private void ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
if (e.CrawledPage.HttpWebResponse != null && e.CrawledPage.HttpWebResponse.StatusCode == HttpStatusCode.OK)
{
_crawlingStats.ProcessCrawledPage(e.CrawledPage);
}
}
static void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
string strPage=e.CrawledPage.Content.Text;
HtmlNodeCollection aTags = e.CrawledPage.HtmlDocument.DocumentNode.SelectNodes("//h1");
string name="";
if(aTags!=null&&aTags.Count>0)
{
name = aTags[0].InnerText;
Console.WriteLine(name);
}
HtmlNodeCollection aTable = e.CrawledPage.HtmlDocument.DocumentNode.SelectNodes("//table[@id='auction-bidhist']");
HtmlNodeCollection aTr = e.CrawledPage.HtmlDocument.DocumentNode.SelectNodes("//table[@id='auction-bidhist']//tr");
//int index = strPage.IndexOf("col_half col_last single-product");
//int devEnd = strPage.IndexOf("</h1>", index);
//string str = strPage.Substring(index, devEnd - index);
//str = str.Substring(str.IndexOf("<h1>") + 4);
if (aTr != null && aTr[1].InnerText.IndexOf("No") == -1 )
{
if( aTr[0].InnerText.IndexOf("Winning")==-1)
{
string k = "#";
}
}
//Console.WriteLine(e.CrawledPage.Content);
//Process data
}
public void Constructor_ValidArg_SetsPublicProperty()
{
CrawledPage page = new CrawledPage(new Uri("http://aaa.com/"));
PageCrawlCompletedArgs uut = new PageCrawlCompletedArgs(new CrawlContext(), page);
Assert.AreSame(page, uut.CrawledPage);
}
static void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
saveWebPage(e);
if (e.CrawledPage.Uri.AbsoluteUri.Contains(DemoParameters.shouldSaveToPropertyTableParameter))
saveProperty(e);
}
private void crawler_PageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
PageResult pageResult = new PageResult();
pageResult.Url = e.CrawledPage.Uri.AbsoluteUri;
if(e.CrawledPage.HttpWebResponse != null)
pageResult.HttpStatusCode = Convert.ToInt32(e.CrawledPage.HttpWebResponse.StatusCode);
_actualCrawledPages.Add(pageResult);
}
void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
CrawledPage crawledPage = e.CrawledPage;
if (crawledPage.WebException != null || crawledPage.HttpWebResponse.StatusCode != HttpStatusCode.OK)
Console.WriteLine("Crawl of page failed {0}", crawledPage.Uri.AbsoluteUri);
else
Console.WriteLine("Crawl of page succeeded {0}", crawledPage.Uri.AbsoluteUri);
if (string.IsNullOrEmpty(crawledPage.Content.Text))
Console.WriteLine("Page had no content {0}", crawledPage.Uri.AbsoluteUri);
}
static void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
CrawledPage crawledPage = e.CrawledPage;
if (crawledPage.WebException != null || crawledPage.HttpWebResponse.StatusCode != HttpStatusCode.OK)
SaveURLFail(crawledPage.Uri.AbsoluteUri.ToString());
else
SaveURLSuccess(crawledPage.Uri.AbsoluteUri.ToString());
if (string.IsNullOrEmpty(crawledPage.RawContent))
SaveURLNoContent(crawledPage.Uri.AbsoluteUri.ToString());
}
private static void OnPageCrawlCompleted(object p_Sender, PageCrawlCompletedArgs p_PageCrawlCompletedArgs)
{
CrawledPage page = p_PageCrawlCompletedArgs.CrawledPage;
if (page.WebException != null) {
Console.WriteLine("Crawl of page \"{0}\" failed{2}. Error: {1}",
page.Uri.AbsoluteUri,
page.WebException.Message,
page.IsRetry ? String.Format(" (Retry #{0})", page.RetryCount) : "");
} else if (page.HttpWebResponse.StatusCode != HttpStatusCode.OK) {
Console.WriteLine("Crawl of page \"{0}\" failed{2}. HTTP Status Code: {1}",
page.Uri.AbsoluteUri,
page.HttpWebResponse.StatusCode,
page.IsRetry ? String.Format(" (Retry #{0})", page.RetryCount) : "");
} else {
Console.WriteLine("Page crawl completed [{0}]", page.Uri.AbsoluteUri);
}
}
