|
{ |
|
"title": "Input schema test", |
|
"type": "object", |
|
"schemaVersion": 1, |
|
"properties": { |
|
"startUrls": { |
|
"title": "Start URLs", |
|
"type": "array", |
|
"description": "URLs to start with", |
|
"default": [ |
|
{ "url": "http://example.com" } |
|
], |
|
"editor": "requestListSources" |
|
}, |
|
"startUrls2": { |
|
"title": "Start URLs", |
|
"type": "array", |
|
"description": "URLs to start with", |
|
"prefill": [ |
|
{ "url": "http://example.com" } |
|
], |
|
"editor": "requestListSources" |
|
}, |
|
"proxy": { |
|
"title": "Proxy configuration", |
|
"type": "object", |
|
"description": "Proxy configuration", |
|
"default": { "useApifyProxy": false }, |
|
"editor": "proxy" |
|
}, |
|
"pageFunction": { |
|
"title": "Page function", |
|
"type": "string", |
|
"description": "Function executed for each request", |
|
"default": "async () => {\n return $('title').text();\n\n}", |
|
"editor": "javascript" |
|
}, |
|
"textfieldProp": { |
|
"title": "Some text field", |
|
"type": "string", |
|
"description": "Xxx", |
|
"default": "blaah blaah", |
|
"editor": "textfield" |
|
}, |
|
"textfieldProp2": { |
|
"title": "Some text field with prefill", |
|
"type": "string", |
|
"description": "Xxx", |
|
"prefill": "tohle je prefill", |
|
"editor": "textfield" |
|
}, |
|
"textareaProp": { |
|
"title": "Some text area", |
|
"type": "string", |
|
"description": "Yyy", |
|
"default": "blaah\nblaah\nblaah", |
|
"editor": "textarea" |
|
}, |
|
"useRequestQueue": { |
|
"title": "Use request queue", |
|
"type": "boolean", |
|
"description": "Request queue enables recursive crawling", |
|
"default": false, |
|
"groupCaption": "Options", |
|
"groupDescription": "Various crawler settings" |
|
}, |
|
"verboseLog": { |
|
"title": "Verbose log", |
|
"type": "boolean", |
|
"description": "Debug messages will be included in the log.", |
|
"default": true |
|
}, |
|
"disableWebSecurity": { |
|
"title": "Disable web security?", |
|
"type": "boolean", |
|
"description": "Crawler will ignore SSL certificate errors.", |
|
"default": false |
|
}, |
|
"enumPropTitles": { |
|
"title": "Country", |
|
"type": "string", |
|
"description": "Select country", |
|
"default": "us", |
|
"enum": ["us", "fr", "de"], |
|
"enumTitles": ["USA", "France", "Germany"] |
|
}, |
|
"enumProp": { |
|
"title": "Country", |
|
"type": "string", |
|
"description": "Select country", |
|
"default": "us", |
|
"enum": ["us", "fr", "de"] |
|
}, |
|
"maxPagesPerCrawl": { |
|
"title": "Miximum pages per crawl", |
|
"type": "integer", |
|
"description": "Maximum number of pages that the crawler will open.", |
|
"minimum": 1, |
|
"maximum": 20, |
|
"default": 2, |
|
"unit": "Pages" |
|
}, |
|
"pseudoUrls": { |
|
"title": "Pseudo-URLs", |
|
"type": "array", |
|
"description": "Pseudo-URLs matching requests you want to enqueue", |
|
"editor": "json" |
|
}, |
|
"outputFormats": { |
|
"title": "Output formats", |
|
"type": "array", |
|
"description": "Select one or more formats to which the target web pages will be extracted and saved in the resulting dataset.", |
|
"editor": "select", |
|
"default": ["markdown"], |
|
"items": { |
|
"type": "string", |
|
"enum": ["text", "markdown", "html"], |
|
"enumTitles": ["Plain text", "Markdown", "HTML"] |
|
} |
|
} |
|
}, |
|
"required": ["startUrls", "pageFunction", "maxPagesPerCrawl"] |
|
} |