//Parse IMDb page data
private void parseIMDbPage(string html, bool GetExtraInfo)
{
Id = match(@"<link rel=""canonical"" href=""http://www.imdb.com/title/(tt\d{7})/"" />", html);
if (!string.IsNullOrEmpty(Id))
{
DoEvents();
status = true;
Title = match(@"<title>(IMDb \- )*(.*?) \(.*?</title>", html, 2);
OriginalTitle = match(@"title-extra"">(.*?)<", html);
Year = match(@"<title>.*?\(.*?(\d{4}).*?\).*?</title>", html);
Rating = match(@"ratingValue"">(\d.\d)<", html);
Genres = new ArrayList();
Genres = matchAll(@"<a.*?>(.*?)</a>", match(@"Genres:</h4>(.*?)</div>", html));
Directors = new ArrayList();
Directors = matchAll(@"<a.*?>(.*?)</a>", match(@"Directors?:[\n\r\s]*</h4>(.*?)(</div>|>.?and )", html));
Writers = matchAll(@"<a.*?>(.*?)</a>", match(@"Writers?:[\n\r\s]*</h4>(.*?)(</div>|>.?and )", html));
Stars = matchAll(@"<a.*?>(.*?)</a>", match(@"Stars?:(.*?)</div>", html));
Cast = matchAll(@"class=""name"">[\n\r\s]*<a.*?>(.*?)</a>", html);
Plot = match(@"<p itemprop=""description"">(.*?)</p>", html);
ReleaseDate = match(@"Release Date:</h4>.*?(\d{1,2} (January|February|March|April|May|June|July|August|September|October|November|December) (19|20)\d{2}).*(\(|<span)", html);
Runtime = match(@"Runtime:</h4>[\s]*.*?(\d{1,4}) min[\s]*.*?\<\/div\>", html);
if (String.IsNullOrEmpty(Runtime))
{
Runtime = match(@"infobar.*?([0-9]+) min.*?</div>", html);
}
Top250 = match(@"Top 250 #(\d{1,3})<", html);
Oscars = match(@"Won (\d{1,2}) Oscars\.", html);
Awards = match(@"(\d{1,4}) wins", html);
Nominations = match(@"(\d{1,4}) nominations", html);
Storyline = match(@"Storyline</h2>[\s]*<p>(.*?)[\s]*(<em|</p>)", html);
Tagline = match(@"Taglines?:</h4>(.*?)(<span|</div)", html);
MpaaRating = match(@"infobar"">.*?<img.*?alt=""(.*?)"" src="".*?certificates.*?"".*?>", html);
Votes = match(@"ratingCount"">(\d+,?\d*)</span>", html);
Languages = new ArrayList();
Languages = matchAll(@"<a.*?>(.*?)</a>", match(@"Language.?:(.*?)(</div>|>.?and )", html));
Countries = new ArrayList();
Countries = matchAll(@"<a.*?>(.*?)</a>", match(@"Country:(.*?)(</div>|>.?and )", html));
Poster = match(@"img_primary"">[\n\r\s]*?<a.*?><img src=""(.*?)"".*?</td>", html);
if (!string.IsNullOrEmpty(Poster) && Poster.IndexOf("nopicture") < 0)
{
PosterSmall = Regex.Replace(Poster, @"_V1\..*?.jpg", "_V1._SY150.jpg");
PosterLarge = Regex.Replace(Poster, @"_V1\..*?.jpg", "_V1._SY500.jpg");
PosterFull = Regex.Replace(Poster, @"_V1\..*?.jpg", "_V1._SY0.jpg");
}
else
{
Poster = string.Empty;
PosterSmall = string.Empty;
PosterLarge = string.Empty;
PosterFull = string.Empty;
}
ImdbURL = "http://www.imdb.com/title/" + Id + "/";
if (GetExtraInfo)
{
ReleaseDates = getReleaseDates();
MediaImages = getMediaImages();
}
}
}
//Parse IMDb page data
private void parseIMDbPage(string imdbUrl, bool GetExtraInfo)
{
string html = getUrlData(imdbUrl + "combined");
Id = match(@"<link rel=""canonical"" href=""http://www.imdb.com/title/(tt\d{7})/combined"" />", html);
if (!string.IsNullOrEmpty(Id))
{
status = true;
//Title = match(@"<title>(IMDb \- )*(.*?) \(.*?</title>", html, 2);
Title = match(@"tn15title\""><h1>(.*?)<", html); //match(@"<title>(IMDb \- )*(.*?) \([^)]*?(\d{4}).*?\)?.*?</title>", html, 2);
OriginalTitle = match(@"title-extra"">(.*?)<", html);
if (IsSeries)
{
string episodeName = match(@"tn15title\""><h1>[^<]*?<span><em>(.*?)<", html);
string episodeExtra = match(@"tn15title\""><h1>[^<]*?<span><em>[^<]*?</em>(.*?)<", html);
SeriesSubtitle = episodeName + " " + episodeExtra + "\r\n" + "Season " + SeriesSeason + ", Episode " + SeriesEpisode;
}
else
{
try
{
var season = match(@"\(Season (\d*), Episode \d*\)", html);
var episode = match(@"\(Season \d*, Episode (\d*)\)", html);
string episodeName = match(@"tn15title\""><h1>[^<]*?<span><em>(.*?)<", html);
string episodeExtra = match(@"tn15title\""><h1>[^<]*?<span><em>[^<]*?</em>(.*?)<", html);
IsSeries = !string.IsNullOrEmpty(season);
if (IsSeries)
{
SeriesSeason = Convert.ToInt32(season);
SeriesEpisode = Convert.ToInt32(episode);
SeriesSubtitle = episodeName + " " + episodeExtra + "\r\n" + "Season " + SeriesSeason + ", Episode " + SeriesEpisode;
}
else
{
SeriesSeason = 0;
SeriesEpisode = 0;
SeriesSubtitle = "";
}
}
catch
{
IsSeries = false;
}
}
if (OriginalTitle == "")
{
var eng = match(@">\s*\""([^<]*)\"" -.*?International <em>\(English title\)", html, 1);
OriginalTitle = eng;
}
//Year = match(@"<title>.*?\(.*?(\d{4}).*?\).*?</title>", html);
Year = match(@"<title>(IMDb \- )*(.*?) \([^)]*?(\d{4}).*?\)?.*?</title>", html, 3);
Rating = match(@"<b>(\d.\d)/10</b>", html);
Genres = matchAll(@"<a.*?>(.*?)</a>", match(@"Genre.?:(.*?)(</div>|See more)", html));
Directors = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Directed by</a></h5>(.*?)</table>", html));
Writers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Writing credits</a></h5>(.*?)</table>", html));
Producers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Produced by</a></h5>(.*?)</table>", html));
Musicians = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Original Music by</a></h5>(.*?)</table>", html));
Cinematographers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Cinematography by</a></h5>(.*?)</table>", html));
Editors = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Film Editing by</a></h5>(.*?)</table>", html));
Cast = matchAll(@"<td class=""nm""><a.*?href=""/name/.*?/"".*?>(.*?)</a>", match(@"<h3>Cast</h3>(.*?)</table>", html));
Plot = match(@"Plot:</h5>.*?<div class=""info-content"">(.*?)(<a|</div)", html);
PlotKeywords = matchAll(@"<a.*?>(.*?)</a>", match(@"Plot Keywords:</h5>.*?<div class=""info-content"">(.*?)</div", html));
ReleaseDate = match(@"Release Date:</h5>.*?<div class=""info-content"">.*?(\d{1,2} (January|February|March|April|May|June|July|August|September|October|November|December) (19|20)\d{2})", html);
Runtime = match(@"Runtime:</h5><div class=""info-content"">(\d{1,4}) min[\s]*.*?</div>", html);
Top250 = match(@"Top 250: #(\d{1,3})<", html);
Oscars = match(@"Won (\d+) Oscars?\.", html);
if (string.IsNullOrEmpty(Oscars) && "Won Oscar.".Equals(match(@"(Won Oscar\.)", html)))
{
Oscars = "1";
}
Awards = match(@"(\d{1,4}) wins", html);
Nominations = match(@"(\d{1,4}) nominations", html);
Tagline = match(@"Tagline:</h5>.*?<div class=""info-content"">(.*?)(<a|</div)", html);
MpaaRating = match(@"MPAA</a>:</h5><div class=""info-content"">Rated (G|PG|PG-13|PG-14|R|NC-17|X) ", html);
Votes = match(@">(\d+,?\d*) votes<", html);
