我正在学习节点,表达,mongo,以及在此过程中,javascript。我正在尝试使用rssparser获取一个功能,获取故事列表并将其保存到mongoose的mongo数据库中。
我已经完成了RSS工作,我正在重复这些故事,这是我遇到问题的拯救。我想1)检查数据库中是否存在故事,2)如果没有,请保存。我想我在处理回调的过程中迷失了方向。这是我当前的代码,带有注释。
rssparser.parseURL(url, options, function(err,out){
// out.items is an array of the items pulled
var items = out.items;
var story;
for (var i=0; i<items.length; i++){
//create a mongoose story
story = new schemas.Stories({
title: items[i].title,
url: items[i].url,
summary: items[i].summary,
published: items[i].published_at
});
//TODO: for testing - these show up correctly.
//If I pull 10 stories, I get 10 entries from here that match
//So "story" is holding the current story
console.log("items[i] is :" + items[i].title);
console.log("story title is : " + story.title);
// setup query to see if it's already in db
var query = schemas.Stories.findOne({
"title" : story.title,
"url" : story.url
});
//execute the query
query.exec( function(err, row){
if(err) console.log("error-query: " + err);
console.log("row: "+ row);
if(!row) {
// not there, so save
console.log('about to save story.title: ' + story.title);
story.save(function (err){
console.log("error in save: " + err);
});
}
});
}
});
当这个运行时,我看到的是很多控制台输出:
它开始显示所有故事(许多省略):
items[i] is :TSA Drops Plan to Let Passengers Carry Small Knives on Planes
story title is : TSA Drops Plan to Let Passengers Carry Small Knives on Planes
items[i] is :BUILDING COLLAPSE:1 Reportedly Dead, 13 Pulled From Philly Rubble
story title is : BUILDING COLLAPSE:1 Reportedly Dead, 13 Pulled From Philly Rubble
items[i] is :CONTROVERSIAL PAST: Obama's UN Nominee Once Likened US 'Sins' to Nazis'
story title is : CONTROVERSIAL PAST: Obama's UN Nominee Once Likened US 'Sins' to Nazis'
items[i] is :WRITING OUT WRIGHTS: Bill Gives First Powered Flight Nod to Whitehead
story title is : WRITING OUT WRIGHTS: Bill Gives First Powered Flight Nod to Whitehead
items[i] is :BREAKING NEWS: Rice Named to Top Security Post Despite Libya Fallout
story title is : BREAKING NEWS: Rice Named to Top Security Post Despite Libya Fallout
然后继续像(许多省略):
row: null
about to save story.title: Best Ribs in America
row: null
about to save story.title: Best Ribs in America
row: null
about to save story.title: Best Ribs in America
row: null
about to save story.title: Best Ribs in America
row: null
about to save story.title: Best Ribs in America
row: null
about to save story.title: Best Ribs in America
row: { title: 'Best Ribs in America',
url: 'http://www.foxnews.com/leisure/2013/06/05/10-best-ribs-in-america/',
published: 1370463800000,
_id: 51af9f881995d40425000023,
__v: 0 }
它重复了“即将保存”标题(这是Feed中的最后一个故事),它会像上一行一样保存故事。
console.log输出显示我把它放在顶部的所有故事标题输出,然后是底部的query.exec()调用内的所有内容。
感谢任何帮助...
答案 0 :(得分:2)
这个问题是exec回调中引用的故事将被设置为for循环中迭代的最后一件事,一旦回调将被执行,因为所有执行的函数都引用相同的变量的实例。
解决这个问题的最简单方法是简单地将for循环中的每个东西包装在您使用参数立即执行的函数中,如:
rssparser.parseURL(url, options, function(err,out){
// out.items is an array of the items pulled
var items = out.items;
for (var i=0; i<items.length; i++){
(function(item) {
//create a mongoose story
var story = new schemas.Stories({
title: item.title,
url: item.url,
summary: item.summary,
published: item.published_at
});
// setup query to see if it's already in db
var query = schemas.Stories.findOne({
"title" : story.title,
"url" : story.url
});
//execute the query
query.exec( function(err, row){
if(err) console.log("error-query: " + err);
console.log("row: "+ row);
if(!row) {
// not there, so save
console.log('about to save story.title: ' + story.title);
story.save(function (err){
console.log("error in save: " + err);
});
}
});
})(items[i]);
}
});
我没有测试过这个,但我相信你会发现它会解决你的问题
另一种更简单,更简洁,更好的方法是迭代数组上forEach循环中的项目,如果你的平台支持(node.js那样做) - 这个版本更漂亮:
rssparser.parseURL(url, options, function(err,out){
// out.items is an array of the items pulled
out.items.forEach(function(item) {
//create a mongoose story
var story = new schemas.Stories({
title: item.title,
url: item.url,
summary: item.summary,
published: item.published_at
});
// setup query to see if it's already in db
var query = schemas.Stories.findOne({
"title" : story.title,
"url" : story.url
});
//execute the query
query.exec( function(err, row){
if(err) console.log("error-query: " + err);
console.log("row: "+ row);
if(!row) {
// not there, so save
console.log('about to save story.title: ' + story.title);
story.save(function (err){
console.log("error in save: " + err);
});
}
});
});
});
答案 1 :(得分:2)
好吧,节点是事件驱动的服务器,javascript也是事件驱动的,所以你可以异步调用东西。
你需要使用一些异步模式来做你想做的事。
首先,如果您使用mongoose,您可以利用它的架构类来检查已存在的项目,而无需再次查询数据库:
var mongoose = require('mongoose');
var schema = new mongoose.Schema({
title: String,
url: { type: String, unique: true },
summary: String,
published: Date
})
var model = mongoose.model('stories', schema)
网址是唯一的,因此保存会导致重复错误,猫鼬不会保存查询。
现在要遍历项目并保存每个项目我们需要某种模式,幸运的是我们有async:
var async = require('async');
rssparser.parseURL(url, options, function(err, out){
async.each(out.items, function(item, callback){
var m = new model({
title: item.title,
url: item.url,
summary: item.summary,
published: item.published_at
})
m.save(function(err, result){
callback(null)
});
}, function(err){
//we complete the saving we can do stuff here
});
}
我们在并行模式下使用async,因为我们不关心某些是否重复。 你也可以用一个数组跟踪它,你可以推送它错误的||结果如此 你可以看到你保存了多少项。