Untitled

#USAGE: md5-convert.py "directory_with_files" ".csv file"

import hashlib
import codecs
import sys
import os
import re
import time

DIR = sys.argv[1]
CSV_FILE= sys.argv[2]
count = 0;

#gets md5 hash of file
def md5(fname):
    hash = hashlib.md5()
    with open(fname, "rb") as f:
        for chunk in iter(lambda: f.read(4096), b""):
            hash.update(chunk)
    return hash.hexdigest()

f = codecs.open(CSV_FILE, encoding='utf-8', mode='r')
data = f.read()
f.close()

with codecs.open(CSV_FILE, encoding='utf-8', mode='r') as f:
  for line in f:

    line = line[:-1]
    line = line.split('\t')
    ext = re.search("\.jpg|\.jpeg|\.png|\.gif|\.webm", line[2]).group(0)
    hash = line[1]

    #construct absolute path for the md5 function
    path = sys.argv[1] + '\\'+ hash + ext

    #check to make sure the file exists
    if os.path.isfile(path) and os.access(path,os.R_OK):
        filehash = md5(path)
        newdata = data.replace(hash,filehash)

        #write data to temp file
        f2 = codecs.open('temp.csv',encoding='utf-8', mode='w')
        f2.write(newdata)
        f2.close()

        #set old data to the newdata
        data = newdata
        count+=1
        print "line #{count}  converted to md5.".format(count = count)
        #time.sleep(.250)

print "All hashes have been converted."