class Entry:
    def __init__(self):
        self.dupes = []

    def add(self, l):
        self.dupes.append(l.split("	"))

    def _parse(self, s):
        s = s.split(' ')[0]      # remove the ' MB' suffix
        s = s.replace(',', '.')  # change , into . for float(...) parsing
        try:
            return float(s)
        except:
            return 0.0


    def size(self):
        s = self.dupes[0][2]     # 3rd field of the first 'line'
        return self._parse(s)

    def name(self):
        return self.dupes[0][0]

    def count(self):
        return len(self.dupes)

    def __repr__(self):
        n = self.name()
        c = self.count()
        s = self.size()
        return '%s : %d * %d MB' % (n, c, s)

class Entry2(Entry):
    def add(self, l):
        fs = l.split("	")
        self.n = fs[0]
        self.s = self._parse(fs[2])
        path = fs[1]
        date = fs[3]
        self.dupes.append((path, date))

    def name(self):
        return self.n

    def size(self):
        return self.s

def remap(lines, kind=Entry2):
    e = None
    for l in lines:
        if l.startswith('--------------'):
            yield e
            e = kind()
            continue
        else:
            e.add(l)

def main(f):
    with open(f, "r") as i:
        ls = i.readlines()
        yield from remap(ls)

F = "c:/Users/noob/Desktop/duplicate_marion.txt"
es = main(F)
total = sum(e.size() for e in es if e)