fork(1) download
  1. import re
  2. text1 = "The disease has spread to three countries: Guinea, Guinea-Bassau and Equatorial Guinea."
  3. text2 = "Only Guinea-Bassau and Equatorial Guinea contained strains of the virus."
  4. list_of_countries = ['Guinea', 'Guinea-Bassau', 'Equatorial Guinea']
  5. list_of_countries=sorted(list_of_countries,key=len,reverse=True)
  6.  
  7. rx=r'\b(?:{})\b'.format("|".join(list_of_countries))
  8. print(re.findall(rx, text1))
  9. print(re.findall(rx, text2))
Success #stdin #stdout 0.02s 27744KB
stdin
Standard input is empty
stdout
['Guinea', 'Guinea-Bassau', 'Equatorial Guinea']
['Guinea-Bassau', 'Equatorial Guinea']