Read PDF and extract data in JSON format

I have a PDF file which contains a variable number of entries which are to be extracted to a JSON output format. The number of pages varies. The PDF follows a fairly set structure but some of the entries are optional.





Deliverables



A Python based solution using any of the popular Python PDF libraries. You will need to support me setting up my local development environment to run your code.









Output JSON example



{

"JSON_creation_date_time" : "15/01/2024 15.38",

"document_date": "Catalogue for Sale on Monday, January, 15, 2024",

"source_pdf_pages": "31",

"vehicles": [

{

"lot": "10203",

"registration": "SL64RZJ",

"make_model": "MERCEDES-BENZ A180 BLUE-CY AMG SPORT CD -",

"colour": "White",

"mileage": "85,327",

"row": "OBOL",

"running_order": "(1)",

"registration_date": "17/11/2014",

"body_type": "5 Door Hatchback",

"location": "Glasgow",

"mileage_warranty": "Warranted",

"fuel_type": "Diesel",

"v5_location": "V5 - HERE",

"MOT": "16/11/2024",

"owners": "Four Owners",

"previous_registration": "D17LAK",

"service_history": "Service History - 6 stamp(s)",

"extras": "~Extras~ Air Con, Climate, Cruise Control, Alloy Wheels, Sat Nav, Bluetooth ~",

"supplier": "Main Agent",

"at_retail": "8779",

"price_CAP_retail": "7800",

"price_clean": "5825",

"price_average": "5100",

"price_below": "4375"

},

{

"lot": "10222",

"registration": "SC65SBX",

"make_model": "RENAULT CAPTUR DYNAMIQUE NAV DCI - 1461cc",

"colour": "Blue/cream",

"mileage": "65,353",

"row": "2",

"running_order": "(2)",

"registration_date": "25/11/2015",

"body_type": "5 Door Hatchback",

"location": "Glasgow",

"mileage_warranty": "Warranted",

"fuel_type": "Diesel",

"v5_location": "V5 - HERE",

"MOT": "19/10/2024",

"owners": "Four Owners",

"previous_registration": "K123WLS",

"service_history": "6 stamp(s)",

"extras": "~Extras~ Air Con, Climate, Cruise Control, Alloy Wheels, Sat Nav, Bluetooth ~",

"supplier": "Main Agent",

"at_retail": "6788",

"price_CAP_retail": "6400",

"price_clean": "4600",

"price_average": "3900",

"price_below": "3225"

}

]

}







PDF to field mapping



1 = "lot"

2 = "registration"

3 = "make_model"

4 = "colour"

5 = "mileage"

6 = "row"

7 = "running_order"

8 = "registration_date"

9 = "body_type"

10 = "location"

11 = "mileage_warranty"

12 = "fuel_type"

13 = "v5_location"

14 = "MOT"

15 = "owners"

16 = "previous_registration"

17 = "service_history"

18 = "extras"

19 = "supplier"

20 = "at_retail"

21 = "price_CAP_retail"

22 = "price_clean"

23 = "price_average"

24 = "price_below"