Well, i've been working in a script that obtains the most data from culturalia and the one that culturalia doesn't give, from IMDB. Otherwise, it's simple to configure script to obtain more data from IMDB, if somebody needs it.
It's a first release, it works with the movies that i tried, but sure it has some bugs and needs fixes. Try it and reply with them.
LATEST VERSION OF SCRIPT :
Code: Select all
// GETINFO SCRIPTING
// Culturalia+IMDB
(***************************************************
* Script merged by Jose Miguel Folgueira, based *
* on a similar script merged by Antoine Potten *
* *
* Movie importation script for: *
* Culturalia, http://www.culturalianet.com *
* *
* Original version made by David Arenillas *
* New version made by Antoine Potten *
* Contributors: *
* Jose Miguel Folgueira *
* RedDwarf *
* Hades666 *
* KaBeCi *
* Pollopolea *
* *
* Thanks to Culturalia's webmaster for his help *
* and for providing more direct access to his *
* database *
* *
* Movie importation script for: *
* IMDB (US), http://us.imdb.com *
* *
* TransformTitle function from IMDB (US) Script *
* (c) 2002-2004 Antoine Potten *
* software@antp.be *
* *
* (c) 2002 Antoine Potten antoine@buypin.com *
* Contributors : *
* Danny Falkov *
* Kai Blankenhorn *
* lboregard *
* Ork <ork@everydayangels.net> *
* Trekkie <Asimov@hotmail.com> *
* Youri Heijnen *
* *
* For use with Ant Movie Catalog 3.4.x *
* www.ant.be.tf/moviecatalog ··· www.buypin.com *
* *
* The source code of the script can be used in *
* another program only if full credits to *
* script author and a link to Ant Movie Catalog *
* website are given in the About box or in *
* the documentation of the program *
* *
***************************************************)
program Culturalia_IMDb;
const
BaseURLCulturalia = 'http://www.culturalianet.com/bus/catalogo.php';
UseLongestDescIMDB = False; // If set to False shortest description available will be imported, faster since taken from main page
// Set the following constants to True to import field, or False to skip field (fiels to import from IMDB). By default, only the fields not available at Culturalia are set to True.
// Pon las siguientes constantes a True para importar campo o False para no hacerlo (campos a importar de IMDB). Por defecto, sólo los campos no disponibles en Culturalia están a True.
ImportActors = False;
ImportCategory = False;
ImportComments = False;
ImportCountry = False;
ImportDescription = False;
ImportDirector = False;
ImportLength = True;
ImportLanguage = False;
ImportOriginalTitle = False;
ImportTranslatedTitle = False;
LeaveOriginalTitle = False; // True will get Translated Title, yet Original Title field will remain same
ImportPicture = False;
ImportLargePicture = False; // If set to False small pic will be imported
ImportRating = True;
ImportURL = False;
ImportYear = False;
TitleMixedCase = False; // If true, each letter of each word of title begins with Uppercase. If false, the script transforms the titles in lowercase except first word
ExternalPictures = False;
{ True: Pictures will be stored as external files in the folder of the
catalog
False: Pictures will be stored inside the catalog (only for .amc files) }
ManualPictureSelect = False;
{ True: If no Title Match found a picture selection window appears
False: Revert to IMDB picture }
// Donde vamos a buscar en el caso de no haber introducido ni el título original ni el traducido en los campos correspondientes, sino en la ventana que
// se abre y nos lo solicita.
// 1-Titulo traducido, 2-Titulo original, 3-General
// What type of search in case we don't write the original title nor traslated one in the corresponding fields, we do it in the input box.
