Code: Select all
// SCRIPTING
// IMDB (US) automated batch importing (use Editor to change options)
//
// Note(!): This script will take first found Movie title, which in some cases
// will mean it will take the wrong movie title. However, this script will
// save you a ton of time when importing info for a large list. Just correct
// the falsely imported infos manually later. Be sure to make a backup of your
// list beforehand.
(****************************************************
* Movie importation script for: *
* IMDB (US), http://us.imdb.com *
* *
* (c) 2002 Antoine Potten antoine@buypin.com *
* Improvements made by Danny Falkov *
* Improvements made by Kai Blankenhorn *
* Batch-import improvements made by YH *
* *
* For use with Ant Movie Catalog 3.3.0 *
* www.ant.be.tf/moviecatalog ··· www.buypin.com *
****************************************************)
program IMDb;
const
// Set the following constants to True to import field, or False to skip field
ImportURL = True;
ImportOriginalTitle = True;
ImportTranslatedTitle = True;
LeaveOriginalTitle = True; // True will get Translated Title, yet Original Title field will remain same
ImportYear = True;
ImportRating = True;
ImportPicture = True;
ImportLargePicture = False; // If set to False small pic will be imported
ImportDirector = True;
ImportActors = True;
ImportCountry = True;
ImportCategory = True;
ImportDescription = True;
UseLongestDescription = False; // If set to False shortest description available will be imported
ImportComments = True;
ImportLength = True;
ImportLanguage = True;
var
MovieName: string;
function FindLine(Pattern: string; List: TStringList; StartAt: Integer): Integer;
var
i: Integer;
begin
result := -1;
if StartAt < 0 then
StartAt := 0;
for i := StartAt to List.Count-1 do
if Pos(Pattern, List.GetString(i)) <> 0 then
begin
result := i;
Break;
end;
end;
procedure AnalyzePage(Address: string);
var
Page: TStringList;
LineNr: Integer;
TitleFound: Boolean;
MovieURL: String;
begin
Page := TStringList.Create;
Page.Text := GetPage(Address);
if pos('<TITLE>IMDb', Page.Text) = 0 then
begin
if ImportURL then
SetField(fieldURL, Address);
AnalyzeMoviePage(Page)
end else
begin
TitleFound := False;
LineNr := 0;
LineNr := FindLine('<H2><A NAME="top">Most popular searches</A></H2>', Page, LineNr);
if LineNr > -1 then
begin
MovieURL := AddMoviesTitles(Page, LineNr);
TitleFound := True;
end;
LineNr := FindLine('<H2><A NAME="mov">Movies</A></H2>', Page, LineNr);
if (LineNr > -1) And Not (TitleFound) then
begin
MovieURL := AddMoviesTitles(Page, LineNr);
TitleFound := True;
end;
LineNr := FindLine('<H2><A NAME="tvm">TV-Movies</A></H2>', Page, LineNr);
if (LineNr > -1) And Not (TitleFound) then
begin
MovieURL := AddMoviesTitles(Page, LineNr);
TitleFound := True;
end;
LineNr := FindLine('<H2><A NAME="tvs">TV series</A></H2>', Page, LineNr);
if (LineNr > -1) And Not (TitleFound) then
begin
MovieURL := AddMoviesTitles(Page, LineNr);
TitleFound := True;
end;
LineNr := FindLine('<H2><A NAME="vid">Made for video</A></H2>', Page, LineNr);
if (LineNr > -1) And Not (TitleFound) then
begin
MovieURL := AddMoviesTitles(Page, LineNr);
TitleFound := True;
end;
if TitleFound then
AnalyzePage(MovieURL);
end;
Page.Free;
end;
procedure AnalyzeMoviePage(Page: TStringList);
var
Line, Value, Value2, FullValue, OldOriginalTitle: string;
LineNr, Desc, i: Integer;
BeginPos, EndPos: Integer;
Descriptions, OldTitleParts: TStringList;
begin
// Original Title & Year
if (ImportOriginalTitle) or (ImportYear) then
begin
LineNr := FindLine('<title>', Page, 0);
Line := Page.GetString(LineNr);
if LineNr > -1 then
begin
BeginPos := pos('<title>', Line);
if BeginPos > 0 then
BeginPos := BeginPos + 7;
EndPos := pos('(', Line);
if EndPos = 0 then
EndPos := Length(Line);
Value := copy(Line, BeginPos, EndPos - BeginPos - 1);
HTMLDecode(Value);
if ImportOriginalTitle then
OldOriginalTitle := GetField(fieldOriginalTitle);
if (ImportTranslatedTitle) and Not (LeaveOriginalTitle) then
SetField(fieldOriginalTitle, Value);
BeginPos := pos('(', Line) + 1;
if BeginPos > 0 then
begin
EndPos := pos(')', Line);
Value := copy(Line, BeginPos, EndPos - BeginPos);
if ImportYear then
SetField(fieldYear, Value);
end;
end;
end;
// Translated Title
if ImportTranslatedTitle then
begin
OldTitleParts := TStringList.Create;
// Tokenize OldOriginalTitle while removing certain chars/common words ("the", "of")
Value := AnsiUpperCase(OldOriginalTitle);
Value := StringReplace(StringReplace(Value, ',', ' '), ':', ' ');
Value := StringReplace(StringReplace(Value, '(', ' '), ')', ' ');
Value := StringReplace(StringReplace(Value, 'OF', ' '), 'THE', ' ');
repeat
Value := StringReplace(Value, ' ', ' ');
until Pos(' ', Value) = 0;
Value := StringReplace(Trim(Value), ' ', ',');
// Value now contains the original title (comma-separated) that was filled in before running the script
Value2 := '';
for i := 1 to Length(Value) do
begin
if Pos(',', Copy(Value, i, 1)) = 0 then
Value2 := Value2 + Copy(Value, i, 1);
if (Pos(',', Copy(Value, i, 1)) = 1) or (i = Length(Value)) then
begin
OldTitleParts.Add(Value2); // put each comma-separated value from Value into a separate string in TitleParts
Value2 := '';
end;
end;
for i := 0 to OldTitleParts.Count - 1 do
// Begin comparing title parts (from the title originally filled in by moviedb owner) with
// the 'true' Original Title (extracted from IMDb) to see if it's a foreign title and needs a Translated Title
begin
if Pos(OldTitleParts.GetString(i), AnsiUpperCase(GetField(fieldOriginalTitle))) <= 0 then
begin // no match, must be a foreign title
LineNr := FindLine('Also Known As', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr);
if Pos('Also Known As', Line) > 0 then
begin
BeginPos := Pos('Also Known As', Line) + 26;
Value := Copy(Line, BeginPos, Length(Line) - BeginPos - 4);
Value := StringReplace(Value, '<br>', '/ ');
SetField(fieldTranslatedTitle, Value);
end;
end;
Break;
end;
end;
OldTitleParts.Free;
end;
// Rating
if ImportRating then
begin
LineNr := FindLine('User Rating:', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr + 4);
if Pos('awaiting', Line) > 0 then
begin
BeginPos := pos('<b>', Line) + 3;
Value := IntToStr(Round(StrToInt(StrGet(Line, BeginPos), 0) + (StrToInt(StrGet(Line, BeginPos + 2), 0) / 10)));
SetField(fieldRating, Value);
end;
end;
end;
// Direct Link (FIX: when IMDb finds only one entry for the movie title, the script assumes the search URL as Movie URL)
// Before Fix: http://us.imdb.com/Tsearch?title=Final Fantasy%3A+The+Spirits+Within
// After Fix: http://us.imdb.com/Title?0173840
if ImportURL then
begin
if Pos('Tsearch', GetField(fieldURL)) > 0 then
begin
LineNr := FindLine('User Rating:', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr + 2);
if Pos('/Ratings?', Line) > 0 then
begin
BeginPos := pos('/Ratings?', Line) + 9;
Value := 'http://us.imdb.com/Title?' + Copy(Line, BeginPos, 7);
SetField(fieldURL, Value);
end;
end;
end;
end;
// Picture
if ImportPicture then
begin
LineNr := FindLine('<img alt="cover" align="left" src="http://posters.imdb.com/', Page, 0);
if LineNr < 0 then
LineNr := FindLine('<img alt="cover" align="left" src="http://images.amazon.com/', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr);
