feat(amazon-shopping): scrape and filter amazon product results

This commit is contained in:
2026-04-15 18:48:51 -05:00
parent ef326896f4
commit 1e0e265f1e
15 changed files with 844 additions and 6 deletions
+228
View File
@@ -0,0 +1,228 @@
import { execFile } from "node:child_process";
import { pathToFileURL } from "node:url";
import { join } from "node:path";
import { promisify } from "node:util";
import { extractDetailPage } from "./detail-page.js";
import { applyFiltersAndLimit } from "./filters.js";
import { createResponse } from "./report.js";
import { extractSearchPage } from "./search-page.js";
import type { ProductSearchResult, SearchProductsRequest, SearchProductsResponse } from "./types.js";
import { resolveWebAutomationRuntime } from "./web-automation-runtime.js";
const execFileAsync = promisify(execFile);
const AMAZON_ROOT = "https://www.amazon.com";
const DEFAULT_WAIT_MS = 4500;
export type HttpClassification = "ok" | "retryable" | "challenge";
interface BrowserDeps {
fetchText?: (url: string) => Promise<string>;
sleep?: (ms: number) => Promise<void>;
now?: () => Date;
}
export function plannedAmazonPaths(asins: string[]): string[] {
return [
"/s",
...asins.flatMap((asin) => [`/dp/${asin}`, `/gp/product/${asin}`])
];
}
export function classifyHttpStatus(status: number | null | undefined): HttpClassification {
if (status === 429 || status === 503) return "retryable";
if (status === 401 || status === 403) return "challenge";
return "ok";
}
export function isPathAllowedByRobots(robots: string, userAgent: string, path: string): boolean {
const groups: Array<{ agents: string[]; disallows: string[] }> = [];
let current: { agents: string[]; disallows: string[] } | undefined;
let hasDirectives = false;
const lines = robots.split(/\r?\n/);
for (const rawLine of lines) {
const line = rawLine.replace(/#.*/, "").trim();
if (!line) continue;
const [rawKey, ...rest] = line.split(":");
const key = rawKey.trim().toLowerCase();
const value = rest.join(":").trim();
if (key === "user-agent") {
if (!current || hasDirectives) {
current = { agents: [], disallows: [] };
groups.push(current);
hasDirectives = false;
}
current.agents.push(value.toLowerCase());
continue;
}
if (key === "disallow") {
hasDirectives = true;
if (current && value) {
current.disallows.push(value);
}
}
}
const normalizedAgent = userAgent.toLowerCase();
const exactGroups = groups.filter((group) => group.agents.includes(normalizedAgent));
const matchedGroups = exactGroups.length > 0 ? exactGroups : groups.filter((group) => group.agents.includes("*"));
const disallows = matchedGroups.flatMap((group) => group.disallows);
return !disallows.some((rule) => path.startsWith(rule));
}
async function defaultFetchText(url: string): Promise<string> {
const response = await fetch(url);
return response.text();
}
async function checkRobots(paths: string[], deps: BrowserDeps): Promise<string[]> {
const warnings: string[] = [];
const robots = await (deps.fetchText ?? defaultFetchText)(`${AMAZON_ROOT}/robots.txt`);
for (const path of paths) {
if (!isPathAllowedByRobots(robots, "*", path)) {
warnings.push(`Amazon robots directives disallow planned path: ${path}`);
}
}
return warnings;
}
async function loadCloakBrowser(runtimeDir: string): Promise<{
ensureBinary?: () => Promise<void>;
launchContext: (options: Record<string, unknown>) => Promise<any>;
}> {
const moduleUrl = pathToFileURL(join(runtimeDir, "node_modules", "cloakbrowser", "dist", "index.js")).toString();
return import(moduleUrl) as Promise<any>;
}
async function checkRuntime(): Promise<string> {
const runtime = await resolveWebAutomationRuntime();
