Geek Answers Handbook

How to extract destination URL from google search result?

I am trying to extract URLs from Google search results. I am using Indy IdHTTP to get HTML results from Google, and I am using Achmad Z code to get hrefs links from a page . How can I get the real link target for each URL, and not the one sent through the Google redirector?

I tried this, but in this part of the code I get the error "Operand is not applicable":

function ToUTF8Encode(str: string): string;
var
  b: Byte;
begin
  for b in BytesOf(UTF8Encode(str)) do
  begin
    Result := Format('%s%s%.2x', [Result, '%', b]);
  end;
end;

I am using Delphi 7 with Indy 9.00.10. Maybe updating indy will help?

+5
source share
3 answers

, Google Search API, , Delphi 7.

SuperObject ( JSON Delphi), this version ( ). ; , . , Delphi 2009, , TIdHTTP.Get , 9.00.10 .

, ( :)

URL-, , , DxGoogleSearchApi.pas, , Google Web Search API reference. DxGoogleSearchApi.pas , . .

,

uses
  IdHTTP, IdURI, SuperObject;

const
  GSA_Version = '1.0';
  GSA_BaseURL = 'http://ajax.googleapis.com/ajax/services/search/';

procedure TForm1.GoogleSearch(const Text: string);
var
  I: Integer;
  RequestURL: string;
  HTTPObject: TIdHTTP;
  HTTPStream: TMemoryStream;
  JSONResult: ISuperObject;
  JSONResponse: ISuperObject;
begin
  RequestURL := TIdURI.URLEncode(GSA_BaseURL + 'web?v=' + GSA_Version + '&q=' + Text);

  HTTPObject := TIdHTTP.Create(nil);
  HTTPStream := TMemoryStream.Create;

  try
    HTTPObject.Get(RequestURL, HTTPStream);
    JSONResponse := TSuperObject.ParseStream(HTTPStream, True);

    if JSONResponse.I['responseStatus'] = 200 then
    begin
      ListBox1.Items.Add('Search time: ' + JSONResponse.S['responseData.cursor.searchResultTime']);
      ListBox1.Items.Add('Fetched count: ' + IntToStr(JSONResponse['responseData.results'].AsArray.Length));
      ListBox1.Items.Add('Total count: ' + JSONResponse.S['responseData.cursor.resultCount']);
      ListBox1.Items.Add('');

      for I := 0 to JSONResponse['responseData.results'].AsArray.Length - 1 do
      begin
        JSONResult := JSONResponse['responseData.results'].AsArray[I];
        ListBox1.Items.Add(JSONResult.S['unescapedUrl']);
      end;
    end;

  finally
    HTTPObject.Free;
    HTTPStream.Free;
  end;
end;

procedure TForm1.Button1Click(Sender: TObject);
begin
  GoogleSearch('Delphi');
end;
+4

, Google, TIdHTTP.Get. , API Google,

, . here Delphi demo API Google. Delphi 2009 Windows 7/64, .

+5

, , - : -:

memo1.Lines.Text := idhttp1.Get('http://ajax.googleapis.com/aja...tart=1&rsz=large&q=max');

URL-:

function ExtractText(const Str, Delim1, Delim2: string; PosStart: integer; var PosEnd: integer): string;
var
  pos1, pos2: integer;
begin
  Result := '';
  pos1 := PosEx(Delim1, Str, PosStart);
  if pos1 > 0 then
  begin
    pos2 := PosEx(Delim2, Str, pos1 + Length(Delim1));
    if pos2 > 0 then
    begin
      PosEnd := pos2 + Length(Delim2);
      Result := Copy(Str, pos1 + Length(Delim1), pos2 - (pos1 + Length(Delim1)));
    end;
  end;
end;

Button1 :

procedure TForm1.Button1Click(Sender: TObject);
var Pos: integer;
    sText: string;
begin
  sText := ExtractText(Memo1.Lines.Text, '"url":"', '","visibleUrl"', 1, Pos);
  while sText <> '' do
  begin
    Memo2.Lines.Add(sText);
    sText := ExtractText(Memo1.Lines.Text, '"url":"', '","visibleUrl"', Pos, Pos);
  end;
end;

www.delphi.about.com , Zarko Gajic :) . google , .

+1
source

More articles:


All Articles