public void GenStuff()
{
PoliteWebCrawler crawler = new PoliteWebCrawler();
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
//PageObjects are being created as they are asynchronously found during the crawl
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
CrawlResult result = crawler.Crawl(new Uri(ConfigurationManager.AppSettings["HomePageURL"]));
int count = result.CrawlContext.CrawledCount;
Console.WriteLine(result.CrawlContext.ToJSON());
Console.WriteLine(result.ToJSON());
Console.WriteLine("Total Crawled Page Count = " + count);
////Parse txt file URLS and Get all page elements from each page and put into a dictionary
//var xpathElements = CreateXpathsFromUrls();
////Get all values that are the same
//var sameValues = GetSameValues(xpathElements);
////get New Elements that do not exist on multiple pages
//var newElements = GetNewElements(sameValues, xpathElements);
Console.WriteLine("hello");
}
static void DoCrawl()
{
CrawlConfiguration crawlConfig = AbotConfigurationSectionHandler.LoadFromXml().Convert();
crawlConfig.CrawlTimeoutSeconds = 100;
crawlConfig.MaxConcurrentThreads = 10;
crawlConfig.MaxPagesToCrawl = 5000;
crawlConfig.UserAgentString = "abot v1.0 http://code.google.com/p/abot";
//crawlConfig.ConfigurationExtensions.Add("SomeCustomConfigValue1", "1111");
//crawlConfig.ConfigurationExtensions.Add("SomeCustomConfigValue2", "2222");
//Will use app.config for confguration
PoliteWebCrawler crawler = new PoliteWebCrawler();
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
CrawlResult result = crawler.Crawl(new Uri("http://sunnah.com/"));
Console.WriteLine("jumlah crawled content :" + result.CrawlContext.CrawledCount);
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
}
protected AbotRecipeExtractor(PoliteWebCrawler politeWebCrawler, IHtmlRecipeParser htmlRecipeParser, ILogger <AbotRecipeExtractor> logger = null)
{
_politeWebCrawler = politeWebCrawler;
_htmlRecipeParser = htmlRecipeParser;
Logger = logger;
_politeWebCrawler.PageCrawlCompleted += OnPageCrawlCompleted;
}
public WebSpider()
{
_crawler = new PoliteWebCrawler();
_crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
_crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
_crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
_crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
_crawler.ShouldCrawlPage((pageToCrawl, crawlContext) =>
{
CrawlDecision decision = new CrawlDecision {
Allow = true
};
var isCrawlDepth1 = pageToCrawl.CrawlDepth == 0 && !pageToCrawl.Uri.AbsoluteUri.Contains("www.baidu.com/s?wd");
var isCrawlDepth2 = pageToCrawl.CrawlDepth == 1 && !pageToCrawl.Uri.AbsoluteUri.Contains("www.baidu.com/link");
if (isCrawlDepth1 || isCrawlDepth2)
{
return new CrawlDecision {
Allow = false, Reason = "Dont want to crawl google pages"
}
}
;
return(decision);
});
}
private static IWebCrawler GetCustomBehaviorUsingLambdaWebCrawler()
{
IWebCrawler crawler = new PoliteWebCrawler();
crawler.ShouldCrawlPage((pageToCrawl, crawlContext) =>
{
return(new CrawlDecision {
Allow =
(pageToCrawl.Uri.AbsoluteUri.StartsWith("https://home.treasury.gov") ||
pageToCrawl.Uri.AbsoluteUri.StartsWith("https://www.treasury.gov")) &&
!pageToCrawl.Uri.AbsoluteUri.EndsWith(".pdf")
});
});
crawler.ShouldDownloadPageContent((crawledPage, crawlContext) =>
{
return(new CrawlDecision {
Allow = true
});
});
//Register a lambda expression that will tell Abot to not crawl links on any page that is not internal to the root uri.
