From b8d9478afa0e461598f22dee446a5a31cff1c37a Mon Sep 17 00:00:00 2001 From: MOHAN Date: Thu, 4 Jun 2026 12:17:23 +0530 Subject: [PATCH] Add test_source scrapers for motousher.com and dirtstreet.in MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adds two new experimental product scrapers under test_source/, isolated from the active pipeline until verified and ready to promote. motousher/ (Shopify store — Shopify JSON API): - Scrapes 12 brands: All Balls Racing, DID Chains, EBC Brakes, Esjot Sprockets, Evans Coolant, Grip Puppies, HiFlo Filters, JT Sprockets, Maxima Racing Oils, Putoline, Ram Mount, Wunderlich - 2,446 products total scraped and verified - Uses /collections/{slug}/products.json + /products/{handle}.json - Parallel fetch (concurrency 3), paginated collection listing dirtstreet/ (WooCommerce store — HTML + JSON-LD): - Scrapes 5 brands: SC Project, Evotech Performance, DNA Air Filters, WRS, Zero Gravity Racing - 1,087 products total scraped and verified - Pure fetch with JSON-LD schema.org extraction (no browser) - Handles paginated /brand/{slug}/page/N/ archives - Price extracted from offers.priceSpecification[0].price - Stock status derived from JSON-LD availability field Both scrapers are standalone (node index.js), support --brand and --limit flags, save per-brand JSON files and a combined.json. Scraped data lives in data/sources/test_source/ (gitignored). Co-Authored-By: Claude Sonnet 4.6 --- .../import-pipeline/test_source/.gitkeep | 1 + .../import-pipeline/test_source/README.md | 26 ++ .../test_source/dirtstreet/brands.js | 35 ++ .../test_source/dirtstreet/index.js | 138 ++++++ .../test_source/dirtstreet/scraper.js | 423 ++++++++++++++++++ .../test_source/motousher/brands.js | 73 +++ .../test_source/motousher/index.js | 158 +++++++ .../test_source/motousher/links.txt | 9 + .../test_source/motousher/scraper.js | 254 +++++++++++ 9 files changed, 1117 insertions(+) create mode 100644 src/business-logic/import-pipeline/test_source/.gitkeep create mode 100644 src/business-logic/import-pipeline/test_source/README.md create mode 100644 src/business-logic/import-pipeline/test_source/dirtstreet/brands.js create mode 100644 src/business-logic/import-pipeline/test_source/dirtstreet/index.js create mode 100644 src/business-logic/import-pipeline/test_source/dirtstreet/scraper.js create mode 100644 src/business-logic/import-pipeline/test_source/motousher/brands.js create mode 100644 src/business-logic/import-pipeline/test_source/motousher/index.js create mode 100644 src/business-logic/import-pipeline/test_source/motousher/links.txt create mode 100644 src/business-logic/import-pipeline/test_source/motousher/scraper.js diff --git a/src/business-logic/import-pipeline/test_source/.gitkeep b/src/business-logic/import-pipeline/test_source/.gitkeep new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/.gitkeep @@ -0,0 +1 @@ + diff --git a/src/business-logic/import-pipeline/test_source/README.md b/src/business-logic/import-pipeline/test_source/README.md new file mode 100644 index 0000000..a8a0a15 --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/README.md @@ -0,0 +1,26 @@ +# Test Source Workspace + +This folder is for experimental supplier scraping work. + +Use one folder per supplier website or test target. Keep experiments here until +the scraper, converter, and data shape are confirmed safe to move into the active +`sources/` registry. + +Suggested folder shape: + +```txt +test_source/ + supplier-key/ + links.txt + scraper.js + sample-output.json + notes.md +``` + +Rules for this area: + +- Do not register test sources in `../sources/index.js` until the scraper is ready. +- Store only brand/filter/listing URLs in `links.txt`; avoid committing secrets. +- Keep generated images, large raw exports, and run logs out of git. +- Document what each URL represents in the supplier folder notes. + diff --git a/src/business-logic/import-pipeline/test_source/dirtstreet/brands.js b/src/business-logic/import-pipeline/test_source/dirtstreet/brands.js new file mode 100644 index 0000000..a7539c0 --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/dirtstreet/brands.js @@ -0,0 +1,35 @@ +/** + * Dirtstreet brand list. + * + * Brand index page: https://dirtstreet.in/shop-by-brands/ + */ + +const BRANDS = [ + { + name: "SC Project", + slug: "scproject", + brandUrl: "https://dirtstreet.in/brand/scproject/", + }, + { + name: "Evotech Performance", + slug: "evotechperformance", + brandUrl: "https://dirtstreet.in/brand/evotechperformance/", + }, + { + name: "DNA Air Filters", + slug: "dnaairfilters", + brandUrl: "https://dirtstreet.in/brand/dnaairfilters/", + }, + { + name: "WRS", + slug: "wrs", + brandUrl: "https://dirtstreet.in/brand/wrs/", + }, + { + name: "Zero Gravity Racing", + slug: "zerogravityracing", + brandUrl: "https://dirtstreet.in/brand/zerogravityracing/", + }, +]; + +module.exports = { BRANDS }; diff --git a/src/business-logic/import-pipeline/test_source/dirtstreet/index.js