public void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
backgroundWorker.ReportProgress(1);
string strPage = e.CrawledPage.Content.Text;
HtmlNodeCollection aTags = e.CrawledPage.HtmlDocument.DocumentNode.SelectNodes("//h1");
string name = "", seller = "", buyer = "";
if (aTags != null && aTags.Count > 0)
{
name = aTags[0].InnerText;
}
HtmlNodeCollection aTable = e.CrawledPage.HtmlDocument.DocumentNode.SelectNodes("//table[@id='auction-bidhist']");
HtmlNodeCollection aTr = e.CrawledPage.HtmlDocument.DocumentNode.SelectNodes("//table[@id='auction-bidhist']//tr");
//int index = strPage.IndexOf("col_half col_last single-product");
//int devEnd = strPage.IndexOf("</h1>", index);
//string str = strPage.Substring(index, devEnd - index);
//str = str.Substring(str.IndexOf("<h1>") + 4);
HtmlNodeCollection sellerA = e.CrawledPage.HtmlDocument.DocumentNode.SelectNodes("//h4//a");
if (sellerA != null && sellerA.Count > 0)
{
seller = sellerA[0].InnerText;
}
if (aTr != null && aTr[1].InnerText.IndexOf("No") == -1)
{
if (aTr[0].InnerText.IndexOf("Winning") == -1)
{
HtmlNodeCollection abbTr = aTr[1].SelectNodes("//td//a");
buyer = abbTr[0].InnerText;
}
}
if (name.Trim().Length > 0)
{
SetText(name, seller, buyer, e.CrawledPage.Uri.ToString());
}
//Console.WriteLine(e.CrawledPage.Content);
//Process data
}
/// <summary>
/// Asynchronous event that is fired when an individual page has been crawled.
/// </summary>
public static void ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
if (e.CrawledPage.WebException != null || e.CrawledPage.HttpWebResponse.StatusCode != HttpStatusCode.OK)
Console.WriteLine("Crawl of page failed: {0}\n", e.CrawledPage.Uri.AbsoluteUri);
else if (string.IsNullOrEmpty(e.CrawledPage.RawContent))
{
Console.WriteLine("Page Crawled had no content: {0}\n", e.CrawledPage.Uri.AbsoluteUri);
}
else
{
String uri = e.CrawledPage.Uri.AbsoluteUri;
//String date = new DateTime(e.CrawledPage.HttpWebResponse.Headers["Last-Modified"]);
DateTime lastModified = e.CrawledPage.HttpWebResponse.LastModified;
CrawledWebPage page = new CrawledWebPage(lastModified, e.CrawledPage.HtmlDocument.DocumentNode);
_crawledPages.Add(uri, page);
//Console.WriteLine("Crawled page saved: {0}", crawledPage.Uri.AbsoluteUri);
}
}
static void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
CrawledPage crawledPage = e.CrawledPage;
if (Regex.IsMatch(crawledPage.Uri.ToString(), @"http://www.tingchina.com/erge/(\d+)/play_(\d+)_(\d+)\.htm"))
{
var csQuery = crawledPage.CsQueryDocument.Find("iframe");
foreach (var query in csQuery)
{
if(query.Name=="playmedia")
{
var playSrc = query.GetAttribute("src");
var request = String.Format("http://{0}{1}", crawledPage.Uri.Host, playSrc);
var http = WebRequest.Create(request);
var response = http.GetResponse();
var stream = response.GetResponseStream();
var sr = new StreamReader(stream);
var content = sr.ReadToEnd();
stream.Dispose();
var realUrlIndex = content.IndexOf("url[3]=");
var realUrlIndex1 = content.IndexOf(";", realUrlIndex);
var realUrl = content.Substring(realUrlIndex, realUrlIndex1 - realUrlIndex);
Console.WriteLine("!!!!!!!!!!!!!!!!!!!! " + realUrl + " !!!!!!!!!!!!!!!!!!!!");
}
}
}
if (crawledPage.WebException != null || crawledPage.HttpWebResponse.StatusCode != HttpStatusCode.OK)
Console.WriteLine("Crawl of page failed {0}", crawledPage.Uri.AbsoluteUri);
else
Console.WriteLine("Crawl of page succeeded {0}", crawledPage.Uri.AbsoluteUri);
if (string.IsNullOrEmpty(crawledPage.Content.Text))
Console.WriteLine("Page had no content {0}", crawledPage.Uri.AbsoluteUri);
}
private void ThrowExceptionWhen_PageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
throw new Exception("Oh No!");
}
static void saveWebPage(PageCrawlCompletedArgs e)
{
// save to WebPage table
//Process data
var webpageContext = new WebPageDataContext(DemoParameters.connectionString);
//var webpageContext = new WebPageDataContext();
//IEnumerable<WebPage> wp = dbContext.WebPages.OrderBy(c => c.pageUrl);
WebPage page = new WebPage
{
pageUrl = e.CrawledPage.Uri.ToString(),
parentUrl = e.CrawledPage.ParentUri.ToString(),
requestStartTime = e.CrawledPage.RequestStarted.ToString(),
requestEndTime = e.CrawledPage.RequestCompleted.ToString(),
downloadStartTime = e.CrawledPage.DownloadContentStarted.ToString(),
downloadEndTime = e.CrawledPage.DownloadContentCompleted.ToString(),
//pageHtml = e.CrawledPage.Content.Text
pageHtml = ""
};
webpageContext.WebPages.InsertOnSubmit(page);
try
{
webpageContext.SubmitChanges();
}
catch (Exception ex)
{
Console.WriteLine(ex);
// Make some adjustments.
// ...
// Try again.
webpageContext.SubmitChanges();
}
finally
{
if (webpageContext != null)
webpageContext.Dispose();
}
}
static void saveProperty(PageCrawlCompletedArgs e)
{
// save to Property table
var propertyContext = new PropertyDataContext(DemoParameters.connectionString);
//var propertyContext = new PropertyDataContext();
HtmlNode addressNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//span[@class='js-address']");
string addr = "";
if (addressNode != null) addr = addressNode.InnerText.Trim();
HtmlNode priceNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//dd[@class='price']");
string pric = "";
if (priceNode != null) pric = priceNode.InnerText.Trim();
HtmlNode propertytypeNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//dd[@class='propertytype']");
string ptype = "";
if (propertytypeNode != null) ptype = propertytypeNode.InnerText.Trim();
HtmlNode saletypeNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//dd[@class='saleType']");
string stype = "";
if (saletypeNode != null) stype = saletypeNode.InnerText.Trim();
HtmlNode saledateNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//dd[@class='saleDate']");
string sdate = "";
if (saledateNode != null) sdate = saledateNode.InnerText.Trim();
HtmlNode landsizeNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//dd[@class='land']");
string land = "";
if (landsizeNode != null) land = landsizeNode.InnerText.Trim();
HtmlNode featureNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//p[@class='features']");
string feature = "";
if (featureNode != null) feature = featureNode.InnerText.Trim();
HtmlNode agentNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//ul[@class='cB-agentList']");
string agentInfo = "";
if (agentNode != null) agentInfo = agentNode.InnerText.Trim();
HtmlNode schoolNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//div[@class='schoolData bdy collapsible collapsed']");
string school = "";
if (schoolNode != null) school = schoolNode.InnerText.Trim();
HtmlNode descriptionNode = e.CrawledPage.HtmlDocument.DocumentNode.SelectSingleNode("//div[@class='cT-productDescription']");
string desc = "";
if (descriptionNode != null) desc = descriptionNode.InnerText.Trim();
Property p = new Property
{
pageUrl = e.CrawledPage.Uri.ToString(),
address = addr,
price = pric,
propertyType = ptype,
saleType = stype,
saleDate = sdate,
suburb = "",
landSize = land,
propertyFeature = feature,
agents = agentInfo,
schoolData = school,
propertyDescription = desc
};
propertyContext.Properties.InsertOnSubmit(p);
try
{
propertyContext.SubmitChanges();
}
catch (Exception ex)
{
Console.WriteLine(ex);
// Make some adjustments.
// ...