//NOTE: This lambda is run after the regular ICrawlDecsionMaker.ShouldCrawlPageLinks method is run
crawler.ShouldCrawlPageLinks((crawledPage, crawlContext) =>
{
return(new CrawlDecision {
Allow = true
});
});
return(crawler);
}
public void Crawl_MinCrawlDelayDelayZero_DomainRateLimiterNotCalled()
{
Uri uri1 = new Uri(_rootUri.AbsoluteUri + "a.html");
Uri uri2 = new Uri(_rootUri.AbsoluteUri + "b.html");
CrawledPage homePage = new CrawledPage(_rootUri)
{
RawContent = "content here"
};
CrawledPage page1 = new CrawledPage(uri1);
CrawledPage page2 = new CrawledPage(uri2);
List <Uri> links = new List <Uri> {
uri1, uri2
};
_fakeHttpRequester.Setup(f => f.MakeRequest(_rootUri, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(homePage);
_fakeHttpRequester.Setup(f => f.MakeRequest(uri1, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(page1);
_fakeHttpRequester.Setup(f => f.MakeRequest(uri2, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(page2);
_fakeHyperLinkParser.Setup(f => f.GetLinks(It.Is <CrawledPage>(p => p.Uri == homePage.Uri))).Returns(links);
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPage(It.IsAny <PageToCrawl>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPageLinks(It.IsAny <CrawledPage>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_unitUnderTest = new PoliteWebCrawler(_dummyConfiguration, _fakeCrawlDecisionMaker.Object, _dummyThreadManager, _dummyScheduler, _fakeHttpRequester.Object, _fakeHyperLinkParser.Object, _fakeMemoryManager.Object, _fakeDomainRateLimiter.Object, _fakeRobotsDotTextFinder.Object);
_unitUnderTest.Crawl(_rootUri);
_fakeDomainRateLimiter.Verify(f => f.RateLimit(It.IsAny <Uri>()), Times.Never());
}
public void Crawl_MinCrawlDelayGreaterThanZero_CallsDomainRateLimiter()
{
Uri uri1 = new Uri(_rootUri.AbsoluteUri + "a.html");
Uri uri2 = new Uri(_rootUri.AbsoluteUri + "b.html");
CrawledPage homePage = new CrawledPage(_rootUri)
{
RawContent = "content here"
};
CrawledPage page1 = new CrawledPage(uri1);
CrawledPage page2 = new CrawledPage(uri2);
List <Uri> links = new List <Uri> {
uri1, uri2
};
_fakeHttpRequester.Setup(f => f.MakeRequest(_rootUri, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(homePage);
_fakeHttpRequester.Setup(f => f.MakeRequest(uri1, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(page1);
_fakeHttpRequester.Setup(f => f.MakeRequest(uri2, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(page2);
_fakeHyperLinkParser.Setup(f => f.GetLinks(It.Is <CrawledPage>(p => p.Uri == homePage.Uri))).Returns(links);
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPage(It.IsAny <PageToCrawl>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPageLinks(It.IsAny <CrawledPage>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_dummyConfiguration.MinCrawlDelayPerDomainMilliSeconds = 1;//BY HAVING A CRAWL DELAY ABOVE ZERO WE EXPECT THE IDOMAINRATELIMITER TO BE CALLED
_unitUnderTest = new PoliteWebCrawler(_dummyConfiguration, _fakeCrawlDecisionMaker.Object, _dummyThreadManager, _dummyScheduler, _fakeHttpRequester.Object, _fakeHyperLinkParser.Object, _fakeMemoryManager.Object, _fakeDomainRateLimiter.Object, _fakeRobotsDotTextFinder.Object);
_unitUnderTest.Crawl(_rootUri);
_fakeDomainRateLimiter.Verify(f => f.RateLimit(It.IsAny <Uri>()), Times.Exactly(3));//BY HAVING A CRAWL DELAY ABOVE ZERO WE EXPECT THE IDOMAINRATELIMITER TO BE CALLED
}
private static void Main(string[] args)
{
try
{
Uri uriToCrawl = GetSiteToCrawl();
// I'm using the default crawler
var crawler = new PoliteWebCrawler();
// I need to subscribe to this event in order to process pages that have been crawled
crawler.PageCrawlCompletedAsync += ProcessPageCrawlCompleted;
// Start the crawl
CrawlResult crawlResult = crawler.Crawl(uriToCrawl);
// Generate report
Task <ReportResult> reportTask = GenerateReport();
PrintResultInformation(reportTask.Result);
}
catch (Exception ex)
{
System.Console.ForegroundColor = ConsoleColor.Red;
System.Console.WriteLine("There was an error when trying to crawl page.");
System.Console.Write(ex);
System.Console.ReadKey();
}
}
static void Main(string[] args)
{
CrawlConfiguration crawlConfig = new CrawlConfiguration();
crawlConfig.CrawlTimeoutSeconds = 100;
crawlConfig.MaxConcurrentThreads = 1;
crawlConfig.MaxPagesToCrawl = 1;
PoliteWebCrawler crawler = new PoliteWebCrawler(crawlConfig);
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
//crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
//crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
CrawlResult result = crawler.Crawl(new Uri("http://www.kmhk.kmu.edu.tw/news/list.asp?P_classify=9")); //This is synchronous, it will not go to the next line until the crawl has completed
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
}
/// <summary>
/// 运行爬虫
/// </summary>
public void StartCrawl()
{
//设置爬虫
PoliteWebCrawler crawler = new PoliteWebCrawler();
//设置爬取条件
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
//开始爬取
CrawlResult result = crawler.Crawl(new Uri(link)); //This is synchronous, it will not go to the next line until the crawl has completed
//返回结果
if (result.ErrorOccurred)
{
log.Error("链接" + result.RootUri.AbsoluteUri + "出现差错爬取完成:" + result.ErrorException.Message);
Console.WriteLine("链接 {0} 出现差错爬取完成: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
log.Info("链接" + result.RootUri.AbsoluteUri + "无差错爬取完成!");
Console.WriteLine("链接 {0} 无差错爬取完成.", result.RootUri.AbsoluteUri);
}
flag = false;
}
public WebsiteIndexer(string host, ICollection <string> ignoredPathes = null, int delayPerRequestMilliSeconds = 1000, int maxPagesToCrawl = 1000)
{
_host = host;
var config = new CrawlConfiguration
{
MaxPagesToCrawl = maxPagesToCrawl,
MinCrawlDelayPerDomainMilliSeconds = delayPerRequestMilliSeconds,
IsExternalPageCrawlingEnabled = false
};
Crawler = new PoliteWebCrawler(config)
{
ShouldCrawlPageDecisionMaker = (pageToCrawl, crawlContext) =>
{
var ignored = string.IsNullOrEmpty(pageToCrawl.Uri?.AbsolutePath) || ignoredPathes?.Any(p => Regex.IsMatch(pageToCrawl.Uri.AbsolutePath, p)) == true;
if (ignored)
{
Console.WriteLine($"Ignored '{pageToCrawl.Uri?.AbsolutePath}'");
return(new CrawlDecision {
Allow = false, Reason = "Path matches pattern in blacklist"
});
}
return(new CrawlDecision {
Allow = true
});
}
};
Crawler.PageCrawlCompleted += PageCrawlCompleted;
}
public static void StartCrawlEbuyer(string url)
{
try
{
PoliteWebCrawler crawler = new PoliteWebCrawler();
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
TimeSpan ts = new TimeSpan(0, 0, 5);
CancellationTokenSource cancellationTokenSource = new CancellationTokenSource(ts);
CrawlResult result = crawler.Crawl(new Uri(url), cancellationTokenSource);
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
}catch (Exception)
{
}
ExtractingHtml.ExtractDetailsEbuyer();
}
public void StartCrawl(string[] pages)
{
CrawlConfiguration();
PoliteWebCrawler crawler = new PoliteWebCrawler(_crawlConfiguration);
crawler.PageCrawlStartingAsync += Crawler_PageCrawlStartingAsync;
crawler.PageCrawlCompletedAsync += Crawler_PageCrawlCompletedAsync;
crawler.PageCrawlDisallowedAsync += Crawler_PageCrawlDisallowedAsync;
crawler.PageLinksCrawlDisallowedAsync += Crawler_PageLinksCrawlDisallowedAsync;
foreach (var page in pages)
{
_parser.IdentifyParser(page);
var result = crawler.Crawl(new Uri(page));
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
_parser.Save();
}
}
public async Task Crawl_IsRespectRobotsDotTextTrue_RobotsDotTextFound_PageIsDisallowed_DoesNotCallHttpRequester()
{
var homePage = new CrawledPage(_rootUri)
{
Content = new PageContent
{
Text = "content here"
}
};
_fakeRobotsDotText.Setup(f => f.GetCrawlDelay(It.IsAny <string>())).Returns(0);
_fakeRobotsDotText.Setup(f => f.IsUrlAllowed(It.IsAny <string>(), It.IsAny <string>())).Returns(false);
_fakeRobotsDotTextFinder.Setup(f => f.FindAsync(It.IsAny <Uri>())).Returns(Task.FromResult(_fakeRobotsDotText.Object));
_dummyConfiguration.IsRespectRobotsDotTextEnabled = true;
_unitUnderTest = new PoliteWebCrawler(_dummyConfiguration, _fakeCrawlDecisionMaker.Object, _dummyThreadManager, _dummyScheduler, _fakeHttpRequester.Object, _fakeHtmlParser.Object, _fakeMemoryManager.Object, _fakeDomainRateLimiter.Object, _fakeRobotsDotTextFinder.Object);
