public bool InitializeCrawler(string seedUrl, int sessionId, int crawlerId, CrawlConfiguration config)
{
_config = config;
//check if a crawl is already defined
var existingRun = _repo.GetCrawl(sessionId, crawlerId);
if (existingRun != null)
{
var mssg = string.Format("CrawlerRun exists with sessionId: {0} and crawlerId: {1}; cancelling run ...", sessionId, crawlerId);
_logger.Error(mssg);
return(false);
}
Seed = new Uri(seedUrl);
CrawlerDefinition = new CrawlerRun()
{
SessionId = sessionId,
SeedUrl = Seed.AbsoluteUri,
CrawlerId = crawlerId,
BaseDomain = Seed.GetBaseDomain()
};
_repo.AddCrawl(CrawlerDefinition);
_scheduler = new MyScheduler(new LogicProvider(), CrawlerDefinition, _repo);
_crawler = new PoliteWebCrawler(_config, null, null, _scheduler, null, null, null, null, null);
_crawler.CrawlBag.SessionId = CrawlerDefinition.SessionId;
_crawler.CrawlBag.CrawlerId = CrawlerDefinition.CrawlerId;
_crawler.ShouldScheduleLink(ShouldScheduleLink);
_crawler.ShouldCrawlPage(ShouldCrawlPage);
if (IsAsync)
{
_crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
_crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
_crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
_crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
}
else
{
_crawler.PageCrawlStarting += crawler_ProcessPageCrawlStarting;
_crawler.PageCrawlCompleted += crawler_ProcessPageCrawlCompleted;
_crawler.PageCrawlDisallowed += crawler_PageCrawlDisallowed;
_crawler.PageLinksCrawlDisallowed += crawler_PageLinksCrawlDisallowed;
}
return(true);
}
// This method gets called by the runtime. Use this method to configure the HTTP request pipeline.
// Injecting services
public void Configure(IApplicationBuilder app, IHostingEnvironment env, IMyScheduler sch)
{
if (env.IsDevelopment())
{
app.UseDeveloperExceptionPage();
}
// Setup HangFire Scheduled tasks (run )
app.UseHangfireServer();
app.UseHangfireDashboard();
// Run Offer exiry processing every (web interface http://localhost/hangfire)
//RecurringJob.AddOrUpdate(() => sch.ProcessExpiredOffers(), Cron.Minutely);
//RecurringJob.AddOrUpdate(() => Console.WriteLine("Minutely Job executed"), Cron.Minutely);
RecurringJob.AddOrUpdate(() => sch.ProcessExpiredOffers(), "*/1 * * * *");
app.UseCors("default");
app.UseAuthentication();
app.UseMvc();
}
public bool InitializeCrawler(string seedUrl, int sessionId, int crawlerId, CrawlConfiguration config)
{
_config = config;
//check if a crawl is already defined
var existingRun = _repo.GetCrawl(sessionId, crawlerId);
if (existingRun != null)
{
var mssg = string.Format("CrawlerRun exists with sessionId: {0} and crawlerId: {1}; cancelling run ...", sessionId, crawlerId);
_logger.Error(mssg);
return false;
}
Seed = new Uri(seedUrl);
CrawlerDefinition = new CrawlerRun()
{
SessionId = sessionId,
SeedUrl = Seed.AbsoluteUri,
CrawlerId = crawlerId,
BaseDomain = Seed.GetBaseDomain()
};
_repo.AddCrawl(CrawlerDefinition);
_scheduler = new MyScheduler(new LogicProvider(), CrawlerDefinition, _repo);
_crawler = new PoliteWebCrawler(_config, null, null, _scheduler, null, null, null, null, null);
_crawler.CrawlBag.SessionId = CrawlerDefinition.SessionId;
_crawler.CrawlBag.CrawlerId = CrawlerDefinition.CrawlerId;
_crawler.ShouldScheduleLink(ShouldScheduleLink);
_crawler.ShouldCrawlPage(ShouldCrawlPage);
if (IsAsync)
{
_crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
_crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
_crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
_crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
}
else
{
_crawler.PageCrawlStarting += crawler_ProcessPageCrawlStarting;
_crawler.PageCrawlCompleted += crawler_ProcessPageCrawlCompleted;
_crawler.PageCrawlDisallowed += crawler_PageCrawlDisallowed;
_crawler.PageLinksCrawlDisallowed += crawler_PageLinksCrawlDisallowed;
}
return true;
}
