Created
March 25, 2016 13:11
-
-
Save drvenabili/34cdfe24805c13474d43 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/python | |
# -*- coding: utf-8 -*- | |
import codecs | |
import re | |
import io | |
import os,glob | |
path = '*' # change this according to where the script is and where the alto files are | |
files=glob.glob(path) | |
for chemin in files : | |
if os.path.isfile(chemin) == True : # we only want the files, not the directories | |
f = io.open(chemin,'r',encoding="utf-8") # opens every file | |
lines = f.readlines() # reads the file line by line | |
x = io.open(chemin[:-4]+".txt","w",encoding='utf-8') # removes the .xml from the filename of the file we're reading, creates a .txt file with the same name | |
for line in lines: # for each line, | |
y = re.search('CONTENT=\"(.*?)\"',line) # we search for the matching " "CONTENT="xyz" " regex | |
if y: # if we find it, | |
y = y.group(0) # we write every match of it inside the file, while removing " "CONTENT=" and the trailing " " " and adding a space between each word | |
z = y[9:] | |
zz = z[:-1] | |
zz = zz+" " | |
x.write(zz) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment