mzinfo/V2/app/tasks/preprocess.py

# -*- coding: utf-8 -*-
# @Author: privacy
# @Date:   2023-12-25 10:19:57
# @Last Modified by:   privacy
# @Last Modified time: 2024-01-12 14:26:31
import pandas as pd
from urllib import parse

all_keys = []

def parse_url(url):
    query_string = parse.urlparse(url)
    return query_string.scheme, query_string.netloc, query_string.path, query_string.params, query_string.fragment, parse.parse_qs(query_string.query)

def parse_path(url):
    path_string = parse.urlparse(url).path
    return path_string

def parse_appCode(url):
    query_string = parse.urlparse(url).query
    appCode = parse.parse_qs(query_string).get('appCode')
    if appCode:
        return appCode[0]

def parse_iframeUrl(url):
    fragment_string = parse.urlparse(url).fragment
    iframe_url = parse.parse_qs(fragment_string).get('url')
    iframe_from = parse.parse_qs(fragment_string).get('from')
    if iframe_url:
        path = parse.urlparse(iframe_url[0]).path
        if path and iframe_from:
            return path, iframe_from[0]
        elif path:
            return path, None
        elif iframe_from:
            return None, iframe_from[0]

def parse_appcontext(url):
    query_string = parse.urlparse(url).query
    appcontext = parse.parse_qs(query_string).get('appcontext')
    if appcontext:
        return appcontext[0]

def parse_Edit(url):
    query_string = parse.urlparse(url).query
    isEdit = parse.parse_qs(query_string).get('isEdit')
    if isEdit:
        return isEdit[0]

def parse_Query(url):
    query_string = parse.urlparse(url).query
    isQuery = parse.parse_qs(query_string).get('isQuery')
    if isQuery:
        return isQuery[0]

def parse_editFlag(url):
    query_string = parse.urlparse(url).query
    editFlag = parse.parse_qs(query_string).get('editFlag')
    if editFlag:
        return editFlag[0]


"""
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="基建管理应用")
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="数字供应链")
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="合同管理")
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="安全生产")
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="创新管理")
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="基建智慧工程")
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="并网服务管理")
# df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="基础应用")

# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="计划预算管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="成本管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="资金管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="核算管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="报账管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="工程财务管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="资产价值管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="物资财务管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="价格管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="税务管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="会计档案")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="共享服务")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="报表管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="综合管理")
# df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="基础应用")

df['tag'] = df['Unnamed: 1'].apply(lambda x: x.split()[2])
df['url'] = df['Unnamed: 1'].apply(lambda x: x.split()[1])

del df['Unnamed: 0']
del df['Unnamed: 1']

df.drop(df[df['tag'] == 'undefined'].index, inplace=True)

df.to_excel("temp.xlsx", sheet_name='Sheet1')
"""


# df['tag'] = df['url'].apply(lambda x: x.split("/")[-1].split("=")[-1])


"""
df = pd.read_excel("资产域关联字段查询表.xlsx", sheet_name="资产域")
del df['域']
df['domain'] = '资产域'

df['path'] = df['url'].apply(lambda x: parse_path(x))

df['appCode'] = df['url'].apply(lambda x: parse_appCode(x))

del df['url']

print(df)

df.to_json('资产域.json', orient='records', lines=True, force_ascii=False)
"""


"""
df = pd.read_excel("财务域关联字段查询表.xlsx", sheet_name="财务域")
df['domain'] = '财务域'

df['path'] = df['url'].apply(lambda x: parse_path(x))

df['appCode'] = df['url'].apply(lambda x: parse_appCode(x))

del df['url']

print(df)

df.to_json('财务域.json', orient='records', lines=True, force_ascii=False)
"""


"""
df = pd.read_excel("营销域关联字段查询表.xlsx", sheet_name="营销域")
df['一级标题'] = df['一级标题'].apply(lambda x: x.strip('\''))
df['二级标题'] = df['二级标题'].apply(lambda x: x.strip('\''))
df['三级标题'] = df['三级标题'].apply(lambda x: x.strip('\''))
df['四级标题'] = df['四级标题'].apply(lambda x: x.strip('\'') if isinstance(x, str) else None)
df['url'] = df['url'].apply(lambda x: x.strip('\''))
df['domain'] = '营销域'

df['path'] = df['url'].apply(lambda x: parse_path(x))

df['appcontext'] = df['url'].apply(lambda x: parse_appcontext(x))

df['isEdit'] = df['url'].apply(lambda x: parse_Edit(x))
df['editFlag'] = df['url'].apply(lambda x: parse_editFlag(x))
df['isQuery'] = df['url'].apply(lambda x: parse_Query(x))

print(df)

df.to_json('营销域.json', orient='records', lines=True, force_ascii=False)
"""


"""
df = pd.read_excel("人资域关联字段查询表.xlsx", sheet_name="Sheet1")
df['domain'] = '人资域'

df['netloc'] = '10.10.21.23'

df['path'] = df['url'].apply(lambda x: parse_path(x))

df['appCode'] = df['url'].apply(lambda x: parse_appCode(x))

df['iframe'] = df['url'].apply(lambda x: parse_iframeUrl(x))

del df['url']

print(df)

df.to_json('人资域.json', orient='records', lines=True, force_ascii=False)
"""