# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(^\s+_[A-Za-z]+\._)"
test_str = ("was from an authentic copy, and a careful comparison of the text with\n"
"the earlier one shows that in the meantime the play \"underwent revision,\n"
"received some slight augmentation, and in some few places must have been\n"
"entirely rewritten.\" A marked instance of this rewriting--the only one\n"
"of considerable length--is in ii. 6. 6-37, where the first quarto reads\n"
"thus (spelling and pointing being modernized):--\n\n"
" _Jul._ Romeo.\n\n"
" _Rom._ My Juliet, welcome. As do waking eyes\n"
" Closed in Night's mists attend the frolick Day,\n"
" So Romeo hath expected Juliet,\n"
" And thou art come.\n\n"
" _Jul._ I am, if I be Day,\n"
" Come to my Sun: shine forth and make me fair.\n\n"
" _Rom._ All beauteous fairness dwelleth in thine eyes.\n\n"
" _Jul._ Romeo, from thine all brightness doth arise.\n\n"
" _Fri._ Come, wantons, come, the stealing hours do pass,\n"
" Defer embracements till some fitter time.\n"
" Part for a while, you shall not be alone\n"
" Till holy Church have joined ye both in one.\n\n"
" _Rom._ Lead, holy Father, all delay seems long.\n\n"
" _Jul._ Make haste, make haste, this lingering doth us wrong.\n\n"
"For convenient comparison I quote the later text here:--\n\n"
" _Juliet._ Good even to my ghostly confessor.\n\n"
" _Friar Laurence._ Romeo shall thank thee, daughter, for us both.\n\n"
" _Juliet._ As much to him, else is his thanks too much.\n\n"
" _Romeo._ Ah, Juliet, if the measure of thy joy\n"
" Be heap'd like mine and that thy skill be more\n"
" To blazon it, then sweeten with thy breath\n"
" This neighbour air, and let rich music's tongue\n"
" Unfold the imagin'd happiness that both\n"
" Receive in either by this dear encounter.\n\n"
" _Juliet._ Conceit, more rich in matter than in words,\n"
" Brags of his substance, not of ornament.\n"
" They are but beggars that can count their worth;\n"
" But my true love is grown to such excess\n"
" I cannot sum up half my sum of wealth.\n\n"
" _Friar Laurence._ Come, come with me, and we will make short work;\n"
" For, by your leaves, you shall not stay alone\n"
" Till holy church incorporate two in one.\n\n"
"The \"omission, mutilation, or botching\" by which some German editors\n"
"would explain all differences between the earlier and later texts will\n"
"not suffice to account for such divergence as this. \"The two dialogues\n"
"do not differ merely in expressiveness and effect; they embody different\n"
"conceptions of the characters;\" and yet we cannot doubt that both were\n"
"written by Shakespeare.\n")
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