Here is a working program that downloads a snapshot of the page on Windows. Download this code and save as "Scraper.js" on your desktop:
URL = "https://www.flashscore.com/football/england/premier-league-2018 +-2019/results/"; // <= WEBSITE YOU WANT TO SCRAPE WEB_BROWSER = "C:\\BIN\\SUPERMIUM\\chrome.exe"; // <= PUT YOUR WEB +BROWSER'S FULL NAME AND PATH HERE WEB_BROWSER_NAME = "Supermium"; // <= PUT YOUR WEB +BROWSER'S SHORT NAME HERE try { FSO = new ActiveXObject("Scripting.FileSystemObject"); WshShell = WScript.CreateObject("WScript.Shell"); } catch (e) { ABORT("The script cannot access the file system!"); } ContinueOrExit("This script will try to open the web browser " + WEB_BROWSER_NAME + ", load a website and\n" + "copy the contents and save it in a file called Scraper.txt."); ALERT("This program will run for approx. 20 seconds after\nyou press t +he OK button, and then\nit will terminate and say \"done\"."); RUN(QUOTE(WEB_BROWSER) + " " + QUOTE(URL)); WAIT(5); WINFOCUS( WEB_BROWSER_NAME ); WAIT(10); // WAIT FOR PAGE TO FULLY LOAD. GIVE IT ABOUT 10 + SECONDS. PRESS("{ESCAPE}"); // SEND ESC KEYSTROKE TO CLOSE POPUP AD ON THE W +EBSITE WAIT(0.2); PRESS("^{a}"); // SEND CTRL+A KEYSTROKE (SELECT ALL) WAIT(0.05); PRESS("^{a}"); // SEND CTRL+A KEYSTROKE AGAIN JUST IN CASE WAIT(0.2); PRESS("^{INSERT}"); // SEND CTRL+INSERT KEYSTROKE (COPY TEXT) WAIT(0.2); TEXT = ReadClipboardText(); CURDIR = GetCurDir(); // GET CURRENT DIRECTORY // Note: When you save using CreateFile(), this will discard ALL // unicode characters from the TEXT. If you want to save Unicode // characters in the output, then use CreateUnicodeFile() // function instead: // Here we remove everything that appears BEFORE the first occurrence +of "Premier League" // We only keep the text that appears after this text: TEXT = StrAfter(TEXT, "Premier League"); // And here we remove everything that appears AFTER the last occurrenc +e of "Show more matches" // We only keep whatever we have before this text: TEXT = StrBefore(TEXT, "Show more matches"); // So, we're left with the results, and we save that in a text file: CreateFile(CURDIR + "Scraper.txt", TEXT); SAY("done"); EXIT(); // END OF SCRIPT //////////////////////////////////////////////////////////////////// // // F U N C T I O N S // // This function displays a simple OK popup message box. function ALERT(MSG) { WScript.Echo(MSG); } // Display an error message and terminate the script. function ABORT(MSG) { EXIT("Error: " + MSG); } // Display a message and terminate the script. function EXIT(MSG) { if (typeof(MSG) != "undefined") ALERT(MSG); WScri +pt.Quit(0); } // Show a popup box, display a Yes/No question, and return the user's +response. function YES(QUESTION, TITLE) { try { if (WshShell.Popup(QUESTION, 0, +(typeof(TITLE) == "string" ? TITLE : "Question"), 36) == 6) return 1; + } catch (e) {} return 0; } // Asks whether to continue the script or not. If user selects no, the +n terminates the script. function ContinueOrExit(QUESTION) { if (!YES(QUESTION + "\n\nContinue? +", "Do you want to continue?")) EXIT(); } // This function returns the current directory with a backslash at the + end. function GetCurDir() { return WScript.ScriptFullName.replace(/\\[^\\]+ +$/, "\\"); } // This function will run a separate program which will be independent + from this script. function RUN(CMD) { WshShell.Run(CMD, 9); } // This function will transfer focus to the named application. This fu +nction does not work in every situation. // If it doesn't