await execFileAsync(runtime.checkInstall.command, runtime.checkInstall.args, { cwd: runtime.checkInstall.cwd });
return runtime.scriptsDir;
}
function searchUrl(query: string, pageNumber: number): string {
const url = new URL("/s", AMAZON_ROOT);
url.searchParams.set("k", query);
if (pageNumber > 1) {
url.searchParams.set("page", String(pageNumber));
}
return url.toString();
}
async function pageHtml(page: any, url: string, deps: BrowserDeps): Promise<{ html: string; status: number | null }> {
let lastStatus: number | null = null;
for (let attempt = 0; attempt < 3; attempt += 1) {
const response = await page.goto(url, { waitUntil: "domcontentloaded", timeout: 45000 });
await page.waitForTimeout?.(DEFAULT_WAIT_MS);
lastStatus = response?.status?.() ?? null;
if (classifyHttpStatus(lastStatus) !== "retryable") {
return {
html: await page.content(),
status: lastStatus
};
}
await (deps.sleep ?? ((ms) => new Promise((resolve) => setTimeout(resolve, ms))))((2 ** attempt) * 1000 + Math.floor(Math.random() * 500));
}
return {
html: await page.content(),
status: lastStatus
};
}
async function enrichDetails(page: any, products: ProductSearchResult[], deps: BrowserDeps): Promise<ProductSearchResult[]> {
const enriched: ProductSearchResult[] = [];
for (const product of products) {
await (deps.sleep ?? ((ms) => new Promise((resolve) => setTimeout(resolve, ms))))(1500 + Math.floor(Math.random() * 1500));
const loaded = await pageHtml(page, product.url, deps);
const classification = classifyHttpStatus(loaded.status);
if (classification === "challenge") {
enriched.push({
...product,
extractionNotes: [...product.extractionNotes, "Detail page returned a challenge/block status."]
});
continue;
}
enriched.push(extractDetailPage(loaded.html, product));
}
return enriched;
}
export async function searchProducts(request: SearchProductsRequest, deps: BrowserDeps = {}): Promise<SearchProductsResponse> {
const warnings: string[] = [];
const robotsWarnings = await checkRobots(plannedAmazonPaths([]), deps);
if (robotsWarnings.length > 0) {
return createResponse({
query: request.query,
filters: request.filters,
limit: request.limit,
maxSearchPages: request.maxSearchPages,
results: [],
filteredOutCount: 0,
warnings: robotsWarnings,
now: deps.now
});
}
const runtimeDir = await checkRuntime();
const cloak = await loadCloakBrowser(runtimeDir);
await cloak.ensureBinary?.();
const context = await cloak.launchContext({
headless: process.env.CLOAKBROWSER_HEADLESS !== "false",
locale: "en-US",
viewport: { width: 1440, height: 900 },
humanize: true
});
const page = await context.newPage();
try {
const candidates: ProductSearchResult[] = [];
let nextUrl: string | undefined = searchUrl(request.query, 1);
for (let pageNumber = 1; pageNumber <= request.maxSearchPages && nextUrl; pageNumber += 1) {
const loaded = await pageHtml(page, nextUrl, deps);
const classification = classifyHttpStatus(loaded.status);
if (classification === "challenge" || classification === "retryable") {
warnings.push(`Amazon returned status ${loaded.status}; stopping without bypass.`);
break;
}
const extracted = extractSearchPage(loaded.html, nextUrl);
warnings.push(...extracted.warnings);
if (extracted.status === "challenge") {
break;
}
candidates.push(...extracted.products);
if (candidates.length >= request.limit * 3) {
break;
}
nextUrl = extracted.nextPageUrl ?? (pageNumber + 1 <= request.maxSearchPages ? searchUrl(request.query, pageNumber + 1) : undefined);
}
let detailCandidates = candidates;
if (!request.skipDetails) {
const detailPaths = plannedAmazonPaths(candidates.map((candidate) => candidate.asin)).filter((path) => path !== "/s");
