How to use the apify.openDataset function in apify

To help you get started, we’ve selected a few apify examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github apifytech / actor-scraper / cheerio-scraper / src / crawler_setup.js View on Github external
async _initializeAsync() {
        // RequestList
        const startUrls = this.input.startUrls.map((req) => {
            req.useExtendedUniqueKey = true;
            req.keepUrlFragment = this.input.keepUrlFragments;
            return req;
        });
        this.requestList = await Apify.openRequestList('CHEERIO_SCRAPER', startUrls);

        // RequestQueue if selected
        if (this.input.useRequestQueue) this.requestQueue = await Apify.openRequestQueue();

        // Dataset
        this.dataset = await Apify.openDataset();
        const { itemsCount } = await this.dataset.getInfo();
        this.pagesOutputted = itemsCount || 0;

        // KeyValueStore
        this.keyValueStore = await Apify.openKeyValueStore();
    }
github apifytech / actor-scraper / puppeteer-scraper / src / crawler_setup.js View on Github external
async _initializeAsync() {
        // RequestList
        const startUrls = this.input.startUrls.map((req) => {
            req.useExtendedUniqueKey = true;
            req.keepUrlFragment = this.input.keepUrlFragments;
            return req;
        });
        this.requestList = await Apify.openRequestList('PUPPETEER_SCRAPER', startUrls);

        // RequestQueue if selected
        if (this.input.useRequestQueue) this.requestQueue = await Apify.openRequestQueue();

        // Dataset
        this.dataset = await Apify.openDataset();
        const { itemsCount } = await this.dataset.getInfo();
        this.pagesOutputted = itemsCount || 0;

        // KeyValueStore
        this.keyValueStore = await Apify.openKeyValueStore();
    }
github apifytech / actor-scraper / web-scraper / src / crawler_setup.js View on Github external
async _initializeAsync() {
        // RequestList
        const startUrls = this.input.startUrls.map((req) => {
            req.useExtendedUniqueKey = true;
            req.keepUrlFragment = this.input.keepUrlFragments;
            return req;
        });
        this.requestList = await Apify.openRequestList('WEB_SCRAPER', startUrls);

        // RequestQueue if selected
        if (this.input.useRequestQueue) this.requestQueue = await Apify.openRequestQueue();

        // Dataset
        this.dataset = await Apify.openDataset();
        const { itemsCount } = await this.dataset.getInfo();
        this.pagesOutputted = itemsCount || 0;

        // KeyValueStore
        this.keyValueStore = await Apify.openKeyValueStore();
    }
github VaclavRut / actor-amazon-crawler / src / utils.js View on Github external
async function checkSaveCount(datasetId, maxResults) {
    const dataset = await Apify.openDataset(datasetId);
    const { itemCount } = await dataset.getInfo();

    if (maxResults === null || maxResults === 0) {
        return true;
    }

    if (itemCount < maxResults) {
        return true;
    }
    return false;
}

apify

The scalable web crawling and scraping library for JavaScript/Node.js. Enables development of data extraction and web automation jobs (not only) with headless Chrome and Puppeteer.

Apache-2.0
Latest version published 1 month ago

Package Health Score

87 / 100
Full package analysis