I have this page: www.unnu.com/music-artists
need to retrieve this complete list of all the artists and their links.
HtmlAgilityPack.HtmlDocument htmlDoc = new HtmlAgilityPack.HtmlDocument();
// There are various options, set as needed
htmlDoc.OptionFixNestedTags = true;
// filePath is a path to a file containing the html
htmlDoc.Load("http://www.unnu.com/music-artists");
// Use: htmlDoc.LoadHtml(xmlString); to load from a string (was htmlDoc.LoadXML(xmlString)
// ParseErrors is an ArrayList containing any errors from the Load statement
if (htmlDoc.ParseErrors != null && htmlDoc.ParseErrors.Count() > 0)
{
// Handle any parse errors as required
}
else
{
if (htmlDoc.DocumentNode != null)
{
HtmlAgilityPack.HtmlNode bodyNode = htmlDoc.DocumentNode.SelectSingleNode("//a");
if (bodyNode != null)
{
listBox1 = ????//this is not working, do not know if the code is correct and just missing here or is this all wrong.
}
}
}
Please, I need this with urgency as it is a job. If you need my skype is gnrmalazagnr can add.
I am not sure what you want to do here, but if just want to download and read the html file. you need
WebClient web = new WebClient();
web.DownloadStringAsync(new Uri("www.unnu.com/music-artists"));
web.DownloadStringCompleted += web_DownloadStringCompleted;
void web_DownloadStringCompleted(object sender, DownloadStringCompletedEventArgs e)
{
string HtmlPage = e.Result;
}
I resolve the problem thanks:
void web_DownloadStringCompleted(object sender, DownloadStringCompletedEventArgs e) {
if (!e.Cancelled && e.Error == null && !String.IsNullOrEmpty(e.Result))
{
_artistas = new List<Artista>();
// Aqui você pega todos os links da página
// P.S.: Se a página mudar, você tem que alterar o pattern aqui.
string pattern = @"\<a\shref\=[\""|\'](?<url>[^\""|\']+)[\""|\']\stitle\=[\""|\'](?<title>[^\""|\']+)[\""|\']\>(?<author>[^\<]+)\<\/a\>";
// Busca no HTML todos os links
MatchCollection ms = Regex.Matches(e.Result, pattern, RegexOptions.Multiline);
Debug.WriteLine("----- OK {0} links encontrados", ms.Count);
foreach (Match m in ms)
{
// O pattern acima está dizendo onde fica o Url e onde fica o nome do artista
// e esses são resgatados aqui
Group url = m.Groups["url"];
Group author = m.Groups["author"];
if (url != null && author != null)
{
//Debug.WriteLine("author: {0}\nUrl: {1}", author.Value, url.Value);
// Se caso tenha encontrado o link do artista (pois há outros links na página) continua
if(url.Value.ToLower().IndexOf("/artist/") > -1)
{
// Adiciona um objeto Artista à lista
Artista artista = new Artista(author.Value, url.Value);
_artistas.Add(artista);
}
}
}
listBox1.ItemsSource = _artistas;
}
}