AI Data Extraction with Scrapfly API

Pipedream makes it easy to connect APIs for Scrapfly and 2,400+ other apps remarkably fast.

Trigger workflow on

HTTP requests, schedules and app events

Next, do this

AI Data Extraction with the Scrapfly API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

Create a workflow to AI Data Extraction with the Scrapfly API. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Configure the AI Data Extraction action
1. Connect your Scrapfly account
2. Configure Body
3. Select a Content Type
4. Configure URL
5. Optional- Configure Charset
6. Optional- Configure Extraction Template
7. Optional- Configure Extraction Prompt
8. Optional- Configure Extraction Model
9. Optional- Configure Webhook Name
Select a trigger to run your workflow on HTTP requests, schedules or app events
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Integrations#

AI Data Extraction with Scrapfly API on New Requests (Payload Only) from HTTP / Webhook API

HTTP / Webhook + Scrapfly

Try it

AI Data Extraction with Scrapfly API on New Submission from Typeform API

Typeform + Scrapfly

Try it

AI Data Extraction with Scrapfly API on New Submission (Instant) from Jotform API

Jotform + Scrapfly

Try it

AI Data Extraction with Scrapfly API on New Scheduled Tasks from Pipedream API

Pipedream + Scrapfly

Try it

AI Data Extraction with Scrapfly API on New Download Counts from npm API

npm + Scrapfly

Try it

Details#

This is a pre-built, source-available component from Pipedream's GitHub repo. The component is developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

AI Data Extraction on Scrapfly

Description:Automate content extraction from any text-based source using AI, LLM, and custom parsing. [See the documentation](https://scrapfly.io/docs/extraction-api/getting-started)

Version:0.0.1

Key:scrapfly-ai-data-extraction

View on GitHub

Code#

import { ConfigurationError } from "@pipedream/platform";
import fs from "fs";
import { checkTmp } from "../../common/utils.mjs";
import scrapfly from "../../scrapfly.app.mjs";

export default {
  key: "scrapfly-ai-data-extraction",
  name: "AI Data Extraction",
  description: "Automate content extraction from any text-based source using AI, LLM, and custom parsing. [See the documentation](https://scrapfly.io/docs/extraction-api/getting-started)",
  version: "0.0.1",
  type: "action",
  props: {
    scrapfly,
    body: {
      propDefinition: [
        scrapfly,
        "body",
      ],
    },
    contentType: {
      propDefinition: [
        scrapfly,
        "contentType",
      ],
    },
    url: {
      propDefinition: [
        scrapfly,
        "url",
      ],
    },
    charset: {
      type: "string",
      label: "Charset",
      description: "Charset of the document pass in the body. If you are not sure, you can use the `auto` value and we will try to detect it. Bad charset can lead to bad extraction, so it's important to set it correctly. **The most common charset is `utf-8` for text document and `ascii` for binary**. The symptom of a bad charset is that the text is not correctly displayed (accent, special characters, etc).",
      default: "auto",
      optional: true,
    },
    extractionTemplate: {
      type: "string",
      label: "Extraction Template",
      description: "Define an extraction template to get structured data. Use an ephemeral template (declared on the fly on the API call) or a stored template (declared in the dashboard) by using the template name.",
      optional: true,
    },
    extractionPrompt: {
      type: "string",
      label: "Extraction Prompt",
      description: "Instruction to extract data or ask a question on the scraped content with an LLM (Large Language Model). [Must be url encoded](https://scrapfly.io/web-scraping-tools/urlencode).",
      optional: true,
    },
    extractionModel: {
      type: "string",
      label: "Extraction Model",
      description: "AI Extraction to auto parse document to get structured data. E.g., `product`, `review`, `real-estate`, `article`.",
      optional: true,
    },
    webhookName: {
      type: "string",
      label: "Webhook Name",
      description: "Queue you scrape request and redirect API response to a provided webhook endpoint. You can create a webhook endpoint from your `dashboard`, it takes the name of the webhook. Webhooks are scoped to the given project/env.",
      optional: true,
    },
  },
  async run({ $ }) {
    if (!this.extractionTemplate && !this.extractionPrompt && !this.extractionModel) {
      throw new ConfigurationError("You must provide at least **Extraction Template**, **Extraction Prompt** or **Extraction Model**");
    }
    const response = await this.scrapfly.automateContentExtraction({
      $,
      headers: {
        "content-type": this.contentType,
      },
      maxBodyLength: Infinity,
      params: {
        url: this.url,
        charset: this.charset,
        extraction_template: this.extractionTemplate,
        extraction_prompt: this.extractionPrompt,
        extraction_model: this.extractionModel,
        webhook_name: this.webhookName,
      },
      data: fs.readFileSync(checkTmp(this.body)).toString(),
    });

    $.export("$summary", "Successfully extracted content");
    return response;
  },
};

Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
Scrapfly	`scrapfly`	`app`	This component uses the Scrapfly app.
Body	`body`	`string`	The request body must contain the content of the page you want to extract data from. The content must be in the format specified by the `content-type` header or via the `content_type` HTTP parameter. Provide a file from `/tmp`. To upload a file to `/tmp` folder, please follow the doc here
Content Type	`contentType`	`string`	Select a value from the drop down menu:`application/jsonapplication/jsonldapplication/xmltext/plaintext/htmltext/markdowntext/csvapplication/xhtml+xml`
URL	`url`	`string`	This URL is used to transform any relative URLs in the document into absolute URLs automatically. It can be either the base URL or the exact URL of the document. Must be url encoded.
Charset	`charset`	`string`	Charset of the document pass in the body. If you are not sure, you can use the `auto` value and we will try to detect it. Bad charset can lead to bad extraction, so it's important to set it correctly. The most common charset is `utf-8` for text document and `ascii` for binary. The symptom of a bad charset is that the text is not correctly displayed (accent, special characters, etc).
Extraction Template	`extractionTemplate`	`string`	Define an extraction template to get structured data. Use an ephemeral template (declared on the fly on the API call) or a stored template (declared in the dashboard) by using the template name.
Extraction Prompt	`extractionPrompt`	`string`	Instruction to extract data or ask a question on the scraped content with an LLM (Large Language Model). Must be url encoded.
Extraction Model	`extractionModel`	`string`	AI Extraction to auto parse document to get structured data. E.g., `product`, `review`, `real-estate`, `article`.
Webhook Name	`webhookName`	`string`	Queue you scrape request and redirect API response to a provided webhook endpoint. You can create a webhook endpoint from your `dashboard`, it takes the name of the webhook. Webhooks are scoped to the given project/env.