const detailRobotsWarnings = await checkRobots(detailPaths, deps);
if (detailRobotsWarnings.length > 0) {
warnings.push(...detailRobotsWarnings, "Detail enrichment skipped because robots directives disallow at least one planned detail path.");
} else {
detailCandidates = await enrichDetails(page, candidates.slice(0, request.limit * 3), deps);
}
}
const filtered = applyFiltersAndLimit(detailCandidates, request.filters, request.limit);
return createResponse({
query: request.query,
filters: request.filters,
limit: request.limit,
maxSearchPages: request.maxSearchPages,
results: filtered.results,
filteredOutCount: filtered.filteredOutCount,
warnings,
now: deps.now
});
} finally {
await context.close();
}
}
+16 -2
View File
@@ -3,7 +3,9 @@
import minimist from "minimist";
import { fileURLToPath } from "node:url";
import { searchProducts } from "./browser.js";
import { parseNaturalLanguageRequest } from "./query-parser.js";
import { createMarkdownReport } from "./report.js";
import type { ProductFilters, SearchProductsRequest, SearchProductsResponse } from "./types.js";
export interface CliDeps {
@@ -138,7 +140,19 @@ async function defaultSearchProducts(request: SearchProductsRequest, deps: CliDe
if (request.dryRun) {
return createDryRunResponse(request, deps.now ?? (() => new Date()));
}
throw new Error("Live Amazon search is not implemented yet. Use --dry-run until browser orchestration is installed.");
return searchProducts(request, { now: deps.now });
}
function writeResponse(response: SearchProductsResponse, output: SearchProductsRequest["output"], deps: CliDeps): void {
if (output === "markdown") {
deps.stdout.write(createMarkdownReport(response));
return;
}
if (output === "both") {
deps.stdout.write(`${JSON.stringify(response, null, 2)}\n\n${createMarkdownReport(response)}`);
return;
}
deps.stdout.write(`${JSON.stringify(response, null, 2)}\n`);
}
export async function runCli(
@@ -156,7 +170,7 @@ export async function runCli(
const response = deps.searchProducts
? await deps.searchProducts(request)
: await defaultSearchProducts(request, deps);
deps.stdout.write(`${JSON.stringify(response, null, 2)}\n`);
writeResponse(response, request.output, deps);
return 0;
} catch (error: unknown) {
const message = error instanceof Error ? error.message : String(error);
+133
View File
@@ -0,0 +1,133 @@
import { HTMLElement, parse } from "node-html-parser";
import { parseMoney, parseRating, parseReviewCount, parseStarBreakdown } from "./parsers.js";
import type { DeliverySummary, ProductSearchResult, ProductSpec } from "./types.js";
function textOf(node: HTMLElement | null | undefined): string {
return cleanText(node?.textContent ?? "");
}
function attrOf(node: HTMLElement | null | undefined, name: string): string {
return cleanText(node?.getAttribute(name) ?? "");
}
function cleanText(text: string): string {
return text
.replace(/\s+/g, " ")
.replace(/\s*\{".*$/g, "")
.trim();
}
function isScriptLike(text: string): boolean {
return /\(function\s*\(|window\.|P\.when|ue\.count|tracking\(\)|logShoppableMetrics|buying options|add to cart/i.test(text);
}
function firstText(root: HTMLElement, selectors: string[]): string {
for (const selector of selectors) {
const text = textOf(root.querySelector(selector));
if (text) {
return text;
}
}
return "";
}
function extractBullets(root: HTMLElement): string[] {
const spanBullets = root.querySelectorAll("#feature-bullets li span")
.map((node) => textOf(node))
.filter((text) => text && !/make sure this fits/i.test(text));
if (spanBullets.length > 0) {
return spanBullets;
}