// Try again.
propertyContext.SubmitChanges();
}
finally
{
if (propertyContext != null)
propertyContext.Dispose();
}
}
void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
try
{
SaveContent(e.CrawledPage);
}
catch (Exception ex)
{
LogHelper.Instance.WriteError(ex,GetType(),MethodBase.GetCurrentMethod().Name);
}
//Process data
}
private void PageCrawlCompletedEvent(object sender, PageCrawlCompletedArgs e)
{
}
static void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
//Process data
}
private void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
CrawledPage crawledPage = e.CrawledPage;
bool externalLinksFound = false;
_logger.DebugFormat("Page Crawl Completed {0}; Status {1}; Source URL: {2}; CrawlerId: {3}; SessionId: {4}",
crawledPage.Uri.AbsoluteUri,
crawledPage.HttpWebResponse.StatusCode,
crawledPage.ParentUri.AbsoluteUri,
crawledPage.PageBag.CrawlerId,
crawledPage.PageBag.SessionId);
//----------------------------------------
// create and store the crawled link
var crawledLink = new CrawledLink();
crawledLink.SessionId = crawledPage.PageBag.SessionId;
crawledLink.CrawlerId = crawledPage.PageBag.CrawlerId;
crawledLink.SourceUrl = crawledPage.ParentUri.AbsoluteUri;
crawledLink.TargetUrl = crawledPage.Uri.AbsoluteUri; // what was crawled
crawledLink.StatusCode = crawledPage.HttpWebResponse.StatusCode;
crawledLink.IsRoot = crawledPage.IsRoot;
crawledLink.CrawlDepth = crawledPage.CrawlDepth;
//------------
if (crawledPage.WebException != null)
{
// store error information if it occurred
crawledLink.ErrorOccurred = true;
crawledLink.Exception = crawledPage.WebException.Message; //TODO store more data of the exception
_logger.Error(string.Format("A WebException occurred for Target Url: {0}; Source URL: {1}; CrawlerId: {2}; SessionId: {3}",
crawledLink.TargetUrl, crawledLink.SourceUrl, crawledLink.CrawlerId, crawledLink.SessionId),
crawledPage.WebException);
}
_scheduler.RecordCrawledLink(crawledLink);
//----------------------------------------
// Check if the page should be processed, if true process it
// - extract the title, keywords, description, cookies, etc from the page
// and save processed data.
if (crawledPage.WebException == null)
{
if (IsPageToBeProcessed(crawledPage.Uri, crawledPage.HttpWebResponse.StatusCode))
{
using (var processor = _provider.GetInstanceOf<ICrawledPageProcessor>())
{
var result = processor.ProcessPage(crawledPage);
_repo.AddProcessedPage(result);
}
}
externalLinksFound = _scheduler.ProcessParsedLinks(crawledPage);
if (externalLinksFound)
{
OnExternalLinksFound(CrawlerId, crawledPage.Uri);
}
}
string mssg = null;
if (crawledPage.WebException != null || crawledPage.HttpWebResponse.StatusCode != HttpStatusCode.OK)
{
mssg = string.Format("Crawl of page failed {0}; source: {1}", crawledPage.Uri.AbsoluteUri, crawledPage.ParentUri.AbsoluteUri);
_logger.Error(mssg);
}
else
{
mssg = string.Format("Crawl of page succeeded {0}; source: {1}", crawledPage.Uri.AbsoluteUri, crawledPage.ParentUri.AbsoluteUri);
_logger.Debug(mssg);
}
if (string.IsNullOrEmpty(crawledPage.Content.Text))
{
mssg = string.Format("Page had no content {0}", crawledPage.Uri.AbsoluteUri);
_logger.Error(mssg);
}
//------------
OnLinkCrawlCompleted(CrawlerDefinition,
crawledPage.ParentUri.AbsoluteUri,
crawledPage.Uri.AbsoluteUri,
crawledPage.HttpWebResponse.StatusCode,
crawledPage.WebException != null,
