Feed Source
The following code samples show how to create a basic source that extracts data from an RSS feed.
Sample RSS Feed Source
{
"description": "Article on Medical Issues",
"harvestBadSource": false,
"isApproved": true,
"isPublic": true,
"key": "http.www.mayoclinic.com.rss.blog.xml",
"mediaType": "News",
"modified": "Oct 19, 2010 11:31:59 AM",
"tags": [
"topic:healthcare",
"industry:healthcare",
"mayo clinic",
"health"
],
"title": "MayoClinic: General Topics",
"processingPipeline": [
{
"feed": {
"extraUrls": [
{
"url": "http://www.mayoclinic.com/rss/blog.xml"
}
]
}
},
{
"textEngine": {
"engineName": "AlchemyAPI"
}
},
{
"featureEngine": {
"engineName": "OpenCalais"
}
}
]
}
.
Sample Output from RSS Feed Source Above
{
"_id" : "4e1c8afa7d56bb818ed10f76",
"created" : "1310493434159",
"description" : "Clarify the role of carbohydrates in the Dr. Bernstein diet and find a
healthy eating plan that works for you.",
"entities" : [
{
"actual_name" : "certified diabetes",
"dimension" : "What",
"disambiguous_name" : "certified diabetes",
"doccount" : NumberLong(38),
"frequency" : 3,
"gazateer_index" : "certified diabetes/medicalcondition",
"relevance" : "0.711",
"totalfrequency" : NumberLong(114),
"type" : "MedicalCondition"
},
{
"actual_name" : "Diabetes Unit",
"dimension" : "Who",
"disambiguous_name" : "Diabetes Unit",
"doccount" : NumberLong(38),
"frequency" : 1,
"gazateer_index" : "diabetes unit/organization",
"relevance" : "0.235",
"totalfrequency" : NumberLong(38),
"type" : "Organization"
},
{
"actual_name" : "Mayo Clinic",
"dimension" : "What",
"disambiguous_name" : "Mayo Clinic",
"doccount" : NumberLong(514),
"frequency" : 2,
"gazateer_index" : "mayo clinic/facility",
"relevance" : "0.305",
"totalfrequency" : NumberLong(1033),
"type" : "Facility"
},
{
"actual_name" : "Rochester",
"dimension" : "Where",
"disambiguous_name" : "Rochester,Minnesota,United States",
"doccount" : NumberLong(345),
"frequency" : 2,
"gazateer_index" : "rochester,minnesota,united states/city",
"geotag" : {
"latitude" : "44.0217",
"longitude" : "-92.4697",
"loc" : [
44.0217,
-92.4697
]
},
"linkdata" : [
"http://d.opencalais.com/er/geo/city/ralg-geo1/9d780656-b9a4-6789-bcaf-370cabc32490"
],
"relevance" : "0.305",
"totalfrequency" : NumberLong(404),
"type" : "City"
},
{
"actual_name" : "Minnesota",
"dimension" : "Where",
"disambiguous_name" : "Minnesota,United States",
"doccount" : NumberLong(2103),
"frequency" : 2,
"gazateer_index" : "minnesota,united states/provinceorstate",
"geotag" : {
"latitude" : "46.0",
"longitude" : "-94.0",
"loc" : [
46,
-94
]
},
"linkdata" : [
"http://d.opencalais.com/er/geo/provinceorstate/ralg-geo1/b99d1bcd-ec35-113e-54ad-4d6c44682ce1"
],
"relevance" : "0.305",
"totalfrequency" : NumberLong(3134),
"type" : "ProvinceOrState"
},
{
"actual_name" : "R.N.",
"dimension" : "Who",
"disambiguous_name" : "R.N.",
"doccount" : NumberLong(108),
"frequency" : 1,
"gazateer_index" : "r.n./position",
"relevance" : "0.138",
"totalfrequency" : NumberLong(130),
"type" : "Position"
},
{
"actual_name" : "coordinator",
"dimension" : "Who",
"disambiguous_name" : "coordinator",
"doccount" : NumberLong(220),
"frequency" : 1,
"gazateer_index" : "coordinator/position",
"relevance" : "0.235",
"totalfrequency" : NumberLong(238),
"type" : "Position"
},
{
"actual_name" : "Division of Endocrinology, Diabetes, Metabolism, & Nutrition",
"dimension" : "Who",
"disambiguous_name" : "Division of Endocrinology, Diabetes, Metabolism, & Nutrition",
"doccount" : NumberLong(38),
"frequency" : 2,
"gazateer_index" : "division of endocrinology, diabetes, metabolism, & nutrition/organization",
"relevance" : "0.305",
"totalfrequency" : NumberLong(76),
"type" : "Organization"
},
{
"actual_name" : "self-management",
"dimension" : "What",
"disambiguous_name" : "self-management",
"doccount" : NumberLong(72),
