html正则匹配img src,如何用正则表达式获取文章内容中的<img标签和 src的路径

怎么用正则表达式获取文章内容中的

正则:

查找Img标签开头的图片路径

[iI][mM][gG][\s]*[sS][rR][cC][\s]*=[\s'"]*(?.*?(\.gif|\.jpg|\.png))

查找Function中的图片路径

[a-zA-Z_][a-zA-Z0-9_]+[\s]*\([^)]+?('|")(?[a-zA-Z0-9/\\-_\.]+?(\.gif|\.jpg|\.png))('|")[^)]*\)

查找background标签的图片路径

background="(?[^"]+)

查找URL的图片路径

:[\s]*url[\s]*\([\s"']*(?["']*[^)]+)

通用的:

("|')(?[^"']+?(\.gif|\.png|\.jpg))("|')

url\(['\"]?\s*(?[^>]+?)['\"]?\s*\)

Cimg[\d+]*[\s]*\([\s"']*(?[^"')]+)

private IList MatchImgPath(string content, string regexPattern)

{

IList _ret = new List();

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;

}