public void TestReadingEncodedFile(string fileName, System.Text.Encoding encoding, System.Text.Encoding defaultEncoding)
{
// Set some options, so that we can know if things are working...
LoaderOptions loaderOptions = new LoaderOptions();
loaderOptions.DetectEncoding = true;
loaderOptions.DefaultEncoding = defaultEncoding;
loaderOptions.ParserOptions.IncludeMetaData = true;
// Load multi-byte html file into memory
XmlDocument doc = XHtmlLoader.LoadHtml(_sampleMultiByteHtml);
// Ensure Sample directory exists
string sampleDir = (new DirectoryInfo(AssemblyDirectory)).Parent.Parent.Parent.FullName + "\\SampleData\\";
if (!Directory.Exists(sampleDir))
{
Directory.CreateDirectory(sampleDir);
}
// Create Encoded file
string fullName = sampleDir + fileName;
using (TextWriter sw = new StreamWriter(File.Create(fullName), encoding))
{
doc.Save(sw);
}
// Re-load into memory
XmlDocument doc2 = XHtmlLoader.LoadWebPageAsync("file://" + fullName, loaderOptions).Result;
Console.WriteLine("Reading file: " + fileName);
Console.WriteLine(doc2.OuterXml);
Assert.AreEqual(doc.SelectSingleNode("//body").OuterXml, doc2.SelectSingleNode("//body").OuterXml);
}
static void Main(string[] args)
{
// Load Html string into an XmlDocument
XmlDocument doc1 = XHtmlLoader.LoadHtml("<html><head><title>Hello World!</title><body><h1>Hello World</h1><p>This is a test</body>");
Console.WriteLine("OuterXml is: " + doc1.OuterXml);
// Load web page into an XmlDocument
XmlDocument doc2 = XHtmlLoader.LoadWebPageAsync("http://wikipedia.org").Result;
string title = doc2.SelectSingleNode("//title").InnerText;
Console.WriteLine("Title is: " + title);
}
/// <summary>
/// Sample scraper
/// </summary>
public static async Task <Article[]> GetCodeProjectArticlesAsync(int pageNum = 1)
{
List <Article> results = new List <Article>();
// Get web page as an XHtml document using XHtmlKit
string url = "https://www.codeproject.com/script/Articles/Latest.aspx?pgnum=" + pageNum;
XmlDocument page = await XHtmlLoader.LoadWebPageAsync(url);
// Select all articles using an anchor node containing a robust @class attribute
var articles = page.SelectNodes("//table[contains(@class,'article-list')]/tr[@valign]");
// Get each article
foreach (XmlNode a in articles)
{
// Extract article data - we need to be aware that sometimes there are no results
// for certain fields
var category = a.SelectSingleNode("./td[1]//a/text()");
var title = a.SelectSingleNode(".//div[@class='title']/a/text()");
var date = a.SelectSingleNode(".//div[contains(@class,'modified')]/text()");
var rating = a.SelectSingleNode(".//div[contains(@class,'rating-stars')]/@title");
var desc = a.SelectSingleNode(".//div[@class='description']/text()");
var author = a.SelectSingleNode(".//div[contains(@class,'author')]/text()");
XmlNodeList tagNodes = a.SelectNodes(".//div[@class='t']/a/text()");
StringBuilder tags = new StringBuilder();
foreach (XmlNode tagNode in tagNodes)
{
tags.Append((tags.Length > 0 ? "," : "") + tagNode.Value);
}
// Create the data structure we want
Article article = new Article
{
Category = category != null ? category.Value : string.Empty,
Title = title != null ? title.Value : string.Empty,
Author = author != null ? author.Value : string.Empty,
Description = desc != null ? desc.Value : string.Empty,
Rating = rating != null ? rating.Value : string.Empty,
Date = date != null ? date.Value : string.Empty,
Tags = tags.ToString()
};
// Add to results
results.Add(article);
}
return(results.ToArray());
}
static void Crawl(string[] args)
{
// Get crawler settings from the command-line
Settings crawlerSettings = new Settings();
// Get command-line settings - use XHtmlKit parser. Why not.
