Files
jackwener__opencli/clis/amazon/discussion.js
jakevin d2974a9ff6 refactor(adapters): convert adapter layer from TypeScript to JavaScript (#928)
* refactor(adapters): convert adapter layer from TypeScript to JavaScript

Core framework stays TypeScript; adapter layer moves to JS-first.
Adapters are essentially "executable config + browser scripts" that
barely use TS features — this simplifies the build/distribution pipeline
by removing the dist/clis/ intermediate compilation step.

Changes:
- Convert all 753 adapter files in clis/ from .ts to .js
- Update tsconfig to exclude clis/ from compilation
- Simplify build-manifest to scan clis/*.js directly (no dist/clis/)
- Update discovery, main, fetch-adapters to load JS adapters from clis/
- Update generate-verified to output .js artifacts
- Update package.json files field: dist/clis/ → clis/
- Fix all test files for the .ts → .js transition

* fix(main): use findPackageRoot for BUILTIN_CLIS path

The previous relative path (../../clis from __dirname) only worked for
dist/src/main.js but broke dev mode (tsx src/main.ts) where __dirname
is <repo>/src — resolving to /clis instead of <repo>/clis.

Use findPackageRoot() which works for both dev and prod paths.
2026-04-10 14:52:18 +08:00

92 lines
4.4 KiB
JavaScript

import { CommandExecutionError } from '@jackwener/opencli/errors';
import { cli, Strategy } from '@jackwener/opencli/registry';
import { buildDiscussionUrl, buildProvenance, cleanText, extractAsin, normalizeProductUrl, parseRatingValue, parseReviewCount, trimRatingPrefix, uniqueNonEmpty, assertUsableState, gotoAndReadState, } from './shared.js';
function normalizeDiscussionPayload(payload) {
const sourceUrl = cleanText(payload.href) || buildDiscussionUrl(payload.href ?? '');
const asin = extractAsin(payload.href ?? '') ?? null;
const averageRatingText = cleanText(payload.average_rating_text) || null;
const totalReviewCountText = cleanText(payload.total_review_count_text) || null;
const provenance = buildProvenance(sourceUrl);
return {
asin,
product_url: asin ? normalizeProductUrl(asin) : null,
discussion_url: sourceUrl,
...provenance,
average_rating_text: averageRatingText,
average_rating_value: parseRatingValue(averageRatingText),
total_review_count_text: totalReviewCountText,
total_review_count: parseReviewCount(totalReviewCountText),
qa_urls: uniqueNonEmpty(payload.qa_links ?? []),
review_samples: (payload.review_samples ?? []).map((sample) => ({
title: trimRatingPrefix(sample.title) || null,
rating_text: cleanText(sample.rating_text) || null,
rating_value: parseRatingValue(sample.rating_text),
author: cleanText(sample.author) || null,
date_text: cleanText(sample.date_text) || null,
body: cleanText(sample.body) || null,
verified_purchase: sample.verified === true,
})),
};
}
async function readDiscussionPayload(page, input, limit) {
const url = buildDiscussionUrl(input);
const state = await gotoAndReadState(page, url, 2500, 'discussion');
assertUsableState(state, 'discussion');
return await page.evaluate(`
(() => ({
href: window.location.href,
title: document.title || '',
average_rating_text: document.querySelector('[data-hook="rating-out-of-text"]')?.textContent || '',
total_review_count_text: document.querySelector('[data-hook="total-review-count"]')?.textContent || '',
qa_links: Array.from(document.querySelectorAll('a[href*="ask/questions"]')).map((anchor) => anchor.href || ''),
review_samples: Array.from(document.querySelectorAll('[data-hook="review"]')).slice(0, ${limit}).map((card) => ({
title: card.querySelector('[data-hook="review-title"]')?.textContent || '',
rating_text:
card.querySelector('[data-hook="review-star-rating"]')?.textContent
|| card.querySelector('[data-hook="cmps-review-star-rating"]')?.textContent
|| '',
author: card.querySelector('.a-profile-name')?.textContent || '',
date_text: card.querySelector('[data-hook="review-date"]')?.textContent || '',
body: card.querySelector('[data-hook="review-body"]')?.textContent || '',
verified: !!card.querySelector('[data-hook="avp-badge"]'),
})),
}))()
`);
}
cli({
site: 'amazon',
name: 'discussion',
description: 'Amazon review summary and sample customer discussion from product review pages',
domain: 'amazon.com',
strategy: Strategy.COOKIE,
navigateBefore: false,
args: [
{
name: 'input',
required: true,
positional: true,
help: 'ASIN or product URL, for example B0FJS72893',
},
{
name: 'limit',
type: 'int',
default: 10,
help: 'Maximum number of review samples to return (default 10)',
},
],
columns: ['asin', 'average_rating_value', 'total_review_count'],
func: async (page, kwargs) => {
const input = String(kwargs.input ?? '');
const limit = Math.max(1, Number(kwargs.limit) || 10);
const payload = await readDiscussionPayload(page, input, limit);
const normalized = normalizeDiscussionPayload(payload);
if (!normalized.average_rating_text && !normalized.total_review_count_text) {
throw new CommandExecutionError('amazon discussion page did not expose review summary', 'The review page may have changed or hit a robot check. Open the review page in Chrome and retry.');
}
return [normalized];
},
});
export const __test__ = {
normalizeDiscussionPayload,
};