The New York Times web site provides a rich set of APIs, as described here: http://developer.nytimes.com/docs You’ll need to start by signing up for an API key. Your task is to choose one of the New York Times APIs, construct an interface in R to read in the JSON data, and transform it to an R dataframe.
library(httr)
library(jsonlite)
library(RCurl)## Loading required package: bitopsAPIkey <- "&api-key=23b48cef8cb5434b8efec48a494a9a62"
#url <- "http://api.nytimes.com/svc/semantic/v2/geocodes/query.json?(query parameters)&api-key=your-API-key" (general form of query)
base_url <-getURL("http://api.nytimes.com/svc/semantic/v2/geocodes/query.json?country_code=US&api-key=23b48cef8cb5434b8efec48a494a9a62")
req <- fromJSON(base_url)
req <- data.frame(req)
head(req)## status
## 1 OK
## 2 OK
## 3 OK
## 4 OK
## 5 OK
## 6 OK
## copyright
## 1 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 2 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 3 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 4 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 5 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 6 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## num_results results.concept_id results.concept_name
## 1 20 24012 Charlottesville (Va)
## 2 20 28132 Philadelphia (Pa)
## 3 20 28848 San Juan National Forest (Colo)
## 4 20 27356 Nantucket (Mass)
## 5 20 71052 Yamhill (Ore)
## 6 20 27744 Ohio River
## results.geocode_id results.geoname_id results.name
## 1 2840 4752031 Charlottesville
## 2 436 4560349 Philadelphia
## 3 7240 5437675 San Juan National Forest
## 4 1312 4944903 Nantucket
## 5 8680 5761959 Yamhill
## 6 3916 4401696 Ohio River
## results.latitude results.longitude results.elevation results.population
## 1 38.02931 -78.47668 142 34703
## 2 39.95233 -75.16379 12 1517550
## 3 37.69166 -107.80895 3472 NA
## 4 41.28346 -70.09946 13 14775
## 5 45.34150 -123.18733 60 1024
## 6 36.98672 -89.13062 87 NA
## results.country_code results.country_name results.admin_code1
## 1 US United States VA
## 2 US United States PA
## 3 US United States CO
## 4 US United States MA
## 5 US United States OR
## 6 US United States MO
## results.admin_code2 results.admin_code3 results.admin_code4
## 1 540 NA NA
## 2 101 NA NA
## 3 111 NA NA
## 4 019 NA NA
## 5 071 NA NA
## 6 133 NA NA
## results.admin_name1 results.admin_name2 results.admin_name3
## 1 Virginia City of Charlottesville NA
## 2 Pennsylvania Philadelphia County NA
## 3 Colorado San Juan County NA
## 4 Massachusetts Nantucket County NA
## 5 Oregon Yamhill County NA
## 6 Missouri Mississippi County NA
## results.admin_name4 results.feature_class results.feature_code
## 1 NA P PPL
## 2 NA P PPL
## 3 NA V FRST
## 4 NA P PPL
## 5 NA P PPL
## 6 NA H STM
## results.feature_code_name results.time_zone_id results.dst_offset
## 1 populated place America/New_York -4
## 2 populated place America/New_York -4
## 3 forest(s) America/Shiprock -6
## 4 populated place America/New_York -4
## 5 populated place America/Los_Angeles -7
## 6 stream America/Indiana/Knox -5
## results.gmt_offset results.geocodes_created results.geocodes_updated
## 1 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 2 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 3 -7 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 4 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 5 -8 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 6 -6 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00APIkey <- "23b48cef8cb5434b8efec48a494a9a62"
base_url1 <-getURL("http://api.nytimes.com/svc/semantic/v2/geocodes/query.json?admin_code1=NY&api-key=23b48cef8cb5434b8efec48a494a9a62")
req1 <- fromJSON(base_url1)
req1 <- data.frame(req1)
head(req1)## status
## 1 OK
## 2 OK
## 3 OK
## 4 OK
## 5 OK
## 6 OK
## copyright
## 1 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 2 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 3 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 4 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 5 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 6 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## num_results results.concept_id results.concept_name
## 1 20 25820 Huntington Station (NY)
## 2 20 27508 New Rochelle (NY)
## 3 20 25796 Hudson River
## 4 20 29604 Tarrytown (NY)
## 5 20 29260 Southold (NY)
## 6 20 29956 Valhalla (NY)
## results.geocode_id results.geoname_id results.name
## 1 5320 5121650 Huntington Station
## 2 2652 5128549 New Rochelle
## 3 564 5121521 Hudson River
## 4 3648 5140538 Tarrytown
## 5 4352 5139054 Southold
## 6 3652 5142090 Valhalla
## results.latitude results.longitude results.elevation results.population
## 1 40.85343 -73.41151 66 30484
## 2 40.91149 -73.78235 26 72786
## 3 40.69677 -74.02820 NA NA
## 4 41.07621 -73.85875 37 11460
## 5 41.06482 -72.42620 7 5554
## 6 41.07482 -73.77513 78 5463
## results.country_code results.country_name results.admin_code1
## 1 US United States NY
## 2 US United States NY
## 3 US United States NY
## 4 US United States NY
## 5 US United States NY
## 6 US United States NY
## results.admin_code2 results.admin_code3 results.admin_code4
## 1 103 NA NA
## 2 119 NA NA
## 3 061 NA NA
## 4 119 NA NA
## 5 103 NA NA
## 6 119 NA NA
## results.admin_name1 results.admin_name2 results.admin_name3
## 1 New York Suffolk County NA
## 2 New York Westchester County NA
## 3 New York New York County NA
## 4 New York Westchester County NA
## 5 New York Suffolk County NA
## 6 New York Westchester County NA
## results.admin_name4 results.feature_class results.feature_code
## 1 NA P PPL
## 2 NA P PPL
## 3 NA H STM
## 4 NA P PPL
## 5 NA P PPL
## 6 NA P PPL
## results.feature_code_name results.time_zone_id results.dst_offset
## 1 populated place America/New_York -4
## 2 populated place America/New_York -4
## 3 stream America/New_York -4
## 4 populated place America/New_York -4
## 5 populated place America/New_York -4
## 6 populated place America/New_York -4
## results.gmt_offset results.geocodes_created results.geocodes_updated
## 1 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 2 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 3 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 4 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 5 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 6 -5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00APIkey <- "23b48cef8cb5434b8efec48a494a9a62"
base_url2 <-getURL("http://api.nytimes.com/svc/semantic/v2/geocodes/query.json?feature_class=P&country_code=US&population=50000_&api-key=23b48cef8cb5434b8efec48a494a9a62")
req2 <- fromJSON(base_url2)
req2 <- data.frame(req2)
head(req2)## status
## 1 OK
## 2 OK
## 3 OK
## 4 OK
## 5 OK
## 6 OK
## copyright
## 1 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 2 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 3 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 4 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 5 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## 6 Copyright (c) 2015 The New York Times Company. All Rights Reserved.
## num_results results.concept_id results.concept_name results.geocode_id
## 1 20 24012 Charlottesville (Va) 2840
## 2 20 28132 Philadelphia (Pa) 436
## 3 20 27356 Nantucket (Mass) 1312
## 4 20 71052 Yamhill (Ore) 8680
## 5 20 23236 Bellport (NY) 5036
## 6 20 29164 Sleepy Hollow (NY) 4340
## results.geoname_id results.name results.latitude results.longitude
## 1 4752031 Charlottesville 38.02931 -78.47668
## 2 4560349 Philadelphia 39.95233 -75.16379
## 3 4944903 Nantucket 41.28346 -70.09946
## 4 5761959 Yamhill 45.34150 -123.18733
## 5 5108714 Bellport 40.75704 -72.93927
## 6 5138371 Sleepy Hollow 41.08565 -73.85847
## results.elevation results.population results.country_code
## 1 142 34703 US
## 2 12 1517550 US
## 3 13 14775 US
## 4 60 1024 US
## 5 8 2377 US
## 6 27 9286 US
## results.country_name results.admin_code1 results.admin_code2
## 1 United States VA 540
## 2 United States PA 101
## 3 United States MA 019
## 4 United States OR 071
## 5 United States NY 103
## 6 United States NY 119
## results.admin_code3 results.admin_code4 results.admin_name1
## 1 NA NA Virginia
## 2 NA NA Pennsylvania
## 3 NA NA Massachusetts
## 4 NA NA Oregon
## 5 NA NA New York
## 6 NA NA New York
## results.admin_name2 results.admin_name3 results.admin_name4
## 1 City of Charlottesville NA NA
## 2 Philadelphia County NA NA
## 3 Nantucket County NA NA
## 4 Yamhill County NA NA
## 5 Suffolk County NA NA
## 6 Westchester County NA NA
## results.feature_class results.feature_code results.feature_code_name
## 1 P PPL populated place
## 2 P PPL populated place
## 3 P PPL populated place
## 4 P PPL populated place
## 5 P PPL populated place
## 6 P PPL populated place
## results.time_zone_id results.dst_offset results.gmt_offset
## 1 America/New_York -4 -5
## 2 America/New_York -4 -5
## 3 America/New_York -4 -5
## 4 America/Los_Angeles -7 -8
## 5 America/New_York -4 -5
## 6 America/New_York -4 -5
## results.geocodes_created results.geocodes_updated
## 1 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 2 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 3 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 4 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 5 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00
## 6 2013-02-25 15:10:12-05:00 2013-02-25 15:10:12-05:00