forked from D-Net/dnet-hadoop
44 lines
1.2 KiB
JSON
44 lines
1.2 KiB
JSON
[
|
|
{
|
|
"paramName": "n",
|
|
"paramLongName": "nameNode",
|
|
"paramDescription": "the Name Node URI",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "w",
|
|
"paramLongName": "workingPath",
|
|
"paramDescription": "the working path",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "r",
|
|
"paramLongName": "rdfOutput",
|
|
"paramDescription": "the working path",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "u",
|
|
"paramLongName": "sitemapUrl",
|
|
"paramDescription": "the sitemap url",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "k",
|
|
"paramLongName": "sitemapURLKey",
|
|
"paramDescription": "the sitemap file contains a list of xml entries, each one has a tag identified with sitemapURLKey with the url as value",
|
|
"paramRequired": true
|
|
},
|
|
{
|
|
"paramName": "d",
|
|
"paramLongName": "dynamic",
|
|
"paramDescription": "the dynamic boolean determines if the scraper should start using selenium or JSOUP to scrape the information (dynamic and static respectively)",
|
|
"paramRequired": false
|
|
},
|
|
{
|
|
"paramName": "m",
|
|
"paramLongName": "maxScrapedPages",
|
|
"paramDescription": "max number of pages that will be scraped, default: no limit",
|
|
"paramRequired": false
|
|
}
|
|
] |