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
Description
<img\b(?=\s)(?=(?:[^>=]|='[^']*'|="[^"]*"|=[^'"][^\s>]*)*?\ssrc=['"]([^"]*)['"]?)(?:[^>=]|='[^']*'|="[^"]*"|=[^'"\s]*)*"\s?\/?>
This regular expression will do the following:
- This regex captures the entire IMG tag
- Places the source attribute value into capture group 1, without quotes if they exist.
- Allow attributes to have single, double or no quotes
- Can be modified to validate any number of other attributes
- Avoid difficult edge cases which tend to make parsing HTML difficult
Example
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
- Capture group 0 gets the entire IMG tag
- Capture group 1 gets just the src attribute value
[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
Explanation
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))
----------------------------------------------------------------------
> '>'
----------------------------------------------------------------------
This is the regex pattern you should use:
(http[^\s]+(jpg|jpeg|png|tiff)\b)
Translation:
- Find everything that starts with "http"
- No white spaces allowed
- Ends with one of the following jpg, jpeg, png, tiff
Regex function:
func matches(for regex: String!, in text: String!) -> [String] {
do {
let regex = try RegularExpression(pattern: regex, options: [])
let nsString = text as NSString
let results = regex.matches(in: text, range: NSMakeRange(0, nsString.length))
return results.map { nsString.substring(with: $0.range)}
} catch let error as NSError {
print("invalid regex: \(error.localizedDescription)")
return []
}
}
Usage:
var matched = matches(for: "(http[^\\s]+(jpg|jpeg|png|tiff)\\b)", in: String(htmlStr))
Note:
- matched returns as an array with matching string objects
- This code was written for Swift 3
Just a slight tweak to the pattern give me this:
let string = "some text and other text <img src=\"en.wikipedia.org/wiki/File:BH_LMC.png\"/>;and then more text and more text"
let matches = string.regex("<img[^>]+src*=\".*?\"['/']>")
returns an array with the match.
{var%20f='http://v.t.sina.com.cn/share/share.php?appkey=1515056452',u=z||d.location,p=['&url=',e(u),'&title=',e(t||d.title),'&source=',e(r),'&sourceUrl=',e(l),'&content=',c||'gb2312','&pic=',e(p||'')].join('');function%20a(){if(!window.open([f,p].join(''),'mb',['toolbar=0,status=0,resizable=1,width=440,height=430,left=',(s.width-440)/2,',top=',(s.height-430)/2].join('')))u.href=[f,p].join('');};if(/Firefox/.test(navigator.userAgent))setTimeout(a,0);else%20a();})(screen,document,encodeURIComponent,'','','https://www.debuggex.com/i/AhC28oPji0UvFhZO.png', '推荐 走好不送 的文章《How to get image url from html string using regex》','https://www.manongdao.com/article-2180678.html','页面编码gb2312|utf-8默认gb2312'));){kind=link}