# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<a[\s\S]*? \bhref=\"(mailto:(.*?))\"[\s\S]*?>(.*?)</a>"
test_str = "<p>Lorem ipsum dolor sit amet, <a href=\"#coucou\">consectetur </a> dipiscing elit. <a href=\"mailto:fakeEmail@gmail.com\">Email Tag Content 1</a>.Sic enim censent, oportunitatis esse beate vivere. Omnia contraria, quos etiam insanos esse vultis. Virtutis, magnitudinis animi, patientiae, fortitudinis fomentis dolor mitigari solet. <a href=\"mailto:email@address.uk\">Quid</a>, cum fictas fabulas, e quibus utilitas nulla elici potest, cum voluptate legimus? Duo Reges: <a href=\"mailto:tt@tt.com\" class=\"asdkfj\">constructio</a> interrete. Vos autem cum perspicuis dubia debeatis illustrare, dubiis perspicua conamini tollere. Quid ad utilitatem <a class=\"t\" href=\"mailto:aaa@uuu.ik\">tantae</a> pecuniae? Quod non subducta utilitatis ratione effici solet, sed ipsum a se oritur et sua sponte nascitur."
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