python charmap codec can't decode byte X in position Y character maps to < undefined>

[owais]

Here is the code:

# --- pythonTwitterTest.py --- The main client module which is using all other code
import tweepy
import json
from TwitterPoint.TwitterEngine import *
from dbLayer.dbHelper import rHelper
from process.processData import *

processAndCleanData('trumpFollowers')

print('breakpoint here')

# --- processData.py ---
from geotext import GeoText # for classifying and seperating City , Country and States/Provinces
#import pycountry # for en to English
import simplejson
#import babelfish
from dbLayer.dbHelper import rHelper
from langcodes import Language

def getLocations(array):
    return []

def processAndCleanData(tableName):    
    rdb = rHelper('tw') #gets data from rethinkdb (in json format)
    rawCursor = rdb.getRawDumpCursor(tableName)
    cleanData = []
    langPyCountry = ''
    for raw in rawCursor:
        langPyCountry = Language.get(raw['lang']).language_name()
        places = GeoText(x.location)

        cleanData.append({"id": raw['id_str'],
                          "name": raw['name'],
                          "location": raw['location'],
                          "locationExtract" : places.[color=#000000]cities,[/color]

                          "language": raw['lang'],
                          "LangExtract": langPyCountry})
    dumpToFile(cleanData)

def dumpToFile(array):
    f = open('dump.txt', 'w')
    simplejson.dump(array, f)
    f.close()

Traceback (most recent call last):
  File "pythonTwitterTest.py", line 5, in <module>
    from process.processData import *
  File "C:\OwaisWorkx\Courses\5th Semester\Project\pythonTwitterTest\pythonTwitterTest\process\processData.py", line 1, in <module>
    from geotext import GeoText # for classifying and seperating City , Country and States/Provinces
  File "c:\Python33\lib\site-packages\geotext\__init__.py", line 7, in <module>
    from .geotext import GeoText
  File "c:\Python33\lib\site-packages\geotext\geotext.py", line 87, in <module>
    class GeoText(object):
  File "c:\Python33\lib\site-packages\geotext\geotext.py", line 103, in GeoText
    index = build_index()
  File "c:\Python33\lib\site-packages\geotext\geotext.py", line 77, in build_index
    cities = read_table(get_data_path('cities15000.txt'), usecols=[1, 8])
  File "c:\Python33\lib\site-packages\geotext\geotext.py", line 54, in read_table
    for line in lines:
  File "c:\Python33\lib\site-packages\geotext\geotext.py", line 51, in <genexpr>
    lines = (line for line in f if not line.startswith(comment))
  File "c:\Python33\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 0x81 in position 165: character maps to <undefined>

---

Testing and fixing his code.

Fix:
Line 45 geotext.py:

with open(filename, 'r') as f:

To:

with open(filename, 'r', encoding='utf-8') as f:

Test.

(geo_test) C:\Python36\geo_test
λ python
Python 3.6.0 (v3.6.0:41df79263a11, Dec 23 2016, 07:18:10) [MSC v.1900 32 bit (Intel)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> from geotext import GeoText
>>> places = GeoText("London is a great city")
>>> places.cities
['London']

>>> GeoText('New York, Texas, and also China').country_mentions
OrderedDict([('US', 2), ('CN', 1)])

>>> places = GeoText("Oslo is a great city")
>>> places.cities
['Oslo']

Edit:
There where 1-bug rapport about this.
So i have given this info to author of geotext on GitHub.

Thanks that solved the problem,this issue wasted few days.