// 1-Translated title, 2-Original Title, 3-General
defdonde='1';
var
MovieName, Titulo: string;
MovieURL: string;
tmp: string;
donde: string;
Articles: array of string;
Index: Integer;
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 AnalyzePageIMDB(Address: string);
var
Page: TStringList;
LineNr: Integer;
MovieURL: string;
begin
Page := TStringList.Create;
Page.Text := GetPage(Address);
if pos('<title>IMDb', Page.Text) = 0 then
begin
AnalyzeMoviePageIMDB(Page)
end
else
begin
MovieURL := AddMoviesTitles(Page, '<b>Exact Matches</b>');
if MovieURL = '' then
MovieURL := AddMoviesTitles(Page, '<b>Partial Matches</b>');
if MovieURL = '' then
MovieURL := AddMoviesTitles(Page, '<b>Approximate Matches</b>');
if MovieURL <> '' then
AnalyzePageIMDB(MovieURL);
end;
Page.Free;
end;
function FindValue(BeginTag, EndTag: string; Page: TStringList; var LineNr: Integer; var Line: string): string;
var
BeginPos, EndPos: Integer;
Value: string;
begin
Result := '';
Value := '';
BeginPos := Pos(BeginTag, Line);
if BeginPos > 0 then
begin
BeginPos := BeginPos + Length(BeginTag);
if BeginTag = EndTag then
begin
Delete(Line,1,BeginPos-1);
BeginPos := 1;
end;
EndPos := pos(EndTag, Line);
while ((EndPos = 0) and (LineNr < Page.Count-1 )) do
begin
Value := Value + copy(Line, BeginPos, Length(Line) - BeginPos);
// Next Line
BeginPos := 1;
LineNr := LineNr + 1;
Line := Page.GetString(LineNr);
if Value = '' then
Exit;
EndPos := Pos(EndTag, Line);
end;
Value := Value + copy(Line, BeginPos, EndPos - BeginPos);
end;
Result := Value;
end;
procedure AnalyzeMoviePageIMDB(Page: TStringList);
var
Line, Value, Value2, FullValue, OldOriginalTitle: string;
LineNr, Desc, i: Integer;
BeginPos, EndPos: Integer;
OldTitleParts, AllTitles: TStringList;
LongDescr: Boolean;
begin
LongDescr := UseLongestDescIMDB;
if (LongDescr) and (Pos('<a href="plotsummary">', Page.Text) = 0) then
LongDescr := False;
MovieURL := 'http://imdb.com/title/tt' + Copy(Page.Text, Pos('?pending&add=', Page.Text) + 17, 7);
// URL
if ImportURL then
SetField(fieldURL, MovieURL);
AllTitles := TStringList.Create;
// 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('/I', Line);
if EndPos < BeginPos then
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>', '/ ');
HTMLDecode(Value);
SetField(fieldTranslatedTitle, Trim(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('/10', 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;
// Language
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);
if ImportLanguage then
SetField(fieldLanguages, Value);
end;
if ImportPicture then
GetMoviePicture(Value, Page, AllTitles);
AllTitles.Free;
// 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('ast overview', Page, 0);
if LineNr = -1 then
LineNr := FindLine('redited 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
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="/rg/', Line);
if EndPos < 1 then
begin
Line := Line + Page.GetString(LineNr+1);
EndPos := pos('<a href="/rg/', Line);
if EndPos < 1 then
EndPos := pos('<br><br>', Line);
if EndPos < 1 then
EndPos := Length(Line);
end;
Value := copy(Line, BeginPos, EndPos - BeginPos);
HTMLDecode(Value);
HTMLRemoveTags(Value);
if UseLongestDescIMDB then
SetField(fieldDescription, GetDescriptions(MovieURL + 'plotsummary'))
else
SetField(fieldDescription, Value);
end;
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 - 1;
