20

I am student doing my master thesis. As part of my thesis, I am working with python. I am reading a log file of .csv format and writing the extracted data to another .csv file in a well formatted way. However, when the file is read, I am getting this error:

Traceback (most recent call last): File "C:\Users\SGADI\workspace\DAB_Trace\my_code\trace_parcer.py", line 19, in for row in reader:

  • File "C:\Users\SGADI\Desktop\Python-32bit-3.4.3.2\python-3.4.3\lib\encodings\cp1252.py", line 23, in decode return codecs.charmap_decode(input,self.errors,decoding_table)[0]
  • UnicodeDecodeError: 'charmap' codec can't decode byte 0x8d in position 7240: character maps to <undefined>
import csv
import re
#import matplotlib
#import matplotlib.pyplot as plt
import datetime
#import pandas
#from dateutil.parser import parse
#def parse_csv_file():
timestamp = datetime.datetime.strptime('00:00:00.000', '%H:%M:%S.%f')
timestamp_list = []
snr_list = []
freq_list = []
rssi_list = []
dab_present_list = []
counter = 0
f =  open("output.txt","w")
with open('test_log_20150325_gps.csv') as csvfile:
    reader = csv.reader(csvfile, delimiter=';') 
    for row in reader:
        #timestamp = datetime.datetime.strptime(row[0], '%M:%S.%f')
        #timestamp.split(" ",1)
        
        timestamp = row[0]
        timestamp_list.append(timestamp)
          

        #timestamp = row[0]
        details = row[-1]
        counter += 1
        print (counter)
        #if(counter > 25000):
        #  break
        #timestamp = datetime.datetime.strptime(row[0], '%M:%S.%f')  
      


        #timestamp_list.append(float(timestamp))

        #search for SNRLevel=\d+
        snr = re.findall('SNRLevel=(\d+)', details)
        if snr == []:
            snr = 0
        else:
            snr = snr[0]
        snr_list.append(int(snr))
                            
        #search for Frequency=09ABC
        freq = re.findall('Frequency=([0-9a-fA-F]+)', details)
        if freq == []:
            freq = 0
        else:
            freq = int(freq[0], 16)
        freq_list.append(int(freq))

        #search for RSSI=\d+
        rssi = re.findall('RSSI=(\d+)', details)
        if rssi == []:
            rssi = 0
        else:
            rssi = rssi[0]
        rssi_list.append(int(rssi))

        #search for DABSignalPresent=\d+
        dab_present = re.findall('DABSignalPresent=(\d+)', details)
        if dab_present== []:
            dab_present = 0
        else:
            dab_present = dab_present[0]
        dab_present_list.append(int(dab_present))

        f.write(str(timestamp) + "\t")
        f.write(str(freq) + "\t")
        f.write(str(snr) + "\t")
        f.write(str(rssi) + "\t")
        f.write(str(dab_present) + "\n")
        print (timestamp, freq, snr, rssi, dab_present)

        #print (index+1)

        #print(timestamp,freq,snr)
        #print (counter)
#print(timestamp_list,freq_list,snr_list,rssi_list)


'''if  snr != []:
           if freq != []:
               timestamp_list.append(timestamp)
               snr_list.append(snr)
               freq_list.append(freq)
f.write(str(timestamp_list) + "\t")
f.write(str(freq_list) + "\t")
f.write(str(snr_list) + "\n")
        
print(timestamp_list,freq_list,snr_list)'''
f.close()

I searched for the special character and I did not find any. I searched the Internet which suggested to change the format: I tried ut8, latin1 and few other formats, but i am still getting this error. Can you please help me how to solve with pandas as well. I also tried with pandas but I am still getting the error. I even removed a line in the log file, but the error occurs in the next line.

pppery
  • 3,731
  • 22
  • 33
  • 46
Goutham Sai Siddardha
  • 393
  • 1
  • 2
  • 9
  • 2
    Please post `repr(open('test_log_20150325_gps.csv', 'rb').read(7290)[7190:])`. This will show us some of the contents of the CSV file around the 7240th byte. Using that we *might* be able to *guess* what is the likely codec. – unutbu Jun 02 '15 at 14:26
  • I got this as in the console when i posted the above command b'XPMSG_OPCODE_SET_CONTROL_FLAGS_CMD;;;;;;;;;RR=2 OP=DAB_NXPMSG_OPCODE_SET_CONTROL_FLAGS_CMD CAVisibil' – Goutham Sai Siddardha Jun 02 '15 at 14:55
  • Something is inconsistent here, since there is no byte `'\x8d'` in the `repr` you posted. Can you post `test_log_20150325_gps.csv`? – unutbu Jun 02 '15 at 16:35
  • here is the link for the file https://drive.google.com/open?id=0B-EIwtmNvOGEWUdNYVlVam4yb1k&authuser=0 – Goutham Sai Siddardha Jun 02 '15 at 17:38

3 Answers3

19

I have solved this issue. we can use this code

import codecs
types_of_encoding = ["utf8", "cp1252"]
for encoding_type in types_of_encoding:
    with codecs.open(filename, encoding = encoding_type, errors ='replace') as csvfile:
        your code
        ....
        ....
pppery
  • 3,731
  • 22
  • 33
  • 46
Goutham Sai Siddardha
  • 393
  • 1
  • 2
  • 9
12

I have solved this issue by simply adding a parameter in open()

with open(filename, encoding = 'cp850') as csv_file:
    csv_reader = csv.reader(csv_file, delimiter=',')
Kenneth So
  • 121
  • 2
  • 3
6
with open('input.tsv','rb') as f:
for ln in f:
    decoded=False
    line=''
    for cp in ('cp1252', 'cp850','utf-8','utf8'):
        try:
            line = ln.decode(cp)
            decoded=True
            break
        except UnicodeDecodeError:
            pass
    if decoded:
        # use 'line'
Palash Kumar
  • 429
  • 6
  • 18