Wait for Javascript Web Scraping Function to finish before running for next page?

Question

I am attempting to create a web scraper (in node.js) that will pull down information from a site, and write it to a file. I have it built to correctly work for one page, but when I try to use the function in a for loop, to iterate through multiple games, I get bad data in all of the games.

I understand that this is related to Javascript's asynchronous nature, and I have read about callback functions, but I'm not sure I understand how to apply it to my code. Any help would be GREATLY appreciated:

for(x = 4648; x < 4650; x++){  //iterate over a few gameIDs, used in URL for request
    scrapeGame(x);
}

function scrapeGame(gameId){
    //request from URL, scrape HTML to arrays as necessary
    //write final array to file
}

Essentially, what I am looking to do, is within the for loop, tell it to WAIT to finish the scrapeGame(x) function before incrementing x and running it for the next game -- otherwise, the arrays start to overwrite each other and the data becomes a huge mess.

EDIT: I've now included the full code which I am attempting to run! I'm getting errors when looking in the files after they are written. For example, the first file is 8kb, second is ~16, 3rd is ~32, etc. It seems things aren't getting cleared before running the next game.

Idea of the program is to pull Jeopardy questions/answers from the archive site in order to eventually build a quiz app for myself.

//Iterate over arbitrary number of games, scrape each

for(x = 4648; x < 4650; x++){
    scrapeGame(x, function(scrapeResult) {
        if(scrapeResult){
            console.log('Scrape Successful');
        } else {
            console.log('Scrape ERROR');
        }
    });
}

function scrapeGame(gameId, callback){
    var request = require('request');
        cheerio = require('cheerio');
        fs = require('fs');
        categories = [];
        categorylist = [];
        ids = [];
        clues = [];
        values = ['0','$200','$400','$600','$800','$1000','$400','$800','$1200','$1600','$2000'];
        valuelist = [];
        answers = [];
        array = [];
        file = [];
        status = false;

    var showGameURL = 'http://www.j-archive.com/showgame.php?game_id=' + gameId;
    var showAnswerURL = 'http://www.j-archive.com/showgameresponses.php?game_id=' + gameId;

    request(showGameURL, function(err, resp, body){ 
    if(!err && resp.statusCode === 200){
        var $ = cheerio.load(body);
        //add a row to categories to avoid starting at 0
        categories.push('Category List');
        //pull all categories to use for later
        $('td.category_name').each(function(){
            var category = $(this).text();
            categories.push(category);
        });
        //pull all clue IDs (coordinates), store to 1d array
        //pull any id that has "stuck" in the string, to prevent duplicates
        $("[id*='stuck']").each(function(){
            var id = $(this).attr('id');
            id = id.toString();
            id = id.substring(0, id.length - 6);
            ids.push(id);
            //if single J, pick category 1-6
            if (id.indexOf("_J_") !== -1){
                var catid = id.charAt(7);
                categorylist.push(categories[catid]);
                var valId = id.charAt(9);
                valuelist.push(values[valId]);
            }
            //if double J, pick category 7-12
            else if (id.indexOf("_DJ_") !== -1){
                var catid = parseInt(id.charAt(8)) + 6;
                categorylist.push(categories[catid]);
                var valId = parseInt(id.charAt(10)) + 5;
                valuelist.push(values[valId]);                
            }
            //if final J, pick category 13
            else {
                categorylist.push(categories[13]);
            }
        });
        //pull all clue texts, store to 1d array
        $('td.clue_text').each(function(){
            var clue = $(this).text();
            clues.push(clue);
        });
        //push pulled values to big array
        array.push(ids);
        array.push(categorylist);
        array.push(valuelist);
        array.push(clues);

        //new request to different URL to pull responses
        request(showAnswerURL, function(err, resp, body){ 
            if(!err && resp.statusCode === 200){
                var $ = cheerio.load(body);

                $('.correct_response').each(function(){
                    var answer = $(this).text();
                    answers.push(answer);
                });
                //push answers to big array
                array.push(answers);
                //combine arrays into 1-d array to prep for writing to file
                for(var i = 0; i < array[0].length; i++){
                    var print = array[0][i] + "|" + array[1][i] + "|" + array[2][i] + "|" + array[3][i] + "|" + array[4][i];
                    var stringPrint = print.toString();
                    file.push(stringPrint);
                }
                //update string, add newlines, etc.
                var stringFile = JSON.stringify(file);
                stringFile = stringFile.split('\\').join('');
                stringFile = stringFile.split('","').join('\n');
                //write to file, eventually will append to end of one big file
                fs.writeFile('J_GAME_' + gameId +'.txt', stringFile, function(err) {
                    if(err) {
                        console.log(err);
                    } else {
                        console.log("Game #" + gameId + " has been scraped.");
                        status = true;
                    }
                });
            }
        });
    }
});
        //clear arrays used
        valuelist = [];
        answers = [];
        categories = [];
        categorylist = [];
        ids = [];
        clues = [];
        array = [];
        file = [];
        //feed callback status
        callback(status);
}

Answer 1

// Iterate over a few gameIDs, used in URL for request.
for (x = 4648; x < 4650; x++) {
  // Pass in the callback as an anonymous function.
  // So below I am passing in the id and the function I want to execute.
  // AND, defining the results I am expecting as passed in arguments. 
  scrapeGame(x, function(scrapeResult, err) {
    // This will *NOT* execute *UNTIL* you call it in the function below.
    // That means that the for loop's execution is halted. 
    // This function receives the status that is passed in, 
    // in this case, a boolean true/false and an error if any.
    if (scrapeResult) {
      // Scrape was true, nothing to do.
      // The for loop will now move on to the next iteration.
      console.log('Scrape Successful');
    } else {
      // Scrape was false, output error to console.log and 
      // break loop to handle error.
      console.log('Scrape ERROR :: ' + err);
      // Notice we are calling break while in the 
      // scope of the callback function
      // Remove the break if you want to just move onto
      // the next game ID and not stop the loop
      break;
    }
  });
}

// This function now accepts two arguments.
function scrapeGame(gameId, callback) {

  // ************************************************
  // ** Do Your Work Here **
  // Request from URL, scrape HTML to arrays as necessary.
  // Write final array to file.
  // After file creation, execute the callback and pass bool
  // status (true/false).
  // ************************************************

  var request = require('request'),
      cheerio = require('cheerio'),
      fs = require('fs'),
      categories = [],
      categorylist = [],
      ids = [],
      clues = [],
      values = [
          '0',
          '$200',
          '$400',
          '$600',
          '$800',
          '$1000',
          '$400',
          '$800',
          '$1200',
          '$1600',
          '$2000'
      ],
      valuelist = [],
      answers = [],
      array = [],
      file = [],
      showGameURL = 'http://www.j-archive.com/showgame.php?game_id=' + gameId,
      showAnswerURL = 'http://www.j-archive.com/showgameresponses.php?game_id=' + gameId;

  request(showGameURL, function(err, resp, body) {
    if (!err && resp.statusCode === 200) {
      var $ = cheerio.load(body);
      //add a row to categories to avoid starting at 0
      categories.push('Category List');
      //pull all categories to use for later
      $('td.category_name').each(function() {
        var category = $(this).text();
        categories.push(category);
      });
      //pull all clue IDs (coordinates), store to 1d array
      //pull any id that has "stuck" in the string, to prevent duplicates
      $("[id*='stuck']").each(function() {
        var id = $(this).attr('id');
        id = id.toString();
        id = id.substring(0, id.length - 6);
        ids.push(id);
        //if single J, pick category 1-6
        if (id.indexOf("_J_") !== -1) {
          var catid = id.charAt(7);
          categorylist.push(categories[catid]);
          var valId = id.charAt(9);
          valuelist.push(values[valId]);
        }
        //if double J, pick category 7-12
        else if (id.indexOf("_DJ_") !== -1) {
          var catid = parseInt(id.charAt(8)) + 6;
          categorylist.push(categories[catid]);
          var valId = parseInt(id.charAt(10)) + 5;
          valuelist.push(values[valId]);
        }
        //if final J, pick category 13
        else {
          categorylist.push(categories[13]);
        }
      });
      //pull all clue texts, store to 1d array
      $('td.clue_text').each(function() {
        var clue = $(this).text();
        clues.push(clue);
      });
      //push pulled values to big array
      array.push(ids);
      array.push(categorylist);
      array.push(valuelist);
      array.push(clues);

      //new request to different URL to pull responses
      request(showAnswerURL, function(err, resp, body) {
        if (!err && resp.statusCode === 200) {
          var $ = cheerio.load(body);

          $('.correct_response').each(function() {
            var answer = $(this).text();
            answers.push(answer);
          });
          //push answers to big array
          array.push(answers);
          //combine arrays into 1-d array to prep for writing to file
          for (var i = 0; i < array[0].length; i++) {
            var print = array[0][i] + "|" + array[1][i] + "|" + array[2][i] + "|" + array[3][i] + "|" + array[4][i];
            var stringPrint = print.toString();
            file.push(stringPrint);
          }
          //update string, add newlines, etc.
          var stringFile = JSON.stringify(file);
          stringFile = stringFile.split('\\').join('');
          stringFile = stringFile.split('","').join('\n');
          //write to file, eventually will append to end of one big file
          fs.writeFile('J_GAME_' + gameId + '.txt', stringFile, function(err) {

            //clear arrays used
            valuelist = [];
            answers = [];
            categories = [];
            categorylist = [];
            ids = [];
            clues = [];
            array = [];
            file = [];

            if (err) {
              // ******************************************
              // Callback false with error.
              callback(false, err);
              // ******************************************
            } else {
              console.log("Game #" + gameId + " has been scraped.");
              // ******************************************
              // Callback true with no error. 
              callback(true);
              // ******************************************
            }
          });
        }
      });
    }
  });
}

Answer 2

I solved the ROOT cause of the issue that I was seeing, though I do believe without the callback assistance from red above, I would have been just as lost.

Turns out the data was processing correctly, but the file write was scrambling. Turns out that there is a different method to call instead of writeFile or appendFile:

fs.appendFileSync();

Calling the Synchronous version processed the writes to the file IN THE ORDER they got appended to the file, instead of just going for it. This, in addition to the callback help above, solved the issue.

Thanks to everyone for the assistance!

Answer 3

My assumption is that you want them to be scraped one after one, not in parallel. So, for loop won't help. The following approach should do the trick:

    var x = 4648;
    var myFunc = scrapeGame(x, function cb(){
        if(x >= 4650){
           return; 
        }
        x++;
        return myFunc(x, cb); 
    });



function scrapeGame(gameId){
    //request from URL, scrape HTML to arrays as necessary
    //write final array to file
}

For nested async function, where you want them be executed in serial manner, you should just forget about for loop.

An example of correct request handling with http client:

function scrapeGame(gameId, cb){

//your code and set options

http.request(options, function(response){
    var result = "";
    response.on('data', function (chunk) {
                result += chunk;
             });
    response.on('end',function(){
               //write data here;

               //do the callback
               cb();    
            });
});

}