Effortlessly Extract Data

import { 
    ScrapflyClient, ExtractionConfig 
} from 'jsr:@scrapfly/scrapfly-sdk';

const client = new ScrapflyClient({ key: Deno.env.get("SCRAPFLY_KEY") });
// product from https://web-scraping.dev/product/1
const document_text = Deno.readTextFileSync("./product.html").toString();

const api_result = await client.extract(
    new ExtractionConfig({
        body: document_text,
        url: "https://web-scraping.dev/product/1",
        content_type: "text/html",
        extraction_prompt: "extract price as json",
    })
);
console.log(JSON.stringify(api_result));

import { 
    ScrapflyClient, ExtractionConfig 
} from 'jsr:@scrapfly/scrapfly-sdk';

const client = new ScrapflyClient({ key: Deno.env.get("SCRAPFLY_KEY") });
// product from https://web-scraping.dev/product/1
const document_text = Deno.readTextFileSync("./product.html").toString();

const api_result = await client.extract(
    new ExtractionConfig({
        body: document_text,
        url: "https://web-scraping.dev/product/1",
        extraction_prompt: "find the product price",
        // use almost any file type identified through content_type
        content_type: "text/html",
        // content_type: "text/xml",
        // content_type: "text/plain",
        // content_type: "text/markdown",
        // content_type: "application/json",
        // content_type: "application/csv",
    })
);
console.log(JSON.stringify(api_result));

import { 
    ScrapflyClient, ExtractionConfig 
} from 'jsr:@scrapfly/scrapfly-sdk';

const client = new ScrapflyClient({ key: Deno.env.get("SCRAPFLY_KEY") });
// product from https://web-scraping.dev/product/1
const document_text = Deno.readTextFileSync("./product.html").toString();

const api_result = await client.extract(
    new ExtractionConfig({
        body: document_text,
        content_type: "text/html",
        url: "https://web-scraping.dev/product/1",
        extraction_model: "product"
    })
);
console.log(JSON.stringify(api_result));

import { 
    ScrapflyClient, ExtractionConfig 
} from 'jsr:@scrapfly/scrapfly-sdk';

const client = new ScrapflyClient({ key: Deno.env.get("SCRAPFLY_KEY") });
// product from https://web-scraping.dev/product/1
const document_text = Deno.readTextFileSync("./product.html").toString();

const api_result = await client.extract(
    new ExtractionConfig({
        body: document_text,
        content_type: "text/html",
        url: "https://web-scraping.dev/product/1",
        extraction_model: "product"
    })
);
console.log(JSON.stringify(api_result));

import { 
    ScrapflyClient, ExtractionConfig 
} from 'jsr:@scrapfly/scrapfly-sdk';

const client = new ScrapflyClient({ key: Deno.env.get("SCRAPFLY_KEY") });
// product from https://web-scraping.dev/reviews
const document_text = Deno.readTextFileSync("./reviews.html").toString();

// define your template as JSON 
const template = {  
  "source": "html",
  "selectors": [
    {
      "name": "date_posted",
      // use css selectors
      "type": "css",
      "query": "[data-testid='review-date']::text",
      "multiple": true,  // one or multiple?
      // post process results with formatters
      "formatters": [ {
        "name": "datetime",
        "args": {"format": "%Y, %b %d — %A"}
      } ]
    }
  ]
}
const api_result = await client.extract(
    new ExtractionConfig({
        body: document_text,
        url: "https://web-scraping.dev/product/1",
        content_type: "text/html",
        ephemeral_template: template,
    })
);
console.log(JSON.stringify(api_result));