# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\d+(\.\d+)?([Ee]\D+)?"
test_str = ("This is just a test\n"
"where we can have multiple email addresses\n"
"which can be gil@home.com\n"
"g.echeverria@tec.mx\n"
"gil2@one.long.domain.org\n"
"Or something more elaborate\n"
"one1.two2-three3@is.this-site.real.net\n"
"brave_world@survive.com.it\n"
"And just like that there can me more formats for emails\n"
"But how can we extract those\n"
"34.76e4\n"
"875\n"
"34.43.34.676")
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