public void Constructor_ValidArg_SetsPublicProperty() { PageToCrawl page = new CrawledPage(new Uri("http://aaa.com/")); PageCrawlStartingArgs args = new PageCrawlStartingArgs(new CrawlContext(), page); Assert.AreSame(page, args.PageToCrawl); }
private void ThrowExceptionWhen_PageCrawlStarting(object sender, PageCrawlStartingArgs e) { throw new Exception("no!!!"); }
void crawler_ProcessPageCrawlStarting(object sender, PageCrawlStartingArgs e) { PageToCrawl pageToCrawl = e.PageToCrawl; Console.WriteLine("About to crawl link {0} which was found on page {1}", pageToCrawl.Uri.AbsoluteUri, pageToCrawl.ParentUri.AbsoluteUri); }
/// <summary> /// Asynchronous event that is fired before a page is crawled. /// </summary> public static void ProcessPageCrawlStarting(object sender, PageCrawlStartingArgs e) { PageToCrawl pageToCrawl = e.PageToCrawl; String uri = e.PageToCrawl.Uri.AbsoluteUri; //Console.WriteLine("About to crawl link {0} which was found on page {1}", pageToCrawl.Uri.AbsoluteUri, pageToCrawl.ParentUri.AbsoluteUri); //Check if the page has been modified since the last crawl if (_crawledPages.ContainsKey(uri) && !ReVisit.ShouldReVisit(_crawledPages, uri)) { PageCrawlDisallowed(pageToCrawl, null); } }
static void crawler_ProcessPageCrawlStarting(object sender, PageCrawlStartingArgs e) { //Process data }
static void crawler_ProcessPageCrawlStarting(object sender, PageCrawlStartingArgs e) { PageToCrawl pageToCrawl = e.PageToCrawl; //Debug.WriteLine(string.Format("从链接: {1},获得链接: {0}", pageToCrawl.Uri.AbsoluteUri, pageToCrawl.ParentUri.AbsoluteUri)); }
private void crawler_ProcessPageCrawlStarting(object sender, PageCrawlStartingArgs e) { CrawlContext context = e.CrawlContext; //Also id info to the page to crawl (will be passed to Crawled Page) e.PageToCrawl.PageBag.SessionId = SessionId; e.PageToCrawl.PageBag.CrawlerId = CrawlerId; PageToCrawl pageToCrawl = e.PageToCrawl; _logger.DebugFormat("Page Crawl Starting {0} which was found on page {1}", pageToCrawl.Uri.AbsoluteUri, pageToCrawl.ParentUri.AbsoluteUri); }
private void PageCrawlStartingEvent(object sender, PageCrawlStartingArgs e) { }