/// <summary>
/// Asynchronoulsy Returns a d3 tree node headlines object for the given url,site name and headline selector.
/// Fetches the html of the webpage asynchornously and extracts the news headline texts values
/// using the provided selector (uses Html Agility pack nuget package). The list of headlines is
/// cleaned and limited to the set headline count value. A D3TreeNode is then constrcuted for the
/// headlines and returned.
/// If in error, returns an empty D3TreeNode object.
/// </summary>
/// <param name="siteName"></param>
/// <param name="url"></param>
/// <param name="headlineSelector"></param>
/// <returns>Task<D3TreeNode></returns>
private async Task <D3TreeNode> ConstructHeadlineData(string siteName, string url, string headlineSelector)
{
try
{
/* Asynchoronusly read webpage and extract news headlines */
//TODO: Refactor methods to form a pipeed chain of functions
var doc = await WebScraper.GetHtmlDocument(url);
var rawList = WebScraper.GetRawHeadlines(doc, headlineSelector);
var cleanedList = WebScraper.CleanHeadlines(rawList);
var list = WebScraper.GetLimitedHeadlines(cleanedList, 12);
/* Construct D3 tree data from news headline list*/
var headlineNodes = D3TreeNodeMaker.GetNodesFromStringList(list);
var node = D3TreeNodeMaker.ConstructNode(siteName, "null", headlineNodes);
return(node);
}
catch (Exception)
{
//TODO: Propagate error to caller
return(D3TreeNode.Empty());
}
}
public static int InjectScraperServiceDependecies()
{
WebScraper.InjectDependencies();
D3TreeNodeMaker.InjectDependencies();
return(0);
}
