为《木偶演员》改编web scraper JavaScript代码

我几乎没有编码知识，我正在尝试改编一些教程，但没有成功

我希望修改的JavaScript代码（脚本A）被粘贴到Chrome开发者控制台中，并成功地提取了我需要的数据。此JavaScript代码段标识了电子商务站点中最大的价格图形

第二个教程（脚本B）从shell中运行，并调用puppeter库。此脚本提取一些酒店预订数据并成功运行

我希望使用Puppeter库使脚本A从shell运行

这是一个脚本-

let elements = [
 ...document.querySelectorAll(' body *')
]

function createRecordFromElement(element) {
 const text = element.textContent.trim()
 var record = {}
 const bBox = element.getBoundingClientRect()

if(text.length <= 30 && !(bBox.x == 0 && bBox.y == 0)) {
 record['fontSize'] = parseInt(getComputedStyle(element)['fontSize']) } 
 record['y'] = bBox.y 
 record['x'] = bBox.x 
 record['text'] = text 
 return record 
} 
let records = elements.map(createRecordFromElement) 

function canBePrice(record) { 
 if( record['y'] > 600 ||
  record['fontSize'] == undefined ||
  !record['text'].match(/(^(US ){0,1}(rs\.|Rs\.|RS\.|\$|₹|INR|USD|CAD|C\$){0,1}(\s){0,1}[\d,]+(\.\d+){0,1}(\s){0,1}(AED){0,1}$)/)
)
 return false
 else return true
}

let possiblePriceRecords = records.filter(canBePrice)
let priceRecordsSortedByFontSize = possiblePriceRecords.sort(function(a, b) {
if (a['fontSize'] == b['fontSize']) return a['y'] > b['y']
return a['fontSize'] < b['fontSize']

})
console.log(priceRecordsSortedByFontSize[0]['text']);console.log(priceRecordsSortedByFontSize[1]['text']);

我曾多次尝试将脚本A改编成脚本B的格式。出现了各种各样的错误。如果没有编码知识，我将一事无成

这是我尝试过的众多变体之一，称为脚本C-

const puppeteer = require('puppeteer-core');

let bookingUrl = 'https://shop.coles.com.au/a/dianella/product/moccona-coffee-capsules-espresso-7';
(async () => {
    const browser = await puppeteer.launch({
        executablePath: '/usr/bin/chromium-browser',
        headless: true
        });
    const page = await browser.newPage();
    await page.setViewport({ width: 1920, height: 926 });
    await page.goto(bookingUrl);

    // get hotel details
    let hotelData = await page.evaluate(() => {
        let hotels = [];
        // get the hotel elements
        let elements = [
 ...document.querySelectorAll(' body *')
]

function createRecordFromElement(element) {
 const text = element.textContent.trim()
 var record = {}
 const bBox = element.getBoundingClientRect()

if(text.length <= 30 && !(bBox.x == 0 && bBox.y == 0)) {
 record['fontSize'] = parseInt(getComputedStyle(element)['fontSize']) } 
 record['y'] = bBox.y 
 record['x'] = bBox.x 
 record['text'] = text 
 return record 
} 
let records = elements.map(createRecordFromElement) 

function canBePrice(record) { 
 if( record['y'] > 600 ||
  record['fontSize'] == undefined ||
  !record['text'].match(/(^(US ){0,1}(rs\.|Rs\.|RS\.|\$|₹|INR|USD|CAD|C\$){0,1}(\s){0,1}[\d,]+(\.\d+){0,1}(\s){0,1}(AED){0,1}$)/)
)
 return false
 else return true
}

let possiblePriceRecords = records.filter(canBePrice)
let priceRecordsSortedByFontSize = possiblePriceRecords.sort(function(a, b) {
if (a['fontSize'] == b['fontSize']) return a['y'] > b['y']
return a['fontSize'] < b['fontSize']

})
console.log(priceRecordsSortedByFontSize[0]['text']);
})();

const puppeter=require（'puppeter-core'）；
让我们预订吧https://shop.coles.com.au/a/dianella/product/moccona-coffee-capsules-espresso-7';
（异步（）=>{
const browser=wait puppeter.launch({
可执行路径：'/usr/bin/chromium browser'，
无头：是的
});
const page=wait browser.newPage（）；
等待page.setViewport（{宽度：1920，高度：926}）；
等待页面。转到（bookingUrl）；
//获取酒店详细信息
让hotelData=wait page.evaluate（（）=>{
让酒店=[]；
//获取酒店元素
设元素=[
…document.querySelectorAll（'body*'））
]
函数createRecordFromElement（元素）{
const text=element.textContent.trim（）
var记录={}
const bBox=element.getBoundingClientRect（）
如果（文本长度600||
记录['fontSize']==未定义||
！record['text'].match（/（^（US）{0,1}（rs\.| rs\.| rs\.）|\$|₹|印度卢比{0,1}（\s）{0,1}[\d，]+（\.\d+{0,1}（\s）{0,1}（AED）{0,1}/）
)
返回错误
否则返回true
}
let possiblePriceRecords=records.filter（canBePrice）
让PriceRecordsOrderedByFontSize=possiblePriceRecords.sort（函数（a，b）{
如果（a['fontSize']==b['fontSize']）返回a['y']>b['y']
返回a['fontSize']

以下是教程的链接以获取信息-

---

脚本C中是否有任何明显的错误？

阅读脚本C后，您似乎没有犯任何错误，而您试图访问的网站决定阻止scraper Bot

在域上快速查找主机表明，他们正在使用security service section.io阻止其网站上的刮板机器人。请参阅：

shop.coles.com.au是shop.coles.com.au.c.section.io的别名。

---

shop.coles.com.au.c.section.io是shop.coles.com.au.x.section.io的别名

感谢您查看代码。我没想到他们会阻止机器人！

const puppeteer = require('puppeteer-core');

let bookingUrl = 'https://shop.coles.com.au/a/dianella/product/moccona-coffee-capsules-espresso-7';
(async () => {
    const browser = await puppeteer.launch({
        executablePath: '/usr/bin/chromium-browser',
        headless: true
        });
    const page = await browser.newPage();
    await page.setViewport({ width: 1920, height: 926 });
    await page.goto(bookingUrl);

    // get hotel details
    let hotelData = await page.evaluate(() => {
        let hotels = [];
        // get the hotel elements
        let elements = [
 ...document.querySelectorAll(' body *')
]

function createRecordFromElement(element) {
 const text = element.textContent.trim()
 var record = {}
 const bBox = element.getBoundingClientRect()

if(text.length <= 30 && !(bBox.x == 0 && bBox.y == 0)) {
 record['fontSize'] = parseInt(getComputedStyle(element)['fontSize']) } 
 record['y'] = bBox.y 
 record['x'] = bBox.x 
 record['text'] = text 
 return record 
} 
let records = elements.map(createRecordFromElement) 

function canBePrice(record) { 
 if( record['y'] > 600 ||
  record['fontSize'] == undefined ||
  !record['text'].match(/(^(US ){0,1}(rs\.|Rs\.|RS\.|\$|₹|INR|USD|CAD|C\$){0,1}(\s){0,1}[\d,]+(\.\d+){0,1}(\s){0,1}(AED){0,1}$)/)
)
 return false
 else return true
}

let possiblePriceRecords = records.filter(canBePrice)
let priceRecordsSortedByFontSize = possiblePriceRecords.sort(function(a, b) {
if (a['fontSize'] == b['fontSize']) return a['y'] > b['y']
return a['fontSize'] < b['fontSize']

})
console.log(priceRecordsSortedByFontSize[0]['text']);
})();