if (args.Length > 0)
{
string settingsHtml = "<settings " + string.Join(" ", args) + " />";
XmlDocument settingsDoc = new XmlDocument();
XHtmlLoader.LoadHtmlFragment(settingsDoc, settingsHtml.ToLower());
XmlElement settings = settingsDoc.DocumentElement;
crawlerSettings.Url = (settings.Attributes["url"] != null && !string.IsNullOrWhiteSpace(settings.Attributes["url"].Value)) ? settings.Attributes["url"].Value.Trim() : crawlerSettings.Url;
crawlerSettings.Depth = settings.Attributes["depth"] != null?Convert.ToInt32(settings.Attributes["depth"].Value) : crawlerSettings.Depth;
crawlerSettings.UrlFilter = (settings.Attributes["urlfilter"] != null && !string.IsNullOrWhiteSpace(settings.Attributes["urlfilter"].Value)) ? settings.Attributes["urlfilter"].Value.Trim() : crawlerSettings.UrlFilter;
crawlerSettings.OutputDir = (settings.Attributes["outputdir"] != null && !string.IsNullOrWhiteSpace(settings.Attributes["outputdir"].Value)) ? settings.Attributes["outputdir"].Value.Trim() : crawlerSettings.OutputDir;
crawlerSettings.Encoding = (settings.Attributes["encoding"] != null && !string.IsNullOrWhiteSpace(settings.Attributes["encoding"].Value)) ? settings.Attributes["encoding"].Value.Trim() : crawlerSettings.Encoding;
crawlerSettings.IncludeMetaData = (settings.Attributes["includemetadata"] != null);
}
// Gather HtmlParser and HtmlClient options
LoaderOptions xhtmlLoaderOptions = new LoaderOptions();
xhtmlLoaderOptions.ParserOptions.IncludeMetaData = crawlerSettings.IncludeMetaData;
xhtmlLoaderOptions.DetectEncoding = (crawlerSettings.Encoding == null);
xhtmlLoaderOptions.DefaultEncoding = crawlerSettings.Encoding != null?System.Text.Encoding.GetEncoding(crawlerSettings.Encoding) : xhtmlLoaderOptions.DefaultEncoding;
// Create 'todo' and 'done' lists
Queue <Link> urlsToCrawl = new Queue <Link>();
HashSet <string> urlsCrawled = new HashSet <string>();
Uri baseUri = new Uri(crawlerSettings.Url.ToLower());
// Add the root url to the todo list
urlsToCrawl.Enqueue(new Link {
Url = crawlerSettings.Url
});
Console.WriteLine("Crawling Url = " + crawlerSettings.Url + " Depth = " + crawlerSettings.Depth + " OutputDir = '" + crawlerSettings.OutputDir + "' UrlFilter = '" + crawlerSettings.UrlFilter + "'");
// Crawl all urls on the 'todo' list
while (urlsToCrawl.Count > 0)
{
Link currentUrl = urlsToCrawl.Dequeue();
Console.Write(currentUrl.Url);
urlsCrawled.Add(currentUrl.Url.ToLower());
// Crawl the Url using XHtmlKit
XmlDocument xhtmlDoc;
try
{
xhtmlDoc = XHtmlLoader.LoadWebPageAsync(currentUrl.Url, xhtmlLoaderOptions).Result;
Console.WriteLine(", [OK]");
}
catch (Exception ex)
{
Console.WriteLine(", [Error], " + (ex.InnerException != null ? ex.InnerException.Message : ""));
continue;
}
// Get title from the XHtml document
var title = xhtmlDoc.SelectSingleNode("//title");
if (title != null)
{
currentUrl.PageTitle = title.InnerText.Trim();
}
// Save the XHtml file to disk
try
{
if (!string.IsNullOrWhiteSpace(crawlerSettings.OutputDir))
{
Uri currentUri = new Uri(currentUrl.Url.ToLower());
string fileName = currentUri.PathAndQuery.Trim();
// Replace invalid characters
foreach (char c in System.IO.Path.GetInvalidFileNameChars())
{
fileName = fileName.Replace(c.ToString(), ".");
}
fileName = fileName.Trim(new char[] { '.' });
// Set default file name
if (string.IsNullOrWhiteSpace(fileName))
{
fileName = "default";
}
// Add xml extension
fileName = fileName + ".xml";
// Ensure output directory exists
string outputDir = crawlerSettings.OutputDir + "\\" + currentUri.Host;
if (!System.IO.Directory.Exists(outputDir))
{
System.IO.Directory.CreateDirectory(outputDir);
}
// Save file
xhtmlDoc.Save(outputDir + "\\" + fileName);
}
}
catch (Exception ex)
{
Console.WriteLine("Error saving document: " + ex.Message);
}
// Get sub-links from the XHtml
var subLinkElems = xhtmlDoc.SelectNodes("//a");
// If we are at the Max Depth, we won't crawl deeper
if (currentUrl.Depth >= crawlerSettings.Depth)
{
continue;
}
// Add sub-links to the 'todo' list
int numSubLinks = 0;
foreach (XmlNode subLinkElem in subLinkElems)
{
// Don't add empty links
if (subLinkElem.Attributes["href"] == null || string.IsNullOrWhiteSpace(subLinkElem.Attributes["href"].InnerText))
{
continue;
}
// Get the sub-link
string sublink = subLinkElem.Attributes["href"].InnerText;
if (!Uri.IsWellFormedUriString(sublink.ToLower(), UriKind.RelativeOrAbsolute))
{
continue;
}
Uri subUri = new Uri(sublink.ToLower());
// Don't add links that don't match the UrlFilter
if (!string.IsNullOrWhiteSpace(crawlerSettings.UrlFilter) && (!sublink.Contains(crawlerSettings.UrlFilter)))
{
continue;
}
// Don't add links that we have already crawled...
if (urlsCrawled.Contains(sublink.ToLower()))
{
continue;
}
// Add the sub-link
urlsToCrawl.Enqueue(new Link {
Url = sublink, LinkText = subLinkElem.InnerText.Trim(), Depth = (currentUrl.Depth + 1)
});
numSubLinks++;
}
currentUrl.SubLinks = numSubLinks;
// Todo - put the currentUrl metadata somewhere...
}
}
public static async Task LoadWebPageAsync(this XmlDocument doc, string url)
{
await XHtmlLoader.LoadWebPageAsync(doc, url, new LoaderOptions());
}
