/// <summary> Extract the link from the given string. The URL of the actual html page is also
/// provided.
/// </summary>
public virtual string ExtractLink(Tag tag, string url)
{
try
{
System.Collections.Hashtable table = tag.Attributes;
string relativeLink = (string)table["HREF"];
if (relativeLink != null)
{
relativeLink = ParserUtils.RemoveChars(relativeLink, '\n');
relativeLink = ParserUtils.RemoveChars(relativeLink, '\r');
}
return(processor.Extract(relativeLink, url));
}
catch (System.Exception e)
{
string msg;
if (tag != null)
{
msg = tag.Text;
}
else
{
msg = "null";
}
throw new ParserException(
"HTMLLinkScanner.ExtractLink() : Error while extracting link from tag " + msg + ", url = " + url, e);
}
}
/// <summary> Extract the location of the image, given the string to be parsed, and the url
/// of the html page in which this tag exists.
/// </summary>
/// <param name="tag">String to be parsed
/// </param>
/// <param name="url">URL of web page being parsed
///
/// </param>
public virtual string ExtractImageLocn(Tag tag, string url)
{
string relativeLink = null;
try
{
table = tag.Attributes;
relativeLink = (string)table["SRC"];
if (relativeLink != null)
{
relativeLink = ParserUtils.RemoveChars(relativeLink, '\n');
relativeLink = ParserUtils.RemoveChars(relativeLink, '\r');
}
if (relativeLink == null || relativeLink.Length == 0)
{
// try fix
string tagText = tag.Text.ToUpper();
int indexSrc = tagText.IndexOf("SRC");
if (indexSrc != -1)
{
// There is a missing equals.
tag.Text = tag.Text.Substring(0, (indexSrc + 3) - (0)) + "=" +
tag.Text.Substring(indexSrc + 3, (tag.Text.Length) - (indexSrc + 3));
table = tag.RedoParseAttributes();
relativeLink = (string)table["SRC"];
}
}
if (relativeLink == null)
{
return("");
}
else
{
return(processor.Extract(relativeLink, url));
}
}
catch (System.Exception e)
{
throw new ParserException(
"HTMLImageScanner.ExtractImageLocn() : Error in extracting image location, relativeLink = " +
relativeLink + ", url = " + url, e);
}
}