# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(?<!\S)(?:(Lord|Lady|Ser)\s+)?(Agatha|John)?(?:\s*(?<=\b)(Cain))?(?<=\S)\b"
test_str = ("Lord John Cain asked...\n"
"Ser John has...\n"
"Lady Agatha and Lord John are...\n"
"Lady Agatha Cain was...\n"
"Inside the castle, Lord Cain was speaking with Lady Cain.\n"
"John was eating...\n"
"He looked at them. Cain was walking...\n"
"Cain is...\n"
"Outside the castle, in a small courtyard, a page was leading Ser\n"
"John and his horse into the stables.\n"
"Yes, my lord... My Lord Tom, that is...\n")
matches = re.finditer(regex, test_str, re.IGNORECASE)
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