Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -6,18 +6,43 @@ import streamlit as st
|
|
| 6 |
import pandas as pd
|
| 7 |
import os
|
| 8 |
from google.oauth2.credentials import Credentials
|
|
|
|
|
|
|
| 9 |
from googleapiclient.discovery import build
|
| 10 |
from googleapiclient.http import MediaIoBaseDownload,MediaFileUpload
|
| 11 |
|
| 12 |
# Load credentials from environment variables
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
MAPPING_FILENAME = "Data Mapping with ItemCode.xlsx"
|
| 23 |
|
|
@@ -75,8 +100,11 @@ def convert_pdf_to_excel(pdf_file):
|
|
| 75 |
whole_data.columns = ["Part No.","Part Color Code","Part Name",'Date Qty']
|
| 76 |
extracted_file = "Data Extracted.xlsx"
|
| 77 |
data_for_mapping = "Data Mapping.xlsx"
|
|
|
|
| 78 |
extracted_data_for_mapping = whole_data.drop('Date Qty',axis=1)
|
| 79 |
extracted_data_for_mapping = extracted_data_for_mapping.drop_duplicates(subset=["Part No.","Part Color Code","Part Name"])
|
|
|
|
|
|
|
| 80 |
whole_data.to_excel(extracted_file, index=False)
|
| 81 |
extracted_data_for_mapping.to_excel(data_for_mapping, index=False)
|
| 82 |
return extracted_file,data_for_mapping
|
|
@@ -85,7 +113,7 @@ def map_data_to_template(excel_file, mapping_file):
|
|
| 85 |
# Load Excel file and mapping file
|
| 86 |
extracted_data = pd.read_excel(excel_file)
|
| 87 |
mapping_data = pd.read_excel(mapping_file)
|
| 88 |
-
mapping_data.to_excel(MAPPING_FILENAME)
|
| 89 |
save_mapping_file_to_drive()
|
| 90 |
mapping_data = mapping_data.rename(columns = {'Customer Part no as per pdf':'Part No.'})
|
| 91 |
|
|
@@ -102,7 +130,9 @@ def map_data_to_template(excel_file, mapping_file):
|
|
| 102 |
return mapped_data
|
| 103 |
|
| 104 |
def save_mapping_file_to_drive():
|
| 105 |
-
creds = Credentials.from_authorized_user_info(credentials_dict)
|
|
|
|
|
|
|
| 106 |
# Authenticate with Google Drive API
|
| 107 |
service = build('drive', 'v3', credentials=creds)
|
| 108 |
folder_id = "1HBRUZePST0D0buyU9MxeYg2vQyEL4wLF"
|
|
@@ -112,7 +142,7 @@ def save_mapping_file_to_drive():
|
|
| 112 |
q=f"'{folder_id}' in parents and mimeType='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'",
|
| 113 |
fields="files(id, name)").execute()
|
| 114 |
files = results.get('files', [])
|
| 115 |
-
files = [i for i in files if i.get('name')==
|
| 116 |
|
| 117 |
if not files:
|
| 118 |
print('No Excel Mapping files found in the folder.')
|
|
@@ -130,7 +160,9 @@ def save_mapping_file_to_drive():
|
|
| 130 |
service.files().create(body=file_metadata, media_body=media, fields='id').execute()
|
| 131 |
|
| 132 |
def pull_mapping_file_from_drive():
|
| 133 |
-
creds =
|
|
|
|
|
|
|
| 134 |
# Authenticate with Google Drive API
|
| 135 |
service = build('drive', 'v3', credentials=creds)
|
| 136 |
|
|
@@ -138,7 +170,7 @@ def pull_mapping_file_from_drive():
|
|
| 138 |
q="mimeType='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'",
|
| 139 |
fields="files(id, name)").execute()
|
| 140 |
files = results.get('files', [])
|
| 141 |
-
files = [i for i in files if i.get('name')==
|
| 142 |
if files:
|
| 143 |
file_id = files[0]['id']
|
| 144 |
file_name = files[0]['name']
|
|
@@ -153,8 +185,9 @@ def pull_mapping_file_from_drive():
|
|
| 153 |
|
| 154 |
fh.close()
|
| 155 |
return 1
|
| 156 |
-
return 0
|
| 157 |
|
|
|
|
|
|
|
| 158 |
|
| 159 |
def main():
|
| 160 |
st.title("PDF to Excel Converter")
|
|
@@ -168,6 +201,14 @@ def main():
|
|
| 168 |
# Convert PDF to Excel
|
| 169 |
extracted_file,data_for_mapping = convert_pdf_to_excel(uploaded_file)
|
| 170 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 171 |
# Download link for the Excel file
|
| 172 |
# st.markdown(f"Download the extracted data in Excel file [here](/{excel_file})")
|
| 173 |
|
|
@@ -183,23 +224,26 @@ def main():
|
|
| 183 |
else:
|
| 184 |
st.error("Error: Converted Excel file not found")
|
| 185 |
|
| 186 |
-
|
| 187 |
-
if not os.path.exists("Data Mapping with ItemCode.xlsx"):
|
| 188 |
st.markdown("## Upload the Data Master file with Item Code mapping")
|
| 189 |
mapping_uploaded_file = st.file_uploader("Upload the Data Master file with Item Code mapping", type=["xlsx","ods"])