await _unitUnderTest.CrawlAsync(_rootUri);
_fakeHttpRequester.Setup(f => f.MakeRequestAsync(It.IsAny <Uri>(), It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(Task.FromResult(homePage));
_fakeRobotsDotText.VerifyAll();
_fakeRobotsDotTextFinder.VerifyAll();
_fakeDomainRateLimiter.Verify(f => f.AddDomain(It.IsAny <Uri>(), It.IsAny <long>()), Times.Exactly(0));
_fakeDomainRateLimiter.Verify(f => f.RateLimit(It.IsAny <Uri>()), Times.Exactly(0));
}
public void Crawl(CrawlRequest request)
{
CrawlConfiguration crawlConfig = new CrawlConfiguration();
crawlConfig.CrawlTimeoutSeconds = 100;
crawlConfig.MaxConcurrentThreads = 10;
crawlConfig.MaxPagesToCrawl = 1000;
crawlConfig.UserAgentString = "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; abot v1.0 http://code.google.com/p/abot)";
crawlConfig.ConfigurationExtensions.Add("SomeCustomConfigValue1", "1111");
crawlConfig.ConfigurationExtensions.Add("SomeCustomConfigValue2", "2222");
crawlConfig.MaxCrawlDepth = 10;
crawlConfig.DownloadableContentTypes = "text/html, text/plain";
//Will use the manually created crawlConfig object created above
PoliteWebCrawler crawler = new PoliteWebCrawler(crawlConfig, null, null, null, null, null, null, null, null);
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowed;
crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowed;
CrawlResult result = crawler.Crawl(new Uri(request.EntryURL));
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
}
public void Crawl_IsRespectRobotsDotTextTrue_RobotsDotTextFound_PageIsDisallowed_IsIgnoreRobotsDotTextIfRootDisallowedEnabledTrue_CallsHttpRequester()
{
CrawledPage homePage = new CrawledPage(_rootUri)
{
Content = new PageContent
{
Text = "content here"
}
};
CrawledPage page1 = new CrawledPage(_rootUri);
_fakeRobotsDotText.Setup(f => f.IsUrlAllowed(It.IsAny <string>(), It.IsAny <string>())).Returns(false);
_fakeRobotsDotTextFinder.Setup(f => f.Find(It.IsAny <Uri>())).Returns(_fakeRobotsDotText.Object);
_fakeHttpRequester.Setup(f => f.MakeRequest(_rootUri, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(page1);
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPage(It.IsAny <PageToCrawl>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_dummyConfiguration.IsRespectRobotsDotTextEnabled = true;
_dummyConfiguration.IsIgnoreRobotsDotTextIfRootDisallowedEnabled = true;
_unitUnderTest = new PoliteWebCrawler(_dummyConfiguration, _fakeCrawlDecisionMaker.Object, _dummyThreadManager, _dummyScheduler, _fakeHttpRequester.Object, _fakeHyperLinkParser.Object, _fakeMemoryManager.Object, _fakeDomainRateLimiter.Object, _fakeRobotsDotTextFinder.Object);
_unitUnderTest.Crawl(_rootUri);
_fakeCrawlDecisionMaker.VerifyAll();
_fakeRobotsDotText.VerifyAll();
_fakeRobotsDotTextFinder.VerifyAll();
_fakeHttpRequester.VerifyAll();
}
public void Crawl_IsRateLimited()
{
new PageRequester(new CrawlConfiguration {
UserAgentString = "aaa"
}).MakeRequest(new Uri("http://localhost.fiddler:1111/PageGenerator/ClearCounters"));
CrawlConfiguration configuration = new CrawlConfiguration();
configuration.MaxPagesToCrawl = 3;
configuration.MinCrawlDelayPerDomainMilliSeconds = 1000; // 1 second * 2 pages = 2 (or more) seconds
int pagesCrawledCount = 0;
var crawler = new PoliteWebCrawler(configuration);
crawler.PageCrawlCompletedAsync += (a, b) => pagesCrawledCount++;
var uriToCrawl = new Uri("http://localhost.fiddler:1111/");
var start = DateTime.Now;
crawler.Crawl(uriToCrawl);
var elapsed = DateTime.Now - start;
Assert.GreaterOrEqual(elapsed.TotalMilliseconds, 2000);
Assert.AreEqual(3, pagesCrawledCount);
}
static void Main(string[] args)
{
CrawlConfiguration config = new CrawlConfiguration();
config.MaxConcurrentThreads = 1; // Web Extractor is not currently thread-safe.
// Create the PhantomJS instance. This will spawn a new PhantomJS process using phantomjs.exe.
// Make sure to dispose this instance or you will have a zombie process!