Languages = matchAll(@"<a.*?>(.*?)</a>", match(@"Language.?:(.*?)(</div>|>.?and )", html));
Countries = matchAll(@"<a.*?>(.*?)</a>", match(@"Country:(.*?)(</div>|>.?and )", html));
Poster = match(@"<div class=""photo"">.*?<a name=""poster"".*?><img.*?src=""(.*?)"".*?</div>", html);
if (!string.IsNullOrEmpty(Poster) && Poster.IndexOf("media-imdb.com") > 0)
{
Poster = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY200.jpg");
PosterLarge = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY500.jpg");
PosterFull = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY0.jpg");
}
else
{
Poster = string.Empty;
PosterLarge = string.Empty;
PosterFull = string.Empty;
}
ImdbURL = "http://www.imdb.com/title/" + Id + "/";
if (GetExtraInfo)
{
string plotHtml = getUrlData(imdbUrl + "plotsummary");
Storyline = match(@"<p class=""plotpar"">(.*?)(<i>|</p>)", plotHtml);
ReleaseDates = getReleaseDates();
MediaImages = getMediaImages();
RecommendedTitles = getRecommendedTitles();
}
}
}
//Get IMDb URL from search results
//static public ArrayList getIMDbUrl(string MovieName, string searchEngine = "google")
//{
// string url = GoogleSearch + MovieName; //default to Google search
// if (searchEngine.ToLower().Equals("bing")) url = BingSearch + MovieName;
// if (searchEngine.ToLower().Equals("ask")) url = AskSearch + MovieName;
// string html = getUrlData(url);
// ArrayList imdbUrls = matchAll(@"<a href=""(http://www.imdb.com/title/tt\d{7}/)"".*?>.*?</a>", html);
// if (imdbUrls.Count > 0)
// return imdbUrls; //return first IMDb result
// else if (searchEngine.ToLower().Equals("google")) //if Google search fails
// return getIMDbUrl(MovieName, "bing"); //search using Bing
// else if (searchEngine.ToLower().Equals("bing")) //if Bing search fails
// return getIMDbUrl(MovieName, "ask"); //search using Ask
// else //search fails
// return new ArrayList {string.Empty};
//}
//Parse IMDb page data
private void ParseImdbPage(string html, bool getExtraInfo)
{
Id = match(@"<link rel=""canonical"" href=""http://www.imdb.com/title/(tt\d{7})/combined"" />", html);
if (!string.IsNullOrEmpty(Id))
{
Status = true;
Title = match(@"<title>(IMDb \- )*(.*?) \(.*?</title>", html, 2);
OriginalTitle = match(@"title-extra"">(.*?)<", html);
Year = match(@"<title>.*?\(.*?(\d{4}).*?\).*?</title>", html);
Rating = match(@"<b>(\d.\d)/10</b>", html);
Genres = matchAll(@"<a.*?>(.*?)</a>", match(@"Genre.?:(.*?)(</div>|See more)", html));
Directors = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Directed by</a></h5>(.*?)</table>", html));
Writers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Writing credits</a></h5>(.*?)</table>", html));
Producers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Produced by</a></h5>(.*?)</table>", html));
Musicians = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Original Music by</a></h5>(.*?)</table>", html));
Cinematographers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Cinematography by</a></h5>(.*?)</table>", html));
Editors = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Film Editing by</a></h5>(.*?)</table>", html));
Cast = matchAll(@"<td class=""nm""><a.*?href=""/name/.*?/"".*?>(.*?)</a>", match(@"<h3>Cast</h3>(.*?)</table>", html));
Plot = match(@"Plot:</h5>.*?<div class=""info-content"">(.*?)(<a|</div)", html);
