This is my code
# -*- coding: utf-8 -*- import json import re with open("/Users/paul/Desktop/file.json") as json_file: file = json.load(json_file) print file["desc"] key="capacità" result = re.findall("((?:[\S,]+\s+){0,3})"+key+"\s+((?:[\S,]+\s*){0,3})", file["desc"], re.IGNORECASE) print result This is the content of the file
{ "desc": "Frigocongelatore, capacit\u00e0 di 215 litri, h 122 cm, classe A+" } My result is []
but what I want is result = "capacità"
You need to treat your string as an Unicode string, like this:
str = u"Frigocongelatore, capacit\u00e0 di 215 litri, h 122 cm, classe A+" And as you can see if you print str.encode('utf-8') you'll get:
Frigocongelatore, capacità di 215 litri, h 122 cm, classe A+ The same way you can make your regex string an unicode or raw string with u or r respectively.
You can use this function to display different encodings.
The default encoding on your editor should be UTF-8. Check you settings with sys.getdefaultencoding().
def find_context(word_, n_before, n_after, string_): # finds the word and n words before and after it import re b= '\w+\W+' * n_before a= '\W+\w+' * n_after pattern = '(' + b + word_ + a + ')' return re.search(pattern, string_).groups(1)[0] s = "Frigocongelatore, capacità di 215 litri, h 122 cm, classe A+" # find 0 words before and 3 after the word capacità print(find_context('capacità',0,3,s) ) capacità di 215 litri print(find_context(' capacit\u00e0',0,3,s) ) capacità di 215 litri 
