postabuse/check_postcsv.py

#!/usr/bin/python

import csv, sys, os, glob

FNAME_CHECKED = 'checked_numbers.csv'

checked_list = {}
tr_list = []
dub_tr = []
new_dub_tr = []


dirname = sys.argv[1]
print "Verwende Verzeichnis", dirname

# read checked tracking numbers
with open (os.path.join(dirname, FNAME_CHECKED)) as checked_obj:
  d = csv.reader(checked_obj, delimiter=',', quoting=csv.QUOTE_ALL)  
  for r in d:
    tr_id = int(r[0])
    reason = r[1]
    checked_list[tr_id] = reason


dirlist = os.listdir(dirname)
for fname in dirlist:
  fbase, fext = os.path.splitext(fname)
  fullfname = os.path.join(dirname, fname)
  #print fname, fbase, fext
  if fext != ".csv" or fname == FNAME_CHECKED:
    #print "Ueberspringe Datei", fname
    continue

  print "Verarbeite Datei", fullfname
  with open (fullfname, 'rb') as fobj:
    d = csv.reader(fobj, delimiter=';', quoting=csv.QUOTE_ALL)
    # skip header
    d.next()
    for r in d:
      tr_id = int(r[8].replace("=", "").strip('"'))
      if tr_id in tr_list:
        print "doublette detected", tr_id
        dub_tr.append(r)
        #print r[7], tr_id
        #print checked_list, tr_id
        if not checked_list.has_key(tr_id):
          new_dub_tr.append(r)
      else:
        tr_list.append(tr_id)


print    
print "***********************"    
print "Dubletten erkannt:", len(dub_tr)    
print "***********************"    

for dub in dub_tr:
  tracking_nr = int(dub[8].replace("=", "").strip('"'))
  if checked_list.has_key(tracking_nr):
    print dub[0], dub[4], dub[5], dub[6], dub[7], int(dub[8].replace("=", "").strip('"')), checked_list[tracking_nr]
  else:
    print dub[0], dub[4], dub[5], dub[6], dub[7], int(dub[8].replace("=", "").strip('"')), "***** CHECK-IT! *****"
  
print "***********************"    
print "Neue erkannt: %i / %i" %(len(new_dub_tr), len(dub_tr))
print "***********************"    
for dub in new_dub_tr:
  print dub[0], dub[4], dub[5], dub[6], dub[7], int(dub[8].replace("=", "").strip('"')), "***** CHECK-IT! *****"