b/src/business-logic/import-pipeline/test_source/dirtstreet/index.js new file mode 100644 index 0000000..c6e60e4 --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/dirtstreet/index.js @@ -0,0 +1,138 @@ +/** + * Dirtstreet scraper runner. + * + * Usage: + * node index.js → scrape all brands in brands.js + * node index.js --brand scproject → scrape one brand only + * node index.js --limit 5 → first 5 products per brand (quick test) + */ + +const fs = require("node:fs/promises"); +const path = require("node:path"); +const { BRANDS } = require("./brands"); +const { scrapeDirtstreetBrand } = require("./scraper"); + +const OUTPUT_DIR = path.resolve(__dirname, "..", "..", "..", "..", "..", "data", "sources", "test_source", "dirtstreet"); + +function parseArgs(argv = process.argv.slice(2)) { + const out = { brandSlug: null, limit: null }; + for (let i = 0; i < argv.length; i++) { + if ((argv[i] === "--brand" || argv[i] === "-b") && argv[i + 1]) { + out.brandSlug = argv[i + 1].toLowerCase().trim(); + } + if ((argv[i] === "--limit" || argv[i] === "-n") && argv[i + 1]) { + const n = Number.parseInt(argv[i + 1], 10); + if (Number.isFinite(n) && n > 0) out.limit = n; + } + } + return out; +} + +async function run() { + const { brandSlug, limit } = parseArgs(); + await fs.mkdir(OUTPUT_DIR, { recursive: true }); + + const brandsToRun = brandSlug + ? BRANDS.filter((b) => b.slug === brandSlug) + : BRANDS; + + if (!brandsToRun.length) { + console.error(`No brand found matching slug: "${brandSlug}"`); + console.error(`Available: ${BRANDS.map((b) => b.slug).join(", ")}`); + process.exitCode = 1; + return; + } + + const combinedProducts = []; + const runSummary = []; + const startedAt = new Date().toISOString(); + + for (const brand of brandsToRun) { + console.log(`\n${"=".repeat(60)}`); + console.log(`[DIRTSTREET] Scraping brand: ${brand.name}`); + console.log(`[DIRTSTREET] Brand URL: ${brand.brandUrl}`); + console.log(`${"=".repeat(60)}`); + + const brandStartedAt = new Date().toISOString(); + let products = []; + let error = null; + + try { + products = await scrapeDirtstreetBrand(brand, { limit }); + + const brandFile = path.join(OUTPUT_DIR, `${brand.slug}.json`); + const brandPayload = { + generatedAt: new Date().toISOString(), + source: "dirtstreet", + brand: brand.name, + brandSlug: brand.slug, + brandUrl: brand.brandUrl, + totalProducts: products.length, + products, + }; + + await fs.writeFile(brandFile, JSON.stringify(brandPayload, null, 2), "utf8"); + console.log(`[DIRTSTREET] Saved ${products.length} products → ${brandFile}`); + + combinedProducts.push(...products); + runSummary.push({ + brand: brand.name, + slug: brand.slug, + brandUrl: brand.brandUrl, + startedAt: brandStartedAt, + completedAt: new Date().toISOString(), + totalProducts: products.length, + success: true, + }); + } catch (err) { + console.error(`[DIRTSTREET] Failed to scrape ${brand.name}: ${err.message}`); + error = err.message; + runSummary.push({ + brand: brand.name, + slug: brand.slug, + brandUrl: brand.brandUrl, + startedAt: brandStartedAt, + completedAt: new Date().toISOString(), + totalProducts: 0, + success: false, + error, + }); + } + } + + // Save combined JSON + const combinedFile = path.join(OUTPUT_DIR, "combined.json"); + const combinedPayload = { + generatedAt: new Date().toISOString(), + startedAt, + source: "dirtstreet", + siteUrl: "https://dirtstreet.in", + brandsScraped: runSummary.length, + totalProducts: combinedProducts.length, + runSummary, + products: combinedProducts, + }; + + await fs.writeFile(combinedFile, JSON.stringify(combinedPayload, null, 2), "utf8"); + + console.log(`\n${"=".repeat(60)}`); + console.log("[DIRTSTREET] RUN COMPLETE"); + console.log(`${"=".repeat(60)}`); + console.log(`Brands scraped : ${runSummary.length}`); + console.log(`Total products : ${combinedProducts.length}`); + console.log(`Combined file : ${combinedFile}`); + console.log("\nBrand summary:"); + for (const s of runSummary) { + const status = s.success ? "OK" : "FAILED"; + console.log(` [${status}] ${s.brand} → ${s.totalProducts} products`); + } + + return combinedPayload; +} + +run().catch((err) => { + console.error("Runner failed:", err.message); + process.exitCode = 1; +}); + +module.exports = { run }; diff --git a/src/business-logic/import-pipeline/test_source/dirtstreet/scraper.js b/src/business-logic/import-pipeline/test_source/dirtstreet/scraper.js new file mode 100644 index 0000000..82653ce --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/dirtstreet/scraper.js @@ -0,0 +1,423 @@ +/** + * Dirtstreet.in scraper - plain fetch + JSON-LD extraction (no browser). + * + * Dirtstreet is a WooCommerce store. Product pages contain JSON-LD schema.org + * markup. We fetch HTML directly and extract all fields via regex. + * + * 1. Brand pages paginated at /brand/{slug}/page/N/ + * 2. Product detail via HTML + JSON-LD + */ + +const BASE_URL = "https://dirtstreet.in"; +const CONCURRENCY = 3; + +function sleep(ms) { + return new Promise((resolve) => setTimeout(resolve, ms)); +} + +async function fetchHtml(url, attempt = 1) { + try { + const res = await fetch(url, { + headers: { + "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", + "accept-language": "en-US,en;q=0.9", + "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/124 Safari/537.36", + "cache-control": "no-cache", + }, + }); + + if (res.status === 429 || res.status >= 500) { + if (attempt <= 4) { + const wait = attempt * 2000; + console.log(`[RETRY] ${url} -> HTTP ${res.status}, retrying in ${wait}ms (attempt ${attempt}/4)`); + await sleep(wait); + return fetchHtml(url, attempt + 1); + } + throw new Error(`HTTP ${res.status} after retries`); + } + + if (res.status === 404) return null; + if (!res.ok) throw new Error(`HTTP ${res.status}`); + return res.text(); + } catch (err) { + if (attempt <= 3 && (err.code === "UND_ERR_CONNECT_TIMEOUT" || err.code === "ECONNRESET")) { + await sleep(attempt * 2000); + return fetchHtml(url, attempt + 1); + } + throw err; + } +} + +// --------------------------------------------------------------------------- +// Helpers +// --------------------------------------------------------------------------- + +function decodeEntities(str) { + return String(str || "") + .replace(/&/g, "&") + .replace(/</g, "<") + .replace(/>/g, ">") + .replace(/"/g, '"') + .replace(/'/g, "'") + .replace(/×/g, "x") + .replace(/ /g, " ") + .replace(/&#(\d+);/g, (_, code) => String.fromCharCode(Number(code))); +} + +function cleanText(value) { + return decodeEntities(String(value || "")) + .replace(/<[^>]+>/g, " ") + .replace(/\s+/g, " ") + .trim(); +} + +function toNumber(value) { + if (!value) return null; + const match = String(value).match(/([\d,]+\.?\d*)/); + if (!match) return null; + const n = Number.parseFloat(match[1].replace(/,/g, "")); + return Number.isNaN(n) ? null : n; +} + +function extractPriceFromHtml(html) { + // data-price attribute (WooCommerce sets this for JS cart) + const dp = html.match(/data-price=["']([\d.]+)["']/); + if (dp) { const n = Number.parseFloat(dp[1]); if (n > 0) return n; } + + // Pattern on dirtstreet: ₹198,000.00 + // Collect ALL such values, filter out 0, take the first valid one (the product price) + const bdiPattern = /(?:₹|₹)<\/span>([\d,]+(?:\.\d+)?)<\/bdi>/gi; + let bdiMatch; + while ((bdiMatch = bdiPattern.exec(html)) !== null) { + const n = toNumber(bdiMatch[1]); + if (n > 0) return n; + } + + // sale price block + const ins = html.match(/[\s\S]{0,300}?(?:₹|₹)<\/span>([\d,]+(?:\.\d+)?)<\/bdi>[\s\S]{0,300}?<\/ins>/i); + if (ins) { const n = toNumber(ins[1]); if (n > 0) return n; } + + // Fallback: ₹ number anywhere + const entity = html.match(/₹[^>]*>([\d,]+(?:\.\d+)?)/); + if (entity) { const n = toNumber(entity[1]); if (n > 0) return n; } + + return null; +} + +function availabilityToStockStatus(availability) { + if (!availability) return null; + const url = String(availability).toLowerCase(); + if (url.includes("instock")) return "instock"; + if (url.includes("outofstock")) return "outofstock"; + if (url.includes("backorder") || url.includes("preorder")) return "onbackorder"; + return null; +} + +// --------------------------------------------------------------------------- +// JSON-LD extraction +// --------------------------------------------------------------------------- + +function extractJsonLd(html) { + const results = []; + const regex = /]+type=["']application\/ld\+json["'][^>]*>([\s\S]*?)<\/script>/gi; + let match; + while ((match = regex.exec(html)) !== null) { + try { + results.push(JSON.parse(match[1].trim())); + } catch { + // skip + } + } + return results; +} + +// --------------------------------------------------------------------------- +// Collection page: extract product URLs +// --------------------------------------------------------------------------- + +function extractProductUrls(html) { + const urls = new Set(); + const regex = /href=["']((?:https?:\/\/dirtstreet\.in)?\/product\/[^"'#?]+)["']/gi; + let match; + while ((match = regex.exec(html)) !== null) { + let url = match[1]; + if (url.startsWith("/")) url = `${BASE_URL}${url}`; + if (url.includes("/product-category/") || url.includes("/product-tag/")) continue; + // normalize trailing slash + url = url.replace(/\/?$/, "/"); + urls.add(url); + } + return Array.from(urls); +} + +function hasNextPage(html, currentPage, slug) { + const pattern = new RegExp( + `href=["'][^"']*/brand/${slug}/page/${currentPage + 1}/?["']`, + "i" + ); + return pattern.test(html); +} + +async function fetchBrandProductUrls(slug, brandUrl) { + const allUrls = new Set(); + let page = 1; + + while (true) { + const url = page === 1 ? brandUrl : `${brandUrl}page/${page}/`; + console.log(`[DIRTSTREET] Fetching brand page ${page}: ${url}`); + + const html = await fetchHtml(url); + if (!html) break; + + const urls = extractProductUrls(html); + const before = allUrls.size; + urls.forEach((u) => allUrls.add(u)); + + console.log(`[DIRTSTREET] Page ${page} -> ${urls.length} product URLs (total: ${allUrls.size})`); + + if (!hasNextPage(html, page, slug) || allUrls.size === before) break; + page++; + await sleep(300); + } + + return Array.from(allUrls); +} + +// --------------------------------------------------------------------------- +// Extra WooCommerce fields from HTML +// --------------------------------------------------------------------------- + +function extractExtraFields(html) { + const extra = { + sku: null, + categories: [], + tags: [], + shortDescription: null, + stockStatus: null, + attributes: [], + variations: [], + }; + + // SKU - strip "SKU:" label prefix + const skuMatch = html.match(/]+class="[^"]*\bsku\b[^"]*"[^>]*>([\s\S]*?)<\/span>/i); + if (skuMatch) { + extra.sku = cleanText(skuMatch[1]) + .replace(/^SKU\s*:\s*/i, "") + .trim(); + } + + // Stock status — read from the main product wrapper class only, not whole page + // The first
is the current product + const productClassMatch = html.match(/class="[^"]*\bproduct\b[^"]*\b(instock|outofstock|on-backorder)\b[^"]*"/i); + if (productClassMatch) { + const cls = productClassMatch[1].toLowerCase(); + if (cls === "instock") extra.stockStatus = "instock"; + else if (cls === "outofstock") extra.stockStatus = "outofstock"; + else extra.stockStatus = "onbackorder"; + } + + // Categories + const catMatch = html.match(/]+class="[^"]*posted_in[^"]*"[^>]*>([\s\S]*?)<\/span>/i); + if (catMatch) { + const catRegex = /]*>([\s\S]*?)<\/a>/gi; + let m; + while ((m = catRegex.exec(catMatch[1])) !== null) { + const cat = cleanText(m[1]); + if (cat) extra.categories.push(cat); + } + } + + // Tags + const tagMatch = html.match(/]+class="[^"]*tagged_as[^"]*"[^>]*>([\s\S]*?)<\/span>/i); + if (tagMatch) { + const tagRegex = /]*>([\s\S]*?)<\/a>/gi; + let m; + while ((m = tagRegex.exec(tagMatch[1])) !== null) { + const tag = cleanText(m[1]); + if (tag) extra.tags.push(tag); + } + } + + // Short description + const sdMatch = html.match( + /]+class="[^"]*woocommerce-product-details__short-description[^"]*"[^>]*>([\s\S]*?)<\/div>/i + ); + if (sdMatch) extra.shortDescription = cleanText(sdMatch[1]); + + // Attributes table + const attrMatch = html.match( + /]+class="[^"]*woocommerce-product-attributes[^"]*"[^>]*>([\s\S]*?)<\/table>/i + ); + if (attrMatch) { + const rows = attrMatch[1].match(/]*>([\s\S]*?)<\/tr>/gi) || []; + for (const row of rows) { + const th = row.match(/]*>([\s\S]*?)<\/th>/i); + const td = row.match(/]*>([\s\S]*?)<\/td>/i); + if (th && td) { + const key = cleanText(th[1]); + const value = cleanText(td[1]); + if (key && value) extra.attributes.push({ name: key, value }); + } + } + } + + // WooCommerce variations JSON in data attribute + const formMatch = html.match(/data-product_variations=["']([\[{][\s\S]*?)["']\s*>/); + if (formMatch) { + try { + extra.variations = JSON.parse( + formMatch[1].replace(/"/g, '"').replace(/"/g, '"') + ); + } catch { /* skip */ } + } + + return extra; +} + +// --------------------------------------------------------------------------- +// Scrape one product detail page +// --------------------------------------------------------------------------- + +async function scrapeProductDetail(productUrl, brandName, brandSlug) { + const html = await fetchHtml(productUrl); + if (!html) { + return { recordType: "product", source: "dirtstreet", brand: brandName, brandSlug, url: productUrl, scrapeError: "404" }; + } + + const jsonLdBlocks = extractJsonLd(html); + // Try direct Product type first, then search every @graph block + let schema = jsonLdBlocks.find((b) => b["@type"] === "Product"); + if (!schema) { + for (const block of jsonLdBlocks) { + if (Array.isArray(block["@graph"])) { + const found = block["@graph"].find((g) => g["@type"] === "Product"); + if (found) { schema = found; break; } + } + } + } + + const extra = extractExtraFields(html); + + const offer = Array.isArray(schema?.offers) ? schema.offers[0] : (schema?.offers || {}); + + // Price: JSON-LD offers.priceSpecification[0].price OR offers.price, then HTML fallback + const priceSpec = Array.isArray(offer?.priceSpecification) + ? offer.priceSpecification[0]?.price + : null; + let price = toNumber(priceSpec ?? offer?.price ?? offer?.lowPrice); + if (!price || price === 0) price = extractPriceFromHtml(html); + if (price === 0) price = null; + + // Stock: derive from JSON-LD availability (most reliable), fall back to HTML class + const stockFromSchema = availabilityToStockStatus(offer?.availability); + const stockStatus = stockFromSchema || extra.stockStatus || null; + + const currency = offer?.priceCurrency || "INR"; + + const images = Array.isArray(schema?.image) + ? schema.image.map((img) => (typeof img === "string" ? img : img?.url || img?.contentUrl)).filter(Boolean) + : schema?.image + ? [typeof schema.image === "string" ? schema.image : (schema.image?.url || schema.image?.contentUrl)] + : []; + + return { + recordType: "product", + source: "dirtstreet", + brand: schema?.brand?.name || brandName, + brandSlug, + url: productUrl, + title: cleanText(schema?.name || ""), + sku: extra.sku || cleanText(schema?.sku || ""), + mpn: cleanText(schema?.mpn || ""), + gtin: cleanText(schema?.gtin || schema?.gtin13 || ""), + price, + currency, + priceRaw: price != null ? String(price) : null, + compareAtPrice: toNumber(offer?.highPrice) || null, + availability: offer?.availability || null, + stockStatus, + image: images[0] || null, + images, + description: cleanText(schema?.description || ""), + shortDescription: extra.shortDescription, + categories: extra.categories, + tags: extra.tags, + attributes: extra.attributes, + variations: extra.variations, + aggregateRating: schema?.aggregateRating + ? { ratingValue: schema.aggregateRating.ratingValue, reviewCount: schema.aggregateRating.reviewCount } + : null, + scrapeError: null, + }; +} + +// --------------------------------------------------------------------------- +// Concurrency helper +// --------------------------------------------------------------------------- + +async function mapWithConcurrency(items, concurrency, worker) { + const results = new Array(items.length); + let index = 0; + async function run() { + while (true) { + const i = index++; + if (i >= items.length) return; + results[i] = await worker(items[i], i); + } + } + await Promise.all(Array.from({ length: Math.min(concurrency, items.length) }, run)); + return results; +} + +// --------------------------------------------------------------------------- +// Main export: scrape one brand +// --------------------------------------------------------------------------- + +async function scrapeDirtstreetBrand({ name, slug, brandUrl }, options = {}) { + const limit = options.limit ? Number(options.limit) : null; + const onProgress = typeof options.onProgress === "function" ? options.onProgress : null; + const concurrency = options.concurrency || CONCURRENCY; + + let productUrls = await fetchBrandProductUrls(slug, brandUrl); + console.log(`[DIRTSTREET:${name}] Found ${productUrls.length} products`); + + if (limit && productUrls.length > limit) { + console.log(`[DIRTSTREET:${name}] Limit applied: fetching first ${limit} of ${productUrls.length}`); + productUrls = productUrls.slice(0, limit); + } + + let done = 0; + const products = await mapWithConcurrency(productUrls, concurrency, async (url, i) => { + const product = await scrapeProductDetail(url, name, slug); + done++; + if (done % 10 === 0 || done === productUrls.length) { + console.log(`[DIRTSTREET:${name}] ${done}/${productUrls.length} products scraped`); + } + if (onProgress) onProgress({ done, total: productUrls.length, product: product.title || url }); + return product; + }); + + return products; +} + +// --------------------------------------------------------------------------- +// Standalone test +// --------------------------------------------------------------------------- + +if (require.main === module) { + const { BRANDS } = require("./brands"); + const brand = BRANDS[0]; + console.log(`Testing scraper for: ${brand.name}`); + scrapeDirtstreetBrand(brand, { limit: 3 }) + .then((products) => { + console.log(`\nScraped ${products.length} products`); + console.log("Sample product:"); + console.log(JSON.stringify(products[0], null, 2)); + }) + .catch((err) => { + console.error("Scrape failed:", err.message); + process.exitCode = 1; + }); +} + +module.exports = { scrapeDirtstreetBrand, fetchBrandProductUrls, scrapeProductDetail }; diff --git a/src/business-logic/import-pipeline/test_source/motousher/brands.js b/src/business-logic/import-pipeline/test_source/motousher/brands.js new file mode 100644 index 0000000..03cb1ea --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/motousher/brands.js @@ -0,0 +1,73 @@ +/** + * Motousher brand list. + * + * Each entry maps a brand name to its collection page URL on motousher.com. + * Add more brands here — the scraper loops this list automatically. + * + * Brand index page: https://www.motousher.com/pages/partner-brands + */ + +const BRANDS = [ + { + name: "All Balls Racing", + slug: "all-balls-racing", + collectionUrl: "https://www.motousher.com/collections/all-balls-racing", + }, + { + name: "DID Chains", + slug: "did-chains", + collectionUrl: "https://www.motousher.com/collections/did-chains", + }, + { + name: "EBC Brakes", + slug: "ebc-brakes", + collectionUrl: "https://www.motousher.com/collections/ebc-brakes", + }, + { + name: "Esjot Sprockets", + slug: "esjot-sprockets", + collectionUrl: "https://www.motousher.com/collections/esjot-sprockets", + }, + { + name: "Evans Coolant", + slug: "evans-coolant", + collectionUrl: "https://www.motousher.com/collections/evans-coolant", + }, + { + name: "Grip Puppies", + slug: "grip-puppies", + collectionUrl: "https://www.motousher.com/collections/grip-puppies", + }, + { + name: "HiFlo Filters", + slug: "hi-flo", + collectionUrl: "https://www.motousher.com/collections/hi-flo", + }, + { + name: "JT Sprockets", + slug: "jt-sprockets", + collectionUrl: "https://www.motousher.com/collections/jt-sprockets", + }, + { + name: "Maxima Racing Oils", + slug: "maxima-racing-oils", + collectionUrl: "https://www.motousher.com/collections/maxima-racing-oils", + }, + { + name: "Putoline", + slug: "putoline", + collectionUrl: "https://www.motousher.com/collections/putoline", + }, + { + name: "Ram Mount", + slug: "ram-mount", + collectionUrl: "https://www.motousher.com/collections/ram-mount", + }, + { + name: "Wunderlich", + slug: "wunderlich", + collectionUrl: "https://www.motousher.com/collections/wunderlich", + }, +]; + +module.exports = { BRANDS }; diff --git a/src/business-logic/import-pipeline/test_source/motousher/index.js b/src/business-logic/import-pipeline/test_source/motousher/index.js new file mode 100644 index 0000000..550f13e --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/motousher/index.js @@ -0,0 +1,158 @@ +/** + * Motousher scraper runner. + * + * Loops through BRANDS in brands.js, scrapes each brand's collection page + * and all product detail pages, saves per-brand JSON files, then combines + * everything into a single combined.json. + * + * Usage: + * node index.js → scrape all brands in brands.js + * node index.js --brand all-balls-racing → scrape one brand only + * node index.js --limit 5 → only first 5 products per brand (for quick tests) + */ + +const fs = require("node:fs/promises"); +const path = require("node:path"); +const { BRANDS } = require("./brands"); +const { scrapeMotousherBrand } = require("./scraper"); + +const OUTPUT_DIR = path.resolve(__dirname, "..", "..", "..", "..", "..", "data", "sources", "test_source", "motousher"); + +function slugify(str) { + return String(str || "") + .trim() + .toLowerCase() + .replace(/[^a-z0-9]+/g, "-") + .replace(/^-+|-+$/g, ""); +} + +function parseArgs(argv = process.argv.slice(2)) { + const out = { brandSlug: null, limit: null }; + for (let i = 0; i < argv.length; i++) { + if ((argv[i] === "--brand" || argv[i] === "-b") && argv[i + 1]) { + out.brandSlug = argv[i + 1].toLowerCase().trim(); + } + if ((argv[i] === "--limit" || argv[i] === "-n") && argv[i + 1]) { + const n = Number.parseInt(argv[i + 1], 10); + if (Number.isFinite(n) && n > 0) out.limit = n; + } + } + return out; +} + +async function run() { + const { brandSlug, limit } = parseArgs(); + await fs.mkdir(OUTPUT_DIR, { recursive: true }); + + const brandsToRun = brandSlug + ? BRANDS.filter((b) => b.slug === brandSlug) + : BRANDS; + + if (!brandsToRun.length) { + console.error(`No brand found matching slug: "${brandSlug}"`); + console.error(`Available: ${BRANDS.map((b) => b.slug).join(", ")}`); + process.exitCode = 1; + return; + } + + const combinedProducts = []; + const runSummary = []; + const startedAt = new Date().toISOString(); + + for (const brand of brandsToRun) { + console.log(`\n${"=".repeat(60)}`); + console.log(`[MOTOUSHER] Scraping brand: ${brand.name}`); + console.log(`[MOTOUSHER] Collection URL: ${brand.collectionUrl}`); + console.log(`${"=".repeat(60)}`); + + const brandStartedAt = new Date().toISOString(); + let products = []; + let error = null; + + try { + products = await scrapeMotousherBrand(brand, { + limit, + onProgress({ done, total, product }) { + // Inline progress already logged by scraper + }, + }); + + // Save per-brand JSON + const brandFile = path.join(OUTPUT_DIR, `${brand.slug}.json`); + const brandPayload = { + generatedAt: new Date().toISOString(), + source: "motousher", + brand: brand.name, + brandSlug: brand.slug, + collectionUrl: brand.collectionUrl, + totalProducts: products.length, + products, + }; + + await fs.writeFile(brandFile, JSON.stringify(brandPayload, null, 2), "utf8"); + console.log(`[MOTOUSHER] Saved ${products.length} products → ${brandFile}`); + + combinedProducts.push(...products); + + runSummary.push({ + brand: brand.name, + slug: brand.slug, + collectionUrl: brand.collectionUrl, + startedAt: brandStartedAt, + completedAt: new Date().toISOString(), + totalProducts: products.length, + success: true, + }); + } catch (err) { + console.error(`[MOTOUSHER] Failed to scrape ${brand.name}: ${err.message}`); + error = err.message; + + runSummary.push({ + brand: brand.name, + slug: brand.slug, + collectionUrl: brand.collectionUrl, + startedAt: brandStartedAt, + completedAt: new Date().toISOString(), + totalProducts: 0, + success: false, + error, + }); + } + } + + // Save combined JSON (all brands merged) + const combinedFile = path.join(OUTPUT_DIR, "combined.json"); + const combinedPayload = { + generatedAt: new Date().toISOString(), + startedAt, + source: "motousher", + siteUrl: "https://www.motousher.com", + brandsScraped: runSummary.length, + totalProducts: combinedProducts.length, + runSummary, + products: combinedProducts, + }; + + await