|
| 190 |
else:
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 201 |
st.markdown("#### Using the Mapping file available in Google Drive")
|
| 202 |
-
mapping_uploaded_file =
|
| 203 |
|
| 204 |
if mapping_uploaded_file is not None:
|
| 205 |
# st.write("Uploaded Mapping Excel file:", mapping_uploaded_file.name)
|
|
|
|
| 6 |
import pandas as pd
|
| 7 |
import os
|
| 8 |
from google.oauth2.credentials import Credentials
|
| 9 |
+
from google.auth.transport.requests import Request
|
| 10 |
+
from google_auth_oauthlib.flow import InstalledAppFlow
|
| 11 |
from googleapiclient.discovery import build
|
| 12 |
from googleapiclient.http import MediaIoBaseDownload,MediaFileUpload
|
| 13 |
|
| 14 |
# Load credentials from environment variables
|
| 15 |
+
config = {'installed': {'client_id': os.environ.get("client_id"),
|
| 16 |
+
'project_id': os.environ.get("project_id"),
|
| 17 |
+
'auth_uri': os.environ.get("auth_uri"),
|
| 18 |
+
'token_uri': os.environ.get("token_uri"),
|
| 19 |
+
'auth_provider_x509_cert_url': os.environ.get("auth_provider_x509_cert_url"),
|
| 20 |
+
'client_secret': os.environ.get("client_secret"),
|
| 21 |
+
'redirect_uris': ['http://localhost']}}
|
| 22 |
+
|
| 23 |
+
SCOPES = ['https://www.googleapis.com/auth/drive']
|
| 24 |
+
|
| 25 |
+
def authenticate():
|
| 26 |
+
creds = None
|
| 27 |
+
|
| 28 |
+
# Check if token file exists
|
| 29 |
+
if os.path.exists('token.json'):
|
| 30 |
+
creds = Credentials.from_authorized_user_file('token.json')
|
| 31 |
+
|
| 32 |
+
# If no valid credentials available, ask the user to login
|
| 33 |
+
if not creds or not creds.valid:
|
| 34 |
+
if creds and creds.expired and creds.refresh_token:
|
| 35 |
+
creds.refresh(Request())
|
| 36 |
+
else:
|
| 37 |
+
# flow = InstalledAppFlow.from_client_secrets_file("credentials.json", SCOPES)
|
| 38 |
+
flow = InstalledAppFlow.from_client_config(config,SCOPES)
|
| 39 |
+
creds = flow.run_local_server(port=0)
|
| 40 |
+
|
| 41 |
+
# Save the credentials for next run
|
| 42 |
+
with open('token.json', 'w') as token:
|
| 43 |
+
token.write(creds.to_json())
|
| 44 |
+
|
| 45 |
+
return creds
|
| 46 |
|
| 47 |
MAPPING_FILENAME = "Data Mapping with ItemCode.xlsx"
|
| 48 |
|
|
|
|
| 100 |
whole_data.columns = ["Part No.","Part Color Code","Part Name",'Date Qty']
|
| 101 |
extracted_file = "Data Extracted.xlsx"
|
| 102 |
data_for_mapping = "Data Mapping.xlsx"
|
| 103 |
+
|
| 104 |
extracted_data_for_mapping = whole_data.drop('Date Qty',axis=1)
|
| 105 |
extracted_data_for_mapping = extracted_data_for_mapping.drop_duplicates(subset=["Part No.","Part Color Code","Part Name"])
|
| 106 |
+
extracted_data_for_mapping.columns = ['Customer Part no as per pdf','Customer Part name as per pdf','Customer Part color as per pdf']
|
| 107 |
+
|
| 108 |
whole_data.to_excel(extracted_file, index=False)
|
| 109 |
extracted_data_for_mapping.to_excel(data_for_mapping, index=False)
|
| 110 |
return extracted_file,data_for_mapping
|
|
|
|
| 113 |
# Load Excel file and mapping file
|
| 114 |
extracted_data = pd.read_excel(excel_file)
|
| 115 |
mapping_data = pd.read_excel(mapping_file)
|
| 116 |
+
mapping_data.to_excel(MAPPING_FILENAME,index=False)
|
| 117 |
save_mapping_file_to_drive()
|
| 118 |
mapping_data = mapping_data.rename(columns = {'Customer Part no as per pdf':'Part No.'})
|
| 119 |
|
|
|
|
| 130 |
return mapped_data
|
| 131 |
|
| 132 |
def save_mapping_file_to_drive():
|
| 133 |
+
# creds = Credentials.from_authorized_user_info(credentials_dict)
|
| 134 |
+
creds = authenticate()
|
| 135 |
+
service = build('drive', 'v3', credentials=creds)
|
| 136 |
# Authenticate with Google Drive API
|
| 137 |
service = build('drive', 'v3', credentials=creds)
|
| 138 |
folder_id = "1HBRUZePST0D0buyU9MxeYg2vQyEL4wLF"
|
|
|
|
| 142 |
q=f"'{folder_id}' in parents and mimeType='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'",
|
| 143 |
fields="files(id, name)").execute()
|
| 144 |
files = results.get('files', [])
|
| 145 |
+
files = [i for i in files if i.get('name')==MAPPING_FILENAME]
|
| 146 |
|
| 147 |
if not files:
|
| 148 |
print('No Excel Mapping files found in the folder.')
