【发布时间】:2017-11-28 16:37:10
【问题描述】:
我在 Node.js 中玩 Cheerio。我有一个刮板,它会进入文章列表,抓取所有文章 URL,然后转到每篇文章并刮掉标题和 URL。一切正常,除了当我尝试将结果更新到我的 Mongodb 时,我得到未定义。
我假设它在定义值之前尝试更新插入......但即使使用 Request-Response 我也无法让它工作。任何帮助将不胜感激!由于代码不是太长,我将粘贴整个内容,以便更容易看到我正在尝试做什么。同样,主要问题是让upsertArticle 实际插入变量。
const request = require('request');
const cheerio = require('cheerio');
const rp = require('request-promise');
const mongoose = require('mongoose');
const Article = require('./models/article');
var urls = [];
//get the list of articles to scrape
rp('https://www.somesite.com/', function(error, response, html) {
if (!error && response.statusCode == 200) {
var $ = cheerio.load(html);
$('.c-entry-box--compact__title').each(function(i, element) {
var a = $(this);
urls.push(a.children().attr('href'));
}); } })
//scrape over each article individually
.then(function(getStuff) {
var arrayLength = urls.length;
//get the list of articles to scrape and upsert each one
for (var i = 0; i < arrayLength; i++) {
const result = rp(urls[i], function(error, response, html) {
if (!error && response.statusCode == 200) {
var $ = cheerio.load(html);
var parsedResults = [];
$('.l-main-content').each(function(n, element) {
var a = $(this);
var title = a.find('.c-page-title').text();
var url = response.request.uri.href;
//I also tried upserting the variables right here, that didn't work
return { title, url };
});
} else {console.log(error);}
}).then(function(upsertStuff) {
//also tried returning and upserting stuff here... but nothing gets upserted
upsertArticle({
title: result.title,
source: result.url,
dateCrawled: new Date()
});
console.log('Upserted ' + result.title);
}).catch(function(err) {console.log(err); }); }
}) .catch(function(err) {console.log(err); });
function upsertArticle(userObj) {
const DB_URL = 'mongodb://localhost/articles';
if (mongoose.connection.readyState == 0) {
mongoose.connect(DB_URL, {
useMongoClient: true
});
}
let conditions = {
title: userObj.title
};
let options = {
upsert: true,
new: true,
setDefaultsOnInsert: true
};
Article.findOneAndUpdate(conditions, userObj, options, (err, result) => {
if (err) throw err;
});
}
【问题讨论】:
标签: javascript node.js mongodb response cheerio