Machine Learning local --> SRT

ml2srt.py

from xml.dom.minidom import parse
import os

def getText(nodelist):
    rc = []
    for node in nodelist:
        if node.nodeType == node.TEXT_NODE:
            rc.append(node.data)
    return ''.join(rc)

def startGr(slide,file_o):
    getListOf(slide.getElementsByTagName("p"), file_o)

def getListOf(points, file_o):
    i=1
    f=open('video/10/'+file_o, 'w')
    for point in points:
            f.write(str(i)+'\n')
            begin = point.getAttribute('begin').split(':')
            dur = point.getAttribute('dur').split(':')
            h=str( (int(begin[0])+int(dur[0])) if (int(begin[0])+int(dur[0]))>10 else '0'+str(int(begin[0])+int(dur[0])) )
            m=str(int(begin[1])+int(dur[1])) if (int(begin[1])+int(dur[1]))>10 else '0'+str(int(begin[1])+int(dur[1]))
            f.write(point.getAttribute('begin').split('.')[0]+','+ point.getAttribute('begin').split('.')[1]+' -->'+''.join(h+':'+m+':'+str(float(begin[2])+float(dur[2])).split('.')[0]+','+str(float(begin[2])+float(dur[2])).split('.')[1]  ))
            f.write(getText(point.childNodes)+'\n\n')
            i+=1

listing = os.listdir('xml/')

for file_i in listing:
        dom= parse('xml/'+file_i)
        file_o=file_i.split('-subtitles.xml')[0]+'.srt'
        startGr(dom, file_o)