public void ParseNoAuthorHtml()
{
var context = TestUtilites.ExecuteExtractor(HtmlWithNoAuthor, new AuthorsExtractor());
context.Authors
.Should()
.HaveCount(0);
}
public void ParseTwoAuthorHtml()
{
var context = TestUtilites.ExecuteExtractor(HtmlWithTwoAuthor, new AuthorsExtractor());
context.Authors
.Should()
.HaveCount(2)
.And
.Contain("John Smith", "Bill Gates");
}
public void ParseOneAuthorHtml()
{
var context = TestUtilites.ExecuteExtractor(HtmlWithAuthor, new AuthorsExtractor());
context.Authors
.Should()
.HaveCount(1)
.And
.Contain("John Smith");
}
public void ShouldExtractFromTitleTag()
{
var htmlContent = string.Format(TitleTagTemplate, "my title");
var htmlDocument = TestUtilites.CreateHtmlDocument(htmlContent);
var context = new ExtractorContext(htmlDocument);
var extractor = new TitleExtractor();
extractor.Execute(context);
context.Title.Should().Be("my title");
}
public void ParseSimpleHtml()
{
var htmlDocument = TestUtilites.CreateHtmlDocument(HtmlWithOpenGraph);
var context = new ExtractorContext(htmlDocument);
var extractor = new OpengraphExtractor();
extractor.Execute(context);
context.OpenGraph.Should().ContainKeys("title", "type", "url", "image");
context.OpenGraph["title"].Should().Be("The Rock");
context.OpenGraph["type"].Should().Be("video.movie");
context.OpenGraph["url"].Should().Be("http://www.imdb.com/title/tt0117500/");
context.OpenGraph["image"].Should().Be("http://ia.media-imdb.com/images/rock.jpg");
}
public void ShouldExtractFromOpenGraph(string title, string expectedTitle)
{
var htmlDocument = TestUtilites.CreateHtmlDocument("<html></hmtl>");
var context = new ExtractorContext(htmlDocument)
{
OpenGraph = new Dictionary <string, string>()
{
{ "title", title },
{ "site_name", "hi" }
},
Domain = "www.example.com"
};
var extractor = new TitleExtractor();
extractor.Execute(context);
context.Title.Should().Be(expectedTitle);
}
