Pricing
Pay per usage
Scrape Harney Sons Fine Teas and extract data on coffee and tea from harney.com. Our Harney Sons Fine Teas API lets you crawl product information and pricing. The saved data can be downloaded as HTML, JSON, CSV, Excel, and XML.
0.0 (0)
Pricing
Pay per usage
1
4
2
Last modified
3 years ago
{ "title": "harney-and-sons-fine-scraper", "description": "", "type": "object", "schemaVersion": 1, "properties": { "maxRequestsPerCrawl": { "title": "Max items", "description": "How many items to extract from harney.com", "default": 20, "prefill": 20, "type": "integer", "editor": "number" }, "extendOutputFunction": { "title": "Extend Output Function", "description": "Add or remove properties on the output object or omit the output returning null", "type": "string", "default": "async ({ data, item, product, images, fns, name, request, variants, context, customData, input, Apify }) => {\n return item;\n}", "prefill": "async ({ data, item, product, images, fns, name, request, variants, context, customData, input, Apify }) => {\n return item;\n}", "editor": "javascript", "sectionCaption": "Extend scraper functionality", "sectionDescription": "You can change the output of the items for your dataset here, or add additional behavior on the scraper." }, "extendScraperFunction": { "title": "Extend Scraper Function", "description": "Advanced function that allows you to extend the default scraper functionality, allowing you to manually perform actions on the page", "type": "string", "default": "async ({ fns, customData, Apify, label }) => {\n \n}", "prefill": "async ({ fns, customData, Apify, label }) => {\n \n}", "editor": "javascript" }, "customData": { "title": "Custom data", "description": "Any data that you want to have available inside the Extend Output/Scraper Function", "default": {}, "prefill": {}, "type": "object", "editor": "json" }, "fetchHtml": { "title": "Fetch HTML", "description": "If you decide to fetch the HTML of the pages, it will take twice as long. Make sure to only enable this if needed", "default": true, "editor": "checkbox", "type": "boolean" }, "maxConcurrency": { "title": "Max concurrency", "description": "Max concurrency to use", "default": 20, "prefill": 20, "type": "integer", "editor": "number" }, "maxRequestRetries": { "title": "Max request retries", "description": "Set the max request retries", "default": 3, "prefill": 3, "type": "integer", "editor": "number" }, "debugLog": { "title": "Debug Log", "description": "Enable a more verbose logging to be able to understand what's happening during the scraping", "type": "boolean", "default": false, "editor": "checkbox" } }}1import Apify from 'apify';2
3Apify.main(async () => {4 const input = await Apify.getInput();5
6 await Apify.metamorph('pocesar/shopify-scraper', {7 ...input,8 startUrls: [{9 url: 'http://www.harney.com',10 }],11 });12});{ "name": "harney-and-sons-fine-scraper", "version": "0.0.1", "type": "module", "dependencies": { "apify": "^2.3.2" }, "scripts": { "start": "node main.js" }}# First, specify the base Docker image. You can read more about# the available images at https://sdk.apify.com/docs/guides/docker-images# You can also use any other image from Docker Hub.FROM apify/actor-node:16
# Second, copy just package.json and package-lock.json since those are the only# files that affect "npm install" in the next step, to speed up the build.COPY package*.json ./
RUN npm --quiet set progress=false \ && npm install --only=prod --no-optional \ && echo "Installed NPM packages:" \ && (npm list --only=prod --no-optional --all || true) \ && echo "Node.js version:" \ && node --version \ && echo "NPM version:" \ && npm --version
COPY . ./
ENV APIFY_DISABLE_OUTDATED_WARNING 1ENV npm_config_loglevel=silent