Bzj Amazon Actor
Under maintenance
Go to Store
This Actor is under maintenance.
This Actor may be unreliable while under maintenance. Would you like to try a similar Actor instead?
See alternative ActorsBzj Amazon Actor
fateful_orangerie/bzj-amazon-actor
Crawl and extract unlimited data using actors integrated with the scrapeless amazon scraper api
Developer
BazerMaintained by Community
Categories
.actor/Dockerfile
1# Specify the base Docker image. You can read more about
2# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
3# You can also use any other image from Docker Hub.
4FROM apify/actor-node:20 AS builder
5
6# Check preinstalled packages
7RUN npm ls crawlee apify puppeteer playwright
8
9# Copy just package.json and package-lock.json
10# to speed up the build using Docker layer cache.
11COPY package*.json ./
12
13# Install all dependencies. Don't audit to speed up the installation.
14RUN npm install --include=dev --audit=false
15
16# Next, copy the source files using the user set
17# in the base image.
18COPY . ./
19
20# Install all dependencies and build the project.
21# Don't audit to speed up the installation.
22RUN npm run build
23
24# Create final image
25FROM apify/actor-node:20
26
27# Check preinstalled packages
28RUN npm ls crawlee apify puppeteer playwright
29
30# Copy just package.json and package-lock.json
31# to speed up the build using Docker layer cache.
32COPY package*.json ./
33
34# Install NPM packages, skip optional and development dependencies to
35# keep the image small. Avoid logging too much and print the dependency
36# tree for debugging
37RUN npm --quiet set progress=false \
38 && npm install --omit=dev --omit=optional \
39 && echo "Installed NPM packages:" \
40 && (npm list --omit=dev --all || true) \
41 && echo "Node.js version:" \
42 && node --version \
43 && echo "NPM version:" \
44 && npm --version \
45 && rm -r ~/.npm
46
47# Copy built JS files from builder image
48COPY /usr/src/app/dist ./dist
49
50# Next, copy the remaining files and directories with the source code.
51# Since we do this after NPM install, quick build will be really fast
52# for most source file changes.
53COPY . ./
54
55
56# Run the image.
57CMD npm run start:prod --silent.actor/actor.json
1{
2 "actorSpecification": 1,
3 "name": "bzj-amazon-actor",
4 "title": "Scrape single page in TypeScript",
5 "description": "Scrape data from single page with provided URL.",
6 "version": "0.0",
7 "meta": {
8 "templateId": "ts-start"
9 },
10 "input": "./input_schema.json",
11 "dockerfile": "./Dockerfile",
12 "storages": {
13 "dataset": "./dataset_schema.json"
14 }
15}.actor/dataset_schema.json
1{
2 "actorSpecification": 1,
3 "views": {
4 "overview": {
5 "title": "Overview",
6 "transformation": {
7 "fields": [
8 "count",
9 "data",
10 "code",
11 "message"
12 ]
13 },
14 "display": {
15 "component": "table",
16 "properties": {
17 "count": {
18 "label": "count",
19 "format": "text"
20 },
21 "data": {
22 "label": "data",
23 "format": "object"
24 },
25 "code": {
26 "label": "code",
27 "format": "text"
28 },
29 "message": {
30 "label": "message",
31 "format": "text"
32 }
33 }
34 }
35 }
36 }
37}.actor/input_schema.json
1{
2 "title": "Actor BZJ",
3 "type": "object",
4 "schemaVersion": 1,
5 "properties": {
6 "apiKey": {
7 "title": "API Key",
8 "type": "string",
9 "editor": "textfield",
10 "description": "Start getting your [API KEY](https://app.scrapeless.com/dashboard/account?tab=apiKey) for free"
