Created
June 6, 2015 00:15
-
-
Save dgellow/8fbde8583b70560863be to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from os import path | |
import re | |
import pdb | |
import sys | |
filename = path.join( | |
path.dirname(__file__), 'semaine_depenses.txt' | |
) | |
with open(filename, 'r') as file: | |
data = file.read() | |
# Split file data by week | |
weeks = re.compile('"\s*"').split(data) | |
# Remove double quotes | |
weeks = [week.replace('"', '') for week in weeks] | |
csv_file = open('data.csv', 'w') | |
for week in weeks: | |
try: | |
full_week_number = re.compile('^.*\n').findall(week)[0] | |
week_number = re.search('\d+', week).group(0) | |
week = week.replace(full_week_number, '') | |
except: | |
pdb.set_trace() | |
for day in week.split('\n\n'): | |
splitted_day = day.split('\n') | |
date = splitted_day[0] | |
only_items = [item for item in splitted_day if ':' in item] | |
for item in only_items: | |
try: | |
item_parts_arr = re.findall('(.+):\s+(\S+)\s+(.+)?$', | |
item) | |
item_parts = item_parts_arr[0] if item_parts_arr else [] | |
location = item_parts[0] if item_parts else '' | |
price = item_parts[1] if len(item_parts) > 1 else '' | |
thing = item_parts[2] if len(item_parts) > 2 else '' | |
except: | |
pdb.set_trace() | |
csv_data = ';'.join([ | |
week_number, | |
date, | |
location, | |
price, | |
thing | |
]) | |
csv_file.write(csv_data + '\n') | |
csv_file.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment