如何在Node.js中按顺序发送许多http请求？

Question

I am creating a crawler using Node.js.

In the target web page, there are 10+ categories.

I can get them using my crawler.

And I make requests for each category. (10+ requests)

Then, each category page has 100+ items.

And I make requests for each item. (100+ requests)

So I need 10+ * 100+ requests!

My code is here.

const axios = require("axios")
const cheerio = require("cheerio");

async function request(url) {
    return await axios.get(url);
}

function main() {
    request(url).then(html => {
        const $ = cheerio.load(html.data);
        const categoryArray = $('table.table tbody').children('tr').toArray()

        categoryArray.map(category => {
            console.log("category: " + category.name)

            request(category.url).then( html => {
                const $ = cheerio.load(html.data);
                const items = $('table.table tbody').children('tr').toArray()

                console.log("item.length: " + items.length)

                items.map(item => {
                    request(item).then(html => {
                        const $ = cheerio.load(html.data);
                        const itemDetails = $('table.table tbody').children('tr').toArray()

                        console.log("item.name: " + itemDetails.name)
                    })
                })
            })
        })
    })
}

But it doesn't work...

The console.log looks like:

category: A
category: B
category: C
category: D
category: E
category: F
category: G
category: H
category: I
category: J
category: K
category: L
category: M
category: N
item.length: 0
item.length: 100
item.length: 100
item.length: 0
item.length: 100
item.length: 0
item.length: 0
item.length: 100
item.length: 0
item.length: 0
item.length: 0
item.length: 0
item.length: 0
item.length: 0
item.name: item1
(node:5409) UnhandledPromiseRejectionWarning: Unhandled promise rejection. This error originated either by throwing inside of an async function without a catch block, or by rejecting a promise which was not handled with .catch(). (rejection id: 2)
(node:5409) [DEP0018] DeprecationWarning: Unhandled promise rejections are deprecated. In the future, promise rejections that are not handled will terminate the Node.js process with a non-zero exit code.

At the first time, it looks like working fine, but after some seconds, doesn't work.

I think that "categoryArray.map" doesn't wait for children's requests.

So the HTTP connection thread number is up to maximum.

I don't know how to fix it...

Answer 1

Your problem is that Array.prototype.map is not Promise -aware, so it can't wait for your requests.

Instead of using map , simply use async / await and iterate arrays using for ... of :

async function main() {
    const categoryArray = await request(categoryUrl)
    for (const category of categoryArray) {
        console.log("category: " + category.name)

        const items = await request(category.url)
        console.log("item.length: " + items.length)

        for (const item of items) {
            const itemDetails = await request(item)
            console.log("item.name: " + itemDetails.name)
        }
    }
}