asdf forums

Code: Select all

src = r'root folder' #This had the location of the set of files

import os
from os.path import join
import codecs

for root, dirs, names in os.walk(src): #This loops through all of the directories and subdirectories.
    for name in names: #This loops through all of the files in the current directory.
        #r+ lets me read and write from the files. b basically means that the returns are conserved.
        with codecs.open(join(root,name), 'rb+', 'UTF-8') as a:
            #get the file contents in UTF-8, encode in ASCII, and replace characters outside of the ASCII range.
            #In one line.
            temp = a.read().encode('ascii', 'backslashreplace').replace('\\x', '\\u00') #The magic line.
            a.seek(0) #Reset the file cursor to the beginning.
            a.write(temp) #Overwrite the previous file content with the updated content.
print "Done!"