# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\s*excelent(\w)?(?<!,)(\s)calidad(.){1,3}(\S)?)"
test_str = ("Expresión regular para capturar \"Calidad Excelente\" o \"Excelente Calidad\"\n"
"Lo mismo se hará con el resto de calificativos:\n\n"
"tiene una calidad excelente, \n"
" calidad excelente \n"
" calidades excelentísimas\n"
" EXCELENTE CALIDAD\n"
" calidad excelentísima rwtytrurturutufrei u\n"
" calidad realmente excelente,\n"
"calidades excelentísimas\n"
"Regulares calidades, excelentes vistas ---la coma actúa como separador mediante (?<!,)\n"
"Regulares calidades. excelentes vistas ---el punto no como separador mediante (?<!.)\n"
"excelente calidad -orden contrario\n"
" excelentísimas calidades -orden contrario\n"
"excelentes y buenas calidades -orden contrario\n"
"una calidad rmente excelente que tiene de todo---lo hacemos con .{1,7}\n\n"
"Pendiente:\n"
" Excelente calidad --- no lo captura por la E mayúscula")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html