/// <summary>
/// Initializes a new instance of NReadabilityWebTranscoder.
/// Allows passing in custom-constructed NReadabilityTranscoder,
/// and a custom IUrlFetcher.
/// </summary>
/// <param name="transcoder">A NReadabilityTranscoder.</param>
/// <param name="urlFetcher">IFetcher instance to download content.</param>
/// <param name="pageSeparatorBuilder">A function that creates a HTML fragment for page separator. It takes the page number as an argument.</param>
public NReadabilityWebTranscoder(NReadabilityTranscoder transcoder, IUrlFetcher urlFetcher, Func<int, string> pageSeparatorBuilder)
{
_transcoder = transcoder;
_urlFetcher = urlFetcher;
_sgmlDomSerializer = new SgmlDomSerializer();
_pageSeparatorBuilder = pageSeparatorBuilder;
}
/// <summary>
/// Initializes a new instance of NReadabilityWebTranscoder.
/// Allows passing in custom-constructed NReadabilityTranscoder,
/// and a custom IUrlFetcher. This overload is mostly used for testing.
/// </summary>
/// <param name="transcoder">A NReadabilityTranscoder.</param>
/// <param name="urlFetcher">IFetcher instance to download content.</param>
public NReadabilityWebTranscoder(NReadabilityTranscoder transcoder, IUrlFetcher urlFetcher)
{
_transcoder = transcoder;
_urlFetcher = urlFetcher;
_sgmlDomSerializer = new SgmlDomSerializer();
_pageSeparatorBuilder = _DefaultPageSeparatorBuilder;
}
public void Download(string url, string targetDir, string targetFname)
{
string fname = targetFname.RemoveColon();
string filepath = Path.Combine(targetDir, fname);
//ensure it respects mppl
filepath = Utilities.TrimPathPart(filepath, _futureleanCourse.Max_path_part_len);
WebHeaderCollection responseHeaders = _futureleanCourse._client.ResponseHeaders;
int contentLength = GetContentLength(responseHeaders);
bool isFileNeeded = IsFileNeeded(filepath, contentLength, fname);
if (isFileNeeded)
{
if (Path.GetExtension(filepath) == ".html")
{
string content = _futureleanCourse._client.DownloadString(url);
NReadabilityTranscoder transcoder = new NReadabilityTranscoder();
TranscodingInput tiInput = new TranscodingInput(content);
TranscodingResult transcodedContent = transcoder.Transcode(tiInput);
//.Transcode(content, out success);
File.WriteAllText(filepath, transcodedContent.ExtractedContent);
}
else
{
_futureleanCourse._client.DownloadFile(url, filepath);
}
}
}
public string GetArticle(string filepath)
{
FileStream file =File.OpenRead(filepath);
StreamReader reader = new StreamReader(file);
string Html = reader.ReadToEnd();
reader.Close();
file.Close();
bool success = false;
NReadabilityTranscoder util = new NReadabilityTranscoder();
string Article = util.Transcode(Html, out success);
return Article;
}
private static String GetWebpageContents(String url)
{
var nreadabilityTranscoder = new NReadabilityTranscoder();
using (var wc = new WebClient())
{
var rawHtml = wc.DownloadString(url);
var transcodingInput = new TranscodingInput(rawHtml);
var extractedHtml = nreadabilityTranscoder.Transcode(transcodingInput).ExtractedContent;
var pageHtml = new HtmlDocument();
pageHtml.LoadHtml(extractedHtml);
return pageHtml.DocumentNode.SelectSingleNode("//body").InnerText;
}
}
public static string getTitle(string url)
{
bool mainContentExtracted;
//結果
string source = "";
string title = "";
//トランスコーダー
NReadabilityTranscoder nReadabilityTranscoder = new NReadabilityTranscoder();
//パーサー
HtmlParser hp = new HtmlParser();
//仮想ブラウザ
NonDispBrowser nb = new NonDispBrowser();
//HTMLの取得
source = hp.getHtmlSource(url);
try
{
nb.NavigateAndWaitFromSource(hp.getHtmlPlainTextFromSourceWB(nReadabilityTranscoder.Transcode(source, out mainContentExtracted)));
title = nb.Document.Title;
}
catch
{
}
finally
{
//確実に破棄
nb.Dispose();
}
//結果を返す
return title;
//return hp.getHtmlPlainTextFromSource(nReadabilityTranscoder.Transcode(getHtmlSource(url), out mainContentExtracted));
}
