Jon’s Project Blog

# python script to extract lecture slides and mp3's from UCSF lecture files for conversion
 
#requires swfextract
 
import commands,sys,re
 
def parse(filename):
    #check filename for .swf extension
    if not filename.find('.swf'): # not a comprehensive check
        return
 
    #open file
    status, output = commands.getstatusoutput("swfextract %s" % (filename,))
 
    print output
 
    #find "JPEGs: ID(s)"
    slide_identifier = "JPEGs: ID(s)"
    start=output.find(slide_identifier)
    slide_extract=[]
    if start:
        start += len(slide_identifier)+1
        slide_end = output.find("[-s]",start)
        print start,slide_end
        slide_extract=output[start:slide_end-2].replace(" ","")
 
    #find "Sounds: ID(s)"
    sound_identifier = "Sounds: ID(s)"
    start=output.find(sound_identifier)
    sound_extract=[]
    if start:
        start += len(sound_identifier)+1
        sound_end = output.find("[-f]",start)
        sound_extract=output[start:sound_end-2].replace(" ","")
 
    # now extract all the data
    print "swfextract %s -P -j %s -s %s" % (filename,slide_extract,sound_extract)
 
    status, output = commands.getstatusoutput("swfextract %s -P -j %s -s %s" % (filename,slide_extract,sound_extract))
 
    return slide_extract,sound_extract
 
def create(slide_extract,sound_extract,outputfile):
    #first throw out every other picture because second picture is always a thumbnail
    slides=slide_extract.replace(","," ").split(" ");
    slides=[slides[i] for i in range(len(slides)) if i%2 ==0]
 
    sounds=sound_extract.replace(","," ").split(" ");
 
    print "Number of slides: %s, number of mp3's: %s" % (len(slides),len(sounds))
    for i in range(len(sounds)):
 
        vidcmd="jpeg2yuv -n %d -I p -f 2 -j %s | yuv2lav -o temp.avi" % (int(round(2*10*(duration("sound%s.mp3" % (sounds[i],))))/10),"pic%s.jpg" % (slides[i],))
        # print vidcmd
        status,output=commands.getstatusoutput(vidcmd)
 
        sndcmd="mencoder temp.avi -o slide%d.avi -ovc lavc -lavcopts vcodec=msmpeg4 -oac copy -audiofile sound%s.mp3" %(i,sounds[i])
 
        # print sndcmd
        commands.getstatusoutput(sndcmd)
        print "Finished processing slide %d" % (i,)
 
    print "Cleaning up..."
    # remove unnecessary data
    commands.getstatusoutput("rm *.jpg *.mp3 temp.avi")
 
    slidevids=["slide%s.avi" % (i,) for i in range(len(slides))]
 
    slidevids=" ".join(slidevids)
 
    print "Combining slides..."
    # combine all of them
    commands.getstatusoutput("mencoder -oac copy -ovc copy %s -o %s" % (slidevids,outputfile))
 
    print "Cleaning up..."
    commands.getstatusoutput("rm slide*.avi")
 
def duration(mp3):
    # find duration of mp3 using exiftool
    cmd="exiftool %s -Duration -n -S -s" % (mp3,)
    status,output = commands.getstatusoutput(cmd)
    return float(output)
 
if __name__=="__main__":
    slides,sounds=parse(sys.argv[1])
    if len(sys.argv)==2:
        create(slides,sounds,"output.avi")
    elif len(sys.argv)==3:
        create(slides,sounds,sys.argv[2])