INPUT_SCHEMA.json

{
    "title": "Schema for batch-cancel-accounts actor",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "domains": {
            "title": "Domains",
            "type": "string",
            "description": "List of domains to crawl. The domains must be naked, i.e. specified without a protocol and sub-domains (e.g. <code>example.com</code>).",
            "prefill": "example.com\niana.org\napify.com",
            "default": "",
            "editor": "textarea"
        },
        "domainsFileUrl": {
            "title": "Domains file URL",
            "type": "string",
            "description": "URL of a text file that contains the list of domains to crawl. The domains must be naked, i.e. specified without a protocol and sub-domains (e.g. <code>example.com</code>).<br><br>This field is useful if you have a large number of domains.",
            "editor": "textfield"
        },
        "domainsFileOffset": {
            "title": "Domains file offset",
            "type": "integer",
            "description": "Indicates how many domains from the file should be skipped in the beginning. This is useful if you only want to crawl a portion of the domains.",
            "default": 0,
            "minimum": 0,
            "maximum": 999999999
        },
        "domainsFileCount": {
            "title": "Domains file count",
            "type": "integer",
            "description": "Indicates how many domains from the file should be crawled, starting from the offset. This is useful if you only want to crawl a portion of the domains. Leave empty to crawl all domains.",
            "minimum": 0,
            "maximum": 999999999
        },
        "useChrome": {
            "title": "Use Chrome",
            "type": "boolean",
            "description": "If checked, the actor uses Chrome instead of Puppeteer's Chromium for the crawling. This might help to prevent blocking of some pages.",
            "default": false
        },
        "useApifyProxy": {
            "title": "Use Apify Proxy",
            "type": "boolean",
            "description": "If checked, the actor uses Apify Proxy to access the target pages. This might help to prevent blocking of some pages.",
            "default": false
        },
        "maxRequestRetries": {
            "title": "Max page retries",
            "type": "integer",
            "description": "Indicates how many times shall the crawler retry to load a page on error.",
            "prefill": 2,
            "default": 0,
            "minimum": 0,
            "maximum": 5
        },
        "crawlLinkCount": {
            "title": "Crawl domain links",
            "type": "integer",
            "description": "Indicates how many links from the main page going to the same domain shall also be crawled.",
            "prefill": 5,
            "default": 0,
            "minimum": 0,
            "maximum": 100
        },
        "crawlHttpsVersion": {
            "title": "Crawl HTTPS version",
            "type": "boolean",
            "description": "If checked, the actor attempts to crawl HTTPs version of the website (e.g. <code>https://example.com</code> for domain <code>example.com</code>).",
            "default": true
        },
        "crawlWwwSubdomain": {
            "title": "Crawl www. sub-domain",
            "type": "boolean",
            "description": "If checked, the actor attempts to crawl <code>www.</code> sub-domain of the website (e.g. <code>http://www.example.com</code> for domain <code>example.com</code>).",
            "default": true
        },
        "saveScreenshot": {
            "title": "Save screenshots",
            "type": "boolean",
            "description": "If checked, the actor stores screenshots of all loaded pages into the key-value store.",
            "default": true
        },
        "saveHtml": {
            "title": "Save HTML content",
            "type": "boolean",
            "description": "If checked, the actor stores HTML content of all loaded pages into the key-value store.",
            "default": true
        },
        "saveText": {
            "title": "Save text content",
            "type": "boolean",
            "description": "If checked, the actor stores text content of all loaded pages into the dataset results.",
            "default": true
        },
        "considerChildFrames": {
            "title": "Consider child frames",
            "type": "boolean",
            "description": "If checked, the actor searches for social handles even in the content of the first-level child frames. The 'page.text' also contains the combined text of the main frame and direct child frames.",
            "default": false
        }
    },
    "required": []
}