# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(?<![-#/])literal(?!</a>)\b"
test_str = ("<p>Literal in computer science is a\n"
"<a href='http://www.google.com/something/literal#literal'>literal</a>\n"
"for representing a fixed value in source code. Almost all programming \n"
"<a href='http://www.google.com/something/else-literal#literal'>languages</a>\n"
"have notations for atomic values such as integers, floating-point \n"
"numbers, and strings, and usually for booleans and characters; some\n"
"also have notations for elements of enumerated types and compound\n"
"values such as arrays, records, and objects. An anonymous function\n"
"is a literal for the function type which is LITERAL</p>")
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