public void Should_crawl_website()
{
var configuration = new Configuration();
var pageDownloader = new PageDownloader(configuration);
var htmlParser = new HtmlParser();
var pageCrawler = new SinglePageCrawler(htmlParser, pageDownloader);
var documentStore = new DocumentStoreInitializer("http://localhost:8080", "NetCrawler").DocumentStore;
var persister = new RavenDbCrawlPersister(documentStore);
var urlHasher = new UrlHasher();
var crawlUrlRepository = new InMemoryCrawlUrlRepository();
var websiteCrawler = new WebsiteCrawler(new CrawlScheduler(urlHasher, configuration, pageCrawler, crawlUrlRepository), persister);
var task = websiteCrawler.RunAsync(new Website
{
RootUrl = "http://www.karenmillen.com/",
MaxConcurrentConnections = 100
});
// task.Wait(new TimeSpan(0, 10, 0));
// task.Wait(new TimeSpan(0, 2, 0));
task.Wait();
task.Status.ShouldBeEquivalentTo(TaskStatus.RanToCompletion);
var result = task.Result;
Console.WriteLine("Crawl completed: {0} urls crawled in {1}", result.NumberOfPagesCrawled, (result.CrawlEnded - result.CrawlStarted).ToString());
}
public void Should_extract_links_from_page()
{
var configuration = new Configuration();
var pageDownloader = new PageDownloader(configuration);
var htmlParser = new HtmlParser();
var crawler = new SinglePageCrawler(htmlParser, pageDownloader);
var result = crawler.Crawl(new Uri("http://vladpetroff.com"));
}
static void Main()
{
XmlConfigurator.Configure();
var log = LogManager.GetLogger(typeof (Program));
var configuration = new Configuration();
var pageDownloader = new PageDownloader(configuration);
var htmlParser = new HtmlParser();
var pageCrawler = new SinglePageCrawler(htmlParser, pageDownloader);
var urlHasher = new UrlHasher();
var documentStore = new DocumentStoreInitializer("http://localhost:8080", "NetCrawler2").DocumentStore;
// var documentStore = new DocumentStoreInitializer("http://SLB-4B6WZN1:8080", "NetCrawler2").DocumentStore;
var persister = new RavenDbCrawlPersister(documentStore);
// var crawlUrlRepository = new InMemoryCrawlUrlRepository();
var crawlUrlRepository = new RedisCrawlUrlRepository();
var websiteCrawler = new WebsiteCrawler(new CrawlScheduler(urlHasher, configuration, pageCrawler, crawlUrlRepository), persister);
var task = websiteCrawler.RunAsync(new [] {
new Website
{
RootUrl = "http://www.karenmillen.com/",
MaxConcurrentConnections = 25
},
new Website
{
RootUrl = "http://uk.tommy.com/",
MaxConcurrentConnections = 25
},
new Website
{
RootUrl = "http://www.houseoffraser.co.uk/",
MaxConcurrentConnections = 25
},
new Website
{
RootUrl = "http://vladpetroff.com/",
MaxConcurrentConnections = 25
},
});
var result = task.Result;
log.InfoFormat("Crawl completed: {0} urls crawled in {1}", result.Sum(x => x.NumberOfPagesCrawled), (result.Max(x => x.CrawlEnded) - result.Min(x => x.CrawlStarted)).ToString());
}