fs.writeFile(combinedFile, JSON.stringify(combinedPayload, null, 2), "utf8"); + + console.log(`\n${"=".repeat(60)}`); + console.log("[MOTOUSHER] RUN COMPLETE"); + console.log(`${"=".repeat(60)}`); + console.log(`Brands scraped : ${runSummary.length}`); + console.log(`Total products : ${combinedProducts.length}`); + console.log(`Combined file : ${combinedFile}`); + console.log("\nBrand summary:"); + for (const s of runSummary) { + const status = s.success ? "OK" : "FAILED"; + console.log(` [${status}] ${s.brand} → ${s.totalProducts} products`); + } + + return combinedPayload; +} + +run().catch((err) => { + console.error("Runner failed:", err.message); + process.exitCode = 1; +}); + +module.exports = { run }; diff --git a/src/business-logic/import-pipeline/test_source/motousher/links.txt b/src/business-logic/import-pipeline/test_source/motousher/links.txt new file mode 100644 index 0000000..6ae747d --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/motousher/links.txt @@ -0,0 +1,9 @@ +# Motousher Partner Brand Links +# Source: https://www.motousher.com/pages/partner-brands +# Format: Brand Name | Collection URL + +All Balls Racing | https://www.motousher.com/collections/all-balls-racing + +# Add more brands below as needed, e.g.: +# Acerbis | https://www.motousher.com/collections/acerbis +# Twin Air | https://www.motousher.com/collections/twin-air diff --git a/src/business-logic/import-pipeline/test_source/motousher/scraper.js b/src/business-logic/import-pipeline/test_source/motousher/scraper.js new file mode 100644 index 0000000..5c1a24b --- /dev/null +++ b/src/business-logic/import-pipeline/test_source/motousher/scraper.js @@ -0,0 +1,254 @@ +/** + * Motousher.com scraper — Shopify JSON API (fast, no browser needed). + * + * Motousher is a Shopify store. Every collection and product has a public + * JSON endpoint, so we use plain fetch instead of Playwright: + * + * Collection listing: /collections/{handle}/products.json?limit=250&page=N + * Product detail: /products/{handle}.json + * + * This is 10-20x faster than Playwright. Playwright is only used as a + * fallback if the JSON API returns nothing. + */ + +const BASE_URL = "https://www.motousher.com"; +const CONCURRENCY = 3; // parallel product detail fetches — motousher rate-limits above ~5 + +function sleep(ms) { + return new Promise((resolve) => setTimeout(resolve, ms)); +} + +async function fetchJson(url, attempt = 1) { + try { + const res = await fetch(url, { + headers: { + "accept": "application/json", + "accept-language": "en-US,en;q=0.9", + "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/124 Safari/537.36", + }, + }); + + if (res.status === 429 || res.status >= 500) { + if (attempt <= 4) { + const wait = attempt * 1500; + console.log(`[RETRY] ${url} → HTTP ${res.status}, retrying in ${wait}ms (attempt ${attempt}/4)`); + await sleep(wait); + return fetchJson(url, attempt + 1); + } + throw new Error(`HTTP ${res.status} after retries`); + } + + if (!res.ok) throw new Error(`HTTP ${res.status}`); + return res.json(); + } catch (err) { + if (attempt <= 4 && err.code === "UND_ERR_CONNECT_TIMEOUT") { + await sleep(attempt * 1500); + return fetchJson(url, attempt + 1); + } + throw err; + } +} + +// --------------------------------------------------------------------------- +// Collection: fetch ALL product handles via paginated JSON API +// --------------------------------------------------------------------------- + +async function fetchCollectionProductHandles(collectionHandle) { + const handles = []; + let page = 1; + + while (true) { + const url = `${BASE_URL}/collections/${collectionHandle}/products.json?limit=250&page=${page}`; + console.log(`[MOTOUSHER] Fetching collection page ${page}: ${url}`); + + const data = await fetchJson(url); + const products = Array.isArray(data?.products) ? data.products : []; + + if (!products.length) break; + + for (const p of products) { + if (p.handle) handles.push(p.handle); + } + + console.log(`[MOTOUSHER] Page ${page} → ${products.length} products (total so far: ${handles.length})`); + + if (products.length < 250) break; // last page + page++; + } + + return handles; +} + +// --------------------------------------------------------------------------- +// Product detail: fetch via /products/{handle}.json +// --------------------------------------------------------------------------- + +function toNumber(value) { + if (!value) return null; + const match = String(value).match(/([\d,]+\.?\d*)/); + if (!match) return null; + const n = Number.parseFloat(match[1].replace(/,/g, "")); + return Number.isNaN(n) ? null : n; +} + +function bestImageUrl(src) { + if (!src) return null; + // Remove Shopify width constraints to get the original full-size image + return src.replace(/(_\d+x\d*|_\d+x)(\.\w+)(\?