public void Download_ReleaseBB_MovieIndex(int StartPage = 1, int LastPage = 1366)
{
_Parse.XML xml = new _Parse.XML();
_Lists lst = new _Lists();
_Sites.Imdb imdb = new Imdb();
string startURL = "http://rlsbb.ru/category/movies/page/";
int LastPageNum = LastPage;
int pageNum = StartPage;
do
{
string URL = startURL + pageNum + "/";
string HTML = ahk.Download_HTML(URL);
string xmlPath = "//*[@id=\"contentArea\"]";
List <string> segs = xml.Parse_HTML_XML(HTML, xmlPath); // extract sections of text from html xml
int segNum = 1;
foreach (string seg in segs)
{
ReleaseBBMovies obj = new ReleaseBBMovies();
// skip segs on page that aren't posts
if (segNum == 1)
{
segNum++; continue;
}
if (segNum == 2)
{
segNum++; continue;
}
if (segNum == 13)
{
segNum++; continue;
}
if (segNum == 14)
{
segNum++; continue;
}
//ahk.MsgBox(segNum + " | " + seg);
segNum++;
string PostTitle = "";
string PostURL = "";
string IMDbID = "";
List <string> links = imdb.Regex_IMDbLinks(seg);
if (links.Count > 0)
{
IMDbID = imdb.IMDb_ID_FromURL(links[0]);
}
// parse index page segment
List <string> lines = lst.Text_To_List(seg, true, true, false);
foreach (string line in lines)
{
if (line.Contains("postTitle"))
{
PostURL = line.Replace("<h2 class=\"postTitle\"><span></span><a href=\"", "");
PostTitle = ahk.StringSplit(PostURL, ">", 1);
PostTitle = ahk.StringSplit(PostTitle, "<", 0);
PostURL = ahk.StringSplit(PostURL, "\"", 0);
//ahk.MsgBox("IMDB: " + IMDbID + "\n\n" + PostTitle + "\n\n" + PostURL);
}
}
obj.IMDbID = IMDbID;
obj.PostTitle = PostTitle;
obj.PostURL = PostURL;
bool Updated = ReleaseBBMovies_UpdateInsert_IndexEntry(obj);
}
pageNum++;
}while (pageNum <= LastPageNum);
}
