I am trying to get from html string using regex which I am currently working on was this :
extension String {
func regex (pattern: String) -> [String] {
do {
let regex = try NSRegularExpression(pattern: pattern, options: NSRegularExpressionOptions(rawValue: 0))
let nsstr = self as NSString
let all = NSRange(location: 0, length: nsstr.length)
var matches : [String] = [String]()
regex.enumerateMatchesInString(self, options: NSMatchingOptions(rawValue: 0), range: all) {
(result : NSTextCheckingResult?, _, _) in
if let r = result {
let result = nsstr.substringWithRange(r.range) as String
matches.append(result)
}
}
return matches
} catch {
return [String]()
}
}
And the pattern is : <img[^>]+src\\s*=\\s*['\']([^'\"]+)['\"][^>]*>
I still can't get the image url from it which mean it return me empty array.Actually my html string include one image.I don't want to useUIWebView
because of UITableView
resizing problem.So,I need to fetch the image url out of html and show it in UIImageView using AlamofireImage.
Any Help?It was just one url that i need to fetch.
Here is my tag :
<img src="https://en.wikipedia.org/wiki/File:BH_LMC.png"/>
To :
https://en.wikipedia.org/wiki/File:BH_LMC.png
<img\b(?=\s)(?=(?:[^>=]|='[^']*'|="[^"]*"|=[^'"][^\s>]*)*?\ssrc=['"]([^"]*)['"]?)(?:[^>=]|='[^']*'|="[^"]*"|=[^'"\s]*)*"\s?\/?>
This regular expression will do the following:
Live Demo
https://regex101.com/r/qW9nG8/1
Sample text
Note the difficult edge case in the first line where we are looking for a specific droid.
<img onmouseover=' if ( 6 > 3 { funSwap(" src="NotTheDroidYourLookingFor.jpg", 6 > 3 ) } ; ' src="http://website/ThisIsTheDroidYourLookingFor.jpeg" onload="img_onload(this);" onerror="img_onerror(this);" data-pid="jihgfedcba" data-imagesize="ppew" />
some text
<img src="http://website/someurl.jpeg" onload="img_onload(this);" />
more text
<img src="https://en.wikipedia.org/wiki/File:BH_LMC.png"/>
Sample Matches
[0][0] = <img onmouseover=' funSwap(" src='NotTheDroidYourLookingFor.jpg", data-pid) ; ' src="http://website/ThisIsTheDroidYourLookingFor.jpeg" onload="img_onload(this);" onerror="img_onerror(this);" data-pid="jihgfedcba" data-imagesize="ppew" />
[0][1] = http://website/ThisIsTheDroidYourLookingFor.jpeg
[1][0] = <img src="http://website/someurl.jpeg" onload="img_onload(this);" />
[1][1] = http://website/someurl.jpeg
[2][0] = <img src="https://en.wikipedia.org/wiki/File:BH_LMC.png"/>
[2][1] = https://en.wikipedia.org/wiki/File:BH_LMC.png
NODE EXPLANATION
----------------------------------------------------------------------
<img '<img'
----------------------------------------------------------------------
\b the boundary between a word char (\w) and
something that is not a word char
----------------------------------------------------------------------
(?= look ahead to see if there is:
----------------------------------------------------------------------
\s whitespace (\n, \r, \t, \f, and " ")
----------------------------------------------------------------------
) end of look-ahead
----------------------------------------------------------------------
(?= look ahead to see if there is:
----------------------------------------------------------------------
(?: group, but do not capture (0 or more
times (matching the least amount
possible)):
----------------------------------------------------------------------
[^>=] any character except: '>', '='
----------------------------------------------------------------------
| OR
----------------------------------------------------------------------
=' '=\''
----------------------------------------------------------------------
[^']* any character except: ''' (0 or more
times (matching the most amount
possible))
----------------------------------------------------------------------
' '\''
----------------------------------------------------------------------
| OR
----------------------------------------------------------------------
=" '="'
----------------------------------------------------------------------
[^"]* any character except: '"' (0 or more
times (matching the most amount
possible))
----------------------------------------------------------------------
" '"'
----------------------------------------------------------------------
| OR
----------------------------------------------------------------------
= '='
----------------------------------------------------------------------
[^'"] any character except: ''', '"'
----------------------------------------------------------------------
[^\s>]* any character except: whitespace (\n,
\r, \t, \f, and " "), '>' (0 or more
times (matching the most amount
possible))
----------------------------------------------------------------------
)*? end of grouping
----------------------------------------------------------------------
\s whitespace (\n, \r, \t, \f, and " ")
----------------------------------------------------------------------
src= 'src='
----------------------------------------------------------------------
['"] any character of: ''', '"'
----------------------------------------------------------------------
( group and capture to \1:
----------------------------------------------------------------------
[^"]* any character except: '"' (0 or more
times (matching the most amount
possible))
----------------------------------------------------------------------
) end of \1
----------------------------------------------------------------------
['"]? any character of: ''', '"' (optional
(matching the most amount possible))
----------------------------------------------------------------------
) end of look-ahead
----------------------------------------------------------------------
(?: group, but do not capture (0 or more times
(matching the most amount possible)):
----------------------------------------------------------------------
[^>=] any character except: '>', '='
----------------------------------------------------------------------
| OR
----------------------------------------------------------------------
=' '=\''
----------------------------------------------------------------------
[^']* any character except: ''' (0 or more
times (matching the most amount
possible))
----------------------------------------------------------------------
' '\''
----------------------------------------------------------------------
| OR
----------------------------------------------------------------------
=" '="'
----------------------------------------------------------------------
[^"]* any character except: '"' (0 or more
times (matching the most amount
possible))
----------------------------------------------------------------------
" '"'
----------------------------------------------------------------------
| OR
----------------------------------------------------------------------
= '='
----------------------------------------------------------------------
[^'"\s]* any character except: ''', '"',
whitespace (\n, \r, \t, \f, and " ") (0
or more times (matching the most amount
possible))
----------------------------------------------------------------------
)* end of grouping
----------------------------------------------------------------------
" '"'
----------------------------------------------------------------------
\s? whitespace (\n, \r, \t, \f, and " ")
(optional (matching the most amount
possible))
----------------------------------------------------------------------
\/? '/' (optional (matching the most amount
possible))
----------------------------------------------------------------------
> '>'
----------------------------------------------------------------------
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With