11 },
12 "action": {
13 "title": "Scraper Action",
14 "type": "string",
15 "enum": [
16 "keywords",
17 "product",
18 "seller"
19 ],
20 "description": "Amazon Scraper action types used for crawling",
21 "prefill": "keywords"
22 },
23 "webhook": {
24 "title": "webhook",
25 "type": "string",
26 "editor": "textfield",
27 "description": "webhook URL to send the data to",
28 "default": ""
29 },
30 "keywords": {
31 "title": "Keywords",
32 "sectionCaption": "keywords options",
33 "sectionDescription": "Configuration of action Product",
34 "type": "string",
35 "editor": "textfield",
36 "description": "Amazon keywords to search for",
37 "default": "iphone 12",
38 "prefill": "iPhone 12"
39 },
40 "maxConcurrency": {
41 "title": "Maximum concurrency",
42 "type": "integer",
43 "maximum": 100,
44 "description": "Maximum concurrency to use for crawling",
45 "default": 10,
46 "prefill": 10
47 },
48 "pages": {
49 "title": "Pages",
50 "type": "integer",
51 "maximum": 100,
52 "description": "Total number of pages crawled",
53 "default": 3,
54 "prefill": 3
55 },
56 "domain": {
57 "title": "Domain",
58 "type": "string",
59 "editor": "textfield",
60 "description": "Amazon domain",
61 "default": "com",
62 "prefill": "com"
63 },
64 "productUrl": {
65 "title": "Product details URL",
66 "sectionCaption": "product options",
67 "sectionDescription": "Configuration of action Product",
68 "type": "string",
69 "editor": "textfield",
70 "description": "Amazon product details URL",
71 "prefill": "https://www.amazon.com/dp/B0BQXHK363"
72 },
73 "sellerUrl": {
74 "title": "seller details URL",
75 "sectionCaption": "seller options",
76 "sectionDescription": "Configuration of action seller",
77 "type": "string",
78 "editor": "textfield",
79 "description": "Amazon seller details URL",
80 "prefill": "https://www.amazon.com/dp/B0BQXHK363"
81 }
82 },
83 "required": [
84 "apiKey",
85 "action"
86 ]
87}src/main.ts
1import { Actor, log } from 'apify';
2import Scrapeless from 'scrapeless-sdk-node';
3
4await Actor.init();
5
6enum AmazonActionEnum {
7 product = 'product',
8 seller = 'seller',
9 keywords = 'keywords',
10}
11
12interface Input {
13 apiKey: string;
14 action: AmazonActionEnum;
15 webhook: string;
16 productUrl: string;
17 sellerUrl: string;
18 keywords: string;
19 maxConcurrency: number
20 pages: number;
21 domain: string;
22}
23
24const {
25 apiKey = '',
26 action = AmazonActionEnum.keywords,
27 webhook = '',
28 keywords = 'iPhone 12',
29 domain = 'com',
30 pages = 3,
31 maxConcurrency = 10,
32 productUrl = 'https://www.amazon.com/dp/B0BQXHK363',
33 sellerUrl = 'https://www.amazon.com/dp/B0BQXHK363',
34} = await Actor.getInput<Input>() ?? {};
35
36const CONCURRENCY_LIMIT = pages < maxConcurrency ? pages : maxConcurrency;
37
38// @ts-expect-error scrapeless-sdk-node
39const scrapeless = new Scrapeless({ apiKey });
40
41function getScrapelessInput(currentPage = 1) {
42 const baseInput = { action };
43 if (action === AmazonActionEnum.seller) {
44 return { ...baseInput, url: sellerUrl };
45 }
46 if (action === AmazonActionEnum.product) {
47 return { ...baseInput, url: productUrl };
48 }
49 // keywords
50 return { ...baseInput, keywords, page: currentPage.toString(), domain };
51}
52
53async function scraperFetch() {
54 const response = await scrapeless.scraper({
55 actor: 'scraper.amazon',
56 webhook,
57 input: getScrapelessInput(),
58 });
59 await Actor.pushData(response as object);