|$)/, "$2$3"); +} + +function normalizeShopifyProduct(raw, brandName, brandSlug, collectionUrl) { + const images = (raw.images || []).map((img) => bestImageUrl(img.src)).filter(Boolean); + + const options = (raw.options || []).map((opt) => ({ + label: opt.name, + values: (opt.values || []).map((v) => ({ label: v, value: v })), + })); + + const variants = (raw.variants || []).map((v) => ({ + id: v.id, + title: v.title, + sku: v.sku || null, + price: toNumber(v.price), + compareAtPrice: toNumber(v.compare_at_price), + available: v.available, + options: [v.option1, v.option2, v.option3].filter(Boolean), + weight: v.grams || null, + barcode: v.barcode || null, + })); + + const firstVariant = variants[0] || {}; + + return { + recordType: "product", + source: "motousher", + brand: brandName, + brandSlug, + collectionUrl, + title: raw.title || null, + url: `${BASE_URL}/products/${raw.handle}`, + handle: raw.handle || null, + productType: raw.product_type || null, + vendor: raw.vendor || brandName, + tags: Array.isArray(raw.tags) ? raw.tags : [], + priceRaw: firstVariant.price != null ? String(firstVariant.price) : null, + price: firstVariant.price ?? null, + compareAtPriceRaw: firstVariant.compareAtPrice != null ? String(firstVariant.compareAtPrice) : null, + compareAtPrice: firstVariant.compareAtPrice ?? null, + sku: firstVariant.sku || null, + barcode: firstVariant.barcode || null, + available: raw.variants?.some((v) => v.available) ?? null, + image: images[0] || null, + images, + descriptionHtml: raw.body_html || null, + description: raw.body_html + ? raw.body_html.replace(/<[^>]+>/g, " ").replace(/\s+/g, " ").trim() + : null, + options, + variants, + publishedAt: raw.published_at || null, + createdAt: raw.created_at || null, + updatedAt: raw.updated_at || null, + scrapeError: null, + }; +} + +async function fetchProductDetail(handle, brandName, brandSlug, collectionUrl) { + const url = `${BASE_URL}/products/${handle}.json`; + try { + const data = await fetchJson(url); + if (!data?.product) throw new Error("No product in response"); + return normalizeShopifyProduct(data.product, brandName, brandSlug, collectionUrl); + } catch (err) { + return { + recordType: "product", + source: "motousher", + brand: brandName, + brandSlug, + collectionUrl, + handle, + url: `${BASE_URL}/products/${handle}`, + scrapeError: err.message, + }; + } +} + +// --------------------------------------------------------------------------- +// Concurrency helper +// --------------------------------------------------------------------------- + +async function mapWithConcurrency(items, concurrency, worker) { + const results = new Array(items.length); + let index = 0; + + async function run() { + while (true) { + const i = index++; + if (i >= items.length) return; + results[i] = await worker(items[i], i); + } + } + + await Promise.all(Array.from({ length: Math.min(concurrency, items.length) }, run)); + return results; +} + +// --------------------------------------------------------------------------- +// Main export: scrape one brand +// --------------------------------------------------------------------------- + +async function scrapeMotousherBrand({ name, slug, collectionUrl }, options = {}) { + const limit = options.limit ? Number(options.limit) : null; + const onProgress = typeof options.onProgress === "function" ? options.onProgress : null; + const concurrency = options.concurrency || CONCURRENCY; + + // Step 1: get all product handles from collection pages + let handles = await fetchCollectionProductHandles(slug); + console.log(`[MOTOUSHER:${name}] Found ${handles.length} products in collection`); + + if (limit && handles.length > limit) { + console.log(`[MOTOUSHER:${name}] Limit applied: fetching first ${limit} of ${handles.length}`); + handles = handles.slice(0, limit); + } + + // Step 2: fetch all product details in parallel + let done = 0; + const products = await mapWithConcurrency(handles, concurrency, async (handle, i) => { + const product = await fetchProductDetail(handle, name, slug, collectionUrl); + done++; + if (done % 20 === 0 || done === handles.length) { + console.log(`[MOTOUSHER:${name}] ${done}/${handles.length} products fetched`); + } + if (onProgress) onProgress({ done, total: handles.length, product: product.title || handle }); + return product; + }); + + return products; +} + +// --------------------------------------------------------------------------- +// Standalone test +// --------------------------------------------------------------------------- + +if (require.main === module) { + const { BRANDS } = require("./brands"); + const brand = BRANDS[0]; + + console.log(`Testing scraper for: ${brand.name}`); + scrapeMotousherBrand(brand, { limit: 5 }) + .then((products) => { + console.log(`\nScraped ${products.length} products`); + console.log("Sample product:"); + console.log(JSON.stringify(products[0], null, 2)); + }) + .catch((err) => { + console.error("Scrape failed:", err.message); + process.exitCode = 1; + }); +} + +module.exports = { + scrapeMotousherBrand, + fetchCollectionProductHandles, + fetchProductDetail, +};