API-Code/API Data Export v2.R at master · sabrina-rc/API-Code · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
rm(list=ls())

# Export Data from API for Each Endpoint

options(stringsAsFactors = FALSE, scipen = 4, digits =8)
#install.packages("splitstackshape")
library(splitstackshape)
library(jsonlite)
library(dplyr)
library(tidyr)
library(data.table)
library(curl)
setwd()

########################################################
# ENDPOINT Account Awards
acc_awardurl <- "https://api.usaspending.gov/api/v1/accounts/awards/?limit=100"
pages <- list()
acc_awardapi <- fromJSON(acc_awardurl, flatten = TRUE)
acc_awardapi$page_metadata$has_next_page=TRUE
i<-1

while(acc_awardapi$pagemetadata$has_next_page=TRUE) {
  acc_awardapi <- fromJSON(paste0(acc_awardurl, "&page=", i), flatten=TRUE)
  message("Retrieving page ",i)
  pages[[i]] <- acc_awardapi$results
  i<-i+1
}

account_awards <- bind_rows(pages)
write.csv(account_awards, file="Raw API Data Export\\Account_awards_data.csv", row.names = FALSE)

########################################################
# ENDPOINT: AWARD DATA

award_url <- "https://api.usaspending.gov/api/v1/awards/?limit=100"
pages <- list()
award_api <- fromJSON(award_url, flatten=TRUE)
award_api$page_metadata$has_next_page=TRUE
i<-1

while(award_api$page_metadata$has_next_page==TRUE){
  award_api <- fromJSON(paste0(award_url, "&page=", i), flatten=TRUE)
  message("Retrieving page ", i)
  pages[[i]] <- award_api$results
  i<-i+1
}

awards_data <- bind_rows(pages)
str(awards_data)

#DATA FRAME INCLUDES COLUMN WITH A LIST, FLATTEN TO WRITE TO CSV
awards_data <- listCol_l(awards_data, "recipient.business_categories")
write.csv(awards_data, file="awards_data.csv", row.names = FALSE)

########################################################
# ENDPOINT: Federal Accounts
fedacct_url <- "https://api.usaspending.gov/api/v1/federal_accounts/?limit=100"
pages<- list()
fedacct_api <- fromJSON(fedacct_url, flatten=TRUE)
fedacct_api$page_metadata$has_next_page=TRUE
i<-1

while(fedacct_api$page_metadata$has_next_page==TRUE){
  fedacct_api <- fromJSON(paste0(fedacct_url, "&page=", i), flatten=TRUE)
  message("Retrieving page ", i)
  pages[[i]] <- fedacct_api$results
  i<-i+1
}

fedacct_data <- bind_rows(pages)
names(fedacct_data)
write.csv(fedacct_data, file="federalaccount_data.csv", row.names = FALSE)

########################################################
# ENDPOINT: TAS - Treasury Appropriation Symbol (TAS)

tas_url <- "https://api.usaspending.gov/api/v1/tas/?limit=100"
pages <-list()
tas_api <- fromJSON(tas_url, flatten=TRUE)
tas_api$page_metadata$has_next_page=TRUE
i<-1

while(tas_api$page_metadata$has_next_page==TRUE){
  tas_api <- fromJSON(paste0(tas_url, "&page=", i),flatten = TRUE)
  message("Retrieving Page ", i)
  pages[[i]]<- tas_api$results
  i<-i+1
}

tas_data <- bind_rows(pages)
names(tas_data)
write.csv(tas_data, file="tas_data.csv", row.names = FALSE)

########################################################
# ENDPOINT: SubAward Data

sub_url <- "https://api.usaspending.gov/api/v1/subawards/?limit=100"
pages <- list()
sub_api <- fromJSON(sub_url, flatten =TRUE)
sub_api$page_metadata$has_next_page=TRUE
i<-1

while(sub_api$page_metadata$has_next_page==TRUE){
  sub_api <- fromJSON(paste0(sub_url, "&page=", i), flatten = TRUE)
  message("Retrieving Page ", i)
  pages[[i]]<- sub_api$results
  i<- i+1
}

subaward_data <- bind_rows(pages)
names(sub_data)
str(sub_data)
subaward_data2 <- listCol_l(subaward_data, "recipient.business_categories")
write.csv(subaward_data2, file="Subaward_data.csv", row.names = FALSE)
rm(sub_data, subaward_data)

########################################################
# ENDPOINT: Transactions Data
transact_url <- "https://api.usaspending.gov/api/v1/transactions/?limit=100"
pages <- list()
transact_api <- fromJSON(transact_url, flatten = TRUE)
transact_api$page_metadata$has_next_page=TRUE
i<-1

while(transact_api$page_metadata$has_next_page==TRUE){
  transact_api <- fromJSON(paste0(transact_url, "&page=", i), flatten=TRUE)
  message("Retrieving Page", i)
  pages[[i]]<- transact_api$results
  i<- i+1
}

transact_data <- bind_rows(pages)
str(transact_data)
transact_data <- unnest(transact_data, recipient.business_categories)
write.csv(transact_data, file="Transaction_Data.csv", row.names = FALSE)

########################################################
# ENDPOINT: References Data

ref_url <- "https://api.usaspending.gov/api/v1/references/agency/"
pages <- list()
ref_api <- fromJSON(ref_url, flatten = TRUE)
ref_api$page_metadata$has_next_page=TRUE
i<- 1

while(ref_api$page_metadata$has_next_page==TRUE){
  ref_api <- fromJSON(paste0(ref_url, "&page=", i), flatten = TRUE)
  message("Retrieving Page ", i)
  pages[[i]] <- ref_api$results
  i<- i+1
}

ref_data <- bind_rows(pages)
str(ref_data)
write.csv(ref_data, file="Reference_Data.csv", row.names = FALSE)