CSS Extraction

interface CssExtractionSchema {
  name: string;          // Schema name (for identification)
  baseSelector: string;  // CSS selector for repeating elements
  fields: CssField[];    // Fields to extract from each element
}

interface CssField {
  name: string;                              // Output field name
  selector: string;                          // CSS selector within base element
  type: "text" | "attribute" | "html" | "list"; // Extraction type
  attribute?: string;                        // For "attribute" type (default: "href")
}

const result = await crawler.crawl("https://store.example.com", {
  extractionStrategy: {
    type: "css",
    params: {
      name: "products",
      baseSelector: ".product-card",
      fields: [
        { name: "title", selector: ".product-title", type: "text" },
        { name: "price", selector: ".price", type: "text" },
        { name: "url", selector: "a.product-link", type: "attribute", attribute: "href" },
        { name: "image", selector: "img", type: "attribute", attribute: "src" },
        { name: "tags", selector: ".tag", type: "list" },
        { name: "description", selector: ".desc", type: "html" },
      ],
    },
  },
});

const products = JSON.parse(result.extractedContent!).map(
  (item) => JSON.parse(item.content)
);
// [{ title: "Widget A", price: "$9.99", url: "/widget-a", tags: ["sale", "new"] }, ...]

import { CssExtractionStrategy } from "feedstock";

const strategy = new CssExtractionStrategy({
  name: "articles",
  baseSelector: "article",
  fields: [
    { name: "headline", selector: "h2", type: "text" },
    { name: "body", selector: ".content", type: "html" },
  ],
});

const items = await strategy.extract(url, html);