BeginPos := pos('src="', Line) + 4;
Delete(Line, 1, BeginPos);
EndPos := pos('"', Line);
Value := copy(Line, 1, EndPos - 1);
if ImportLargePicture then
Value := StringReplace(Value, 'MZZZZZZZ', 'LZZZZZZZ');
GetPicture(Value, False); // False = do not store picture externally ; store it in the catalog file
end;
end;
// Director
if ImportDirector then
begin
LineNr := FindLine('Directed by', Page, 0);
if LineNr > -1 then
begin
FullValue := '';
Line := Page.GetString(LineNr + 1);
repeat
BeginPos := pos('">', Line) + 2;
EndPos := pos('</a>', Line);
Value := copy(Line, BeginPos, EndPos - BeginPos);
if (Value <> '(more)') and (Value <> '') then
begin
if FullValue <> '' then
FullValue := FullValue + ', ';
FullValue := FullValue + Value;
end;
Delete(Line, 1, EndPos);
until Pos('</a>', Line) = 0;
HTMLDecode(FullValue);
SetField(fieldDirector, FullValue);
end;
end;
// Actors
if ImportActors then
begin
LineNr := FindLine('Cast overview', Page, 0);
if LineNr = -1 then
LineNr := FindLine('cast overview', Page, 0);
if LineNr = -1 then
LineNr := FindLine('Complete credited cast', Page, 0);
if LineNr > -1 then
begin
FullValue := '';
Line := Page.GetString(LineNr);
repeat
BeginPos := Pos('<td valign="top">', Line);
if BeginPos > 0 then
begin
Delete(Line, 1, BeginPos);
Line := copy(Line, 25, Length(Line));
BeginPos := pos('">', Line) + 2;
EndPos := pos('</a>', Line);
if EndPos = 0 then
EndPos := Pos('</td>', Line);
Value := copy(Line, BeginPos, EndPos - BeginPos);
if (Value <> '(more)') and (Value <> '') then
begin
BeginPos := pos('.... </td><td valign="top">', Line);
if BeginPos > 0 then
begin
EndPos := pos('</td></tr>', Line);
BeginPos := BeginPos + 27;
Value2 := copy(Line, BeginPos, EndPos - BeginPos);
if Value2 <> '' then
begin
Value := Value + ' (as ' + Value2 + ')';
end;
end;
if FullValue <> '' then
FullValue := FullValue + ', ';
FullValue := FullValue + Value;
end;
EndPos := Pos('</td></tr>', Line);
Delete(Line, 1, EndPos);
end else
begin
Line := '';
end;
until Line = '';
HTMLDecode(FullValue);
SetField(fieldActors, FullValue);
end;
end;
// Country
if ImportCountry then
begin
LineNr := FindLine('Country:', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr + 1);
BeginPos := pos('/">', Line) + 3;
EndPos := pos('</a>', Line);
Value := copy(Line, BeginPos, EndPos - BeginPos);
HTMLDecode(Value);
SetField(fieldCountry, Value);
end;
end;
// Category
if ImportCategory then
begin
LineNr := FindLine('Genre:', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr + 1);
BeginPos := pos('/">', Line) + 3;
EndPos := pos('</a>', Line);
Value := copy(Line, BeginPos, EndPos - BeginPos);
HTMLDecode(Value);
SetField(fieldCategory, Value);
end;
end;
// Description
if ImportDescription then
begin
Descriptions := TStringList.Create;
LineNr := FindLine('Plot Summary:', Page, 0);
if LineNr < 1 then
LineNr := FindLine('Plot Outline:', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr);
BeginPos := pos('</b>', Line) + 5;
EndPos := pos('<a href', Line);
if EndPos < 1 then
Line := Line + Page.GetString(LineNr+1);
EndPos := pos('<a href="/Plot?', Line);
if EndPos < 1 then
EndPos := pos('<br><br>', Line);
if EndPos < 1 then
EndPos := Length(Line);
Value := copy(Line, BeginPos, EndPos - BeginPos);
HTMLDecode(Value);
Descriptions.Add(Value);
BeginPos := pos('/Plot?', Line);
EndPos := pos('">(more)', Line);
Desc := 0;
if (BeginPos <> 0) and (EndPos <> 0) then
begin
Value := copy(Line, BeginPos, EndPos - BeginPos);
GetDescriptions(Value, Descriptions);
For i := 0 to Descriptions.Count - 1 do
begin
if UseLongestDescription then
if Length(Descriptions.GetString(i)) > Length(Descriptions.GetString(Desc)) then
