# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?!<[^>]*?>)\bhello world\b(?![^<]*?(?:</[^/]*>|>))"
test_str = ("one two three hello world four five\n\n"
"one <a href='index.html'> hello world </a> four five\n\n"
"foo bar <p>hello world</p> hello\n\n"
"<p name=\"hello world\">hello world</p>\n\n"
"one two three <img alt='hello world' \\>four five\n"
"<img alt=\"hello world\"> foo \n\n"
"foo bar <a href=\"index.html\">hello world</a> again\n\n"
"one two three hello world four five\n\n"
"one two three <img alt='hello world' \\>four five")
matches = re.finditer(regex, test_str)
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