public static string transeForJapa(string url)
{
bool mainContentExtracted;
//結果
string result = "";
string source = "";
string title = "";
//トランスコーダー
NReadabilityTranscoder nReadabilityTranscoder = new NReadabilityTranscoder();
//パーサー
HtmlParser hp = new HtmlParser();
//仮想ブラウザ
using (NonDispBrowser nb = new NonDispBrowser())
{
//HTMLの取得
source = hp.getHtmlSource(url);
try
{
//まずは要約データからボディの取得を試みる
nb.NavigateAndWaitFromSource(hp.getHtmlPlainTextFromSourceWB(nReadabilityTranscoder.Transcode(source, out mainContentExtracted)));
title = nb.Document.Title;
result = nb.Document.Body.InnerText.Replace(title, "");
if (result != "") { return result; }
result = HtmlParser.htmlGomiRegularRemove(HtmlParser.htmlTagRegularRemove(source));
}
catch
{
}
}
//結果を返す
return result;
//return hp.getHtmlPlainTextFromSource(nReadabilityTranscoder.Transcode(getHtmlSource(url), out mainContentExtracted));
}
private CleanText getCleanText(string url, string content)
{
var transcoder = new NReadabilityTranscoder();
bool success;
try
{
//transcoder.Ti
TranscodingResult textRes = transcoder.Transcode(new TranscodingInput(content));
if (textRes.ContentExtracted)
{
var title = "";
if (textRes.TitleExtracted)
title = textRes.ExtractedTitle;
else
{
var titleNode = transcoder.FoundDocument.GetElementsByTagName("title").First();
if (titleNode != null)
title = titleNode.Value;
}
var imgUrl = "";
var imgNode = transcoder.FoundDocument.GetElementsByTagName("meta").Where(e => e.GetAttributeValue("property", "") == "og:image").First();//doc.SelectSingleNode("//meta[@property='og:image']");
if (imgNode != null)
imgUrl = imgNode.GetAttributeValue("content", "");
var mainText = "";
if (transcoder.FoundContentElement != null)
{
mainText = transcoder.FoundContentElement.GetInnerHtml();
}
return new CleanText { Title = title, Image = imgUrl, Content = mainText, Url = url, FetchDate = DateTime.Now };
}
else
{
return new CleanText { Title = "Content not found", Image = "", Content = "", Url = url, FetchDate = DateTime.Now };
}
}
catch (Exception ex)
{
return new CleanText { Title = "Content not found", Image = ex.Message, Content = "", Url = url, FetchDate = DateTime.Now };
}
}
public void TestImageSourceTransformer()
{
Func<AttributeTransformationInput, AttributeTransformationResult> imgSrcTransformer =
input =>
new AttributeTransformationResult
{
TransformedValue = string.Format("http://imageresizer.com/u={0}", input.AttributeValue),
OriginalValueAttributeName = "origsrc",
};
string originalSrcValue = "http://example.com/some_image.jpg";
string expectedSrcValue = imgSrcTransformer.Invoke(new AttributeTransformationInput { AttributeValue = originalSrcValue, Element = null }).TransformedValue;
string dummyParagraphs = "<p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p>";
string htmlContent = "<html><body>" + dummyParagraphs + "<p><img src=\"" + originalSrcValue + "\" /></p>" + dummyParagraphs + "</body></html>";
var nReadabilityTranscoder =
new NReadabilityTranscoder
{
ImageSourceTranformer = imgSrcTransformer,
};
bool mainContentExtracted;
string transcodedContent = nReadabilityTranscoder.Transcode(htmlContent, "http://immortal.pl/", out mainContentExtracted);
Assert.IsTrue(mainContentExtracted);
Assert.IsTrue(transcodedContent.Contains("src=\"" + expectedSrcValue + "\""));
Assert.IsTrue(transcodedContent.Contains("origsrc=\"" + originalSrcValue + "\""));
}
public void TestAnchorHrefTransformer()
{
Func<AttributeTransformationInput, AttributeTransformationResult> anchorHrefTransformer =
input =>
new AttributeTransformationResult
{
TransformedValue = string.Format("http://redirector.com/u={0}", input.AttributeValue),
OriginalValueAttributeName = "orighref",
};
string originalHrefValue = "http://example.com/some_article.html";
string expectedHrefValue = anchorHrefTransformer.Invoke(new AttributeTransformationInput { AttributeValue = originalHrefValue, Element = null }).TransformedValue;
