# coding: utf-8

import re

fileName = 'tweets.csv'
f = open(fileName, 'r', encoding="utf-8_sig")

totalMinutes = 0

while True:
    line = f.readline()
    
    if not line:
        print('line is false')
        break
    if not isinstance(line, str):
        break

    # get study time
    matchStudy = re.search(r'(#mandarin\s*)(#study\s*)(\d+)(\s*)', line)

    # get date info
    matchDate = re.search(r'(\d{4})-(\d{2}-\d{2} \d{2}:\d{2}:\d{2})', line)

    if matchDate and matchStudy:
        if int(matchDate.group(1)) == 2014:
            if matchStudy:
                print('found :',matchStudy.group(3))
                totalMinutes += int(matchStudy.group(3))

print('合計時間 ',totalMinutes,'分')