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;
DisplayResults;
end;
procedure GetMoviePicture(Language: string; Page, AllTitles: TStringList);
var
Line, Value, Value2, Aka, PictureAddress: string;
AmazonPage: TStringList;
FoundOnAmazon, PickTreeSelected, PictureAvailable: Boolean;
TitleRef, ImgRef, NoImage: string;
LineNr, BeginPos, EndPos, PickTreeCount, ParagraphIndex, Index, TitleLine, LastMatch: Integer;
begin
FoundOnAmazon := False;
if ImportLargePicture then
begin
// Find Alternate Titles for Movies which are not in English
Aka := '';
if Language <> 'English' Then
begin
LineNr:= FindLine('Also Known As',Page,0);
EndPos:=0;
if LineNr > -1 then
begin
Line := Page.GetString(LineNr);
repeat
Aka:=FindValue('<br>','<br>',Page,LineNr,Line);
if Aka <> '' then
begin
BeginPos:=1;
EndPos:=Pos('(',Line);
if EndPos = 0 then
EndPos := Length(Aka);
Value := copy(Aka, BeginPos, EndPos - BeginPos - 1);
Value:=TransFormIMDBTitle(Value);
AllTitles.Add(Value);
end;
until (Pos('</td>', Line) > 0) or (Pos('Runtime', Line) > 0) or (Pos('MPAA', Line) > 0 ) or (Pos('Country', Line) > 0) or (Pos('Certification', Line) > 0);
end;
end;
TitleRef:='dvd>';
ImgRef:='dvd><img';
NoImage:='/icons/dvd-no-image.gif';
LineNr := FindLine('title="DVD available at Amazon.com"', Page, 0);
if LineNr = -1 then
begin
LineNr := FindLine('title="VHS available at Amazon.com"', Page, 0);
if LineNr > -1 then
begin
TitleRef:='video>';
ImgRef:='video><img';
NoImage:='/icons/video-no-image.gif';
end;
end;
if LineNr > -1 then
begin
Line := Page.GetString(LineNr);
if(TitleRef='dvd>') then
begin
EndPos := pos('title="DVD', Line);
BeginPos := pos('title="VHS', Line);
while (BeginPos > 0) and (BeginPos<EndPos) do
begin
Delete(Line, 1, BeginPos+1);
BeginPos := pos('title="VHS', Line);
end;
end;
BeginPos := Pos('href="', Line) + 5;
Delete(Line, 1, BeginPos);
EndPos := Pos('"', Line);
Value := Copy(Line, 1, EndPos - 1);
AmazonPage := TStringList.Create;
AmazonPage.Text := GetPage('http://us.imdb.com' + Value);
// Original Title
Value2 := AllTitles.GetString(0);
Value2 := TransFormIMDBTitle(Value2);
PickTreeClear;
PickTreeCount := 0;
PickTreeAdd('Available Titles for matching a picture to: ' + Value2, '');
ParagraphIndex := 1;
LineNr := 0;
LastMatch := -1;
TitleLine := -1;
repeat
LineNr := FindLine('<b>'+IntToStr(ParagraphIndex)+'.', AmazonPage, LineNr);
if LineNr > -1 then
begin
TitleLine:=LineNr;
Value:='';
PictureAvailable:=False;
repeat
TitleLine:=TitleLine +1;
Line:= AmazonPage.GetString(TitleLine);
BeginPos:=0;
if Pos(TitleRef,Line) > 0 then
begin
if Pos(ImgRef,Line) = 0 then
begin
for Index:=0 to AllTitles.Count -1 do
begin
Value2:=AllTitles.GetString(Index);
BeginPos:=Pos(Value2,Line);
if BeginPos > 0 then
Break;
end;
// Match not found
if BeginPos = 0 then
begin
BeginPos:=Pos(TitleRef,Line)+Length(TitleRef);
EndPos:=Pos('</a>',Line);
Value:=Copy(Line,BeginPos,EndPos-BeginPos);
end;
end
else
begin
PictureAvailable:=(Pos(NoImage,Line) = 0);
PictureAddress:=IntToStr(TitleLine);
end;
end;
if BeginPos > 0 then
Break;
until (Pos('</table>',Line ) > 0);
// Try to Find a Title Match
if Pos(Value2,Line) > 0 then
begin
// Compare Current Title to Original
BeginPos := Pos(TitleRef, Line) + Length(TitleRef) -1;
Delete(Line, 1, BeginPos);
EndPos:= Pos('(',Line);
if EndPos = 0 Then
EndPos := Pos('</a>', Line);
Value := Copy(Line, 1, EndPos - 1);
