"searchConfig": {
"userAgent": string, // (Optional) Overrides the "parent" (rss) setting for "search" operations (see usage guide)
"proxyOverride": string, // (Optional) "direct" to bypass proxy (the default), or a proxy specification "(http|socks)://host:port"
"cookies": string, // (Optional) appends this string to the "Cookies" field (can included multiple semi-colon separated cookie values). If not specified then uses rss.cookies (if specified).
"globals": string, // Optional Javascript that is evaluated before script or extraMeta (ie to define global functions)
"script": string, // (Mandatory) Script, must "return" (last statement evaluated) an array of the following format:
// [ { "url": string, "title": string /* optional-ish */,
// "description": string /* optional */, publishedDate: string /* optional */,
// "spiderOut": string /*optional */ }
"scriptlang": string, // (Mandatory) Only "javascript" is supported, use extraMeta for different script types
"scriptflags": string, // (Optional) The flags to apply to the above script, see "unstructuredAnalysis.meta" for more details
"extraMeta": [ {...} ], // (Optional) A pipeline of metadata extraction operations that are applied prior to "script", see "Using The Feed Harvester" overview
"pageChangeRegex": string, // (Optional) If non-null, this regex should be used to match the pagination URL parameter (which will be replaced by pageChangeReplace)
// Also, group 1 should be the start, to allow any offsets specified in the URL to be respected
"pageChangeReplace": string, // (Optional) Mandatory if pageChangeRegex is non-null, must be a replace string where $1 is the page*numResultsPerPage
"numPages": integer, // (Optional) Mandatory if pageChangeRegex is non-null - controls the number of pages deep the search will go
"stopPaginatingOnDuplicate": boolean, // (Ignored unless pageChangeRegex is non-null) If true (default: false) then will stop harvesting as soon as an already harvested link is encountered
// (for APIs that return docs in time order, ensures that no time is wasted harvesting and then discarding duplicate links)
"numResultsPerPage": integer, // (Optional) Mandatory if pageChangeRegex is non-null - controls the number of results per page
"waitTimeBetweenPages_ms": integer, // (Optional) Only used if pageChangeRegex is non-null - controls a wait between successive pages if set
"maxDepth": integer // (Optional, defaults to 2) If spidering out (returning "spiderOut": "true" from the script) the maximum depth to go
} |