string dummyParagraphs = "<p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p><p>Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet. Lorem ipsum dolor et amet.</p>";
string htmlContent = "<html><body>" + dummyParagraphs + "<p><a href=\"" + originalHrefValue + "\">Some article</a></p>" + dummyParagraphs + "</body></html>";
var nReadabilityTranscoder =
new NReadabilityTranscoder
{
AnchorHrefTranformer = anchorHrefTransformer,
};
bool mainContentExtracted;
string transcodedContent = nReadabilityTranscoder.Transcode(htmlContent, "http://immortal.pl/", out mainContentExtracted);
Assert.IsTrue(mainContentExtracted);
Assert.IsTrue(transcodedContent.Contains("href=\"" + expectedHrefValue + "\""));
Assert.IsTrue(transcodedContent.Contains("orighref=\"" + originalHrefValue + "\""));
}
public void SetUp()
{
_nReadabilityTranscoder = new NReadabilityTranscoder();
}
private static string embed(string url, out string title)
{
title = url;
Console.WriteLine("Embeding " + url);
if (url.Contains("youtube.com/"))
{
string vidid = "";
Regex s = new Regex(@"^.*((youtu.be\/)|(v\/)|(embed\/)|(watch\?))\??v?=?([^#\&\?]*).*");
Match ss = s.Match(url);
if (ss.Success)
{
vidid = ss.Groups[6].Value;
return " <iframe width=\"560\" height=\"349\" src=\"http://www.youtube.com/embed/" + vidid + "\" frameborder=\"0\" allowfullscreen></iframe> ";
}
}
string embedlyurl = "http://api.embed.ly/1/oembed?url=" + url;
string embedoutput = "";
try
{
embedoutput = c.DownloadString(embedlyurl);
}
catch (Exception e)
{
}
Regex html = new Regex(@"""html"": ""(.*?)\"",");
Regex urlre = new Regex(@"""url"": ""(.*?)\"",.*?""width"": (.*?),");
Regex type = new Regex(@"""type"": ""(.*?)""");
Regex titles = new Regex(@"""title"": ""(.*?)""");
Match embtype = type.Match(embedoutput);
if (embtype.Success)
{
Match embtitle = titles.Match(embedoutput);
if (embtitle.Success)
{
title = embtitle.Groups[1].Value;
}
if (embtype.Groups[1].Value == "photo")
{
Match emburl = urlre.Match(embedoutput);
if (emburl.Success)
{
string width = emburl.Groups[2].Value;
int iwidth = 0;
int.TryParse(width, out iwidth);
if (iwidth > 700)
{
return "<img src=\"" + emburl.Groups[1].Value + "\" width=\"700\"/>";
}
else
{
return "<img src=\"" + emburl.Groups[1].Value + "\"/>";
}
}
}
else
{
Match embhtml = html.Match(embedoutput);
if (embhtml.Success)
{
return embhtml.Groups[1].Value;
}
}
}
try
{
// string realhtml = c.DownloadString(url);
//NReadabilityTranscoder rd = new NReadabilityTranscoder();
NReadabilityWebTranscoder rdw = new NReadabilityWebTranscoder();
bool extracted = false;
// string transcoded = rd.Transcode(realhtml, out extracted);
string transcoded = rdw.Transcode(url, out extracted);
if (extracted)
{
Regex body = new Regex("<body>(.*?)</body>", RegexOptions.Singleline);
Match bodym = body.Match(transcoded);
if (bodym.Success)
{
transcoded = "<html><body>" + bodym.Groups[1].Value + "</body></html>";
}
Regex header = new Regex("(<h1>.*?</h1>)", RegexOptions.Singleline);
transcoded = header.Replace(transcoded, "");
string realhtml = c.DownloadString(url);
Regex regexs = new Regex("<title>(.*?)</title>",
RegexOptions.IgnoreCase);
Match match = regexs.Match(realhtml);
if (match.Success)
{
title = match.Groups[1].Value;
}
return transcoded;
}
}
catch (Exception e)
{
try
{
string realhtml = c.DownloadString(url);
Regex regexs = new Regex(".*<head>.*<title>(.*)</title>.*</head>.*",
RegexOptions.IgnoreCase);
Match match = regexs.Match(realhtml);
if (match.Success)
{
title = match.Groups[0].Value;
}
realhtml = SanitizeXmlString(realhtml);
bool extracted = false;
NReadabilityTranscoder rd = new NReadabilityTranscoder();
//NReadabilityWebTranscoder rdw = new NReadabilityWebTranscoder();
// string transcoded = rd.Transcode(realhtml, out extracted);
string transcoded = rd.Transcode(realhtml, url, out extracted);