|
|
|
|
| 160 |
service.files().create(body=file_metadata, media_body=media, fields='id').execute()
|
| 161 |
|
| 162 |
def pull_mapping_file_from_drive():
|
| 163 |
+
creds = authenticate()
|
| 164 |
+
service = build('drive', 'v3', credentials=creds)
|
| 165 |
+
# creds = Credentials.from_authorized_user_info(credentials_dict)
|
| 166 |
# Authenticate with Google Drive API
|
| 167 |
service = build('drive', 'v3', credentials=creds)
|
| 168 |
|
|
|
|
| 170 |
q="mimeType='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'",
|
| 171 |
fields="files(id, name)").execute()
|
| 172 |
files = results.get('files', [])
|
| 173 |
+
files = [i for i in files if i.get('name')==MAPPING_FILENAME]
|
| 174 |
if files:
|
| 175 |
file_id = files[0]['id']
|
| 176 |
file_name = files[0]['name']
|
|
|
|
| 185 |
|
| 186 |
fh.close()
|
| 187 |
return 1
|
|
|
|
| 188 |
|
| 189 |
+
print('No Excel files found.')
|
| 190 |
+
return 0
|
| 191 |
|
| 192 |
def main():
|
| 193 |
st.title("PDF to Excel Converter")
|
|
|
|
| 201 |
# Convert PDF to Excel
|
| 202 |
extracted_file,data_for_mapping = convert_pdf_to_excel(uploaded_file)
|
| 203 |
|
| 204 |
+
file_present = pull_mapping_file_from_drive()
|
| 205 |
+
|
| 206 |
+
if file_present:
|
| 207 |
+
mapping_data_from_drive = pd.read_excel(MAPPING_FILENAME)
|
| 208 |
+
extracted_data_for_mapping = pd.read_excel(data_for_mapping)
|
| 209 |
+
extracted_data_for_mapping = extracted_data_for_mapping.merge(mapping_data_from_drive, on = ['Customer Part no as per pdf','Customer Part name as per pdf','Customer Part color as per pdf'], how='outer')
|
| 210 |
+
extracted_data_for_mapping.to_excel(data_for_mapping,index=False)
|
| 211 |
+
|
| 212 |
# Download link for the Excel file
|
| 213 |
# st.markdown(f"Download the extracted data in Excel file [here](/{excel_file})")
|
| 214 |
|
|
|
|
| 224 |
else:
|
| 225 |
st.error("Error: Converted Excel file not found")
|
| 226 |
|
| 227 |
+
if not file_present:
|
|
|
|
| 228 |
st.markdown("## Upload the Data Master file with Item Code mapping")
|
| 229 |
mapping_uploaded_file = st.file_uploader("Upload the Data Master file with Item Code mapping", type=["xlsx","ods"])
|
| 230 |
else:
|
| 231 |
+
try:
|
| 232 |
+
mapping_data = pd.read_excel(MAPPING_FILENAME)
|
| 233 |
+
# mapping_data = mapping_data.rename(columns = {'Customer Part no as per pdf':'Part No.'})
|
| 234 |
+
data_for_mapping = "Data Mapping.xlsx"
|
| 235 |
+
extracted_data_for_mapping = pd.read_excel(data_for_mapping)
|
| 236 |
+
extracted_data_for_mapping = extracted_data_for_mapping[~extracted_data_for_mapping['Customer Part no as per pdf'].isin(mapping_data['Customer Part no as per pdf'])]
|
| 237 |
+
unmapped_part_no = extracted_data_for_mapping['Customer Part no as per pdf'].nunique()
|
| 238 |
+
if unmapped_part_no>0:
|
| 239 |
+
st.markdown("#### There are {} Part No. with No ItemCode present. Upload a new file after mapping them".format(unmapped_part_no))
|
| 240 |
+
mapping_uploaded_file = st.file_uploader("Upload the Data Master file with Item Code mapping", type=["xlsx","ods"])
|
| 241 |
+
else:
|
| 242 |
+
st.markdown("#### Using the Mapping file available in Google Drive")
|
| 243 |
+
mapping_uploaded_file = MAPPING_FILENAME
|
| 244 |
+
except:
|
| 245 |
st.markdown("#### Using the Mapping file available in Google Drive")
|
| 246 |
+
mapping_uploaded_file = MAPPING_FILENAME
|
| 247 |
|
| 248 |
if mapping_uploaded_file is not None:
|
| 249 |
# st.write("Uploaded Mapping Excel file:", mapping_uploaded_file.name)
|