PlotKeywords = matchAll(@"<a.*?>(.*?)</a>", match(@"Plot Keywords:</h5>.*?<div class=""info-content"">(.*?)</div", html));
ReleaseDate = match(@"Release Date:</h5>.*?<div class=""info-content"">.*?(\d{1,2} (January|February|March|April|May|June|July|August|September|October|November|December) (19|20)\d{2})", html);
Runtime = match(@"Runtime:</h5><div class=""info-content"">(\d{1,4}) min[\s]*.*?</div>", html);
Top250 = match(@"Top 250: #(\d{1,3})<", html);
Oscars = match(@"Won (\d+) Oscars?\.", html);
if (string.IsNullOrEmpty(Oscars) && "Won Oscar.".Equals(match(@"(Won Oscar\.)", html)))
{
Oscars = "1";
}
Awards = match(@"(\d{1,4}) wins", html);
Nominations = match(@"(\d{1,4}) nominations", html);
Tagline = match(@"Tagline:</h5>.*?<div class=""info-content"">(.*?)(<a|</div)", html);
MpaaRating = match(@"MPAA</a>:</h5><div class=""info-content"">Rated (G|PG|PG-13|PG-14|R|NC-17|X) ", html);
Votes = match(@">(\d+,?\d*) votes<", html);
Languages = matchAll(@"<a.*?>(.*?)</a>", match(@"Language.?:(.*?)(</div>|>.?and )", html));
Countries = matchAll(@"<a.*?>(.*?)</a>", match(@"Country:(.*?)(</div>|>.?and )", html));
Poster = match(@"<div class=""photo"">.*?<a name=""poster"".*?><img.*?src=""(.*?)"".*?</div>", html);
if (!string.IsNullOrEmpty(Poster) && Poster.IndexOf("media-imdb.com") > 0)
{
Poster = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY200.jpg");
PosterLarge = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY500.jpg");
PosterFull = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY0.jpg");
}
else
{
Poster = string.Empty;
PosterLarge = string.Empty;
PosterFull = string.Empty;
}
ImdbUrl = "http://www.imdb.com/title/" + Id + "/";
//Get Stars
var html2 = GetUrlData(ImdbUrl);
Stars = matchAll(@"<a.*?><span class=""itemprop"" itemprop=""name"">(.*?)</span></a>", match(@"Stars?:(.*?)</div>", html2));
if (getExtraInfo)
{
string plotHtml = GetUrlData(ImdbUrl + "plotsummary");
Storyline = StripHtml(match(@"<p class=""plotSummary"">(.*?)(<i>|</p>)", plotHtml));
//ReleaseDates = GetReleaseDates();
MediaImages = GetMediaImages();
//RecommendedTitles = GetRecommendedTitles();
}
}
}
//Parse IMDb page data
private bool parseIMDbPage(string imdbUrl, bool GetExtraInfo)
{
int istart, iend;
string substr1;
string html = getUrlData(imdbUrl + "combined");
if (!string.IsNullOrEmpty(html))
{
status = true;
Id = match(@"<link rel=""canonical"" href=""http://www.imdb.com/title/(tt\d{7})/combined"" />", html);
Title = match(@"<title>(IMDb \- )*(.*?) \(.*?</title>", html, 2);
Title = System.Web.HttpUtility.HtmlDecode(Title);
Title = System.Web.HttpUtility.HtmlDecode(Title);
OriginalTitle = System.Web.HttpUtility.HtmlDecode(match(@"title-extra"">(.*?)<", html));
OriginalTitle = System.Web.HttpUtility.HtmlDecode(OriginalTitle);
istart = html.IndexOf("<title>");
iend = html.IndexOf("</title>") + 8;
substr1 = html.Substring(istart, iend - istart);
Year = match(@"<title>.*?\(.*?(\d{4}).*?\).*?</title>", substr1);
Rating = match(@"<b>(\d.\d)/10</b>", html);
Genres = matchAll(@"<a.*?>(.*?)</a>", match(@"Genre.?:(.*?)(</div>|See more)", html));
Directors = new ArrayList();
Directors = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Directed by</a></h5>(.*?)</table>", html));