60}
61
62async function keywordsConcurrencyScraperFetch() {
63 const RequestQueue: (() => Promise<object>)[] = [];
64 for (let page = 1; page <= pages; page++) {
65 RequestQueue.push(() => {
66 return scrapeless.scraper({
67 actor: 'scraper.amazon',
68 webhook,
69 input: getScrapelessInput(page),
70 });
71 });
72 }
73
74 const successfulResults: object[] = [];
75 let currentIndex = 0;
76 async function worker() {
77 while (currentIndex < RequestQueue.length) {
78 try {
79 log.info(`[Current page number]: ${currentIndex + 1}`);
80 const result = await RequestQueue[currentIndex++]();
81 await Actor.pushData(result);
82 successfulResults.push(result);
83 } catch (error) {
84 log.error(`[Request failed]: ${error}`);
85 }
86 }
87 }
88
89 const workers = [];
90 for (let i = 1; i <= CONCURRENCY_LIMIT; i++) {
91 workers.push(worker());
92 }
93 await Promise.all(workers);
94 log.info(`[🎉 Successfully captured ${successfulResults.length} pages of data]`);
95 await Actor.setValue('OUTPUT', successfulResults);
96}
97
98if (action === AmazonActionEnum.keywords) {
99 await keywordsConcurrencyScraperFetch();
100} else {
101 await scraperFetch();
102}
103
104await Actor.exit();.dockerignore
1# configurations
2.idea
3.vscode
4
5# crawlee and apify storage folders
6apify_storage
7crawlee_storage
8storage
9
10# installed files
11node_modules
12
13# git folder
14.git
15
16# dist folder
17dist.editorconfig
1root = true
2
3[*]
4indent_style = space
5indent_size = 4
6charset = utf-8
7trim_trailing_whitespace = true
8insert_final_newline = true
9end_of_line = lf.eslintrc
1{
2 "root": true,
3 "env": {
4 "browser": true,
5 "es2020": true,
6 "node": true
7 },
8 "extends": [
9 "@apify/eslint-config-ts"
10 ],
11 "parserOptions": {
12 "project": "./tsconfig.json",
13 "ecmaVersion": 2020
14 },
15 "ignorePatterns": [
16 "node_modules",
17 "dist",
18 "**/*.d.ts"
19 ]
20}.gitignore
1# This file tells Git which files shouldn't be added to source control
2
3.idea
4.vscode
5storage
6apify_storage
7crawlee_storage
8node_modules
9dist
10tsconfig.tsbuildinfo
11storage/*
12!storage/key_value_stores
13storage/key_value_stores/*
14!storage/key_value_stores/default
15storage/key_value_stores/default/*
16!storage/key_value_stores/default/INPUT.json
17
18# Added by Apify CLI
19.venvpackage.json
1{
2 "name": "bzj-amazon-actor",
3 "version": "0.0.1",
4 "type": "module",
5 "description": "This is an example of an Apify actor.",
6 "engines": {
7 "node": ">=18.0.0"
8 },
9 "dependencies": {
10 "apify": "^3.2.6",
11 "axios": "^1.5.0",
12 "cheerio": "^1.0.0-rc.12",
13 "scrapeless-sdk-node": "^0.0.3"
14 },
15 "devDependencies": {
16 "@apify/eslint-config-ts": "^0.3.0",
17 "@apify/tsconfig": "^0.1.0",
18 "@typescript-eslint/eslint-plugin": "^7.18.0",
19 "@typescript-eslint/parser": "^7.18.0",
20 "eslint": "^8.50.0",
21 "tsx": "^4.6.2",
22 "typescript": "^5.3.3"
23 },
24 "scripts": {
25 "start": "npm run start:dev",
26 "start:prod": "node dist/main.js",
27 "start:dev": "tsx src/main.ts",
28 "build": "tsc",
29 "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
30 },
31 "author": "It's not you it's me",
32 "license": "ISC"
33}tsconfig.json
1{
2 "extends": "@apify/tsconfig",
3 "compilerOptions": {
4 "module": "NodeNext",
5 "moduleResolution": "NodeNext",
6 "target": "ES2022",
7 "outDir": "dist",
8 "noUnusedLocals": false,
9 "skipLibCheck": true,
10 "lib": ["DOM"]
11 },
12 "include": [
13 "./src/**/*"
14 ]
15}
