Add data to dataset

This example demonstrates how to store extracted data into datasets using the context.push_data() helper function. If the specified dataset does not already exist, it will be created automatically. Additionally, you can save data to custom datasets by providing dataset_id or dataset_name parameters to the push_data method.

BeautifulSoupCrawler

import asyncio

from crawlee.beautifulsoup_crawler import BeautifulSoupCrawler, BeautifulSoupCrawlingContext


async def main() -> None:
    crawler = BeautifulSoupCrawler()

    # Define the default request handler, which will be called for every request.
    @crawler.router.default_handler
    async def request_handler(context: BeautifulSoupCrawlingContext) -> None:
        context.log.info(f'Processing {context.request.url} ...')

        # Extract data from the page.
        data = {
            'url': context.request.url,
            'title': context.soup.title.string,
            'html': str(context.soup)[:1000],
        }

        # Push the extracted data to the default dataset.
        await context.push_data(data)

    # Run the crawler with the initial list of requests.
    await crawler.run(
        [
            'https://crawlee.dev',
            'https://apify.com',
            'https://example.com',
        ]
    )


if __name__ == '__main__':
    asyncio.run(main())

PlaywrightCrawler

import asyncio

from crawlee.playwright_crawler import PlaywrightCrawler, PlaywrightCrawlingContext


async def main() -> None:
    crawler = PlaywrightCrawler()

    # Define the default request handler, which will be called for every request.
    @crawler.router.default_handler
    async def request_handler(context: PlaywrightCrawlingContext) -> None:
        context.log.info(f'Processing {context.request.url} ...')

        # Extract data from the page.
        data = {
            'url': context.request.url,
            'title': await context.page.title(),
            'html': str(await context.page.content())[:1000],
        }

        # Push the extracted data to the default dataset.
        await context.push_data(data)

    # Run the crawler with the initial list of requests.
    await crawler.run(
        [
            'https://crawlee.dev',
            'https://apify.com',
            'https://example.com',
        ]
    )


if __name__ == '__main__':
    asyncio.run(main())

Each item in the dataset will be stored in its own file within the following directory:

{PROJECT_FOLDER}/storage/datasets/default/

For more control, you can also open a dataset manually using the asynchronous constructor Dataset.open() and interact with it directly:

from crawlee.storages import Dataset

# ...

async def main() -> None:
    # Open dataset manually using asynchronous constructor open().
    dataset = await Dataset.open()

    # Interact with dataset directly.
    await dataset.push_data({'key': 'value'})

# ...