externalLinksFound);
}
static void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
CrawledPage crawledPage = e.CrawledPage;
if (crawledPage.WebException != null || crawledPage.HttpWebResponse.StatusCode != HttpStatusCode.OK)
Debug.WriteLine(string.Format("页面：{0}抓取失败,原因：{1}", crawledPage.Uri.AbsoluteUri, crawledPage.WebException.Message));
string text = crawledPage.Content.Text;
if (string.IsNullOrEmpty(text))
Console.WriteLine("Page had no content {0}", crawledPage.Uri.AbsoluteUri);
else if (text.Contains("活动八"))
{
}
else
{
var c = Regex.Matches(text, "活动(一|二|三|四|五|六|七|八|九|十)(.|\n)*?活动时间(.|\n)*?<br");
if (c.Count == 0)
{
var a = Regex.Match(text, "thread_subject(.|\n)*?活动(.|\n){1,50}?</a");
if (a.Value != "")
{
var b = Regex.Match(text, "活动时间(.|\n)*?<br");
var time = Regex.Match(b.Value, "\\d{1,2}月\\d{1,2}(-|日)").Value;
Debug.Write(DateTime.Parse(time) + " ");
Debug.WriteLine(Regex.Match(a.Value, "活动(.|\n)*?</a").Value.Replace("】", "：").Replace("<br", "").Replace("</a", ""));
}
}
List<string> list = new List<string>() { "古城探宝", "天降神剑" };
foreach (Match item in c)
{
string date = Regex.Match(item.Value, "\\d{1,2}月\\d{1,2}(-|日)").Value;
if (date != "" && !date.Contains("日"))
{
date = date.Replace("-", "日");
}
Debug.Write(DateTime.Parse(date) + " ");
Debug.WriteLine(Regex.Match(item.Value, "活动(一|二|三|四|五|六|七|八|九|十)(.|\n)*?<br").Value.Replace("】", "：").Replace("<br", "").Replace("</a", ""));
var index = list.FindIndex(x => item.Value.Contains(x));
if (index != -1)
{
Activity activity = new Activity();
activity.Name = list[index];
activity.Date = DateTime.Parse(date);
}
}
}
}
void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
CrawledPage crawledPage = e.CrawledPage;
var crawledPageUri = crawledPage.Uri.ToString();
//Crawling books
if (Regex.IsMatch(crawledPageUri, @"http://www.tingchina.com/*.*/disp_(\d+).htm"))
{
int id = Int32.Parse(Regex.Match(crawledPageUri, @"(\d+)").Captures[0].Value);
lock (booksLockObject)
{
var book = new BookViewModel(id, crawledPage.Uri);
Books.Add(book);
}
}
//Crawling book sections
if (Regex.IsMatch(crawledPageUri, @"http://www.tingchina.com/*.*/(\d+)/play_(\d+)_(\d+)\.htm"))
{
var csQuery = crawledPage.CsQueryDocument.Find("iframe");
foreach (var query in csQuery)
{
if (query.Name == "playmedia")
{
var playSrc = query.GetAttribute("src");
var request = String.Format("http://{0}{1}", crawledPage.Uri.Host, playSrc);
lock (lockObject)
{
Sources.Add(new SoundPlayerSourceViewModel(request));
}
}
}
}
if (crawledPage.WebException != null || crawledPage.HttpWebResponse.StatusCode != HttpStatusCode.OK)
Console.WriteLine("Crawl of page failed {0}", crawledPage.Uri.AbsoluteUri);
else
Console.WriteLine("Crawl of page succeeded {0}", crawledPage.Uri.AbsoluteUri);
if (string.IsNullOrEmpty(crawledPage.Content.Text))
Console.WriteLine("Page had no content {0}", crawledPage.Uri.AbsoluteUri);
}
void crawler_ProcessPageCrawlCompleted(object sender, PageCrawlCompletedArgs e)
{
if (e.CrawledPage.HttpWebResponse != null)
{
int status = (int)e.CrawledPage.HttpWebResponse.StatusCode;
string url = e.CrawledPage.Uri.ToString();
string parent = e.CrawledPage.ParentUri.ToString();
lock (_lock)
{
_logfile.WriteLine("Url {0} - status code {1} seen at {2}", url, status, parent);
}
}
pagesDownloaded++;
Console.Write("Pages downloaded {0}\r", pagesDownloaded);
AddNewPage(e.CrawledPage);
}
