# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(opening soon)|(coming soon)|(under construction)"
test_str = ("abcd coming soon.\n"
"...\n"
"123 \"414-898-7667\"\n"
"under construction. Bill Gates. Some other text. MSFT, AAPL, AMZN. Coming soon.\n"
"Opening later. Or may be opening soon.\n\n"
"Are you sure? Opening soon?\n\n"
"I bet they are still under construction. The builder said that the truck is coming Soon.")
matches = re.finditer(regex, test_str, re.MULTILINE | 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