Scrape Structured Web Data

curl -X POST https://api.iterationlayer.com/document-extraction/v1/extract \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "files": [
      {
        "type": "url",
        "name": "page.html",
        "url": "https://example.com/products/widget-pro"
      }
    ],
    "schema": {
      "fields": [
        { "name": "page_title", "type": "TEXT", "description": "Title of the web page" },
        { "name": "headings", "type": "ARRAY", "description": "List of headings on the page", "fields": [
          { "name": "text", "type": "TEXT", "description": "Heading text" }
        ]},
        { "name": "links", "type": "ARRAY", "description": "List of links on the page", "fields": [
          { "name": "text", "type": "TEXT", "description": "Link anchor text" },
          { "name": "url", "type": "TEXT", "description": "Link URL" }
        ]}
      ]
    }
  }'

import { IterationLayer } from "iterationlayer";
const client = new IterationLayer({ apiKey: "YOUR_API_KEY" });

const result = await client.extract({
  files: [
    {
      type: "url",
      name: "page.html",
      url: "https://example.com/products/widget-pro",
    },
  ],
  schema: {
    fields: [
      { name: "page_title", type: "TEXT", description: "Title of the web page" },
      { name: "headings", type: "ARRAY", description: "List of headings on the page", fields: [
        { name: "text", type: "TEXT", description: "Heading text" },
      ]},
      { name: "links", type: "ARRAY", description: "List of links on the page", fields: [
        { name: "text", type: "TEXT", description: "Link anchor text" },
        { name: "url", type: "TEXT", description: "Link URL" },
      ]},
    ],
  },
});

console.log(result);

from iterationlayer import IterationLayer
client = IterationLayer(api_key="YOUR_API_KEY")

result = client.extract(
    files=[
        {
            "type": "url",
            "name": "page.html",
            "url": "https://example.com/products/widget-pro",
        }
    ],
    schema={
        "fields": [
            {"name": "page_title", "type": "TEXT", "description": "Title of the web page"},
            {"name": "headings", "type": "ARRAY", "description": "List of headings on the page", "fields": [
                {"name": "text", "type": "TEXT", "description": "Heading text"},
            ]},
            {"name": "links", "type": "ARRAY", "description": "List of links on the page", "fields": [
                {"name": "text", "type": "TEXT", "description": "Link anchor text"},
                {"name": "url", "type": "TEXT", "description": "Link URL"},
            ]},
        ]
    },
)

print(result)

package main

import il "github.com/iterationlayer/sdk-go"

client := il.NewClient("YOUR_API_KEY")

result, err := client.Extract(il.ExtractRequest{
    Files: []il.FileInput{
        il.NewFileFromURL("page.html", "https://example.com/products/widget-pro"),
    },
    Schema: il.ExtractionSchema{
        "page_title": il.NewTextFieldConfig("page_title", "Title of the web page"),
        "headings": il.NewArrayFieldConfig("headings", "List of headings on the page", []il.FieldConfig{
            il.NewTextFieldConfig("text", "Heading text"),
        }),
        "links": il.NewArrayFieldConfig("links", "List of links on the page", []il.FieldConfig{
            il.NewTextFieldConfig("text", "Link anchor text"),
            il.NewTextFieldConfig("url", "Link URL"),
        }),
    },
})