Value:= Trim(Value);
if Value = Value2 then
begin
if PictureAvailable then
LastMatch:=LineNr;
//Break
end;
end;
if PictureAvailable then
begin
PickTreeAdd(Value,PictureAddress);
PickTreeCount:=PickTreeCount+1;
end;
end;
ParagraphIndex:=ParagraphIndex+1;
until (LineNr = -1);
LineNr:=LastMatch;
if (LineNr = -1) then
begin
// Handle Amazon Page Redirection(s)
LineNr:= FindLine('You clicked on this item',AmazonPage,0);
if (LineNr = -1) then
LineNr:=FindLine('Customers who bought',AmazonPage,0);
// Display the Picture Selection Window
if (LineNr = -1) and ManualPictureSelect and (PickTreeCount > 0) then
begin
PickTreeSelected:=PickTreeExec(PictureAddress);
if PickTreeSelected then
LineNr:=StrToInt(PictureAddress,0);
end;
if (LineNr > -1 ) then
begin
LineNr := FindLine('src="http://images.amazon.com/images/P/',AmazonPage, LineNr);
if not PickTreeSelected then
TitleLine:= FindLine('/exec/obidos/ASIN/',AmazonPage, 0);
if (LineNr > TitleLine) then
LineNr:=-1;
if LineNr > -1 then
begin
Line := AmazonPage.GetString(LineNr);
BeginPos := Pos('src="http://images.amazon.com/images/P/', Line) + 4;
Delete(Line, 1, BeginPos);
EndPos := Pos('"', Line);
Value := Copy(Line, 1, EndPos - 1);
Value := StringReplace(Value, 'TZZZZZZZ', 'LZZZZZZZ');
Value := StringReplace(Value, 'THUMBZZZ', 'LZZZZZZZ');
GetPicture(Value, ExternalPictures);
FoundOnAmazon := True;
end;
end;
end
else
begin
LineNr := FindLine('http://images.amazon.com/images/P/', AmazonPage, LineNr);
if LineNr < TitleLine then
begin
Line := AmazonPage.GetString(LineNr);
BeginPos := Pos('src="', Line) + 4;
Delete(Line, 1, BeginPos);
EndPos := Pos('"', Line);
Value := Copy(Line, 1, EndPos - 1);
Value := StringReplace(Value, 'THUMBZZZ', 'LZZZZZZZ');
GetPicture(Value, ExternalPictures);
FoundOnAmazon := True;
end;
end;
AmazonPage.Free;
end;
end; // if ImportLargePicture
if not FoundOnAmazon then
begin
{ not found on Amazon, so taking what's available directly on IMDB. }
LineNr := FindLine('<img border="0" alt="cover"', 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);
GetPicture(Value, ExternalPictures);
end;
end;
end;
function TransformTitle(Title: string): string;
var
BeginPos, EndPos: Integer;
Value: string;
Words: array of string;
Articles: array of string;
Replace,Original: string;
Index, CommaCount: Integer;
Begin
// Original Title
Result:=Title;
Setarraylength(Words,11);
Words[0]:=' In ';
Words[1]:=' On ';
Words[2]:=' Of ';
Words[3]:=' As ';
Words[4]:=' The ';
Words[5]:=' At ';
Words[6]:=' And A ';
Words[7]:=' And ';
Words[8]:=' An ';
Words[9]:=' To ';
Words[10]:=' For ';
SetArrayLength(Articles,35);
Articles[0]:=' The';
Articles[1]:=' a';
Articles[2]:=' An';
Articles[3]:=' Le';
Articles[4]:=' L''';
Articles[5]:=' Les';
Articles[6]:=' Der';
Articles[7]:=' Das';
Articles[8]:=' Die';
Articles[9]:=' Des';
Articles[10]:=' Dem';
Articles[11]:=' Den';
Articles[12]:=' Ein';
Articles[13]:=' Eine';
Articles[14]:=' Einen';
Articles[15]:=' Einer';
Articles[16]:=' Eines';
Articles[17]:=' Einem';
Articles[18]:=' Il';
Articles[19]:=' Lo';
Articles[20]:=' La';
Articles[21]:=' I';
Articles[22]:=' Gli';
Articles[23]:=' Le';
Articles[24]:=' Uno';
Articles[25]:=' Una';
Articles[26]:=' Un''';
Articles[27]:=' O';
Articles[28]:=' Os';
Articles[29]:=' As';
Articles[30]:=' El';
Articles[31]:=' Los';
Articles[32]:=' Las';
Articles[33]:=' Unos';
Articles[34]:=' Unas';