if (extracted)
{
Regex body = new Regex("<body>(.*?)</body>", RegexOptions.Singleline);
Match bodym = body.Match(transcoded);
if (bodym.Success)
{
transcoded = "<html><body>" + bodym.Groups[1].Value + "</body></html>";
}
Regex header = new Regex("(<h1>.*?</h1>)", RegexOptions.Singleline);
transcoded = header.Replace(transcoded, "");
return transcoded;
}
}
catch (Exception ex)
{
try
{
string realhtml = SanitizeXmlString(c.DownloadString(url));
Regex regexs = new Regex(".*<head>.*<title>(.*)</title>.*</head>.*",
RegexOptions.IgnoreCase);
Match match = regexs.Match(realhtml);
if (match.Success)
{
title = match.Groups[0].Value;
}
bool extracted = false;
using (Document doc = Document.FromString(realhtml))
{
doc.ShowWarnings = false;
doc.Quiet = true;
doc.OutputXhtml = true;
doc.CleanAndRepair();
realhtml = doc.Save();
}
NReadabilityTranscoder rd = new NReadabilityTranscoder();
//NReadabilityWebTranscoder rdw = new NReadabilityWebTranscoder();
// string transcoded = rd.Transcode(realhtml, out extracted);
string transcoded = rd.Transcode(realhtml, url, out extracted);
if (extracted)
{
Regex body = new Regex("<body>(.*?)</body>", RegexOptions.Singleline);
Match bodym = body.Match(transcoded);
if (bodym.Success)
{
transcoded = "<html><body>" + bodym.Groups[1].Value + "</body></html>";
}
Regex header = new Regex("(<h1>.*?</h1>)", RegexOptions.Singleline);
transcoded = header.Replace(transcoded, "");
return transcoded;
}
}
catch (Exception exx)
{
}
}
}
return "";
}
/// <summary>
/// Initializes a new instance of NReadabilityWebTranscoder.
/// Allows passing in custom-constructed NReadabilityTranscoder.
/// </summary>
/// <param name="transcoder">A NReadailityTranscoder.</param>
public NReadabilityWebTranscoder(NReadabilityTranscoder transcoder)
: this(transcoder, new UrlFetcher())
{
}
/// <summary>
/// Initializes a new instance of NReadabilityWebTranscoder.
/// Allows passing in custom-constructed NReadabilityTranscoder,
/// and a custom IUrlFetcher.
/// </summary>
/// <param name="transcoder">A NReadabilityTranscoder.</param>
/// <param name="urlFetcher">IFetcher instance to download content.</param>
public NReadabilityWebTranscoder(NReadabilityTranscoder transcoder, IUrlFetcher urlFetcher)
: this(transcoder, urlFetcher, _DefaultPageSeparatorBuilder)
{
}
private async void OnUrlChangedImp(DependencyPropertyChangedEventArgs e)
{
var u = (string)e.NewValue;
if (string.IsNullOrEmpty(u))
return;
UiInvoke(() => ReasonPhrase = Properties.Resources.DownloadinPrompt);
var fp = await HttpDownloadToLocalFile.DownloadAsync(u, "html", ".htm","text/html", 1*1024* 1024);
if(string.IsNullOrEmpty(fp) || !File.Exists(fp))
{
UiInvoke(() => ReasonPhrase = Properties.Resources.DownloadFailedPrompt);
return;
}
var fdocn = fp + ".xaml";
if(!File.Exists(fdocn))
{
var charset = File.ReadAllText(fp + ".enc");
if(string.IsNullOrEmpty(charset))
{
charset = DetectEncoding(fp);
}//zh-cn 不能被getencoding识别
if("zh-cn".Equals(charset,StringComparison.InvariantCultureIgnoreCase))
{
charset = "gb2312";
}
var enc = string.IsNullOrEmpty(charset) ? Encoding.GetEncoding(936) : Encoding.GetEncoding(charset);
UiInvoke(()=>ReasonPhrase = Properties.Resources.FormattingPrompt);
var result = new NReadabilityTranscoder().Transcode(new TranscodingInput(File.ReadAllText(fp,enc))
{
Url = u,
BackupFilePath = fp,
});
if(result.ContentExtracted)
{
File.WriteAllText(fdocn,result.ExtractedContent);
UiInvoke(()=>ReasonPhrase = Properties.Resources.ReadyPrompt);
}else
{
UiInvoke(()=>ReasonPhrase = Properties.Resources.ConvertingFailedPrompt);
return;
}
}
UiInvoke(() =>
{
var fdoc = (FlowDocument)XamlReader.Load(File.OpenRead(fdocn));
if (fdoc == null)
{
ReasonPhrase = Properties.Resources.ConvertingFailedPrompt;
return;
}
_container.Children.Clear();
var fv = new FlowDocumentScrollViewer { Document = fdoc };
_container.Children.Add(fv);
});
}
