static void Main(string[] args) { string[] keywords = new string[] { "hello", "csharp" }; Policy p = new GooglePolicy(); Crawler c = new Crawler(p); c.PrepareQueries(keywords); c.Start(); }
static void Main(string[] args) { //const string baseUrl = "https://softuni.bg/users/profile/show/"; //const string baseUrl = "https://softuni.bg/forum?page=0&pageSize=5000"; //get content from forum: https://softuni.bg/forum/4400/0/100 const string fileName = "content"; const string user = "******"; const string forumBaseUrl = "https://softuni.bg/forum/"; var list = new List<int>(); for (int i = 4; i < 4500; i++) { var spider = new Crawler(); var htmlContent = spider.GetHtml(forumBaseUrl + i + "/0/100"); Console.Write("Forum [" + i +"]"); if (htmlContent.ToString().Contains(user)) { list.Add(i); Console.Write("[1]"); } else { Console.Write("[0]"); } Console.WriteLine(); } Console.WriteLine("Completed"); Console.WriteLine(string.Join(", ", list)); Console.ReadLine(); //try //{ // var spider = new Crawler(); // var htmlContent = spider.GetHtml(forumBaseUrl); // spider.SaveHtmlContent(htmlContent, fileName); //} //catch (Exception e) //{ // throw new Exception("There's an error"); //} //finally //{ // Console.WriteLine("Process comepleted!"); // Console.ReadLine(); //} }
public void CrawlWebSite(string domain, IFilter whatAreWeSearchingForToDay) { Crawler c = new Crawler(domain, userAgent == null ? "User-agent: *".ToLower() : userAgent, whatAreWeSearchingForToDay, this); c.Start(); }
public void OnResult(object source, Crawler.Event.SearchResultEventArgs e) { }
/// <summary> /// Creates a crawler, the nth. /// </summary> /// <param name="n">The number of the crawler to start.</param> /// <param name="trainTest">If true, the crawler will actually only train+test, not crawl.</param> private void CreateCrawler(int n, bool trainTest) { crawlers[n] = new Crawler(n, this); if (!trainTest) { // Train the crawlers here, if we're not testing crawlers[n].Train(); SetRichText("Created and trained crawler " + n + "\n"); } }