use strict;
my $str = 'In this case, $url will indeed contain http://example.com/whatever.jpg. But what happens when you start getting HTML like this:
<img src=\'http://example.com/whatever.jpg\'>
or
<img src=http://example.com/whatever.jpg>
or
<img border=0 src="http://example.com/whatever.jpg">
or
<img border src="http://example.com/whatever.jpg">
or
<img
src="http://example.com/whatever.jpg">
or you start getting false positives from
<!-- // commented out
<img src="http://example.com/outdated.png">
-->
<script><![CDATA[ This is <b>not</b> parsed ]]></script>
<asd ASD=asd>
<!-- // commented out <img src="http://example.com/outdated.png"> -->
No quotes:
<iframe src=test.html target=xyz></ iframe >
Self-closing tag:
<a href=test.html target=xyz/>
Self closing tag with a space before closure:
<a href=test.html target=xyz />
Double quotes:
<a href="test.html" target="xyz">
Single quotes:
<a href=\'test.html\' target=\'xyz\'>
Escaping double quotes:
<a href="test.html?val=1" title="\\"No rules exist\\" Andre Breton\'s quote">
Escaping single quotes (also with spaces between equals signs):
<a href = "test.html?val=1" title = \'Charlie\\\'s Angels\'>
Tag without closure (ignored):
<a href = "test.html?val=1" title=\'Charlie\\\'s Angels\'
Tag without opening (ignored):
a href = "test.html?val=1" title="Charlie\\"s Angels">
';
my $regex = qr/(?P<content>.*?) # Content up to next tag
(?P<markup> # Entire tag
<!\[CDATA\[(?P<cdata>.+?)]]>| # <![CDATA[ ... ]]>
<!--(?P<comment>.+?)-->| # <!-- Comment -->
</\s*(?P<close_tag>\w+)\s*>| # </tag>
<(?P<tag>\w+) # <tag ...
(?P<attributes>
(?P<attribute>\s+
# <snip>: Use this part to get the attributes out of 'attributes' group.
(?P<attribute_name>\w+)
(?:\s*=\s*
(?P<attribute_value>
[\w:/.\-]+| # Unquoted
(?=(?P<_v> # Quoted
(?P<_q>['\"]).*?(?<!\\)(?P=_q)))
(?P=_v)
))?
# </snip>
)*
)\s*
(?P<is_self_closing>/?) # Self-closing indicator
>) # End of tag
/sxp;
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