public override async Task <List <XRay.Term> > GetTerms(string dataUrl, IProgressBar progress, CancellationToken token)
{
if (sourceHtmlDoc == null)
{
Logger.Log("Downloading Goodreads page...");
sourceHtmlDoc = new HtmlDocument();
sourceHtmlDoc.LoadHtml(await HttpDownloader.GetPageHtmlAsync(dataUrl));
}
var charNodes = sourceHtmlDoc.DocumentNode.SelectNodes("//div[@class='infoBoxRowTitle' and text()='Characters']/../div[@class='infoBoxRowItem']/a");
if (charNodes == null)
{
return(new List <XRay.Term>());
}
// Check if ...more link exists on Goodreads page
var moreCharNodes = sourceHtmlDoc.DocumentNode.SelectNodes("//div[@class='infoBoxRowTitle' and text()='Characters']/../div[@class='infoBoxRowItem']/span[@class='toggleContent']/a");
var allChars = moreCharNodes == null ? charNodes : charNodes.Concat(moreCharNodes);
var termCount = moreCharNodes == null ? charNodes.Count : charNodes.Count + moreCharNodes.Count;
Logger.Log($"Gathering term information from Goodreads... ({termCount})");
progress?.Set(0, termCount);
if (termCount > 20)
{
Logger.Log("More than 20 characters found. Consider using the 'download to XML' option if you need to build repeatedly.");
}
var terms = new ConcurrentBag <XRay.Term>();
await allChars.ParallelForEachAsync(async charNode =>
{
try
{
terms.AddNotNull(await GetTerm(dataUrl, charNode.GetAttributeValue("href", "")).ConfigureAwait(false));
progress?.Add(1);
}
catch (Exception ex)
{
if (ex.Message.Contains("(404)"))
{
Logger.Log("Error getting page for character. URL: " + "https://www.goodreads.com" + charNode.GetAttributeValue("href", "")
+ "\r\nMessage: " + ex.Message + "\r\n" + ex.StackTrace);
}
}
}, MaxConcurrentRequests, token);
return(terms.ToList());
}
