public override void HtmlCapture(string webHtml)
{
var text = ToTraditional(webHtml);
text = Regex.Replace(text, "(<!D).+?(<div id=\"contentmain)", "<"); //文庫去頭
text = Regex.Replace(text, "(</ul></div>).+?(html>)", "</ul>"); //文庫去尾
text = Regex.Replace(text, " ", "-空白-");
text = Regex.Replace(text, "<ul id=\"contentdp\">", "-換行-");
text = Regex.Replace(text, "<br />", "-換行-");
text = Regex.Replace(text, "(<ul).+?(</ul>)", string.Empty); //細切
text = Regex.Replace(text, "<.+?>", " "); //去除其餘tag
text = Regex.Replace(text, "-空白-", " ");
text = Regex.Replace(text, "-換行-", "<br />");
NovelText.Add(text);
}
public override void HtmlCapture(string webHtml)
{
string str = webHtml;
string line = "";
str = Regex.Replace(str, "(<!D).+?(<!-- END -->)", string.Empty); //卡提諾第一頁 切頭
str = Regex.Replace(str, "(<td class=\"t_f).+?(\">)", "--頭--頭--"); //卡提諾每章節開頭tag
str = Regex.Replace(str, "</td></tr>", "~尾~~--"); //卡提諾每章節結尾tag
str = "~--" + str + "--頭-"; //添加頭尾tag
str = Regex.Replace(str, "(~--).+?(--頭-)", "\n\n"); //切除尾~頭之間的所有內容
//str = Regex.Replace(str, " ", " ");
MatchCollection matches = Regex.Matches(str, "(?<=-頭--).+?(?=~尾~)", RegexOptions.IgnoreCase | RegexOptions.Multiline);
foreach (Match match in matches)
{
line = Regex.Replace(match.Value, "<br />", "-換行-");
line = Regex.Replace(line, "<.+?>", " ");
line = Regex.Replace(line, "-換行-", "<br />");
NovelText.Add(line);
}
}
/*
* 小説のダウンロードを行う。
*
*
* */
public void DownloadNovel()
{
var urls = getNovelUrl();
var text = new List <string>();
var title = new List <string>();
foreach (string url in urls)
{
string html = getHtml(url);
text.Add(analysisHtml(html));
if (Juge)
{
title.Add(analysisHtmTitlel(html));
}
}
NovelText.Add(Ncode, text);
if (Juge)
{
Title.Add(Ncode, title);
}
return;
}