work, try to substitute it by sending ALT+TAB keycode +, which will bring into focus // the other running app. Make sure there are no other windows open! function WINFOCUS(W) { WshShell.AppActivate(W); } // This script will wait for N seconds and then continue execution of +the script. function WAIT(N) { WScript.Sleep(N * 1000); } // This function will use the builtin text-to-speech engine of Windows + to say a sentence in English. function SAY(TEXT) { var VOICE = WScript.CreateObject("SAPI.SpVoice"); + VOICE.Volume = 100; VOICE.Speak(TEXT); } // This function sends a keypress to the currently running app. function PRESS(KEYCODE) { WAIT(0.1); WshShell.SendKeys(KEYCODE); } // This function inserts double quotes around a string. function QUOTE(S) { return '"' + S + '"'; } // This function returns a section of string S that comes before the L +AST occurrence of string M. The match is case sensitive. function StrBefore(S, M) { var E = S.lastIndexOf(M); return (E > 0) ? +S.substr(0, E) : ""; } // This function returns a section of string S that comes after the FI +RST occurrence of string M. The match is case sensitive. function StrAfter(S, M) { var E = S.indexOf(M); return (E > 0) ? S.sli +ce(E + M.length) : ""; } //////////////////////////////////////////////////////////////////// // // This function creates and overwrites a file in plain text ASCII mod +e. // Return 1 on success or 0 if an error occurred. // // Usage: INTEGER = CreateFile(FILENAME, STRING) // function CreateFile(FILENAME, S) { S += ""; // Ensure that no errors will occur during write: // Here we convert certain special characters which would cause // a "hiccup" with the Write() function when we have the // file open in plain text ASCII mode. S = S.replace(/[^\x00-\xFF]+/g, ""); S = S.replace(/[\x80-\x9F]{1}/g, function (c, x) { return "\u20AC\x8 +1\u201A\u0192\u201E\u2026\u2020\u2021\u02C6\u2030\u0160\u2039\u0152\x +8D\u017D\x8F\x90\u2018\u2019\u201C\u201D\u2022\u2013\u2014\u02DC\u212 +2\u0161\u203A\u0153\x9D\u017E\u0178".charAt(x - 128); }); try { var FILE = FSO.CreateTextFile(FILENAME, 1, 0); // Create plain A +SCII file. FILE.Write(S); FILE.Close(); return 1; } catch (e) {} return 0; } //////////////////////////////////////////////////////////////////// // // This function creates and overwrites a file with a string that // may contain Unicode characters. The file will be saved in // UTF-16BE format! The function returns 1 on success or // zero if an error occurred. // // Usage: INTEGER = CreateUnicodeFile(FILENAME, STRING) // function CreateUnicodeFile(FILENAME, S) { try { var FILE = FSO.CreateTextFile(FILENAME, 1, 1); // Create UTF16 fi +le FILE.Write(S); FILE.Close(); return 1; } catch (e) {} return 0; } //////////////////////////////////////////////////////////////////// // // This function copies all text from the clipboard. We accomplish // this by launching Internet Explorer in the background. We create // a document with a textbox for user input. We paste whatever is // on the clipboard into the textarea, and then we read its content // and return the string. This process takes about 200ms. // // Usage: STRING = ReadClipboardText() // function ReadClipboardText() { var MSIE = WScript.CreateObject("InternetExplorer.Application"); MSIE.Visible = 0; MSIE.Navigate("about:blank"); var HTML = "<HTML><HEAD><TITLE></TITLE></HEAD><BODY onLoad='Init();' + SCROLL=NO><FORM NAME=MAIN><TEXTAREA NAME=INPUT COLS=20 ROWS=5></TEXT +AREA><SCRIPT> function Init() { document.MAIN.INPUT.focus(); } </SCRI +PT>"; MSIE.Document.open(); MSIE.Document.write(HTML); MSIE.Document.close(); WScript.Sleep(100); PRESS("+{INSERT}"); WScript.Sleep(60); var TEXT = MSIE.Document.MAIN.INPUT.value; MSIE.Quit(); return TEXT; } ////////////////////////////////////////////////////////////////////
