(原)C#正则表达式举例,采用正则表达式找出html,css,js文件中的图片路径

正则:

查找Img标签开头的图片路径
[iI][mM][gG][\s]*[sS][rR][cC][\s]*=[\s'"]*(?<ref_value>.*?(\.gif|\.jpg|\.png))

查找Function中的图片路径
[a-zA-Z_][a-zA-Z0-9_]+[\s]*\([^)]+?('|")(?<ref_value>[a-zA-Z0-9/\\-_\.]+?(\.gif|\.jpg|\.png))('|")[^)]*\)

查找background标签的图片路径
background="(?<ref_value>[^"]+)

查找URL的图片路径
:[\s]*url[\s]*\([\s"']*(?<ref_value>["']*[^)]+)

通用的:
("|')(?<ref_value>[^"']+?(\.gif|\.png|\.jpg))("|')

url\(['\"]?\s*(?<ref_value>[^>]+?)['\"]?\s*\)
Cimg[\d+]*[\s]*\([\s"']*(?<ref_value>[^"')]+)

 

 

private IList<string> MatchImgPath(string content, string regexPattern)
        {
            IList<string> _ret = new List<string>();
            Regex reg = new Regex(regexPattern);
            string _imgPath = "";
            MatchCollection mc = reg.Matches(content);
            if (mc != null && mc.Count > 0)
            {
                foreach (Match match in mc)
                {
                    if (match.Success == false || match.Value == null || match.Value == "")
                        continue;

                    foreach (string name in reg.GetGroupNames())
                    {
                        if (name == null || name == "" || name == "0")
                            continue;

                        if (name == "ref_value"
                            && match.Groups[name].Value != null
                            && match.Groups[name].Value != "")
                        {
                            _imgPath = match.Groups[name].Value;
                            if(!_ret.Contains(_imgPath.ToLower()))
                                _ret.Add(_imgPath.ToLower());
                        }
                    }
                }
            }
            return _ret;
        }