【发布时间】:2019-07-25 04:29:58
【问题描述】:
我创建了一个脚本,用于从网页中抓取信息并将其写入 Google 表格。这在我的本地机器上运行良好,但我想在 GCP 上安排。
听起来云函数是要走的路,但是当我部署我的函数时,我收到了这个错误:
函数加载用户代码失败。错误消息:文件 working.js 定义的 Node.js 模块应导出名为 run 的函数
我不确定我应该使用什么作为“执行函数”。这是我上传的函数:
const puppeteer = require('puppeteer');
const jsonexport = require('jsonexport');
const GoogleSpreadsheet = require('google-spreadsheet');
const creds = require('./google-generated-creds.json');
const fs = require('fs');
var doc = new GoogleSpreadsheet('1qaFi0xnhaCZEduylUvGXWpyMJv00Rz6Y9qqyFR1E9oI');
function run() {
return new Promise(async (resolve, reject) => {
try {
const browser = await puppeteer.launch({args: ['--no-sandbox', '--disable-setuid-sandbox']});
const page = await browser.newPage();
const urls = [
"https://www.marksandspencer.com/pure-cotton-long-sleeve-jumpsuit/p/p60258655?image=SD_01_T42_6701_XB_X_EC_90&color=INDIGO&prevPage=plp",
"https://www.marksandspencer.com/cotton-rich-striped-3-4-sleeve-t-shirt/p/p60210598?prevPage=plp",
"https://www.marksandspencer.com/high-neck-long-sleeve-blouse/p/p60260040?image=SD_01_T43_5168_HD_X_EC_90&color=LIGHTDENIM&prevPage=plp",
"https://www.marksandspencer.com/pure-cotton-printed-short-sleeve-t-shirt/p/p60263529?image=SD_01_T41_8030Z_Z4_X_EC_90&color=WHITEMIX&prevPage=plp",
"https://www.marksandspencer.com/pure-cotton-button-detailed-denim-mini-skirt/p/p60260145?image=SD_01_T57_4004_QP_X_EC_90&color=DARKINDIGO&prevPage=plp",
"https://www.marksandspencer.com/pure-cotton-long-sleeve-shirt-midi-dress/p/p60258654?image=SD_01_T42_6703_HP_X_EC_90&color=DENIM&prevPage=plp",
"https://www.marksandspencer.com/mid-rise-skinny-leg-ankle-grazer-jeans/p/p60220155?prevPage=plp",
"https://www.marksandspencer.com/pure-cotton-long-sleeve-shirt/p/p60260208?image=SD_01_T43_5181_HP_X_EC_90&color=DENIM&prevPage=plp",
"https://www.marksandspencer.com/long-sleeve-shirt-mini-dress/p/p60258652?image=SD_01_T42_6704_HP_X_EC_90&color=DENIM&prevPage=plp",
"https://www.marksandspencer.com/wide-fit-suede-lace-up-trainers/p/p60216277?prevPage=plp",
"https://www.marksandspencer.com/suede-ankle-boots/p/p60226911?prevPage=plp",
"https://www.marksandspencer.com/leather-buckle-hip-belt/p/p60186701?prevPage=plp",
"https://www.marksandspencer.com/cross-body-bag/p/p60215352?prevPage=plp"
];
const productsList = [];
for (let i = 0; i < urls.length; i++) {
const url = urls[i];
await page.goto(url);
let products = await page.evaluate(() => {
let product = document.querySelector('h1[itemprop=name]').innerText;
let results = [];
let items = document.querySelectorAll('[data-ttip-id=sizeGridTooltip] tbody tr td label');
items.forEach((element) => {
let size = element.getAttribute('for');
let stockLevel = "";
let nearest_td = element.closest('td');
if (nearest_td.classList.contains('low-stock')) {
stockLevel = "Low stock"
} else if (nearest_td.classList.contains('out-of-stock')) {
stockLevel = "Out of stock"
} else {
stockLevel = "In stock"
}
results.push({
product: product,
size: size,
stock: stockLevel
})
});
return results
})
productsList.push(products)
}
browser.close();
function flatten(arr) {
return arr.reduce(function(flat, toFlatten) {
return flat.concat(Array.isArray(toFlatten) ? flatten(toFlatten) : toFlatten);
}, []);
}
var flatProducts = flatten(productsList)
flatProducts.forEach(function(row) {
// Authenticate with the Google Spreadsheets API.
doc.useServiceAccountAuth(creds, function(err) {
// Get all of the rows from the spreadsheet.
doc.addRow(1, row, function(err, rows) {
console.log(row);
});
});
});
} catch (e) {
return reject(e);
}
})
}
run().then(console.log).catch(console.error);
我以前从未使用过 Cloud Functions,所以不确定我需要修改多少脚本。
【问题讨论】:
标签: node.js google-cloud-platform google-cloud-functions puppeteer