Last active
January 30, 2019 19:37
-
-
Save robsalasco/a3bb807dac617a9fad663184793bf888 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Proof of concept - Extract data from REDATAM web interface (CENSUS 2017) directly to R | |
library(httr) | |
library(rvest) | |
headers <- add_headers( | |
"User-Agent" = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36", | |
"Referer" = "https://redatam-ine.ine.cl/redbin/RpWebStats.exe/AreaList?BASE=CENSO_2017&ITEM=AREAPOB&lang=esp", | |
"Host" = "redatam-ine.ine.cl", | |
"X-Requested-With" = "XMLHttpRequest" | |
) | |
body <- 'MAIN=WebServerMain.inl&BASE=CENSO_2017&LANG=esp&CODIGO=XXUSUARIOXX&ITEM=AREAPOB&MODE=RUN&inputTitle=&VARIABLE=PERSONA.P08&OUTPUT=COMUNA&SELECTION=ALL&INLINESELECTION=&FORMAT=HTML&TOTCOL=on&UNIVERSE=&FILTER=&TEXT_FILTER=&Submit=Ejecutar' | |
data = POST("https://redatam-ine.ine.cl/redbin/RpWebStats.exe/AreaList?", body = body, headers) | |
tmp_doc = read_html(content(data, "text")) %>% html_nodes("iframe") %>% html_attr("src") | |
data_census = GET(tmp_doc, headers) | |
data_final = read_html(content(data_census, "text")) %>% html_nodes(xpath='//*/table') %>% html_table() | |
data_final <- data_final[[1]] | |
data_final <- data_final[10:nrow(data_final), ] | |
data_final <- as.data.frame(data_final,stringsAsFactors=F) | |
data_final <- data_final[!(data_final$X2=="Fuente: Censo 2017" | data_final$X2 == "Procesado con Redatam WebServer" | data_final$X2 == "2017. CELADE/CEPAL, Naciones Unidas"),] | |
data_final <- data_final[!sapply(data_final, function(x) all(x == ""))] | |
colnames(data_final) <- as.character(unlist(data_final[1,])) | |
data_final <- data_final[-1, ] | |
data_final[, 3:ncol(data_final)] <- sapply(3:ncol(data_final), function(x) {gsub("\\s", "", data_final[, x])}) | |
data_final <- data_final[!apply(data_final == "", 1, any), ] | |
data_final |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment