internal void PrintProgress(HtmlCrawler crawler)
 {
     if (_timeLastLogged < DateTime.Now.AddSeconds(-10))
     {
         string template = "Crawled: {0}: {1} pages, {2} links, {3} links remaining";
         string progress = string.Format(template, DateTime.Now.ToString("MM/dd/yyyy HH:mm:ss"), crawler.NumberOfPagesCrawled, crawler.NumberOfLinksCrawled, crawler.NumberOfLinksToCrawl);
         Console.WriteLine(progress);
         _timeLastLogged = DateTime.Now;
     }
 }
Example #2
0
        static void Main(string[] args)
        {
            Console.WriteLine("Started Crawling at " + DateTime.Now.ToString("MM/dd/yyyy HH:mm:ss"));

            var crawlerProgress = new HtmlCrawlerProgress();
            var crawler         = new HtmlCrawler("http://www.leg.wa.gov", "/house", crawlerProgress);

            crawler.Crawl(200);

            Console.WriteLine("Press the Enter key to exit anytime... ");
            Console.ReadLine();
        }