public static bool GetDownloadUrl(this BookInfo book, DependencyObject dispatcher = null)
{
if (book.ReadBookUrl == null || book.ReadBookUrl == "")
{
GetReadBookUrl(book);
}
string source = null;
if (book.IsReadAll)
{
source = HttpWebResponseUtility.GetHtmlByWebBrowser(book.ReadBookUrl, dispatcher);
}
else
{
source = HttpWebResponseUtility.GetHtmlByHttpWebRequest(book.ReadBookUrl);
}
string regexStr = "did = \"(.*?)\"[\\s\\S]*?PdgPath = \"(.*?)\"[\\s\\S]*?var str = \"(.*?)\"";
Match m = Regex.Match(source, regexStr);
if (!m.Success)
{
throw new Exception("获取STR时出现错误！");
}
book.did = m.Groups[1].Value;
book.PdgPath = m.Groups[2].Value;
String str = m.Groups[3].Value;
if (!book.IsReadAll)
{
book.DownloadUrlTemp = String.Format(unreadableDownloadUrl, str, "{0}");
string pid = null;
try
{
pid = BookDataBase.GetInstance().GetBookPID(book.DXID);
}
catch
{
return(false);
}
string regex = @"img\d*/(.*?)/";
m = Regex.Match(str, regex);
if (pid != null && m.Success)
{
book.DownloadUrl = book.DownloadUrlTemp.Replace(m.Groups[1].Value, pid);
}
else
{
return(false);
}
}
else
{
book.DownloadUrlTemp = String.Format(readableDownloadUrl, str, "{0}");
book.DownloadUrl = book.DownloadUrlTemp;
}
return(true);
}
public static BookContentNode GetBookContent(String did, String codepdgpath)
{
String host = DataExtraction.GetPdgHost(did);
String pdgpath = DecodePdgPath(codepdgpath);
String path = "http://" + host + "/" + pdgpath + "BookContents.dat";
Stream stream = HttpWebResponseUtility.CreateGetHttpResponse(path);
stream.Read(new byte[0x28], 0, 0x28);
StreamReader reader = new StreamReader(ZipUnCode(stream), Encoding.Default);
BookContentNode root = new BookContentNode()
{
Parent = null
};
root.Bookcontent = new BookContentInfo()
{
Title = "root",
Lever = "",
Page = 0,
Reserved = null,
Type = 0
};
BookContentNode curnode = root;
while (!reader.EndOfStream)
{
BookContentNode newnode = new BookContentNode();
String str = reader.ReadLine().Trim();
String[] strlist = str.Split('|');
newnode.Bookcontent = new BookContentInfo()
{
Title = strlist[0].Trim(),
Lever = strlist[1].Trim(),
Page = Int32.Parse(strlist[2].Trim()),
Reserved = strlist[3].Trim(),
Type = Int32.Parse(strlist[4].Trim())
};
int newIndentation = newnode.Bookcontent.Lever.Length;
int curIndentation = curnode.Bookcontent.Lever.Length;
if (newIndentation <= curIndentation)
{
curnode = curnode.Parent;
for (int i = newIndentation; i != curIndentation; i += 2)
{
curnode = curnode.Parent;
}
}
newnode.Parent = curnode;
curnode.Children.Add(newnode);
curnode = newnode;
}
return(root);
}
public static String GetPdgHost(String did)
{
String source = HttpWebResponseUtility.GetHtmlByHttpWebRequest(PdgPathSever);
string regexStr = String.Format("<td>{0}</td><td>(.*?)</td>", did);
Match m = Regex.Match(source, regexStr);
if (m.Success)
{
return(m.Groups[1].Value);
}
else
{
return(null);
}
}
private static BookInfo GetBriefBookInfo(this GroupCollection gc)
{
BookInfo book = new BookInfo();
book.DetailInfoUrl = gc[1].Value;
book.SmallCoverImage = HttpWebResponseUtility.GetImage(gc[2].Value);
book.DXID = gc[3].Value;
book.SSID = gc[4].Value;
book.Title = RemoveHTMLTab(gc[5].Value);
book.ReadBookUrlTemp = Setting.platformHost[Setting.platformIndex] + gc[6].Value;
book.IsReadAll = book.ReadBookUrlTemp.Contains("gobaoku");
book.BriefInfo = RemoveHTMLTab(gc[7].Value.Replace(" ", " ").Replace("<br>", "\n"));
book.PagesNum = GetPageNum(book.BriefInfo);
return(book);
}
public static void AddNewBook(this BookList booklist, String keyword, int page)
{
String url = String.Format(Setting.searchUrl, UrlEncode(keyword), page);
String regexStr = "url\" value=\"(.*?)\"[\\s\\S]*?封面 src='(.*?)'[\\s\\S]*?dxid\" value=\"(\\d*)[\\s\\S]*?ssid\" value=\"(\\d*)[\\s\\S]*?《(.*?)》</a>[\\s\\S]*?(/(?:gobaoku.jsp|readDetail.jsp).*?)\"[\\s\\S]*?(作者.*)";
String html = HttpWebResponseUtility.GetHtmlByHttpWebRequest(url);
MatchCollection m = Regex.Matches(html, regexStr);
m.AsParallel();
booklist.GetMoreable = html.Contains("下一页");
string[] s = new string[10];
Match[] ms = new Match[m.Count];
m.CopyTo(ms, 0);
Parallel.ForEach(ms, match =>
{
booklist.addBook(GetBriefBookInfo(match.Groups));
});
}
private bool DownloadPage(string url, string path)
{
System.Drawing.Image image = HttpWebResponseUtility.GetImage(url);
if (image == null)
{
return(false);
}
Bitmap bitmap = new Bitmap(image);
System.Drawing.Size size = bitmap.Size;
if (size.Height == 1 && size.Width == 1)
{
return(false);
}
removeMark(bitmap);
bitmap.Save(path);
return(true);
}
public static void GetReadBookUrl(this BookInfo book)
{
if (!book.IsReadAll)
{
book.ReadBookUrl = book.ReadBookUrlTemp;
return;
}
string source = HttpWebResponseUtility.GetHtmlByHttpWebRequest(book.ReadBookUrlTemp);
string regexStr = @"window\.location\.href='(.*?)'";
Match m = Regex.Match(source, regexStr);
if (m.Success)
{
book.ReadBookUrl = m.Groups[1].Value;
}
else
{
throw new Exception("获取在线读地址时出现错误！");
}
}
public static void GetDetailInfo(this BookInfo book)
{
if (book.isDetail)
{
return;
}
String coveReg = "(http://cover.*?)\"";
string source = HttpWebResponseUtility.GetHtmlByHttpWebRequest(book.DetailInfoUrl);
Match m = Regex.Match(source, coveReg);
if (m.Success)
{
book.BigCoverImage = HttpWebResponseUtility.GetImage(m.Groups[1].Value);
book.isDetail = true;
}
String regexStr = "<p>([\\s\\S]*?)</p>";
m = Regex.Match(source, regexStr);
while (m.Success)
{
book.DetailInfo += DataExtraction.RemoveHTMLTab(m.Groups[1].Value).Replace("\n", "").Replace("\r", "").Replace("\t", "").Replace(" ", "").Replace(">", "->") + "\n";
m = m.NextMatch();
}
}
