foodora_payroll_parser.py

# script to extract foodora payment info from a string
# assumes columns are organized as:
#	Order Code / Date / Time / KMs / Tips / Zone / Corp Tips

# for testing
info = '''s5wd-i3oh 31/01/2018 18:32:00 1.84 2.91 Toronto - Center
s3dj-e0fm 31/01/2018 18:41:00 0.25 3.75 Toronto - Center
s4rh-j6dp 31/01/2018 19:03:00 1.54 3.80 Toronto - Center
s4hf-f7ar 31/01/2018 19:20:00 0.23 4.35 Toronto - Center
s4bo-z2sn 31/01/2018 19:30:00 1.42 2.70 Toronto - Center
s5dr-g4oc 31/01/2018 19:52:00 1.71

- Toronto - Center
s5dr-g4oc 31/01/2018 19:52:00 1.71 Toronto - Center 2.09
s7gv-s7rw 31/01/2018 20:06:00 2.04

- Toronto - Center
s7gv-s7rw 31/01/2018 20:06:00 2.04 Toronto - Center 3.89'''

#info = raw_input('paste info: ')

def parse_info( info ):
	area_delim = 'Toronto - Center'

	info = info.replace ('Toronto - Center', '<AREA>')
	area_info = info
	info = info.replace('\n', ' ')
	info = info.replace('  ', ' ')
	info = info.split(' ')

	for i,e in enumerate(info):
		if '-' in e and len(e) == 9: info[i] = '<START>'	

	info = ' '.join(info)
	start_info = info
	info = info.split('<START>')

	n_orders = 0
	tips = 0
	distance = 0
	order_mult = 4.5
	distance_mult = 1

	seen_datetimes = {}
	for line in info:
		if len(line) < 4: continue
		#if '-' in items: continue
		items = line.split(' ')	
		print(line)
		print(items)

		item_date = items[1]
		item_time = items[2]
		datetime = item_date + item_time
		
		# n_orders
		if datetime not in seen_datetimes:	
			seen_datetimes[datetime] = ''
			n_orders += 1

		# tips
		if 't' not in seen_datetimes[datetime] and items[4] not in ['-','<AREA>']:	
			seen_datetimes[datetime] += 't'
			tips += float(items[4])

		# corp tips
		area_idx = items.index('<AREA>')
		if 'c' not in seen_datetimes[datetime] and len(items) > area_idx+1 and items[area_idx + 1] != '':	
			seen_datetimes[datetime] += 'c'
			tips += float(items[area_idx + 1])

		# distance
		distance += float(items[3] )

	print(' ')
	print('n orders: {}'.format(n_orders))
	print('tips: {}'.format(tips))
	print('distance: {}'.format(distance))
	total = n_orders * order_mult + distance * distance_mult + tips
	print('Total Income: {}'.format(total))