How to make multiple http requests from a Google C

Question

MY PROBLEM:

I'm building a web-scraper with Cheerio, Node.js, and Google Cloud Functions.

The problem is I need to make multiple requests, then write data from each request to a Firestore database before calling response.send() and thereby terminating the function.

My code requires two loops: the first loop is with urls from my db, with each one making a separate request. The second loop is with Cheerio using .each to scrape multiple rows of table data from the DOM and make a separate write for each row.

WHAT I'VE TRIED:

I've tried pushing each request to an array of promises and then waiting for all the promises to resolve with promises.all() before calling res.send(), but I'm still a little shaky on promises and not sure that is the right approach. (I have gotten the code to work for smaller datasets that way, but still inconsistently.)

I also tried creating each request as a new promise and using async/await to await each function call from the forEach loop to allow time for each request and write to fully finish so I could call res.send() afterward, but I found out that forEach doesn't support Async/await.

I tried to get around that with the p-iteration module but because its not actually forEach but rather a method on the query (doc.forEach()) I don't think it works like that.

So here's my code.

NOTE:

As mentioned, this is not everything I tried (I removed my promise attempts), but this should show what I am trying to accomplish.

export const getCurrentLogs = functions.https.onRequest((req, response) => {


//First, I make a query from my db to get the urls 
// that I want the webscrapper to loop through. 

const ref = scheduleRef.get()

.then((snapshot) => {

    snapshot.docs.forEach((doc) => {

        const scheduleGame = doc.data()
        const boxScoreUrl = scheduleGame.boxScoreURL

//Inside the forEach I call the request 
// as a function with the url passed in

        updatePlayerLogs("https://" + boxScoreUrl + "/");


    });

})

.catch(err => {
    console.log('Error getting schedule', err);
});


function updatePlayerLogs (url){


//Here I'm not sure on how to set these options 
// to make sure the request stays open but I have tried 
// lots of different things. 

    const options = {
        uri: url,
        Connection: 'keep-alive',
        transform: function (body) {
            return cheerio.load(body);
        }
    };

   request(options)

        .then(($) => {


//Below I loop through some table data 
// on the dom with cheerio. Every loop 
// in here needs to be written to firebase individually. 


                $('.stats-rows').find('tbody').children('tr').each(function(i, element){


                    const playerPage = $(element).children('td').eq(0).find('a').attr('href');


                    const pts = replaceDash($(element).children('td').eq(1).text());
                    const reb =  replaceDash($(element).children('td').eq(2).text());
                    const ast =  replaceDash($(element).children('td').eq(3).text());
                    const fg =  replaceDash($(element).children('td').eq(4).text());
                    const _3pt =  replaceDash($(element).children('td').eq(5).text());
                    const stl =  replaceDash($(element).children('td').eq(9).text());
                    const blk =  replaceDash($(element).children('td').eq(10).text());
                    const to =  replaceDash($(element).children('td').eq(11).text());


                    const currentLog = {
                        'pts': + pts,
                        'reb': + reb,
                        'ast': + ast,
                        'fg':  fgPer,
                        '3pt': + _3ptMade,
                        'stl': + stl,
                        'blk':  + blk,
                        'to':  + to
                    }

                   //here is the write
                    playersRef.doc(playerPage).update({

                        'currentLog': currentLog

                    }) 
                    .catch(error => 
                        console.error("Error adding document: ", error + " : " + url)
                     );
                });

            })

        .catch((err) => {
            console.log(err); 
        });

    };

//Here I call response.send() to finish the function. 
// I have tried doing this lots of different ways but 
// whatever I try the response is being sent before all 
// docs are written.

   response.send("finished writing logs")

});

Everything I have tried either results in a deadline exceeded error (possibly because of quota limits which I have looked into but I don't think I should be exceeding) Or some unexplained error where the code doesn't finish executing but shows me nothing in the logs.

Please help, is there a way to use async/await in this scenario that I am not understanding? Is there a way to use promises to make this elegant?

Many thanks,

Answer 1

Maybe have a look at something like this. It uses Bluebird promises and the request-promise library

const Promise = require('bluebird');
var rp = require('request-promise');

const urlList = ['http://www.google.com', 'http://example.com']

async function getList() {
  await Promise.map(urlList, (url, index, length) => { 

    return rp(url)
      .then((response) => {

        console.log(`${'\n\n\n'}${url}:${'\n'}${response}`);
        return;
      }).catch(async (err) => {
        console.log(err);
        return;

      })


  }, {
    concurrency: 10
  }); //end Promise.map

}

getList();