Created
May 23, 2021 17:38
-
-
Save AugustoCL/866b568efbebff538f198986fec22ef7 to your computer and use it in GitHub Desktop.
Criando Base de Dados via Webscraping da ANBIMA [Webscraping] [R]
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
# imports ----------------------------------------------------------------- | |
library(tidyverse) | |
library(httr) | |
library(bizdays) | |
# set inputs and workdir -------------------------------------------------------------- | |
wkdir <- "~/dev_R/schedule_R/" | |
name_db <- "hist_coef_pre_ipca.csv" | |
setwd(wkdir) | |
# load functions ---------------------------------------------------------- | |
get_ettj_param <- function(dt){ | |
stopifnot(is(dt,"Date"), length(dt) == 1) | |
url <- "https://www.anbima.com.br/informacoes/est-termo/CZ-down.asp" | |
r <- httr::POST(url = url, | |
body = list(Idioma = "PT", | |
Dt_Ref = format(dt, "%d/%m/%Y"), | |
saida = "csv"), | |
encode = "form") | |
texto_puro <- rawToChar(content(r,as = "raw")) | |
dados <- | |
read_csv2(texto_puro, n_max = 2) %>% | |
`colnames<-`(c("Grupo","B1","B2","B3","B4","L1","L2")) %>% | |
mutate(data = dt) | |
return(dados) | |
} | |
# get list of dates --------------------------------------------------------------- | |
data(holidaysANBIMA, package = 'bizdays') # load the working days by calendar of anbima | |
cal <- create.calendar(holidaysANBIMA, weekdays=c('saturday', 'sunday'), name='ANBIMA') | |
d2 = Sys.Date() | |
d1 = add.bizdays(d2, -6, cal = cal) | |
data_seq <- bizseq(d1,d2,cal) | |
# get data ---------------------------------------------------------------- | |
deal_error <- | |
purrr::possibly(get_ettj_param, | |
otherwise = NA_real_) # deal with error | |
result <- | |
purrr::map_df(data_seq[1:6], deal_error) %>% | |
select(data, everything()) | |
# save/append data -------------------------------------------------------- | |
if (file.exists(name_db)){ | |
datas_unicas <- unique(as.Date(read.csv2(name_db,header = 1)$data, "%Y-%m-%d")) | |
result <- result %>% filter(!data %in% datas_unicas) | |
write.table(result, | |
file = name_db, | |
append = TRUE, | |
row.names = FALSE, | |
col.names = FALSE, | |
sep = ";", | |
fileEncoding = "UTF-8") | |
} else { | |
write.table(result, | |
file = name_db, | |
append = FALSE, | |
row.names = FALSE, | |
sep = ";", | |
fileEncoding = "UTF-8") | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment