match_ids.py

import ififuncs
import sys
import csv
# Create a list containing dictionaries of the spreadsheet values, and the relevant headings.
filmo_data = ififuncs.extract_metadata(sys.argv[1])
tech_data = ififuncs.extract_metadata(sys.argv[2])

# This just isolates the list of dictionaries, not the spreadsheet headings.
filmo_dict = filmo_data[0]
tech_dict = tech_data[0]

# Initialising some empty lists that we will populate by auditing the data later in the script.
new_tech_list = []
filmo_records_with_tech_records = []

# Loop through each filmographic record
for filmo_record in filmo_dict:
    #print filmo_record
    # Grab the OE number for a record
    filmo_oe_number = filmo_record['Object Entry']
    # For each OE number in the filmographic, loop through the tech records..
    for tech_record in tech_dict:
        # Keep looping through the tech records until the Object Entry number matches the one in the filmographic
        tech_oe_number = tech_record['Reference Number']
        if filmo_oe_number == tech_oe_number:
            # updates the 'new tech record' with the correct AFXXXXX reference number.
            tech_record['new_ref'] = filmo_record['Reference Number']
            new_tech_list.append(tech_record)
            #print tech_record['Accession Number'], filmo_oe_number, tech_oe_number, filmo_record['Reference Number'], tech_record['new_ref']
            filmo_records_with_tech_records.append(filmo_record['Reference Number'])
all_filmos = []
for i in filmo_dict:
    all_filmos.append(i['Reference Number'])
for x in all_filmos:
    if x not in filmo_records_with_tech_records:
        print x    
with open(sys.argv[3], 'w') as csvfile:
            fieldnames = tech_data[1]
            writer = csv.DictWriter(csvfile, fieldnames=fieldnames, delimiter=',', lineterminator='\n')
            writer.writeheader()
            for i in new_tech_list:
                writer.writerow(i)