- /// <summary>
- /// 取得HTML中所有图片的 URL。
- /// </summary>
- /// <param name="sHtmlText">HTML代码</param>
- /// <returns>图片的URL列表</returns>
- public static string[] GetHtmlImageUrlList(string sHtmlText)
- {
- // 定义正则表达式用来匹配 img 标签
- Regex regImg = new Regex(@"<img[^<>]*?src[s ]*=[s ]*[""']?[s ]*(?<imgUrl>[^s ""'<>]*)[^<>]*?/?[s ]*>", RegexOptions.IgnoreCase);
- // 搜索匹配的字符串
- MatchCollection matches = regImg.Matches(sHtmlText);
- int i = 0;
- string[] sUrlList = new string[matches.Count];
- // 取得匹配项列表
- foreach (Match match in matches)
- sUrlList[i++] = match.Groups["imgUrl"].Value;
- return sUrlList;
- }