public void StripTagsRegexCompiled_NoTags()
{
//Arrange
var stringToParse = "Hello World!";
//Act
var strippedString = CustomUtlities.StripTagsRegexCompiled(stringToParse);
//Assert
Assert.AreEqual(stringToParse, strippedString);
}
public void StripTagsRegexCompiled_WithTags()
{
//Arrange
var stringToParse = "<html>Hello <strong>World!</strong></html>";
var expectedString = "Hello World!";
//Act
var strippedString = CustomUtlities.StripTagsRegexCompiled(stringToParse);
//Assert
Assert.AreEqual(strippedString, expectedString);
}
public IEnumerable <ISearchResult> Parse(string searchHtmlResult)
{
List <ISearchResult> results = new List <ISearchResult>();
HtmlDocument doc = new HtmlDocument();
doc.LoadHtml(searchHtmlResult);
var searchResultNodes = doc.DocumentNode.SelectNodes(".//li[@class='b_algo']");
//Exit if no results
if (searchResultNodes == null)
{
return(results);
}
foreach (var node in searchResultNodes)
{
//TODO: implement exception handling
var newResult = new SearchResult();
try
{
var url = node.SelectSingleNode(".//h2/a").GetAttributeValue("href", "");
var title = node.SelectSingleNode(".//h2/a/@href").InnerHtml;
var summary = node.SelectSingleNode(".//div[@class='b_caption']/p").InnerHtml;
newResult.Url = CustomUtlities.StripTagsRegexCompiled(url);
newResult.Title = CustomUtlities.StripTagsRegexCompiled(title);
newResult.Summary = CustomUtlities.StripTagsRegexCompiled(summary);
results.Add(newResult);
}
catch (Exception ex)
{
newResult.Title = "Error in parsing";
newResult.Summary = ex.Message;
}
}
return(results);
}