"frequency" : 1,
"gazateer_index" : "self-management/medicaltreatment",
"relevance" : "0.076",
"totalfrequency" : NumberLong(78),
"type" : "MedicalTreatment"
},
{
"actual_name" : "Peggy Moreland",
"dimension" : "Who",
"disambiguous_name" : "Peggy Moreland",
"doccount" : NumberLong(38),
"frequency" : 3,
"gazateer_index" : "peggy moreland/person",
"relevance" : "0.358",
"totalfrequency" : NumberLong(114),
"type" : "Person"
},
{
"actual_name" : "University of Phoenix",
"dimension" : "What",
"disambiguous_name" : "University of Phoenix",
"doccount" : NumberLong(64),
"frequency" : 1,
"gazateer_index" : "university of phoenix/facility",
"relevance" : "0.102",
"totalfrequency" : NumberLong(68),
"type" : "Facility"
},
{
"actual_name" : "registered nurse",
"dimension" : "Who",
"disambiguous_name" : "registered nurse",
"doccount" : NumberLong(69),
"frequency" : 1,
"gazateer_index" : "registered nurse/position",
"relevance" : "0.335",
"totalfrequency" : NumberLong(70),
"type" : "Position"
},
{
"actual_name" : "American Diabetes Association",
"dimension" : "Who",
"disambiguous_name" : "American Diabetes Association",
"doccount" : NumberLong(120),
"frequency" : 1,
"gazateer_index" : "american diabetes association/organization",
"relevance" : "0.102",
"totalfrequency" : NumberLong(226),
"type" : "Organization"
},
{
"actual_name" : "N.\n Peggy Moreland",
"dimension" : "Who",
"disambiguous_name" : "N.\n Peggy Moreland",
"doccount" : NumberLong(38),
"frequency" : 1,
"gazateer_index" : "n.\n peggy moreland/person",
"relevance" : "0.146",
"totalfrequency" : NumberLong(38),
"type" : "Person"
},
{
"actual_name" : "insulin pump",
"dimension" : "What",
"disambiguous_name" : "insulin pump",
"doccount" : NumberLong(52),
"frequency" : 1,
"gazateer_index" : "insulin pump/medicaltreatment",
"relevance" : "0.184",
"totalfrequency" : NumberLong(69),
"type" : "MedicalTreatment"
},
{
"actual_name" : "M.S.N.\n Peggy",
"dimension" : "Who",
"disambiguous_name" : "M.S.N.\n Peggy",
"doccount" : NumberLong(38),
"frequency" : 2,
"gazateer_index" : "m.s.n.\n peggy/person",
"relevance" : "0.482",
"totalfrequency" : NumberLong(76),
"type" : "Person"
},
{
"actual_name" : "Nancy Klobassa Davidson",
"dimension" : "Who",
"disambiguous_name" : "Nancy Klobassa Davidson",
"doccount" : NumberLong(38),
"frequency" : 5,
"gazateer_index" : "nancy klobassa davidson/person",
"relevance" : "0.659",
"totalfrequency" : NumberLong(190),
"type" : "Person"
},
{
"actual_name" : "University of Phoenix",
"dimension" : "Who",
"disambiguous_name" : "University of Phoenix",
"doccount" : NumberLong(65),
"frequency" : 1,
"gazateer_index" : "university of phoenix/organization",
"relevance" : "0.102",
"totalfrequency" : NumberLong(69),
"type" : "Organization"
},
{
"actual_name" : "diabetes",
"dimension" : "What",
"disambiguous_name" : "diabetes",
"doccount" : NumberLong(1702),
"frequency" : 3,
"gazateer_index" : "diabetes/medicalcondition",
"relevance" : "0.733",
"totalfrequency" : NumberLong(4284),
"type" : "MedicalCondition"
},
{
"actual_name" : "insulin therapy",
"dimension" : "What",
"disambiguous_name" : "insulin therapy",
"doccount" : NumberLong(53),
"frequency" : 1,
"gazateer_index" : "insulin therapy/medicaltreatment",
"relevance" : "0.235",
"totalfrequency" : NumberLong(57),
"type" : "MedicalTreatment"
},
{
"actual_name" : "American Association of Diabetes Educators",
"dimension" : "Who",
"disambiguous_name" : "American Association of Diabetes Educators",
"doccount" : NumberLong(38),
"frequency" : 1,
"gazateer_index" : "american association of diabetes educators/organization",
"relevance" : "0.102",
"totalfrequency" : NumberLong(38),
"type" : "Organization"
},
{
"actual_name" : "member",
"dimension" : "Who",
"disambiguous_name" : "member",
"doccount" : NumberLong(795),
"frequency" : 1,
"gazateer_index" : "member/position",
