private List <BinaryFile> GetImages(Guid pageId, string address, string content)
{
HtmlDocument document = new HtmlDocument();
document.LoadHtml(content);
List <BinaryFile> images = new List <BinaryFile>();
WebClient downloadClient = new WebClient();
try
{
foreach (HtmlNode image in document.DocumentNode.SelectNodes("//img[@src]"))
{
HtmlAttribute imgSrcAttribute = image.Attributes["src"];
UrlObject urlObject = UrlObject.FromRelativeString(address, imgSrcAttribute.Value.ToString());
if (urlObject.Path.LastOrDefault() != null)
{
bool hasValidExtension = false;
foreach (var extension in ValidImgExtensions)
{
var lastOrDefault = urlObject.Path.LastOrDefault();
if (lastOrDefault != null && lastOrDefault.Contains("." + extension))
{
hasValidExtension = true;
}
}
if (hasValidExtension)
{
try
{
byte[] fileBytes = downloadClient.DownloadData(urlObject.GetFullPath(false));
images.Add(new BinaryFile(pageId)
{
Url = urlObject,
Tag = image.OuterHtml,
Name = urlObject.Path.LastOrDefault(),
Contents = new MemoryStream(fileBytes),
});
Console.WriteLine("Found image: " + urlObject.GetFullPath(false));
}
catch (WebException wex)
{
log.Warn(wex);
}
}
}
}
}
catch (Exception e)
{
log.Warn("No image tags present in document", e);
}
return(images);
}
public override bool Equals(Object o1)
{
if (o1 != null)
{
UrlObject o1obj = (UrlObject)o1;
return(o1obj.GetFullPath(false) == this.GetFullPath(false));
}
else
{
return(false);
}
}
private Page GetPage(UrlObject address)
{
// web client for downloading the file
try
{
string fullPath = address.GetFullPath(false);
string pageContent = StringFromAddress(fullPath); // Client.DownloadString yada yada yada...
string title = GetTitle(pageContent);
var pageId = Guid.NewGuid();
List <LinkTag> links = null;
links = GetLinks(pageId, fullPath, pageContent);
List <BinaryFile> images = null;
if (this.JobType == SpiderJobType.PAGE_ONLY ||
this.JobType == SpiderJobType.PING_ONLY)
{
images = new List <BinaryFile>();
}
else
{
images = GetImages(pageId, fullPath, pageContent);
}
List <BinaryFile> files = null;
if (this.JobType == SpiderJobType.PAGE_ONLY ||
this.JobType == SpiderJobType.PING_ONLY)
{
files = new List <BinaryFile>();
}
else
{
files = GetFiles(pageId, fullPath, pageContent);
}
return(new Page
{
Content = pageContent,
Name = title,
FileTags = files,
ImageTags = images,
LinkTags = links,
Link = address,
PageId = pageId
});
}
catch (Exception wex)
{
log.Warn(wex);
return(null);
}
}
private Page GetPage(UrlObject address)
{
// web client for downloading the file
try
{
string fullPath = address.GetFullPath(false);
string pageContent = StringFromAddress(fullPath); // Client.DownloadString yada yada yada...
string title = GetTitle(pageContent);
var pageId = Guid.NewGuid();
List<LinkTag> links = null;
links = GetLinks(pageId, fullPath, pageContent);
List<BinaryFile> images = null;
if (this.JobType == SpiderJobType.PAGE_ONLY
|| this.JobType == SpiderJobType.PING_ONLY)
{
images = new List<BinaryFile>();
}
else
{
images = GetImages(pageId, fullPath, pageContent);
}
List<BinaryFile> files = null;
if (this.JobType == SpiderJobType.PAGE_ONLY
|| this.JobType == SpiderJobType.PING_ONLY)
{
files = new List<BinaryFile>();
}
else
{
files = GetFiles(pageId, fullPath, pageContent);
}
return new Page
{
Content = pageContent,
Name = title,
FileTags = files,
ImageTags = images,
LinkTags = links,
Link = address,
PageId = pageId
};
}
catch (Exception wex)
{
log.Warn(wex);
return null;
}
}