return root.querySelectorAll("#feature-bullets li")
.map((node) => textOf(node))
.filter((text) => text && !/make sure this fits/i.test(text));
}
function extractSpecs(root: HTMLElement): ProductSpec[] {
const specs: ProductSpec[] = [];
const seen = new Set<string>();
const excludedNames = new Set(["customer reviews"]);
for (const row of root.querySelectorAll("tr")) {
const cells = row.querySelectorAll("th,td").map((cell) => textOf(cell)).filter(Boolean);
if (cells.length >= 2) {
const name = cells[0];
const value = cells.slice(1).join(" ");
const key = name.toLowerCase();
if (seen.has(key) || excludedNames.has(key) || isScriptLike(name) || isScriptLike(value)) {
continue;
}
seen.add(key);
specs.push({ name, value });
}
}
return specs;
}
function extractHistogramText(root: HTMLElement): string {
const rows = root.querySelectorAll("#histogramTable tr, [aria-label*='star'] tr");
const parts: string[] = [];
for (const row of rows) {
const cells = row.querySelectorAll("th,td").map((cell) => textOf(cell)).filter(Boolean);
if (cells.length >= 2) {
parts.push(`${cells[0]} ${cells[1]}`);
}
}
return parts.join(" ");
}
function deliveryFromText(text: string): DeliverySummary | undefined {
const display = text.replace(/\s+/g, " ").trim();
if (!display) {
return undefined;
}
return {
display,
free: /\bfree\b/i.test(display),
prime: /\bprime\b/i.test(display)
};
}
export function extractDetailPage(html: string, base: ProductSearchResult): ProductSearchResult {
const root = parse(html);
const title = firstText(root, ["#productTitle", "h1"]) || base.title;
const priceText = firstText(root, [
"#corePriceDisplay_desktop_feature_div .a-offscreen",
".a-price .a-offscreen",
".a-price"
]);
const deliveryText = firstText(root, [
"#mir-layout-DELIVERY_BLOCK-slot-PRIMARY_DELIVERY_MESSAGE_LARGE",
"#deliveryBlockMessage",
"[data-csa-c-delivery-price]"
]);
const availability = firstText(root, ["#availability", "#availabilityInsideBuyBox_feature_div"]);
const seller = firstText(root, ["#merchant-info", "#sellerProfileTriggerId"]);
const ratingText = attrOf(root.querySelector("#acrPopover"), "title") || textOf(root.querySelector("#acrPopover"));
const reviewText = textOf(root.querySelector("#acrCustomerReviewText"));
const histogram = parseStarBreakdown(extractHistogramText(root));
const product: ProductSearchResult = {
...base,
title,
price: parseMoney(priceText) ?? base.price,
rating: parseRating(ratingText) ?? base.rating,
reviewCount: parseReviewCount(reviewText) ?? base.reviewCount,
delivery: deliveryFromText(deliveryText) ?? base.delivery,
availability: availability || base.availability,
seller: seller || base.seller,
bullets: extractBullets(root),
specs: extractSpecs(root),
starBreakdown: histogram ?? base.starBreakdown,
missingFields: [...base.missingFields],
extractionNotes: [...base.extractionNotes]
};
for (const field of ["price", "delivery", "rating", "reviewCount", "starBreakdown"] as const) {
if (product[field] === undefined && !product.missingFields.includes(field)) {
product.missingFields.push(field);
}
}
return product;
}
+86
View File
@@ -0,0 +1,86 @@
import type { FilteredProducts, ProductFilters, ProductSearchResult } from "./types.js";
function passesMin(value: number | undefined, threshold: number, comparison: "gt" | "gte" | undefined): boolean {
if (value === undefined) {
return false;
}
return comparison === "gt" ? value > threshold : value >= threshold;
}
function filterReasons(product: ProductSearchResult, filters: ProductFilters): string[] {
const reasons: string[] = [];
if (filters.minRating !== undefined && !passesMin(product.rating, filters.minRating, filters.ratingComparison)) {
reasons.push(product.rating === undefined ? "rating unknown" : `rating ${product.rating} below filter`);
}
if (filters.minReviews !== undefined && !passesMin(product.reviewCount, filters.minReviews, filters.reviewCountComparison)) {
reasons.push(product.reviewCount === undefined ? "review count unknown" : `review count ${product.reviewCount} below filter`);
}
if (filters.maxPrice !== undefined) {
if (!product.price) {
reasons.push("price unknown");
} else if (product.price.amount > filters.maxPrice) {
reasons.push(`price ${product.price.display} above filter`);
}
}
if (filters.maxUnitPrice !== undefined) {
if (!product.unitPrice) {
reasons.push("unit price unknown");
} else if (product.unitPrice.amount > filters.maxUnitPrice) {
reasons.push(`unit price ${product.unitPrice.display} above filter`);
}
}
if (filters.requirePrime && !product.delivery?.prime) {
reasons.push("Prime delivery not verified");
}
if (filters.requireFreeDelivery && !product.delivery?.free) {
reasons.push("free delivery not verified");
}
return reasons;
}
function rankProducts(a: ProductSearchResult, b: ProductSearchResult): number {
const ratingDiff = (b.rating ?? -1) - (a.rating ?? -1);
if (ratingDiff !== 0) return ratingDiff;
const reviewDiff = (b.reviewCount ?? -1) - (a.reviewCount ?? -1);
if (reviewDiff !== 0) return reviewDiff;
return (a.price?.amount ?? Number.POSITIVE_INFINITY) - (b.price?.amount ?? Number.POSITIVE_INFINITY);
}
export function applyFiltersAndLimit(
products: ProductSearchResult[],
filters: ProductFilters,
limit: number
): FilteredProducts {
const filteredOutReasons: Record<string, string[]> = {};
const uniqueProducts = new Map<string, ProductSearchResult>();
for (const product of products) {
if (!uniqueProducts.has(product.asin)) {
uniqueProducts.set(product.asin, product);
}
}
const passing: ProductSearchResult[] = [];
for (const product of uniqueProducts.values()) {
const reasons = filterReasons(product, filters);
if (reasons.length > 0) {
filteredOutReasons[product.asin] = reasons;
continue;
}
passing.push({
...product,
matchedFilters: [
...product.matchedFilters,
...(filters.minRating !== undefined ? [`rating ${filters.ratingComparison ?? "gte"} ${filters.minRating}`] : []),
...(filters.minReviews !== undefined ? [`reviews ${filters.reviewCountComparison ?? "gte"} ${filters.minReviews}`] : []),
...(filters.maxPrice !== undefined ? [`price <= ${filters.maxPrice}`] : []),
...(filters.maxUnitPrice !== undefined ? [`unit price <= ${filters.maxUnitPrice}`] : [])
]
});
}
return {
results: passing.sort(rankProducts).slice(0, limit),
filteredOutCount: uniqueProducts.size - passing.length,
filteredOutReasons
};
}
+9 -3
View File
@@ -21,13 +21,19 @@ export function parseMoney(text: string | undefined | null): MoneyValue | undefi
}
export function parseUnitPrice(text: string | undefined | null): MoneyValue | undefined {
if (!text || !(/[/]\s*\d|\$\s*\d/.test(text))) {
if (!text) {
return undefined;
}
if (!/(\/|\bper\b|\beach\b|\bcount\b)/i.test(text)) {
const compact = text.replace(/\s+/g, " ").trim();
const unitMatch = compact.match(/(\$\s*[0-9][0-9,]*(?:\.[0-9]{1,2})?)(?:\s*\$\s*[0-9][0-9,]*(?:\.[0-9]{1,2})?)?\s*(?:\/|\bper\b\s*)\s*(?:count|unit|item|piece|pack|each)\b/i)
?? compact.match(/(\$\s*[0-9][0-9,]*(?:\.[0-9]{1,2})?)\s*(?:each)\b/i);
if (!unitMatch) {
return undefined;
}
return parseMoney(text);
const display = unitMatch[0]
.replace(/\$\s*([0-9][0-9,]*(?:\.[0-9]{1,2})?)\s*\$\s*\1/i, "$$$1")
.replace(/\s+/g, "");
return parseMoney(display);
}
export function parseRating(text: string | undefined | null): number | undefined {
+1 -1
View File
@@ -50,7 +50,7 @@ export function parseNaturalLanguageRequest(input: string): ParsedNaturalLanguag
remaining = removeMatched(remaining, reviewMatch);
}
const exclusiveRating = remaining.match(/\b(?:a\s+)?(?:review score of\s+)?(?:more than|over|above|rated above)\s+([0-5](?:\.[0-9])?)\s*(?:stars?)?\b/i);
const exclusiveRating = remaining.match(/\b(?:a\s+)?(?:(?:review score|rating)\s+of\s+|rating\s+)?(?:more than|over|above|rated above)\s+([0-5](?:\.[0-9])?)\s*(?:stars?)?\b/i);
const inclusiveRating = remaining.match(/\b([0-5](?:\.[0-9])?)\s*stars?\s+or\s+better\b/i)
?? remaining.match(/\b(?:at least|minimum|min\.?)\s+([0-5](?:\.[0-9])?)\s*(?:stars?|rating)?\b/i);
const ratingMatch = exclusiveRating ?? inclusiveRating;
+69
View File
@@ -0,0 +1,69 @@
import type { ProductFilters, ProductSearchResult, SearchProductsResponse } from "./types.js";
export interface ResponseInput {
query: string;
filters: ProductFilters;
limit: number;
maxSearchPages: number;
results: ProductSearchResult[];
filteredOutCount: number;
warnings: string[];
now?: () => Date;
}
export function createResponse(input: ResponseInput): SearchProductsResponse {
return {
query: input.query,
filters: input.filters,
limit: input.limit,
maxSearchPages: input.maxSearchPages,
results: input.results,
filteredOutCount: input.filteredOutCount,
warnings: input.warnings,
source: {
site: "amazon.com",
scrapedAt: (input.now ?? (() => new Date()))().toISOString(),
automation: "web-automation/CloakBrowser"
}
};
}
function formatFilters(filters: ProductFilters): string {
const parts = [
filters.minRating !== undefined ? `rating ${filters.ratingComparison ?? "gte"} ${filters.minRating}` : "",
filters.minReviews !== undefined ? `reviews ${filters.reviewCountComparison ?? "gte"} ${filters.minReviews}` : "",
filters.maxPrice !== undefined ? `price <= $${filters.maxPrice}` : "",
filters.maxUnitPrice !== undefined ? `unit price <= $${filters.maxUnitPrice}` : ""
].filter(Boolean);
return parts.length > 0 ? parts.join(", ") : "none";
}
function formatProduct(product: ProductSearchResult, index: number): string {
const specs = product.specs.slice(0, 3).map((spec) => `${spec.name}: ${spec.value}`).join("; ");
const lines = [
`${index}. ${product.title}`,
` Link: ${product.url}`,
` Price: ${product.price?.display ?? "unknown"}${product.unitPrice ? ` (${product.unitPrice.display})` : ""}`,
` Rating: ${product.rating ?? "unknown"} stars; reviews: ${product.reviewCount ?? "unknown"}`,
` Delivery: ${product.delivery?.display ?? "unknown"}`,
specs ? ` Specs: ${specs}` : "",
product.bullets[0] ? ` Notes: ${product.bullets.slice(0, 2).join(" ")}` : "",
product.missingFields.length > 0 ? ` Missing: ${product.missingFields.join(", ")}` : "",
product.isSponsored ? " Sponsored: yes" : ""
].filter(Boolean);
return lines.join("\n");
}
export function createMarkdownReport(response: SearchProductsResponse): string {
const lines = [
`# Amazon Shopping Results`,
"",
`Query: ${response.query}`,
`Filters: ${formatFilters(response.filters)}`,
`Results returned: ${response.results.length} (filtered out: ${response.filteredOutCount})`,
response.warnings.length > 0 ? `Warnings: ${response.warnings.join("; ")}` : "",
"",
...response.results.map((product, index) => formatProduct(product, index + 1))
].filter((line) => line !== "");
return `${lines.join("\n")}\n`;
}
+6
View File
@@ -103,3 +103,9 @@ export interface SearchPageExtraction {
warnings: string[];
nextPageUrl?: string;
}
export interface FilteredProducts {
results: ProductSearchResult[];
filteredOutCount: number;
filteredOutReasons: Record<string, string[]>;
}