package main
import (
"regexp"
"fmt"
)
func main() {
var re = regexp.MustCompile(`(?is)(?:\<\!\-\-(?:(?!\-\-\>)\r\n?|\n|.)*?-\-\>)|(?:<(\S+)\s+(?=.*>)|(?<=[=\s])\G)(?:((?:(?!\s|=).)*)\s*?=\s*?[\"']?((?:(?<=\")(?:(?<=\\)\"|[^\"])*|(?<=')(?:(?<=\\)'|[^'])*)|(?:(?!\"|')(?:(?!\/>|>|\s).)+))[\"']?\s*)`)
var 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
src="http://example.com/whatever.jpg">
or you start getting false positives from
<!-- // commented out
<img src="http://example.com/outdated.png">
-->
<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img src="http://example.com/outdated.png"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 opening (ignore attributes):
a href = "test.html?val=1" title='Charlie\'s Angels'>
Tag without closure (ignore attributes):
<a href = "test.html?val=1" title='Charlie\'s Angels'
`
for i, match := range re.FindAllString(str, -1) {
fmt.Println(match, "found at index", i)
}
}
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 Golang, please visit: https://golang.org/pkg/regexp/