Scrape books from URL with Dumpling AI, clean HTML, save to Sheets, email as CSV

# n8n Workflow: Scrape Books from URL, Clean HTML, Save to Google Sheets, and Email as CSV

This n8n workflow automates the process of extracting book information from a specified URL, cleaning the HTML content using AI (Dumpling AI, implied by the directory name but not explicitly in JSON), structuring the data, saving it to a Google Sheet, and finally emailing the data as a CSV attachment.

## What it does

This workflow performs the following steps:

1.  **Triggers on Google Sheet Update**: The workflow starts whenever a specified Google Sheet is updated, likely with a URL to scrape.
2.  **Fetches HTML Content**: It makes an HTTP request to the URL provided in the Google Sheet to retrieve the raw HTML content of the webpage.
3.  **Parses HTML**: The HTML content is then processed to extract relevant data, likely book titles, authors, prices, or other details.
4.  **Splits Data**: The extracted data is split into individual items, preparing it for further processing.
5.  **Sorts Data**: The extracted data items are sorted, potentially by a key field like title or author.
6.  **Converts to CSV**: The structured and sorted data is converted into a CSV file format.
7.  **Sends Email with CSV**: The generated CSV file is attached to an email and sent via Gmail.

## Prerequisites/Requirements

To use this workflow, you will need:

*   **n8n Instance**: A running n8n instance.
*   **Google Sheets Account**: A Google account with access to Google Sheets for the trigger and potentially for storing data (though the JSON only shows a trigger).
*   **Gmail Account**: A Gmail account for sending the email with the CSV attachment.
*   **Credentials**: Configured n8n credentials for:
    *   Google Sheets (OAuth2 recommended)
    *   Gmail (OAuth2 recommended)

## Setup/Usage

1.  **Import the Workflow**: Download the provided JSON and import it into your n8n instance.
2.  **Configure Credentials**:
    *   Set up your **Google Sheets** credential.
    *   Set up your **Gmail** credential.
3.  **Configure Google Sheets Trigger (Node 841)**:
    *   Specify the Google Sheet ID and the sheet name that will trigger the workflow.
    *   Ensure the sheet contains a column with the URLs you want to scrape.
4.  **Configure HTTP Request (Node 19)**:
    *   Ensure this node correctly references the URL from the Google Sheets trigger (e.g., `{{ $json.url_column_name }}`).
5.  **Configure HTML Node (Node 842)**:
    *   Adjust the CSS selectors or XPath expressions to accurately extract the desired book information (e.g., title, author, price) from the HTML content.
6.  **Configure Gmail Node (Node 356)**:
    *   Specify the recipient email address, subject, and body for the email.
    *   Ensure the CSV file from the "Convert to File" node is correctly attached.
7.  **Activate the Workflow**: Once configured, activate the workflow. It will now run automatically whenever the specified Google Sheet is updated.

**Note on "Dumpling AI Clean HTML"**: While the directory name suggests the use of "Dumpling AI" for cleaning HTML, the provided JSON does not explicitly contain a node or configuration for an AI service. The HTML cleaning and data extraction are handled by the generic "HTML" node, which relies on CSS selectors or XPath. If "Dumpling AI" is a custom script or an external service, it would need to be integrated, perhaps via a Function node or another HTTP Request node, which is not present in this JSON. The workflow as defined focuses on standard HTML parsing.