public string Convert(string html) { var cleaner = new Cleaner(); html = cleaner.PreTidy(html); HtmlDocument doc = new HtmlDocument(); doc.LoadHtml(html); var root = doc.DocumentNode; string result = this.Lookup(root.Name).Convert(root); return result; }
public string Convert(string html) { var cleaner = new Cleaner(); html = cleaner.PreTidy(html); HtmlDocument doc = new HtmlDocument(); doc.LoadHtml(html); var root = doc.DocumentNode; string result = this.Lookup(root.Name).Convert(root); return(result); }
public string Convert(string html) { html = Cleaner.PreTidy(html, Config.RemoveComments); var doc = new HtmlDocument(); doc.LoadHtml(html); var root = doc.DocumentNode; // ensure to start from body and ignore head etc if (root.Descendants("body").Any()) { root = root.SelectSingleNode("//body"); } var result = Lookup(root.Name).Convert(root); return(result); }
public string Convert(string html) { html = Cleaner.PreTidy(html, Config.RemoveComments); var doc = new HtmlDocument(); doc.LoadHtml(html); var root = doc.DocumentNode; // ensure to start from body and ignore head etc if (root.Descendants("body").Any()) { root = root.SelectSingleNode("//body"); } var result = Lookup(root.Name).Convert(root); // cleanup multiple new lines result = Regex.Replace(result, @"(^\p{Zs}*(\r\n|\n)){2,}", Environment.NewLine, RegexOptions.Multiline); return(result.Trim()); }
public string Convert(string html) { html = Cleaner.PreTidy(html, Config.RemoveComments); var doc = new HtmlDocument(); doc.LoadHtml(html); var root = doc.DocumentNode; var body = root.SelectSingleNode("//body"); if (body != null) { return(this.Lookup(body.Name).Convert(body)); } string result = this.Lookup(root.Name).Convert(root); if (Config.CompressNewlines) { int oldlen = result.Length; while (true) { result = result.Replace(_nlnlnl, _nlnl); int newlen = result.Length; if (newlen == oldlen) { break; } oldlen = newlen; } } return(result); }