我想获取价格和卖家数据，但我只获取第一行，为什么？我正在尝试学习js，但在这里我花了很多时间，请帮助。我从不同的站点获取代码并根据我的要求修改它，但仍然无法正常工作Puppeteer js、nodejsvar url = 'https://www.amazon.co.uk/gp/offer-listing/3770436385/ref=olp_f_used?ie=UTF8&f_new=true&f_usedAcceptable=true&f_usedGood=true&f_used=true&f_usedLikeNew=true&f_usedVeryGood=true';const puppeteer = require('puppeteer');(async function main(){ try{ const browser = await puppeteer.launch({headless: false }); const page = await browser.newPage(); page.setUserAgent('Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) HeadlessChrome/67.0.3372.0 Safari/537.36'); await page.goto(url); await page.waitForSelector('div.navFooterLine:nth-child(6)'); const sections = await page.$$('.olpOffer'); console.log(sections.length); for (const section of sections){ const result = await page.evaluate(() => { // let amaOffer = document.querySelector('#olpOfferList img').innerText; // let amaPrice = document.querySelector('#olpOfferList img').innerText; let seller = document.querySelector('.a-text-bold a').innerText; let price = document.querySelector('.olpOfferPrice').innerText; return { // amaOffer, seller, price } } ) console.log(result); } } catch (e) { console.log('Our error', e); }})();
2 回答
qq_笑_17
TA贡献1818条经验 获得超7个赞
你基本上是这样做的：
for (const section of sections) {
const result = someValue;
console.log(result);
}
因此，您只是result在循环中的 over 上声明了一个新变量，而不是将每个单独的结果累积到一个数组中，这样您就可以获得所有结果。
不是 100% 清楚您想要结果的位置，但您至少可以将它们累积到这样的数组中：
(async function main() {
try {
const browser = await puppeteer.launch({headless: false});
const page = await browser.newPage();
page.setUserAgent('Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3372.0 Safari/537.36');
await page.goto(url);
await page.waitForSelector('div.navFooterLine:nth-child(6)');
const sections = await page.$$('.olpOffer');
console.log(sections.length);
let results = [];
for (const section of sections) {
const result = await page.evaluate(() => {
// let amaOffer = document.querySelector('#olpOfferList img').innerText;
// let amaPrice = document.querySelector('#olpOfferList img').innerText;
let seller = document.querySelector('.a-text-bold a').innerText;
let price = document.querySelector('.olpOfferPrice').innerText;
return {
// amaOffer,
seller,
price
}
});
console.log(result);
results.push(result);
}
// see all results here
console.log(results);
return results;
} catch (e) {
console.log('Our error', e);
}
})();
互换的青春
TA贡献1797条经验 获得超6个赞
我知道问题出在哪里。
Puppeteer JS 在两个引擎中运行 javascript，两者的作用域不同，所以我们需要将
section数字传递给page.evaluate亚马逊网站显示亚马逊产品的结果，选择器没有选择正确的产品，所以我将其更改为
.olpSellerName我添加了一些改进以使脚本运行得更快。
希望这能有所帮助。
let url = 'https://www.amazon.co.uk/gp/offer-listing/3770436385/ref=olp_f_used?ie=UTF8&f_new=true&f_usedAcceptable=true&f_usedGood=true&f_used=true&f_usedLikeNew=true&f_usedVeryGood=true'
let chromeUA = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3372.0 Safari/537.36'
const puppeteer = require('puppeteer')
;(async function main() {
try {
const browser = await puppeteer.launch({headless: false})
const page = (await browser.pages())[0]
page.setUserAgent(chromeUA)
page.setDefaultNavigationTimeout(0)
page.setRequestInterception(true)
page.on('request', async request => {
if (
request.resourceType() === 'image' ||
request.resourceType() === 'media' ||
request.resourceType() === 'script' ||
request.resourceType() === 'stylesheet' ||
request.resourceType() === 'font' ||
request.resourceType() === 'other'
) {
request.abort()
} else {
request.continue()
}
})
await page.goto(url)
await page.waitForSelector('div.navFooterLine:nth-child(6)')
const sections = await page.$$('.olpOffer')
let results = []
for (let num = 0; num < sections.length; num++) {
let result = await page.evaluate( (num) => {
let seller = document.querySelectorAll('.olpSellerName')[num].innerText
let price = document.querySelectorAll('.olpOfferPrice')[num].innerText
return {
// amaOffer,
seller,
price
}
}, num)
results.push(result)
}
// see all results here
console.log(results)
return results
} catch (e) {
console.log('Our error', e);
}
})()
我还有一个问题：
我想为不同的亚马逊网站循环
let AmazonSites = ['de','co.uk','ca'];
for(AmazonSite of AmazonSites){
let url = 'https://www.amazon.'+ AmazonSite +'/gp/offer-listing/'+ Asin +'/ref=olp_f_used?ie=UTF8&f_new=true&f_usedAcceptable=true&f_usedGood=true&f_used=true&f_usedLikeNew=true&f_usedVeryGood=true';
await page.goto(url)
因此，您可以通过 for 循环重复脚本来发出多个请求
let domains = ['co.uk', 'de', 'ca']
let url = 'https://www.amazon.tld/gp/offer-listing/3770436385/ref=olp_f_used?ie=UTF8&f_new=true&f_usedAcceptable=true&f_usedGood=true&f_used=true&f_usedLikeNew=true&f_usedVeryGood=true'
let chromeUA = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3372.0 Safari/537.36'
const puppeteer = require('puppeteer')
;(async function main() {
try {
const browser = await puppeteer.launch({headless: false})
const page = (await browser.pages())[0]
page.setUserAgent(chromeUA)
page.setDefaultNavigationTimeout(0)
page.setRequestInterception(true)
page.on('request', async request => {
if ( request.resourceType() === 'document' ) {
request.continue()
} else {
request.abort()
}
})
for (let tld in domains) {
await page.goto(url.replace('tld', domains[tld]))
await page.waitForSelector('div.navFooterLine:nth-child(6)')
const sections = await page.$$('.olpOffer')
let results = []
for (let num = 0; num < sections.length; num++) {
let result = await page.evaluate( (num) => {
let seller = document.querySelectorAll('.olpSellerName')[num].innerText
let price = document.querySelectorAll('.olpOfferPrice')[num].innerText
return {
// amaOffer,
seller,
price
}
}, num)
results.push(result)
}
// see all results here
console.log (`\n\nRESULT FOR DOMAIN TLD : www.amazon.${domains[tld]}`)
console.log(results)
}
await browser.close()
} catch (e) {
console.log('Our error', e);
}
})()
添加回答
举报
0/150
提交
取消