हम मैक ओएस एक्स पर रूसी ग्रंथों को पायथन स्क्रिप्ट के साथ एक एन्कोडिंग में लाते हैं

#!/usr/bin/python # -*- coding: utf-8 -*- __author__ = 'virtustilus' import os import sys #      automatic=False #  appdata={'enc':'','curfile':''} #    toconvert=[] #   r=[] if len(sys.argv)>1: r=sys.argv[1:] automatic=True else: i=raw_input(u'INPUT PATH:') r+=[i] def print1(s): """   ,      """ if not automatic: print s #    utfrustring=u'' utfrustring+=u'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz' utfrustring+=u'1234567890-=—+_}{][\\"|;:\'/?><.,`~§±!@#$%^&*()№ \r\n « » \u0009 \u2013 \u201c \u201d' def checkline(s,encoding=''): """       """ hist='' b=True for i in range(0,len(s)): c=s[i] try: if not c in utfrustring: #:   UTF-8   ,    if encoding==u'UTF-8': hist+= c + u' ' + str(hex(ord(c))) + u' at ' + str(i) + u' in: ' + s + '\n' b=False break except: if encoding==u'UTF-8': hist+=u'error encoding \n' b=False break return (b,hist) def check_all_lines(lines, encoding=''): """      """ foundenc=appdata['enc'] if foundenc: return foundenc if encoding=='': foundenc=u'UNICODE' else: foundenc=encoding x=lines[:] for j in x: if encoding!='': try: j=unicode(j,encoding) except: foundenc='' break cl=checkline(j,encoding) if not cl[0]: if cl[1]!='': print1(u'Error in:'+appdata['curfile']) print1(cl[1]) foundenc='' break appdata['enc']=foundenc #  ,   ,      if len(r)==1 and os.path.isdir(r[0]): a=r[0] r[:]=[] for i in os.walk(a): p=i[2] for j in p: if j.endswith('.txt'): r+=[i[0]+'/'+j] if len(r)>0: for i in r: i=unicode(i,u'UTF-8') # ,      UNICODE   txt   UNICODE: u'.txt' if i.endswith(u'.txt'): f=file(i,'r') lines=f.readlines() f.close() appdata['curfile']=i #    check_all_lines(lines,'') check_all_lines(lines,u'MACCYRILLIC') check_all_lines(lines,u'CP866') check_all_lines(lines,u'CP1251') check_all_lines(lines,u'KOI8R') check_all_lines(lines,u'CP10007') check_all_lines(lines,u'UTF-8-MAC') check_all_lines(lines,u'UTF-8') check_all_lines(lines,u'UTF-8-MAC') check_all_lines(lines,u'UTF-16') check_all_lines(lines,u'UTF-16BE') check_all_lines(lines,u'UTF-7') check_all_lines(lines,u'CP1252') check_all_lines(lines,u'KOI8-U') check_all_lines(lines,u'KOI8-RU') check_all_lines(lines,u'ISO-8859-5') if not appdata['enc']: toconvert.append((i,u'NOT FOUND ENCODING')) if appdata['enc'] and appdata['enc']!=u'UTF-8': toconvert.append((i,appdata['enc'])) else: print1(u'\nFile '+i+u' is not text file. \n\n') if toconvert: c=0 for i in toconvert: if i[1]!=u'NOT FOUND ENCODING': c+=1 if c>0: print1(u'\n\n FOUND FILES TO CONVERT: ') for i in toconvert: print1(i[0] + u' in encoding ' + i[1]) bt=True if not automatic: w=raw_input(u'Convert '+str(c)+u' files? (N)') bt= (w=='Y' or w=='y' or w=='' or w=='' or w=='' or w=='') if bt: for i in toconvert: if i[1]!=u'NOT FOUND ENCODING': f=file(i[0],'r') x=f.readlines() f.close() x=[ unicode(k,i[1]) for k in x ] x=[ k.encode(u'UTF-8') for k in x] f=file(i[0],'w') f.writelines(x) f.close() print1(u'FILE '+i[0]+u' CONVERTED SUCCESSFULLY :) ') else: print1(u'Bye!') else: print1(u'NO FILES TO CONVERT') for i in toconvert: print1(i[0] + u' in encoding ' + i[1]) else: print1(u' ALL ENCODING IS OK (UTF-8)!!! :)') else: print1(u'NO ONE TXT FILE') 

 #!/usr/bin/python # -*- coding: utf-8 -*- __author__ = 'virtustilus' import os import sys import chardet files=sys.argv[1:] #   ,   if len(files)==0: files=[raw_input(u'INPUT PATH:')] #       files_to_convert=[] for i in files: if os.path.exists(i): if os.path.isdir(i): for w in os.walk(i): for wfile in w[2]: if wfile.lower().endswith('.txt'): files_to_convert+=[w[0]+'/'+wfile] elif os.path.isfile(i): #    ,     files_to_convert+=[i] if len(files_to_convert)>0: for i in files_to_convert: f=file(i,'r') text=''.join(f.readlines()) f.close() enc=chardet.detect(text).get('encoding') #      (dropbox),    if enc!='UTF-8': #          try: text=text.decode(enc).encode('UTF-8') f=file(i,'w') f.write(text) f.close() except: pass