"rss": {
"feedType": string, // Currently not used - will allow for RSS vs Atom in future releases (currently only RSS is supported)
"waitTimeOverride_ms": integer, // Optional - if specified, controls the amount of time between successive reads to a site (default: 10s10000ms):
// ie if a site is timing out it may limit the number of accesses from a given IP - set the number higher
// for large sites you can increase the performance of the harvester by setting this number lower
"regexInclude": string, // Optional - if specified, only URLs matching the regex will be harvested
"regexExclude": string, // Optional - if specified, any URLs matching the regex will not be harvested
"extraUrls": [ // This array allows for manually specified URLs to be harvested once
{
"url": string, // The URL
"title": string, // The title that the document will be given (ie the equivalent to the RSS title)
"description": string // The description that the document will be given (ie the equivalent to the RSS description)
},
//etc
]
} |