from pprint import pprint

filedata = ("""<codec freq="140.15">
    <face actor="SOLID SNAKE" image="f73b"></face>
    <face actor="MERYL SILVERBURGH" image="7702"></face>
    <face actor="MERYL SILVERBURGH" image="7d66"></face>
    <voice hash="3d43">
        <text actor="MERYL SILVERBURGH" face="39c3">Be careful, Snake. That air lock is set with infrared sensors.</text>
    </voice>
    <if condition="02:0 IsZero writeVAR[01009c]">
        <voice hash="3d5a">
            <text actor="MERYL SILVERBURGH" face="39c3">You probably can't see them with your naked eyes, but there are infrared beams coming out of that wall.</text>
            <text actor="MERYL SILVERBURGH" face="39c3">Touch any one of them, and the doors will seal off and the place will be flooded with poison gas.</text>
            <text actor="MERYL SILVERBURGH" face="39c3">Somehow, you've got to get through without setting off those sensors.</text>
        </voice>
        <set math="writeVAR[01009c] = 02:1"></set>
    </if>

    <face actor="MERYL SILVERBURGH" image="6d84"></face>
</codec>""" )

def clean(filedata): # Receives codec filedata, removes tabs and empty lines, then returns list of lines.
    filedata = filedata.replace("\t", "")
    filedata = filedata.replace("\n\n", "\n")

    return filedata.splitlines() # returning as intended (text and number of lines)


def getLineID(Line):
    Line = Line.lstrip(' ')
    LineId = Line[Line.find('<')+1:Line.find(' ')]

    return LineId

def getLineAttr(Line):
    Line = Line.lstrip(' ')
    LineAttr = []

    for Lina in Line.split(' '):
        if Lina.find('"') != -1:
            Lina.replace('"', '')
            LineAttr.append({
                Lina.replace('=', ':')
            })

    return LineAttr

testCode = clean(filedata)
dick = []

for testLine in testCode:
    a = []
    a.append(getLineID(testLine))
    a.append(getLineAttr(testLine))
    dick.append(a)