"relevance" : "0.102",
"totalfrequency" : NumberLong(881),
"type" : "Position"
}
],
"events" : [
{
"entity1" : "nancy klobassa davidson",
"entity1_index" : "nancy klobassa davidson/person",
"verb" : "be",
"verb_category" : "generic relations",
"entity2" : "coordinator of the diabetes unit's intensive insulin therapy
program within the division of endocrinology",
"event_type" : "Summary"
},
{
"entity1" : "peggy moreland",
"entity1_index" : "peggy moreland/person",
"verb" : "work",
"verb_category" : "generic relations",
"event_type" : "Summary"
},
{
"entity1" : "nancy klobassa davidson",
"entity1_index" : "nancy klobassa davidson/person",
"verb" : "current",
"verb_category" : "career",
"entity2" : "coordinator",
"entity2_index" : "coordinator/position",
"event_type" : "Fact"
},
{
"entity1" : "m.s.n.\n peggy",
"entity1_index" : "m.s.n.\n peggy/person",
"verb" : "current",
"verb_category" : "career",
"entity2" : "r.n.",
"entity2_index" : "r.n./position",
"event_type" : "Fact"
},
{
"entity1" : "peggy moreland",
"entity1_index" : "peggy moreland/person",
"verb" : "graduate",
"verb_category" : "generic relations",
"event_type" : "Summary"
},
{
"entity1" : "n.\n peggy moreland",
"entity1_index" : "n.\n peggy moreland/person",
"verb" : "be",
"verb_category" : "generic relations",
"entity2" : "a certified diabetes educator",
"event_type" : "Summary"
},
{
"entity1" : "nancy klobassa davidson",
"entity1_index" : "nancy klobassa davidson/person",
"verb" : "be",
"verb_category" : "generic relations",
"entity2" : "a certified diabetes educator",
"event_type" : "Summary"
},
{
"entity1" : "peggy moreland",
"entity1_index" : "peggy moreland/person",
"verb" : "current",
"verb_category" : "career",
"entity2" : "r.n.",
"entity2_index" : "r.n./position",
"event_type" : "Fact"
},
{
"entity1" : "nancy klobassa davidson",
"entity1_index" : "nancy klobassa davidson/person",
"verb" : "be",
"verb_category" : "generic relations",
"entity2" : "a registered nurse",
"event_type" : "Summary"
},
{
"entity1" : "nancy klobassa davidson",
"entity1_index" : "nancy klobassa davidson/person",
"verb" : "work",
"verb_category" : "generic relations",
"event_type" : "Summary"
},
{
"entity1" : "nancy klobassa davidson",
"entity1_index" : "nancy klobassa davidson/person",
"verb" : "current",
"verb_category" : "career",
"entity2" : "registered nurse",
"entity2_index" : "registered nurse/position",
"event_type" : "Fact"
},
{
"entity1" : "peggy moreland",
"entity1_index" : "peggy moreland/person",
"verb_category" : "person education",
"entity2" : "master of science",
"event_type" : "Summary"
},
{
"entity1" : "peggy moreland",
"entity1_index" : "peggy moreland/person",
"verb" : "current",
"verb_category" : "career",
"entity2" : "member",
"entity2_index" : "member/position",
"event_type" : "Fact"
}
],
"groupids" : [ "4c927585d591d31d7b37097a" ],
"index" : "doc_4c927585d591d31d7b37097a",
"mediaType" : "News",
"modified" : "1310493434159",
"publishedDate" : "Fri Jul 08 01:00:00 EDT 2011",
"source" : "MayoClinic: General Topics",
"sourceKey" : "http.www.mayoclinic.com.rss.blog.xml",
"tags" : [
"topic:healthcare",
"industry:healthcare",
"mayo clinic",
"health"
],
"title" : "Dr. Bernstein diet and beyond",
"url" : "http://www.mayoclinic.com/health/dr-bernstein-diet/MY01817/rss=5"
}
Annex - old format source
Sample RSS Feed Source
{
"description" : "Article on Medical Issues",
"extractType" : "Feed",
"harvestBadSource" : false,
"isApproved" : true,
"isPublic" : true,
"key" : "http.www.mayoclinic.com.rss.blog.xml",
"mediaType" : "News",
"modified" : "Oct 19, 2010 11:31:59 AM",
"tags" : [
"topic:healthcare",
"industry:healthcare",
"mayo clinic",
"health"
],
"title" : "MayoClinic: General Topics",
"url" : "http://www.mayoclinic.com/rss/blog.xml"
"useTextExtractor":"AlchemyAPI",
"useExtractor":"OpenCalais"
}