IWebDriver driver = CreatePhantomJsDriver(config);
// Create the content extractor that uses PhantomJS.
IWebContentExtractor extractor = new JavaScriptContentExtractor(driver);
// Create a PageRequester that will use the extractor.
IPageRequester requester = new PageRequester(config, extractor);
using (IWebCrawler crawler = new PoliteWebCrawler(config, null, null, null, requester, null, null, null, null)) {
crawler.PageCrawlCompleted += OnPageCrawlCompleted;
CrawlResult result = crawler.Crawl(new Uri("http://wvtesting2.com/"));
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
}
Console.Read();
}
public static void Main(string[] args)
{
PoliteWebCrawler crawler = new PoliteWebCrawler();
crawler.PageCrawlCompletedAsync += Crawler_ProcessPageCrawlCompleted;
var start = DateTime.Now;
var uri = new Uri("https://lord.technology");
CrawlResult result = crawler.Crawl(uri);
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
var finish = DateTime.Now;
Console.WriteLine((finish - start).TotalMinutes);
using (FileStream fs = File.Open(@"./crawl.json", FileMode.Create))
using (StreamWriter sw = new StreamWriter(fs))
using (JsonWriter jw = new JsonTextWriter(sw))
{
jw.Formatting = Formatting.Indented;
JsonSerializer serializer = new JsonSerializer();
serializer.Serialize(jw, new { nodes = _pages, edges = _relationships });
}
}
public async Task Crawl_MaxPagesTo25_OnlyCrawls25Pages()
{
await new PageRequester(new CrawlConfiguration {
UserAgentString = "aaa"
}).MakeRequestAsync(new Uri("http://localhost:1111/PageGenerator/ClearCounters"));
CrawlConfiguration configuration = new CrawlConfiguration();
configuration.MaxPagesToCrawl = 25;
configuration.IsExternalPageCrawlingEnabled = true;
configuration.IsExternalPageLinksCrawlingEnabled = true;
int pagesCrawledCount = 0;
PoliteWebCrawler crawler = new PoliteWebCrawler(configuration, null, null, null, null, null, null, null, null);
crawler.PageCrawlCompleted += (a, b) =>
{
pagesCrawledCount++;
};
var res = await crawler.CrawlAsync(new Uri("http://localhost:1111/"));
Assert.AreEqual(25, pagesCrawledCount);
}
//Crawling code for GSM
public static void StartCrawlGSM(string url)
{
PoliteWebCrawler crawler = new PoliteWebCrawler();
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStartingGSM;
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompletedGSM;
crawler.PageCrawlDisallowedAsync += crawler_PageCrawlDisallowedGSM;
crawler.PageLinksCrawlDisallowedAsync += crawler_PageLinksCrawlDisallowedGSM;
TimeSpan ts = new TimeSpan(0, 0, 0);
CancellationTokenSource cancellationTokenSource = new CancellationTokenSource(ts);
CrawlResult result = crawler.Crawl(new Uri(url), cancellationTokenSource);
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} completed with error: {1}", result.RootUri.AbsoluteUri, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} completed without error.", result.RootUri.AbsoluteUri);
}
//FileStream fs = new FileStream("url.txt", FileMode.Open);
//StreamReader sr = new StreamReader(fs);
//string str = "";
//while ((str = sr.ReadLine()) != null)
//{
// StartCrawl(str);
//}
ExtractingHtml.ExtractingDetailsGSM();
}
public async Task Crawl(string rootUri, int maxPages)
{
try
{
PoliteWebCrawler crawler = new PoliteWebCrawler(CreateCrawlConfiguration(maxPages), null, null, null, null, null, null, null, null);
crawler.PageCrawlStartingAsync += crawler_ProcessPageCrawlStarting;
crawler.PageCrawlCompletedAsync += crawler_ProcessPageCrawlCompleted;
CrawlResult result = crawler.Crawl(new Uri(rootUri)); //This is synchronous, it will not go to the next line until the crawl has completed
if (result.ErrorOccurred)
{
