If you want to parse Google News RSS image from link, for example > http://news.google.com/news?hl=us&q=android&output=rss
The following code can be used to match all
img src
in the source text and to populate list with value of src
attribute.
private static IEnumerable<string> GetImagesInGoogleNewsString(string htmlString)
{
List<string> imgSrcs = new List<string>();
//const string pattern = Imgpattern;
//var rgx = new Regex(pattern, RegexOptions.IgnoreCase);
var imgSrcMatches = System.Text.RegularExpressions.Regex.Matches(htmlString, string.Format(@"<\s*img\s*src\s*=\s*{0}\s*([^{0}]+)\s*{0}", "\""),
RegexOptions.CultureInvariant | RegexOptions.IgnoreCase |
RegexOptions.Multiline);
foreach (Match match in imgSrcMatches)
imgSrcs.Add("http:" + match.Groups[1].Value);
return imgSrcs;
}
No comments:
Post a Comment