Develop Reference

return codecs.ascii_decode(input, self.errors)[0]

I am reading a songs file in csv format and I do not know what I am doing wrong.
import csv
import os
import random
file = open("songs.csv", "rU")
reader = csv.reader(file)
for song in reader:
print(song[0], song[1], song[2])
file.close()
This is the error:
Traceback (most recent call last):
File "/Users/kuku/Desktop/hey/mine/test.py", line 10, in <module>
for song in reader:
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/encodings/ascii.py", line 26, in decode
return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe2 in position 414: ordinal not in range(128)

try
for song in [unicode(song, 'utf-8') for song in reader]:
print(...)

With this bit of your code:
for song in reader:
print( song[0], song[1],song[2])
you are printing elements 0, 1 and 2 of the lines in reader during each iteration of the loop. This will cause a (different) error if there are fewer than 3 elements in total.
If you don't know that there will be at least 3 elements in each line, you could include the code in a try, except block:
with open("songs.csv", "r") as f:
song_reader = csv.reader(f)
for song_line in song_reader:
lyric = song_line
try:
print(lyric[0], lyric[1], lyric[2])
except:
pass # ...or preferably do something better
It's worth noting that in most cases it is preferable to open a file within a with block, as shown above. This negates the need for file.close().

You can open the file in utf-8 encoding.
file = open("songs.csv", "rU", encoding="utf-8")

codecs.ascii_decode(input, self.errors)[0] UnicodeDecodeError: 'ascii' codec can't decode byte 0xc2 in position 318: ordinal not in range(128)

I am trying to open and readlines a .txt file that contains a large amount of text. Below is my code, i dont know how to solve this problem. Any help would be very appreciated.
file = input("Please enter a .txt file: ")
myfile = open(file)
x = myfile.readlines()
print (x)
when i enter the .txt file this is the full error message is displayed below:
line 10, in <module> x = myfile.readlines()
line 26, in decode return codecs.ascii_decode(input, self.errors)[0]
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc2 in position 318: ordinal not in range(128)

Instead of using codecs, I solve it this way:
def test():
path = './test.log'
file = open(path, 'r+', encoding='utf-8')
while True:
lines = file.readlines()
if not lines:
break
for line in lines:
print(line)
You must give encoding param precisely.

You can also try to encode :
with open(file) as f:
for line in f:
line = line.encode('ascii','ignore').decode('UTF-8','ignore')
print(line)

#AndriiAbramamov is right, your shoud check that question, here is a way you can open your file which is also on that link
import codecs
f = codecs.open('words.txt', 'r', 'UTF-8')
for line in f:
print(line)
Another way is to use regex, so when you open the file you can remove any special character like double quotes and so on.

Read xml as a txt in python

i have following code in python (which only load data from txt):
def main():
f = open("text.txt", "r" ) //load txt
a = [] // new array
for line in f:
a.append(line.strip()) //append line
main()
How can i do this with xml file? f = open("myxml.xml", "r" ) doesnt work. I get error : UnicodeDecodeError: 'charmap' codec can't decode byte 0x88 in position 4877: character maps to <undefined>

This has nothing to do with the xml file format, but in which encoding your file is. Python3 assumes everything to be in utf-8, but if you are on windows your file is probably in windows-1252. You should use:
f = open("text.txt", "r", encoding="cp1252")

this will sure do your job.
a=[]
with open('reboot.xml', 'r') as f:
a = f.read()
f.closed
print a

python : unicodeEncodeError: 'charpmap' codec can't encode character '\u2026'

I try to analyse some tweets I got from tweeter, but It seems I have a probleme of encoding, if you have any idea..
import json
#Next we will read the data in into an array that we call tweets.
tweets_data_path = 'C:/Python34/TESTS/twitter_data.txt'
tweets_data = []
tweets_file = open(tweets_data_path, "r")
for line in tweets_file:
try:
tweet = json.loads(line)
tweets_data.append(tweet)
except:
continue
print(len(tweets_data))#412 tweets
print(tweet)
I got the mistake :
File "C:\Python34\lib\encodings\cp850.py", line 19, in encode return codecs.charmap_encode(input,self.errors,encoding_map)[0]
unicodeEncodeError: 'charpmap' codec can't encode character '\u2026' in position 1345: character maps to undefined
At work, I didn't get the error, but I have python 3.3, does it make a difference, do you think ?
-----EDIT
The comment from #MarkRamson answered my question

You should specify the encoding when opening the file:
tweets_file = open(tweets_data_path, "r", encoding="utf-8-sig")

'ascii' codec can't encode character

I am trying to parse an HTML link into the code and take its source code as list of strings. As I have to use get some relevant data from it, I am decoding everything into UTF-8 scheme.
I am also using beautifulsoup4 which extracts the text in decoded form.
This is my code that I have used.
def do_underline(line,mistakes):
last = u'</u></font>'
first = u"<u><font color='red'>"
a = [i.decode(encoding='UTF-8', errors='ignore') for i in line]
lenm = len(mistakes)
for i in range(lenm):
a.insert(mistakes[lenm-i-1][2],last)
a.insert(mistakes[lenm-i-1][1],first)
b = u''
return b.join(a)
def readURL(u):
"""
URL -> List
Opens a webpage's source code and extract it text
along with blank and new lines.
enumerate all lines.(including blank and new lines
"""
global line_dict,q
line_dict = {}
p = opener.open(u)
p1 = p.readlines()
q = [i.decode(encoding = 'UTF-8',errors='ignore') for i in p1]
q1 = [BeautifulSoup(i).get_text() for i in q]
q2 = list(enumerate(q1))
line_dict = {i:j for (i,j) in enumerate(q)}
return q2
def process_file(f):
"""
(.html file) -> List of Spelling Mistakes
"""
global line_dict
re = readURL(f)
de = del_blankempty(re)
fd = form_dict(de)
fflist = []
chklst = []
for i in fd:
chklst = chklst + list_braces(i,line_dict)
fflist = fflist + find_index_mistakes(i,fd)
final_list = list(set(is_inside_braces_or_not(chklst,fflist)))
final_dict = {i:sorted(list(set([final_list[j] for j in range(len(final_list)) if final_list[j][0] == i])),key=lambda student: student[1]) for i in fd}
for i in line_dict:
if i in fd:
line_dict[i] = do_underline(line_dict[i],final_dict[i])
else:
line_dict[i] = line_dict[i]
create_html_file(line_dict)
print "Your Task is completed"
def create_html_file(a):
import io
fl = io.open('Spellcheck1.html','w', encoding='UTF-8')
for i in a:
fl.write(a[i])
print "Your HTML text file is created"
I am getting the following error every time i run the script.
Traceback (most recent call last):
File "checker.py", line 258, in <module>
process_file('https://www.fanfiction.net/s/9421614/1/The-Night-Blooming-Flower')
File "checker.py", line 243, in process_file
line_dict[i] = do_underline(line_dict[i],final_dict[i])
File "checker.py", line 89, in do_underline
a = [i.decode(encoding='UTF-8', errors='ignore') for i in line]
File "/usr/lib/python2.7/encodings/utf_8.py", line 16, in decode
return codecs.utf_8_decode(input, errors, True)
UnicodeEncodeError: 'ascii' codec can't encode character u'\xf3' in position 0: ordinal not in range(128)
Any suggestions how i can remove this error.
if there is a way which decodes evrything into UTF-8 coming from the given link, then i think it will solve the problem.