# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\w+\s+\w+(?:(?:\s\d+-\d+-\d+)?\s+[A-Za-z0-9.+_*-]+@[a-z0-9.+_-]+\.[a-z]+|\s\d+-\d+-\d+)"
test_str = ("A lot of text... First Name1 0723-111-222 email@address1.com ...a lot of text\n"
"A lot of text... Second Name2 0723-333-444 ...a lot of text\n"
"A lot of text... Third Name3 email@address3.com ...a lot of text\n"
"A lot of text... Fourth Name4 0723-777-888 email@address4.com ...a lot of text\n"
"A lot of text... Fifth Name5 0723-999-000 email@address5.com ...a lot of text")
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