Marathi Voter PDF Data Extraction
Budget: ₹4,000 – ₹5,000 INR
I have several thousand voter-list PDFs written entirely in Marathi. I need a reliable workflow—script, desktop utility, or small web app—that will scan every page, recognise the Marathi text correctly, and export each voter’s details to an Excel spreadsheet.
The fields I must see in separate columns are:
• Name and address
• Voter ID / EPIC number with any contact details that appear
• Date of birth and gender
• Age
Accuracy is critical; diacritics and vowel signs in Marathi must not be lost or misread. I will provide sample PDFs so you can tune your OCR or pattern-matching logic. The final deliverable is:
1. An Excel file containing every voter record, perfectly aligned to the columns above.
2. The complete, well-commented source code or repeatable process so I can rerun it on future PDF batches.
Please ensure the solution works end-to-end on bulk data (thousands of pages) without manual intervention once started, and that it can be executed on a standard Windows machine or through a simple Python environment I can set up myself.
The fields I must see in separate columns are:
• Name and address
• Voter ID / EPIC number with any contact details that appear
• Date of birth and gender
• Age
Accuracy is critical; diacritics and vowel signs in Marathi must not be lost or misread. I will provide sample PDFs so you can tune your OCR or pattern-matching logic. The final deliverable is:
1. An Excel file containing every voter record, perfectly aligned to the columns above.
2. The complete, well-commented source code or repeatable process so I can rerun it on future PDF batches.
Please ensure the solution works end-to-end on bulk data (thousands of pages) without manual intervention once started, and that it can be executed on a standard Windows machine or through a simple Python environment I can set up myself.
Related categories:
Python
Visual Basic
Data Processing
Data Entry
Excel
OCR
Data Extraction
Data Analysis
Data Management
Text Recognition