use strict;
my $str = '<w:p w:rsidR="00AE2D8E" w:rsidRPr="00AE2D8E" w:rsidRDefault="00AE2D8E">
<w:pPr>
<w:rPr>
<w:lang w:val="en-US"/>
</w:rPr>
</w:pPr>
<w:r w:rsidRPr="00AE2D8E">
<w:rPr>
<w:lang w:val="en-US"/>
</w:rPr>
<w:t xml:space="preserve"> Lorem ipsum dolor sit </w:t>
</w:r>
<w:proofErr w:type="spellStart"/>
<w:r w:rsidRPr="00AE2D8E">
<w:rPr>
<w:b/>
<w:lang w:val="en-US"/>
</w:rPr>
<w:t>amet</w:t>
</w:r>
<w:proofErr w:type="spellEnd"/>
<w:r w:rsidRPr="00AE2D8E">
<w:rPr>
<w:b/>
<w:lang w:val="en-US"/>
</w:rPr>
<w:t xml:space="preserve"> </w:t>
</w:r>
<w:proofErr w:type="spellStart"/>
<w:r w:rsidRPr="00AE2D8E">
<w:rPr>
<w:b/>
<w:lang w:val="en-US"/>
</w:rPr>
<w:t>consecteur</w:t>
</w:r>
<w:proofErr w:type="spellEnd"/>
<w:r w:rsidRPr="00AE2D8E">
<w:rPr>
<w:b/>
<w:lang w:val="en-US"/>
</w:rPr>
<w:t>.</w:t>
</w:r>
<w:bookmarkStart w:id="0" w:name="_GoBack"/>
<w:bookmarkEnd w:id="0"/>
</w:p>';
my $regex = qr/>([A-zÀ-ÿ.,:?! ]{1,})<|>([ A-zÀ-ÿ.,:?!]{1,})\n/p;
if ( $str =~ /$regex/g ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
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 Perl, please visit: http://perldoc.perl.org/perlre.html