    # print(f'第{col}列, 第{row}行...')
+                    value = sheet.cell(row=row, column=col).value
+                    if value:
+                        for data in self.pic_datas:
+                            if str(value) == data['商家编码']:
+                                # print(value, data['sku'])
+                                print(f'转换: 第{col}列, 第{row}行, 商家编码: {data['商家编码']} ...')
+                                image_path = os.path.join(data['文件路径'], data['文件名称'])
+                                with open(image_path, 'rb') as f:
+                                    img_data = f.read()
+                                img = Image(io.BytesIO(img_data))
+                                width, height = self.img_resize(img.width, img.height)  # 等比例缩放图片
+                                col_letter = 'A'
+                                # col_letter = get_column_letter(col)  # 将数字索引转换为列标签 A、B、C、D...
+                                sheet.column_dimensions[col_letter].width = 13
+                                sheet.row_dimensions[row].height = 80
+                                img.width = width
+                                img.height = height
+                                sheet.add_image(img, f'{col_letter}{row}')
+                                is_trange = True
+                                break  # 商家编码只需要添加一次，所以必须 break，否则可能添加多个图片到某个单元格
+
+        if is_trange == False:  # 如果 sku 和商家编码都没有匹配到任何值，则使用 商品id
+            for col in range(1, columns + 1):  # 遍历每一列
+                # if is_trange == True:
+                #     break
+                for row in range(1, rows + 1):  # 遍历每一行
+                    # print(f'第{col}列, 第{row}行...')
+                    value = sheet.cell(row=row, column=col).value
+                    if value:
+                        for data in self.pic_datas:
+                            if str(value) == data['商品id']:
+                                # print(value, data['sku'])
+                                print(f'转换: 第{col}列, 第{row}行, 商品id: {data['商品id']} ...')
+                                image_path = os.path.join(data['文件路径'], data['文件名称'])
+                                with open(image_path, 'rb') as f:
+                                    img_data = f.read()
+                                img = Image(io.BytesIO(img_data))
+                                width, height = self.img_resize(img.width, img.height)  # 等比例缩放图片
+                                col_letter = 'A'
+                                # col_letter = get_column_letter(col)  # 将数字索引转换为列标签 A、B、C、D...
+                                sheet.column_dimensions[col_letter].width = 13
+                                sheet.row_dimensions[row].height = 80
+                                img.width = width
+                                img.height = height
+                                sheet.add_image(img, f'{col_letter}{row}')
+                                is_trange = True
+                                break  # 商品id只需要添加一次，所以必须 break，否则可能添加多个图片到某个单元格
+
+        if is_trange == False:
+            print(f'{self.filename}:\n'
+                  f'在该文件中没有找到匹配的 skuid/商品id/商家编码, 注意程序只会转换当前活动的 sheet, \n'
+                  f'1. 如果您确定文件中确实存在 skuid/商品id/商家编码, 可能是因为 sheet 不是活动状态, 请切换后再重新运行本程序。\n'
+                  f'2. 程序只能转换已经收录的商品图, 如果未被收录亦会转换失败, 请联系开发者添加。')
+
+        workbook.save(os.path.join(self.path, f'ok_{self.filename}'))
+
+    def img_resize(self, width, height, num=100):
+        """
+        设置基础大小为 num， 并等比例缩放
+        """
+        if width > height:
+            height = height * num // width
+            width = num
+        else:
+            width = width * num // height
+            height = num
+        return width, height
+
+    def get_filename(self):
+        for root, dirs, files in os.walk(os.path.join(self.path, 'sku图片链接'), topdown=False):
+            for name in files:
+                if name.endswith('.jpg'):
+                    sku_id = re.findall(r'\d+_\d+_(\d+)_|\d+_\d+_(\d+-\d+)_|\d+_\d+_([A-Za-z]+\d+)_', name)
+                    sku_id = [item for item in sku_id[0] if item != '']
+                    sp_id = re.findall(r'^(\d+)_', name)
+                    spbm = re.findall(r'(\d{13})\d+', sku_id[0])
+                    if not spbm:
+                        spbm = ['0']
+                    self.pic_datas.append(
+                        {
+                            '文件路径': root,
+                            '文件名称': name,
+                            'sku': sku_id[0],
+                            '商品id': sp_id[0],
+                            '商家编码': spbm[0],
+                        }
+                    )
+
+
+def main3():
+    p = InsertPicture()
+    p.filename = 'test222.xlsx'
+    # p.header = 1
+    p.insert_data()
+
+
+
 if __name__ == '__main__':
-    main(service_name='company', database='mysql')
+    # main(service_name='company', database='mysql')
+    # main2(service_name='company', database='mysql')
+    main3()

{mdbq-1.8.0.dist-info → mdbq-1.8.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 1.8.0
+Version: 1.8.2
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-1.8.0.dist-info → mdbq-1.8.2.dist-info}/RECORD

@@ -30,13 +30,13 @@ mdbq/mysql/year_month_day.py,sha256=VgewoE2pJxK7ErjfviL_SMTN77ki8GVbTUcao3vFUCE,
 mdbq/other/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/other/porxy.py,sha256=UHfgEyXugogvXgsG68a7QouUCKaohTKKkI4RN-kYSdQ,4961
 mdbq/other/pov_city.py,sha256=AEOmCOzOwyjHi9LLZWPKi6DUuSC-_M163664I52u9qw,21050
-mdbq/other/sku_picture.py,sha256=U9NG-laKns3g0FJsK-JwqlW1EQZRTEXvIsbdFNBR0Ro,22250
+mdbq/other/sku_picture.py,sha256=xNXOzyaO-qz1htYroPmYnsct_CXF4MLJASereVEGN6g,33429
 mdbq/other/ua_sj.py,sha256=JuVYzc_5QZ9s_oQSrTHVKkQv4S_7-CWx4oIKOARn_9U,22178
 mdbq/pbix/__init__.py,sha256=Trtfaynu9RjoTyLLYBN2xdRxTvm_zhCniUkVTAYwcjo,24
 mdbq/pbix/pbix_refresh.py,sha256=JUjKW3bNEyoMVfVfo77UhguvS5AWkixvVhDbw4_MHco,2396
 mdbq/pbix/refresh_all.py,sha256=0uAnBKCd5cx5FLTkawN1GV9yi87rfyMgYal5LABtumQ,7186
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
-mdbq-1.8.0.dist-info/METADATA,sha256=hb11aMvPCn1u8Jtmn2BQaMfgkUloamu_-ri-FFpgpns,245
-mdbq-1.8.0.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-mdbq-1.8.0.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-1.8.0.dist-info/RECORD,,
+mdbq-1.8.2.dist-info/METADATA,sha256=PsbFqqZUVz03tpO86vKRA68rj6Oy3JtEQ2qOUqnauQI,245
+mdbq-1.8.2.dist-info/WHEEL,sha256=cpQTJ5IWu9CdaPViMhC9YzF8gZuS5-vlfoFihTBC86A,91
+mdbq-1.8.2.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-1.8.2.dist-info/RECORD,,

{mdbq-1.8.0.dist-info → mdbq-1.8.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.44.0)
+Generator: setuptools (70.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any