Kadaster-zoekschil-conversie

1-Kadaster-zoekschil-conversie.py

#!/usr/bin/env python3
import csv,os
from collections import defaultdict

rows = [ row for row in csv.DictReader(open("kadaster.csv")) ]

# "id","gemeente","arrondissement","dvd_nr","dvd_code","soort","leggerart","begin","eind","begino","eindo","invnr","reeksdeel","Sectie","pad","filenaam","naam1","naam2"

file_paths = defaultdict(list)

inv_nrs = defaultdict(dict)

for row in rows:
	file_path = row['dvd_nr'] + row['pad'] + row["filenaam"]
	file_paths[file_path].append(row)    # row is any row
	inv_nrs[row["invnr"].strip()][row["filenaam"]] = row #.append(row)

for inv_nr,rows in inv_nrs.items():
	source_folder = "/Volumes/archiefbestanden\\$/Kadaster/DVD\\'s/"
	dest_folder = "scans/Kadaster-Scans/scans/NL-UtHUA_1294_" + inv_nr

	if not os.path.isdir(dest_folder):
		os.makedirs(dest_folder)

	for filename,row in rows.items():
		
		source_file_path = source_folder + (row['dvd_nr'] + row['pad'] + row["filenaam"]).replace("\\","/")
		dest_file_path = dest_folder + "/NL-UtHUA_1294_" + inv_nr + "_" + row["filenaam"]
		
		print(source_file_path + "\t" + dest_file_path)
	

2.Kadaster-zoekschil-copy-convert.py

#!/usr/bin/env python3
import csv,os,sys
from collections import defaultdict
from joblib import Parallel, delayed
from tqdm import tqdm
import shutil
from os.path import exists

def processRow(row):
	src = row["src"]
	dst = row["dst"]

	if not exists(src.replace("\\","")):
		print(f"ERROR src: {src} not found")
		return

	# create dst folder recursive
	dest_folder = os.path.split(dst)[0]
	if not os.path.isdir(dest_folder):
		os.makedirs(dest_folder)

	# check extension, convert TIF to JPG or just copy JPG 
	dst = dst.replace(".TIF",".JPG")

	if exists(dst):
		# print(f"SKIP {dst} already exists.")
		return

	filename, ext = os.path.splitext(dst)
	if ext==".TIF":
		os.system(f"convert {src} {dst} 2>>err.txt")
	elif ext==".JPG":
		src_without_backlash = src.replace("\\","")
		shutil.copy2(src_without_backlash, dst)
	else:
		print(f"ERROR file format unsupported: {src} {dst}")
		return


	if not exists(dst):
		print(f"ERROR dst: {dst} not found for src: {src}.")
		# os.system(f"ffmpeg -i {src} {dst}")

		# if not exists(dst):
		# 	print(f"Error dst: {dst} STILL not found for src: {src}")
		# else:
		# 	print(f"Succesfully converted {src} to {dst} using FFMPEG")



rows = [ dict(row) for row in csv.DictReader(open("scans.tsv"), delimiter='\t', fieldnames=["src","dst"]) ]

results = Parallel(n_jobs=8)(
  delayed(processRow)(row)
  for row in tqdm(rows)
)