// Count the Comma in The Title
CommaCount := 0;
EndPos := 0;
Value := Title;
repeat
BeginPos := Pos(',', Value);
if BeginPos > 0 then
begin
Delete(Value, 1, BeginPos);
CommaCount := CommaCount + 1;
EndPos := EndPos + BeginPos;
end;
until( Pos(',',Value) = 0);
// Compare the Article to a list of known ones
for Index := 0 to 34 do
begin
if Pos(Articles[Index], Value) <> 0 then
begin
CommaCount := 1;
BeginPos := EndPos;
Break;
end;
end;
if (BeginPos > 0) and (CommaCount = 1) then
begin
Value := Copy(Title, BeginPos + 1, Length(Title));
Value := Trim(Value);
Result := Value + ' ' + Copy(Title, 1, BeginPos - 1);
end;
BeginPos := Pos(': ', Result);
if BeginPos > 0 then
Result := StringReplace(Result, ': ', ' - ');
Result := AnsiMixedCase(Result, ' ');
for Index := 0 to 10 do
begin
if Pos(Words[Index],Result) <> 0 then
begin
Original := Words[Index];
Replace := AnsiLowerCase(Original);
Result := StringReplace(Result, Original, Replace);
end;
end;
Result := StringReplace(Result, ' - the ', ' - The ');
Result := Trim(Result);
end;
function GetDescriptions(Address: string): string;
var
Line, Value: string;
LineNr: Integer;
BeginPos, EndPos,Longest: Integer;
Page: TStringList;
begin
Result := '';
Longest := 0;
Page := TStringList.Create;
Page.Text := GetPage(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);
HTMLDecode(Value);
HTMLRemoveTags(Value);
PickListAdd(Value);
if Length(Value) > Longest then
begin
Result := Value;
Longest := Length(Value);
end;
LineNr := FindLine('<p class="plotpar">', Page, LineNr);
end;
Page.Free;
end;
function AddMoviesTitles(Page: TStringList; Tag: string): string;
var
Line: string;
LineNr: Integer;
StartPos: Integer;
begin
Result := '';
LineNr := FindLine(tag, Page, 0);
if LineNr > -1 then
begin
Line := Page.GetString(LineNr);
HTMLRemoveTags(Line);
PickTreeAdd(Trim(Line), '');
LineNr := LineNr + 5;
Line := Page.GetString(LineNr);
StartPos := pos('href="', Line) + 5;
Delete(Line, 1, StartPos);
Result := Copy(Line, 1, pos('">', Line) - 1);
end;
end;
procedure AnalyzePageCulturalia(Address: string);
var
Page: TStringList;
LineNr: Integer;
Code, Title, TitleOrig, Year: string;
begin
Page := TStringList.Create;
Page.Text := GetPage(Address);
if Pos('No se ha encontrado ningún artículo por título', Page.Text) > 0 then
begin
ShowMessage('No se ha encontrado ninguna coincidencia por título');
end else
begin
PickTreeClear;
LineNr := 1;
Page.Text := StringReplace(Page.Text, '<br>', #13#10);
PickTreeAdd('Resultados más probables de la búsqueda:', '');
while LineNr + 3 < Page.Count do
begin
Code := GetValueAfter(Page.GetString(LineNr), 'Codigo = ');
Title := GetValueAfter(Page.GetString(LineNr+1), 'Titulo = ');
TitleOrig := GetValueAfter(Page.GetString(LineNr+2), 'Titulo original = ');
Year := GetValueAfter(Page.GetString(LineNr+3), 'Año = ');
PickTreeAdd(Title + ' (' + TitleOrig + '), ' + Year, BaseURLCulturalia + '?catalogo=1&codigo=' + Code);
LineNr := LineNr + 5;
end;
Page.Free;
if PickTreeExec(Address) then
AnalyzeMoviePageCulturalia(Address);
end;
end;
procedure AnalyzeMoviePageCulturalia(Address: string);
var
Page: TStringList;
Comments: string;
strTitle: string;
strSinopsis: string;
Line: string;
LineNr: Integer;
tmp: string;
begin
Page := TStringList.Create;
Page.Text := StringReplace(GetPage(Address), '<br><br>', #13#10);
Page.Text := StringReplace(Page.Text, '<br>', #13#10);