Console.WriteLine("Crawl of {0} ({1} pages) completed with error: {2}", result.RootUri.AbsoluteUri, PageCount, result.ErrorException.Message);
}
else
{
Console.WriteLine("Crawl of {0} ({1} pages) completed without error.", result.RootUri.AbsoluteUri, PageCount);
}
await _handler.CrawlFinishedAsync();
}
catch (Exception e)
{ }
}
public void Crawl_IsRespectRobotsDotTextTrue_RobotsDotTextFound_PageIsDisallowed_DoesNotCallHttpRequester()
{
Uri uri1 = new Uri(_rootUri.AbsoluteUri + "a.html");
Uri uri2 = new Uri(_rootUri.AbsoluteUri + "b.html");
CrawledPage homePage = new CrawledPage(_rootUri)
{
Content = new PageContent
{
Text = "content here"
}
};
CrawledPage page1 = new CrawledPage(uri1);
CrawledPage page2 = new CrawledPage(uri2);
List <Uri> links = new List <Uri> {
uri1, uri2
};
_fakeRobotsDotText.Setup(f => f.GetCrawlDelay(It.IsAny <string>())).Returns(0);
_fakeRobotsDotText.Setup(f => f.IsUrlAllowed(It.IsAny <string>(), It.IsAny <string>())).Returns(false);
_fakeRobotsDotTextFinder.Setup(f => f.Find(It.IsAny <Uri>())).Returns(_fakeRobotsDotText.Object);
_dummyConfiguration.IsRespectRobotsDotTextEnabled = true;
_unitUnderTest = new PoliteWebCrawler(_dummyConfiguration, _fakeCrawlDecisionMaker.Object, _dummyThreadManager, _dummyScheduler, _fakeHttpRequester.Object, _fakeHyperLinkParser.Object, _fakeMemoryManager.Object, _fakeDomainRateLimiter.Object, _fakeRobotsDotTextFinder.Object);
_unitUnderTest.Crawl(_rootUri);
_fakeHttpRequester.Setup(f => f.MakeRequest(It.IsAny <Uri>(), It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(homePage);
_fakeRobotsDotText.VerifyAll();
_fakeRobotsDotTextFinder.VerifyAll();
_fakeDomainRateLimiter.Verify(f => f.AddDomain(It.IsAny <Uri>(), It.IsAny <long>()), Times.Exactly(0));
_fakeDomainRateLimiter.Verify(f => f.RateLimit(It.IsAny <Uri>()), Times.Exactly(0));
}
public KwestiaSmakuRecipeExtractor(
PoliteWebCrawler politeWebCrawler,
IHtmlRecipeParser htmlRecipeParser,
ILogger <AbotRecipeExtractor> logger = null)
: base(politeWebCrawler, htmlRecipeParser, logger)
{
}
public void Test(Uri uri)
{
pageCount = 0;
baseUri = uri;
string message;
CrawlConfiguration crawlConfiguration = new CrawlConfiguration();
crawlConfiguration.MaxConcurrentThreads = 4;
crawlConfiguration.UserAgentString =
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) " +
"AppleWebKit/537.36 (KHTML, like Gecko) " +
"Chrome/60.0.3112.113 Safari/537.36 bot";
crawlConfiguration.MaxPagesToCrawl = 10000;
crawlConfiguration.DownloadableContentTypes =
"text/html, text/plain, image/jpeg, image/pjpeg, image/png";
crawlConfiguration.CrawlTimeoutSeconds = 100;
crawlConfiguration.MinCrawlDelayPerDomainMilliSeconds = 1000;
using PoliteWebCrawler crawler =
new PoliteWebCrawler(crawlConfiguration);
crawler.PageCrawlStarting += ProcessPageCrawlStarted;
crawler.PageCrawlCompleted += ProcessPageCrawlCompleted;
CrawlResult result = crawler.CrawlAsync(baseUri).Result;
if (result.ErrorOccurred)
{
message = StringTable.GetString(
"CRAWL_COMPLETE_ERROR",
CultureInfo.InstalledUICulture);
Log.InfoFormat(
CultureInfo.InvariantCulture,
message,
result.RootUri.AbsoluteUri,
result.ErrorException.Message);
}
else
{
message = StringTable.GetString(
"CRAWL_COMPLETE_NO_ERROR",
CultureInfo.InstalledUICulture);
Log.InfoFormat(
CultureInfo.InvariantCulture,
message,
result.RootUri.AbsoluteUri);
}
message = StringTable.GetString(
"TOTAL_PAGES",
CultureInfo.InstalledUICulture);
Log.InfoFormat(
CultureInfo.InvariantCulture,
message,
pageCount.ToString(CultureInfo.InvariantCulture));
}
private static async Task DemoSimpleCrawler()
{
var config = new CrawlConfiguration
{
UserAgentString = "2019RLCrawlAThon",
MaxPagesToCrawl = 0,
MinCrawlDelayPerDomainMilliSeconds = 10,
};