And here is the output that it produces:
2018/2019 Advertisement SCORES NEWS LOGIN Advertisement Advertisement FOOTBALL ENGLAND Premier League Premier League 2018/2019 SUMMARY NEWS RESULTS FIXTURES STANDINGS ARCHIVE ENGLAND : Premier League Standings ROUND 38 12.05. 08:00 Brighton Brighton Manchester City Manchester City 1 4 12.05. 08:00 Burnley Burnley Arsenal Arsenal 1 3 12.05. 08:00 Crystal Palace Crystal Palace Bournemouth Bournemouth 5 3 12.05. 08:00 Fulham Fulham Newcastle Newcastle 0 4 12.05. 08:00 Leicester Leicester Chelsea Chelsea 0 0 12.05. 08:00 Liverpool Liverpool Wolves Wolves 2 0 12.05. 08:00 Manchester Utd Manchester Utd Cardiff Cardiff 0 2 12.05. 08:00 Southampton Southampton Huddersfield Huddersfield 1 1 12.05. 08:00 Tottenham Tottenham Everton Everton 2 2 12.05. 08:00 Watford Watford West Ham West Ham 1 4 ROUND 37 06.05. 13:00 Manchester City Manchester City Leicester Leicester 1 0 05.05. 09:30 Arsenal Arsenal Brighton Brighton 1 1 05.05. 07:00 Chelsea Chelsea Watford Watford 3 0 05.05. 07:00 Huddersfield Huddersfield Manchester Utd Manchester Utd 1 1 04.05. 12:45 Newcastle Newcastle Liverpool Liverpool 2 3 04.05. 10:30 Cardiff Cardiff Crystal Palace Crystal Palace 2 3 04.05. 08:00 West Ham West Ham Southampton Southampton 3 0 04.05. 08:00 Wolves Wolves Fulham Fulham 1 0 04.05. 05:30 Bournemouth Bournemouth Tottenham Tottenham 2 1 0 03.05. 13:00 Everton Everton Burnley Burnley 2 0 ROUND 36 28.04. 09:30 Manchester Utd Manchester Utd Chelsea Chelsea 1 1 28.04. 07:05 Burnley Burnley Manchester City Manchester City 0 1 28.04. 05:00 Leicester Leicester Arsenal Arsenal 3 0 27.04. 10:30 Brighton Brighton Newcastle Newcastle 1 1 27.04. 08:00 Crystal Palace Crystal Palace Everton Everton 0 0 27.04. 08:00 Fulham Fulham Cardiff Cardiff 1 0 27.04. 08:00 Southampton Southampton Bournemouth Bournemouth 3 3 27.04. 08:00 Watford Watford Wolves Wolves 1 2 27.04. 05:30 Tottenham Tottenham West Ham West Ham 0 1 26.04. 13:00 Liverpool Liverpool Huddersfield Huddersfield 5 0 ROUND 31 24.04. 13:00 Manchester Utd Manchester Utd Manchester City Manchester City 0 2 24.04. 12:45 Wolves Wolves Arsenal Arsenal 3 1 ROUND 33 23.04. 12:45 Tottenham Tottenham Brighton Brighton 1 0 ROUND 31 23.04. 12:45 Watford Watford Southampton Southampton 1 1 ROUND 35 22.04. 13:00 Chelsea Chelsea Burnley Burnley 2 2 21.04. 09:00 Arsenal Arsenal Crystal Palace Crystal Palace 2 3 21.04. 09:00 Cardiff Cardiff Liverpool Liverpool 0 2 21.04. 06:30 Everton Everton Manchester Utd Manchester Utd 4 0 20.04. 10:30 Newcastle Newcastle Southampton Southampton 3 1 20.04. 08:00 Bournemouth Bournemouth Fulham Fulham 0 1 20.04. 08:00 Huddersfield Huddersfield Watford Watford 1 2 20.04. 08:00 West Ham West Ham Leicester Leicester 2 2 20.04. 08:00 Wolves Wolves Brighton Brighton 0 0 20.04. 05:30 Manchester City Manchester City Tottenham Tottenham 1 0 ROUND 31 16.04. 12:45 Brighton Brighton Cardiff Cardiff 0 2 ROUND 34 15.04. 13:00 Watford Watford Arsenal Arsenal 0 1 14.04. 09:30 Liverpool Liverpool Chelsea Chelsea 2 0 14.04. 07:05 Crystal Palace Crystal Palace Manchester City Manchester City 1 3 13.04. 10:30 Manchester Utd Manchester Utd West Ham West Ham 2 1 13.04. 08:00 Brighton Brighton Bournemouth Bournemouth 0 5 13.04. 