056c47581f
Ships the second dashboard surface — a Pattern Library + Preview Theatre — that presents the 4-section PDP pilot batch back to Umar, compliance, and the board in an editorial format. Adds the full data layer that drives it: 5 source-backed per-SKU drafts at QA 100/100, 15 competitor PDP semantic extracts, PubMed evidence packs, EFSA claims library extension, JV brand voice guide, hand-curated product FAQs, and the Matrixify-ready CSV exports for Lewis. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
125 lines
4.8 KiB
TypeScript
125 lines
4.8 KiB
TypeScript
#!/usr/bin/env bun
|
|
import { mkdirSync, writeFileSync } from 'fs'
|
|
import { dirname, join } from 'path'
|
|
|
|
const root = process.cwd()
|
|
const rawRoot = join(root, 'data', 'sources', 'apify', 'raw')
|
|
const token = Bun.env.APIFY_TOKEN || Bun.env.APIFY_API_TOKEN
|
|
const generatedAt = new Date().toISOString()
|
|
if (!token) throw new Error('Missing APIFY_TOKEN or APIFY_API_TOKEN')
|
|
|
|
const maxReviews = Number(Bun.env.APIFY_AMAZON_JUNGLEE_MAX_REVIEWS || 5)
|
|
const maxTotalChargeUsd = Number(Bun.env.APIFY_AMAZON_JUNGLEE_MAX_USD || 0.5)
|
|
const onlySkus = (Bun.env.APIFY_AMAZON_JUNGLEE_ONLY || '')
|
|
.split(',')
|
|
.map(value => value.trim())
|
|
.filter(Boolean)
|
|
|
|
const products = [
|
|
{
|
|
sku: 'JV-TURMERIC500',
|
|
asin: 'B009756A58',
|
|
url: 'https://www.amazon.co.uk/dp/B009756A58',
|
|
context: 'exact_jv_listing',
|
|
note: 'Exact ASIN from local DataForSEO asin-map.csv.'
|
|
},
|
|
{
|
|
sku: 'JV-DEFF1000',
|
|
asin: 'B09LR671LT',
|
|
url: 'https://www.amazon.co.uk/dp/B09LR671LT',
|
|
context: 'closest_effervescent_competitor',
|
|
note: 'Closest Amazon effervescent vitamin D competitor from local DataForSEO product search; not JV product truth.'
|
|
},
|
|
{
|
|
sku: 'JV-VISISOFT',
|
|
asin: 'B009756BHA',
|
|
url: 'https://www.amazon.co.uk/dp/B009756BHA',
|
|
context: 'exact_jv_listing',
|
|
note: 'Exact ASIN from local DataForSEO asin-map.csv.'
|
|
}
|
|
].filter(product => onlySkus.length === 0 || onlySkus.includes(product.sku))
|
|
|
|
if (!products.length) throw new Error('No products selected for Amazon review capture.')
|
|
|
|
function writeJson(path: string, data: any) {
|
|
mkdirSync(dirname(path), { recursive: true })
|
|
writeFileSync(path, JSON.stringify(data, null, 2) + '\n', 'utf8')
|
|
}
|
|
|
|
async function apify(path: string, options: RequestInit = {}) {
|
|
const sep = path.includes('?') ? '&' : '?'
|
|
const res = await fetch(`https://api.apify.com${path}${sep}token=${encodeURIComponent(token!)}`, {
|
|
...options,
|
|
headers: { 'Content-Type': 'application/json', ...(options.headers || {}) }
|
|
})
|
|
const text = await res.text()
|
|
let data: any
|
|
try { data = text ? JSON.parse(text) : null } catch { data = text }
|
|
if (!res.ok) throw new Error(`Apify ${res.status} ${res.statusText}: ${typeof data === 'string' ? data : JSON.stringify(data)}`)
|
|
return data
|
|
}
|
|
|
|
async function waitForRun(runId: string, timeoutMs = 1000 * 60 * 12) {
|
|
const started = Date.now()
|
|
let run = (await apify(`/v2/actor-runs/${runId}`)).data
|
|
while (!['SUCCEEDED', 'FAILED', 'ABORTED', 'TIMED-OUT'].includes(run.status)) {
|
|
if (Date.now() - started > timeoutMs) throw new Error(`Timed out waiting for ${runId}`)
|
|
await new Promise(resolve => setTimeout(resolve, 5000))
|
|
run = (await apify(`/v2/actor-runs/${runId}`)).data
|
|
console.log(`${runId}: ${run.status} usd=${run.usageTotalUsd || 0}`)
|
|
}
|
|
return run
|
|
}
|
|
|
|
const input = {
|
|
productUrls: products.map(product => ({ url: product.url })),
|
|
maxReviews,
|
|
includeGdprSensitive: false,
|
|
sort: 'recent',
|
|
filterByRatings: ['allStars'],
|
|
reviewsUseProductVariantFilter: false,
|
|
scrapeProductDetails: false,
|
|
reviewsAlwaysSaveCategoryData: true,
|
|
deduplicateRedirectedAsins: true
|
|
}
|
|
|
|
console.log(`Starting junglee/amazon-reviews-scraper for ${products.length} exact ASIN URLs, maxReviews=${maxReviews}, cap=$${maxTotalChargeUsd}`)
|
|
const start = await apify(`/v2/acts/junglee~amazon-reviews-scraper/runs?maxTotalChargeUsd=${maxTotalChargeUsd}`, {
|
|
method: 'POST',
|
|
body: JSON.stringify(input)
|
|
})
|
|
const run = await waitForRun(start.data.id)
|
|
const items = run.defaultDatasetId ? await apify(`/v2/datasets/${run.defaultDatasetId}/items?clean=true`) : []
|
|
const result = {
|
|
capturedAt: generatedAt,
|
|
job: 'amazon-reviews-junglee',
|
|
actor: 'junglee/amazon-reviews-scraper',
|
|
note: 'Capped Amazon review capture for exact ASINs only. JV-DEFF1000 is excluded because no exact ASIN is confirmed.',
|
|
maxTotalChargeUsd,
|
|
input,
|
|
productMap: products,
|
|
run: {
|
|
id: run.id,
|
|
status: run.status,
|
|
statusMessage: run.statusMessage,
|
|
defaultDatasetId: run.defaultDatasetId,
|
|
startedAt: run.startedAt,
|
|
finishedAt: run.finishedAt,
|
|
usageTotalUsd: run.usageTotalUsd,
|
|
usage: run.usage,
|
|
stats: run.stats,
|
|
chargedEventCounts: run.chargedEventCounts
|
|
},
|
|
itemCount: Array.isArray(items) ? items.length : 0,
|
|
items: Array.isArray(items) ? items.map((item: any) => {
|
|
const raw = JSON.stringify(item)
|
|
const matched = products.find(product => raw.includes(product.asin) || raw.includes(product.url))
|
|
return matched ? { ...item, sku: matched.sku, matchedAsin: matched.asin, matchContext: matched.context, matchNote: matched.note } : item
|
|
}) : items
|
|
}
|
|
|
|
const stamp = generatedAt.replace(/[:.]/g, '-')
|
|
writeJson(join(rawRoot, `top3-specialist-amazon-reviews-junglee-${stamp}.json`), result)
|
|
writeJson(join(rawRoot, 'top3-specialist-amazon-reviews-junglee-latest.json'), result)
|
|
console.log(`Amazon reviews junglee ${run.status}: ${result.itemCount} items, usd=${run.usageTotalUsd || 0}`)
|