strTitle := GetValueAfter(Page.GetString(1), 'Titulo = ');
if copy(strTitle, Length(strTitle), Length(strTitle)) = '.' then
begin
tmp := Copy(strTitle, 1, Length(strTitle) -1);
end else
begin
tmp := strTitle;
end;
SetField(fieldTranslatedTitle, TransformTitle(tmp));
tmp := GetValueAfter(Page.GetString(2), 'Titulo original = ');
SetField(fieldOriginalTitle, TransformTitle(tmp));
SetField(fieldYear, GetValueAfter(Page.GetString(3), 'Año = '));
SetField(fieldCategory, GetValueAfter(Page.GetString(4), 'Genero = '));
SetField(fieldCountry, GetValueAfter(Page.GetString(5), 'Nacion = '));
SetField(fieldDirector, GetValueAfter(Page.GetString(6), 'Director = '));
SetField(fieldActors, GetValueAfter(Page.GetString(7), 'Actores = '));
SetField(fieldProducer, GetValueAfter(Page.GetString(8), 'Productor = '));
Comments := 'Guión: ' + GetValueAfter(Page.GetString(9), 'Guion = ');
Comments := Comments + #13#10 + 'Fotografía: ' + GetValueAfter(Page.GetString(10), 'Fotografia = ');
Comments := Comments + #13#10 + 'Música: ' + GetValueAfter(Page.GetString(11), 'Musica = ');
SetField(fieldComments, Comments);
LineNr := FindLine('Sinopsis = ', Page, 0);
Line := Page.GetString(LineNr);
strSinopsis := GetValueAfter(Line, 'Sinopsis = ');
LineNr := LineNr + 1;
Line := Page.GetString(LineNr);
while pos('URL = ', Line) = 0 do
begin
strSinopsis := strSinopsis + #13#10 + Line;
LineNr := LineNr + 1;
Line := Page.GetString(LineNr);
end
HTMLRemoveTags(strSinopsis);
SetField(fieldDescription, StringReplace(StringReplace(strSinopsis, '“', '"'), '”', '"'));
LineNr := FindLine('URL = ', Page, 0);
if LineNr <> -1 then
SetField(fieldURL, GetValueAfter(Page.GetString(LineNr), 'URL = '));
LineNr := FindLine('Imagen = ', Page, 0);
if LineNr <> -1 then
GetPicture(GetValueAfter(Page.GetString(LineNr), 'Imagen = '), False);
Page.Free;
end;
function GetValueAfter(Line, Identifier: string): string;
begin
if Pos(Identifier, Line) = 1 then
Result := Copy(Line, Length(Identifier)+1, Length(Line))
else
Result := '';
end;
begin
SetArrayLength(Articles,11);
Articles[0]:='Lo ';
Articles[1]:='La ';
Articles[2]:='Le ';
Articles[3]:='Uno ';
Articles[4]:='Una ';
Articles[5]:='Un ';
Articles[6]:='El ';
Articles[7]:='Los ';
Articles[8]:='Las ';
Articles[9]:='Unos ';
Articles[10]:='Unas ';
if CheckVersion(3,4,0) then
begin
MovieName := GetField(fieldOriginalTitle);
donde := '&donde=2';
if MovieName = '' then
begin
MovieName := GetField (fieldTranslatedTitle);
donde := '&donde=1';
end
if MovieName = '' then
begin
Input('Importar de Culturalia', 'Introduce el Titulo de la Pelicula:', MovieName);
donde := '&donde=' + defdonde;
end
If MovieName <> '' then
begin
// Eliminate spanish article if exists
for Index := 0 to 10 do
begin
if Pos(Articles[Index], MovieName) <> 0 then
MovieName := copy(MovieName, length(Articles[Index]), length(MovieName));
end;
// Eliminate point(s) at final of MovieName before search
tmp := MovieName;
if Copy(tmp, Length(tmp), Length(tmp)) = '.' then
MovieName := Copy(tmp, 1, Length(tmp) -1);
AnalyzePageCulturalia(BaseURLCulturalia + '?catalogo=1&texto=' + UrlEncode(MovieName) + donde);
AnalyzePageIMDB('http://us.imdb.com/Tsearch?title='+UrlEncode(GetField(fieldOriginalTitle)));
DisplayResults;
end;
end else
ShowMessage('This script requires a newer version of Ant Movie Catalog (at least the version 3.4.0)');
end.
nice