Desc := i
else
if Length(Descriptions.GetString(i)) < Length(Descriptions.GetString(Desc)) then
Desc := i;
end;
end;
Value := '';
SetField(fieldDescription, Descriptions.GetString(Desc));
end;
Descriptions.Free;
end;
// Comments
if ImportComments then
begin
LineNr := FindLine('<b>Summary:</b>', Page, 0);
if LineNr > -1 then
begin
Value := '';
repeat
LineNr := LineNr + 1;
Line := Page.GetString(LineNr);
EndPos := Pos('</blockquote>', Line);
if EndPos = 0 then
EndPos := Length(Line)
else
EndPos := EndPos - 2;
Value := Value + Copy(Line, 1, EndPos) + ' ';
until Pos('</blockquote>', Line) > 0;
HTMLDecode(Value);
Value := StringReplace(Value, '<br>', #13#10);
Value := StringReplace(Value, #13#10+' ', #13#10);
SetField(fieldComments, Value);
end;
end;
// Length
if ImportLength then
begin
LineNr := FindLine('Runtime:', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr + 1);
EndPos := pos(' min', Line);
if EndPos = 0 then
EndPos := pos(' /', Line);
if EndPos = 0 then
EndPos := Length(Line);
if Pos(':', Line) < EndPos then
BeginPos := Pos(':', Line) + 1
else
BeginPos := 1;
Value := copy(Line, BeginPos, EndPos - BeginPos);
SetField(fieldLength, Value);
end;
end;
// Language
if ImportLanguage then
begin
LineNr := FindLine('Language:', Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr + 1);
BeginPos := pos('/">', Line) + 3;
EndPos := pos('</a>', Line);
if EndPos = 0 then
EndPos := Length(Line);
Value := copy(Line, BeginPos, EndPos - BeginPos);
SetField(fieldLanguages, Value);
end;
end;
DisplayResults;
end;
procedure GetDescriptions(Address: string; var Descriptions: TStringlist);
var
Line, Value: string;
LineNr: Integer;
BeginPos, EndPos: Integer;
Page: TStringList;
begin
Page := TStringList.Create;
Page.Text := GetPage('http://us.imdb.com' + Address);
LineNr := FindLine('<P CLASS="plotpar">', Page, 0);
while LineNr > -1 do
begin
Value := '';
repeat
Line := Page.GetString(LineNr);
BeginPos := pos('"plotpar">', Line);
if BeginPos > 0 then
BeginPos := BeginPos + 10
else
BeginPos := 1;
EndPos := pos('</P>', Line);
if EndPos < 1 then
EndPos := Length(Line) + 1;
if Value <> '' then
Value := Value + ' ';
Value := Value + copy(Line, BeginPos, EndPos - BeginPos);
LineNr := LineNr + 1;
until (pos('</P>', Line) > 0) or (LineNr = Page.Count);
Descriptions.Add(Value);
LineNr := FindLine('<P CLASS="plotpar">', Page, LineNr);
end;
Page.Free;
end;
function AddMoviesTitles(Page: TStringList; var LineNr: Integer): String;
var
Line: string;
MovieTitle, MovieAddress: string;
StartPos: Integer;
begin
repeat
LineNr := LineNr + 1;
Line := Page.GetString(LineNr);
StartPos := pos('="', Line);
if StartPos > 0 then
begin
Startpos := Startpos + 2;
MovieAddress := copy(Line, StartPos, pos('">', Line) - StartPos);
StartPos := pos('">', Line) + 2;
MovieTitle := copy(Line, StartPos, pos('</A>', Line) - StartPos);
HTMLDecode(Movietitle);
if Length(Result) <= 0 then
Result := 'http://us.imdb.com' + MovieAddress;
end;
until pos('</OL>', Line) > 0;
end;
begin
if CheckVersion(3,2,1) then
begin
MovieName := GetField(fieldOriginalTitle);
if MovieName = '' then
MovieName := GetField(fieldTranslatedTitle);
if MovieName = '' then
MovieName := Input('IMDb Import', 'Enter the title of the movie:', MovieName);
if MovieName <> '' then
begin
// AnalyzePage('http://us.imdb.com/Tsearch?title='+UrlEncode(MovieName)+'&restrict=Movies+only');
AnalyzePage('http://us.imdb.com/Tsearch?title='+UrlEncode(MovieName));
end;
end else
ShowMessage('This script requires a newer version of Ant Movie Catalog (at least the version 3.2.1)');
end.
thanks everyone for these wonderful scriptZ 
