public TwitterMonitor(string consumerKey, string consumerSecret, string accessToken, string accessTokenSecret) { // Set up your credentials (https://apps.twitter.com) Auth.SetUserCredentials(consumerKey, consumerSecret, accessToken, accessTokenSecret); m_HtmlStripper = new HTMLStripper(); }
public FeedDownloader() { m_HtmlStripper = new HTMLStripper(); m_EntityHasher = new SHA256Managed(); m_EntityHasher.Initialize(); m_Utf8Encoding = new UTF8Encoding(); }
public WebScraper() { m_BlackList = new HashSet <string> { "www.siliconarmada.com" }; // Configure a generic Text Extractor, which just remove HTML tags from retrieved webpages // and customized extractor based on tag properties for specific domains m_TextExtractors = new Dictionary <string, ITextExtractor> { { "default", new BaseTextExtractor() }, { "techcrunch.com", new TagSelectorTextExtractor("//div[@class='article-entry text']") }, { "mashable.com", new TagSelectorTextExtractor("//section[@class='article-content blueprint']") }, { "twitter.com", new TagSelectorTextExtractor("//div[@class='js-tweet-text-container']") } }; m_HtmlStripper = new HTMLStripper(); m_Client = new HttpClient(); m_Client.DefaultRequestHeaders.Add("User-Agent", MSEdgeFCUUserAgent); }