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 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);
}
}
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));
});
}
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();
}
}