08:00 Burnley Burnley Cardiff Cardiff 2 0 13.04. 08:00 Fulham Fulham Everton Everton 2 0 13.04. 08:00 Southampton Southampton Wolves Wolves 3 1 13.04. 05:30 Tottenham Tottenham Huddersfield Huddersfield 4 0 12.04. 13:00 Leicester Leicester Newcastle Newcastle 0 1 ROUND 33 08.04. 13:00 Chelsea Chelsea West Ham West Ham 2 0 07.04. 07:05 Everton Everton Arsenal Arsenal 1 0 06.04. 08:00 Bournemouth Bournemouth Burnley Burnley 1 3 06.04. 08:00 Huddersfield Huddersfield Leicester Leicester 1 4 06.04. 08:00 Newcastle Newcastle Crystal Palace Crystal Palace 0 1 05.04. 13:00 Southampton Southampton Liverpool Liverpool 1 3 ROUND 27 03.04. 12:45 Chelsea Chelsea Brighton Brighton 3 0 ROUND 33 03.04. 12:45 Manchester City Manchester City Cardiff Cardiff 2 0 ROUND 31 03.04. 12:45 Tottenham Tottenham Crystal Palace Crystal Palace 2 0 ROUND 33 02.04. 12:45 Watford Watford Fulham Fulham 4 1 02.04. 12:45 Wolves Wolves Manchester Utd Manchester Utd 2 1 ROUND 32 01.04. 13:00 Arsenal Arsenal Newcastle Newcastle 2 0 31.03. 09:30 Liverpool Liverpool Tottenham Tottenham 2 1 31.03. 07:05 Cardiff Cardiff Chelsea Chelsea 1 2 30.03. 11:30 West Ham West Ham Everton Everton 0 2 30.03. 09:00 Brighton Brighton Southampton Southampton 0 1 30.03. 09:00 Burnley Burnley Wolves Wolves 2 0 30.03. 09:00 Crystal Palace Crystal Palace Huddersfield Huddersfield 2 0 30.03. 09:00 Leicester Leicester Bournemouth Bournemouth 2 0 30.03. 09:00 Manchester Utd Manchester Utd Watford Watford 2 1 30.03. 06:30 Fulham Fulham Manchester City Manchester City 0 2 ROUND 31 17.03. 10:30 Everton Everton Chelsea Chelsea 2 0 17.03. 08:15 Fulham Fulham Liverpool Liverpool 1 2 16.03. 09:00 Bournemouth Bournemouth Newcastle Newcastle 2 2 16.03. 09:00 Burnley Burnley Leicester Leicester 1 2 16.03. 09:00 West Ham West Ham Huddersfield Huddersfield 4 3 ROUND 30 10.03. 10:30 Arsenal Arsenal Manchester Utd Manchester Utd 2 0 10.03. 08:05 Chelsea Chelsea Wolves Wolves 1 1 10.03. 06:00 Liverpool Liverpool Burnley Burnley 4 2 09.03. 11:30 Manchester City Manchester City Watford Watford 3 1 09.03. 09:00 Cardiff Cardiff West Ham West Ham 2 0 09.03. 09:00 Huddersfield Huddersfield Bournemouth Bournemouth 0 2 09.03. 09:00 Leicester Leicester Fulham Fulham 3 1 09.03. 09:00 Newcastle Newcastle Everton Everton 3 2 09.03. 09:00 Southampton Southampton Tottenham Tottenham 2 1 09.03. 06:30 Crystal Palace Crystal Palace Brighton Brighton 1 2 ROUND 29 03.03. 10:15 Everton Everton Liverpool Liverpool 0 0 03.03. 08:05 Fulham Fulham Chelsea Chelsea 1 2 03.03. 06:00 Watford Watford Leicester Leicester 2 1 02.03. 11:30 West Ham West Ham Newcastle Newcastle 2 0 02.03. 09:00 Bournemouth Bournemouth Manchester City Manchester City 0 1 02.03. 09:00 Brighton Brighton Huddersfield Huddersfield 1 0 02.03. 09:00 Burnley Burnley Crystal Palace Crystal Palace 1 3 02.03. 09:00 Manchester Utd Manchester Utd Southampton Southampton 3 2 02.03. 09:00 Wolves Wolves Cardiff Cardiff 2 0 02.03. 06:30 Tottenham Tottenham Arsenal Arsenal 1 1 ROUND 28 27.02. 14:00 Chelsea Chelsea Tottenham Tottenham 2 0 27.02. 14:00 Crystal Palace Crystal Palace Manchester Utd Manchester Utd 1 3 27.02. 14:00 Liverpool Liverpool Watford Watford 5 0 27.02. 14:00 Manchester City Manchester City West Ham West Ham 1 0 27.02. 13:45 Arsenal Arsenal Bournemouth Bournemouth 5 1 27.02. 13:45 Southampton Southampton Fulham Fulham 2 0
In reply to Re: Web scrapping
by harangzsolt33
in thread Web scrapping
by joyfedl
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |