Reputation:
I have a small issue with mongoose, what I am doing is getting data from online rss feeds, parsing it, and passing it to an array, from which I feed a mongoose model, and all this happens in the get route, what I want to accomplish is delete all the data first from the mongoose model and then populate it with the new data, but it always either deletes the data all together, since the parser iterates a few times, or it doesn't delete anything and the data just keeps adding to the model.
Here's my code
'use strict';
const Promise = require('bluebird');
const request = require('request');
const FeedParser = require('feedparser');
const express = require('express');
const router = express.Router();
const xray = require('x-ray')();
var Post = require('../models/post');
var dataArray = [];
router.get('/', function (req, res) {
const fetch = (url) => {
return new Promise((resolve, reject) => {
if (!url) {
return reject(new Error(`Bad URL (url: ${url}`));
}
const feedparser = new FeedParser();
const items = [];
feedparser.on('error', (e) => {
return reject(e);
}).on('readable', () => {
// This is where the action is!
var item;
console.time('loading')
while (item = feedparser.read()) {
items.push(item);
}
}).on('end', () => {
resolve({
meta: feedparser.meta,
records: items
});
});
request({
method: 'GET',
url: url
}, (e, res, body) => {
if (e) {
return reject(e);
} else if (res.statusCode != 200) {
return reject(new Error(`Bad status code (status: ${res.statusCode}, url: ${url})`));
}
feedparser.end(body);
feedparser.on('end', function () {
console.log('Done');
});
});
});
};
Promise.map([
'url',
'url',
'url',
'url'], (url) => fetch(url), { concurrency: 4 }) // note that concurrency limit
.then((feeds) => {
feeds.forEach(feed => {
feed.records.forEach(record => {
dataArray.push(record);
});
});
}).catch(function (error) {
console.log(error);
});
Post.remove({}, function (err) {
if (err) {
console.log(err);
} else {
console.log('collection removed');
}
});
dataArray.forEach(post => {
Post.create({
title: post.title,
content: post.description,
created: post.date,
image: post['rss:image']['#'],
link: post.link
}, function (err, newPost) {
console.log(newPost.title);
});
});
Post.find({}, function (err, posts) {
if (err) {
console.log(err);
} else {
res.render('index/home', {
posts: posts
});
}
});
});
module.exports = router;
Upvotes: 1
Views: 248
Reputation: 39462
None of this is going to run synchronously. You can do Something like this :
'use strict';
const Promise = require('bluebird');
const request = require('request');
const FeedParser = require('feedparser');
const express = require('express');
const router = express.Router();
const xray = require('x-ray')();
var Post = require('../models/post');
var dataArray = [];
const fetch;
router.get('/', function (req, res) {
Post.remove({}, function (err) {
if (err) {
console.log(err);
} else {
console.log('collection removed. Starting to fetch Posts from Service');
fetch = (url) => {
return new Promise((resolve, reject) => {
if (!url) {
return reject(new Error(`Bad URL (url: ${url}`));
}
const feedparser = new FeedParser();
const items = [];
feedparser.on('error', (e) => {
return reject(e);
}).on('readable', () => {
// This is where the action is!
var item;
console.time('loading')
while (item = feedparser.read()) {
items.push(item);
}
}).on('end', () => {
resolve({
meta: feedparser.meta,
records: items
});
});
request({
method: 'GET',
url: url
}, (e, res, body) => {
if (e) {
return reject(e);
} else if (res.statusCode != 200) {
return reject(new Error(`Bad status code (status: ${res.statusCode}, url: ${url})`));
}
feedparser.end(body);
feedparser.on('end', function () {
console.log('Done');
});
});
});
};
}
});
Promise.map([
'url',
'url',
'url',
'url'], (url) => fetch(url), { concurrency: 4 }) // note that concurrency limit
.then((feeds) => {
feeds.forEach(feed => {
dataArray = dataArray.concat(feed.records);
/*feed.records.forEach(record => {
dataArray.push(record);
});*/
});
console.log('inserting posts in the collection');
dataArray.forEach(post => {
Post.create({
title: post.title,
content: post.description,
created: post.date,
image: post['rss:image']['#'],
link: post.link
}, function (err, newPost) {
console.log(newPost.title);
});
});
console.log("Fetching posts from the collection");
Post.find({}, function (err, posts) {
if (err) {
console.log(err);
} else {
res.render('index/home', {
posts: posts
});
}
});
}).catch(function (error) {
console.log(error);
});
});
module.exports = router;
I haven't tested this. Please test it on your end. Let me know if there's an error or something.
Upvotes: 1