Last active
April 1, 2020 00:10
-
-
Save kossal/9c1402d93120b5cef8ca78ee1eae68de to your computer and use it in GitHub Desktop.
This file contains 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
library(tabulizer) | |
library(purrr) | |
url <- "https://www.gob.mx/cms/uploads/attachment/file/544266/Tabla_casos_positivos_COVID-19_resultado_InDRE_2020.03.30.pdf" | |
# Cada página es una lista | |
infectados_ss <- extract_tables(url, encoding = "UTF-8") | |
# Las primeras 5 filas son los nombres de las columnas | |
# Los uno y filtro de la lista original | |
columnas <- sapply(asinfectados_ss[[1]][1:5]) | |
nomColumnas <- trimws(sapply(as.data.frame(infectados_ss[[1]][1:5,]), paste, collapse = " ")) | |
infectados_ss[[1]] <- infectados_ss[[1]][-(1:5),] | |
# Finalmente asigno los colnames en todos las páginas y lo uno en un data.frame | |
infectados_ss2 <- lapply(infectados_ss, function(x) {colnames(x) <- nomColumnas; x}) | |
infectados_ss3 <- map_dfr(infectados_ss2, as.data.frame) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment