Commit: eca957feb5186614e1c95812655e3fc0d1d1f5b9 - myprojects-hg-reborn (hg)

Commit MetaInfo

• Revisión: eca957feb5186614e1c95812655e3fc0d1d1f5b9 (tree)
• Tiempo: 2024-09-27 02:53:18
• Autor: Lorenzo Isella <lorenzo.isella@gmai...>
• Commiter: Lorenzo Isella

Log Message

Now I input the period and the code automatically retrieves the number of records and the number of pages to download.

Cambiar Resumen

• modified: R-codes/spanish_json.R

Diferencia incremental

diff -r e263e2550477 -r eca957feb518 R-codes/spanish_json.R
--- a/R-codes/spanish_json.R	Thu Sep 26 14:42:02 2024 +0200
+++ b/R-codes/spanish_json.R	Thu Sep 26 19:53:18 2024 +0200
@@ -7,25 +7,60 @@
 
 source("/home/lorenzo/myprojects-hg/R-codes/stat_lib.R")
 
+## NB: I have 628,468 records of SA awards for ES in the year 2022
+
+
+ini <- "01/01/2022" ##initial time dd/mm/yyyy
+fin <- "31/12/2022"
+
 ## url <- "https://www.infosubvenciones.es/bdnstrans/api/ayudasestado/busqueda?page=0&pageSize=10000&order=numeroConvocatoria&direccion=asc&vpd=GE&fechaDesde=01%2F01%2F2019&fechaHasta=31%2F12%2F2022"
 
+ini2 <- transform_date_url(ini)
+fin2 <- transform_date_url(fin)
+
+
 options(timeout=120)
 
 url1 <- "https://www.infosubvenciones.es/bdnstrans/api/ayudasestado/busqueda?page="
 
 
 
-url2 <- "&pageSize=10000&order=numeroConvocatoria&direccion=asc&vpd=GE&fechaDesde=01%2F01%2F2019&fechaHasta=31%2F12%2F2022"
+## url2 <- "&pageSize=10000&order=numeroConvocatoria&direccion=asc&vpd=GE&fechaDesde=01%2F01%2F2022&fechaHasta=31%2F12%2F2022"
+
+url2a <- "&pageSize=10000&order=numeroConvocatoria&direccion=asc&vpd=GE&fechaDesde"
+
+
+url2b <- "&fechaHasta"
+
+
+url_for_pages <- paste(url1, 0, url2a, ini2, url2b, fin2,  sep="")
+
+data_for_pages <- fromJSON(url_for_pages) 
+
+n_records <- data_for_pages$totalElements
+
+print("The total number of records is, ")
+print(n_records)
+
+n_pages <- data_for_pages$totalPages
+
+print("and the total number of pages is, ")
+print(n_pages)
+
+saveRDS(n_pages, "../input/number_pages.RDS")
 
 remove_files_with_pattern("../input/data*RDS")
 
-for (counter in 0:250){
+for (counter in 0:(n_pages-1)){
 
     print("counter is, ")
     print(counter)
 
-    url <- paste(url1, counter, url2, sep="")
+    ## url <- paste(url1, counter, url2, sep="")
 
+    url <- paste(url1, counter, url2a, ini2, url2b, fin2,  sep="")
+
+    
     mydata <- fromJSON(url)