var start = new Uri("https://thailand.kyocera.com/");
var crawler = new PoliteWebCrawler(
config,
new BetterDecisionMaker(start),
null,
new Scheduler(false, null, new PriorityUriRepository()),
null,
null,
null,
null,
null);
var files = new HashSet <string>();
var decMaker = new CrawlDecisionMaker();
var batch = new HashSet <string>();
crawler.PageCrawlCompleted += Crawler_PageCrawlCompleted;
crawler.PageCrawlCompleted += (sender, e) =>
{
if (new[] { ".exe", ".zip", ".tar" }.Any(c => e.CrawledPage.Uri.AbsolutePath.Contains(c)))
{
lock (files)
{
Console.WriteLine("Found file: " + e.CrawledPage.Uri.Host + e.CrawledPage.Uri.LocalPath);
Console.WriteLine(e.CrawledPage.CrawlDepth);
if (!files.Contains(e.CrawledPage.Uri.ToString()))
{
files.Add(e.CrawledPage.Uri.ToString());
batch.Add(e.CrawledPage.Uri.ToString());
if (batch.Count >= 10)
{
using (var httpClient = new HttpClient())
{
using (var request = new HttpRequestMessage(new HttpMethod("POST"), "http://hackathon.reversinglabs.com/api/test/bulk"))
{
var base64authorization = Convert.ToBase64String(Encoding.ASCII.GetBytes("tztok_jadnici:7@dQ6dqq7YZggcd"));
request.Headers.TryAddWithoutValidation("Authorization", $"Basic {base64authorization}");
var body = "{\"crawlathon\": {\"query\": {\"site\": \"filehippo\", \"links\":[" + string.Join(", ", batch.Select(s => "\"" + s + "\"")) + "]}}}";
request.Content = new StringContent(body, Encoding.UTF8, "application/json");
var resp = httpClient.SendAsync(request).Result;
batch.Clear();
}
}
}
}
}
}
};
var crawlResult = await crawler.CrawlAsync(start);
}
public async Task Crawl_IsRespectRobotsDotTextTrue_RobotsDotTextFound_CrawlDelayAboveMinDomainCrawlDelay_CallsDomainRateLimiter()
{
var uri1 = new Uri(_rootUri.AbsoluteUri + "a.html");
var uri2 = new Uri(_rootUri.AbsoluteUri + "b.html");
var homePage = new CrawledPage(_rootUri)
{
Content = new PageContent
{
Text = "content here"
}
};
var page1 = new CrawledPage(uri1);
var page2 = new CrawledPage(uri2);
var links = new List <HyperLink>
{
new HyperLink()
{
HrefValue = uri1
},
new HyperLink()
{
HrefValue = uri2
}
};
_fakeHttpRequester.Setup(f => f.MakeRequestAsync(_rootUri, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(Task.FromResult(homePage));
_fakeHttpRequester.Setup(f => f.MakeRequestAsync(uri1, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(Task.FromResult(page1));
_fakeHttpRequester.Setup(f => f.MakeRequestAsync(uri2, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(Task.FromResult(page2));
_fakeHtmlParser.Setup(f => f.GetLinks(It.Is <CrawledPage>(p => p.Uri == homePage.Uri))).Returns(links);
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPage(It.IsAny <PageToCrawl>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPageLinks(It.IsAny <CrawledPage>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_fakeCrawlDecisionMaker.Setup(f => f.ShouldRecrawlPage(It.IsAny <CrawledPage>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = false
});
_fakeRobotsDotText.Setup(f => f.GetCrawlDelay(It.IsAny <string>())).Returns(3);//this is more then the max configured crawl delay (should be ignored)
_fakeRobotsDotText.Setup(f => f.IsUrlAllowed(It.IsAny <string>(), It.IsAny <string>())).Returns(true);
_fakeRobotsDotTextFinder.Setup(f => f.FindAsync(It.IsAny <Uri>())).Returns(Task.FromResult(_fakeRobotsDotText.Object));
_dummyConfiguration.IsRespectRobotsDotTextEnabled = true; //BY HAVING A THIS EQUAL TO TRUE WE EXPECT THE IDOMAINRATELIMITER TO BE CALLED
_dummyConfiguration.MaxRobotsDotTextCrawlDelayInSeconds = 2; //This is less than the crawl delay (Should Be used)
_unitUnderTest = new PoliteWebCrawler(_dummyConfiguration, _fakeCrawlDecisionMaker.Object, _dummyThreadManager, _dummyScheduler, _fakeHttpRequester.Object, _fakeHtmlParser.Object, _fakeMemoryManager.Object, _fakeDomainRateLimiter.Object, _fakeRobotsDotTextFinder.Object);
await _unitUnderTest.CrawlAsync(_rootUri);
_fakeHttpRequester.VerifyAll();
_fakeHtmlParser.VerifyAll();
_fakeRobotsDotText.VerifyAll();
_fakeRobotsDotTextFinder.VerifyAll();
_fakeDomainRateLimiter.Verify(f => f.AddDomain(It.IsAny <Uri>(), 2000), Times.Exactly(1));
_fakeDomainRateLimiter.Verify(f => f.RateLimit(It.IsAny <Uri>()), Times.Exactly(3));//BY HAVING A CRAWL DELAY ABOVE ZERO WE EXPECT THE IDOMAINRATELIMITER TO BE CALLED
}
static void Main(string[] args)
{
SiteMapFinder finder = new SiteMapFinder();
PoliteWebCrawler crawler = new PoliteWebCrawler(null, null, null, null, null, finder, null, null, null);
crawler.PageCrawlCompleted += Crawler_PageCrawlCompleted;
CrawlResult result = crawler.Crawl(new Uri("http://tenders.rfpalertservices.com/sitemap/"));
}
public async Task Crawl_IsRespectRobotsDotTextTrue_RobotsDotTextFound_ZeroCrawlDelay_StillCallsDomainRateLimiter()
{
var uri1 = new Uri(_rootUri.AbsoluteUri + "a.html");
var uri2 = new Uri(_rootUri.AbsoluteUri + "b.html");
var homePage = new CrawledPage(_rootUri)
{
Content = new PageContent
{
Text = "content here"
}
};
var page1 = new CrawledPage(uri1);
var page2 = new CrawledPage(uri2);
var links = new List <HyperLink>
{
new HyperLink()
{
HrefValue = uri1
},
new HyperLink()
{
HrefValue = uri2
}
};
_fakeHttpRequester.Setup(f => f.MakeRequestAsync(_rootUri, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(Task.FromResult(homePage));
_fakeHttpRequester.Setup(f => f.MakeRequestAsync(uri1, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(Task.FromResult(page1));
_fakeHttpRequester.Setup(f => f.MakeRequestAsync(uri2, It.IsAny <Func <CrawledPage, CrawlDecision> >())).Returns(Task.FromResult(page2));
_fakeHtmlParser.Setup(f => f.GetLinks(It.Is <CrawledPage>(p => p.Uri == homePage.Uri))).Returns(links);
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPage(It.IsAny <PageToCrawl>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_fakeCrawlDecisionMaker.Setup(f => f.ShouldCrawlPageLinks(It.IsAny <CrawledPage>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = true
});
_fakeCrawlDecisionMaker.Setup(f => f.ShouldRecrawlPage(It.IsAny <CrawledPage>(), It.IsAny <CrawlContext>())).Returns(new CrawlDecision {
Allow = false
});
_fakeRobotsDotText.Setup(f => f.GetCrawlDelay(It.IsAny <string>())).Returns(0);
_fakeRobotsDotText.Setup(f => f.IsUrlAllowed(It.IsAny <string>(), It.IsAny <string>())).Returns(true);
_fakeRobotsDotTextFinder.Setup(f => f.FindAsync(It.IsAny <Uri>())).Returns(Task.FromResult(_fakeRobotsDotText.Object));
_dummyConfiguration.IsRespectRobotsDotTextEnabled = true;
_unitUnderTest = new PoliteWebCrawler(_dummyConfiguration, _fakeCrawlDecisionMaker.Object, _dummyThreadManager, _dummyScheduler, _fakeHttpRequester.Object, _fakeHtmlParser.Object, _fakeMemoryManager.Object, _fakeDomainRateLimiter.Object, _fakeRobotsDotTextFinder.Object);
await _unitUnderTest.CrawlAsync(_rootUri);
_fakeHttpRequester.VerifyAll();
_fakeHtmlParser.VerifyAll();
_fakeRobotsDotText.VerifyAll();
_fakeRobotsDotTextFinder.VerifyAll();
_fakeDomainRateLimiter.Verify(f => f.AddDomain(It.IsAny <Uri>(), It.IsAny <long>()), Times.Exactly(0));
_fakeDomainRateLimiter.Verify(f => f.RateLimit(It.IsAny <Uri>()), Times.Exactly(3));
}
public void Constructor_ZeroMinCrawlDelay_DoesNotThrowExceptionCreatingAnIDomainRateLimiterWithLessThan1Millisec()
{
using (var unused = new PoliteWebCrawler(new CrawlConfiguration {
MinCrawlDelayPerDomainMilliSeconds = 0
},
null, null, null, null, null, null, null, null))
{
}
}
