Spaces:
Running
Running
File size: 5,560 Bytes
f20a244 3ad62d6 f20a244 3ad62d6 f20a244 3ad62d6 f20a244 3ad62d6 f20a244 3ad62d6 f20a244 3ad62d6 f20a244 3ad62d6 f20a244 3ad62d6 f20a244 27a08f1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 |
import PyPDF2
import pandas as pd
import os
import ast
import streamlit as st
import pandas as pd
def convert_pdf_to_excel(pdf_file):
inputpdf = PyPDF2.PdfReader(pdf_file)
pages_no = len(inputpdf.pages)
whole_data = []
for i in range(pages_no):
inputpdf = PyPDF2.PdfReader(pdf_file)
# output = PyPDF2.PdfWriter()
# output.add_page(inputpdf.pages[i])
pageObj = inputpdf.pages[i]
page_content = pageObj.extract_text()
for each_table in [i for i in page_content.split('Delivery Schedule Sheet') if i]:
data = each_table.split('\n')
each_table_data = []
date_qty = []
row_start_index = 0
row_stop_index = 0
for index in range(len(data)):
if data[index].strip() == 'Part No.':
each_table_data.append(data[index+1].replace('Part Color Code',""))
if 'Part Name' not in data[index+2]:
each_table_data.append(data[index+2].replace('Part Color Code',""))
else:
each_table_data.append("")
if 'Part Name' in data[index].strip():
each_table_data.append(data[index+1])
if data[index].strip() == 'ADJ':
row_start_index = index + 1
if data[index].strip() == 'Total':
row_stop_index = index
if row_start_index>0 and row_stop_index>0:
for index in range(row_start_index,row_stop_index):
if '/' in data[index].strip():
date_qty.append([data[index].strip()[-5:].strip(),data[index+1].strip()])
if not date_qty:
date_qty = [["",""]]
each_table_data.append(date_qty)
whole_data.append(each_table_data)
whole_data = pd.DataFrame(whole_data)
whole_data.columns = ["Part No.","Part Color Code","Part Name",'Date Qty']
extracted_file = "Data Extracted.xlsx"
data_for_mapping = "Data Mapping.xlsx"
extracted_data_for_mapping = whole_data.drop('Date Qty',axis=1)
extracted_data_for_mapping = extracted_data_for_mapping.drop_duplicates(subset=["Part No.","Part Color Code","Part Name"])
whole_data.to_excel(extracted_file, index=False)
extracted_data_for_mapping.to_excel(data_for_mapping, index=False)
return extracted_file,data_for_mapping
def map_data_to_template(excel_file, mapping_file):
# Load Excel file and mapping file
extracted_data = pd.read_excel(excel_file)
mapping_data = pd.read_excel(mapping_file)
mapping_data = mapping_data.rename(columns = {'Customer Part no as per pdf':'Part No.'})
# Perform mapping
extracted_data['Date Qty'] = extracted_data['Date Qty'].apply(lambda x: ast.literal_eval(x))
extracted_data = extracted_data.explode('Date Qty')
extracted_data[['SchDate','Qty']]= pd.DataFrame(extracted_data['Date Qty'].to_list(), index= extracted_data.index)
extracted_data = extracted_data.drop('Date Qty',axis=1)
mapped_data = extracted_data.merge(mapping_data, on =['Part No.'])[['Item Code','SchDate','Qty']]
return mapped_data
def main():
st.title("PDF to Excel Converter")
# File uploader
uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
if uploaded_file is not None:
st.write("Uploaded PDF file:", uploaded_file.name)
# Convert PDF to Excel
extracted_file,data_for_mapping = convert_pdf_to_excel(uploaded_file)
# Download link for the Excel file
# st.markdown(f"Download the extracted data in Excel file [here](/{excel_file})")
if os.path.exists(data_for_mapping):
with open(data_for_mapping, "rb") as f:
excel_bytes = f.read()
st.download_button(
label="Download Excel file",
data=excel_bytes,
file_name=data_for_mapping,
mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
)
else:
st.error("Error: Converted Excel file not found")
st.markdown("## Upload the Data Master file with Item Code mapping")
mapping_uploaded_file = st.file_uploader("Upload the Data Master file with Item Code mapping", type=["xlsx","ods"])
if mapping_uploaded_file is not None:
st.write("Uploaded Mapping Excel file:", mapping_uploaded_file.name)
# Perform data mapping
mapped_data = map_data_to_template(extracted_file, mapping_uploaded_file)
# Provide a link to download the final Excel file after mapping
st.markdown("### Final Excel File After Mapping")
final_excel_file = 'Final Data.xlsx'
mapped_data.to_excel(final_excel_file, index=False)
if os.path.exists(final_excel_file):
with open(final_excel_file, "rb") as f:
excel_bytes = f.read()
st.download_button(
label="Download Excel file",
data=excel_bytes,
file_name=final_excel_file,
mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
)
else:
st.error("Error: Converted Excel file not found")
if __name__ == "__main__":
main() |