Writers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Writing credits</a></h5>(.*?)</table>", html));
Producers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Produced by</a></h5>(.*?)</table>", html));
Musicians = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Original Music by</a></h5>(.*?)</table>", html));
Cinematographers = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Cinematography by</a></h5>(.*?)</table>", html));
Editors = matchAll(@"<td valign=""top""><a.*?href=""/name/.*?/"">(.*?)</a>", match(@"Film Editing by</a></h5>(.*?)</table>", html));
Cast = matchAll(@"<td class=""nm""><a.*?href=""/name/.*?/"".*?>(.*?)</a>", match(@"<h3>Cast</h3>(.*?)</table>", html));
Plot = System.Web.HttpUtility.HtmlDecode(match(@"Plot:</h5>.*?<div class=""info-content"">(.*?)(<a|</div)", html));
Plot = System.Web.HttpUtility.HtmlDecode(Plot);
Plot = Plot.Replace("|", "");
Plot = Plot.Trim();
PlotKeywords = matchAll(@"<a.*?>(.*?)</a>", match(@"Plot Keywords:</h5>.*?<div class=""info-content"">(.*?)</div", html));
ReleaseDate = match(@"Release Date:</h5>.*?<div class=""info-content"">.*?(\d{1,2} (January|February|March|April|May|June|July|August|September|October|November|December) (19|20)\d{2})", html);
Runtime = match(@"Runtime:</h5><div class=""info-content"">(\d{1,4}) min[\s]*.*?</div>", html);
Top250 = match(@"Top 250: #(\d{1,3})<", html);
Oscars = match(@"Won (\d+) Oscars?\.", html);
if (string.IsNullOrEmpty(Oscars) && "Won Oscar.".Equals(match(@"(Won Oscar\.)", html)))
{
Oscars = "1";
}
Awards = match(@"(\d{1,4}) wins", html);
Nominations = match(@"(\d{1,4}) nominations", html);
Tagline = System.Web.HttpUtility.HtmlDecode(match(@"Tagline:</h5>.*?<div class=""info-content"">(.*?)(<a|</div)", html));
Tagline = System.Web.HttpUtility.HtmlDecode(Tagline);
MpaaRating = match(@"MPAA</a>:</h5><div class=""info-content"">Rated (G|PG|PG-13|PG-14|R|NC-17|X) ", html);
if (MpaaRating.Length == 0)
{
// If MPAA rating is not set check the Certification
MpaaRating = match(@"Certification:</h5><div class=""info-content""><a href=""/search/title\?certificates=us:g"">USA:(G|PG|PG-13|PG-14|R|NC-17|X)", html);
}
Votes = match(@">(\d+,?\d*) votes<", html);
Languages = matchAll(@"<a.*?>(.*?)</a>", match(@"Language.?:(.*?)(</div>|>.?and )", html));
Countries = matchAll(@"<a.*?>(.*?)</a>", match(@"Country:(.*?)(</div>|>.?and )", html));
Poster = match(@"<div class=""photo"">.*?<a name=""poster"".*?><img.*?src=""(.*?)"".*?</div>", html);
if (!string.IsNullOrEmpty(Poster) && Poster.IndexOf("media-imdb.com") > 0)
{
Poster = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY200.jpg");
PosterLarge = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY500.jpg");
PosterFull = Regex.Replace(Poster, @"_V1.*?.jpg", "_V1._SY0.jpg");
}
else
{
Poster = string.Empty;
PosterLarge = string.Empty;
PosterFull = string.Empty;
}
ImdbURL = "http://www.imdb.com/title/" + Id + "/";
if (GetExtraInfo)
{
string plotHtml = getUrlData(imdbUrl + "plotsummary");
Storyline = match(@"<p class=""plotpar"">(.*?)(<i>|</p>)", plotHtml);
ReleaseDates = getReleaseDates();
MediaImages = getMediaImages();
RecommendedTitles = getRecommendedTitles();
}
return(true);
}
else
{
Id = null;
return(false);
}
}
