public string ExtractBodyTextFromArticleDocument(HtmlDocument articleHtmlDocument)
{
RemoveHeadersFromDocument(articleHtmlDocument);
RemoveLinksFromDocument(articleHtmlDocument);
RemoveUnorderedListsFromDocument(articleHtmlDocument);
RemoveScriptsFromDocument(articleHtmlDocument);
if (articleHtmlDocument?.DocumentNode?.OuterHtml == null)
{
return(String.Empty);
}
var cleanedHtml = articleHtmlDocument.DocumentNode.OuterHtml;
var htmlToTextConversion = _spider.HtmlToTextAsync(cleanedHtml);
Task.WaitAll(htmlToTextConversion);
if (htmlToTextConversion.IsCompletedSuccessfully)
{
var articleText = htmlToTextConversion.Result.Replace("\n", " ");
var finalArticleText = RemoveNonBodyTextSentences(articleText);
return(finalArticleText);
}
else
{
throw new Exception($"could not convert the following html to text {cleanedHtml}");
}
}
