How to remove nonAscii characters in python

Question

This is my code:

#!C:/Python27/python
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import urllib2
import sys
import urlparse
import          


        

Answer 1

To remove non ASCII characters from text.

import string

text = [word for word in text if word not in string.ascii_letters]

Answer 2

Try to normalize the string and then ASCII encode it ignoring errors.

# -*- coding: utf-8 -*-
from unicodedata import normalize

string = 'úäô§'

if isinstance(string, str):
    string = string.decode('utf-8')

print normalize('NFKD', string).encode('ASCII', 'ignore')
>>> uao

Answer 3

characters are 8 byte (0-255), ascii chars are 7 byte (0-127), so you can simply drop all chars with a ord value below 128

chr convert a integer to a character, ord converts a character to an integer.

text = ''.join((c for c in str(div) if ord(c) < 128)

this should be your final code

#!C:/Python27/python
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import urllib2
import sys
import urlparse
import io

url = "http://www.dlib.org/dlib/november14/beel/11beel.html"
#url = "http://eqa.unibo.it/article/view/4554"
#r = requests.get(url)
html = urllib2.urlopen(url)
soup = BeautifulSoup(html, "html.parser")
#soup = BeautifulSoup(r.text,'lxml')

if url.find("http://www.dlib.org") != -1:
    div = soup.find('td', valign='top')
else:
    div = soup.find('div',id='content')

f = open('path/file_name.html', 'w')
text = ''.join((c for c in str(div) if ord(c) < 128)
f.write(text)
f.close()