def __init__(self):
self.dao = CrawlDao.CrawlDao("modeldatas")
self.fileDao = FileUtil.FileDao()
self.stringUtil = StringUtil.StringUtil()
self.sql_category_table = 'db_category'
self.sql_part_table = 'db_category_part'
# 已更新的分类 name+level+parent_id
self.category_have_list = list()
# 已更新的part name+level
self.part_have_list = list()
self.label_dict = {u'字标': '1', u'灯泡': '2', u'四滤': '3', u'': '0'}
self.cat_kind_dict = {u'全车件': 1, u'易损件': 0}
# 分类无法判断标识
self.cat_kind_not = '3'
self.aliss_name_text = ''
self.label_text = ''
# db_category level:dict(name+parent_id)
self.level_name = self.init_category()
# db_category_part name+cate_id:dict(part)
# self.part_name = self.init_part()
self.init_part()
# name+level+parent_id:id
self.category_id_dict = dict()
# name+level+parent_id:vehicle_code
self.category_code_dict = dict()
# cat_id:cat_name
self.cat_id_name = dict()
# 是否是新增的类目
self.is_new = False
def __init__(self):
self.dao = CrawlDao.CrawlDao()
self.fileDao = FileUtil.FileDao()
self.stringUtil = StringUtil.StringUtil()
# p_id+code : id
self.cate_id_dict = dict()
# self.cate_name_dict = dict()
cate_sql = 'SELECT cat_id,cat_name,cat_code,parent_id,vehicle_code,cat_level FROM db_category_dian WHERE cat_id > 2999 '
cate_array = self.dao.db.get_data(cate_sql)
for cate_data in cate_array:
cat_id = str(cate_data['cat_id'])
cat_code = str(cate_data['cat_code'])
parent_id = str(cate_data['parent_id'])
cat_level = str(cate_data['cat_level'])
vehicle_code = str(cate_data['vehicle_code'])
key = str(parent_id) + "_" + str(cat_code)
if cat_level == '3':
key += "_" + vehicle_code
self.cate_id_dict[key] = cat_id
# self.cate_name_dict[cat_id] = str(cate_data['cat_name'])
# g_id:old_cat_id
self.goods_dict = dict()
goods_sql = "select cat_id,goods_id from db_goods where seller_id = 1"
goods_array = self.dao.db.get_data(goods_sql)
for goods_data in goods_array:
self.goods_dict[str(goods_data['goods_id'])] = str(
goods_data['cat_id'])
def __init__(self):
self.dao = CrawlDao.CrawlDao()
self.fileDao = FileUtil.FileDao()
self.stringUtil = StringUtil.StringUtil()
self.table_mapping = 'db_category_mapping'
self.vehicle_dict = {"商用车": "H", "乘用车": "C"}
# 新分类的
self.cate_dict = dict()
cate_sql = "select cat_id,cat_name,vehicle_code,cat_level,parent_id from db_category_new "
cate_array = self.dao.db.get_data(cate_sql)
for cate_data in cate_array:
cat_id = str(cate_data['cat_id'])
cat_name = str(cate_data['cat_name'])
cat_level = str(cate_data['cat_level'])
vehicle_code = str(cate_data['vehicle_code'])
parent_id = str(cate_data['parent_id'])
key = cat_name + "_" + cat_level + "_" + parent_id
if cat_level == '3':
key += "_" + vehicle_code
self.cate_dict[key] = cat_id
# 老cate的图片数据
self.old_cat_dict = dict()
old_cat_sql = "select cat_name,category_thumb from db_category where cat_id < 2999 and parent_id = 0 and is_deleted = 'N'"
old_cate_array = self.dao.db.get_data(old_cat_sql)
for old_cate_data in old_cate_array:
cat_name = str(old_cate_data['cat_name'])
category_thumb = str(old_cate_data['category_thumb'])
self.old_cat_dict[cat_name] = category_thumb
def __init__(self):
self.dao = CrawlDao.CrawlDao("athena_center", "local")
self.fileDao = FileUtil.FileDao()
self.stringUtil = StringUtil.StringUtil()
self.insert_pic_data_list = list()
self.update_goods_car_data_list = list()
# mac pic
self.max_pic_id = 0
# {{pic_num,pic_index}:[oe,oe...]}
self.pic_dict = dict()
def __init__(self):
self.dao = CrawlDao.CrawlDao()
self.stringUtil = StringUtil.StringUtil()
self.sql_category_table = 'db_category'
self.file_name = r'/Users/zxg/Desktop/old_cate.xlsx'
self.cate_id_name = dict()
self.cate_id_parent = dict()
self.second_cat_list = list()
# 其余行
cate_sql = "select cat_id,cat_name,parent_id from db_category where is_deleted = 'N' order by cat_id"
cate_array = self.dao.db.get_data(cate_sql)
for cate_data in cate_array:
cat_id = cate_data['cat_id']
cat_name = cate_data['cat_name']
parent_id = cate_data['parent_id']
self.cate_id_name[cat_id] = cat_name
self.cate_id_parent[cat_id] = parent_id
if int(parent_id) != 0:
self.second_cat_list.append(cat_id)
from selenium import webdriver import time from PIL import Image from selenium.common.exceptions import UnexpectedAlertPresentException, NoAlertPresentException, NoSuchElementException from selenium.webdriver.common.action_chains import ActionChains from selenium.webdriver.common.keys import Keys from util import Util import re import util.StringUtil as StringUil import os, sys from util.BaiduApiUtil import BaiDuApi from openpyxl import load_workbook # pip install openpyxl strUtil = StringUil.StringUtil() file = "C://Users/62526/Desktop/Test/职称信息1.xlsx" wb = load_workbook(file) wb.guess_types = True ws = wb.active name_column = 2 id_num_column = 3 column4 = 4 # 在职单位名称 column5 = 5 # 学历 column6 = 6 # #注册证书信息 column7 = 7 # 注册类别 column8 = 8 # 注册号 column9 = 9 # 注册单位 column10 = 10 # 发证机关 column11 = 11 # 签发日期 column12 = 12 # 有效期 column13 = 13 # #职称证书信息 column14 = 14 # 证书名称
